System

Abstract

An object of a system according to an embodiment is to optimize a design and a message of an Internet advertisement in a short period of time.SOLUTION: A system includes a prompt input unit, an advertisement generation unit, an AB test unit, a prompt improvement unit, and a content improvement unit. The prompt input unit receives a prompt from a user. The advertisement generation unit generates advertisement content based on the prompt received by the prompt input unit. The AB test unit tests the advertisement content generated by the advertisement generation unit. The prompt improvement unit improves the prompt based on the test result obtained by the AB test unit. The content improving unit regenerates the advertisement content based on the prompt improved by the prompt improving unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Conventional technology has the drawback of requiring a lot of time and effort to optimize the design and message of internet advertisements.

[0005] The system according to the embodiment aims to optimize the design and message of internet advertisements in a short period of time. [Means for solving the problem]

[0006] A system according to an embodiment includes a prompt input unit, an advertisement generation unit, an AB testing unit, a prompt improvement unit, and a content improvement unit. The prompt input unit receives a prompt from a user. The advertisement generation unit generates advertisement content based on the prompt received by the prompt input unit. The AB testing unit tests the advertisement content generated by the advertisement generation unit. The prompt improvement unit improves the prompt based on the test results obtained by the AB testing unit. The content improvement unit regenerates the advertisement content based on the prompt improved by the prompt improvement unit. [Effects of the Invention]

[0007] The system according to the embodiment can optimize the design and message of an internet advertisement in a short period of time. [Brief explanation of the drawings]

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

[0028] (Example 1) An advertisement optimization system according to an embodiment of the present invention is a system that optimizes the design and message of Internet advertisements by repeatedly performing A / B testing and content improvement in a short period of time. As a result, the advertisement optimization system automates the generation and improvement of advertisement content and can quickly provide optimal advertisements.

[0029] An advertising optimization system according to an embodiment includes a prompt input unit, an advertisement generation unit, an AB testing unit, a prompt improvement unit, and a content improvement unit. The prompt input unit receives a prompt from a user. For example, the user inputs a prompt such as, "Please create an advertisement for a new product." The advertisement generation unit generates advertising content based on the prompt received by the prompt input unit. For example, the generation AI generates advertising copy including banner images with different designs and different messages. The AB testing unit tests the advertising content generated by the advertisement generation unit. For example, the AI ​​distributes advertisements online and collects performance indicators such as click rates and conversion rates. The prompt improvement unit improves the prompt based on the test results obtained by the AB testing unit. For example, the AI ​​creates a new prompt incorporating elements of an advertisement with a high click rate. The content improvement unit regenerates the advertising content based on the prompt improved by the prompt improvement unit. For example, the AI ​​performs another AB test using the advertising content generated using the new prompt. This enables the advertising optimization system to automate the generation and improvement of advertising content and quickly provide optimal advertisements.

[0030] The prompt input unit can analyze the user's past prompt history and automatically suggest the most appropriate prompt. For example, the prompt input unit stores the prompt history entered by the user in a database and builds a system that automatically suggests the most appropriate prompt based on that history. For example, it analyzes past success stories and suggests similar prompts. The prompt input unit also analyzes the prompt history and develops an algorithm that learns the user's preferences and tendencies. For example, for a user who frequently uses specific keywords or phrases, it suggests prompts related to those. The prompt input unit also builds a system that predicts the effectiveness of prompts entered by the user based on the past prompt history and suggests the most appropriate prompt in real time. For example, it predicts click rates and conversion rates based on past data. This makes it possible to suggest the most appropriate prompt based on the user's past history.

[0031] The prompt input unit can ask additional questions interactively when entering a prompt to more accurately understand the user's intention. For example, the prompt input unit constructs a system in which the generation AI asks the user additional questions when entering a prompt, thereby more accurately understanding the user's intention. For example, it asks a question such as, "What kind of target demographic do you have in mind?" The prompt input unit also develops an algorithm that interactively confirms the user's intention and makes the content of the prompt more specific. For example, it automatically modifies the prompt based on the user's answer. The prompt input unit also constructs a system that resolves ambiguous parts of the prompt through dialogue with the user and provides more specific instructions to the generation AI. For example, it asks a question such as, "Please tell me the specific features of your product." This makes it possible to more accurately understand the user's intention and generate appropriate prompts.

[0032] The prompt input unit can match the prompt input with voice input and generate a prompt using voice recognition technology. The prompt input unit, for example, uses voice recognition technology to build a system that allows a user to input a prompt by voice. For example, a user might say, "Please create an advertisement for a new product." The prompt input unit also develops an algorithm that converts the voice-input prompt into text and provides it to the generation AI. For example, it performs high-precision text conversion using voice recognition technology. The prompt input unit also builds a system that analyzes the voice-input prompt and understands the user's intent. For example, it analyzes the tone of the voice and emphasized parts to specify the content of the prompt. This makes it possible to respond to voice input and generate a prompt using voice recognition technology.

[0033] The prompt input unit can present examples of prompts that other users have successfully used as reference when entering a prompt. The prompt input unit, for example, builds a system that stores examples of prompts that other users have successfully used in a database and presents them as reference when entering a prompt. For example, it displays a list of past success cases. The prompt input unit also analyzes successful examples of prompts and develops an algorithm that automatically suggests examples related to the prompt entered by the user. For example, it suggests similar prompts. The prompt input unit also builds a system that predicts the effectiveness of a prompt entered by a user based on examples of prompts that other users have successfully used. For example, it suggests a prompt that incorporates elements of the success cases. This makes it possible to generate prompts by referring to the success cases of other users.

[0034] The advertising generation unit can learn from success stories and generate more effective advertising content. For example, the advertising generation unit builds a system that has the generation AI learn from past success stories and generates advertising content based on that knowledge. For example, it generates new advertisements based on advertisements with high click-through rates in the past. The advertising generation unit also builds a database of success stories and develops an algorithm that uses the generation AI to refer to that data to generate advertising content. For example, it generates advertisements that incorporate elements of success stories. The advertising generation unit also builds a system that has the generation AI analyze past success stories and generate effective advertising content based on those patterns. For example, it uses the design and messages of success stories as reference. In this way, it can learn from past success stories and generate effective advertising content.

