system

Abstract

The system according to this embodiment aims to analyze past advertising results and generate and deliver advertising text that is optimal for the target audience. [Solution] The system according to the embodiment comprises a collection unit, an analysis unit, a generation unit, a verification unit, and an optimization unit. The collection unit collects past advertising results. The analysis unit analyzes the advertising results collected by the collection unit. The generation unit generates text that is optimal for the target based on the analysis results obtained by the analysis unit. The verification unit delivers advertisements using the text generated by the generation unit and verifies their effectiveness. The optimization unit improves and optimizes the advertising text based on the results obtained by the verification unit.

Description

Technical Field

[0003]

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, including steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of the chatbot's character, encoding the prompt, and inputting the encoded prompt into a language model to generate a chatbot utterance in response to the user utterance.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the prior art, the past advertising results have not been effectively utilized to generate the optimal advertising text for the target, and there is room for improvement.

[0005] The system according to the embodiment aims to analyze past advertising results and generate and distribute the optimal advertising text for the target.

Means for Solving the Problems

[0006] The system according to this embodiment comprises a collection unit, an analysis unit, a generation unit, a verification unit, and an optimization unit. The collection unit collects past advertising results. The analysis unit analyzes the advertising results collected by the collection unit. The generation unit generates text that is optimal for the target audience based on the analysis results obtained by the analysis unit. The verification unit delivers advertisements using the text generated by the generation unit and verifies their effectiveness. The optimization unit improves and optimizes the advertising text based on the results obtained by the verification unit. [Effects of the Invention]

[0007] The system according to this embodiment can analyze past advertising results and generate and deliver advertising text that is optimal for the target audience. [Brief explanation of the drawing]

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

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

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

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

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

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

[0014] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor, an antenna, and the like. The communication I / F manages communication between a plurality of computers. Examples of communication standards applicable to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B". That is, "A and / or B" means that it may be only A, only B, or a combination of A and B. Also, in this specification, when expressing three or more matters connected by "and / or", the same concept as "A and / or B" is applied.

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example of form 1) An advertising text generation system according to an embodiment of the present invention is a system that reads past advertising effectiveness by gender, age group, etc., and generates optimal text tailored to the target audience. The advertising text generation system reads past advertising results categorized by gender, age group, etc., and the AI ​​analyzes this data to generate optimal text for the target audience. For example, the AI ​​reads text with good and bad performance in electronic advertising and identifies which words are effective. By repeating this process and running a PDCA cycle, the effectiveness of advertising appeals is improved. First, past advertising results are read categorized by gender, age group, etc. At this time, detailed data such as the click-through rate and conversion rate of the advertisements are collected. For example, data for advertisements targeting women in their 20s and advertisements targeting men in their 30s are collected separately. This makes it possible to understand the advertising effectiveness for each target audience. Next, the AI ​​analyzes the collected data. Based on the collected data, the AI ​​generates optimal text for the target audience. For example, the AI ​​identifies that words such as "trend" and "stylish" are effective in advertisements targeting women in their 20s. This makes it possible to generate personalized advertising text tailored to the target audience. Furthermore, the advertisement is delivered using the generated text and its effectiveness is verified. For example, ads using AI-generated text are delivered, and click-through rates and conversion rates are measured. This allows for evaluation of the effectiveness of the generated text. Finally, based on the results of the effectiveness verification, the ad text is improved and optimized. For example, if the click-through rate is low, the AI-generated text is revised, and the ad is delivered again. By repeating this process and running the PDCA cycle, the effectiveness of the ad appeal is improved. This mechanism allows for the generation of optimal ad text tailored to the target audience, thereby improving the effectiveness of the ad appeal. For example, by reading both high-performing and low-performing texts from electronic advertising and having the AI ​​identify which words are effective, more effective ads can be delivered. In this way, the ad text generation system can generate optimal ad text tailored to the target audience, improving the effectiveness of the ad appeal.

[0029] The advertising text generation system according to this embodiment comprises a collection unit, an analysis unit, a generation unit, a verification unit, and an optimization unit. The collection unit collects past advertising results. The collection unit can collect detailed data such as click-through rates and conversion rates of advertisements. For example, the collection unit collects click-through rates of advertisements to identify which advertisement was clicked the most. The collection unit can also collect conversion rates to identify which advertisement was the most effective. Furthermore, the collection unit can collect the number of times an advertisement was displayed to identify which advertisement was displayed the most. The analysis unit analyzes the advertising results collected by the collection unit. The analysis unit can analyze the collected data using, for example, data mining techniques. For example, the analysis unit can analyze patterns in click-through rates and conversion rates of advertisements using data mining techniques. Furthermore, the analysis unit can also analyze the collected data using statistical analysis techniques. For example, the analysis unit can quantitatively evaluate the effectiveness of advertisements using statistical analysis techniques. Furthermore, the analysis unit can also analyze the collected data using machine learning algorithms. For example, the analysis unit uses machine learning algorithms to build a model that predicts the effectiveness of advertisements. The generation unit generates text that is optimal for the target based on the analysis results obtained by the analysis unit. The generation unit can generate optimal text based on, for example, the attributes of the target user. For example, the generation unit generates optimal text based on the gender and age of the target user. The generation unit can also generate optimal text based on past advertising effectiveness. For example, the generation unit analyzes past advertising effectiveness, identifies the most effective words, and uses them to generate text. Furthermore, the generation unit can generate optimal text using AI. For example, the generation unit uses text generation AI (e.g., LLM) to generate text that is optimal for the target. The verification unit delivers advertisements using the text generated by the generation unit and verifies their effectiveness. For example, the verification unit can deliver advertisements using the generated text and measure click-through rates and conversion rates. For example, the verification unit delivers advertisements using the generated text and measures click-through rates.Furthermore, the verification unit can deliver advertisements using the generated text and measure the conversion rate. The verification unit can also deliver advertisements using the generated text and collect user feedback. For example, the verification unit can collect user feedback and evaluate the effectiveness of the advertisement. The optimization unit improves and optimizes the advertisement text based on the results obtained by the verification unit. For example, the optimization unit can modify the advertisement text based on the verification results. For example, if the click-through rate is low, the optimization unit can modify the text and deliver the advertisement again. The optimization unit can also modify the text and deliver the advertisement again if the conversion rate is low. Furthermore, the optimization unit can modify the advertisement text based on user feedback. For example, the optimization unit can modify the text based on user feedback and deliver the advertisement again. As a result, the advertisement text generation system according to this embodiment can generate optimal advertisement text tailored to the target audience and improve the effectiveness of the advertisement.

[0030] The data collection unit collects past advertising results. For example, it can collect detailed data such as click-through rates and conversion rates. Specifically, it meticulously records the number of times an ad was displayed, the number of clicks, and the number of conversions (purchases, registrations, etc.) after clicks. This allows for the identification of which ads received the most clicks and which were the most effective. Furthermore, the data collection unit also collects metadata such as the time of day and day of the week the ad was displayed, and the device on which it was displayed (smartphone, tablet, PC, etc.). This enables the analysis of advertising effectiveness at specific times and on specific devices. The data collection unit centrally manages this data and stores it in a database. The database is updated in real time and made accessible to the analysis and generation units. Additionally, the data collection unit can integrate with external advertising platforms and analytics tools to collect a broader range of data. For example, it can collect data from social media advertising and search engine advertising to evaluate overall advertising effectiveness. This allows the data collection unit to gather detailed advertising results from diverse data sources, strengthening the overall data infrastructure of the system.

[0031] The analysis unit analyzes the advertising results collected by the data collection unit. For example, the analysis unit can analyze the collected data using data mining techniques. Specifically, it can use data mining techniques to analyze patterns in ad click-through rates and conversion rates to identify which factors contribute to advertising effectiveness. The analysis unit can also analyze the collected data using statistical analysis techniques. For example, it can use statistical analysis techniques to quantitatively evaluate the effectiveness of ads and calculate confidence intervals and statistical significance. Furthermore, the analysis unit can analyze the collected data using machine learning algorithms. For example, it can use machine learning algorithms to build models that predict the effectiveness of ads and forecast future advertising effectiveness. Specifically, it can use regression analysis, clustering, and classification algorithms to create models that predict ad click-through rates and conversion rates. Additionally, the analysis unit can use natural language processing techniques to analyze the content of ad text and identify effective keywords and phrases. This allows the analysis unit to analyze the collected data from multiple perspectives and provide insights to maximize advertising effectiveness.

[0032] The generation unit generates text optimized for the target based on the analysis results obtained by the analysis unit. For example, the generation unit can generate optimal text based on the attributes of the target user. Specifically, it generates optimal advertising text based on data such as the target user's gender, age, interests, and past behavioral history. The generation unit can also generate optimal text based on past advertising effectiveness. For example, it analyzes past advertising effectiveness to identify the most effective words and phrases and uses them to generate text. Furthermore, the generation unit can also generate optimal text using AI. Specifically, it uses text generation AI (e.g., LLM) to generate text optimized for the target. The generation AI receives past advertising data and target user attribute data as input and generates optimal advertising text. The generated text is designed to attract the target user's interest and encourage action. This allows the generation unit to quickly generate optimal advertising text tailored to the target and maximize advertising effectiveness.

[0033] The verification unit delivers advertisements using text generated by the generation unit and verifies their effectiveness. For example, the verification unit can deliver advertisements using the generated text and measure click-through rates and conversion rates. Specifically, it can deliver advertisements using the generated text on multiple platforms and compare the click-through rates and conversion rates on each platform. The verification unit can also deliver advertisements using the generated text and collect user feedback. For example, it can conduct surveys with users who clicked on the advertisements to collect opinions on the content and appeal of the advertisements. Furthermore, the verification unit can conduct A / B testing to compare the effectiveness of different versions of the advertisement text. This allows it to identify which version of the text is most effective. Based on this data, the verification unit quantitatively evaluates the effectiveness of the advertisement text and provides information for formulating the optimal advertising strategy.

[0034] The optimization unit improves and optimizes ad text based on the results obtained by the verification unit. For example, the optimization unit can revise ad text based on verification results. Specifically, if the click-through rate is low, it will review the content and structure of the text and revise it to make it more appealing. Also, if the conversion rate is low, it will strengthen the appeal points and call to action in the text. Furthermore, the optimization unit can also revise ad text based on user feedback. For example, it will adjust the content of the ad text to reflect user opinions. The optimization unit makes these revisions quickly and delivers the ads again to continuously improve advertising effectiveness. In addition, the optimization unit can automate the ad text optimization process using machine learning algorithms. For example, it can build an algorithm that learns from past verification results and automatically generates optimal revision suggestions. This allows the optimization unit to efficiently improve ad text and maximize advertising effectiveness.

[0035] The data collection unit can collect detailed data such as click-through rates and conversion rates for advertisements. For example, the data collection unit can collect click-through rates to identify which advertisement was clicked the most. It can also collect conversion rates to identify which advertisement was most effective. Furthermore, the data collection unit can collect the number of impressions to identify which advertisement was displayed the most. This improves the accuracy of advertisement effectiveness analysis by collecting detailed data. Detailed data includes, but is not limited to, click-through rates, conversion rates, and time spent on the page. Some or all of the processing described above in the data collection unit may be performed using AI, for example, or not. For example, the data collection unit can input data on click-through rates and conversion rates for advertisements into an AI, which can then collect the data.

