system

Abstract

An object of the system according to the embodiment is to automate an advertisement examination process and provide a specific NG reason and a correction proposal in real time.SOLUTION: A system includes an advertisement content analysis part, an examination result providing part, an NG reason providing part, and a correction proposal providing part. The advertisement content analysis unit analyzes advertisement content. The examination result providing unit provides an examination result based on the advertisement content analyzed by the advertisement content analyzing unit. The NG reason providing unit provides a specific NG reason based on the examination result provided by the examination result providing unit. The revision suggestion providing unit provides a revision suggestion based on the NG reason provided by the NG reason providing unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, the ad review process is often done manually, which is inefficient and can lead to delays in providing specific reasons for rejection and suggested revisions.

[0005] The system according to the embodiment aims to automate the advertising review process and provide specific reasons for rejection and suggested corrections in real time. [Means for solving the problem]

[0006] The system according to the embodiment includes an advertisement content analysis unit, a review result providing unit, a rejection reason providing unit, and a revision suggestion providing unit. The advertisement content analysis unit analyzes advertisement content. The review result providing unit provides a review result based on the advertisement content analyzed by the advertisement content analysis unit. The rejection reason providing unit provides a specific rejection reason based on the review result provided by the review result providing unit. The revision suggestion providing unit provides a revision suggestion based on the rejection reason provided by the rejection reason providing unit. [Effects of the Invention]

[0007] The system according to the embodiment automates the ad review process and can provide specific reasons for rejection and suggested corrections in real time. [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 the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the 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 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[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) The advertising review automation system according to an embodiment of the present invention utilizes generative AI technology to automate the review process of ad publishing sites, and provides the review results along with specific reasons for rejection and suggested corrections in real time. As a result, the advertising review automation system can significantly improve the efficiency of advertising reviews and reduce the workload of both advertisers and media operators.

[0029] An advertising review automation system according to an embodiment includes an advertisement content analysis unit, a review result providing unit, a rejection reason providing unit, and a revision suggestion providing unit. The advertisement content analysis unit analyzes advertisement content. For example, the advertisement content analysis unit analyzes advertisement text and images to check whether the advertisement contains inappropriate content. The advertisement content analysis unit can also analyze advertisement videos to detect inappropriate scenes within the videos. The advertisement content analysis unit can also analyze advertisement audio content to check whether the advertisement contains inappropriate language. The review result providing unit provides a review result based on the advertisement content analyzed by the advertisement content analysis unit. For example, the review result providing unit displays the result in the form of "This advertisement has been approved" or "This advertisement has not been approved." The review result providing unit can also provide the review result in real time. The review result providing unit can also notify the advertiser of the review result. The rejection reason providing unit provides a specific rejection reason based on the review result provided by the review result providing unit. For example, the rejection reason providing unit displays a specific reason in the form of "This advertisement contains inappropriate language" or "This image infringes copyright." The refusal reason providing unit can also explain the refusal reason in detail. The refusal reason providing unit can also notify the advertiser of the refusal reason. The revision suggestion providing unit provides a revision suggestion based on the refusal reason provided by the refusal reason providing unit. For example, the revision suggestion providing unit suggests a specific revision suggestion such as "replace this word with another word" or "delete this image." The revision suggestion providing unit can also explain the revision suggestion in detail. The revision suggestion providing unit can also notify the advertiser of the revision suggestion. As a result, the advertising review automation system according to the embodiment can significantly improve the efficiency of advertising review and reduce the workload of both advertisers and media operators.

[0030] The ad content analysis unit can refer to the advertiser's past advertising history and dynamically adjust the screening criteria based on the performance data. For example, the ad content analysis unit uses a generation AI to retrieve the advertiser's past advertising history from a database and analyze the performance data of past ads. For example, the screening criteria can be dynamically adjusted based on data such as click-through rate and conversion rate. The ad content analysis unit can also refer to the advertiser's past advertising history and adjust the screening criteria based on past examples of successful and unsuccessful ads. The ad content analysis unit can also refer to the advertiser's past advertising history and dynamically adjust the screening criteria based on the performance data of past ads. This enables more effective ad screening by dynamically adjusting the screening criteria based on the advertiser's past advertising history and performance data.

[0031] The advertisement content analysis unit can evaluate the suitability of the advertisement to specific attributes by taking into account attribute information of the advertisement's target audience. For example, the advertisement content analysis unit uses a generation AI to obtain attribute information of the advertisement's target audience from a database and evaluate whether the advertisement content matches those attributes. For example, the evaluation is made based on data such as age, gender, and interests. The advertisement content analysis unit can also evaluate whether the advertisement content matches specific attributes by taking into account attribute information of the target audience. The advertisement content analysis unit can also evaluate whether the advertisement content matches specific attributes by taking into account attribute information of the target audience. In this way, by taking into account attribute information of the target audience, the suitability of the advertisement can be improved.

[0032] The advertisement content analysis unit can evaluate the visual design and layout of an advertisement and take visual appeal into consideration. In the advertisement content analysis unit, for example, a generative AI analyzes the visual design and layout of an advertisement and evaluates its visual appeal. For example, the evaluation is based on the use of colors, fonts, layout balance, etc. The advertisement content analysis unit can also evaluate the visual design and layout of an advertisement and take visual appeal into consideration. The advertisement content analysis unit can also evaluate the visual design and layout of an advertisement and take visual appeal into consideration. In this way, by evaluating the visual design and layout, visually appealing advertisements can be approved.

[0033] The advertisement content analysis unit can analyze the audio content of an advertisement and evaluate the consistency of the tone of the audio and the message. For example, the advertisement content analysis unit uses a generation AI to analyze the audio content of an advertisement and evaluate the consistency of the tone of the audio and the message. For example, the evaluation is made based on the emotional tone of the audio and the consistency of the message. The advertisement content analysis unit can also analyze the audio content of an advertisement and evaluate the consistency of the tone of the audio and the message. The advertisement content analysis unit can also analyze the audio content of an advertisement and evaluate the consistency of the tone of the audio and the message. In this way, the consistency of the tone of the audio and the message can be evaluated by analyzing the audio content.

[0034] The review result providing unit can refer to the advertiser's past feedback history and provide individually customized feedback. For example, the review result providing unit uses a generation AI to retrieve the advertiser's past feedback history from a database and provide individually customized feedback. For example, the review result providing unit suggests specific areas for improvement based on the content of the past feedback. The review result providing unit can also refer to the advertiser's past feedback history and provide individually customized feedback. The review result providing unit can also refer to the advertiser's past feedback history and provide individually customized feedback. In this way, individually customized feedback can be provided by referring to the advertiser's past feedback history.