[0035] The advertisement generation unit can generate personalized advertisement content by taking into account attribute information of the target audience. For example, the advertisement generation unit collects attribute information of the target audience (age, gender, interests, etc.) and builds a system that generates personalized advertisement content based on that information. For example, it generates advertisements aimed at a specific age group. The advertisement generation unit also analyzes the attribute information of the target audience and develops an algorithm that allows the generation AI to generate advertisement content based on that data. For example, it generates advertisements based on interests and concerns. The advertisement generation unit also collects attribute information of the target audience in real time and builds a system that generates personalized advertisement content based on that data. For example, it generates advertisements based on user behavior data. This makes it possible to generate personalized advertisement content by taking into account the attribute information of the target audience.

[0036] The advertising generation unit can generate advertising content that combines different media formats when generating advertising content. For example, the advertising generation unit builds a system in which a generation AI generates advertising content that combines different media formats (video, audio, text). For example, a text message is added to a video advertisement. The advertising generation unit also develops an algorithm that generates more effective advertising content by combining different media formats. For example, a visual element is added to an audio advertisement. The advertising generation unit also builds a system in which a generation AI generates advertising content that combines different media formats in real time. For example, the optimal media format is selected based on user behavior data. This makes it possible to generate advertising content that combines different media formats.

[0037] The advertisement generation unit can reflect the latest trends and news in the advertising content it generates. For example, the advertisement generation unit builds a system in which a generation AI automatically collects the latest trends and news and generates advertising content based on that information. For example, it generates advertisements that reflect the latest fashion trends. The advertisement generation unit also analyzes trends and news and develops an algorithm in which the generation AI generates advertising content based on that data. For example, it generates advertisements that incorporate hot news. The advertisement generation unit also builds a system in which the advertisement generation unit collects the latest trends and news in real time and generates advertising content based on that information. For example, it reflects trend information that matches the user's interests. This makes it possible to generate advertising content that reflects the latest trends and news.

[0038] The AB Testing Department can collect AB test results in real time and analyze them immediately. For example, the AB Testing Department builds a system that collects AB test results in real time and analyzes them immediately. For example, it develops a dashboard that displays click rates and conversion rates in real time. The AB Testing Department also analyzes AB test data collected in real time and develops algorithms that instantly identify effective advertising content. For example, it monitors data fluctuations in real time and selects the optimal advertisement. The AB Testing Department also collects AB test results in real time and builds a system that instantly improves advertising content based on that data. For example, it provides a function to automatically replace ineffective advertisements. This allows AB test results to be collected in real time and analyzed immediately.

[0039] The AB testing department can subdivide the subjects of AB tests and measure the effectiveness for each different segment. For example, the AB testing department will subdivide the subjects of AB tests and build a system to measure the effectiveness for each different segment. For example, it will conduct tests for each attribute such as age, gender, and region. The AB testing department will also analyze the results of AB tests for each different segment and develop an algorithm to identify the optimal advertising content for each segment. For example, it will select advertisements that are effective for a specific age group. The AB testing department will also subdivide the subjects of AB tests and build a system to measure the effectiveness for each different segment in real time. For example, it will provide a dashboard that displays the click rate and conversion rate for each segment. This will allow the effectiveness of AB tests to be measured for each different segment.

[0040] The AB Testing Department can compare AB test results across different regions and cultural spheres to measure effectiveness from a global perspective. For example, the AB Testing Department builds a system that compares AB test results across different regions and cultural spheres to measure effectiveness from a global perspective. For example, it develops a dashboard that displays click rates and conversion rates for each region. The AB Testing Department also analyzes AB test results for different regions and cultural spheres and develops algorithms that identify the optimal advertising content for each region. For example, it selects advertisements that are effective in specific cultural spheres. The AB Testing Department also collects AB test results in real time across different regions and cultural spheres and builds a system that improves advertising content based on that data. For example, it provides a function that automatically replaces advertisements based on regional effectiveness. This makes it possible to compare AB test results across different regions and cultural spheres and measure effectiveness from a global perspective.

[0041] The AB testing department can integrate the results of AB tests with other marketing data to evaluate the overall effectiveness. For example, the AB testing department builds a system that integrates the results of AB tests with other marketing data to evaluate the overall effectiveness. For example, it integrates and evaluates advertising click-through rates and sales data. The AB testing department also develops algorithms that analyze other marketing data and integrate it with the results of AB tests. For example, it evaluates the effectiveness of advertising based on user behavior data and purchase history. The AB testing department also integrates the results of AB tests with other marketing data in real time and builds a system that improves advertising content based on that data. For example, it provides a function that automatically replaces advertisements based on sales data. This allows the results of AB tests to be evaluated by integrating them with other marketing data.

[0042] The prompt improvement department can develop an algorithm that allows the generation AI to automatically improve prompts based on the results of AB testing. For example, the prompt improvement department develops an algorithm that allows the generation AI to automatically improve prompts based on the results of AB testing. For example, it generates a new prompt that incorporates elements of an advertisement that had a high click-through rate. The prompt improvement department also analyzes AB test data and builds a system that allows the generation AI to automatically improve prompts based on that data. For example, it generates prompts that eliminate ineffective elements and emphasize effective elements. The prompt improvement department also collects AB test results in real time and builds a system that allows the generation AI to automatically improve prompts based on that data. For example, it generates highly effective prompts in real time. This makes it possible to develop an algorithm that allows the generation AI to automatically improve prompts based on the results of AB testing.

[0043] The prompt improvement department can refer to past improvement history when improving a prompt and select the optimal improvement method. For example, when improving a prompt, the prompt improvement department stores past improvement history in a database and builds a system that selects the optimal improvement method based on that history. For example, it improves the prompt by referring to past success stories. The prompt improvement department also analyzes past improvement history and develops an algorithm that allows the generation AI to select the optimal improvement method based on that data. For example, it automatically suggests highly effective improvement methods. The prompt improvement department also builds a system that refers to past improvement history in real time when improving a prompt and selects the optimal improvement method based on that data. For example, it suggests highly effective improvement methods in real time. This makes it possible to refer to past improvement history and select the optimal improvement method.

