System

Abstract

A system is provided.SOLUTION: A system comprising: means for creating a database of past creative content and past performance data of measures; means for allowing related parties to centrally browse and check the database; and means for performing scoring on new creative content using AI based on the past creative content and past performance data of measures and proposing an optimal solution.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] When creating creative content for digital advertising, a common issue is the large amount of feedback and revisions required from various parties, slowing down progress. It also takes time to prove the validity of new creative content and measures, and repeating past configurations can hinder novelty. Furthermore, reaching consensus with various parties takes time, making it difficult to implement measures quickly. To solve these problems, efficient feedback management and rapid scoring are required. [Means for solving the problem]

[0005] To solve this problem, the present invention provides the following means: A database of past creative content and performance data on measures is compiled, allowing all parties involved to view and check this data in a centralized manner. Furthermore, AI is used to score new creative content based on past data and propose optimal solutions. This system enables the rapid and efficient evaluation of new creative content, shortening feedback time and quickly verifying validity. Furthermore, the AI ​​scoring uses the TF-IDF method and cosine similarity, and past creative data includes descriptions, titles, and performance scores, enabling more accurate scoring. This means that new creative production and new measures in digital advertising can be developed more smoothly and the time required for consensus building can be significantly reduced.

[0006] "Creative Content" refers to any visual or textual material produced for advertising or promotional purposes.

[0007] A "measure" is a set of actions or measures designed to achieve a particular goal.

[0008] "Performance data" refers to information showing the effectiveness and results of creative and measures implemented in the past.

[0009] A "database" refers to a system that stores information and data in an organized manner and makes them available for efficient search and use.

[0010] "All parties involved" refers to all departments and personnel involved in the production and evaluation of creative content.

[0011] "Centralized" refers to consolidating multiple pieces of information in one place and managing them centrally.

[0012] "Viewing" refers to reading stored information or data.

[0013] "Check" refers to the act of verifying the accuracy and validity of information or data.

[0014] "AI" is an abbreviation for artificial intelligence technology, and refers to a system that processes information and makes decisions by imitating human intelligence.

[0015] "Scoring" refers to the act of providing a numerical evaluation based on specific criteria.

[0016] An "optimal solution" refers to the most effective and efficient method or means under given conditions.

[0017] The "TF-IDF method" refers to a method for calculating importance using the frequency of occurrence of words in a document and the inverse document frequency.

[0018] "Cosine similarity" refers to a method of measuring similarity using the angle between two vectors.

[0019] "Description" refers to text that describes the content and purpose of the creative content.

[0020] "Title" refers to a short phrase that indicates the subject or theme of the creative content.

[0021] "Performance score" refers to a numerical indicator that shows the effectiveness of creative and measures. [Brief explanation of the drawings]

[0022] [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. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0023] 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.

[0024] First, the terms used in the following description will be explained.

[0025] 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, a 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), and an APU (Accelerated Processing Unit).

[0026] 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.

[0027] 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.

[0028] 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), Bluetooth (registered trademark), etc.

[0029] 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."

[0030] [First embodiment]

[0031] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0032] 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.

[0033] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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).

[0034] 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.

[0035] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. 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 acquires the data indicating the user input.

[0036] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The 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.

[0037] 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.

[0038] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0039] 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.

[0040] 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.

[0041] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0042] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0043] The system of the present invention is for efficiently evaluating the adequacy of creative production and new measures for digital advertising. A specific embodiment of this system will be described below.

[0044] System configuration

[0045] Database

[0046] The server first creates a database of performance data for creative content and campaigns that have been executed in the past, including creative titles, descriptions, and performance scores.

[0047] Centralized management and viewing of data

[0048] The server provides a web interface that allows stakeholders to view and check the database in a centralized manner. Through this interface, users and stakeholders can access past data and obtain the information they need.

[0049] AI-based scoring

[0050] The server uses AI to score newly entered creative content. This AI scoring uses the TF-IDF method and cosine similarity. The TF-IDF method calculates the importance of words based on the frequency of their appearance in a document and their inverse document frequency, while the cosine similarity measures the similarity of creative content.

[0051] Program processing

[0052] Database Connection

[0053] The server first connects to a database management system, such as SQLite, and creates the necessary table structure that stores the creative title, description, and performance score.

[0054] Inserting and Retrieving Data

[0055] The server receives new creative content data and inserts it into the database, and also retrieves all past creative data from the database.

[0056] Applying the scoring algorithm

[0057] The server vectorizes the description of the new creative using the TF-IDF method, compares it with past data to calculate the cosine similarity, and calculates a score for the new creative based on this result.

[0058] Specific examples

[0059] 1. Data Entry:

[0060] The user enters the title "New Year Sale Campaign" and the description "Join our New Year Sale and get up to 50% off!" into the terminal.

[0061] 2. Data storage:

[0062] The server stores this in a database and retrieves past creative data.

[0063] 3. Scoring:

[0064] The server uses AI to calculate the score for the new creative. In this case, it uses the TF-IDF method and cosine similarity to compare it with past data and calculates a score of 88.2.

[0065] 4. Display score:

[0066] Users can view this score on their device to assess the suitability of new creatives. For example, the "New Year Sale Campaign" will be shown with a score of 88.2.