[0036] The analysis unit can identify the most suitable words for the target audience based on the collected data. For example, the analysis unit can use data mining techniques to analyze the collected data and identify the most suitable words for the target audience. For instance, the analysis unit can use data mining techniques to analyze patterns in ad click-through rates and conversion rates and identify the most suitable words. Furthermore, the analysis unit can use statistical analysis techniques to analyze the collected data and identify the most suitable words for the target audience. For example, the analysis unit can use statistical analysis techniques to quantitatively evaluate the effectiveness of ads and identify the most suitable words. Additionally, the analysis unit can use machine learning algorithms to analyze the collected data and identify the most suitable words for the target audience. For example, the analysis unit can use machine learning algorithms to build a model that predicts the effectiveness of ads and identify the most suitable words. This improves the effectiveness of ad text by identifying the most suitable words for the target audience. Optimal words include, but are not limited to, frequently occurring keywords and highly relevant words. Some or all of the above-described processes in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input the collected data into an AI, which can then identify the most suitable words.

[0037] The generation unit can generate text that is optimal for the target using specified words. For example, the generation unit can generate optimal text based on the attributes of the target user. For example, the generation unit can generate optimal text based on the gender and age of the target user. The generation unit can also generate optimal text based on past advertising effectiveness. For example, the generation unit can analyze past advertising effectiveness, identify the most effective words, and use them to generate text. Furthermore, the generation unit can also generate optimal text using AI. For example, the generation unit can use text generation AI (e.g., LLM) to generate text that is optimal for the target. This improves the effectiveness of advertising by generating text that is optimal for the target. Optimal text includes, but is not limited to, the attributes of the target user and past advertising effectiveness. Some or all of the above processes in the generation unit may be performed using, for example, AI, or not using AI. For example, the generation unit can input specified words into AI, and the AI ​​can generate optimal text.

[0038] The verification unit can deliver advertisements using the generated text and measure click-through rates and conversion rates. For example, the verification unit can deliver advertisements using the generated text and measure click-through rates. The verification unit can also deliver advertisements using the generated text and measure conversion rates. Furthermore, the verification unit can deliver advertisements using the generated text and collect user feedback. For example, the verification unit can collect user feedback and evaluate the effectiveness of the advertisements. This allows for accurate measurement of the effectiveness of the advertisements and identification of areas for improvement in the text. Click-through rates and conversion rates include, but are not limited to, the number of clicks and completed purchases within a specific period. Some or all of the above processes in the verification unit may be performed using AI, for example, or not. For example, the verification unit can input data on click-through rates and conversion rates of advertisements using the generated text into an AI, which can then analyze the data.

[0039] The optimization unit can modify the ad text based on the verification results and deliver the ad again. For example, if the click-through rate is low, the optimization unit can modify the text and deliver the ad again. For example, if the conversion rate is low, the optimization unit can also modify the text and deliver the ad again. Furthermore, the optimization unit can also modify the ad text based on user feedback. For example, the optimization unit can modify the text based on user feedback and deliver the ad again. This allows for continuous improvement of the ad text, maximizing the effectiveness of the ads. Modifying the ad text includes, but is not limited to, changing wording or adding keywords. Some or all of the above processes in the optimization unit may be performed using, for example, AI, or not using AI. For example, the optimization unit can input the verification results into AI, which can then modify the ad text.

[0040] The data collection unit can select the types of data to collect based on the ad display environment (device, time of day, location, etc.). For example, when an ad is displayed on a mobile device, the data collection unit can collect click-through rates and scroll speeds. For example, when an ad is displayed at night, the data collection unit can also collect viewing time and conversion rates. Furthermore, when an ad is displayed in a specific region, the data collection unit can collect geographic location information and analyze the ad's effectiveness by region. This enables a detailed analysis of ad effectiveness by collecting data according to the display environment. The display environment includes, but is not limited to, device type, time of day, and location. Some or all of the processing described above in the data collection unit may be performed using AI, for example, or not. For example, the data collection unit can input ad display environment data into AI and select the types of data that AI should collect.

[0041] The data collection unit can also collect user behavior data such as ad viewing time and scrolling speed, enabling a detailed analysis of ad effectiveness. For example, the data collection unit can measure ad viewing time and analyze which parts attracted the most attention. For example, the data collection unit can collect user scrolling speed to identify at which part of the ad users lost interest. Furthermore, the data collection unit can collect user click patterns and analyze which elements were most effective. This allows for a detailed analysis of ad effectiveness by collecting user behavior data. User behavior data includes, but is not limited to, viewing time, scrolling speed, and click patterns. Some or all of the processing described above in the data collection unit may be performed using AI, for example, or not. For example, the data collection unit can input data on ad viewing time and scrolling speed into an AI, which can then collect the data.

[0042] The data collection unit can collect advertising data from different platforms, such as social media and news sites, and evaluate the overall effectiveness of advertising. For example, the data collection unit can collect advertising data from social media and analyze engagement rates. For example, the data collection unit can also collect advertising data from news sites and compare click-through rates and conversion rates. Furthermore, the data collection unit can integrate data from different platforms and evaluate the overall effectiveness of advertising. This makes it possible to evaluate the overall effectiveness of advertising by collecting data from different platforms. Different platforms include, but are not limited to, social media, news sites, and blogs. Some or all of the processing described above in the data collection unit may be performed using AI, for example, or not. For example, the data collection unit can input data from social media and news sites into an AI, which can then collect the data.

[0043] The data collection unit can collect advertising effectiveness by region, taking into account the geographical location information of the ad viewers. For example, the data collection unit can collect geographical location information when an ad is displayed in a specific region and analyze the click-through rate by region. The data collection unit can also collect conversion rates by region and evaluate differences in advertising effectiveness. Furthermore, the data collection unit can compare advertising effectiveness by region based on geographical location information and formulate the optimal advertising strategy. This makes it possible to conduct a detailed analysis of advertising effectiveness by region by considering geographical location information. Geographical location information includes, but is not limited to, IP addresses and GPS data. Some or all of the above processing in the data collection unit may be performed using, for example, AI, or not using AI. For example, the data collection unit can input the geographical location information of the ad viewers into AI, and the AI ​​can collect the data.

[0044] The analysis unit can analyze detailed user behavior data, such as ad viewing time and click patterns, to identify factors influencing ad effectiveness. For example, the analysis unit can analyze ad viewing time to identify which parts received the most attention. The analysis unit can also analyze click patterns to identify which elements were most effective. Furthermore, the analysis unit can analyze user behavior data to identify factors influencing ad effectiveness. This allows for the identification of factors influencing ad effectiveness by analyzing detailed user behavior data. Detailed user behavior data includes, but is not limited to, viewing time, click patterns, and scroll speed. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input data on ad viewing time and click patterns into an AI, which can then analyze the data.

[0045] The analysis unit can apply different analysis methods based on the ad display environment (device, time of day, location, etc.). For example, when an ad is displayed on a mobile device, the analysis unit can analyze the click-through rate and scroll speed. For example, when an ad is displayed at night, the analysis unit can also analyze the viewing time and conversion rate. Furthermore, when an ad is displayed in a specific region, the analysis unit can analyze geographic location information and analyze the ad's effectiveness for that region. This allows for a detailed analysis of ad effectiveness by applying analysis methods appropriate to the display environment. The display environment includes, but is not limited to, device type, time of day, and location. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input ad display environment data into AI, and the AI ​​can apply analysis methods.

[0046] The analysis unit can analyze the effectiveness of advertisements by region, taking into account the geographical location information of the ad viewers. For example, when an ad is displayed in a specific region, the analysis unit can analyze geographical location information and analyze the click-through rate for that region. The analysis unit can also analyze conversion rates by region and evaluate differences in advertising effectiveness. Furthermore, based on geographical location information, the analysis unit can compare the effectiveness of advertisements by region and formulate the optimal advertising strategy. This makes it possible to conduct a detailed analysis of advertising effectiveness by region by considering geographical location information. Geographical location information includes, but is not limited to, IP addresses and GPS data. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the geographical location information of the ad viewers into AI, and the AI ​​can analyze the data.

[0047] The analytics unit can analyze data from different platforms, such as social media and news sites, to evaluate overall advertising effectiveness. For example, the analytics unit can analyze data from social media to evaluate engagement rates. It can also analyze data from news sites to compare click-through rates and conversion rates. Furthermore, the analytics unit can integrate data from different platforms to evaluate overall advertising effectiveness. This makes it possible to evaluate overall advertising effectiveness by analyzing data from different platforms. Different platforms include, but are not limited to, social media, news sites, and blogs. Some or all of the above processing in the analytics unit may be performed using AI, for example, or not. For example, the analytics unit can input data from social media and news sites into an AI, which can then analyze the data.

[0048] The generation unit can customize the content of the text it generates based on the ad's display environment (device, time of day, location, etc.). For example, when an ad is displayed on a mobile device, the generation unit can generate short, concise text. For example, when an ad is displayed at night, the generation unit can also generate text with a relaxed tone. Furthermore, when an ad is displayed in a specific region, the generation unit can generate text that is tailored to the local culture and customs. This improves the effectiveness of the ad by customizing the text according to the display environment. The display environment includes, but is not limited to, the type of device, time of day, and location. Some or all of the processing described above in the generation unit may be performed using AI, for example, or not. For example, the generation unit can input ad display environment data into AI, and the AI ​​can customize the text content.

[0049] The generation unit can generate personalized text based on the past behavioral data of the ad viewer. For example, the generation unit can generate engaging text based on data of ads the user has clicked in the past. The generation unit can also generate text about related products based on the user's past purchase history. Furthermore, the generation unit can generate text about engaging content based on the user's past browsing history. This enables personalized advertising by generating text based on past behavioral data. Past behavioral data includes, but is not limited to, click history, purchase history, and browsing history. Some or all of the above processing in the generation unit may be performed using, for example, AI, or not using AI. For example, the generation unit can input the past behavioral data of the ad viewer into AI, and the AI ​​can generate personalized text.

[0050] The generation unit can generate optimal text for each region, taking into account the geographical location information of the ad viewers. For example, when displaying an ad in a specific region, the generation unit can generate text that is tailored to the local culture and customs. The generation unit can also generate optimal text, taking into account the local language and dialect. Furthermore, the generation unit can generate text that maximizes the effectiveness of the ad in each region based on geographical location information. This allows for the generation of optimal ad text for each region by considering geographical location information. Geographical location information includes, but is not limited to, IP addresses and GPS data. Some or all of the above processing in the generation unit may be performed using, for example, AI, or not. For example, the generation unit can input the geographical location information of the ad viewers into AI, and the AI ​​can generate optimal text.

[0051] The generation unit can generate text suitable for different platforms, such as social media and news sites. For example, for social media, the generation unit can generate short, visually appealing text. For news sites, the generation unit can also generate text containing detailed information. Furthermore, the generation unit can generate optimal text for each different platform, maximizing advertising effectiveness. This maximizes advertising effectiveness by generating text suitable for different platforms. Different platforms include, but are not limited to, social media, news sites, and blogs. Some or all of the processing described above in the generation unit may be performed using AI, for example, or not. For example, the generation unit can input data from social media and news sites into an AI, which can then generate optimal text.