[0035] The review result providing unit can provide strategic advice by referring to the advertiser's industry trends and the advertising strategies of competitors. For example, the generation AI retrieves the advertiser's industry trends and the competitors' advertising strategies from a database and provides strategic advice. For example, the review result providing unit provides advice based on the latest industry trends and success stories of competitors. The review result providing unit can also provide strategic advice by referring to the advertiser's industry trends and the competitors' advertising strategies. The review result providing unit can also provide strategic advice by referring to the advertiser's industry trends and the competitors' advertising strategies. In this way, strategic advice can be provided to advertisers by referring to industry trends and the competitors' advertising strategies.

[0036] The review result providing unit can provide region-specific feedback by taking into account the advertiser's region and cultural background. For example, the generation AI retrieves the advertiser's region and cultural background from a database and provides region-specific feedback. For example, specific advice based on the culture and customs of the region is provided. The review result providing unit can also provide region-specific feedback by taking into account the advertiser's region and cultural background. The review result providing unit can also provide region-specific feedback by taking into account the advertiser's region and cultural background. This makes it possible to provide region-specific feedback by taking into account the advertiser's region and cultural background.

[0037] The review result providing unit can take into account the advertiser's brand image and corporate philosophy and provide feedback in line with that. For example, the generation AI retrieves the advertiser's brand image and corporate philosophy from a database and provides feedback in line with that. For example, specific advice that matches the brand image is provided. The review result providing unit can also take into account the advertiser's brand image and corporate philosophy and provide feedback in line with that. The review result providing unit can also take into account the advertiser's brand image and corporate philosophy and provide feedback in line with that. This makes it possible to provide feedback in line with the advertiser's brand image and corporate philosophy by taking into account the advertiser's brand image and corporate philosophy.

[0038] The NG reason providing unit can refer to the advertiser's past history of NG reasons and provide advice to avoid similar problems. For example, the NG reason providing unit uses a generation AI to retrieve the advertiser's past history of NG reasons from a database and provide advice to avoid similar problems. For example, it suggests specific improvements based on the reasons for past NGs. The NG reason providing unit can also refer to the advertiser's past history of NG reasons and provide advice to avoid similar problems. The NG reason providing unit can also refer to the advertiser's past history of NG reasons and provide advice to avoid similar problems. In this way, advice to avoid similar problems can be provided by referring to the advertiser's past history of NG reasons.

[0039] The NG reason providing unit can refer to feedback from the target audience and suggest specific areas for improvement. For example, the NG reason providing unit uses a generation AI to obtain feedback from the target audience from a database and suggest specific areas for improvement. For example, the NG reason providing unit suggests areas for improvement to the advertisement based on the opinions and impressions of the target audience. The NG reason providing unit can also refer to feedback from the target audience and suggest specific areas for improvement. The NG reason providing unit can also refer to feedback from the target audience and suggest specific areas for improvement. In this way, specific areas for improvement can be suggested by referring to feedback from the target audience.

[0040] The rejection reason providing unit can suggest specific improvements regarding the visual design and layout. For example, the rejection reason providing unit uses a generation AI to analyze the visual design and layout of an advertisement and suggest specific improvements. For example, it can suggest improvements based on the use of color, font, layout balance, etc. The rejection reason providing unit can also suggest specific improvements regarding the visual design and layout. The rejection reason providing unit can also suggest specific improvements regarding the visual design and layout. In this way, by suggesting specific improvements regarding the visual design and layout, the quality of the advertisement can be improved.

[0041] The NG reason providing unit can suggest specific improvements regarding the audio content. For example, the NG reason providing unit uses a generation AI to analyze the audio content of an advertisement and suggest specific improvements. For example, the NG reason providing unit can suggest improvements based on the consistency of the tone of the audio or the message. The NG reason providing unit can also suggest specific improvements regarding the audio content. The NG reason providing unit can also suggest specific improvements regarding the audio content. In this way, by suggesting specific improvements regarding the audio content, the quality of the advertisement can be improved.

[0042] The revision suggestion providing unit can refer to the advertiser's past revision history and suggest the most effective revision method. For example, the generation AI retrieves the advertiser's past revision history from a database and suggests the most effective revision method. For example, the revision suggestion providing unit presents a specific revision suggestion based on revision methods that have been successful in the past. The revision suggestion providing unit can also refer to the advertiser's past revision history and suggest the most effective revision method. The revision suggestion providing unit can also refer to the advertiser's past revision history and suggest the most effective revision method. In this way, the most effective revision method can be suggested by referring to the advertiser's past revision history.

[0043] The revision suggestion providing unit can take into account the attribute information of the target audience and present optimal revision suggestions for specific attributes. For example, the generation AI retrieves the attribute information of the target audience from a database and presents optimal revision suggestions for specific attributes. For example, the revision suggestion providing unit proposes revision suggestions based on data such as age, gender, and interests. The revision suggestion providing unit can also take into account the attribute information of the target audience and present optimal revision suggestions for specific attributes. The revision suggestion providing unit can also take into account the attribute information of the target audience and present optimal revision suggestions for specific attributes. In this way, by taking into account the attribute information of the target audience, it is possible to present optimal revision suggestions for specific attributes.

[0044] The revision suggestion providing unit can present specific revision suggestions regarding the visual design and layout. For example, the revision suggestion providing unit uses a generation AI to analyze the visual design and layout of an advertisement and presents specific revision suggestions. For example, the revision suggestion providing unit can propose revision suggestions based on the use of colors, fonts, layout balance, etc. The revision suggestion providing unit can also present specific revision suggestions regarding the visual design and layout. The revision suggestion providing unit can also present specific revision suggestions regarding the visual design and layout. In this way, by presenting specific revision suggestions regarding the visual design and layout, the quality of the advertisement can be improved.

[0045] The revision suggestion providing unit can present specific revision suggestions regarding the audio content. For example, the revision suggestion providing unit uses a generation AI to analyze the audio content of an advertisement and presents specific revision suggestions. For example, the revision suggestion providing unit can present specific revision suggestions regarding the audio content. The revision suggestion providing unit can also present specific revision suggestions regarding the audio content. In this way, by presenting specific revision suggestions regarding the audio content, the quality of the advertisement can be improved.

[0046] The ad content analysis unit can significantly improve the efficiency of ad review by using generative AI technology. The ad content analysis unit, for example, uses generative AI technology to automate the ad review process and review a large number of ads in a shorter time than manual review. For example, it analyzes the text and images of ads to check whether they contain inappropriate content. The ad content analysis unit can also significantly improve the efficiency of ad review by using generative AI technology. The ad content analysis unit can also significantly improve the efficiency of ad review by using generative AI technology. As a result, the use of generative AI technology can significantly improve the efficiency of ad review.