[0067] This system shortens feedback time and enables the rapid production of innovative creatives. It also significantly reduces the time required for consensus building, allowing for the smooth development of new creatives and the implementation of new initiatives in digital advertising.

[0068] The processing flow will be explained below.

[0069] Step 1:

[0070] Database Connection

[0071] The server connects to a database management system such as SQLite by using sqlite3.connect to access the database file and obtain a connection object.

[0072] Step 2:

[0073] Table Creation

[0074] The server creates a table in the database to store the creative data, using the CREATE TABLE SQL statement to set up the table with columns for storing the title, description, and performance score.

[0075] Step 3:

[0076] Data Entry

[0077] The user enters the title and description of the new creative content on the device, for example, "New Year Sale Campaign" and "Join our New Year Sale and get up to 50% off!"

[0078] Step 4:

[0079] Inserting Data

[0080] The server inserts the newly entered creative data into the database using an INSERT INTO SQL statement, inserting the title, description, and initial score (e.g., -1 for unrated).

[0081] Step 5:

[0082] Obtaining past data

[0083] The server retrieves all previously accumulated creative content data from the database, using the SQL statement SELECT FROM Creatives to get a list of titles, descriptions, and performance scores.

[0084] Step 6:

[0085] Text Vectorization

[0086] The server vectorizes the descriptions of the new and past creatives. It converts each description into a numeric vector using the TF-IDF (Term Frequency-Inverse Document Frequency) algorithm. It uses TfidfVectorizer.

[0087] Step 7:

[0088] Similarity calculation

[0089] The server uses cosine similarity to calculate the similarity between the new creative description and the previous description. It uses cosine_similarity to get the similarity score between each resulting vector.

[0090] Step 8:

[0091] Aggregation of Similarity Scores

[0092] The server aggregates the calculated cosine similarity scores and calculates an average score for the new creative, which becomes the performance prediction score for the new creative.

[0093] Step 9:

[0094] Score database update

[0095] The server updates the database with the new creative's performance score using a SQL statement like UPDATE Creatives SET performance_score = ? WHERE id = ?

[0096] Step 10:

[0097] Displaying the score

[0098] On the device, the user sees the performance score for the new creative, specifically the "New Year Sale Campaign" which has a score of 88.2.

[0099] This allows users to quickly assess the relevance of new creative and decide on their next course of action.

[0100] Example 1

[0101] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0102] When creating creative content for digital advertising, there is a need for a method to effectively utilize past performance data and quickly and accurately evaluate the suitability of new content. However, the centralized management of huge amounts of data and the evaluation process using AI are complex, requiring a lot of time and resources.

[0103] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0104] In this invention, the server includes: means for compiling a database of performance data of past digital advertisements and campaigns; means for enabling related parties to centrally view and check the database; means for using artificial intelligence to score new creative content based on the performance data of past digital advertisements and campaigns and propose optimal solutions; means for using artificial intelligence to vectorize and calculate similarity of the new creative content using the TF-IDF method and cosine similarity and calculate its score; and means for storing the score of the new creative content in the database and allowing users to view it on their terminals. This enables the evaluation process of creative content for digital advertisements to be carried out quickly and efficiently.

[0105] "Digital advertising" refers to advertising content delivered via the Internet or digital media.

[0106] "Creative Content" means content created for an advertising campaign, consisting of titles, descriptions, images, videos, and other multimedia elements.

[0107] "Performance data" refers to records of the results and performance of campaigns and measures implemented in the past.

[0108] A "database" is an information system for efficiently storing and managing large amounts of data in a structured format.

[0109] "Artificial intelligence" refers to computer systems that mimic human intelligence and can learn and solve problems automatically.

[0110] "Scoring" is the process of quantifying something for the purposes of evaluation or comparison.

[0111] The "TF-IDF method" is a technique that calculates the importance of each word by combining the term frequency (TF) and inverse document frequency (IDF) of the word in a document.

[0112] "Cosine similarity" is a method for calculating the similarity between two vectors using the dot product and the magnitude of the vectors.

[0113] "Vectorization" is the process of converting text data into vectors of numbers.

[0114] A "terminal" is an electronic device such as a computer or smartphone that a user uses to input and output information.

[0115] The system of the present invention aims to efficiently evaluate the adequacy of creative production and new measures for digital advertising. Specific embodiments of this system are as follows.

[0116] System Overview

[0117] This system is operated by a server, terminals, and users. It also uses artificial intelligence (AI) to score creative content, centrally manages the data, and provides it to users.

[0118] Database construction and operation

[0119] The server first creates a database of performance data for past digital advertisements and campaigns. This database stores the titles, descriptions, and performance scores of creative content. The database management system used is SQLite.

[0120] Centralize and access your data

[0121] The server provides a web interface that allows all parties involved to access, view, and check the database in a centralized manner. Through this interface, users and stakeholders can easily access past data and obtain the information they need. This interface can be accessed through a standard web browser.

[0122] Scoring new creative content

[0123] The server uses artificial intelligence (AI) to score newly entered creative content. This AI scoring uses the TF-IDF method and cosine similarity. The TF-IDF method calculates the importance of each word, and cosine similarity is used to measure the similarity with past creative content.

