system

Abstract

The system according to the embodiment aims to effectively integrate advertising data into the generation AI and display advertisements relevant to the user's query. [Solution] A system according to an embodiment includes an upload unit, an analysis unit, a conversion unit, an integration unit, a selection unit, and a display unit. The upload unit uploads advertising data. The analysis unit analyzes the advertising data uploaded by the upload unit. The conversion unit converts the advertising data analyzed by the analysis unit into a format suitable for the generation AI. The integration unit integrates the advertising data converted by the conversion unit into the generation AI. The selection unit selects an advertisement related to the user's question based on the advertising data integrated by the integration unit. The display unit displays the advertisement selected by the selection unit.

Description

[Technical Field]

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

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

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

[0004] Conventional technologies do not effectively integrate advertising data into generative AI and display ads relevant to the user's questions, leaving room for improvement.

[0005] The system according to the embodiment aims to effectively integrate advertising data into the generation AI and display advertisements relevant to the user's query. [Means for solving the problem]

[0006] The system according to the embodiment includes an upload unit, an analysis unit, a conversion unit, an integration unit, a selection unit, and a display unit. The upload unit uploads advertisement data. The analysis unit analyzes the advertisement data uploaded by the upload unit. The conversion unit converts the advertisement data analyzed by the analysis unit into a format suitable for the generation AI. The integration unit integrates the advertisement data converted by the conversion unit into the generation AI. The selection unit selects an advertisement related to the user's question based on the advertisement data integrated by the integration unit. The display unit displays the advertisement selected by the selection unit. [Effects of the Invention]

[0007] The system according to the embodiment can effectively integrate advertising data into the generation AI and display advertisements relevant to the user's query. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) An advertising data integration platform according to an embodiment of the present invention is a system that assigns advertising data to each company's generation AI (e.g., FAQ system). In this system, advertisers upload advertising data to the platform, which analyzes the advertising data, converts it into a format suitable for the generation AI, and integrates it into each company's generation AI to display advertisements when users use the FAQ system. For example, advertisers upload advertising data in the form of text ads, image ads, video ads, etc. to the platform. The platform then analyzes the advertising data and converts it into a format that is easy for the generation AI to understand. For example, text ads are converted into a format that is easy for the generation AI to understand, and image ads and video ads are converted into an appropriate size and format. The converted advertising data is integrated into each company's generation AI. When a user uses the FAQ system, relevant advertisements are selected and displayed based on the user's question. For example, if a user asks about a specific product, an advertisement related to that product is displayed. This mechanism allows advertisers to effectively deliver advertisements to target users and allows companies providing generation AI to earn advertising revenue. This allows the advertising data integration platform to provide a mechanism that benefits advertisers, companies providing generation AI, and users. Advertisers can effectively deliver their ads to target users, companies providing generative AI can earn advertising revenue, and users can see ads that match their interests.

[0029] An advertising data integration platform according to an embodiment includes an upload unit, an analysis unit, a conversion unit, an integration unit, a selection unit, and a display unit. The upload unit provides a function for an advertiser to upload advertising data to the platform. The advertising data includes, but is not limited to, text ads, image ads, and video ads. The upload unit can, for example, set restrictions on file format and data size. The analysis unit analyzes the advertising data uploaded by the upload unit. The analysis unit supports formats such as text ads, image ads, and video ads. The analysis unit can set the algorithm to be used and the accuracy of the analysis. The conversion unit converts the advertising data analyzed by the analysis unit into a format suitable for the generation AI. The conversion unit can, for example, convert text ads into a format easily understood by the generation AI. The conversion unit can also convert image ads and video ads into an appropriate size and format. The conversion unit can set the format to be converted and the accuracy of the conversion. The integration unit integrates the advertising data converted by the conversion unit into the generation AI. The integration unit can, for example, set the type of data to be integrated and the integration procedure. The selection unit selects advertisements relevant to the user's question based on the advertising data integrated by the integration unit. The selection unit can, for example, set criteria or algorithms for selecting relevant advertisements based on the user's question. The display unit displays the advertisements selected by the selection unit to the user. The display unit can, for example, set a display device or a display format. This allows the advertising data integration platform according to the embodiment to efficiently perform a series of processes from uploading advertising data to displaying it.

[0030] The analysis unit can handle text ads, image ads, and video ads. For example, the analysis unit uses a natural language processing algorithm to analyze text ads. For example, the analysis unit analyzes the content of the text ads and extracts keywords and phrases. The analysis unit can also use an image analysis algorithm to analyze image ads. For example, the analysis unit analyzes the content of the image ads and recognizes objects and text within the images. The analysis unit can also use a video analysis algorithm to analyze video ads. For example, the analysis unit analyzes the content of the video ads and recognizes scenes and objects within the videos. This allows the analysis unit to analyze various types of advertising data.

[0031] The conversion unit can convert text ads into a format that is easy for the generation AI to understand. For example, the conversion unit analyzes the structure of the text and converts it into an appropriate format in order to convert the text ads into a format that is easy for the generation AI to understand. For example, the conversion unit uses an algorithm to analyze the content of the text ads and convert it into a format that is easy for the generation AI to understand. The conversion unit can also summarize the content of the text ads and convert it into a format that is easy for the generation AI to understand. For example, the conversion unit extracts important information from the text ads and converts it into a concise format. Furthermore, the conversion unit can adjust the language and style of the text in order to convert the content of the text ads into a format that is easy for the generation AI to understand. For example, the conversion unit converts the language of the text ads into a language that is easy for the generation AI to understand and adjusts the style. In this way, the conversion unit enables the generation AI to effectively use the text ads.

[0032] The conversion unit can convert image ads or video ads into an appropriate size and format. For example, the conversion unit adjusts the image resolution and file format to convert the image ads into an appropriate size and format. For example, the conversion unit changes the resolution of the image ads to a size that is easy for the generation AI to process and converts the file format into an appropriate format. The conversion unit can also adjust the resolution and playback time of the video to convert the video ads into an appropriate size and format. For example, the conversion unit changes the resolution of the video ads to a size that is easy for the generation AI to process and adjusts the playback time to an appropriate length. Furthermore, the conversion unit can adjust the encoding method to convert the file format of the image ads or video ads into an appropriate format. For example, the conversion unit converts the file format of the image ads or video ads into a format that is easy for the generation AI to process and adjusts the encoding method. In this way, the conversion unit enables the generation AI to effectively use the image ads or video ads.

[0033] The selection unit can select relevant advertisements based on the content of the user's question. The selection unit, for example, uses a natural language processing algorithm to analyze the content of the user's question and select relevant advertisements. For example, the selection unit analyzes the content of the user's question and extracts keywords and phrases related to the content of the question. The selection unit can also use past user behavior data to select relevant advertisements based on the content of the user's question. For example, the selection unit analyzes the user's past question history and browsing history to select relevant advertisements. Furthermore, the selection unit can use a machine learning algorithm to select relevant advertisements based on the content of the user's question. For example, the selection unit selects advertisements using a machine learning model that inputs the content of the user's question and outputs relevant advertisements. This allows the selection unit to effectively display advertisements related to the content of the user's question.

[0034] The display unit can display the selected advertisement to the user. The display unit, for example, adjusts the display device and display format in order to display the selected advertisement to the user. For example, the display unit displays the selected advertisement through a web browser or a mobile application. The display unit can also adjust the timing and frequency of display in order to display the selected advertisement to the user. For example, the display unit adjusts the timing of displaying the advertisement according to the user's usage status and displays the advertisement at an appropriate frequency. Furthermore, the display unit can adjust the display format in order to display the selected advertisement to the user. For example, the display unit adjusts the display method according to the format of a text advertisement, an image advertisement, a video advertisement, etc., and displays the advertisement in a format optimal for the user. In this way, the display unit can display an appropriate advertisement to the user.

[0035] The upload unit can analyze the advertiser's past upload history and select the optimal upload method. The upload unit, for example, uses a data mining algorithm to analyze the advertiser's past upload history. For example, the upload unit can analyze the advertiser's past upload dates and success rates to suggest the optimal upload method. The upload unit can also prioritize the advertiser's past upload methods (manual, scheduled, etc.). For example, the upload unit selects the optimal method based on the upload methods the advertiser has used in the past. Furthermore, the upload unit can suggest the optimal upload method for a specific day of the week or time period based on the advertiser's past upload history. For example, the upload unit selects the optimal upload method for a specific day of the week or time period based on the advertiser's past upload history. In this way, the upload unit can select the optimal upload method based on the past history.

[0036] When uploading advertising data, the uploading unit may filter the advertising data based on the advertiser's current campaign status and target market. The uploading unit may, for example, use a campaign management system to analyze the advertiser's current campaign status. For example, the uploading unit may analyze the type and progress of the advertiser's current campaign and select and upload optimal advertising data. The uploading unit may also preferentially upload highly relevant advertising data based on the advertiser's target market. For example, the uploading unit may select highly relevant advertising data based on the geographical range and demographic information of the advertiser's target market. Furthermore, the uploading unit may filter and upload specific advertising data in accordance with the advertiser's campaign goals. For example, the uploading unit may select advertising data that is effective for a specific target market based on the advertiser's campaign goals. As a result, the uploading unit may upload optimal advertising data based on the current campaign status and target market.