[0044] The prompt improvement department can refer to success stories from different industries when improving prompts. For example, when improving prompts, the prompt improvement department stores success stories from different industries in a database and builds a system to improve prompts based on those stories. For example, the prompt improvement department improves prompts by referring to success stories from other industries. The prompt improvement department also analyzes success stories from different industries and develops an algorithm for the generation AI to improve prompts based on that data. For example, it generates prompts that incorporate successful elements from other industries. The prompt improvement department also refers to success stories from different industries in real time when improving prompts and builds a system to improve prompts based on that data. For example, it reflects success stories from other industries in real time. This makes it possible to improve prompts by referring to success stories from different industries.

[0045] The prompt improvement unit can improve prompts from a global perspective, adapting them to different languages ​​and cultures. For example, the prompt improvement unit builds a system that improves prompts to accommodate different languages ​​and cultures. For example, a generation AI generates prompts that are compatible with multiple languages. The prompt improvement unit also develops an algorithm that improves prompts to accommodate different languages ​​and cultures. For example, it generates prompts that take cultural nuances into consideration. The prompt improvement unit also builds a system that improves prompts from a global perspective. For example, it generates prompts that are optimal for users in different regions. This makes it possible to improve prompts from a global perspective, adapting to different languages ​​and cultures.

[0046] The content improvement department can develop an algorithm that allows the generation AI to automatically suggest the optimal improvement method. For example, the content improvement department develops an algorithm that allows the generation AI to automatically suggest the optimal improvement method. For example, it suggests effective improvement methods based on past data. The content improvement department also builds a system that allows the generation AI to automatically suggest the optimal improvement method when improving content. For example, it suggests improvement methods based on click rates and conversion rates. The content improvement department also develops an algorithm that allows the generation AI to automatically suggest the optimal improvement method, and builds a system that improves content in real time. For example, it suggests improvement methods based on user feedback. This makes it possible to develop an algorithm that allows the generation AI to automatically suggest the optimal improvement method.

[0047] When improving content, the content improvement department can refer to past improvement history and select the optimal improvement method. For example, when improving content, the content improvement department will store past improvement history in a database and build a system that selects the optimal improvement method based on that history. For example, it will improve content by referring to past success stories. The content improvement department will also analyze past improvement history and develop an algorithm that will allow the generation AI to select the optimal improvement method based on that data. For example, it will automatically suggest highly effective improvement methods. The content improvement department will also refer to past improvement history in real time when improving content and build a system that selects the optimal improvement method based on that data. For example, it will suggest highly effective improvement methods in real time. This makes it possible to refer to past improvement history and select the optimal improvement method.

[0048] The content improvement department can improve content in different media formats and measure the overall effectiveness. For example, the content improvement department builds a system in which a generation AI improves content in different media formats (video, audio, text). For example, adding a text message to a video advertisement. The content improvement department also develops an algorithm that generates more effective content by combining different media formats. For example, adding visual elements to an audio advertisement. The content improvement department also builds a system in which a generation AI generates content that combines different media formats in real time and measures its effectiveness. For example, it selects the optimal media format based on user behavior data. This makes it possible to improve content in different media formats and measure the overall effectiveness.

[0049] The content improvement department can improve content from a global perspective, adapting it to different regions and cultural spheres. For example, the content improvement department builds a system that improves content to suit different regions and cultural spheres. For example, a generative AI generates content that is multilingual. The content improvement department also develops an algorithm that improves content to suit different regions and cultural spheres. For example, it generates content that takes cultural nuances into consideration. The content improvement department also builds a system that improves content from a global perspective. For example, it generates content that is optimal for users in different regions. This makes it possible to improve content from a global perspective, adapting it to different regions and cultural spheres.

[0050] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0051] The advertising optimization system can also analyze a user's behavioral history to personalize advertising content. For example, it can generate highly relevant ads based on the ads the user has clicked on or the products the user has purchased in the past. It can also analyze a user's browsing history to suggest ads that are likely to interest the user. It can also monitor a user's social media activity and generate ads based on topics that are likely to interest the user. This makes it possible to utilize a user's behavioral history to provide more effective advertising content.

[0052] The ad optimization system can also take into account user device information to select the optimal ad format. For example, it can provide vertical video ads to smartphone users and horizontal banner ads to desktop users. It can also analyze the user's internet connection speed and deliver rich media ads to those with high-speed connections and lightweight text ads to those with slower connections. It can also automatically adjust the optimal ad layout depending on the screen size and resolution of the user's device. This makes it possible to utilize user device information to provide the optimal ad format.

[0053] The advertising optimization system can also utilize the user's location information to generate advertising content that is specific to the region. For example, if the user is in a particular city, advertisements related to stores and events in that region can be displayed. Coupons and sales information for nearby stores can also be provided based on the user's location information. Furthermore, if the user is traveling, advertisements for tourist spots and restaurants in the user's travel destination can be displayed. In this way, the user's location information can be utilized to provide advertising content that is specific to the region.

[0054] The ad optimization system can also analyze a user's voice input and generate advertising content based on the voice command. For example, if a user voice-inputs, "I'm looking for a new smartphone," an advertisement for a smartphone that meets the request can be displayed. The system can also analyze the user's voice tone and emotions and adjust the tone and message of the advertisement based on the results. Furthermore, the system can convert the voice input into text and generate advertising content based on that text. This allows the system to utilize voice input to provide advertising content that meets the user's request.

[0055] The advertising optimization system can also analyze a user's social media activity and generate advertising content based on topics that are likely to interest them. For example, if a user frequently posts about a particular brand or product, it can display ads related to that brand or product. It can also suggest relevant ads based on the topics that the user's followers and friends are interested in. It can also monitor a user's social media activity in real time and dynamically adjust advertising content based on changes in that activity. This allows it to utilize a user's social media activity to provide advertising content that is likely to interest them.