[0052] The verification unit can collect verification data based on the ad display environment (device, time of day, location, etc.) and perform detailed effectiveness analysis. For example, when an ad is displayed on a mobile device, the verification unit can verify the click-through rate and scroll speed. For example, when an ad is displayed at night, the verification unit can also verify the viewing time and conversion rate. Furthermore, when an ad is displayed in a specific region, the verification unit can verify geographical location information and analyze the effectiveness of the ad for each region. This enables a detailed analysis of ad effectiveness by collecting verification data according to the display environment. The display environment includes, but is not limited to, device type, time of day, and location. Some or all of the above processing in the verification unit may be performed using AI, for example, or without AI. For example, the verification unit can input ad display environment data into AI, and the AI ​​can collect verification data.

[0053] The verification unit can build a predictive model for advertising effectiveness based on past behavioral data of the ad's audience. For example, the verification unit can build a predictive model for advertising effectiveness based on the user's past click data. The verification unit can also build a predictive model for conversion rates based on the user's past purchase history. Furthermore, the verification unit can build a predictive model for viewing time based on the user's past browsing history. This makes it possible to predict advertising effectiveness by building a predictive model based on past behavioral data. Past behavioral data includes, but is not limited to, click history, purchase history, and browsing history. Some or all of the above processing in the verification unit may be performed using AI, for example, or without AI. For example, the verification unit can input past behavioral data of the ad's audience into AI, and the AI ​​can build a predictive model for advertising effectiveness.

[0054] The verification unit can verify the effectiveness of advertisements by region, taking into account the geographical location information of the ad viewers. For example, the verification unit can verify geographical location information when an ad is displayed in a specific region and analyze the click-through rate for each region. The verification unit can also verify conversion rates by region and evaluate differences in advertising effectiveness. Furthermore, the verification unit can compare the effectiveness of advertisements by region based on geographical location information and formulate the optimal advertising strategy. This makes it possible to conduct a detailed analysis of advertising effectiveness by region by considering geographical location information. Geographical location information includes, but is not limited to, IP addresses and GPS data. Some or all of the above processing in the verification unit may be performed using AI, for example, or without AI. For example, the verification unit can input the geographical location information of the ad viewers into AI, and the AI ​​can verify the data.

[0055] The verification unit can verify the effectiveness of advertising on different platforms, such as social media and news sites. For example, the verification unit can verify the effectiveness of advertising on social media and evaluate the engagement rate. For example, the verification unit can also verify the effectiveness of advertising on news sites and compare click-through rates and conversion rates. Furthermore, the verification unit can verify the effectiveness of advertising on each different platform and perform an overall evaluation. This makes it possible to evaluate the overall effectiveness of advertising by verifying the effectiveness of advertising on different platforms. Different platforms include, but are not limited to, social media, news sites, and blogs. Some or all of the above processing in the verification unit may be performed using AI, for example, or not using AI. For example, the verification unit can input data from social media and news sites into AI, and the AI ​​can verify the data.

[0056] The optimization unit can apply an optimization algorithm based on the ad display environment (device, time of day, location, etc.). For example, when displaying an ad on a mobile device, the optimization unit optimizes the text to be short and to the point. For example, when displaying an ad at night, the optimization unit can also optimize the text to have a relaxed tone. Furthermore, when displaying an ad in a specific region, the optimization unit can optimize the text to suit the local culture and customs. This improves the effectiveness of the ad by applying an optimization algorithm according to the display environment. The display environment includes, but is not limited to, the type of device, time of day, and location. Some or all of the above processing in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input the ad display environment data into AI, and the AI ​​can apply the optimization algorithm.

[0057] The optimization unit can perform personalized optimization based on the past behavioral data of the ad viewers. For example, the optimization unit can optimize the text of ads that users have clicked on in the past. The optimization unit can also optimize the text of related products based on the user's past purchase history. Furthermore, the optimization unit can optimize the text of content that users are interested in based on their past browsing history. This enables personalized advertising by optimizing based on past behavioral data. Past behavioral data includes, but is not limited to, click history, purchase history, and browsing history. Some or all of the above processing in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input the past behavioral data of the ad viewers into AI, which can then perform personalized optimization.

[0058] The optimization unit can provide optimal ad text for each region by considering the geographical location information of the ad viewers. For example, when displaying an ad in a specific region, the optimization unit can provide text that is tailored to the local culture and customs. The optimization unit can also provide optimal text by considering the local language and dialect. Furthermore, the optimization unit can provide text that maximizes the advertising effect for each region based on geographical location information. In this way, by considering geographical location information, the optimization unit can provide optimal ad text for each region. Geographical location information includes, but is not limited to, IP addresses and GPS data. Some or all of the above processing in the optimization unit may be performed using, for example, AI, or not using AI. For example, the optimization unit can input the geographical location information of the ad viewers into AI, and the AI ​​can provide optimal ad text.

[0059] The optimization unit can perform optimizations suitable for different platforms, such as social media and news sites. For example, the optimization unit can optimize short, visually appealing text for social media. For example, the optimization unit can also optimize text containing detailed information for news sites. Furthermore, the optimization unit can optimize the text to be optimal for each different platform, maximizing advertising effectiveness. This maximizes advertising effectiveness by performing optimizations suitable for different platforms. Different platforms include, but are not limited to, social media, news sites, and blogs. Some or all of the processing described above in the optimization unit may be performed using AI, for example, or not. For example, the optimization unit can input data from social media and news sites into AI, which can then optimize the text to be optimal.

[0060] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0061] An ad text generation system can adjust the frequency of ad delivery based on a user's past behavioral data. For example, it can frequently deliver similar ads based on data of ads a user has clicked frequently in the past. Furthermore, it can increase the frequency of ads for related products based on data of products a user has purchased in the past. By adjusting the frequency of ad delivery based on past behavioral data, advertising effectiveness is improved. Past behavioral data includes, but is not limited to, click history, purchase history, and browsing history. Some or all of the above processing in the ad text generation system may be performed using AI, for example, or without AI. For example, the ad text generation system can input the user's past behavioral data into AI, which can then adjust the frequency of ad delivery.

[0062] The ad text generation system can adjust the timing of ad delivery based on the ad's display environment (device, time of day, location, etc.). For example, when an ad is displayed on a mobile device, it can deliver a short, concise ad. When an ad is displayed at night, it can deliver an ad with a relaxed tone. Furthermore, when an ad is displayed in a specific region, it can deliver an ad tailored to the local culture and customs. This improves ad effectiveness by adjusting the timing of ad delivery according to the display environment. The display environment includes, but is not limited to, device type, time of day, and location. Some or all of the above processing in the ad text generation system may be performed using AI, for example, or not. For example, the ad text generation system can input ad display environment data into AI, which can then adjust the timing of ad delivery.

[0063] The ad text generation system can generate optimal ad text for each region by considering the geographical location information of the ad viewers. For example, when displaying an ad in a specific region, it can generate text that is tailored to the local culture and customs. It can also generate optimal text considering the local language and dialect. Furthermore, it can generate text that maximizes the effectiveness of the ad in each region based on geographical location information. In this way, by considering geographical location information, it is possible to generate optimal ad text for each region. Geographical location information includes, but is not limited to, IP addresses and GPS data. Some or all of the above processing in the ad text generation system may be performed using AI, for example, or not using AI. For example, the ad text generation system can input the geographical location information of the ad viewers into AI, and the AI ​​can generate optimal text.

[0064] The advertising text generation system can generate text suitable for different platforms, such as social media and news sites. For example, it can generate short, visually appealing text for social media, and text containing detailed information for news sites. Furthermore, it can generate optimal text for each different platform, maximizing advertising effectiveness. This maximizes advertising effectiveness by generating text suitable for different platforms. Different platforms include, but are not limited to, social media, news sites, and blogs. Some or all of the above processing in the advertising text generation system may be performed using AI, for example, or not. For example, the advertising text generation system can input data from social media and news sites into an AI, which can then generate the optimal text.

[0065] An ad text generation system can generate personalized text based on the past behavioral data of ad viewers. For example, it can generate engaging text based on data of ads a user has clicked in the past. It can also generate text about related products based on a user's past purchase history. Furthermore, it can generate text about engaging content based on a user's past browsing history. This enables personalized advertising by generating text based on past behavioral data. Past behavioral data includes, but is not limited to, click history, purchase history, and browsing history. Some or all of the above processes in the ad text generation system may be performed using AI, for example, or not. For example, the ad text generation system can input past behavioral data of ad viewers into an AI, which can then generate personalized text.

[0066] The following briefly describes the processing flow for example form 1.

[0067] Step 1: The data collection unit collects past advertising results. The data collection unit can collect detailed data such as click-through rates and conversion rates for ads. The data collection unit collects click-through rates to identify which ads were clicked the most. The data collection unit can also collect conversion rates to identify which ads were most effective. Furthermore, the data collection unit can collect ad impressions to identify which ads were shown the most. Step 2: The analysis unit analyzes the advertising results collected by the collection unit. The analysis unit can analyze the collected data using, for example, data mining techniques. The analysis unit analyzes patterns in the click-through rate and conversion rate of the advertisements. The analysis unit also analyzes the collected data using statistical analysis techniques to quantitatively evaluate the effectiveness of the advertisements. Furthermore, the analysis unit uses machine learning algorithms to analyze the collected data and build a model to predict the effectiveness of the advertisements. Step 3: The generation unit generates the optimal text for the target based on the analysis results obtained by the analysis unit. The generation unit can generate the optimal text based on the attributes of the target user. For example, it can generate the optimal text based on the gender and age of the target user. The generation unit can also generate the optimal text based on past advertising effectiveness. Furthermore, the generation unit can generate the optimal text using AI. For example, it can use a text generation AI (e.g., LLM) to generate the optimal text for the target. Step 4: The verification unit delivers ads using the text generated by the generation unit and verifies their effectiveness. The verification unit can deliver ads using the generated text and measure click-through rates and conversion rates. The verification unit also collects user feedback and evaluates the effectiveness of the ads. Step 5: The optimization team improves and optimizes the ad text based on the results obtained by the verification team. The optimization team modifies the ad text based on the verification results and delivers the ad again. For example, if the click-through rate or conversion rate is low, the text is modified and the ad is delivered again. Furthermore, the optimization team modifies the ad text based on user feedback and delivers the ad again.