[0037] When uploading advertising data, the uploading unit may prioritize uploading highly relevant data in consideration of the advertiser's geographical location information. The uploading unit may, for example, use GPS data or an IP address to acquire the advertiser's geographical location information. For example, the uploading unit may prioritize uploading advertising data related to a region based on the advertiser's geographical location information. The uploading unit may also select and upload advertising data that is effective in a specific region based on the advertiser's location information. For example, the uploading unit may select data for maximizing advertising effectiveness in a specific region based on the advertiser's location information. Furthermore, the uploading unit may filter and upload optimal advertising data for each region in consideration of the advertiser's geographical location information. For example, the uploading unit may select and upload optimal advertising data for each region based on the advertiser's geographical location information. This allows the uploading unit to upload optimal advertising data based on the geographical location information.

[0038] The uploading unit may analyze the advertiser's social media activities and upload related data when uploading advertising data. For example, the uploading unit may use a social media analysis tool to analyze the advertiser's social media activities. For example, the uploading unit may analyze the content of the advertiser's social media posts and engagement rates, and prioritize uploading related advertising data. The uploading unit may also select and upload optimal advertising data based on the advertiser's social media trends. For example, the uploading unit may analyze the advertiser's social media trends and select highly relevant advertising data. Furthermore, the uploading unit may filter and upload advertising data that is effective for a specific target from the advertiser's social media activities. For example, the uploading unit may select and upload advertising data that is optimal for a specific target market based on the advertiser's social media activities. In this way, the uploading unit can upload optimal advertising data based on the social media activities.

[0039] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the advertising data. The analysis unit, for example, uses an importance evaluation algorithm to evaluate the importance of the advertising data. For example, the analysis unit evaluates the influence of the advertising data or the size of the target market and calculates the importance. The analysis unit can also use a level of detail adjustment algorithm to adjust the level of detail of the analysis based on the importance of the advertising data. For example, the analysis unit performs a detailed analysis on advertising data with high importance. The analysis unit can also perform a concise analysis on advertising data with low importance. Furthermore, the analysis unit can determine the priority of the analysis based on the importance of the advertising data. For example, the analysis unit prioritizes analysis of advertising data with high importance and postpones analysis of advertising data with low importance. This allows the analysis unit to perform optimal analysis based on the importance of the advertising data.

[0040] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the advertising data. The analysis unit, for example, uses a category classification algorithm to classify the category of the advertising data. For example, the analysis unit classifies the advertising data into categories such as text ads, image ads, and video ads. The analysis unit can also use an algorithm selection algorithm to apply different analysis algorithms depending on the category of the advertising data. For example, the analysis unit applies a natural language processing algorithm to text ads. The analysis unit can also apply an image analysis algorithm to image ads. The analysis unit can also apply a video analysis algorithm to video ads. This allows the analysis unit to perform optimal analysis depending on the category of the advertising data.

[0041] During analysis, the analysis unit can determine the priority of analysis based on the submission time of the advertising data. The analysis unit, for example, uses a submission time evaluation algorithm to evaluate the submission time of the advertising data. For example, the analysis unit evaluates the submission date and time or the submission frequency of the advertising data and calculates the submission time. The analysis unit can also use a priority determination algorithm to determine the priority of analysis based on the submission time of the advertising data. For example, the analysis unit prioritizes analysis of the latest advertising data. The analysis unit can also postpone analysis of advertising data that was submitted earlier. Furthermore, the analysis unit can adjust the analysis schedule based on the submission time. For example, the analysis unit optimizes the analysis schedule based on the submission time. This allows the analysis unit to perform analysis in an optimal order based on the submission time.

[0042] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the advertising data. The analysis unit, for example, uses a relevance evaluation algorithm to evaluate the relevance of the advertising data. For example, the analysis unit evaluates the user's interests and past behavior of the advertising data and calculates the relevance. The analysis unit can also use an order adjustment algorithm to adjust the order of analysis based on the relevance of the advertising data. For example, the analysis unit prioritizes analysis of highly relevant advertising data. The analysis unit can also postpone analysis of less relevant advertising data. Furthermore, the analysis unit can determine the order of analysis based on the relevance of the advertising data. For example, the analysis unit optimizes the order of analysis based on the relevance of the advertising data. This allows the analysis unit to perform analysis in an optimal order based on relevance.

[0043] The conversion unit can adjust the level of detail of conversion based on the importance of the advertising data during conversion. The conversion unit, for example, uses an importance evaluation algorithm to evaluate the importance of the advertising data. For example, the conversion unit evaluates the influence of the advertising data or the size of the target market and calculates the importance. The conversion unit can also use a level of detail adjustment algorithm to adjust the level of detail of conversion based on the importance of the advertising data. For example, the conversion unit performs detailed conversion on advertising data with high importance. The conversion unit can also perform simple conversion on advertising data with low importance. Furthermore, the conversion unit can determine the priority of conversion based on the importance of the advertising data. For example, the conversion unit prioritizes conversion of advertising data with high importance and postpones conversion of advertising data with low importance. This allows the conversion unit to perform optimal conversion based on the importance of the advertising data.

[0044] The conversion unit can apply different conversion algorithms depending on the category of the advertisement data during conversion. For example, the conversion unit uses a category classification algorithm to classify the category of the advertisement data. For example, the conversion unit classifies the advertisement data into categories such as text advertisements, image advertisements, and video advertisements. The conversion unit can also use an algorithm selection algorithm to apply different conversion algorithms depending on the category of the advertisement data. For example, the conversion unit can apply a natural language processing algorithm to text advertisements. The conversion unit can also apply an image analysis algorithm to image advertisements. The conversion unit can also apply a video analysis algorithm to video advertisements. This allows the conversion unit to perform optimal conversion depending on the category of the advertisement data.

[0045] During conversion, the conversion unit can adjust the order of conversion based on the submission time of the advertising data. The conversion unit, for example, uses a submission time evaluation algorithm to evaluate the submission time of the advertising data. For example, the conversion unit evaluates the submission date and time or the submission frequency of the advertising data and calculates the submission time. The conversion unit can also use an order adjustment algorithm to adjust the order of conversion based on the submission time of the advertising data. For example, the conversion unit prioritizes converting the most recent advertising data. The conversion unit can also postpone converting advertising data that was submitted earlier. Furthermore, the conversion unit can adjust the conversion schedule based on the submission time. For example, the conversion unit optimizes the conversion schedule based on the submission time. This allows the conversion unit to perform conversion in an optimal order based on the submission time.

[0046] The conversion unit can adjust the order of conversion based on the relevance of the advertising data during conversion. The conversion unit, for example, uses a relevance assessment algorithm to evaluate the relevance of the advertising data. For example, the conversion unit evaluates the user's interests and past behavior of the advertising data and calculates the relevance. The conversion unit can also use an order adjustment algorithm to adjust the order of conversion based on the relevance of the advertising data. For example, the conversion unit prioritizes converting highly relevant advertising data. The conversion unit can also postpone converting less relevant advertising data. Furthermore, the conversion unit can determine the order of conversion based on the relevance of the advertising data. For example, the conversion unit optimizes the order of conversion based on the relevance of the advertising data. This allows the conversion unit to perform conversion in an optimal order based on relevance.

[0047] The integration unit may adjust the level of integration detail based on the importance of the advertising data during integration. The integration unit may, for example, use an importance evaluation algorithm to evaluate the importance of the advertising data. For example, the integration unit may evaluate the influence of the advertising data or the size of the target market and calculate the importance. The integration unit may also use a level of integration adjustment algorithm to adjust the level of integration detail based on the importance of the advertising data. For example, the integration unit may perform detailed integration on advertising data with high importance. The integration unit may also perform simple integration on advertising data with low importance. Furthermore, the integration unit may determine the priority of integration according to the importance of the advertising data. For example, the integration unit may prioritize integration of advertising data with high importance and postpone integration of advertising data with low importance. This allows the integration unit to perform optimal integration according to the importance of the advertising data.

[0048] The integration unit may apply different integration algorithms depending on the category of the advertising data during integration. For example, the integration unit may use a category classification algorithm to classify the category of the advertising data. For example, the integration unit may classify the advertising data into categories such as text ads, image ads, and video ads. The integration unit may also use an algorithm selection algorithm to apply different integration algorithms depending on the category of the advertising data. For example, the integration unit may apply a natural language processing algorithm to text ads. The integration unit may also apply an image analysis algorithm to image ads. The integration unit may also apply a video analysis algorithm to video ads. This allows the integration unit to perform optimal integration depending on the category of the advertising data.