[0056] The advertising optimization system can also analyze a user's purchasing history to generate highly relevant advertising content. For example, it can display advertisements for accessories or additional items related to products the user has previously purchased. It can also suggest advertisements for new products that are likely to interest the user based on the user's purchasing history. It can also monitor a user's purchasing history in real time and dynamically adjust advertising content according to changes in the history. This makes it possible to provide highly relevant advertising content by utilizing the user's purchasing history.

[0057] The processing flow of the first embodiment will be briefly explained below.

[0058] Step 1: The prompt input unit receives a prompt from the user. For example, the user inputs a prompt such as "Please create an advertisement for a new product." Step 2: The advertisement generation unit generates advertisement content based on the prompt received by the prompt input unit. For example, the generation AI generates advertisement copy including a banner image with a different design and a different message. Step 3: The AB testing unit tests the advertising content generated by the advertising generation unit. For example, it distributes the advertisements online and collects performance indicators such as click rates and conversion rates. Step 4: The prompt refinement team refines the prompt based on the test results obtained by the AB testing team. For example, they create a new prompt that incorporates elements of the advertisement that had a high click rate. Step 5: The content improvement unit regenerates the advertising content based on the prompt improved by the prompt improvement unit. For example, the content improvement unit re-runs the AB test using the advertising content generated using the new prompt.

[0059] (Example 2) An advertisement optimization system according to an embodiment of the present invention is a system that optimizes the design and message of Internet advertisements by repeatedly performing A / B testing and content improvement in a short period of time. As a result, the advertisement optimization system automates the generation and improvement of advertisement content and can quickly provide optimal advertisements.

[0060] An advertising optimization system according to an embodiment includes a prompt input unit, an advertisement generation unit, an AB testing unit, a prompt improvement unit, and a content improvement unit. The prompt input unit receives a prompt from a user. For example, the user inputs a prompt such as, "Please create an advertisement for a new product." The advertisement generation unit generates advertising content based on the prompt received by the prompt input unit. For example, the generation AI generates advertising copy including banner images with different designs and different messages. The AB testing unit tests the advertising content generated by the advertisement generation unit. For example, the AI ​​distributes advertisements online and collects performance indicators such as click rates and conversion rates. The prompt improvement unit improves the prompt based on the test results obtained by the AB testing unit. For example, the AI ​​creates a new prompt incorporating elements of an advertisement with a high click rate. The content improvement unit regenerates the advertising content based on the prompt improved by the prompt improvement unit. For example, the AI ​​performs another AB test using the advertising content generated using the new prompt. This enables the advertising optimization system to automate the generation and improvement of advertising content and quickly provide optimal advertisements.

[0061] The prompt input unit can analyze the user's past prompt history and automatically suggest the most appropriate prompt. For example, the prompt input unit stores the prompt history entered by the user in a database and builds a system that automatically suggests the most appropriate prompt based on that history. For example, it analyzes past success stories and suggests similar prompts. The prompt input unit also analyzes the prompt history and develops an algorithm that learns the user's preferences and tendencies. For example, for a user who frequently uses specific keywords or phrases, it suggests prompts related to those. The prompt input unit also builds a system that predicts the effectiveness of prompts entered by the user based on the past prompt history and suggests the most appropriate prompt in real time. For example, it predicts click rates and conversion rates based on past data. This makes it possible to suggest the most appropriate prompt based on the user's past history.

[0062] The prompt input unit can ask additional questions interactively when entering a prompt to more accurately understand the user's intention. For example, the prompt input unit constructs a system in which the generation AI asks the user additional questions when entering a prompt, thereby more accurately understanding the user's intention. For example, it asks a question such as, "What kind of target demographic do you have in mind?" The prompt input unit also develops an algorithm that interactively confirms the user's intention and makes the content of the prompt more specific. For example, it automatically modifies the prompt based on the user's answer. The prompt input unit also constructs a system that resolves ambiguous parts of the prompt through dialogue with the user and provides more specific instructions to the generation AI. For example, it asks a question such as, "Please tell me the specific features of your product." This makes it possible to more accurately understand the user's intention and generate appropriate prompts.

[0063] The prompt input unit uses the emotion estimation function to generate prompts according to the user's emotional state, thereby enabling the creation of more effective advertising content. The prompt input unit, for example, uses the emotion estimation function to analyze the user's emotional state in real time and builds a system that generates prompts based on the results. For example, if the user is in a positive emotional state, the prompt input unit proposes prompts with a bright tone. The prompt input unit also develops an algorithm that adjusts the content of the prompt based on the user's emotional state. For example, if the user is feeling stressed, the prompt input unit proposes prompts with a relaxed tone. The prompt input unit also builds a system that generates prompts optimal for the user's emotional state based on the emotion estimation data. For example, if the user is excited, the prompt proposes prompts with an energetic tone. This makes it possible to generate prompts according to the user's emotional state and create effective advertising content.

[0064] The prompt input unit can match the prompt input with voice input and generate a prompt using voice recognition technology. The prompt input unit, for example, uses voice recognition technology to build a system that allows a user to input a prompt by voice. For example, a user might say, "Please create an advertisement for a new product." The prompt input unit also develops an algorithm that converts the voice-input prompt into text and provides it to the generation AI. For example, it performs high-precision text conversion using voice recognition technology. The prompt input unit also builds a system that analyzes the voice-input prompt and understands the user's intent. For example, it analyzes the tone of the voice and emphasized parts to specify the content of the prompt. This makes it possible to respond to voice input and generate a prompt using voice recognition technology.

[0065] The prompt input unit can present examples of prompts that other users have successfully used as reference when entering a prompt. The prompt input unit, for example, builds a system that stores examples of prompts that other users have successfully used in a database and presents them as reference when entering a prompt. For example, it displays a list of past success cases. The prompt input unit also analyzes successful examples of prompts and develops an algorithm that automatically suggests examples related to the prompt entered by the user. For example, it suggests similar prompts. The prompt input unit also builds a system that predicts the effectiveness of a prompt entered by a user based on examples of prompts that other users have successfully used. For example, it suggests a prompt that incorporates elements of the success cases. This makes it possible to generate prompts by referring to the success cases of other users.