[0068] (Example of form 2) An advertising text generation system according to an embodiment of the present invention is a system that reads past advertising effectiveness by gender, age group, etc., and generates optimal text tailored to the target audience. The advertising text generation system reads past advertising results categorized by gender, age group, etc., and the AI ​​analyzes this data to generate optimal text for the target audience. For example, the AI ​​reads text with good and bad performance in electronic advertising and identifies which words are effective. By repeating this process and running a PDCA cycle, the effectiveness of advertising appeals is improved. First, past advertising results are read categorized by gender, age group, etc. At this time, detailed data such as the click-through rate and conversion rate of the advertisements are collected. For example, data for advertisements targeting women in their 20s and advertisements targeting men in their 30s are collected separately. This makes it possible to understand the advertising effectiveness for each target audience. Next, the AI ​​analyzes the collected data. Based on the collected data, the AI ​​generates optimal text for the target audience. For example, the AI ​​identifies that words such as "trend" and "stylish" are effective in advertisements targeting women in their 20s. This makes it possible to generate personalized advertising text tailored to the target audience. Furthermore, the advertisement is delivered using the generated text and its effectiveness is verified. For example, ads using AI-generated text are delivered, and click-through rates and conversion rates are measured. This allows for evaluation of the effectiveness of the generated text. Finally, based on the results of the effectiveness verification, the ad text is improved and optimized. For example, if the click-through rate is low, the AI-generated text is revised, and the ad is delivered again. By repeating this process and running the PDCA cycle, the effectiveness of the ad appeal is improved. This mechanism allows for the generation of optimal ad text tailored to the target audience, thereby improving the effectiveness of the ad appeal. For example, by reading both high-performing and low-performing texts from electronic advertising and having the AI ​​identify which words are effective, more effective ads can be delivered. In this way, the ad text generation system can generate optimal ad text tailored to the target audience, improving the effectiveness of the ad appeal.

[0069] The advertising text generation system according to this embodiment comprises a collection unit, an analysis unit, a generation unit, a verification unit, and an optimization unit. The collection unit collects past advertising results. The collection unit can collect detailed data such as click-through rates and conversion rates of advertisements. For example, the collection unit collects click-through rates of advertisements to identify which advertisement was clicked the most. The collection unit can also collect conversion rates to identify which advertisement was the most effective. Furthermore, the collection unit can collect the number of times an advertisement was displayed to identify which advertisement was displayed the most. The analysis unit analyzes the advertising results collected by the collection unit. The analysis unit can analyze the collected data using, for example, data mining techniques. For example, the analysis unit can analyze patterns in click-through rates and conversion rates of advertisements using data mining techniques. Furthermore, the analysis unit can also analyze the collected data using statistical analysis techniques. For example, the analysis unit can quantitatively evaluate the effectiveness of advertisements using statistical analysis techniques. Furthermore, the analysis unit can also analyze the collected data using machine learning algorithms. For example, the analysis unit uses machine learning algorithms to build a model that predicts the effectiveness of advertisements. The generation unit generates text that is optimal for the target based on the analysis results obtained by the analysis unit. The generation unit can generate optimal text based on, for example, the attributes of the target user. For example, the generation unit generates optimal text based on the gender and age of the target user. The generation unit can also generate optimal text based on past advertising effectiveness. For example, the generation unit analyzes past advertising effectiveness, identifies the most effective words, and uses them to generate text. Furthermore, the generation unit can generate optimal text using AI. For example, the generation unit uses text generation AI (e.g., LLM) to generate text that is optimal for the target. The verification unit delivers advertisements using the text generated by the generation unit and verifies their effectiveness. For example, the verification unit can deliver advertisements using the generated text and measure click-through rates and conversion rates. For example, the verification unit delivers advertisements using the generated text and measures click-through rates.Furthermore, the verification unit can deliver advertisements using the generated text and measure the conversion rate. The verification unit can also deliver advertisements using the generated text and collect user feedback. For example, the verification unit can collect user feedback and evaluate the effectiveness of the advertisement. The optimization unit improves and optimizes the advertisement text based on the results obtained by the verification unit. For example, the optimization unit can modify the advertisement text based on the verification results. For example, if the click-through rate is low, the optimization unit can modify the text and deliver the advertisement again. The optimization unit can also modify the text and deliver the advertisement again if the conversion rate is low. Furthermore, the optimization unit can modify the advertisement text based on user feedback. For example, the optimization unit can modify the text based on user feedback and deliver the advertisement again. As a result, the advertisement text generation system according to this embodiment can generate optimal advertisement text tailored to the target audience and improve the effectiveness of the advertisement.

[0070] The data collection unit collects past advertising results. For example, it can collect detailed data such as click-through rates and conversion rates. Specifically, it meticulously records the number of times an ad was displayed, the number of clicks, and the number of conversions (purchases, registrations, etc.) after clicks. This allows for the identification of which ads received the most clicks and which were the most effective. Furthermore, the data collection unit also collects metadata such as the time of day and day of the week the ad was displayed, and the device on which it was displayed (smartphone, tablet, PC, etc.). This enables the analysis of advertising effectiveness at specific times and on specific devices. The data collection unit centrally manages this data and stores it in a database. The database is updated in real time and made accessible to the analysis and generation units. Additionally, the data collection unit can integrate with external advertising platforms and analytics tools to collect a broader range of data. For example, it can collect data from social media advertising and search engine advertising to evaluate overall advertising effectiveness. This allows the data collection unit to gather detailed advertising results from diverse data sources, strengthening the overall data infrastructure of the system.

[0071] The analysis unit analyzes the advertising results collected by the data collection unit. For example, the analysis unit can analyze the collected data using data mining techniques. Specifically, it can use data mining techniques to analyze patterns in ad click-through rates and conversion rates to identify which factors contribute to advertising effectiveness. The analysis unit can also analyze the collected data using statistical analysis techniques. For example, it can use statistical analysis techniques to quantitatively evaluate the effectiveness of ads and calculate confidence intervals and statistical significance. Furthermore, the analysis unit can analyze the collected data using machine learning algorithms. For example, it can use machine learning algorithms to build models that predict the effectiveness of ads and forecast future advertising effectiveness. Specifically, it can use regression analysis, clustering, and classification algorithms to create models that predict ad click-through rates and conversion rates. Additionally, the analysis unit can use natural language processing techniques to analyze the content of ad text and identify effective keywords and phrases. This allows the analysis unit to analyze the collected data from multiple perspectives and provide insights to maximize advertising effectiveness.

[0072] The generation unit generates text optimized for the target based on the analysis results obtained by the analysis unit. For example, the generation unit can generate optimal text based on the attributes of the target user. Specifically, it generates optimal advertising text based on data such as the target user's gender, age, interests, and past behavioral history. The generation unit can also generate optimal text based on past advertising effectiveness. For example, it analyzes past advertising effectiveness to identify the most effective words and phrases and uses them to generate text. Furthermore, the generation unit can also generate optimal text using AI. Specifically, it uses text generation AI (e.g., LLM) to generate text optimized for the target. The generation AI receives past advertising data and target user attribute data as input and generates optimal advertising text. The generated text is designed to attract the target user's interest and encourage action. This allows the generation unit to quickly generate optimal advertising text tailored to the target and maximize advertising effectiveness.

[0073] The verification unit delivers advertisements using text generated by the generation unit and verifies their effectiveness. For example, the verification unit can deliver advertisements using the generated text and measure click-through rates and conversion rates. Specifically, it can deliver advertisements using the generated text on multiple platforms and compare the click-through rates and conversion rates on each platform. The verification unit can also deliver advertisements using the generated text and collect user feedback. For example, it can conduct surveys with users who clicked on the advertisements to collect opinions on the content and appeal of the advertisements. Furthermore, the verification unit can conduct A / B testing to compare the effectiveness of different versions of the advertisement text. This allows it to identify which version of the text is most effective. Based on this data, the verification unit quantitatively evaluates the effectiveness of the advertisement text and provides information for formulating the optimal advertising strategy.

[0074] The optimization unit improves and optimizes ad text based on the results obtained by the verification unit. For example, the optimization unit can revise ad text based on verification results. Specifically, if the click-through rate is low, it will review the content and structure of the text and revise it to make it more appealing. Also, if the conversion rate is low, it will strengthen the appeal points and call to action in the text. Furthermore, the optimization unit can also revise ad text based on user feedback. For example, it will adjust the content of the ad text to reflect user opinions. The optimization unit makes these revisions quickly and delivers the ads again to continuously improve advertising effectiveness. In addition, the optimization unit can automate the ad text optimization process using machine learning algorithms. For example, it can build an algorithm that learns from past verification results and automatically generates optimal revision suggestions. This allows the optimization unit to efficiently improve ad text and maximize advertising effectiveness.

[0075] The data collection unit can collect detailed data such as click-through rates and conversion rates for advertisements. For example, the data collection unit can collect click-through rates to identify which advertisement was clicked the most. It can also collect conversion rates to identify which advertisement was most effective. Furthermore, the data collection unit can collect the number of impressions to identify which advertisement was displayed the most. This improves the accuracy of advertisement effectiveness analysis by collecting detailed data. Detailed data includes, but is not limited to, click-through rates, conversion rates, and time spent on the page. Some or all of the processing described above in the data collection unit may be performed using AI, for example, or not. For example, the data collection unit can input data on click-through rates and conversion rates for advertisements into an AI, which can then collect the data.

[0076] The analysis unit can identify the most suitable words for the target audience based on the collected data. For example, the analysis unit can use data mining techniques to analyze the collected data and identify the most suitable words for the target audience. For instance, the analysis unit can use data mining techniques to analyze patterns in ad click-through rates and conversion rates and identify the most suitable words. Furthermore, the analysis unit can use statistical analysis techniques to analyze the collected data and identify the most suitable words for the target audience. For example, the analysis unit can use statistical analysis techniques to quantitatively evaluate the effectiveness of ads and identify the most suitable words. Additionally, the analysis unit can use machine learning algorithms to analyze the collected data and identify the most suitable words for the target audience. For example, the analysis unit can use machine learning algorithms to build a model that predicts the effectiveness of ads and identify the most suitable words. This improves the effectiveness of ad text by identifying the most suitable words for the target audience. Optimal words include, but are not limited to, frequently occurring keywords and highly relevant words. Some or all of the above-described processes in the analysis unit may be performed using, for example, AI, or without AI. For example, the analysis unit can input the collected data into an AI, which can then identify the most suitable words.

[0077] The generation unit can generate text that is optimal for the target using specified words. For example, the generation unit can generate optimal text based on the attributes of the target user. For example, the generation unit can generate optimal text based on the gender and age of the target user. The generation unit can also generate optimal text based on past advertising effectiveness. For example, the generation unit can analyze past advertising effectiveness, identify the most effective words, and use them to generate text. Furthermore, the generation unit can also generate optimal text using AI. For example, the generation unit can use text generation AI (e.g., LLM) to generate text that is optimal for the target. This improves the effectiveness of advertising by generating text that is optimal for the target. Optimal text includes, but is not limited to, the attributes of the target user and past advertising effectiveness. Some or all of the above processes in the generation unit may be performed using, for example, AI, or not using AI. For example, the generation unit can input specified words into AI, and the AI ​​can generate optimal text.

[0078] The verification unit can deliver advertisements using the generated text and measure click-through rates and conversion rates. For example, the verification unit can deliver advertisements using the generated text and measure click-through rates. The verification unit can also deliver advertisements using the generated text and measure conversion rates. Furthermore, the verification unit can deliver advertisements using the generated text and collect user feedback. For example, the verification unit can collect user feedback and evaluate the effectiveness of the advertisements. This allows for accurate measurement of the effectiveness of the advertisements and identification of areas for improvement in the text. Click-through rates and conversion rates include, but are not limited to, the number of clicks and completed purchases within a specific period. Some or all of the above processes in the verification unit may be performed using AI, for example, or not. For example, the verification unit can input data on click-through rates and conversion rates of advertisements using the generated text into an AI, which can then analyze the data.