[0049] During integration, the integration unit can adjust the order of integration based on the submission time of the advertising data. For example, the integration unit uses a submission time evaluation algorithm to evaluate the submission time of the advertising data. For example, the integration unit evaluates the submission date and time or the submission frequency of the advertising data and calculates the submission time. The integration unit can also use an order adjustment algorithm to adjust the order of integration based on the submission time of the advertising data. For example, the integration unit prioritizes integration of the latest advertising data. The integration unit can also postpone integration of advertising data submitted earlier. Furthermore, the integration unit can adjust the integration schedule based on the submission time. For example, the integration unit optimizes the integration schedule based on the submission time. This allows the integration unit to perform integration in an optimal order based on the submission time.

[0050] The integration unit can adjust the order of integration based on the relevance of the advertising data during integration. The integration unit, for example, uses a relevance evaluation algorithm to evaluate the relevance of the advertising data. For example, the integration unit evaluates the user's interests and past behavior of the advertising data and calculates the relevance. The integration unit can also use an order adjustment algorithm to adjust the order of integration based on the relevance of the advertising data. For example, the integration unit prioritizes integration of highly relevant advertising data. The integration unit can also postpone integration of less relevant advertising data. Furthermore, the integration unit can determine the order of integration based on the relevance of the advertising data. For example, the integration unit optimizes the order of integration based on the relevance of the advertising data. This allows the integration unit to perform integration in an optimal order based on relevance.

[0051] At the time of selection, the selection unit can analyze the user's past question history to select the optimal advertisement. The selection unit, for example, uses a data mining algorithm to analyze the user's past question history. For example, the selection unit analyzes the content and frequency of the user's past questions to select a relevant advertisement. The selection unit can also select advertisements related to areas of interest from the user's past question history. For example, the selection unit selects advertisements related to areas of interest based on the user's past question history. Furthermore, the selection unit can analyze the user's question history to select the most effective advertisement. For example, the selection unit selects the most effective advertisement based on the user's question history. This allows the selection unit to select the optimal advertisement based on the past question history.

[0052] The selection unit may filter advertisements based on the user's current areas of interest at the time of selection. The selection unit may, for example, use an area of ​​interest evaluation algorithm to evaluate the user's current areas of interest. For example, the selection unit may analyze the user's recent search history or browsing history to evaluate the current areas of interest. The selection unit may also use a filtering algorithm to filter advertisements based on the user's current areas of interest. For example, the selection unit may preferentially select relevant advertisements based on the user's current areas of interest. The selection unit may also filter and display advertisements related to the user's areas of interest. The selection unit may also analyze the user's current areas of interest and select an optimal advertisement. For example, the selection unit may select an optimal advertisement based on the user's current areas of interest. In this way, the selection unit can select an optimal advertisement based on the current areas of interest.

[0053] During selection, the selection unit can prioritize highly relevant advertisements by taking into consideration the user's geographical location information. The selection unit, for example, uses GPS data or an IP address to acquire the user's geographical location information. For example, the selection unit prioritizes region-related advertisements based on the user's geographical location information. The selection unit can also select advertisements that are effective in a specific region based on the user's location information. For example, the selection unit selects advertisements that maximize advertising effectiveness in a specific region based on the user's location information. Furthermore, the selection unit can filter and select advertisements that are optimal for each region by taking into consideration the user's geographical location information. For example, the selection unit selects and displays advertisements that are optimal for each region based on the user's geographical location information. This allows the selection unit to select optimal advertisements based on the geographical location information.

[0054] At the time of selection, the selection unit may analyze the user's social media activity and select relevant advertisements. The selection unit may, for example, use a social media analysis tool to analyze the user's social media activity. For example, the selection unit may analyze the content of the user's social media posts and engagement rates to preferentially select relevant advertisements. The selection unit may also select optimal advertisements based on the user's social media trends. For example, the selection unit may analyze the user's social media trends and select highly relevant advertisements. Furthermore, the selection unit may filter and select advertisements that are effective for a specific target based on the user's social media activity. For example, the selection unit may select and display advertisements that are optimal for a specific target market based on the user's social media activity. This allows the selection unit to select optimal advertisements based on the social media activity.

[0055] The display unit can adjust the level of detail of the display based on the importance of the advertisement when displaying the advertisement. The display unit, for example, uses an importance evaluation algorithm to evaluate the importance of the advertisement. For example, the display unit evaluates the influence of the advertisement and the size of the target market and calculates the importance. The display unit can also use a level of detail adjustment algorithm to adjust the level of detail of the display based on the importance of the advertisement. For example, the display unit displays an advertisement with high importance in detail. The display unit can also display an advertisement with low importance in a concise manner. Furthermore, the display unit can determine the priority of display according to the importance of the advertisement. For example, the display unit displays an advertisement with high importance first and an advertisement with low importance later. This allows the display unit to optimally display the advertisement according to the importance of the advertisement.

[0056] The display unit can apply different display algorithms depending on the category of the advertisement when displaying the advertisement. The display unit, for example, uses a category classification algorithm to classify the category of the advertisement. For example, the display unit classifies advertisements into categories such as text advertisements, image advertisements, and video advertisements. The display unit can also use an algorithm selection algorithm to apply different display algorithms depending on the category of the advertisement. For example, the display unit can apply a natural language processing algorithm to text advertisements. The display unit can also apply an image analysis algorithm to image advertisements. Furthermore, the display unit can apply a video analysis algorithm to video advertisements. This allows the display unit to perform optimal display depending on the category of the advertisement.

[0057] When displaying an advertisement, the display unit can determine a display priority based on the submission time of the advertisement. The display unit, for example, uses a submission time evaluation algorithm to evaluate the submission time of the advertisement. For example, the display unit evaluates the submission date and time or the submission frequency of the advertisement and calculates the submission time. The display unit can also use a priority determination algorithm to determine the display priority based on the submission time of the advertisement. For example, the display unit prioritizes displaying the most recent advertisement. The display unit can also postpone advertisements that were submitted earlier. Furthermore, the display unit can adjust the display schedule based on the submission time. For example, the display unit optimizes the display schedule based on the submission time. This allows the display unit to display advertisements in an optimal order based on the submission time.

[0058] The display unit can adjust the display order based on the relevance of the advertisements when displaying them. The display unit, for example, uses a relevance evaluation algorithm to evaluate the relevance of the advertisements. For example, the display unit evaluates the user's interest and past behavior of the advertisements and calculates the relevance. The display unit can also use an order adjustment algorithm to adjust the display order based on the relevance of the advertisements. For example, the display unit prioritizes displaying highly relevant advertisements. The display unit can also postpone displaying less relevant advertisements. Furthermore, the display unit can determine the display order based on the relevance of the advertisements. For example, the display unit optimizes the display order based on the relevance of the advertisements. This allows the display unit to display advertisements in an optimal order based on relevance.

[0059] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0060] The advertising data integration platform may further include a suggestion unit that analyzes the advertiser's past advertising performance data and suggests the optimal advertising format. The suggestion unit may, for example, analyze the click-through rate and conversion rate of past advertising campaigns to identify the most effective advertising format. The suggestion unit may also suggest the optimal advertising format based on the characteristics of the advertiser's target market. For example, if it is determined that video advertising is effective for young people, the suggestion unit may recommend video advertising. The suggestion unit may also suggest the optimal advertising format based on the advertiser's budget and campaign goals. This allows the advertiser to obtain useful information for running an effective advertising campaign.

[0061] When analyzing advertising data, the analysis unit can adjust the analysis results taking into account the advertiser's brand image. For example, the analysis unit evaluates whether the content of the advertising data matches the brand image based on the advertiser's brand guidelines. The analysis unit can also detect elements that do not match the brand image and suggest modifications. Furthermore, the analysis unit can adjust design elements of the advertising data, such as colors and fonts, based on the brand image. This allows the advertiser to run effective advertisements while maintaining their brand image.

[0062] When converting advertising data, the conversion unit can adjust the conversion method taking into account the advertiser's past advertising performance data. For example, the conversion unit can analyze data from past advertising campaigns to identify the most effective conversion method. The conversion unit can also select the optimal conversion method based on the characteristics of the advertiser's target market. For example, if it is determined that short video ads are effective in a particular market, the conversion unit shortens the video ads. Furthermore, the conversion unit can adjust the conversion method according to the advertiser's budget and campaign goals. This allows the advertiser to use the optimal conversion method to run an effective advertising campaign.

[0063] The selection unit can analyze the user's past behavioral data and select the most appropriate advertisement. For example, the selection unit can analyze the user's past search history and browsing history and select relevant advertisements. The selection unit can also select advertisements related to products of interest to the user based on the user's past purchase history. Furthermore, the selection unit can analyze the user's past behavioral data and select the most effective advertisement. This allows the selection unit to select the most appropriate advertisement based on the past behavioral data.

[0064] The processing flow of the first embodiment will be briefly explained below.