[0047] The advertisement content analysis unit can maintain consistency in the review criteria by using generative AI technology. The advertisement content analysis unit can, for example, dynamically adjust the review criteria by using generative AI technology to maintain consistency. For example, the review criteria can be adjusted based on past advertising history and performance data. The advertisement content analysis unit can also maintain consistency in the review criteria by using generative AI technology. The advertisement content analysis unit can also maintain consistency in the review criteria by using generative AI technology. As a result, the use of generative AI technology can maintain consistency in the review criteria.

[0048] The advertisement content analysis unit can improve the quality of advertisements by using generative AI technology. The advertisement content analysis unit, for example, builds a system for improving the quality of advertisements by using generative AI technology. For example, it analyzes the text and images of advertisements and checks whether they contain inappropriate content. The advertisement content analysis unit can also improve the quality of advertisements by using generative AI technology. The advertisement content analysis unit can also improve the quality of advertisements by using generative AI technology. In this way, the quality of advertisements can be improved by using generative AI technology.

[0049] The ad content analysis unit can use generative AI technology to reduce the workload on both advertisers and media operators. The ad content analysis unit, for example, uses generative AI technology to build a system to reduce the workload on both advertisers and media operators. For example, it can automate the ad review process, eliminating the need for manual review work. The ad content analysis unit can also use generative AI technology to reduce the workload on both advertisers and media operators. The ad content analysis unit can also use generative AI technology to reduce the workload on both advertisers and media operators. As a result, the use of generative AI technology can reduce the workload on both advertisers and media operators.

[0050] The ad content analysis unit can use generative AI technology to provide advertisers with specific reasons for rejection and suggested revisions in real time. The ad content analysis unit, for example, uses generative AI technology to build a system that provides advertisers with specific reasons for rejection and suggested revisions in real time. For example, it analyzes the text and images of an advertisement and presents a specific reason for rejection if the advertisement contains inappropriate content. The ad content analysis unit can also use generative AI technology to provide advertisers with specific reasons for rejection and suggested revisions in real time. The ad content analysis unit can also use generative AI technology to provide advertisers with specific reasons for rejection and suggested revisions in real time. In this way, by using generative AI technology, it is possible to provide advertisers with specific reasons for rejection and suggested revisions in real time.

[0051] The advertisement content analysis unit can provide specific feedback to advertisers using generative AI technology. The advertisement content analysis unit, for example, builds a system that provides specific feedback to advertisers using generative AI technology. For example, it analyzes the text and images of an advertisement and presents specific feedback if inappropriate content is included. The advertisement content analysis unit can also provide specific feedback to advertisers using generative AI technology. The advertisement content analysis unit can also provide specific feedback to advertisers using generative AI technology. In this way, specific feedback can be provided to advertisers by using generative AI technology.

[0052] By utilizing generative AI technology, the ad content analysis unit can reduce the workload on both advertisers and media operators. For example, by utilizing generative AI technology, the ad content analysis unit can build a system to reduce the workload on both advertisers and media operators. For example, by automating the ad review process, manual review work is no longer necessary. Furthermore, by utilizing generative AI technology, the ad content analysis unit can also reduce the workload on both advertisers and media operators. Furthermore, by utilizing generative AI technology, the ad content analysis unit can also reduce the workload on both advertisers and media operators. In this way, by utilizing generative AI technology, the workload on both advertisers and media operators can be reduced.

[0053] The ad content analysis unit utilizes generative AI technology to enable advertisers to receive specific reasons for rejection and suggested revisions in real time. The ad content analysis unit, for example, utilizes generative AI technology to build a system that enables advertisers to receive specific reasons for rejection and suggested revisions in real time. For example, it analyzes the text and images of an ad and presents a specific reason for rejection if the ad contains inappropriate content. The ad content analysis unit also utilizes generative AI technology to enable advertisers to receive specific reasons for rejection and suggested revisions in real time. The ad content analysis unit also utilizes generative AI technology to enable advertisers to receive specific reasons for rejection and suggested revisions in real time. As a result, by utilizing generative AI technology, advertisers can receive specific reasons for rejection and suggested revisions in real time.

[0054] By utilizing generative AI technology, the advertising content analysis unit eliminates the need for manual review work for media operators, allowing them to focus on other tasks. For example, by utilizing generative AI technology, the advertising content analysis unit builds a system that eliminates the need for manual review work for media operators, allowing them to focus on other tasks. For example, the advertising review process can be automated, eliminating the need for manual review work. Furthermore, by utilizing generative AI technology, the advertising content analysis unit eliminates the need for manual review work for media operators, allowing them to focus on other tasks. Furthermore, by utilizing generative AI technology, the advertising content analysis unit eliminates the need for manual review work for media operators, allowing them to focus on other tasks. Thus, by utilizing generative AI technology, the advertising content analysis unit eliminates the need for manual review work for media operators, allowing them to focus on other tasks.

[0055] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0056] The advertisement content analysis unit can evaluate the visual design and layout of the advertisement and take visual appeal into consideration. For example, the evaluation is performed based on the color usage, font, layout balance, etc. The advertisement content analysis unit can also evaluate the visual design and layout of the advertisement and take visual appeal into consideration. In this way, by evaluating the visual design and layout, it is possible to approve visually appealing advertisements.

[0057] The advertisement content analysis unit can evaluate the suitability of the advertisement to specific attributes by taking into account attribute information of the target audience of the advertisement. For example, the evaluation is performed based on data such as age, gender, and interests. The advertisement content analysis unit can also evaluate whether the advertisement content is suitable for specific attributes by taking into account attribute information of the target audience. In this way, by taking into account attribute information of the target audience, the suitability of the advertisement can be improved.

[0058] The ad content analysis unit can refer to the advertiser's past advertising history and dynamically adjust the screening criteria based on performance data. For example, the generation AI retrieves the advertiser's past advertising history from a database and analyzes the performance data of past ads. For example, the screening criteria can be dynamically adjusted based on data such as click-through rate and conversion rate. The ad content analysis unit can also refer to the advertiser's past advertising history and adjust the screening criteria based on past successful and unsuccessful advertising examples. This enables more effective ad screening by dynamically adjusting the screening criteria based on the advertiser's past advertising history and performance data.