[0124] Specific examples

[0125] 1. Data Entry:

[0126] The user enters the title "New Year Sale Campaign" and the description "Join our New Year Sale and get up to 50% off!" into the terminal.

[0127] 2. Data storage:

[0128] The server stores this in a database and retrieves past creative data.

[0129] 3. Scoring:

[0130] The server uses AI to calculate the score for the new creative. In this case, it uses the TF-IDF method and cosine similarity to compare it with past data and calculates a score of 88.2.

[0131] 4. Display score:

[0132] Users can view this score on their device to assess the suitability of new creatives. For example, the "New Year Sale Campaign" will be shown with a score of 88.2.

[0133] Prompt Sentence Examples

[0134] You can generate a prompt like this:

[0135] Based on the creative description for the digital ad "New Year Sale Campaign" - "Join our New Year Sale and get up to 50% off!" - calculate the similarity to historical data and assign it a new score.

[0136] This system shortens feedback time and enables the rapid production of innovative creatives. It also significantly reduces the time required for consensus building, allowing for the smooth development of new creatives and the implementation of new initiatives in digital advertising.

[0137] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0138] Step 1: Database Connection and Initial Configuration

[0139] When the server starts up, it first connects to the SQLite database management system and then creates a table structure to store the title, description, and performance score of the creative content.

[0140] Input: System startup, database connection request

[0141] Output: Database connection, table initialization

[0142] What happens: The server opens the SQLite database and creates the required table structure (including title, description, and score fields) if it doesn't exist.

[0143] Step 2: User enters new data

[0144] The user uses the device to input new creative content (e.g., title and description).

[0145] Input: User input form

[0146] Output: Input creative content data

[0147] Specific operation: The user enters the title "New Year Sale Campaign" and the description "Join our New Year Sale and get up to 50% off!" through the web interface.

[0148] Step 3: Save the data to a database

[0149] The server stores the new creative content data received from the user in a database.

[0150] Input: New creative data by user

[0151] Output: New creative data stored in the database

[0152] Specific operation: The server inserts the received new creative data (title and description) into the corresponding table in the SQLite database.

[0153] Step 4: Obtaining historical data

[0154] The server retrieves all past creative data from the database.

[0155] Input: A request to retrieve data from the database

[0156] Output: Obtained historical creative data

[0157] What happens: The server uses an SQL query to read the titles, descriptions, and scores of past creative content from a database.

[0158] Step 5: Score new data

[0159] The server vectorizes the description of the new creative using the TF-IDF method, calculates the cosine similarity, and compares it with past data. The result is used to calculate the score of the new creative.

[0160] Input: New creative description and description of past creative data

[0161] Output: New creative score

[0162] Specific operation: The server uses the TF-IDF vectorization tool to convert the new description into a numerical vector, and then calculates the cosine similarity with the previously obtained description data to calculate a score.

[0163] Step 6: Save the score to the database

[0164] The server stores the score of the new creative in a database.

[0165] Inputs: Calculated score, new creative title and description

[0166] Output: Scores stored in the database

[0167] What happens: The server updates the score of the new creative into an existing database record or inserts it into a new record.

[0168] Step 7: User checks score

[0169] The user uses the device to check the score of the new creative.

[0170] Input: Score display request

[0171] Output: Score of the new creative displayed on the device screen

[0172] What happens: Through the web interface, the user sees that the new creative, "New Year Sale Campaign," has a score of 88.2.

[0173] (Application example 1)

[0174] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0175] Creating and evaluating creative content for digital advertising requires a lot of time and effort. Furthermore, there is a lack of ways to quickly predict and optimize the effectiveness of newly created creative content, making it difficult for advertising planners and marketers to work efficiently. To solve this problem, there is a need for a system that utilizes past data to predict and display the performance of new creative content in real time.

[0176] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0177] In this invention, the server includes: means for creating a database of past creative content and performance data of measures; means for enabling related parties to centrally view and check the database; means for using AI to score new creative content based on the past creative content and performance data of measures and proposing optimal solutions; means for inputting the title and description of a new advertisement from a user terminal; and means for displaying the score in real time after the new advertisement is input. This makes it possible to quickly predict the effectiveness of advertising creatives and efficiently produce optimal creatives.

[0178] "Past creative content and campaign performance data" refers to data that records the results of previously created advertising creatives and related marketing campaigns.

[0179] A "database" is a digital information storage location for efficiently storing and managing past creative content and performance data of initiatives.

[0180] "AI" is an abbreviation for artificial intelligence, a technology that uses machine learning algorithms and natural language processing techniques to analyze and evaluate new creative content.

[0181] "Scoring" is the process of using AI to quantify and evaluate the performance of new creative content.

[0182] "Proposing optimal solutions" refers to AI evaluating the performance of new creative content and generating and proposing effective advertising creatives based on the evaluation results.

[0183] A "user terminal" is a device (e.g., a smartphone or tablet) used by advertising planners or marketers to input new advertising information.

[0184] "Real-time" refers to the process of displaying the evaluation results immediately after a new ad is entered.