[0065] Step 1: The upload section allows advertisers to upload their advertising data to the platform. The advertising data can include text ads, image ads, video ads, etc. The upload section can set restrictions on file format and data size. Step 2: The analysis unit analyzes the advertising data uploaded by the upload unit. The analysis unit supports formats such as text ads, image ads, and video ads, and allows you to set the algorithm to be used and the accuracy of the analysis. Step 3: The conversion unit converts the advertising data analyzed by the analysis unit into a format suitable for the generation AI. The conversion unit converts text ads into a format that is easy for the generation AI to understand, and can convert image ads and video ads into the appropriate size and format. The format to be converted and the conversion accuracy can be set. Step 4: The integration unit integrates the advertising data converted by the conversion unit into the generation AI. The integration unit can set the type of data to be integrated and the integration procedure. Step 5: The selection unit selects advertisements related to the user's query based on the advertisement data integrated by the integration unit. The selection unit may set criteria or algorithms for selecting relevant advertisements based on the user's query. Step 6: The display unit displays the advertisement selected by the selection unit to the user. The display unit can set the device and display format for displaying the advertisement.

[0066] (Example 2) An advertising data integration platform according to an embodiment of the present invention is a system that assigns advertising data to each company's generation AI (e.g., FAQ system). In this system, advertisers upload advertising data to the platform, which analyzes the advertising data, converts it into a format suitable for the generation AI, and integrates it into each company's generation AI to display advertisements when users use the FAQ system. For example, advertisers upload advertising data in the form of text ads, image ads, video ads, etc. to the platform. The platform then analyzes the advertising data and converts it into a format that is easy for the generation AI to understand. For example, text ads are converted into a format that is easy for the generation AI to understand, and image ads and video ads are converted into an appropriate size and format. The converted advertising data is integrated into each company's generation AI. When a user uses the FAQ system, relevant advertisements are selected and displayed based on the user's question. For example, if a user asks about a specific product, an advertisement related to that product is displayed. This mechanism allows advertisers to effectively deliver advertisements to target users and allows companies providing generation AI to earn advertising revenue. This allows the advertising data integration platform to provide a mechanism that benefits advertisers, companies providing generation AI, and users. Advertisers can effectively deliver their ads to target users, companies providing generative AI can earn advertising revenue, and users can see ads that match their interests.

[0067] An advertising data integration platform according to an embodiment includes an upload unit, an analysis unit, a conversion unit, an integration unit, a selection unit, and a display unit. The upload unit provides a function for an advertiser to upload advertising data to the platform. The advertising data includes, but is not limited to, text ads, image ads, and video ads. The upload unit can, for example, set restrictions on file format and data size. The analysis unit analyzes the advertising data uploaded by the upload unit. The analysis unit supports formats such as text ads, image ads, and video ads. The analysis unit can set the algorithm to be used and the accuracy of the analysis. The conversion unit converts the advertising data analyzed by the analysis unit into a format suitable for the generation AI. The conversion unit can, for example, convert text ads into a format easily understood by the generation AI. The conversion unit can also convert image ads and video ads into an appropriate size and format. The conversion unit can set the format to be converted and the accuracy of the conversion. The integration unit integrates the advertising data converted by the conversion unit into the generation AI. The integration unit can, for example, set the type of data to be integrated and the integration procedure. The selection unit selects advertisements relevant to the user's question based on the advertising data integrated by the integration unit. The selection unit can, for example, set criteria or algorithms for selecting relevant advertisements based on the user's question. The display unit displays the advertisements selected by the selection unit to the user. The display unit can, for example, set a display device or a display format. This allows the advertising data integration platform according to the embodiment to efficiently perform a series of processes from uploading advertising data to displaying it.

[0068] The analysis unit can handle text ads, image ads, and video ads. For example, the analysis unit uses a natural language processing algorithm to analyze text ads. For example, the analysis unit analyzes the content of the text ads and extracts keywords and phrases. The analysis unit can also use an image analysis algorithm to analyze image ads. For example, the analysis unit analyzes the content of the image ads and recognizes objects and text within the images. The analysis unit can also use a video analysis algorithm to analyze video ads. For example, the analysis unit analyzes the content of the video ads and recognizes scenes and objects within the videos. This allows the analysis unit to analyze various types of advertising data.

[0069] The conversion unit can convert text ads into a format that is easy for the generation AI to understand. For example, the conversion unit analyzes the structure of the text and converts it into an appropriate format in order to convert the text ads into a format that is easy for the generation AI to understand. For example, the conversion unit uses an algorithm to analyze the content of the text ads and convert it into a format that is easy for the generation AI to understand. The conversion unit can also summarize the content of the text ads and convert it into a format that is easy for the generation AI to understand. For example, the conversion unit extracts important information from the text ads and converts it into a concise format. Furthermore, the conversion unit can adjust the language and style of the text in order to convert the content of the text ads into a format that is easy for the generation AI to understand. For example, the conversion unit converts the language of the text ads into a language that is easy for the generation AI to understand and adjusts the style. In this way, the conversion unit enables the generation AI to effectively use the text ads.

[0070] The conversion unit can convert image ads or video ads into an appropriate size and format. For example, the conversion unit adjusts the image resolution and file format to convert the image ads into an appropriate size and format. For example, the conversion unit changes the resolution of the image ads to a size that is easy for the generation AI to process and converts the file format into an appropriate format. The conversion unit can also adjust the resolution and playback time of the video to convert the video ads into an appropriate size and format. For example, the conversion unit changes the resolution of the video ads to a size that is easy for the generation AI to process and adjusts the playback time to an appropriate length. Furthermore, the conversion unit can adjust the encoding method to convert the file format of the image ads or video ads into an appropriate format. For example, the conversion unit converts the file format of the image ads or video ads into a format that is easy for the generation AI to process and adjusts the encoding method. In this way, the conversion unit enables the generation AI to effectively use the image ads or video ads.

[0071] The selection unit can select relevant advertisements based on the content of the user's question. The selection unit, for example, uses a natural language processing algorithm to analyze the content of the user's question and select relevant advertisements. For example, the selection unit analyzes the content of the user's question and extracts keywords and phrases related to the content of the question. The selection unit can also use past user behavior data to select relevant advertisements based on the content of the user's question. For example, the selection unit analyzes the user's past question history and browsing history to select relevant advertisements. Furthermore, the selection unit can use a machine learning algorithm to select relevant advertisements based on the content of the user's question. For example, the selection unit selects advertisements using a machine learning model that inputs the content of the user's question and outputs relevant advertisements. This allows the selection unit to effectively display advertisements related to the content of the user's question.

[0072] The display unit can display the selected advertisement to the user. The display unit, for example, adjusts the display device and display format in order to display the selected advertisement to the user. For example, the display unit displays the selected advertisement through a web browser or a mobile application. The display unit can also adjust the timing and frequency of display in order to display the selected advertisement to the user. For example, the display unit adjusts the timing of displaying the advertisement according to the user's usage status and displays the advertisement at an appropriate frequency. Furthermore, the display unit can adjust the display format in order to display the selected advertisement to the user. For example, the display unit adjusts the display method according to the format of a text advertisement, an image advertisement, a video advertisement, etc., and displays the advertisement in a format optimal for the user. In this way, the display unit can display an appropriate advertisement to the user.

[0073] The upload unit can estimate the advertiser's emotions and adjust the timing of uploading advertising data based on the estimated emotions of the advertiser. The upload unit, for example, uses an emotion analysis algorithm to estimate the advertiser's emotions. For example, the upload unit can analyze the advertiser's facial expressions and voice data to calculate an emotion score. The upload unit can also use a scheduling algorithm to adjust the timing of uploading advertising data based on the advertiser's emotions. For example, if the advertiser is feeling stressed, the upload unit can automatically select the optimal timing to upload the advertising data. Alternatively, if the advertiser is feeling relaxed, the upload unit can allow the advertiser to manually select the upload timing. Furthermore, if the advertiser is in a hurry, the upload unit can perform an immediate upload and quickly process the advertising data. As a result, the upload unit can upload the advertising data at the optimal timing according to the advertiser's emotions.

[0074] The upload unit can analyze the advertiser's past upload history and select the optimal upload method. The upload unit, for example, uses a data mining algorithm to analyze the advertiser's past upload history. For example, the upload unit can analyze the advertiser's past upload dates and success rates to suggest the optimal upload method. The upload unit can also prioritize the advertiser's past upload methods (manual, scheduled, etc.). For example, the upload unit selects the optimal method based on the upload methods the advertiser has used in the past. Furthermore, the upload unit can suggest the optimal upload method for a specific day of the week or time period based on the advertiser's past upload history. For example, the upload unit selects the optimal upload method for a specific day of the week or time period based on the advertiser's past upload history. In this way, the upload unit can select the optimal upload method based on the past history.