[0059] The review result providing unit can provide individually customized feedback by referring to the advertiser's past feedback history. For example, the generation AI retrieves the advertiser's past feedback history from a database and provides individually customized feedback. For example, specific improvements can be suggested based on the content of the past feedback. The review result providing unit can also provide individually customized feedback by referring to the advertiser's past feedback history. As a result, individually customized feedback can be provided by referring to the advertiser's past feedback history.

[0060] The NG reason providing unit can refer to the advertiser's past history of NG reasons and provide advice to avoid similar problems. For example, the generation AI retrieves the advertiser's past history of NG reasons from a database and provides advice to avoid similar problems. For example, it suggests specific areas for improvement based on the reasons for past NGs. The NG reason providing unit can also refer to the advertiser's past history of NG reasons and provide advice to avoid similar problems. By referring to the advertiser's past history of NG reasons, advice to avoid similar problems can be provided.

[0061] The revision suggestion providing unit can refer to the advertiser's past revision history and suggest the most effective revision method. For example, the generation AI retrieves the advertiser's past revision history from a database and suggests the most effective revision method. For example, it presents specific revision suggestions based on revision methods that have been successful in the past. The revision suggestion providing unit can also refer to the advertiser's past revision history and suggest the most effective revision method. In this way, the most effective revision method can be suggested by referring to the advertiser's past revision history.

[0062] The processing flow of the first embodiment will be briefly explained below.

[0063] Step 1: The advertisement content analysis unit analyzes the advertisement content. For example, the advertisement content analysis unit analyzes the text and images of the advertisement to check whether they contain inappropriate content. The advertisement content analysis unit can also analyze the video of the advertisement to detect inappropriate scenes within the video. Furthermore, the advertisement content analysis unit can analyze the audio content of the advertisement to check whether they contain inappropriate language. Step 2: The review result providing unit provides the review result based on the advertisement content analyzed by the advertisement content analysis unit. For example, the review result providing unit displays the result in the form of "This advertisement has been approved" or "This advertisement has not been approved." The review result providing unit can also provide the review result in real time and notify the advertiser of the review result. Step 3: The NG reason providing unit provides a specific NG reason based on the review results provided by the review result providing unit. For example, the NG reason providing unit indicates a specific reason such as "This advertisement contains inappropriate language" or "This image infringes copyright." The NG reason providing unit can also explain the NG reason in detail and notify the advertiser. Step 4: The revision suggestion providing unit provides a revision suggestion based on the rejection reason provided by the rejection reason providing unit. For example, the revision suggestion providing unit suggests specific revision suggestions such as "replace this word with another word" or "delete this image." The revision suggestion providing unit can also explain the revision suggestion in detail and notify the advertiser.

[0064] (Example 2) The advertising review automation system according to an embodiment of the present invention utilizes generative AI technology to automate the review process of ad publishing sites, and provides the review results along with specific reasons for rejection and suggested corrections in real time. As a result, the advertising review automation system can significantly improve the efficiency of advertising reviews and reduce the workload of both advertisers and media operators.

[0065] An advertising review automation system according to an embodiment includes an advertisement content analysis unit, a review result providing unit, a rejection reason providing unit, and a revision suggestion providing unit. The advertisement content analysis unit analyzes advertisement content. For example, the advertisement content analysis unit analyzes advertisement text and images to check whether the advertisement contains inappropriate content. The advertisement content analysis unit can also analyze advertisement videos to detect inappropriate scenes within the videos. The advertisement content analysis unit can also analyze advertisement audio content to check whether the advertisement contains inappropriate language. The review result providing unit provides a review result based on the advertisement content analyzed by the advertisement content analysis unit. For example, the review result providing unit displays the result in the form of "This advertisement has been approved" or "This advertisement has not been approved." The review result providing unit can also provide the review result in real time. The review result providing unit can also notify the advertiser of the review result. The rejection reason providing unit provides a specific rejection reason based on the review result provided by the review result providing unit. For example, the rejection reason providing unit displays a specific reason in the form of "This advertisement contains inappropriate language" or "This image infringes copyright." The refusal reason providing unit can also explain the refusal reason in detail. The refusal reason providing unit can also notify the advertiser of the refusal reason. The revision suggestion providing unit provides a revision suggestion based on the refusal reason provided by the refusal reason providing unit. For example, the revision suggestion providing unit suggests a specific revision suggestion such as "replace this word with another word" or "delete this image." The revision suggestion providing unit can also explain the revision suggestion in detail. The revision suggestion providing unit can also notify the advertiser of the revision suggestion. As a result, the advertising review automation system according to the embodiment can significantly improve the efficiency of advertising review and reduce the workload of both advertisers and media operators.

[0066] The ad content analysis unit can refer to the advertiser's past advertising history and dynamically adjust the screening criteria based on the performance data. For example, the ad content analysis unit uses a generation AI to retrieve the advertiser's past advertising history from a database and analyze the performance data of past ads. For example, the screening criteria can be dynamically adjusted based on data such as click-through rate and conversion rate. The ad content analysis unit can also refer to the advertiser's past advertising history and adjust the screening criteria based on past examples of successful and unsuccessful ads. The ad content analysis unit can also refer to the advertiser's past advertising history and dynamically adjust the screening criteria based on the performance data of past ads. This enables more effective ad screening by dynamically adjusting the screening criteria based on the advertiser's past advertising history and performance data.

[0067] The advertisement content analysis unit can evaluate the suitability of the advertisement to specific attributes by taking into account attribute information of the advertisement's target audience. For example, the advertisement content analysis unit uses a generation AI to obtain attribute information of the advertisement's target audience from a database and evaluate whether the advertisement content matches those attributes. For example, the evaluation is made based on data such as age, gender, and interests. The advertisement content analysis unit can also evaluate whether the advertisement content matches specific attributes by taking into account attribute information of the target audience. The advertisement content analysis unit can also evaluate whether the advertisement content matches specific attributes by taking into account attribute information of the target audience. In this way, by taking into account attribute information of the target audience, the suitability of the advertisement can be improved.

[0068] The advertising content analysis unit can use the emotion estimation function to evaluate the emotional impact of advertising content on the target audience and preferentially approve advertising that elicits positive emotions. For example, the advertising content analysis unit uses a generative AI to analyze advertising content and the emotion estimation function to evaluate the emotional impact of advertising on the target audience. For example, the advertising content analysis unit calculates an emotion score from the advertising text and images and preferentially approves advertising that elicits positive emotions. The advertising content analysis unit can also use the emotion estimation function to evaluate the emotional impact of advertising content on the target audience and preferentially approve advertising that elicits positive emotions. The advertising content analysis unit can also use the emotion estimation function to evaluate the emotional impact of advertising content on the target audience and preferentially approve advertising that elicits positive emotions. As a result, by using the emotion estimation function, advertising that elicits positive emotions in the target audience can be preferentially approved.