[0185] A "title" is a concise expression of the main message or name of the creative content.

[0186] The "description" is the section that describes the detailed information and specific content of the creative content.

[0187] The system for implementing this invention compiles a database of past creative content and performance data of measures, predicts the performance of new creative content based on this data, and proposes optimal advertising creatives.

[0188] System configuration

[0189] Database

[0190] The server maintains a database that stores performance data for creative content created in the past and related measures. This database includes creative titles, descriptions, and performance scores. The database is managed using SQLite.

[0191] Centralized management and viewing of data

[0192] The server provides a web interface that allows stakeholders to view and check the database in a centralized manner. The web interface is built using the Flask framework, allowing stakeholders to easily access past data.

[0193] AI-based scoring

[0194] The server uses a generative AI model to score newly input creative content. This process uses the TF-IDF method and cosine similarity. The server uses the Sklearn library to vectorize the text data of the new creative and calculate the similarity with past data.

[0195] Program processing

[0196] Database connection and configuration

[0197] The server first connects to the SQLite database and creates a table structure to store the creative content data.

[0198] Inserting and Retrieving Data

[0199] The server receives the title and description of the new creative from the user terminal and stores them in the database, and also retrieves past creative data from the database.

[0200] Applying the scoring algorithm

[0201] The server uses the TF-IDF method to vectorize the description of new creative content and calculates the cosine similarity with past creative data. This score is evaluated on a scale of 100 and displayed to the user in real time.

[0202] Specific examples

[0203] For example, a user may enter a title such as "Spring Sale Campaign" and a description such as "Up to 50% off in the Spring Sale!" This input data is sent to the server and stored in a database. The server calculates the similarity between the previous data and the new creative and gives it a score of 85.5. This score is displayed in real time on the web interface on the user's device.

[0204] Prompt Sentence Examples

[0205] Ad Title: Spring Sale Campaign, Description: Up to 50% off in the Spring Sale!

[0206] This system enables advertising planners and marketers to quickly predict the effectiveness of new creatives and efficiently produce effective advertising creatives.

[0207] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0208] Step 1:

[0209] The server connects to the SQLite database and creates the necessary table structure, including tables to store the title, description, and performance score of past creative content. The input is the database structure definition, and the output is the creation of these tables.

[0210] Step 2:

[0211] The user inputs the title and description of the new creative content from the terminal. This input data is sent to the server. As input, details (title and description) of the new creative content are required, and as output, this data is received by the server.

[0212] Step 3:

[0213] The server stores the received new creative data in the database. The new creative details are inserted into the database. As input, it requires the data received from the user and as output, it registers this data in the database.

[0214] Step 4:

[0215] The server retrieves all past creative data from the database. As input, a query to the database is required, and as output, a list of past creative data is obtained.

[0216] Step 5:

[0217] The server uses the Sklearn library to apply the TF-IDF method to vectorize the description of the new creative. As input, it takes the descriptions of the new and previous creatives, and as output, it gets the vectorized descriptions.

[0218] Step 6:

[0219] The server calculates the cosine similarity to measure the similarity between the new creative and the previous creative. Based on this score, it calculates the performance score for the new creative. The input is the vectorized description, and the output is the similarity score and the performance score.

[0220] Step 7:

[0221] The server displays the calculated performance score on the user's device in real time. The user can check the score of the new creative on the device. The performance score is required as input, and the score is displayed on the user's device as output.

[0222] Prompt Sentence Examples

[0223] An example prompt sentence is "Ad title: Spring Sale Campaign, Description: Up to 50% off in the Spring Sale!"

[0224] This series of steps enables advertising planners and marketers to quickly predict the effectiveness of new creatives and efficiently produce optimal advertising creatives.

[0225] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0226] The system of the present invention is designed to efficiently evaluate the creative production of digital advertising and the validity of new initiatives, and by combining it with an emotion engine that recognizes user emotions, it improves the evaluation of creative content. Specific embodiments of this system are described below.

[0227] System configuration

[0228] Database

[0229] The server stores a database of performance data for creative content and campaigns that have been executed in the past, including creative titles, descriptions, and performance scores.

[0230] Centralized management and viewing of data

[0231] The server provides a web interface that allows stakeholders to view and check the database in a centralized manner. Through this interface, users and stakeholders can access past data and obtain the information they need.

[0232] AI-based scoring

[0233] The server uses AI to score newly entered creative content. AI scoring uses the TF-IDF method and cosine similarity. The TF-IDF method calculates the importance of words based on the frequency of their occurrence in a document and their inverse document frequency, while cosine similarity measures the similarity of creative content.

[0234] Emotion engine configuration

[0235] The emotion engine analyzes the user's facial expressions and voice in real time to collect emotional data, which allows it to evaluate how the user feels about the creative content.

[0236] Program processing

[0237] Database Connection

[0238] The server first connects to a database management system, such as SQLite, and creates the necessary table structure that stores the creative title, description, and performance score.

[0239] Inserting and Retrieving Data

[0240] The server receives new creative content data and inserts it into the database, and also retrieves all past creative data from the database.

[0241] Applying the scoring algorithm

[0242] The server vectorizes the description of the new creative using the TF-IDF method, compares it with past data to calculate the cosine similarity, and calculates a score for the new creative based on this result.