[0075] When uploading advertising data, the uploading unit may filter the advertising data based on the advertiser's current campaign status and target market. The uploading unit may, for example, use a campaign management system to analyze the advertiser's current campaign status. For example, the uploading unit may analyze the type and progress of the advertiser's current campaign and select and upload optimal advertising data. The uploading unit may also preferentially upload highly relevant advertising data based on the advertiser's target market. For example, the uploading unit may select highly relevant advertising data based on the geographical range and demographic information of the advertiser's target market. Furthermore, the uploading unit may filter and upload specific advertising data in accordance with the advertiser's campaign goals. For example, the uploading unit may select advertising data that is effective for a specific target market based on the advertiser's campaign goals. As a result, the uploading unit may upload optimal advertising data based on the current campaign status and target market.

[0076] The upload unit may estimate the advertiser's emotions and determine the priority of the advertising data to be uploaded based on the estimated emotions of the advertiser. The upload unit may, for example, use an emotion analysis algorithm to estimate the advertiser's emotions. For example, the upload unit may analyze the advertiser's facial expressions and voice data to calculate an emotion score. The upload unit may also use a priority determination algorithm to determine the priority of the advertising data to be uploaded based on the advertiser's emotions. For example, if the advertiser is feeling stressed, the upload unit may prioritize uploading advertising data of high importance. Furthermore, if the advertiser is relaxed, the upload unit may prioritize uploading advertising data selected by the advertiser. Furthermore, if the advertiser is in a hurry, the upload unit may prioritize processing advertising data that requires immediate upload. As a result, the upload unit may prioritize uploading optimal advertising data according to the advertiser's emotions.

[0077] When uploading advertising data, the uploading unit may prioritize uploading highly relevant data in consideration of the advertiser's geographical location information. The uploading unit may, for example, use GPS data or an IP address to acquire the advertiser's geographical location information. For example, the uploading unit may prioritize uploading advertising data related to a region based on the advertiser's geographical location information. The uploading unit may also select and upload advertising data that is effective in a specific region based on the advertiser's location information. For example, the uploading unit may select data for maximizing advertising effectiveness in a specific region based on the advertiser's location information. Furthermore, the uploading unit may filter and upload optimal advertising data for each region in consideration of the advertiser's geographical location information. For example, the uploading unit may select and upload optimal advertising data for each region based on the advertiser's geographical location information. This allows the uploading unit to upload optimal advertising data based on the geographical location information.

[0078] The uploading unit may analyze the advertiser's social media activities and upload related data when uploading advertising data. For example, the uploading unit may use a social media analysis tool to analyze the advertiser's social media activities. For example, the uploading unit may analyze the content of the advertiser's social media posts and engagement rates, and prioritize uploading related advertising data. The uploading unit may also select and upload optimal advertising data based on the advertiser's social media trends. For example, the uploading unit may analyze the advertiser's social media trends and select highly relevant advertising data. Furthermore, the uploading unit may filter and upload advertising data that is effective for a specific target from the advertiser's social media activities. For example, the uploading unit may select and upload advertising data that is optimal for a specific target market based on the advertiser's social media activities. In this way, the uploading unit can upload optimal advertising data based on the social media activities.

[0079] The analysis unit can estimate the advertiser's emotions and adjust the way the analysis is presented based on the estimated emotions of the advertiser. The analysis unit, for example, uses an emotion analysis algorithm to estimate the advertiser's emotions. For example, the analysis unit analyzes the advertiser's facial expressions and voice data to calculate an emotion score. The analysis unit can also use an expression adjustment algorithm to adjust the way the analysis is presented based on the advertiser's emotions. For example, the analysis unit can provide detailed analysis results when the advertiser is relaxed. The analysis unit can also provide concise and to-the-point analysis results when the advertiser is stressed. Furthermore, the analysis unit can quickly provide analysis results when the advertiser is in a hurry. In this way, the analysis unit can provide optimal analysis results according to the advertiser's emotions.

[0080] During analysis, the analysis unit can adjust the level of detail of the analysis based on the importance of the advertising data. The analysis unit, for example, uses an importance evaluation algorithm to evaluate the importance of the advertising data. For example, the analysis unit evaluates the influence of the advertising data or the size of the target market and calculates the importance. The analysis unit can also use a level of detail adjustment algorithm to adjust the level of detail of the analysis based on the importance of the advertising data. For example, the analysis unit performs a detailed analysis on advertising data with high importance. The analysis unit can also perform a concise analysis on advertising data with low importance. Furthermore, the analysis unit can determine the priority of the analysis based on the importance of the advertising data. For example, the analysis unit prioritizes analysis of advertising data with high importance and postpones analysis of advertising data with low importance. This allows the analysis unit to perform optimal analysis based on the importance of the advertising data.

[0081] During analysis, the analysis unit can apply different analysis algorithms depending on the category of the advertising data. The analysis unit, for example, uses a category classification algorithm to classify the category of the advertising data. For example, the analysis unit classifies the advertising data into categories such as text ads, image ads, and video ads. The analysis unit can also use an algorithm selection algorithm to apply different analysis algorithms depending on the category of the advertising data. For example, the analysis unit applies a natural language processing algorithm to text ads. The analysis unit can also apply an image analysis algorithm to image ads. The analysis unit can also apply a video analysis algorithm to video ads. This allows the analysis unit to perform optimal analysis depending on the category of the advertising data.

[0082] The analysis unit can estimate the advertiser's emotions and adjust the length of the analysis based on the estimated advertiser's emotions. The analysis unit, for example, uses an emotion analysis algorithm to estimate the advertiser's emotions. For example, the analysis unit analyzes the advertiser's facial expressions and voice data to calculate an emotion score. The analysis unit can also use a length adjustment algorithm to adjust the length of the analysis based on the advertiser's emotions. For example, the analysis unit can perform a detailed analysis if the advertiser is relaxed. The analysis unit can also perform a concise analysis if the advertiser is stressed. Furthermore, the analysis unit can perform a quick analysis if the advertiser is in a hurry. As a result, the analysis unit can provide an analysis of an optimal length according to the advertiser's emotions.

[0083] During analysis, the analysis unit can determine the priority of analysis based on the submission time of the advertising data. The analysis unit, for example, uses a submission time evaluation algorithm to evaluate the submission time of the advertising data. For example, the analysis unit evaluates the submission date and time or the submission frequency of the advertising data and calculates the submission time. The analysis unit can also use a priority determination algorithm to determine the priority of analysis based on the submission time of the advertising data. For example, the analysis unit prioritizes analysis of the latest advertising data. The analysis unit can also postpone analysis of advertising data that was submitted earlier. Furthermore, the analysis unit can adjust the analysis schedule based on the submission time. For example, the analysis unit optimizes the analysis schedule based on the submission time. This allows the analysis unit to perform analysis in an optimal order based on the submission time.

[0084] During analysis, the analysis unit can adjust the order of analysis based on the relevance of the advertising data. The analysis unit, for example, uses a relevance evaluation algorithm to evaluate the relevance of the advertising data. For example, the analysis unit evaluates the user's interests and past behavior of the advertising data and calculates the relevance. The analysis unit can also use an order adjustment algorithm to adjust the order of analysis based on the relevance of the advertising data. For example, the analysis unit prioritizes analysis of highly relevant advertising data. The analysis unit can also postpone analysis of less relevant advertising data. Furthermore, the analysis unit can determine the order of analysis based on the relevance of the advertising data. For example, the analysis unit optimizes the order of analysis based on the relevance of the advertising data. This allows the analysis unit to perform analysis in an optimal order based on relevance.

[0085] The conversion unit can estimate the advertiser's emotions and adjust the conversion method based on the estimated advertiser's emotions. The conversion unit, for example, uses an emotion analysis algorithm to estimate the advertiser's emotions. For example, the conversion unit analyzes the advertiser's facial expressions and voice data to calculate an emotion score. The conversion unit can also use a method adjustment algorithm to adjust the conversion method based on the advertiser's emotions. For example, the conversion unit can perform detailed conversion if the advertiser is relaxed. The conversion unit can also perform concise conversion if the advertiser is stressed. Furthermore, the conversion unit can perform quick conversion if the advertiser is in a hurry. In this way, the conversion unit can convert advertising data in an optimal manner according to the advertiser's emotions.

[0086] The conversion unit can adjust the level of detail of conversion based on the importance of the advertising data during conversion. The conversion unit, for example, uses an importance evaluation algorithm to evaluate the importance of the advertising data. For example, the conversion unit evaluates the influence of the advertising data or the size of the target market and calculates the importance. The conversion unit can also use a level of detail adjustment algorithm to adjust the level of detail of conversion based on the importance of the advertising data. For example, the conversion unit performs detailed conversion on advertising data with high importance. The conversion unit can also perform simple conversion on advertising data with low importance. Furthermore, the conversion unit can determine the priority of conversion based on the importance of the advertising data. For example, the conversion unit prioritizes conversion of advertising data with high importance and postpones conversion of advertising data with low importance. This allows the conversion unit to perform optimal conversion based on the importance of the advertising data.