[0066] The prompt input unit can analyze the user's emotional state in real time when the prompt is input, and suggest a prompt that elicits positive emotions. The prompt input unit, for example, builds a system that analyzes the user's emotional state in real time when the prompt is input, and suggests a prompt that elicits positive emotions. For example, if the user is feeling depressed, it suggests a prompt that includes an encouraging message. The prompt input unit also uses an emotion estimation function to develop an algorithm that analyzes the user's emotional state and generates a prompt to elicit positive emotions. For example, if the user is feeling stressed, it suggests a prompt with a relaxing tone. The prompt input unit also builds a system that suggests a prompt that elicits positive emotions in real time based on the user's emotional state. For example, if the user is excited, it suggests a prompt with an energetic tone. In this way, it is possible to analyze the user's emotional state and suggest a prompt that elicits positive emotions.

[0067] The advertising generation unit can learn from success stories and generate more effective advertising content. For example, the advertising generation unit builds a system that has the generation AI learn from past success stories and generates advertising content based on that knowledge. For example, it generates new advertisements based on advertisements with high click-through rates in the past. The advertising generation unit also builds a database of success stories and develops an algorithm that uses the generation AI to refer to that data to generate advertising content. For example, it generates advertisements that incorporate elements of success stories. The advertising generation unit also builds a system that has the generation AI analyze past success stories and generate effective advertising content based on those patterns. For example, it uses the design and messages of success stories as reference. In this way, it can learn from past success stories and generate effective advertising content.

[0068] The advertisement generation unit can generate personalized advertisement content by taking into account attribute information of the target audience. For example, the advertisement generation unit collects attribute information of the target audience (age, gender, interests, etc.) and builds a system that generates personalized advertisement content based on that information. For example, it generates advertisements aimed at a specific age group. The advertisement generation unit also analyzes the attribute information of the target audience and develops an algorithm that allows the generation AI to generate advertisement content based on that data. For example, it generates advertisements based on interests and concerns. The advertisement generation unit also collects attribute information of the target audience in real time and builds a system that generates personalized advertisement content based on that data. For example, it generates advertisements based on user behavior data. This makes it possible to generate personalized advertisement content by taking into account the attribute information of the target audience.

[0069] The advertisement generation unit can use the emotion estimation function to generate advertising content that appeals to the emotions of the target audience. For example, the advertisement generation unit uses the emotion estimation function to analyze the emotional state of the target audience and builds a system that generates advertising content based on the results. For example, it generates advertisements that elicit positive emotions. The advertisement generation unit also develops an algorithm that uses a generative AI to generate advertising content that appeals to emotions based on the emotional state of the target audience. For example, it generates advertisements that include moving messages. The advertisement generation unit also builds a system that generates advertising content that is optimal for the emotions of the target audience based on the emotion estimation data. For example, if a user is excited, it generates an energetic advertisement. This makes it possible to generate advertising content that appeals to the emotions of the target audience.

[0070] The advertising generation unit can generate advertising content that combines different media formats when generating advertising content. For example, the advertising generation unit builds a system in which a generation AI generates advertising content that combines different media formats (video, audio, text). For example, a text message is added to a video advertisement. The advertising generation unit also develops an algorithm that generates more effective advertising content by combining different media formats. For example, a visual element is added to an audio advertisement. The advertising generation unit also builds a system in which a generation AI generates advertising content that combines different media formats in real time. For example, the optimal media format is selected based on user behavior data. This makes it possible to generate advertising content that combines different media formats.

[0071] The advertisement generation unit can reflect the latest trends and news in the advertising content it generates. For example, the advertisement generation unit builds a system in which a generation AI automatically collects the latest trends and news and generates advertising content based on that information. For example, it generates advertisements that reflect the latest fashion trends. The advertisement generation unit also analyzes trends and news and develops an algorithm in which the generation AI generates advertising content based on that data. For example, it generates advertisements that incorporate hot news. The advertisement generation unit also builds a system in which the advertisement generation unit collects the latest trends and news in real time and generates advertising content based on that information. For example, it reflects trend information that matches the user's interests. This makes it possible to generate advertising content that reflects the latest trends and news.

[0072] The advertisement generation unit can use the emotion estimation function to generate advertising content based on the emotions of the target audience in real time. The advertisement generation unit, for example, uses the emotion estimation function to analyze the emotional state of the target audience in real time and builds a system that generates advertising content based on the results. For example, if a user is excited, an energetic advertisement is generated. The advertisement generation unit also develops an algorithm that uses a generative AI to generate emotionally appealing advertising content in real time based on the emotional state of the target audience. For example, an advertisement containing an inspiring message is generated. The advertisement generation unit also builds a system that generates advertising content that is optimal for the emotions of the target audience in real time based on the emotion estimation data. For example, if a user is relaxed, an advertisement with a calm tone is generated. This makes it possible to generate advertising content based on the emotions of the target audience in real time.

[0073] The AB Testing Department can collect AB test results in real time and analyze them immediately. For example, the AB Testing Department builds a system that collects AB test results in real time and analyzes them immediately. For example, it develops a dashboard that displays click rates and conversion rates in real time. The AB Testing Department also analyzes AB test data collected in real time and develops algorithms that instantly identify effective advertising content. For example, it monitors data fluctuations in real time and selects the optimal advertisement. The AB Testing Department also collects AB test results in real time and builds a system that instantly improves advertising content based on that data. For example, it provides a function to automatically replace ineffective advertisements. This allows AB test results to be collected in real time and analyzed immediately.

[0074] The AB testing department can subdivide the subjects of AB tests and measure the effectiveness for each different segment. For example, the AB testing department will subdivide the subjects of AB tests and build a system to measure the effectiveness for each different segment. For example, it will conduct tests for each attribute such as age, gender, and region. The AB testing department will also analyze the results of AB tests for each different segment and develop an algorithm to identify the optimal advertising content for each segment. For example, it will select advertisements that are effective for a specific age group. The AB testing department will also subdivide the subjects of AB tests and build a system to measure the effectiveness for each different segment in real time. For example, it will provide a dashboard that displays the click rate and conversion rate for each segment. This will allow the effectiveness of AB tests to be measured for each different segment.