[0243] Emotion data collection and analysis

[0244] The device collects emotional data from the user's facial expressions and voice, and the emotion engine analyzes this data in real time to evaluate the user's emotional state.

[0245] Emotional Data Integration

[0246] The server then integrates the user's emotional data obtained from the emotion engine into the evaluation of new creatives. By using the user's emotional data in addition to AI scoring, more accurate evaluations are possible.

[0247] Specific examples

[0248] 1. Data Entry:

[0249] The user enters the title "New Year Sale Campaign" and the description "Join our New Year Sale and get up to 50% off!" into the terminal.

[0250] 2. Data storage:

[0251] The server stores this data in a database and retrieves past creative data.

[0252] 3. Scoring:

[0253] The server uses AI to calculate the score for the new creative. In this case, it uses the TF-IDF method and cosine similarity to compare it with past data and calculates a score of 88.2.

[0254] 4. Collecting Emotional Data:

[0255] The emotion engine collects facial and voice data from the user's device via the device's camera and microphone. For example, if a positive facial expression or tone is detected, the data is evaluated as a favorable response.

[0256] 5. Evaluating Emotional Data:

[0257] The emotion engine sends real-time analyzed emotion data to the server, which then reflects this data in the score of the new creative. For example, if the emotion score is 90, that will affect the final score.

[0258] 6. Display score:

[0259] The device allows users to see the combined performance score of new creatives, showing, for example, that the "New Year Sale Campaign" had a final score of 89.6.

[0260] This system shortens feedback time and enables the rapid production of innovative creatives. It also significantly reduces the time required for consensus building, allowing for the smooth development of new creatives and the implementation of new initiatives in digital advertising. Furthermore, by integrating user emotional data, creative evaluations become more accurate and reliable.

[0261] The processing flow will be explained below.

[0262] Step 1:

[0263] Database Connection

[0264] The server connects to a database management system such as SQLite by using sqlite3.connect to access the database file and obtain a connection object.

[0265] Step 2:

[0266] Table Creation

[0267] The server creates a table in the database to store the creative data, using the CREATE TABLE SQL statement to set up the table with columns for storing the title, description, and performance score.

[0268] Step 3:

[0269] Data Entry

[0270] The user enters the title and description of the new creative content on the device, for example, "New Year Sale Campaign" and "Join our New Year Sale and get up to 50% off!"

[0271] Step 4:

[0272] Inserting Data

[0273] The server inserts the newly entered creative data into the database using an INSERT INTO SQL statement, inserting the title, description, and initial score (e.g., -1 for unrated).

[0274] Step 5:

[0275] Obtaining past data

[0276] The server retrieves all previously accumulated creative content data from the database, using the SQL statement SELECT FROM Creatives to get a list of titles, descriptions, and performance scores.

[0277] Step 6:

[0278] Text Vectorization

[0279] The server vectorizes the descriptions of the new and past creatives. It converts each description into a numeric vector using the TF-IDF (Term Frequency-Inverse Document Frequency) algorithm. It uses TfidfVectorizer.

[0280] Step 7:

[0281] Similarity calculation

[0282] The server uses cosine similarity to calculate the similarity between the new creative description and the previous description. It uses cosine_similarity to get the similarity score between each resulting vector.

[0283] Step 8:

[0284] Aggregation of Similarity Scores

[0285] The server aggregates the calculated cosine similarity scores and calculates an average score for the new creative, which becomes the performance prediction score for the new creative.

[0286] Step 9:

[0287] Collecting Emotional Data

[0288] The device collects facial and voice data in real time from the user's camera and microphone, and the emotion engine analyzes the user's facial muscle movements and tone of voice to determine their emotional state.

[0289] Step 10:

[0290] Emotional Data Analysis

[0291] The emotion engine analyzes the collected facial and voice data to determine whether the user is in a positive, negative, or neutral emotional state, and quantifies this emotional data as an emotion score.

[0292] Step 11:

[0293] Sending emotional data

[0294] The terminal transmits the emotion score obtained as a result of the analysis to the server.

[0295] Step 12:

[0296] Emotional Data Integration

[0297] The server integrates the AI ​​text scoring with the sentiment score received from the sentiment engine, which adjusts the final performance score.

[0298] Step 13:

[0299] Score database update

[0300] The server updates the database with the final combined score using a SQL statement such as UPDATE Creatives SET performance_score = ? WHERE id = ?

[0301] Step 14:

[0302] Displaying the score

[0303] On the device, the user sees the combined performance score of the new creative, for example showing that the "New Year Sale Campaign" has a final score of 89.6.

[0304] This allows users to quickly assess the relevance of new creative and decide on their next course of action.

[0305] Example 2

[0306] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0307] In the creative production and evaluation of digital advertising campaigns, there is a need for efficient utilization of past performance data for rapid and accurate evaluation. However, there is a lack of evaluation that takes user emotions into account, making it difficult to accurately evaluate creatives that reflect user reactions.