[0069] The advertisement content analysis unit can evaluate the visual design and layout of an advertisement and take visual appeal into consideration. In the advertisement content analysis unit, for example, a generative AI analyzes the visual design and layout of an advertisement and evaluates its visual appeal. For example, the evaluation is based on the use of colors, fonts, layout balance, etc. The advertisement content analysis unit can also evaluate the visual design and layout of an advertisement and take visual appeal into consideration. The advertisement content analysis unit can also evaluate the visual design and layout of an advertisement and take visual appeal into consideration. In this way, by evaluating the visual design and layout, visually appealing advertisements can be approved.

[0070] The advertisement content analysis unit can analyze the audio content of an advertisement and evaluate the consistency of the tone of the audio and the message. For example, the advertisement content analysis unit uses a generation AI to analyze the audio content of an advertisement and evaluate the consistency of the tone of the audio and the message. For example, the evaluation is made based on the emotional tone of the audio and the consistency of the message. The advertisement content analysis unit can also analyze the audio content of an advertisement and evaluate the consistency of the tone of the audio and the message. The advertisement content analysis unit can also analyze the audio content of an advertisement and evaluate the consistency of the tone of the audio and the message. In this way, the consistency of the tone of the audio and the message can be evaluated by analyzing the audio content.

[0071] The advertisement content analysis unit can use the emotion estimation function to estimate the emotion of the advertiser when submitting an advertisement in real time and provide feedback to elicit positive emotions. The advertisement content analysis unit, for example, uses the emotion estimation function to analyze the emotion of the advertiser when submitting an advertisement in real time. For example, the advertisement content analysis unit can analyze the facial expressions and voice of the advertiser and calculate an emotion score. The advertisement content analysis unit can also use the emotion estimation function to estimate the emotion of the advertiser when submitting an advertisement in real time and provide feedback to elicit positive emotions. The advertisement content analysis unit can also use the emotion estimation function to estimate the emotion of the advertiser when submitting an advertisement in real time and provide feedback to elicit positive emotions. In this way, by estimating the emotion of the advertiser in real time and providing feedback to elicit positive emotions, it is possible to improve advertiser satisfaction.

[0072] The review result providing unit can refer to the advertiser's past feedback history and provide individually customized feedback. For example, the review result providing unit uses a generation AI to retrieve the advertiser's past feedback history from a database and provide individually customized feedback. For example, the review result providing unit suggests specific areas for improvement based on the content of the past feedback. The review result providing unit can also refer to the advertiser's past feedback history and provide individually customized feedback. The review result providing unit can also refer to the advertiser's past feedback history and provide individually customized feedback. In this way, individually customized feedback can be provided by referring to the advertiser's past feedback history.

[0073] The review result providing unit can provide strategic advice by referring to the advertiser's industry trends and the advertising strategies of competitors. For example, the generation AI retrieves the advertiser's industry trends and the competitors' advertising strategies from a database and provides strategic advice. For example, the review result providing unit provides advice based on the latest industry trends and success stories of competitors. The review result providing unit can also provide strategic advice by referring to the advertiser's industry trends and the competitors' advertising strategies. The review result providing unit can also provide strategic advice by referring to the advertiser's industry trends and the competitors' advertising strategies. In this way, strategic advice can be provided to advertisers by referring to industry trends and the competitors' advertising strategies.

[0074] The review result providing unit can provide region-specific feedback by taking into account the advertiser's region and cultural background. For example, the generation AI retrieves the advertiser's region and cultural background from a database and provides region-specific feedback. For example, specific advice based on the culture and customs of the region is provided. The review result providing unit can also provide region-specific feedback by taking into account the advertiser's region and cultural background. The review result providing unit can also provide region-specific feedback by taking into account the advertiser's region and cultural background. This makes it possible to provide region-specific feedback by taking into account the advertiser's region and cultural background.

[0075] The review result providing unit can take into account the advertiser's brand image and corporate philosophy and provide feedback in line with that. For example, the generation AI retrieves the advertiser's brand image and corporate philosophy from a database and provides feedback in line with that. For example, specific advice that matches the brand image is provided. The review result providing unit can also take into account the advertiser's brand image and corporate philosophy and provide feedback in line with that. The review result providing unit can also take into account the advertiser's brand image and corporate philosophy and provide feedback in line with that. This makes it possible to provide feedback in line with the advertiser's brand image and corporate philosophy by taking into account the advertiser's brand image and corporate philosophy.

[0076] The review result providing unit can use the emotion estimation function to estimate the advertiser's emotion regarding the review result in real time and provide additional information for eliciting positive emotions. The review result providing unit, for example, uses the emotion estimation function to estimate the advertiser's emotion regarding the review result in real time. For example, the review result providing unit can analyze the advertiser's facial expressions and voice to calculate an emotion score. The review result providing unit can also use the emotion estimation function to estimate the advertiser's emotion regarding the review result in real time and provide additional information for eliciting positive emotions. The review result providing unit can also use the emotion estimation function to estimate the advertiser's emotion regarding the review result in real time and provide additional information for eliciting positive emotions. In this way, by estimating the advertiser's emotion regarding the review result in real time and providing additional information for eliciting positive emotions, it is possible to improve advertiser satisfaction.

[0077] The NG reason providing unit can refer to the advertiser's past history of NG reasons and provide advice to avoid similar problems. For example, the NG reason providing unit uses a generation AI to retrieve the advertiser's past history of NG reasons from a database and provide advice to avoid similar problems. For example, it suggests specific improvements based on the reasons for past NGs. The NG reason providing unit can also refer to the advertiser's past history of NG reasons and provide advice to avoid similar problems. The NG reason providing unit can also refer to the advertiser's past history of NG reasons and provide advice to avoid similar problems. In this way, advice to avoid similar problems can be provided by referring to the advertiser's past history of NG reasons.

[0078] The NG reason providing unit can refer to feedback from the target audience and suggest specific areas for improvement. For example, the NG reason providing unit uses a generation AI to obtain feedback from the target audience from a database and suggest specific areas for improvement. For example, the NG reason providing unit suggests areas for improvement to the advertisement based on the opinions and impressions of the target audience. The NG reason providing unit can also refer to feedback from the target audience and suggest specific areas for improvement. The NG reason providing unit can also refer to feedback from the target audience and suggest specific areas for improvement. In this way, specific areas for improvement can be suggested by referring to feedback from the target audience.