[0079] The optimization unit can modify the ad text based on the verification results and deliver the ad again. For example, if the click-through rate is low, the optimization unit can modify the text and deliver the ad again. For example, if the conversion rate is low, the optimization unit can also modify the text and deliver the ad again. Furthermore, the optimization unit can also modify the ad text based on user feedback. For example, the optimization unit can modify the text based on user feedback and deliver the ad again. This allows for continuous improvement of the ad text, maximizing the effectiveness of the ads. Modifying the ad text includes, but is not limited to, changing wording or adding keywords. Some or all of the above processes in the optimization unit may be performed using, for example, AI, or not using AI. For example, the optimization unit can input the verification results into AI, which can then modify the ad text.

[0080] The data collection unit can estimate the user's emotions and adjust the timing of ad data collection based on the estimated emotions. For example, if the user is excited, the data collection unit can immediately collect ad data and analyze it in real time. For example, if the user is relaxed, the data collection unit can also periodically collect ad data and analyze long-term trends. Furthermore, if the user is stressed, the data collection unit can reduce the collection frequency to alleviate the user's burden. This allows for more effective data collection by adjusting the collection timing according to the user's emotions. User emotions include, but are not limited to, facial recognition, text analysis, and behavioral data. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using AI, for example, or without AI. For example, the data collection unit can input user emotion data into an AI, which can then adjust the collection timing.

[0081] The data collection unit can select the types of data to collect based on the ad display environment (device, time of day, location, etc.). For example, when an ad is displayed on a mobile device, the data collection unit can collect click-through rates and scroll speeds. For example, when an ad is displayed at night, the data collection unit can also collect viewing time and conversion rates. Furthermore, when an ad is displayed in a specific region, the data collection unit can collect geographic location information and analyze the ad's effectiveness by region. This enables a detailed analysis of ad effectiveness by collecting data according to the display environment. The display environment includes, but is not limited to, device type, time of day, and location. Some or all of the processing described above in the data collection unit may be performed using AI, for example, or not. For example, the data collection unit can input ad display environment data into AI and select the types of data that AI should collect.

[0082] The data collection unit can also collect user behavior data such as ad viewing time and scrolling speed, enabling a detailed analysis of ad effectiveness. For example, the data collection unit can measure ad viewing time and analyze which parts attracted the most attention. For example, the data collection unit can collect user scrolling speed to identify at which part of the ad users lost interest. Furthermore, the data collection unit can collect user click patterns and analyze which elements were most effective. This allows for a detailed analysis of ad effectiveness by collecting user behavior data. User behavior data includes, but is not limited to, viewing time, scrolling speed, and click patterns. Some or all of the processing described above in the data collection unit may be performed using AI, for example, or not. For example, the data collection unit can input data on ad viewing time and scrolling speed into an AI, which can then collect the data.

[0083] The data collection unit can estimate the user's emotions and determine the priority of advertising data to collect based on the estimated user emotions. For example, if the user is excited, the data collection unit may prioritize collecting click-through rates and conversion rates. If the user is relaxed, the data collection unit may also prioritize collecting viewing time and scroll speed. Furthermore, if the user is stressed, the data collection unit may also prioritize collecting ad display frequency and display time. This enables effective data collection by prioritizing data according to the user's emotions. Prioritization of advertising data includes, but is not limited to, emotion scores and past effectiveness. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the data collection unit may be performed using, for example, AI, or not using AI. For example, the data collection unit can input user emotion data into an AI, which can then determine the priority of advertising data to collect.

[0084] The data collection unit can collect advertising data from different platforms, such as social media and news sites, and evaluate the overall effectiveness of advertising. For example, the data collection unit can collect advertising data from social media and analyze engagement rates. For example, the data collection unit can also collect advertising data from news sites and compare click-through rates and conversion rates. Furthermore, the data collection unit can integrate data from different platforms and evaluate the overall effectiveness of advertising. This makes it possible to evaluate the overall effectiveness of advertising by collecting data from different platforms. Different platforms include, but are not limited to, social media, news sites, and blogs. Some or all of the processing described above in the data collection unit may be performed using AI, for example, or not. For example, the data collection unit can input data from social media and news sites into an AI, which can then collect the data.

[0085] The data collection unit can collect advertising effectiveness by region, taking into account the geographical location information of the ad viewers. For example, the data collection unit can collect geographical location information when an ad is displayed in a specific region and analyze the click-through rate by region. The data collection unit can also collect conversion rates by region and evaluate differences in advertising effectiveness. Furthermore, the data collection unit can compare advertising effectiveness by region based on geographical location information and formulate the optimal advertising strategy. This makes it possible to conduct a detailed analysis of advertising effectiveness by region by considering geographical location information. Geographical location information includes, but is not limited to, IP addresses and GPS data. Some or all of the above processing in the data collection unit may be performed using, for example, AI, or not using AI. For example, the data collection unit can input the geographical location information of the ad viewers into AI, and the AI ​​can collect the data.

[0086] The analysis unit can estimate the user's emotions and adjust the analysis algorithm based on the estimated emotions. For example, if the user is relaxed, the analysis unit can perform a detailed analysis and identify long-term trends. If the user is in a hurry, the analysis unit can also perform a rapid analysis and provide immediate results. Furthermore, if the user is excited, the analysis unit can perform a real-time analysis and provide immediate feedback. This allows for more effective analysis by adjusting the analysis algorithm according to the user's emotions. The analysis algorithm includes, but is not limited to, machine learning models and statistical analysis methods. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input user emotion data into AI, and the AI ​​can adjust the analysis algorithm.

[0087] The analysis unit can analyze detailed user behavior data, such as ad viewing time and click patterns, to identify factors influencing ad effectiveness. For example, the analysis unit can analyze ad viewing time to identify which parts received the most attention. The analysis unit can also analyze click patterns to identify which elements were most effective. Furthermore, the analysis unit can analyze user behavior data to identify factors influencing ad effectiveness. This allows for the identification of factors influencing ad effectiveness by analyzing detailed user behavior data. Detailed user behavior data includes, but is not limited to, viewing time, click patterns, and scroll speed. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input data on ad viewing time and click patterns into an AI, which can then analyze the data.

[0088] The analysis unit can apply different analysis methods based on the ad display environment (device, time of day, location, etc.). For example, when an ad is displayed on a mobile device, the analysis unit can analyze the click-through rate and scroll speed. For example, when an ad is displayed at night, the analysis unit can also analyze the viewing time and conversion rate. Furthermore, when an ad is displayed in a specific region, the analysis unit can analyze geographic location information and analyze the ad's effectiveness for that region. This allows for a detailed analysis of ad effectiveness by applying analysis methods appropriate to the display environment. The display environment includes, but is not limited to, device type, time of day, and location. Some or all of the above-described processes in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input ad display environment data into AI, and the AI ​​can apply analysis methods.

[0089] The analysis unit can estimate the user's emotions and adjust the display method of the analysis results based on the estimated user emotions. For example, if the user is tense, the analysis unit can provide a simple and highly visible display method. For example, if the user is relaxed, the analysis unit can also provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the analysis unit can provide a concise display method. By adjusting the display method according to the user's emotions, the understanding of the analysis results is deepened. Display methods for analysis results include, but are not limited to, graph displays, text displays, and interactive displays. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generative AI. The generative AI is, but is not limited to, a text generation AI (e.g., LLM) or a multimodal generation AI. Some or all of the above processing in the analysis unit may be performed using, for example, AI, or not using AI. For example, the analysis unit can input user emotion data into an AI, and the AI ​​can adjust the display method of the analysis results.

[0090] The analysis unit can analyze the effectiveness of advertisements by region, taking into account the geographical location information of the ad viewers. For example, when an ad is displayed in a specific region, the analysis unit can analyze geographical location information and analyze the click-through rate for that region. The analysis unit can also analyze conversion rates by region and evaluate differences in advertising effectiveness. Furthermore, based on geographical location information, the analysis unit can compare the effectiveness of advertisements by region and formulate the optimal advertising strategy. This makes it possible to conduct a detailed analysis of advertising effectiveness by region by considering geographical location information. Geographical location information includes, but is not limited to, IP addresses and GPS data. Some or all of the above processing in the analysis unit may be performed using AI, for example, or without AI. For example, the analysis unit can input the geographical location information of the ad viewers into AI, and the AI ​​can analyze the data.

[0091] The analytics unit can analyze data from different platforms, such as social media and news sites, to evaluate overall advertising effectiveness. For example, the analytics unit can analyze data from social media to evaluate engagement rates. It can also analyze data from news sites to compare click-through rates and conversion rates. Furthermore, the analytics unit can integrate data from different platforms to evaluate overall advertising effectiveness. This makes it possible to evaluate overall advertising effectiveness by analyzing data from different platforms. Different platforms include, but are not limited to, social media, news sites, and blogs. Some or all of the above processing in the analytics unit may be performed using AI, for example, or not. For example, the analytics unit can input data from social media and news sites into an AI, which can then analyze the data.

[0092] The generation unit can estimate the user's emotions and adjust the tone and style of the generated text based on the estimated emotions. For example, if the user is relaxed, the generation unit can generate text with a soft tone. If the user is excited, the generation unit can also generate text with an energetic tone. Furthermore, if the user is stressed, the generation unit can generate text with a calm tone. By adjusting the tone and style of the text according to the user's emotions, more effective advertising text can be generated. Text tones and styles include, but are not limited to, formal, casual, and emotional. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the generation unit may be performed using AI, for example, or not using AI. For example, the generation unit can input user emotion data into an AI, which can then adjust the tone and style of the text.

[0093] The generation unit can customize the content of the text it generates based on the ad's display environment (device, time of day, location, etc.). For example, when an ad is displayed on a mobile device, the generation unit can generate short, concise text. For example, when an ad is displayed at night, the generation unit can also generate text with a relaxed tone. Furthermore, when an ad is displayed in a specific region, the generation unit can generate text that is tailored to the local culture and customs. This improves the effectiveness of the ad by customizing the text according to the display environment. The display environment includes, but is not limited to, the type of device, time of day, and location. Some or all of the processing described above in the generation unit may be performed using AI, for example, or not. For example, the generation unit can input ad display environment data into AI, and the AI ​​can customize the text content.

[0094] The generation unit can generate personalized text based on the past behavioral data of the ad viewer. For example, the generation unit can generate engaging text based on data of ads the user has clicked in the past. The generation unit can also generate text about related products based on the user's past purchase history. Furthermore, the generation unit can generate text about engaging content based on the user's past browsing history. This enables personalized advertising by generating text based on past behavioral data. Past behavioral data includes, but is not limited to, click history, purchase history, and browsing history. Some or all of the above processing in the generation unit may be performed using, for example, AI, or not using AI. For example, the generation unit can input the past behavioral data of the ad viewer into AI, and the AI ​​can generate personalized text.