[0087] The conversion unit can apply different conversion algorithms depending on the category of the advertisement data during conversion. For example, the conversion unit uses a category classification algorithm to classify the category of the advertisement data. For example, the conversion unit classifies the advertisement data into categories such as text advertisements, image advertisements, and video advertisements. The conversion unit can also use an algorithm selection algorithm to apply different conversion algorithms depending on the category of the advertisement data. For example, the conversion unit can apply a natural language processing algorithm to text advertisements. The conversion unit can also apply an image analysis algorithm to image advertisements. The conversion unit can also apply a video analysis algorithm to video advertisements. This allows the conversion unit to perform optimal conversion depending on the category of the advertisement data.

[0088] The conversion unit can estimate the advertiser's emotions and determine conversion priorities based on the estimated advertiser's emotions. The conversion unit, for example, uses an emotion analysis algorithm to estimate the advertiser's emotions. For example, the conversion unit analyzes the advertiser's facial expressions and voice data to calculate an emotion score. The conversion unit can also use a priority determination algorithm to determine conversion priorities based on the advertiser's emotions. For example, the conversion unit can preferentially convert advertising data selected by the advertiser when the advertiser is relaxed. The conversion unit can also preferentially convert advertising data of high importance when the advertiser is stressed. Furthermore, the conversion unit can preferentially process advertising data that requires immediate conversion when the advertiser is in a hurry. In this way, the conversion unit can preferentially convert optimal advertising data according to the advertiser's emotions.

[0089] During conversion, the conversion unit can adjust the order of conversion based on the submission time of the advertising data. The conversion unit, for example, uses a submission time evaluation algorithm to evaluate the submission time of the advertising data. For example, the conversion unit evaluates the submission date and time or the submission frequency of the advertising data and calculates the submission time. The conversion unit can also use an order adjustment algorithm to adjust the order of conversion based on the submission time of the advertising data. For example, the conversion unit prioritizes converting the most recent advertising data. The conversion unit can also postpone converting advertising data that was submitted earlier. Furthermore, the conversion unit can adjust the conversion schedule based on the submission time. For example, the conversion unit optimizes the conversion schedule based on the submission time. This allows the conversion unit to perform conversion in an optimal order based on the submission time.

[0090] The conversion unit can adjust the order of conversion based on the relevance of the advertising data during conversion. The conversion unit, for example, uses a relevance assessment algorithm to evaluate the relevance of the advertising data. For example, the conversion unit evaluates the user's interests and past behavior of the advertising data and calculates the relevance. The conversion unit can also use an order adjustment algorithm to adjust the order of conversion based on the relevance of the advertising data. For example, the conversion unit prioritizes converting highly relevant advertising data. The conversion unit can also postpone converting less relevant advertising data. Furthermore, the conversion unit can determine the order of conversion based on the relevance of the advertising data. For example, the conversion unit optimizes the order of conversion based on the relevance of the advertising data. This allows the conversion unit to perform conversion in an optimal order based on relevance.

[0091] The integration unit may estimate the advertiser's emotion and adjust the integration method based on the estimated advertiser's emotion. The integration unit may, for example, use an emotion analysis algorithm to estimate the advertiser's emotion. For example, the integration unit may analyze the advertiser's facial expression or voice data and calculate an emotion score. The integration unit may also use a method adjustment algorithm to adjust the integration method based on the advertiser's emotion. For example, the integration unit may perform detailed integration if the advertiser is relaxed. The integration unit may also perform simple integration if the advertiser is stressed. Furthermore, the integration unit may also perform quick integration if the advertiser is in a hurry. This allows the integration unit to integrate advertising data in an optimal manner according to the advertiser's emotion.

[0092] The integration unit may adjust the level of integration detail based on the importance of the advertising data during integration. The integration unit may, for example, use an importance evaluation algorithm to evaluate the importance of the advertising data. For example, the integration unit may evaluate the influence of the advertising data or the size of the target market and calculate the importance. The integration unit may also use a level of integration adjustment algorithm to adjust the level of integration detail based on the importance of the advertising data. For example, the integration unit may perform detailed integration on advertising data with high importance. The integration unit may also perform simple integration on advertising data with low importance. Furthermore, the integration unit may determine the priority of integration according to the importance of the advertising data. For example, the integration unit may prioritize integration of advertising data with high importance and postpone integration of advertising data with low importance. This allows the integration unit to perform optimal integration according to the importance of the advertising data.

[0093] The integration unit may apply different integration algorithms depending on the category of the advertising data during integration. For example, the integration unit may use a category classification algorithm to classify the category of the advertising data. For example, the integration unit may classify the advertising data into categories such as text ads, image ads, and video ads. The integration unit may also use an algorithm selection algorithm to apply different integration algorithms depending on the category of the advertising data. For example, the integration unit may apply a natural language processing algorithm to text ads. The integration unit may also apply an image analysis algorithm to image ads. The integration unit may also apply a video analysis algorithm to video ads. This allows the integration unit to perform optimal integration depending on the category of the advertising data.

[0094] The integration unit may estimate the advertiser's emotions and determine integration priorities based on the estimated advertiser's emotions. The integration unit may, for example, use an emotion analysis algorithm to estimate the advertiser's emotions. For example, the integration unit may analyze the advertiser's facial expressions and voice data to calculate an emotion score. The integration unit may also use a priority determination algorithm to determine integration priorities based on the advertiser's emotions. For example, the integration unit may prioritize integration of advertising data selected by the advertiser when the advertiser is relaxed. The integration unit may also prioritize integration of advertising data with high importance when the advertiser is stressed. Furthermore, the integration unit may prioritize processing of advertising data that requires immediate integration when the advertiser is in a hurry. In this way, the integration unit may prioritize integration of optimal advertising data according to the advertiser's emotions.

[0095] During integration, the integration unit can adjust the order of integration based on the submission time of the advertising data. For example, the integration unit uses a submission time evaluation algorithm to evaluate the submission time of the advertising data. For example, the integration unit evaluates the submission date and time or the submission frequency of the advertising data and calculates the submission time. The integration unit can also use an order adjustment algorithm to adjust the order of integration based on the submission time of the advertising data. For example, the integration unit prioritizes integration of the latest advertising data. The integration unit can also postpone integration of advertising data submitted earlier. Furthermore, the integration unit can adjust the integration schedule based on the submission time. For example, the integration unit optimizes the integration schedule based on the submission time. This allows the integration unit to perform integration in an optimal order based on the submission time.

[0096] The integration unit can adjust the order of integration based on the relevance of the advertising data during integration. The integration unit, for example, uses a relevance evaluation algorithm to evaluate the relevance of the advertising data. For example, the integration unit evaluates the user's interests and past behavior of the advertising data and calculates the relevance. The integration unit can also use an order adjustment algorithm to adjust the order of integration based on the relevance of the advertising data. For example, the integration unit prioritizes integration of highly relevant advertising data. The integration unit can also postpone integration of less relevant advertising data. Furthermore, the integration unit can determine the order of integration based on the relevance of the advertising data. For example, the integration unit optimizes the order of integration based on the relevance of the advertising data. This allows the integration unit to perform integration in an optimal order based on relevance.

[0097] The selection unit may estimate a user's emotion and adjust an advertisement selection method based on the estimated user's emotion. The selection unit may, for example, use an emotion analysis algorithm to estimate the user's emotion. For example, the selection unit may analyze the user's facial expression or voice data to calculate an emotion score. The selection unit may also use a method adjustment algorithm to adjust an advertisement selection method based on the user's emotion. For example, the selection unit may provide a detailed advertisement when the user is relaxed. The selection unit may also provide a concise and to-the-point advertisement when the user is stressed. Furthermore, the selection unit may provide a quickly displayed advertisement when the user is in a hurry. In this way, the selection unit may select an optimal advertisement according to the user's emotion.

[0098] At the time of selection, the selection unit can analyze the user's past question history to select the optimal advertisement. The selection unit, for example, uses a data mining algorithm to analyze the user's past question history. For example, the selection unit analyzes the content and frequency of the user's past questions to select a relevant advertisement. The selection unit can also select advertisements related to areas of interest from the user's past question history. For example, the selection unit selects advertisements related to areas of interest based on the user's past question history. Furthermore, the selection unit can analyze the user's question history to select the most effective advertisement. For example, the selection unit selects the most effective advertisement based on the user's question history. This allows the selection unit to select the optimal advertisement based on the past question history.

[0099] The selection unit may filter advertisements based on the user's current areas of interest at the time of selection. The selection unit may, for example, use an area of ​​interest evaluation algorithm to evaluate the user's current areas of interest. For example, the selection unit may analyze the user's recent search history or browsing history to evaluate the current areas of interest. The selection unit may also use a filtering algorithm to filter advertisements based on the user's current areas of interest. For example, the selection unit may preferentially select relevant advertisements based on the user's current areas of interest. The selection unit may also filter and display advertisements related to the user's areas of interest. The selection unit may also analyze the user's current areas of interest and select an optimal advertisement. For example, the selection unit may select an optimal advertisement based on the user's current areas of interest. In this way, the selection unit can select an optimal advertisement based on the current areas of interest.