[0079] The refusal reason providing unit can use the emotion estimation function to monitor the advertiser's emotional response to the refusal reason in real time and provide additional information to mitigate negative reactions. The refusal reason providing unit can, for example, use the emotion estimation function to monitor the advertiser's emotional response to the refusal reason in real time. For example, the refusal reason providing unit can analyze the advertiser's facial expressions and voice to calculate an emotion score. The refusal reason providing unit can also use the emotion estimation function to monitor the advertiser's emotional response to the refusal reason in real time and provide additional information to mitigate negative reactions. The refusal reason providing unit can also use the emotion estimation function to monitor the advertiser's emotional response to the refusal reason in real time and provide additional information to mitigate negative reactions. In this way, by monitoring the advertiser's emotional response to the refusal reason in real time and providing additional information to mitigate negative reactions, it is possible to improve advertiser satisfaction.

[0080] The rejection reason providing unit can suggest specific improvements regarding the visual design and layout. For example, the rejection reason providing unit uses a generation AI to analyze the visual design and layout of an advertisement and suggest specific improvements. For example, it can suggest improvements based on the use of color, font, layout balance, etc. The rejection reason providing unit can also suggest specific improvements regarding the visual design and layout. The rejection reason providing unit can also suggest specific improvements regarding the visual design and layout. In this way, by suggesting specific improvements regarding the visual design and layout, the quality of the advertisement can be improved.

[0081] The NG reason providing unit can suggest specific improvements regarding the audio content. For example, the NG reason providing unit uses a generation AI to analyze the audio content of an advertisement and suggest specific improvements. For example, the NG reason providing unit can suggest improvements based on the consistency of the tone of the audio or the message. The NG reason providing unit can also suggest specific improvements regarding the audio content. The NG reason providing unit can also suggest specific improvements regarding the audio content. In this way, by suggesting specific improvements regarding the audio content, the quality of the advertisement can be improved.

[0082] The NG reason providing unit can use the emotion estimation function to estimate the advertiser's emotion regarding the NG reason in real time and provide additional information for eliciting positive emotions. The NG reason providing unit can, for example, use the emotion estimation function to estimate the advertiser's emotion regarding the NG reason in real time. For example, the unit can analyze the advertiser's facial expressions and voice and calculate an emotion score. The NG reason providing unit can also use the emotion estimation function to estimate the advertiser's emotion regarding the NG reason in real time and provide additional information for eliciting positive emotions. The NG reason providing unit can also use the emotion estimation function to estimate the advertiser's emotion regarding the NG reason in real time and provide additional information for eliciting positive emotions. In this way, by estimating the advertiser's emotion regarding the NG reason in real time and providing additional information for eliciting positive emotions, it is possible to improve advertiser satisfaction.

[0083] The revision suggestion providing unit can refer to the advertiser's past revision history and suggest the most effective revision method. For example, the generation AI retrieves the advertiser's past revision history from a database and suggests the most effective revision method. For example, the revision suggestion providing unit presents a specific revision suggestion based on revision methods that have been successful in the past. The revision suggestion providing unit can also refer to the advertiser's past revision history and suggest the most effective revision method. The revision suggestion providing unit can also refer to the advertiser's past revision history and suggest the most effective revision method. In this way, the most effective revision method can be suggested by referring to the advertiser's past revision history.

[0084] The revision suggestion providing unit can take into account the attribute information of the target audience and present optimal revision suggestions for specific attributes. For example, the generation AI retrieves the attribute information of the target audience from a database and presents optimal revision suggestions for specific attributes. For example, the revision suggestion providing unit proposes revision suggestions based on data such as age, gender, and interests. The revision suggestion providing unit can also take into account the attribute information of the target audience and present optimal revision suggestions for specific attributes. The revision suggestion providing unit can also take into account the attribute information of the target audience and present optimal revision suggestions for specific attributes. In this way, by taking into account the attribute information of the target audience, it is possible to present optimal revision suggestions for specific attributes.

[0085] The revision suggestion providing unit can present specific revision suggestions regarding the visual design and layout. For example, the revision suggestion providing unit uses a generation AI to analyze the visual design and layout of an advertisement and presents specific revision suggestions. For example, the revision suggestion providing unit can propose revision suggestions based on the use of colors, fonts, layout balance, etc. The revision suggestion providing unit can also present specific revision suggestions regarding the visual design and layout. The revision suggestion providing unit can also present specific revision suggestions regarding the visual design and layout. In this way, by presenting specific revision suggestions regarding the visual design and layout, the quality of the advertisement can be improved.

[0086] The revision suggestion providing unit can present specific revision suggestions regarding the audio content. For example, the revision suggestion providing unit uses a generation AI to analyze the audio content of an advertisement and presents specific revision suggestions. For example, the revision suggestion providing unit can present specific revision suggestions regarding the audio content. The revision suggestion providing unit can also present specific revision suggestions regarding the audio content. In this way, by presenting specific revision suggestions regarding the audio content, the quality of the advertisement can be improved.

[0087] The revision suggestion providing unit may use an emotion estimation function to estimate the advertiser's emotion regarding the revision suggestion in real time, and provide additional information for eliciting positive emotions. The revision suggestion providing unit may, for example, use the emotion estimation function to estimate the advertiser's emotion regarding the revision suggestion in real time. For example, the revision suggestion providing unit may analyze the advertiser's facial expressions and voice to calculate an emotion score. The revision suggestion providing unit may also use the emotion estimation function to estimate the advertiser's emotion regarding the revision suggestion in real time, and provide additional information for eliciting positive emotions. The revision suggestion providing unit may also use the emotion estimation function to estimate the advertiser's emotion regarding the revision suggestion in real time, and provide additional information for eliciting positive emotions. In this way, by estimating the advertiser's emotion regarding the revision suggestion in real time and providing additional information for eliciting positive emotions, it is possible to improve advertiser satisfaction.

[0088] The ad content analysis unit can significantly improve the efficiency of ad review by using generative AI technology. The ad content analysis unit, for example, uses generative AI technology to automate the ad review process and review a large number of ads in a shorter time than manual review. For example, it analyzes the text and images of ads to check whether they contain inappropriate content. The ad content analysis unit can also significantly improve the efficiency of ad review by using generative AI technology. The ad content analysis unit can also significantly improve the efficiency of ad review by using generative AI technology. As a result, the use of generative AI technology can significantly improve the efficiency of ad review.

[0089] The advertisement content analysis unit can maintain consistency in the review criteria by using generative AI technology. The advertisement content analysis unit can, for example, dynamically adjust the review criteria by using generative AI technology to maintain consistency. For example, the review criteria can be adjusted based on past advertising history and performance data. The advertisement content analysis unit can also maintain consistency in the review criteria by using generative AI technology. The advertisement content analysis unit can also maintain consistency in the review criteria by using generative AI technology. As a result, the use of generative AI technology can maintain consistency in the review criteria.