[0095] The generation unit can estimate the user's emotions and adjust the length of the generated text based on the estimated emotions. For example, if the user is in a hurry, the generation unit can generate short, concise text. If the user is relaxed, the generation unit can also generate longer text with detailed explanations. Furthermore, if the user is excited, the generation unit can generate text with visually stimulating effects. By adjusting the length of the text according to the user's emotions, more effective advertising text can be generated. Text length includes, but is not limited to, the number of characters, lines, and paragraphs. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or a generation AI. The generation AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to these examples. Some or all of the above processing in the generation unit may be performed using, for example, AI, or not using AI. For example, the generation unit can input user emotion data into an AI, which can then adjust the length of the text.

[0096] The generation unit can generate optimal text for each region, taking into account the geographical location information of the ad viewers. For example, when displaying an ad in a specific region, the generation unit can generate text that is tailored to the local culture and customs. The generation unit can also generate optimal text, taking into account the local language and dialect. Furthermore, the generation unit can generate text that maximizes the effectiveness of the ad in each region based on geographical location information. This allows for the generation of optimal ad text for each region by considering geographical location information. Geographical location information includes, but is not limited to, IP addresses and GPS data. Some or all of the above processing in the generation unit may be performed using, for example, AI, or not. For example, the generation unit can input the geographical location information of the ad viewers into AI, and the AI ​​can generate optimal text.

[0097] The generation unit can generate text suitable for different platforms, such as social media and news sites. For example, for social media, the generation unit can generate short, visually appealing text. For news sites, the generation unit can also generate text containing detailed information. Furthermore, the generation unit can generate optimal text for each different platform, maximizing advertising effectiveness. This maximizes advertising effectiveness by generating text suitable for different platforms. Different platforms include, but are not limited to, social media, news sites, and blogs. Some or all of the processing described above in the generation unit may be performed using AI, for example, or not. For example, the generation unit can input data from social media and news sites into an AI, which can then generate optimal text.

[0098] The verification unit can estimate the user's emotions and adjust the advertising effectiveness verification method based on the estimated user emotions. For example, if the user is relaxed, the verification unit can perform a detailed verification and identify long-term trends. For example, if the user is in a hurry, the verification unit can also perform a rapid verification and provide immediate results. Furthermore, if the user is excited, the verification unit can perform a real-time verification and provide immediate feedback. This allows for more accurate verification of advertising effectiveness by adjusting the verification method according to the user's emotions. Advertising effectiveness verification methods include, but are not limited to, A / B testing, user feedback, and changes in click-through rates. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above processing in the verification unit may be performed using AI, for example, or without AI. For example, the verification unit can input user emotion data into AI, and the AI ​​can adjust the advertising effectiveness verification method.

[0099] The verification unit can collect verification data based on the ad display environment (device, time of day, location, etc.) and perform detailed effectiveness analysis. For example, when an ad is displayed on a mobile device, the verification unit can verify the click-through rate and scroll speed. For example, when an ad is displayed at night, the verification unit can also verify the viewing time and conversion rate. Furthermore, when an ad is displayed in a specific region, the verification unit can verify geographical location information and analyze the effectiveness of the ad for each region. This enables a detailed analysis of ad effectiveness by collecting verification data according to the display environment. The display environment includes, but is not limited to, device type, time of day, and location. Some or all of the above processing in the verification unit may be performed using AI, for example, or without AI. For example, the verification unit can input ad display environment data into AI, and the AI ​​can collect verification data.

[0100] The verification unit can build a predictive model for advertising effectiveness based on past behavioral data of the ad's audience. For example, the verification unit can build a predictive model for advertising effectiveness based on the user's past click data. The verification unit can also build a predictive model for conversion rates based on the user's past purchase history. Furthermore, the verification unit can build a predictive model for viewing time based on the user's past browsing history. This makes it possible to predict advertising effectiveness by building a predictive model based on past behavioral data. Past behavioral data includes, but is not limited to, click history, purchase history, and browsing history. Some or all of the above processing in the verification unit may be performed using AI, for example, or without AI. For example, the verification unit can input past behavioral data of the ad's audience into AI, and the AI ​​can build a predictive model for advertising effectiveness.

[0101] The verification unit can estimate the user's emotions and adjust the display method of the verification results based on the estimated user emotions. For example, if the user is nervous, the verification unit can provide a simple and highly visible display method. For example, if the user is relaxed, the verification unit can also provide a display method that includes detailed information. Furthermore, if the user is in a hurry, the verification unit can provide a concise display method. By adjusting the display method according to the user's emotions, the understanding of the verification results is deepened. Display methods for verification results include, but are not limited to, graph displays, text displays, and interactive displays. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above processing in the verification unit may be performed using, for example, AI, or not using AI. For example, the verification unit can input user emotion data into AI, and the AI ​​can adjust the display method of the verification results.

[0102] The verification unit can verify the effectiveness of advertisements by region, taking into account the geographical location information of the ad viewers. For example, the verification unit can verify geographical location information when an ad is displayed in a specific region and analyze the click-through rate for each region. The verification unit can also verify conversion rates by region and evaluate differences in advertising effectiveness. Furthermore, the verification unit can compare the effectiveness of advertisements by region based on geographical location information and formulate the optimal advertising strategy. This makes it possible to conduct a detailed analysis of advertising effectiveness by region by considering geographical location information. Geographical location information includes, but is not limited to, IP addresses and GPS data. Some or all of the above processing in the verification unit may be performed using AI, for example, or without AI. For example, the verification unit can input the geographical location information of the ad viewers into AI, and the AI ​​can verify the data.

[0103] The verification unit can verify the effectiveness of advertising on different platforms, such as social media and news sites. For example, the verification unit can verify the effectiveness of advertising on social media and evaluate the engagement rate. For example, the verification unit can also verify the effectiveness of advertising on news sites and compare click-through rates and conversion rates. Furthermore, the verification unit can verify the effectiveness of advertising on each different platform and perform an overall evaluation. This makes it possible to evaluate the overall effectiveness of advertising by verifying the effectiveness of advertising on different platforms. Different platforms include, but are not limited to, social media, news sites, and blogs. Some or all of the above processing in the verification unit may be performed using AI, for example, or not using AI. For example, the verification unit can input data from social media and news sites into AI, and the AI ​​can verify the data.

[0104] The optimization unit can estimate the user's emotions and adjust the optimization method of the ad text based on the estimated user emotions. For example, if the user is relaxed, the optimization unit can optimize the text in a soft tone. If the user is excited, the optimization unit can also optimize the text in an energetic tone. Furthermore, if the user is stressed, the optimization unit can also optimize the text in a calm tone. By adjusting the optimization method according to the user's emotions, more effective optimization of the ad text becomes possible. The optimization method of the ad text includes, but is not limited to, changing wording or adding keywords. Emotion estimation is achieved using an emotion estimation function, for example, an emotion engine or generative AI. The generative AI is a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to such examples. Some or all of the above processing in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input user emotion data into the AI, and the AI ​​can adjust the optimization method of the ad text.

[0105] The optimization unit can apply an optimization algorithm based on the ad display environment (device, time of day, location, etc.). For example, when displaying an ad on a mobile device, the optimization unit optimizes the text to be short and to the point. For example, when displaying an ad at night, the optimization unit can also optimize the text to have a relaxed tone. Furthermore, when displaying an ad in a specific region, the optimization unit can optimize the text to suit the local culture and customs. This improves the effectiveness of the ad by applying an optimization algorithm according to the display environment. The display environment includes, but is not limited to, the type of device, time of day, and location. Some or all of the above processing in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input the ad display environment data into AI, and the AI ​​can apply the optimization algorithm.

[0106] The optimization unit can perform personalized optimization based on the past behavioral data of the ad viewers. For example, the optimization unit can optimize the text of ads that users have clicked on in the past. The optimization unit can also optimize the text of related products based on the user's past purchase history. Furthermore, the optimization unit can optimize the text of content that users are interested in based on their past browsing history. This enables personalized advertising by optimizing based on past behavioral data. Past behavioral data includes, but is not limited to, click history, purchase history, and browsing history. Some or all of the above processing in the optimization unit may be performed using AI, for example, or without AI. For example, the optimization unit can input the past behavioral data of the ad viewers into AI, which can then perform personalized optimization.

[0107] The optimization unit can estimate the user's emotions and determine optimization priorities based on the estimated emotions. For example, if the user is excited, the optimization unit can perform optimization immediately and provide results in real time. For example, if the user is relaxed, the optimization unit can also perform optimization periodically to identify long-term trends. Furthermore, if the user is stressed, the optimization unit can reduce the optimization frequency to alleviate the user's burden. This enables effective optimization by determining optimization priorities according to the user's emotions. Optimization priorities include, but are not limited to, emotion scores and past effects. Emotion estimation is achieved using an emotion estimation function, such as an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) and multimodal generation AI. Some or all of the above processing in the optimization unit may be performed using AI, or not. For example, the optimization unit can input user emotion data into an AI, which can then determine optimization priorities.

[0108] The optimization unit can provide optimal ad text for each region by considering the geographical location information of the ad viewers. For example, when displaying an ad in a specific region, the optimization unit can provide text that is tailored to the local culture and customs. The optimization unit can also provide optimal text by considering the local language and dialect. Furthermore, the optimization unit can provide text that maximizes the advertising effect for each region based on geographical location information. In this way, by considering geographical location information, the optimization unit can provide optimal ad text for each region. Geographical location information includes, but is not limited to, IP addresses and GPS data. Some or all of the above processing in the optimization unit may be performed using, for example, AI, or not using AI. For example, the optimization unit can input the geographical location information of the ad viewers into AI, and the AI ​​can provide optimal ad text.

[0109] The optimization unit can perform optimizations suitable for different platforms, such as social media and news sites. For example, the optimization unit can optimize short, visually appealing text for social media. For example, the optimization unit can also optimize text containing detailed information for news sites. Furthermore, the optimization unit can optimize the text to be optimal for each different platform, maximizing advertising effectiveness. This maximizes advertising effectiveness by performing optimizations suitable for different platforms. Different platforms include, but are not limited to, social media, news sites, and blogs. Some or all of the processing described above in the optimization unit may be performed using AI, for example, or not. For example, the optimization unit can input data from social media and news sites into AI, which can then optimize the text to be optimal.

[0110] The system according to the embodiment is not limited to the example described above, and various modifications are possible, for example, as follows.

[0111] An ad text generation system can estimate a user's emotions and adjust the timing of ad delivery based on those emotions. For example, if a user is relaxed, the ad can be delivered immediately; if the user is excited, the ad delivery can be delayed. Furthermore, if a user is stressed, the ad delivery can be paused and resumed after the user's emotions have calmed down. This allows for adjustment of ad delivery timing according to the user's emotions, improving ad effectiveness. Emotion estimation is achieved using, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the ad text generation system may be performed using AI, or not. For example, the ad text generation system can input user emotion data into an AI, which can then adjust the timing of ad delivery.