[0100] The selection unit may estimate a user's emotion and determine a priority of advertisements to be selected based on the estimated user's emotion. The selection unit may, for example, use an emotion analysis algorithm to estimate the user's emotion. For example, the selection unit may analyze the user's facial expression or voice data and calculate an emotion score. The selection unit may also use a priority determination algorithm to determine a priority of advertisements to be selected based on the user's emotion. For example, the selection unit may preferentially display detailed advertisements when the user is relaxed. The selection unit may also preferentially display concise advertisements when the user is stressed. Furthermore, the selection unit may preferentially select advertisements that can be displayed quickly when the user is in a hurry. In this way, the selection unit may preferentially select optimal advertisements according to the user's emotion.

[0101] During selection, the selection unit can prioritize highly relevant advertisements by taking into consideration the user's geographical location information. The selection unit, for example, uses GPS data or an IP address to acquire the user's geographical location information. For example, the selection unit prioritizes region-related advertisements based on the user's geographical location information. The selection unit can also select advertisements that are effective in a specific region based on the user's location information. For example, the selection unit selects advertisements that maximize advertising effectiveness in a specific region based on the user's location information. Furthermore, the selection unit can filter and select advertisements that are optimal for each region by taking into consideration the user's geographical location information. For example, the selection unit selects and displays advertisements that are optimal for each region based on the user's geographical location information. This allows the selection unit to select optimal advertisements based on the geographical location information.

[0102] At the time of selection, the selection unit may analyze the user's social media activity and select relevant advertisements. The selection unit may, for example, use a social media analysis tool to analyze the user's social media activity. For example, the selection unit may analyze the content of the user's social media posts and engagement rates to preferentially select relevant advertisements. The selection unit may also select optimal advertisements based on the user's social media trends. For example, the selection unit may analyze the user's social media trends and select highly relevant advertisements. Furthermore, the selection unit may filter and select advertisements that are effective for a specific target based on the user's social media activity. For example, the selection unit may select and display advertisements that are optimal for a specific target market based on the user's social media activity. This allows the selection unit to select optimal advertisements based on the social media activity.

[0103] The display unit can estimate a user's emotion and adjust the advertisement display method based on the estimated user's emotion. The display unit, for example, uses an emotion analysis algorithm to estimate the user's emotion. For example, the display unit analyzes the user's facial expression and voice data to calculate an emotion score. The display unit can also use a method adjustment algorithm to adjust the advertisement display method based on the user's emotion. For example, the display unit can display a detailed advertisement when the user is relaxed. The display unit can also display a concise and to-the-point advertisement when the user is stressed. Furthermore, the display unit can provide a quickly displayed advertisement when the user is in a hurry. This allows the display unit to display the advertisement in an optimal manner according to the user's emotion.

[0104] The display unit can adjust the level of detail of the display based on the importance of the advertisement when displaying the advertisement. The display unit, for example, uses an importance evaluation algorithm to evaluate the importance of the advertisement. For example, the display unit evaluates the influence of the advertisement and the size of the target market and calculates the importance. The display unit can also use a level of detail adjustment algorithm to adjust the level of detail of the display based on the importance of the advertisement. For example, the display unit displays an advertisement with high importance in detail. The display unit can also display an advertisement with low importance in a concise manner. Furthermore, the display unit can determine the priority of display according to the importance of the advertisement. For example, the display unit displays an advertisement with high importance first and an advertisement with low importance later. This allows the display unit to optimally display the advertisement according to the importance of the advertisement.

[0105] The display unit can apply different display algorithms depending on the category of the advertisement when displaying the advertisement. The display unit, for example, uses a category classification algorithm to classify the category of the advertisement. For example, the display unit classifies advertisements into categories such as text advertisements, image advertisements, and video advertisements. The display unit can also use an algorithm selection algorithm to apply different display algorithms depending on the category of the advertisement. For example, the display unit can apply a natural language processing algorithm to text advertisements. The display unit can also apply an image analysis algorithm to image advertisements. Furthermore, the display unit can apply a video analysis algorithm to video advertisements. This allows the display unit to perform optimal display depending on the category of the advertisement.

[0106] The display unit may estimate a user's emotion and determine the display order of advertisements based on the estimated user's emotion. The display unit may, for example, use an emotion analysis algorithm to estimate the user's emotion. For example, the display unit may analyze the user's facial expression or voice data and calculate an emotion score. The display unit may also use an order determination algorithm to determine the display order of advertisements based on the user's emotion. For example, the display unit may preferentially display detailed advertisements when the user is relaxed. The display unit may also preferentially display concise advertisements when the user is stressed. Furthermore, the display unit may preferentially select advertisements that can be displayed quickly when the user is in a hurry. This allows the display unit to display advertisements in an optimal order according to the user's emotion.

[0107] When displaying an advertisement, the display unit can determine a display priority based on the submission time of the advertisement. The display unit, for example, uses a submission time evaluation algorithm to evaluate the submission time of the advertisement. For example, the display unit evaluates the submission date and time or the submission frequency of the advertisement and calculates the submission time. The display unit can also use a priority determination algorithm to determine the display priority based on the submission time of the advertisement. For example, the display unit prioritizes displaying the most recent advertisement. The display unit can also postpone advertisements that were submitted earlier. Furthermore, the display unit can adjust the display schedule based on the submission time. For example, the display unit optimizes the display schedule based on the submission time. This allows the display unit to display advertisements in an optimal order based on the submission time.

[0108] The display unit can adjust the display order based on the relevance of the advertisements when displaying them. The display unit, for example, uses a relevance evaluation algorithm to evaluate the relevance of the advertisements. For example, the display unit evaluates the user's interest and past behavior of the advertisements and calculates the relevance. The display unit can also use an order adjustment algorithm to adjust the display order based on the relevance of the advertisements. For example, the display unit prioritizes displaying highly relevant advertisements. The display unit can also postpone displaying less relevant advertisements. Furthermore, the display unit can determine the display order based on the relevance of the advertisements. For example, the display unit optimizes the display order based on the relevance of the advertisements. This allows the display unit to display advertisements in an optimal order based on relevance. === Hard Collateral 1-1 === Each of the multiple elements, including the above-mentioned upload unit, analysis unit, conversion unit, integration unit, selection unit, and display unit, is realized, for example, by at least one of the smart device 14 and the data processing device 12. For example, the upload unit is realized by the control unit 46A of the smart device 14 and provides a function for an advertiser to upload advertising data to the platform. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the uploaded advertising data. The conversion unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and converts the analyzed advertising data into a format suitable for the generation AI. The integration unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and integrates the converted advertising data into the generation AI. The selection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and selects an advertisement related to the user's question. The display unit is realized, for example, by the control unit 46A of the smart device 14 and displays the selected advertisement to the user. === Hard Collateral 1-2 === Each of the multiple elements, including the above-mentioned upload unit, analysis unit, conversion unit, integration unit, selection unit, and display unit, is realized, for example, by at least one of the smart glasses 214 and the data processing device 12. For example, the upload unit is realized by the control unit 46A of the smart glasses 214 and provides a function for advertisers to upload advertising data to the platform. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the uploaded advertising data. The conversion unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and converts the analyzed advertising data into a format suitable for the generation AI. The integration unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and integrates the converted advertising data into the generation AI. The selection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and selects an advertisement related to the user's question. The display unit is realized, for example, by the control unit 46A of the smart glasses 214 and displays the selected advertisement to the user. === Hard Collateral 1-3 === Each of the multiple elements, including the above-mentioned upload unit, analysis unit, conversion unit, integration unit, selection unit, and display unit, is realized, for example, by at least one of the headset type terminal 314 and the data processing device 12. For example, the upload unit is realized by the control unit 46A of the headset type terminal 314 and provides a function for advertisers to upload advertising data to the platform. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the uploaded advertising data. The conversion unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and converts the analyzed advertising data into a format suitable for the generation AI. The integration unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and integrates the converted advertising data into the generation AI. The selection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and selects an advertisement related to the user's question. The display unit is realized, for example, by the control unit 46A of the headset type terminal 314 and displays the selected advertisement to the user. === Hard Collateral 1-4 === Each of the multiple elements, including the above-mentioned upload unit, analysis unit, conversion unit, integration unit, selection unit, and display unit, is realized, for example, by at least one of the robot 414 and the data processing device 12. For example, the upload unit is realized by the control unit 46A of the robot 414 and provides a function for advertisers to upload advertising data to the platform. The analysis unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and analyzes the uploaded advertising data. The conversion unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and converts the analyzed advertising data into a format suitable for the generation AI. The integration unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and integrates the converted advertising data into the generation AI. The selection unit is realized, for example, by the specific processing unit 290 of the data processing device 12 and selects an advertisement related to the user's question. The display unit is realized, for example, by the control unit 46A of the robot 414 and displays the selected advertisement to the user.