[0090] The advertisement content analysis unit can improve the quality of advertisements by using generative AI technology. The advertisement content analysis unit, for example, builds a system for improving the quality of advertisements by using generative AI technology. For example, it analyzes the text and images of advertisements and checks whether they contain inappropriate content. The advertisement content analysis unit can also improve the quality of advertisements by using generative AI technology. The advertisement content analysis unit can also improve the quality of advertisements by using generative AI technology. In this way, the quality of advertisements can be improved by using generative AI technology.

[0091] The ad content analysis unit can use generative AI technology to reduce the workload on both advertisers and media operators. The ad content analysis unit, for example, uses generative AI technology to build a system to reduce the workload on both advertisers and media operators. For example, it can automate the ad review process, eliminating the need for manual review work. The ad content analysis unit can also use generative AI technology to reduce the workload on both advertisers and media operators. The ad content analysis unit can also use generative AI technology to reduce the workload on both advertisers and media operators. As a result, the use of generative AI technology can reduce the workload on both advertisers and media operators.

[0092] The ad content analysis unit can use generative AI technology to provide advertisers with specific reasons for rejection and suggested revisions in real time. The ad content analysis unit, for example, uses generative AI technology to build a system that provides advertisers with specific reasons for rejection and suggested revisions in real time. For example, it analyzes the text and images of an advertisement and presents a specific reason for rejection if the advertisement contains inappropriate content. The ad content analysis unit can also use generative AI technology to provide advertisers with specific reasons for rejection and suggested revisions in real time. The ad content analysis unit can also use generative AI technology to provide advertisers with specific reasons for rejection and suggested revisions in real time. In this way, by using generative AI technology, it is possible to provide advertisers with specific reasons for rejection and suggested revisions in real time.

[0093] The advertisement content analysis unit can provide specific feedback to advertisers using generative AI technology. The advertisement content analysis unit, for example, builds a system that provides specific feedback to advertisers using generative AI technology. For example, it analyzes the text and images of an advertisement and presents specific feedback if inappropriate content is included. The advertisement content analysis unit can also provide specific feedback to advertisers using generative AI technology. The advertisement content analysis unit can also provide specific feedback to advertisers using generative AI technology. In this way, specific feedback can be provided to advertisers by using generative AI technology.

[0094] By utilizing generative AI technology, the ad content analysis unit can reduce the workload on both advertisers and media operators. For example, by utilizing generative AI technology, the ad content analysis unit can build a system to reduce the workload on both advertisers and media operators. For example, by automating the ad review process, manual review work is no longer necessary. Furthermore, by utilizing generative AI technology, the ad content analysis unit can also reduce the workload on both advertisers and media operators. Furthermore, by utilizing generative AI technology, the ad content analysis unit can also reduce the workload on both advertisers and media operators. In this way, by utilizing generative AI technology, the workload on both advertisers and media operators can be reduced.

[0095] The ad content analysis unit utilizes generative AI technology to enable advertisers to receive specific reasons for rejection and suggested revisions in real time. The ad content analysis unit, for example, utilizes generative AI technology to build a system that enables advertisers to receive specific reasons for rejection and suggested revisions in real time. For example, it analyzes the text and images of an ad and presents a specific reason for rejection if the ad contains inappropriate content. The ad content analysis unit also utilizes generative AI technology to enable advertisers to receive specific reasons for rejection and suggested revisions in real time. The ad content analysis unit also utilizes generative AI technology to enable advertisers to receive specific reasons for rejection and suggested revisions in real time. As a result, by utilizing generative AI technology, advertisers can receive specific reasons for rejection and suggested revisions in real time.

[0096] By utilizing generative AI technology, the advertising content analysis unit eliminates the need for manual review work for media operators, allowing them to focus on other tasks. For example, by utilizing generative AI technology, the advertising content analysis unit builds a system that eliminates the need for manual review work for media operators, allowing them to focus on other tasks. For example, the advertising review process can be automated, eliminating the need for manual review work. Furthermore, by utilizing generative AI technology, the advertising content analysis unit eliminates the need for manual review work for media operators, allowing them to focus on other tasks. Furthermore, by utilizing generative AI technology, the advertising content analysis unit eliminates the need for manual review work for media operators, allowing them to focus on other tasks. Thus, by utilizing generative AI technology, the advertising content analysis unit eliminates the need for manual review work for media operators, allowing them to focus on other tasks.

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

[0098] The ad content analysis unit can analyze not only the visual elements of an ad but also the audio content of the ad to evaluate the consistency of the audio tone and message. For example, it checks whether the audio of the ad is in an appropriate tone for the target audience and whether the message is consistent. The ad content analysis unit can also evaluate the emotional impact of the audio content and prioritize approval of ads that evoke positive emotions. This can improve the quality of the audio content of ads and provide more effective ads to the target audience.

[0099] The advertisement content analysis unit can evaluate the visual design and layout of the advertisement and take visual appeal into consideration. For example, the evaluation is performed based on the color usage, font, layout balance, etc. The advertisement content analysis unit can also evaluate the visual design and layout of the advertisement and take visual appeal into consideration. In this way, by evaluating the visual design and layout, it is possible to approve visually appealing advertisements.

[0100] The advertisement content analysis unit can evaluate the suitability of the advertisement to specific attributes by taking into account attribute information of the target audience of the advertisement. For example, the evaluation is performed based on data such as age, gender, and interests. The advertisement content analysis unit can also evaluate whether the advertisement content is suitable for specific attributes by taking into account attribute information of the target audience. In this way, by taking into account attribute information of the target audience, the suitability of the advertisement can be improved.

[0101] The advertisement content analysis unit can use the emotion estimation function to evaluate the emotional impact of advertisement content on the target audience and preferentially approve advertisements that elicit positive emotions. For example, it can calculate an emotion score from the text and images of the advertisement and preferentially approve advertisements that elicit positive emotions. The advertisement content analysis unit can also use the emotion estimation function to evaluate the emotional impact of advertisement content on the target audience and preferentially approve advertisements that elicit positive emotions. In this way, by using the emotion estimation function, it is possible to preferentially approve advertisements that elicit positive emotions in the target audience.