[0075] The AB testing unit can use the emotion estimation function to collect users' emotional responses during AB testing and reflect them in the results. For example, the AB testing unit can use the emotion estimation function to collect users' emotional responses during AB testing in real time and build a system that analyzes the results of the AB test based on that data. For example, it can analyze the user's facial expressions and voice and calculate an emotional score. The AB testing unit can also analyze the results of AB testing based on the user's emotional response data and develop an algorithm that identifies advertising content that appeals to emotions. For example, it can select advertisements that have a high number of positive emotional responses. The AB testing unit can also collect AB test results in real time based on the emotion estimation data and build a system that instantly improves advertising content. For example, it can provide a function that automatically replaces advertisements with low emotional scores. This makes it possible to collect users' emotional responses during AB testing and reflect them in the results.

[0076] The AB Testing Department can compare AB test results across different regions and cultural spheres to measure effectiveness from a global perspective. For example, the AB Testing Department builds a system that compares AB test results across different regions and cultural spheres to measure effectiveness from a global perspective. For example, it develops a dashboard that displays click rates and conversion rates for each region. The AB Testing Department also analyzes AB test results for different regions and cultural spheres and develops algorithms that identify the optimal advertising content for each region. For example, it selects advertisements that are effective in specific cultural spheres. The AB Testing Department also collects AB test results in real time across different regions and cultural spheres and builds a system that improves advertising content based on that data. For example, it provides a function that automatically replaces advertisements based on regional effectiveness. This makes it possible to compare AB test results across different regions and cultural spheres and measure effectiveness from a global perspective.

[0077] The AB testing department can integrate the results of AB tests with other marketing data to evaluate the overall effectiveness. For example, the AB testing department builds a system that integrates the results of AB tests with other marketing data to evaluate the overall effectiveness. For example, it integrates and evaluates advertising click-through rates and sales data. The AB testing department also develops algorithms that analyze other marketing data and integrate it with the results of AB tests. For example, it evaluates the effectiveness of advertising based on user behavior data and purchase history. The AB testing department also integrates the results of AB tests with other marketing data in real time and builds a system that improves advertising content based on that data. For example, it provides a function that automatically replaces advertisements based on sales data. This allows the results of AB tests to be evaluated by integrating them with other marketing data.

[0078] The AB testing unit uses the emotion estimation function to monitor users' emotional responses during AB testing in real time and identify optimal advertising content. For example, the AB testing unit uses the emotion estimation function to build a system that monitors users' emotional responses during AB testing in real time. For example, it analyzes the user's facial expressions and voice and calculates an emotional score. The AB testing unit also analyzes the results of AB testing in real time based on the user's emotional response data and develops an algorithm that identifies optimal advertising content. For example, it selects advertisements that have a high number of positive emotional responses. The AB testing unit also collects the results of AB testing in real time based on the emotion estimation data and builds a system that instantly improves advertising content. For example, it provides a function to automatically replace advertisements with low emotional scores. This makes it possible to monitor users' emotional responses during AB testing in real time and identify optimal advertising content.

[0079] The prompt improvement department can develop an algorithm that allows the generation AI to automatically improve prompts based on the results of AB testing. For example, the prompt improvement department develops an algorithm that allows the generation AI to automatically improve prompts based on the results of AB testing. For example, it generates a new prompt that incorporates elements of an advertisement that had a high click-through rate. The prompt improvement department also analyzes AB test data and builds a system that allows the generation AI to automatically improve prompts based on that data. For example, it generates prompts that eliminate ineffective elements and emphasize effective elements. The prompt improvement department also collects AB test results in real time and builds a system that allows the generation AI to automatically improve prompts based on that data. For example, it generates highly effective prompts in real time. This makes it possible to develop an algorithm that allows the generation AI to automatically improve prompts based on the results of AB testing.

[0080] The prompt improvement department can refer to past improvement history when improving a prompt and select the optimal improvement method. For example, when improving a prompt, the prompt improvement department stores past improvement history in a database and builds a system that selects the optimal improvement method based on that history. For example, it improves the prompt by referring to past success stories. The prompt improvement department also analyzes past improvement history and develops an algorithm that allows the generation AI to select the optimal improvement method based on that data. For example, it automatically suggests highly effective improvement methods. The prompt improvement department also builds a system that refers to past improvement history in real time when improving a prompt and selects the optimal improvement method based on that data. For example, it suggests highly effective improvement methods in real time. This makes it possible to refer to past improvement history and select the optimal improvement method.

[0081] The prompt improvement unit can use the emotion estimation function to improve prompts based on the user's emotions. For example, the prompt improvement unit uses the emotion estimation function to analyze the user's emotional state and build a system that improves prompts based on the results. For example, it generates prompts that elicit positive emotions. The prompt improvement unit also develops an algorithm that uses a generation AI to improve prompts based on emotions, based on the user's emotional state. For example, it generates prompts that include moving messages. The prompt improvement unit also builds a system that generates prompts that are optimal for the user's emotions, based on the emotion estimation data. For example, if the user is relaxed, it generates prompts with a calm tone. This makes it possible to improve prompts based on the user's emotions.

[0082] The prompt improvement department can refer to success stories from different industries when improving prompts. For example, when improving prompts, the prompt improvement department stores success stories from different industries in a database and builds a system to improve prompts based on those stories. For example, the prompt improvement department improves prompts by referring to success stories from other industries. The prompt improvement department also analyzes success stories from different industries and develops an algorithm for the generation AI to improve prompts based on that data. For example, it generates prompts that incorporate successful elements from other industries. The prompt improvement department also refers to success stories from different industries in real time when improving prompts and builds a system to improve prompts based on that data. For example, it reflects success stories from other industries in real time. This makes it possible to improve prompts by referring to success stories from different industries.