[0112] An ad text generation system can adjust the frequency of ad delivery based on a user's past behavioral data. For example, it can frequently deliver similar ads based on data of ads a user has clicked frequently in the past. Furthermore, it can increase the frequency of ads for related products based on data of products a user has purchased in the past. By adjusting the frequency of ad delivery based on past behavioral data, advertising effectiveness is improved. Past behavioral data includes, but is not limited to, click history, purchase history, and browsing history. Some or all of the above processing in the ad text generation system may be performed using AI, for example, or without AI. For example, the ad text generation system can input the user's past behavioral data into AI, which can then adjust the frequency of ad delivery.

[0113] An ad text generation system can estimate a user's emotions and customize the ad content based on those emotions. For example, if a user is relaxed, it can generate ad text in a soft tone. If a user is excited, it can generate ad text in an energetic tone. Furthermore, if a user is stressed, it can generate ad text in a calm tone. This allows for the customization of ad content according to the user's emotions, improving ad effectiveness. Emotion estimation is achieved using, for example, an emotion engine or generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the ad text generation system may be performed using AI, or not. For example, the ad text generation system can input user emotion data into an AI, which can then customize the ad content.

[0114] The ad text generation system can adjust the timing of ad delivery based on the ad's display environment (device, time of day, location, etc.). For example, when an ad is displayed on a mobile device, it can deliver a short, concise ad. When an ad is displayed at night, it can deliver an ad with a relaxed tone. Furthermore, when an ad is displayed in a specific region, it can deliver an ad tailored to the local culture and customs. This improves ad effectiveness by adjusting the timing of ad delivery according to the display environment. The display environment includes, but is not limited to, device type, time of day, and location. Some or all of the above processing in the ad text generation system may be performed using AI, for example, or not. For example, the ad text generation system can input ad display environment data into AI, which can then adjust the timing of ad delivery.

[0115] An ad text generation system can estimate a user's emotions and adjust how ads are displayed based on those emotions. For example, if a user is stressed, a simple, highly visible ad can be displayed. If a user is relaxed, an ad containing detailed information can be displayed. Furthermore, if a user is in a hurry, a concise ad can be displayed. This allows for adjustments to how ads are displayed according to the user's emotions, improving advertising effectiveness. Emotion estimation can be achieved using, for example, an emotion engine or generative AI. Generative AI may be, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the ad text generation system may be performed using AI, or not using AI. For example, the ad text generation system can input user emotion data into an AI, which can then adjust how ads are displayed.

[0116] The ad text generation system can generate optimal ad text for each region by considering the geographical location information of the ad viewers. For example, when displaying an ad in a specific region, it can generate text that is tailored to the local culture and customs. It can also generate optimal text considering the local language and dialect. Furthermore, it can generate text that maximizes the effectiveness of the ad in each region based on geographical location information. In this way, by considering geographical location information, it is possible to generate optimal ad text for each region. Geographical location information includes, but is not limited to, IP addresses and GPS data. Some or all of the above processing in the ad text generation system may be performed using AI, for example, or not using AI. For example, the ad text generation system can input the geographical location information of the ad viewers into AI, and the AI ​​can generate optimal text.

[0117] The advertising text generation system can generate text suitable for different platforms, such as social media and news sites. For example, it can generate short, visually appealing text for social media, and text containing detailed information for news sites. Furthermore, it can generate optimal text for each different platform, maximizing advertising effectiveness. This maximizes advertising effectiveness by generating text suitable for different platforms. Different platforms include, but are not limited to, social media, news sites, and blogs. Some or all of the above processing in the advertising text generation system may be performed using AI, for example, or not. For example, the advertising text generation system can input data from social media and news sites into an AI, which can then generate the optimal text.

[0118] An advertising text generation system can estimate a user's emotions and adjust the length of the generated text based on those emotions. For example, if a user is in a hurry, it can generate short, concise text. If a user is relaxed, it can generate longer text with detailed explanations. Furthermore, if a user is excited, it can generate text with visually stimulating effects. By adjusting the text length according to the user's emotions, more effective advertising text can be generated. Text length includes, but is not limited to, the number of characters, lines, and paragraphs. Emotion estimation is achieved using, for example, an emotion engine or a generative AI. The generative AI is, for example, a text generation AI (e.g., LLM) or a multimodal generation AI, but is not limited to those examples. Some or all of the above processing in the advertising text generation system may be performed using, for example, AI, or not using AI. For example, the advertising text generation system can input user emotion data into an AI, which can then adjust the text length.

[0119] An ad text generation system can generate personalized text based on the past behavioral data of ad viewers. For example, it can generate engaging text based on data of ads a user has clicked in the past. It can also generate text about related products based on a user's past purchase history. Furthermore, it can generate text about engaging content based on a user's past browsing history. This enables personalized advertising by generating text based on past behavioral data. Past behavioral data includes, but is not limited to, click history, purchase history, and browsing history. Some or all of the above processes in the ad text generation system may be performed using AI, for example, or not. For example, the ad text generation system can input past behavioral data of ad viewers into an AI, which can then generate personalized text.

[0120] An advertising text generation system can estimate a user's emotions and adjust the tone and style of the generated text based on those emotions. For example, if a user is relaxed, it can generate text in a soft tone. If a user is excited, it can generate text in an energetic tone. Furthermore, if a user is stressed, it can generate text in a calm tone. By adjusting the tone and style of the text according to the user's emotions, more effective advertising text can be generated. Text tones and styles include, but are not limited to, formal, casual, and emotional. Emotion estimation can be achieved using, for example, an emotion engine or a generative AI. Generative AI includes, but is not limited to, text generation AI (e.g., LLM) or multimodal generation AI. Some or all of the above processing in the advertising text generation system may be performed using, for example, AI, or not using AI. For example, the advertising text generation system can input user emotion data into an AI, which can then adjust the tone and style of the text.

[0121] The following briefly describes the processing flow for example form 2.

[0122] Step 1: The data collection unit collects past advertising results. The data collection unit can collect detailed data such as click-through rates and conversion rates for ads. The data collection unit collects click-through rates to identify which ads were clicked the most. The data collection unit can also collect conversion rates to identify which ads were most effective. Furthermore, the data collection unit can collect ad impressions to identify which ads were shown the most. Step 2: The analysis unit analyzes the advertising results collected by the collection unit. The analysis unit can analyze the collected data using, for example, data mining techniques. The analysis unit analyzes patterns in the click-through rate and conversion rate of the advertisements. The analysis unit also analyzes the collected data using statistical analysis techniques to quantitatively evaluate the effectiveness of the advertisements. Furthermore, the analysis unit uses machine learning algorithms to analyze the collected data and build a model to predict the effectiveness of the advertisements. Step 3: The generation unit generates the optimal text for the target based on the analysis results obtained by the analysis unit. The generation unit can generate the optimal text based on the attributes of the target user. For example, it can generate the optimal text based on the gender and age of the target user. The generation unit can also generate the optimal text based on past advertising effectiveness. Furthermore, the generation unit can generate the optimal text using AI. For example, it can use a text generation AI (e.g., LLM) to generate the optimal text for the target. Step 4: The verification unit delivers ads using the text generated by the generation unit and verifies their effectiveness. The verification unit can deliver ads using the generated text and measure click-through rates and conversion rates. The verification unit also collects user feedback and evaluates the effectiveness of the ads. Step 5: The optimization team improves and optimizes the ad text based on the results obtained by the verification team. The optimization team modifies the ad text based on the verification results and delivers the ad again. For example, if the click-through rate or conversion rate is low, the text is modified and the ad is delivered again. Furthermore, the optimization team modifies the ad text based on user feedback and delivers the ad again.

[0123] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0124] Data generation model 58 is a form of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AI include text generation AI, image generation AI, and multimodal generation AI. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats from audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVMs), k-means clustering, convolutional neural networks (CNNs), recurrent neural networks (RNNs), generative adversarial networks (GANs), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each of the above parts is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example.Furthermore, processing performed by AI, including generative AI, may be replaced with rule-based processing, and rule-based processing may be replaced with processing performed by AI, including generative AI.

[0125] Furthermore, the processing performed by the data processing system 10 described above is carried out by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but it may also be carried out by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0126] Each of the multiple elements described above, including the collection unit, analysis unit, generation unit, verification unit, and optimization unit, is implemented in at least one of the smart device 14 and the data processing unit 12. For example, the collection unit can collect detailed data such as the click-through rate and conversion rate of advertisements by the control unit 46A of the smart device 14. The analysis unit analyzes the collected data by the specific processing unit 290 of the data processing unit 12. The generation unit generates text optimized for the target by the specific processing unit 290 of the data processing unit 12. The verification unit delivers advertisements using the text generated by the control unit 46A of the smart device 14 and verifies their effectiveness. The optimization unit improves and optimizes the advertisement text based on the verification results by the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above and can be modified in various ways.

[0127] [Second Embodiment] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0128] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0129] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0130] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0131] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0132] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0133] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0134] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing by the processor 28. The storage 32 stores the specific processing program 56.

[0135] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0136] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0137] In the smart glasses 214, specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0138] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0139] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0140] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0141] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart glasses 214 or an external device, and the smart glasses 214 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0142] Each of the multiple elements described above, including the collection unit, analysis unit, generation unit, verification unit, and optimization unit, is implemented, for example, in at least one of the smart glasses 214 and the data processing unit 12. For example, the collection unit can collect detailed data such as the click-through rate and conversion rate of advertisements by the control unit 46A of the smart glasses 214. The analysis unit analyzes the collected data by the specific processing unit 290 of the data processing unit 12, for example. The generation unit generates text optimized for the target by the specific processing unit 290 of the data processing unit 12, for example. The verification unit delivers advertisements using the text generated by the control unit 46A of the smart glasses 214 and verifies their effectiveness. The optimization unit improves and optimizes the advertisement text based on the verification results by the specific processing unit 290 of the data processing unit 12, for example. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0143] [Third Embodiment] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0144] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0145] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0146] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0147] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0148] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0149] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0150] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0151] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0152] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0153] In the headset terminal 314, specific processing is performed by the processor 46. The storage 50 stores a specific program 60. The processor 46 reads the specific program 60 from the storage 50 and executes the read specific program 60 on the RAM 48. The specific processing is realized by the processor 46 acting as a control unit 46A according to the specific program 60 executed on the RAM 48. The headset terminal 314 also has a data generation model 58 and an emotion identification model 59, similar to the data generation model and emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0154] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0155] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0156] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0157] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset terminal 314, but may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset terminal 314. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the headset terminal 314 or an external device, and the headset terminal 314 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0158] Each of the multiple elements described above, including the collection unit, analysis unit, generation unit, verification unit, and optimization unit, is implemented in at least one of the headset terminal 314 and the data processing unit 12. For example, the collection unit can collect detailed data such as the click-through rate and conversion rate of advertisements by the control unit 46A of the headset terminal 314. The analysis unit analyzes the collected data by the specific processing unit 290 of the data processing unit 12. The generation unit generates text optimized for the target by the specific processing unit 290 of the data processing unit 12. The verification unit delivers advertisements using the text generated by the control unit 46A of the headset terminal 314 and verifies their effectiveness. The optimization unit improves and optimizes the advertisement text based on the verification results by the specific processing unit 290 of the data processing unit 12. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0159] [Fourth Embodiment] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0160] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0161] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN and / or LAN.