[0102] The ad content analysis unit can refer to the advertiser's past advertising history and dynamically adjust the screening criteria based on performance data. For example, the generation AI retrieves the advertiser's past advertising history from a database and analyzes the performance data of past ads. For example, the screening criteria can be dynamically adjusted based on data such as click-through rate and conversion rate. The ad content analysis unit can also refer to the advertiser's past advertising history and adjust the screening criteria based on past successful and unsuccessful advertising examples. This enables more effective ad screening by dynamically adjusting the screening criteria based on the advertiser's past advertising history and performance data.

[0103] The review result providing unit can provide individually customized feedback by referring to the advertiser's past feedback history. For example, the generation AI retrieves the advertiser's past feedback history from a database and provides individually customized feedback. For example, specific improvements can be suggested based on the content of the past feedback. The review result providing unit can also provide individually customized feedback by referring to the advertiser's past feedback history. As a result, individually customized feedback can be provided by referring to the advertiser's past feedback history.

[0104] The review result providing unit can use the emotion estimation function to estimate the advertiser's emotion regarding the review result in real time and provide additional information to elicit positive emotions. For example, the emotion estimation function can be used to analyze the advertiser's facial expressions and voice and calculate an emotion score. The review result providing unit can also use the emotion estimation function to estimate the advertiser's emotion regarding the review result in real time and provide additional information to elicit positive emotions. This can improve the advertiser's satisfaction by estimating the advertiser's emotion regarding the review result in real time and providing additional information to elicit positive emotions.

[0105] The NG reason providing unit can refer to the advertiser's past history of NG reasons and provide advice to avoid similar problems. For example, the generation AI retrieves the advertiser's past history of NG reasons from a database and provides advice to avoid similar problems. For example, it suggests specific areas for improvement based on the reasons for past NGs. The NG reason providing unit can also refer to the advertiser's past history of NG reasons and provide advice to avoid similar problems. By referring to the advertiser's past history of NG reasons, advice to avoid similar problems can be provided.

[0106] The NG reason providing unit can use the emotion estimation function to monitor the advertiser's emotional response to the NG reason in real time and provide additional information to mitigate negative reactions. For example, the unit can analyze the advertiser's facial expressions and voice and calculate an emotion score. The NG reason providing unit can also use the emotion estimation function to monitor the advertiser's emotional response to the NG reason in real time and provide additional information to mitigate negative reactions. In this way, by monitoring the advertiser's emotional response to the NG reason in real time and providing additional information to mitigate negative reactions, it is possible to improve advertiser satisfaction.

[0107] The revision suggestion providing unit can refer to the advertiser's past revision history and suggest the most effective revision method. For example, the generation AI retrieves the advertiser's past revision history from a database and suggests the most effective revision method. For example, it presents specific revision suggestions based on revision methods that have been successful in the past. The revision suggestion providing unit can also refer to the advertiser's past revision history and suggest the most effective revision method. In this way, the most effective revision method can be suggested by referring to the advertiser's past revision history.

[0108] The processing flow of the second embodiment will be briefly explained below.

[0109] Step 1: The advertisement content analysis unit analyzes the advertisement content. For example, the advertisement content analysis unit analyzes the text and images of the advertisement to check whether they contain inappropriate content. The advertisement content analysis unit can also analyze the video of the advertisement to detect inappropriate scenes within the video. Furthermore, the advertisement content analysis unit can analyze the audio content of the advertisement to check whether they contain inappropriate language. Step 2: The review result providing unit provides the review result based on the advertisement content analyzed by the advertisement content analysis unit. For example, the review result providing unit displays the result in the form of "This advertisement has been approved" or "This advertisement has not been approved." The review result providing unit can also provide the review result in real time and notify the advertiser of the review result. Step 3: The NG reason providing unit provides a specific NG reason based on the review results provided by the review result providing unit. For example, the NG reason providing unit indicates a specific reason such as "This advertisement contains inappropriate language" or "This image infringes copyright." The NG reason providing unit can also explain the NG reason in detail and notify the advertiser. Step 4: The revision suggestion providing unit provides a revision suggestion based on the rejection reason provided by the rejection reason providing unit. For example, the revision suggestion providing unit suggests specific revision suggestions such as "replace this word with another word" or "delete this image." The revision suggestion providing unit can also explain the revision suggestion in detail and notify the advertiser.

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

[0111] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0112] 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.

[0113] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0114] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0115] 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.

[0116] 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.

[0117] 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.

[0118] 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).

[0119] 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.

[0120] 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.

[0121] 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.

[0122] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0123] 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. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0124] 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.

[0125] 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.

[0126] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0127] 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.

[0128] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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).

[0134] 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.

[0135] 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.

[0136] 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.

[0137] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0138] 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 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0139] 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.

[0140] 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.

[0141] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0142] 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.

[0143] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0144] 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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).

[0149] 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.

[0150] 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.

[0151] 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.

[0152] 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.

[0153] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0154] In the robot 414, the processor 46 performs the identification process. 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. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0155] 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.

[0156] 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.

[0157] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0158] 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.

[0159] 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.

[0160] 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.

[0161] 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.

[0162] 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).

[0163] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the 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.

[0164] 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."

[0165] 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.

[0166] 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.

[0167] 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.

[0168] 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.

[0169] 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.

[0170] 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.

[0171] 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.

[0172] 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.

[0173] 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.

[0174] 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.

[0175] 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.

[0176] 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. [Explanation of symbols]

[0177] 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 advertisement content analysis unit that analyzes advertisement content; an examination result providing unit that provides examination results based on the advertisement content analyzed by the advertisement content analysis unit; a rejection reason providing unit that provides a specific rejection reason based on the examination result provided by the examination result providing unit; a correction proposal providing unit that provides a correction proposal based on the NG reason provided by the NG reason providing unit; A system characterized by:

2. The advertisement content analysis unit Evaluate the emotional impact of said advertising content on the target audience and prioritize approval of ads that elicit positive emotions 2. The system of claim 1.

3. The examination result providing unit View advertisers' past feedback history and provide personalized feedback 2. The system of claim 1.

4. The NG reason providing unit Refer to the advertiser's past rejection history and provide advice on how to avoid similar issues 2. The system of claim 1.

5. The revision suggestion providing unit: Refer to the advertiser's past revision history and suggest the most effective revision method 2. The system of claim 1.

6. The advertisement content analysis unit Estimates real-time sentiment when advertisers submit their ads and provides feedback to elicit positive sentiment.

2. The system of claim 1.

7. The examination result providing unit Monitor advertisers' emotional responses to the review results in real time and provide additional information to mitigate negative reactions.

2. The system of claim 1.

8. The NG reason providing unit Monitor advertisers' emotional responses to the reasons for rejection in real time and provide additional information to mitigate negative reactions.

2. The system of claim 1.

Images