[0109] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0110] The advertising data integration platform may further include a suggestion unit that analyzes the advertiser's past advertising performance data and suggests the optimal advertising format. The suggestion unit may, for example, analyze the click-through rate and conversion rate of past advertising campaigns to identify the most effective advertising format. The suggestion unit may also suggest the optimal advertising format based on the characteristics of the advertiser's target market. For example, if it is determined that video advertising is effective for young people, the suggestion unit may recommend video advertising. The suggestion unit may also suggest the optimal advertising format based on the advertiser's budget and campaign goals. This allows the advertiser to obtain useful information for running an effective advertising campaign.

[0111] When analyzing advertising data, the analysis unit can adjust the analysis results taking into account the advertiser's brand image. For example, the analysis unit evaluates whether the content of the advertising data matches the brand image based on the advertiser's brand guidelines. The analysis unit can also detect elements that do not match the brand image and suggest modifications. Furthermore, the analysis unit can adjust design elements of the advertising data, such as colors and fonts, based on the brand image. This allows the advertiser to run effective advertisements while maintaining their brand image.

[0112] When converting advertising data, the conversion unit can adjust the conversion method taking into account the advertiser's past advertising performance data. For example, the conversion unit can analyze data from past advertising campaigns to identify the most effective conversion method. The conversion unit can also select the optimal conversion method based on the characteristics of the advertiser's target market. For example, if it is determined that short video ads are effective in a particular market, the conversion unit shortens the video ads. Furthermore, the conversion unit can adjust the conversion method according to the advertiser's budget and campaign goals. This allows the advertiser to use the optimal conversion method to run an effective advertising campaign.

[0113] The conversion unit can estimate the advertiser's emotions when converting advertising data and adjust the level of conversion detail based on the estimated emotions. For example, if the advertiser is relaxed, detailed conversion can be performed, and if the advertiser is stressed, simple conversion can be performed. Also, if the advertiser is in a hurry, conversion can be performed quickly. Furthermore, the conversion unit can determine the priority of conversion based on the advertiser's emotions. This makes it possible to provide an optimal conversion method according to the advertiser's emotions.

[0114] The selection unit can estimate the user's emotions and adjust the advertisement selection criteria based on the estimated emotions. For example, if the user is relaxed, a detailed advertisement can be provided, and if the user is stressed, a concise advertisement can be provided. Also, if the user is in a hurry, an advertisement that is displayed quickly can be provided. Furthermore, the selection unit can determine the priority of advertisements based on the user's emotions. This makes it possible to select the most appropriate advertisement according to the user's emotions.

[0115] The display unit can estimate the user's emotion when displaying an advertisement and adjust the display method based on the estimated emotion. For example, if the user is relaxed, a detailed advertisement can be displayed, and if the user is stressed, a concise advertisement can be displayed. Also, if the user is in a hurry, an advertisement that is displayed quickly can be provided. Furthermore, the display unit can determine the display order of advertisements based on the user's emotion. This allows advertisements to be displayed in an optimal manner according to the user's emotion.

[0116] The upload unit can estimate the advertiser's emotions and determine the priority of the advertising data to be uploaded based on the estimated emotions. For example, if the advertiser is relaxed, advertising data selected by the advertiser can be preferentially uploaded, and if the advertiser is stressed, advertising data of high importance can be preferentially uploaded. Also, if the advertiser is in a hurry, advertising data that needs to be uploaded immediately can be preferentially processed. In this way, optimal advertising data can be preferentially uploaded according to the advertiser's emotions.

[0117] The analysis unit can estimate the advertiser's emotions when analyzing the advertising data and adjust the way the analysis is presented based on the estimated emotions. For example, if the advertiser is relaxed, detailed analysis results can be provided, and if the advertiser is stressed, concise analysis results can be provided. Also, if the advertiser is in a hurry, analysis results can be provided quickly. This makes it possible to provide optimal analysis results according to the advertiser's emotions.

[0118] The integration unit can estimate the advertiser's emotions when integrating advertising data and adjust the integration method based on the estimated emotions. For example, if the advertiser is relaxed, detailed integration can be performed, and if the advertiser is stressed, simple integration can be performed. Also, if the advertiser is in a hurry, integration can be performed quickly. Furthermore, the integration unit can determine integration priorities based on the advertiser's emotions. This allows advertising data to be integrated in an optimal manner according to the advertiser's emotions.

[0119] The selection unit can analyze the user's past behavioral data and select the most appropriate advertisement. For example, the selection unit can analyze the user's past search history and browsing history and select relevant advertisements. The selection unit can also select advertisements related to products of interest to the user based on the user's past purchase history. Furthermore, the selection unit can analyze the user's past behavioral data and select the most effective advertisement. This allows the selection unit to select the most appropriate advertisement based on the past behavioral data.

[0120] The processing flow of the second embodiment will be briefly explained below.

[0121] Step 1: The upload section allows advertisers to upload their advertising data to the platform. The advertising data can include text ads, image ads, video ads, etc. The upload section can set restrictions on file format and data size. Step 2: The analysis unit analyzes the advertising data uploaded by the upload unit. The analysis unit supports formats such as text ads, image ads, and video ads, and allows you to set the algorithm to be used and the accuracy of the analysis. Step 3: The conversion unit converts the advertising data analyzed by the analysis unit into a format suitable for the generation AI. The conversion unit converts text ads into a format that is easy for the generation AI to understand, and can convert image ads and video ads into the appropriate size and format. The format to be converted and the conversion accuracy can be set. Step 4: The integration unit integrates the advertising data converted by the conversion unit into the generation AI. The integration unit can set the type of data to be integrated and the integration procedure. Step 5: The selection unit selects advertisements related to the user's query based on the advertisement data integrated by the integration unit. The selection unit may set criteria or algorithms for selecting relevant advertisements based on the user's query. Step 6: The display unit displays the advertisement selected by the selection unit to the user. The display unit can set the device and display format for displaying the advertisement.

[0122] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0123] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of the generative AI include a neural network (NN) and a neural network (NN). The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats of voice data, text data, image data, etc. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and may perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-mentioned parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. The processing performed by an AI including the generative AI may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI including the generative AI.

[0124] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0125] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0126] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0127] 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.

[0128] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0129] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0130] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0131] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0132] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0133] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0134] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0135] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0136] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0137] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0138] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0139] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0140] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0141] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0142] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0143] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0144] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0145] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0146] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0147] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0148] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0149] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0150] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0151] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0152] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the identification processing unit 290 using these models.

[0153] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0154] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0155] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0156] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0157] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0158] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0159] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0160] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0161] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0162] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0163] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0164] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0165] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0166] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0167] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0168] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0169] In the robot 414, the processor 46 performs the identification process. The storage 50 stores the identification program 60. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as the control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 also has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform the same process as the identification processing unit 290 using these models.

[0170] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0171] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0172] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt including an instruction, as well as inference data such as audio data indicating speech, text data indicating text, and image data indicating an image (e.g., still image data or video data). The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in one or more data formats, such as audio data, text data, and image data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation models 58 include AIs other than the generation AI. Examples of AIs other than the generation AI include, but are not limited to, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), and naive Bayes. These AIs can perform various types of processing, but are not limited to these examples. The AI ​​may also be an AI agent. When the processing of each of the above-described parts is performed by an AI, the processing may be performed in part or entirely by the AI, but is not limited to these examples. Processing performed by an AI, including the generation AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by an AI, including the generation AI.

[0173] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0174] The correspondence between each part and the device or control part is not limited to the example described above, and various modifications are possible.

[0175] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0176] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0177] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0178] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0179] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0180] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0181] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0182] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0183] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0184] 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.

[0185] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0186] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0187] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0188] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0189] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0190] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0191] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0192] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[0193] [Explanation of symbols]

[0194] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an upload unit for uploading advertisement data; an analysis unit that analyzes the advertisement data uploaded by the upload unit; A conversion unit that converts the advertising data analyzed by the analysis unit into a format suitable for the generation AI; an integration unit that integrates the advertising data converted by the conversion unit into a generated AI; a selection unit that selects an advertisement related to the content of the user's question based on the advertisement data integrated by the integration unit; a display unit that displays the advertisement selected by the selection unit. A system characterized by:

2. The analysis unit Supports text, image and video ad formats 2. The system of claim 1.

3. The conversion unit Convert text ads into a format that is easy for AI to understand 2. The system of claim 1.

4. The conversion unit Convert your image or video ads into the right size and format 2. The system of claim 1.

5. The selection unit Select relevant ads based on user questions 2. The system of claim 1.

6. The display unit Display the selected ad to the user 2. The system of claim 1.

7. The upload unit Estimate advertiser sentiment and adjust the timing of uploading advertising data based on the estimated advertiser sentiment.

2. The system of claim 1.

8. The upload unit Analyze the advertiser's upload history and select the optimal upload method 2. The system of claim 1.

Images