[0083] The prompt improvement unit can improve prompts from a global perspective, adapting them to different languages ​​and cultures. For example, the prompt improvement unit builds a system that improves prompts to accommodate different languages ​​and cultures. For example, a generation AI generates prompts that are compatible with multiple languages. The prompt improvement unit also develops an algorithm that improves prompts to accommodate different languages ​​and cultures. For example, it generates prompts that take cultural nuances into consideration. The prompt improvement unit also builds a system that improves prompts from a global perspective. For example, it generates prompts that are optimal for users in different regions. This makes it possible to improve prompts from a global perspective, adapting to different languages ​​and cultures.

[0084] The prompt improvement unit can use the emotion estimation function to analyze the user's emotional state in real time and propose optimal prompt improvements. The prompt improvement unit, for example, uses the emotion estimation function to analyze the user's emotional state in real time and build a system to improve prompts based on the results. For example, it generates prompts that elicit positive emotions. The prompt improvement unit also develops an algorithm that uses a generation AI to improve prompts based on the user's emotional state. For example, it generates prompts that include inspiring messages. The prompt improvement unit also builds a system that generates prompts that are optimal for the user's emotions based on the emotion estimation data. For example, if the user is relaxed, it generates prompts with a calm tone. This makes it possible to analyze the user's emotional state in real time and propose optimal prompt improvements.

[0085] The content improvement department can develop an algorithm that allows the generation AI to automatically suggest the optimal improvement method. For example, the content improvement department develops an algorithm that allows the generation AI to automatically suggest the optimal improvement method. For example, it suggests effective improvement methods based on past data. The content improvement department also builds a system that allows the generation AI to automatically suggest the optimal improvement method when improving content. For example, it suggests improvement methods based on click rates and conversion rates. The content improvement department also develops an algorithm that allows the generation AI to automatically suggest the optimal improvement method, and builds a system that improves content in real time. For example, it suggests improvement methods based on user feedback. This makes it possible to develop an algorithm that allows the generation AI to automatically suggest the optimal improvement method.

[0086] When improving content, the content improvement department can refer to past improvement history and select the optimal improvement method. For example, when improving content, the content improvement department will store past improvement history in a database and build a system that selects the optimal improvement method based on that history. For example, it will improve content by referring to past success stories. The content improvement department will also analyze past improvement history and develop an algorithm that will allow the generation AI to select the optimal improvement method based on that data. For example, it will automatically suggest highly effective improvement methods. The content improvement department will also refer to past improvement history in real time when improving content and build a system that selects the optimal improvement method based on that data. For example, it will suggest highly effective improvement methods in real time. This makes it possible to refer to past improvement history and select the optimal improvement method.

[0087] The content improvement unit can use the emotion estimation function to improve content based on the emotions of the target audience. For example, the content improvement unit uses the emotion estimation function to analyze the emotional state of the target audience and builds a system to improve content based on the results. For example, it generates content that elicits positive emotions. The content improvement unit also develops an algorithm in which the generation AI improves content based on emotions, based on the emotional state of the target audience. For example, it generates content that includes an inspiring message. The content improvement unit also builds a system that generates content that is optimal for the emotions of the target audience, based on the emotion estimation data. For example, if the user is relaxed, it generates content with a calm tone. This makes it possible to improve content based on the emotions of the target audience.

[0088] The content improvement department can improve content in different media formats and measure the overall effectiveness. For example, the content improvement department builds a system in which a generation AI improves content in different media formats (video, audio, text). For example, adding a text message to a video advertisement. The content improvement department also develops an algorithm that generates more effective content by combining different media formats. For example, adding visual elements to an audio advertisement. The content improvement department also builds a system in which a generation AI generates content that combines different media formats in real time and measures its effectiveness. For example, it selects the optimal media format based on user behavior data. This makes it possible to improve content in different media formats and measure the overall effectiveness.

[0089] The content improvement department can improve content from a global perspective, adapting it to different regions and cultural spheres. For example, the content improvement department builds a system that improves content to suit different regions and cultural spheres. For example, a generative AI generates content that is multilingual. The content improvement department also develops an algorithm that improves content to suit different regions and cultural spheres. For example, it generates content that takes cultural nuances into consideration. The content improvement department also builds a system that improves content from a global perspective. For example, it generates content that is optimal for users in different regions. This makes it possible to improve content from a global perspective, adapting it to different regions and cultural spheres.

[0090] The content improvement unit uses the emotion estimation function to monitor the emotional responses of the target audience in real time and continuously improve the content to be optimal. The content improvement unit, for example, uses the emotion estimation function to build a system that monitors the emotional responses of the target audience in real time. For example, it analyzes the user's facial expressions and voice and calculates an emotion score. The content improvement unit also develops an algorithm that improves content in real time based on the user's emotional response data. For example, it prioritizes the adoption of content that has a high number of positive emotional responses. The content improvement unit also builds a system that generates content that is optimal for the target audience's emotions in real time based on the emotion estimation data and continuously monitors its effectiveness. For example, it dynamically adjusts the content in response to changes in the user's emotions. This makes it possible to monitor the emotional responses of the target audience in real time and continuously improve the content to be optimal.

[0091] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0092] The advertising optimization system can also analyze a user's behavioral history to personalize advertising content. For example, it can generate highly relevant ads based on the ads the user has clicked on or the products the user has purchased in the past. It can also analyze a user's browsing history to suggest ads that are likely to interest the user. It can also monitor a user's social media activity and generate ads based on topics that are likely to interest the user. This makes it possible to utilize a user's behavioral history to provide more effective advertising content.

[0093] The ad optimization system can also take into account user device information to select the optimal ad format. For example, it can provide vertical video ads to smartphone users and horizontal banner ads to desktop users. It can also analyze the user's internet connection speed and deliver rich media ads to those with high-speed connections and lightweight text ads to those with slower connections. It can also automatically adjust the optimal ad layout depending on the screen size and resolution of the user's device. This makes it possible to utilize user device information to provide the optimal ad format.

[0094] The advertising optimization system can also utilize the user's location information to generate advertising content that is specific to the region. For example, if the user is in a particular city, advertisements related to stores and events in that region can be displayed. Coupons and sales information for nearby stores can also be provided based on the user's location information. Furthermore, if the user is traveling, advertisements for tourist spots and restaurants in the user's travel destination can be displayed. In this way, the user's location information can be utilized to provide advertising content that is specific to the region.