[0308] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0309] In this invention, the server includes: means for compiling a database of past electronic advertising content and performance data of measures; means for enabling related parties to centrally view and check the database; means for using artificial intelligence to score new electronic advertising content based on the performance data of past electronic advertising content and measures and proposing optimal solutions; and means for analyzing user facial expressions and voice data in real time and integrating data obtained from an emotion analysis engine that evaluates user emotions. This makes it possible to efficiently utilize past data while accurately evaluating creative content in consideration of user emotions.

[0310] "Electronic advertising content" refers to all advertising creatives distributed on digital platforms.

[0311] "Performance data" refers to data showing the results of past measures and creatives, and includes performance scores, titles, descriptions, etc.

[0312] A "database" refers to a system that systematically organizes information and stores and manages it electronically.

[0313] "Artificial intelligence" refers to the technology that allows machines and computers to simulate human intelligence and learn, reason, and make decisions.

[0314] An "emotion analysis engine" refers to technology that analyzes a user's facial expressions and voice and evaluates their emotional state in real time.

[0315] The "TF-IDF method" refers to a method for calculating the importance of words in a document using word frequency and inverse document frequency.

[0316] "Cosine similarity" refers to a method for measuring the similarity between two vectors in vector space based on the angle between them.

[0317] "Scoring" refers to the process of calculating a score for creative content based on specific evaluation criteria.

[0318] "User" refers to a user who views and evaluates electronic advertising content.

[0319] "Means for centralized viewing and checking" refers to an interface that allows multiple parties to access one central data storage and to view and check information.

[0320] MODE FOR CARRYING OUT THE INVENTION

[0321] The system of the present invention is designed to efficiently evaluate the creative production of electronic advertisements and the validity of new measures. In addition, by combining it with a sentiment analysis engine that recognizes user emotions, it improves the evaluation of creative content.

[0322] System configuration

[0323] Database

[0324] The server creates a database of past digital advertising content and performance data for campaigns. This database stores creative titles, descriptions, and performance scores. SQLite is used as the database.

[0325] Centralized management and viewing of data

[0326] The server provides a web interface that allows stakeholders to view and check the database in a centralized manner. Through this interface, users and stakeholders can access past data and obtain the information they need.

[0327] AI-based scoring

[0328] The server uses artificial intelligence to score newly entered digital advertising content. This scoring is performed using the TF-IDF method and cosine similarity. The TF-IDF method calculates the importance of words based on the frequency of their appearance in a document and their inverse document frequency, while the cosine similarity measures the similarity of creative content.

[0329] Sentiment analysis engine configuration

[0330] The device is equipped with an emotion analysis engine that analyzes the user's facial expressions and voice in real time, allowing it to evaluate how the user feels about the digital advertising content.

[0331] Program processing

[0332] Database Connection

[0333] The server first connects to a database management system, such as SQLite, and creates the necessary table structure that stores the creative title, description, and performance score.

[0334] Inserting and Retrieving Data

[0335] The server receives new electronic advertising content data and inserts it into the database, and also retrieves all past electronic advertising data from the database.

[0336] Applying the scoring algorithm

[0337] The server uses the TF-IDF method to vectorize the description of the new digital advertisement, compares it with past data to calculate the cosine similarity, and calculates a score for the new creative based on this result.

[0338] Emotion data collection and analysis

[0339] The device collects emotional data from the user's facial expressions and voice, and the emotion analysis engine analyzes this data in real time to evaluate the user's emotional state.

[0340] Emotional Data Integration

[0341] The server then integrates the user's emotional data obtained from the emotion analysis engine into the evaluation of the new creative. By using the user's emotional data in addition to the AI ​​scoring, a more accurate evaluation is possible.

[0342] Specific examples

[0343] Data Entry

[0344] The user enters the title "New Year Sale Campaign" and the description "Join our New Year Sale and get up to 50% off!" into the terminal.

[0345] Data storage

[0346] The server stores this data in a database and retrieves past creative data.

[0347] Scoring

[0348] The server uses artificial intelligence to calculate the score for the new creative. In this case, it uses the TF-IDF method and cosine similarity to compare it with past data and calculates a score of 88.2.

[0349] Collecting Emotional Data

[0350] The user's facial expression and voice data are collected by the emotion analysis engine through the device's camera and microphone. For example, if a positive expression or tone is detected, the data is evaluated as a favorable reaction.

[0351] Emotional Data Evaluation

[0352] The sentiment analysis engine sends the analyzed sentiment data in real time to the server, which then reflects this data in the score of the new creative. For example, if the sentiment score is 90, it will affect the final score.

[0353] Displaying the score

[0354] The device allows users to see the combined performance score of new creatives, showing, for example, that the "New Year Sale Campaign" had a final score of 89.6.

[0355] Example prompt sentence:

[0356] Enter the title and description of the digital ad creative below, and we'll use artificial intelligence to score it and collect user sentiment data to evaluate it.

[0357] Title: New Year Sale Campaign

[0358] Description: Join our New Year Sale and get up to 50% off!

[0359] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0360] Step 1:

[0361] The server connects to a database, such as SQLite, to store creative data and performance data for digital ads. First, a connection string is generated and used to connect to the database. Next, a table named "creatives_table" is created. The table has fields containing a title, description, and performance score. The input to this process is the database connection information held by the server, and the output is that the database and table are ready.