[0162] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0163] The microphone 238 receives voice signals from the user and accepts instructions from the user. The microphone 238 captures the voice signals from the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0164] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS image sensor or CCD image sensor, which captures images of the area around the user (for example, an imaging range defined by a field of view equivalent to the field of vision of a typical healthy person).

[0165] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0166] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. The robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0167] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0168] The processor 28 reads a specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 acting as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0169] Storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotions using the emotion identification model 59 and perform identification processing using the user's emotions. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotions, including but not limited to these examples. Furthermore, emotion estimation and prediction also include, for example, emotion analysis.

[0170] In robot 414, specific processing is performed by processor 46. A specific program 60 is stored in storage 50. Processor 46 reads the specific program 60 from storage 50 and executes it on RAM 48. The specific processing is achieved by processor 46 acting as a control unit 46A according to the specific program 60 executed on RAM 48. Robot 414 also has data generation model 58 and emotion identification model 59, similar to those of the robot, and can perform processing similar to that of the specific processing unit 290 using these models.

[0171] Furthermore, other devices besides the data processing device 12 may also have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 obtains processing results (such as prediction results) using the data generation model 58 by communicating with the server device that has the data generation model 58. Also, the data processing device 12 may be a server device or a terminal device owned by the user (for example, a mobile phone, robot, home appliance, etc.).

[0172] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0173] The data generation model 58 is a so-called generative AI. An example of a data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and inference data such as audio data representing speech, text data representing text, and image data representing images (e.g., still image data or video data). The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference result in one or more data formats such as audio data, text data, and image data. The data generation model 58 includes, for example, text generation AI, image generation AI, and multimodal generation AI. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specific processing unit 290 performs the specific processing described above using the data generation model 58. The data generation model 58 may be a fine-tuned model that outputs inference results from prompts that do not contain instructions, in which case the data generation model 58 can output inference results from prompts that do not contain instructions. In the data processing device 12, etc., there are multiple types of data generation models 58, and the data generation model 58 includes AI other than generative AI. AI other than generative AI includes, for example, linear regression, logistic regression, decision trees, random forests, support vector machines (SVM), k-means clustering, convolutional neural networks (CNN), recurrent neural networks (RNN), generative adversarial networks (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. Also, the AI ​​may be an AI agent. Furthermore, when the processing of each part described above is performed by the AI, the processing may be performed by the AI ​​in part or in whole, but is not limited to this example. Also, processing performed by an AI including a generative AI may be replaced by rule-based processing, and rule-based processing may be replaced by processing performed by an AI including a generative AI.

[0174] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is performed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but it may also be performed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. In addition, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the robot 414 or an external device, and the robot 414 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0175] Each of the multiple elements described above, including the collection unit, analysis unit, generation unit, verification unit, and optimization unit, is implemented, for example, by at least one of the robot 414 and the data processing unit 12. For example, the collection unit can collect detailed data such as the click-through rate and conversion rate of advertisements by the control unit 46A of the robot 414. The analysis unit analyzes the collected data by the specific processing unit 290 of the data processing unit 12, for example. The generation unit generates text optimized for the target by the specific processing unit 290 of the data processing unit 12, for example. The verification unit delivers advertisements using the text generated by the control unit 46A of the robot 414 and verifies their effectiveness. The optimization unit improves and optimizes the advertisement text based on the verification results by the specific processing unit 290 of the data processing unit 12, for example. The correspondence between each unit and the device or control unit is not limited to the example described above, and various changes are possible.

[0176] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0177] Figure 9 shows the emotion map 400, in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0178] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0179] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0180] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, and motorcycles, emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated based, for example, on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0181] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0182] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0183] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing method for the specific process may be used, which includes computer 22 and multiple other computers.

[0184] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0185] 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.

[0186] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0187] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0188] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0189] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0190] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0191] Furthermore, although the above-described examples were divided into four embodiments, some or all of these embodiments may be combined. Also, the smart device 14, smart glasses 214, headset terminal 314, and robot 414 are just examples, and they may be combined, or other devices may be used. Also, although the above-described examples were divided into two embodiments, Embodiment 1 and Embodiment 2, these may be combined.

[0192] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and other things that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0193] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0194] (Note 1) The data collection department collects past advertising results, An analysis unit analyzes the advertising results collected by the collection unit, A generation unit generates text that is optimal for the target based on the analysis results obtained by the analysis unit, A verification unit delivers advertisements using the text generated by the generation unit and verifies their effectiveness. The system includes an optimization unit that improves and optimizes the advertising text based on the results obtained by the verification unit. A system characterized by the following features. (Note 2) The aforementioned collection unit is Collect detailed data such as ad click-through rates and conversion rates. The system described in Appendix 1, characterized by the features described herein. (Note 3) The aforementioned analysis unit, Based on the collected data, identify the most suitable words for your target audience. The system described in Appendix 1, characterized by the features described herein. (Note 4) The generating unit is Generate text that is best suited to the target using identified words. The system described in Appendix 1, characterized by the features described herein. (Note 5) The verification unit, The system delivers ads using generated text and measures click-through rates and conversion rates. The system described in Appendix 1, characterized by the features described herein. (Note 6) The optimization unit, Based on the verification results, we will revise the ad text and deliver the ad again. The system described in Appendix 1, characterized by the features described herein. (Note 7) The aforementioned collection unit is We estimate the user's emotions and adjust the timing of ad data collection based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 8) The aforementioned collection unit is Select the types of data to collect based on the advertising display environment. The system described in Appendix 1, characterized by the features described herein. (Note 9) The aforementioned collection unit is The system also collects user behavior data such as ad viewing time and scrolling speed, enabling detailed analysis of ad effectiveness. The system described in Appendix 1, characterized by the features described herein. (Note 10) The aforementioned collection unit is It estimates user sentiment and prioritizes the advertising data to collect based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 11) The aforementioned collection unit is We collect advertising data from different platforms, such as social media and news sites, to evaluate overall advertising effectiveness. The system described in Appendix 1, characterized by the features described herein. (Note 12) The aforementioned collection unit is The system collects advertising effectiveness data by region, taking into account the geographical location of the ad viewers. The system described in Appendix 1, characterized by the features described herein. (Note 13) The aforementioned analysis unit, It estimates the user's emotions and adjusts the analysis algorithm based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 14) The aforementioned analysis unit, By analyzing detailed user behavior data such as ad viewing time and click patterns, we identify the factors that contribute to ad effectiveness. The system described in Appendix 1, characterized by the features described herein. (Note 15) The aforementioned analysis unit, Apply different analytical methods based on the ad display environment. The system described in Appendix 1, characterized by the features described herein. (Note 16) The aforementioned analysis unit, It estimates the user's emotions and adjusts how the analysis results are displayed based on the estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 17) The aforementioned analysis unit, Analyze the effectiveness of advertisements by region, taking into account the geographical location of the ad viewers. The system described in Appendix 1, characterized by the features described herein. (Note 18) The aforementioned analysis unit, We analyze data from different platforms, such as social media and news sites, to evaluate the overall effectiveness of advertising. The system described in Appendix 1, characterized by the features described herein. (Note 19) The generating unit is It estimates the user's emotions and adjusts the tone and style of the generated text based on those estimated emotions. The system described in Appendix 1, characterized by the features described herein. (Note 20) The generating unit is Customize the content of the text generated based on the ad display environment. The system described in Appendix 1, characterized by the features described herein. (Note 21) The generating unit is Personalized text is generated based on the past behavioral data of ad viewers. The system described in Appendix 1, characterized by the features described herein. (Note 22) The generating unit is It estimates the user's emotions and adjusts the length of the generated text based on those emotions. The system described in Appendix 1, characterized by the features described herein. (Note 23) The generating unit is The system generates optimal text for each region, taking into account the geographical location of the ad audience. The system described in Appendix 1, characterized by the features described herein. (Note 24) The generating unit is Generate text suitable for different platforms, such as social media and news sites. The system described in Appendix 1, characterized by the features described herein. (Note 25) The verification unit, We estimate user sentiment and adjust the advertising effectiveness verification method based on the estimated user sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 26) The verification unit, We collect verification data based on the ad display environment and conduct detailed effectiveness analysis. The system described in Appendix 1, characterized by the features described herein. (Note 27) The verification unit, We build predictive models for advertising effectiveness based on past behavioral data of ad viewers. The system described in Appendix 1, characterized by the features described herein. (Note 28) The verification unit, It estimates the user's emotions and adjusts how the verification results are displayed based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 29) The verification unit, We will examine the effectiveness of advertising in each region, taking into account the geographical location of the ad's audience. The system described in Appendix 1, characterized by the features described herein. (Note 30) The verification unit, We will verify the effectiveness of advertising across different platforms, such as social media and news sites. The system described in Appendix 1, characterized by the features described herein. (Note 31) The optimization unit, We estimate user sentiment and adjust how ad text is optimized based on that estimated sentiment. The system described in Appendix 1, characterized by the features described herein. (Note 32) The optimization unit, Apply an optimization algorithm based on the ad display environment. The system described in Appendix 1, characterized by the features described herein. (Note 33) The optimization unit, Personalized optimization is performed based on the past behavioral data of ad viewers. The system described in Appendix 1, characterized by the features described herein. (Note 34) The optimization unit, It estimates user emotions and determines optimization priorities based on the estimated user emotions. The system described in Appendix 1, characterized by the features described herein. (Note 35) The optimization unit, We provide optimal ad text for each region, taking into account the geographical location of the ad's audience. The system described in Appendix 1, characterized by the features described herein. (Note 36) The optimization unit, Optimizing for different platforms such as social media and news sites. The system described in Appendix 1, characterized by the features described herein. [Explanation of Symbols]

[0195] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots

Claims

1. The data collection department collects past advertising results, An analysis unit analyzes the advertising results collected by the collection unit, A generation unit generates text that is optimal for the target based on the analysis results obtained by the analysis unit, A verification unit delivers advertisements using the text generated by the generation unit and verifies their effectiveness. The system includes an optimization unit that improves and optimizes the advertising text based on the results obtained by the verification unit. A system characterized by the following features.

2. The aforementioned collection unit is Collect detailed data such as ad click-through rates and conversion rates. The system according to feature 1.

3. The aforementioned analysis unit, Based on the collected data, identify the most suitable words for your target audience. The system according to feature 1.

4. The generating unit is Generate text that is best suited to the target using identified words. The system according to feature 1.

5. The verification unit, The system delivers ads using generated text and measures click-through rates and conversion rates. The system according to feature 1.

6. The optimization unit, Based on the verification results, we will revise the ad text and deliver the ad again. The system according to feature 1.

7. The aforementioned collection unit is We estimate the user's emotions and adjust the timing of ad data collection based on those estimated emotions. The system according to feature 1.

8. The aforementioned collection unit is Select the types of data to collect based on the advertising display environment. The system according to feature 1.

9. The aforementioned collection unit is The system also collects user behavior data such as ad viewing time and scrolling speed, enabling detailed analysis of ad effectiveness. The system according to feature 1.

10. The aforementioned collection unit is It estimates user sentiment and prioritizes the advertising data to collect based on the estimated user sentiment. The system according to feature 1.

Images