[0095] The advertising optimization system can further analyze the user's emotional state and generate advertising content based on the emotion. For example, if the user is in a positive emotional state, it can suggest an advertisement with a bright and cheerful tone. On the other hand, if the user is in a negative emotional state, it can generate an advertisement containing an encouraging or comforting message. Furthermore, it can monitor the user's emotional state in real time and dynamically adjust advertising content according to changes in the user's emotional state. This allows it to provide advertising content based on the user's emotional state.

[0096] The ad optimization system can also analyze a user's voice input and generate advertising content based on the voice command. For example, if a user voice-inputs, "I'm looking for a new smartphone," an advertisement for a smartphone that meets the request can be displayed. The system can also analyze the user's voice tone and emotions and adjust the tone and message of the advertisement based on the results. Furthermore, the system can convert the voice input into text and generate advertising content based on that text. This allows the system to utilize voice input to provide advertising content that meets the user's request.

[0097] The ad optimization system can further analyze the user's emotional state and generate prompts based on the emotion. For example, if the user is stressed, it can suggest prompts with a relaxing tone. Alternatively, if the user is excited, it can suggest prompts with an energetic tone. Furthermore, it can monitor the user's emotional state in real time and dynamically adjust the prompts according to changes in the user's emotional state. This allows it to provide prompts based on the user's emotional state.

[0098] The advertising optimization system can also analyze a user's social media activity and generate advertising content based on topics that are likely to interest them. For example, if a user frequently posts about a particular brand or product, it can display ads related to that brand or product. It can also suggest relevant ads based on the topics that the user's followers and friends are interested in. It can also monitor a user's social media activity in real time and dynamically adjust advertising content based on changes in that activity. This allows it to utilize a user's social media activity to provide advertising content that is likely to interest them.

[0099] The advertising optimization system can further analyze the user's emotional state and generate advertising content based on the emotion. For example, if the user is in a positive emotional state, it can suggest an advertisement with a bright and cheerful tone. On the other hand, if the user is in a negative emotional state, it can generate an advertisement containing an encouraging or comforting message. Furthermore, it can monitor the user's emotional state in real time and dynamically adjust advertising content according to changes in the user's emotional state. This allows it to provide advertising content based on the user's emotional state.

[0100] The advertising optimization system can also analyze a user's purchasing history to generate highly relevant advertising content. For example, it can display advertisements for accessories or additional items related to products the user has previously purchased. It can also suggest advertisements for new products that are likely to interest the user based on the user's purchasing history. It can also monitor a user's purchasing history in real time and dynamically adjust advertising content according to changes in the history. This makes it possible to provide highly relevant advertising content by utilizing the user's purchasing history.

[0101] The advertising optimization system can further analyze the user's emotional state and generate advertising content based on the emotion. For example, if the user is in a positive emotional state, it can suggest an advertisement with a bright and cheerful tone. On the other hand, if the user is in a negative emotional state, it can generate an advertisement containing an encouraging or comforting message. Furthermore, it can monitor the user's emotional state in real time and dynamically adjust advertising content according to changes in the user's emotional state. This allows it to provide advertising content based on the user's emotional state.

[0102] The processing flow of the second embodiment will be briefly explained below.

[0103] Step 1: The prompt input unit receives a prompt from the user. For example, the user inputs a prompt such as "Please create an advertisement for a new product." Step 2: The advertisement generation unit generates advertisement content based on the prompt received by the prompt input unit. For example, the generation AI generates advertisement copy including a banner image with a different design and a different message. Step 3: The AB testing unit tests the advertising content generated by the advertising generation unit. For example, it distributes the advertisements online and collects performance indicators such as click rates and conversion rates. Step 4: The prompt refinement team refines the prompt based on the test results obtained by the AB testing team. For example, they create a new prompt that incorporates elements of the advertisement that had a high click rate. Step 5: The content improvement unit regenerates the advertising content based on the prompt improved by the prompt improvement unit. For example, the content improvement unit re-runs the AB test using the advertising content generated using the new prompt.

[0104] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0105] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0106] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0107] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0108] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0109] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0110] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0111] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0112] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0113] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0114] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0115] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0116] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0117] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0118] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0119] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0120] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0121] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0122] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0123] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0124] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0125] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0126] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0127] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0128] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0129] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0130] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0131] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0132] In the headset type terminal 314, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0133] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0134] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0135] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0136] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0137] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0138] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0139] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0140] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0141] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0142] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0143] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0144] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0145] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0146] The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0147] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0148] In the robot 414, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0149] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0150] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0151] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0152] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0153] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0154] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0155] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0156] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0157] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0158] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0159] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0160] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0161] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0162] 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.

[0163] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0164] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0165] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0166] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0167] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0168] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0169] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0170] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0171] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. a prompt input unit that accepts a prompt from a user; an advertisement generation unit that generates advertisement content based on the prompt received by the prompt input unit; an AB test unit that tests the advertisement content generated by the advertisement generation unit; a prompt improvement unit that improves prompts based on test results obtained by the AB test unit; a content improvement unit that regenerates advertising content based on the prompt improved by the prompt improvement unit. A system characterized by:

2. The prompt input unit Analyzes the user's prompt history and automatically suggests the most appropriate prompt The system of claim 1 .

3. The prompt input unit When a prompt is entered, additional questions are asked interactively to more accurately understand the user's intent. The system of claim 1 .

4. The prompt input unit Prompts are generated according to the emotional state of the user to create more effective advertising content. The system of claim 1 .

5. The prompt input unit Corresponding prompt input to speech input and generating the prompt using speech recognition technology The system of claim 1 .

6. The prompt input unit When completing a prompt, other users will be shown examples of successful prompts for reference. The system of claim 1 .

7. The prompt input unit When a prompt is entered, the emotional state of the user is analyzed in real time and prompts that elicit positive emotions are suggested. The system of claim 1 .

Images