[0362] Step 2:

[0363] The server receives new electronic advertising content data from the terminal and inserts it into the database. For example, a user enters the title "New Year Sale Campaign" and the description "Join our New Year Sale and get up to 50% off!" The server saves this data in the database using the SQL INSERT statement. The input of this process is the advertising content data received from the user, and the output is the new data being inserted into the database.

[0364] Step 3:

[0365] The server retrieves all past digital advertising data from the database using an SQL SELECT statement. After the data is read, it is stored in memory. The input to this process is a specific query statement, and the output is the retrieved past digital advertising data.

[0366] Step 4:

[0367] The server vectorizes the description of the new digital ad using the TF-IDF method. First, the description is tokenized and the TF-IDF method is applied to calculate the importance of each word in the document. Next, the past creative data is similarly vectorized and the cosine similarity between that vector and the vector of the new data is calculated. A score is calculated based on this result. For example, a score of 88.2 is obtained for the new data. The inputs to this process are the new description and past data, and the output is the score for the new creative data.

[0368] Step 5:

[0369] The device collects the user's facial and voice data using the device's camera and microphone. The collected data is sent to an emotion analysis engine and analyzed in real time. The analysis results are evaluated in list form, including emotional states such as positive, negative, and neutral. The input of this process is the user's facial and voice data, and the output is analyzed emotional data.

[0370] Step 6:

[0371] The server receives the sentiment data from the sentiment analysis engine and integrates it into the final rating of the new creative. For example, if the sentiment score is 90, it will be reflected in the final score, which is expected to result in a final score of 89.6. The input of this process is the sentiment data from the sentiment analysis engine, and the output is the integrated final score.

[0372] Step 7:

[0373] The terminal displays the integrated final score to the user. For example, it shows that the final score for the "New Year Sale Campaign" is 89.6. This allows the user to check the evaluation results of the new creative. The input of this process is the final score, and the output is the result displayed in the user interface.

[0374] (Application example 2)

[0375] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0376] When creating and evaluating creative content for digital advertising, there is a need to measure performance quickly and accurately. However, conventional methods mainly rely on past data for evaluation, making it difficult to reflect real-time user sentiment. This makes it impossible to accurately reflect actual user reactions.

[0377] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for compiling a database of past creative content and performance data of measures; means for enabling related parties to centrally view and check the database; means for using AI to score new creative content based on the performance data of past creative content and measures and proposing optimal solutions; means for analyzing the user's facial expressions and voice using a terminal to collect emotional data; means for integrating the emotional data into the scoring of the new creative content; and means for providing the user with an evaluation result based on the scoring and emotional data via an interface. This makes it possible to evaluate creative content in a way that reflects the user's real-time emotions.

[0378] "Means of creating a database" refers to a method for systematically organizing data on past creative content and performance of measures, and storing the information.

[0379] "A single point of access and check" means a method that allows all parties involved to efficiently review and audit the information in the database through a single interface.

[0380] "A method of using AI to score and propose optimal solutions" is a method that utilizes artificial intelligence technology to evaluate new creative content and derive optimal advertising measures.

[0381] "Means for analyzing a user's facial expressions and voice using a terminal and collecting emotional data" refers to a method for measuring a user's emotional state and acquiring data using a device equipped with a camera and microphone.

[0382] The "means for integrating emotional data into the scoring of new creative content" is a method for incorporating collected emotional data into the evaluation process of new creative content to perform a composite evaluation.

[0383] "Means for providing users with evaluation results based on scoring and emotional data via an interface" refers to a method for providing users with evaluation results based on scoring and emotional data via a user interface for displaying the evaluation results.

[0384] The system of the present invention is for quickly and accurately producing and evaluating creative content for digital advertising. Specific embodiments of this system will be described below.

[0385] System configuration

[0386] The system of the present invention includes the following major components:

[0387] 1. Database creation method:

[0388] The server stores historical creative content and performance data in a database, including creative titles, descriptions, and performance scores.

[0389] 2. Centralized viewing and checking:

[0390] The server provides a web interface that allows interested parties to centrally view and check the historical database.

[0391] 3. AI-based scoring and suggestion of optimal solutions:

[0392] The server uses AI to score newly input creative content using TF-IDF and cosine similarity.

[0393] 4. Using a device to analyze a user's facial expressions and voice to collect emotional data:

[0394] The device uses a camera and microphone to analyze the user's facial expressions and voice in real time to collect emotional data, using the DeepFace library for emotion analysis.

[0395] 5. Means of integrating sentiment data into scoring new creative content:

[0396] The server then integrates the emotion data obtained from the emotion engine into the evaluation of the new creative, enabling a more accurate evaluation that reflects the user's emotions.

[0397] 6. Means for providing users with evaluation results based on scoring and emotion data via an interface:

[0398] The server provides an interface for displaying the evaluation results to the user, which displays the evaluation results based on the emotion data along with the performance scores.

[0399] Hardware and software used

[0400] Hardware: Smartphone, head-mounted display, built-in camera, built-in microphone

[0401] Software: Python, OpenCV, DeepFace library, SQLite, scikit-learn

[0402] Specific examples

[0403] A user views a digital advertisement using a smartphone or head-mounted display. They enter "New Year Sale Campaign" as the title and "Join our New Year Sale and get up to 50% off!" as the description. The server stores this data in a database and uses AI to score it. For example, it calculates a score of 88.2 based on the TF-IDF method and cosine similarity.

[0404] Next, the device's camera and microphone are used to collect emotion data from the user's facial expressions and voice. The emotion engine analyzes this data in real time and sends the emotion data to the server. For example, if the user's emotion score is 90, this score will be included in the final performance evaluation.

[0405] Finally, the server provides the consolidated performance score to the user through the interface, where the user can see that the "New Year Sale Campaign" had a final score of 89.6.

[0406] Prompt Sentence Examples

[0407] "Use a camera and microphone to collect real-time sentiment data while users are viewing a commercial. Explain how you would use the sentiment data to calculate a performance score for the ad. Give a thumbs up if the viewer expresses positive sentiment and a thumbs down if the viewer expresses negative sentiment."

[0408] In this way, it becomes possible to evaluate creative content that reflects users' real-time emotions, improving the efficiency of creating and evaluating digital advertisements.

[0409] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0410] Step 1:

[0411] The server stores past creative content and performance data of initiatives in a database. It receives input data such as the title, description, and performance score of creative content provided by users, systematically organizes it, and records it in an SQLite database. This database storage allows for the creation of historical data that can be accessed later by relevant parties.

[0412] Step 2:

[0413] The server provides a web interface that allows interested parties to centrally view and check past creative data in the database. Users or administrators can access past data through the interface and review and evaluate required information (e.g., title, description, performance score). This interface is built using common web technologies such as HTML, CSS, and JavaScript (registered trademark).

[0414] Step 3:

[0415] The server scores new creative content using the TF-IDF method and cosine similarity. It receives the description of the new creative content entered by the user and calculates the TF-IDF vector. It compares the calculated vector with vectors in the past database to calculate the cosine similarity and determines the score for the new creative. The output is a numerical score result (e.g., 88.2).

[0416] Step 4:

[0417] The device uses a camera and microphone to analyze the user's facial expressions and voice in real time to collect emotional data. The device analyzes facial expressions and voice as input data collected while the user is viewing advertisements and classifies them into emotions (joy, anger, sadness, happiness, etc.). The DeepFace library is used to perform the emotion analysis, and the analysis results are output as emotional data.

[0418] Step 5:

[0419] The server integrates the collected emotional data into the scoring of new creative content. It receives the emotional data sent from the device and adds it to the scoring results. For example, if the emotional score is positive, it adjusts it to improve the final score. It outputs the integrated final score (e.g., 89.6).

[0420] Step 6:

[0421] The server provides the user with the evaluation results based on the scoring and emotional data via an interface. The final score and emotional evaluation results calculated on the server side are displayed in a user-viewable interface. The user can check the performance evaluation results of the creative content through the interface, which can be used to improve subsequent advertising measures. Detailed feedback based on the scoring results and emotional data is provided as an output.

[0422] 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.

[0423] 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> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. 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 voice, text data indicating text, and image data indicating an image is also input. 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.

[0424] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0425] [Second embodiment]

[0426] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0427] 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.

[0428] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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).

[0429] 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.

[0430] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0431] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0432] 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.

[0433] 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.

[0434] 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 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.

[0435] 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.

[0436] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0437] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0438] The system of the present invention is for efficiently evaluating the adequacy of creative production and new measures for digital advertising. A specific embodiment of this system will be described below.

[0439] System configuration

[0440] Database

[0441] The server first creates a database of performance data for creative content and campaigns that have been executed in the past, including creative titles, descriptions, and performance scores.

[0442] Centralized management and viewing of data

[0443] The server provides a web interface that allows stakeholders to view and check the database in a centralized manner. Through this interface, users and stakeholders can access past data and obtain the information they need.

[0444] AI-based scoring

[0445] The server uses AI to score newly entered creative content. This AI scoring uses the TF-IDF method and cosine similarity. The TF-IDF method calculates the importance of words based on the frequency of their appearance in a document and their inverse document frequency, while the cosine similarity measures the similarity of creative content.

[0446] Program processing

[0447] Database Connection

[0448] The server first connects to a database management system, such as SQLite, and creates the necessary table structure that stores the creative title, description, and performance score.

[0449] Inserting and Retrieving Data

[0450] The server receives new creative content data and inserts it into the database, and also retrieves all past creative data from the database.

[0451] Applying the scoring algorithm

[0452] The server vectorizes the description of the new creative using the TF-IDF method, compares it with past data to calculate the cosine similarity, and calculates a score for the new creative based on this result.

[0453] Specific examples

[0454] 1. Data Entry:

[0455] The user enters the title "New Year Sale Campaign" and the description "Join our New Year Sale and get up to 50% off!" into the terminal.

[0456] 2. Data storage:

[0457] The server stores this in a database and retrieves past creative data.

[0458] 3. Scoring:

[0459] The server uses AI to calculate the score for the new creative. In this case, it uses the TF-IDF method and cosine similarity to compare it with past data and calculates a score of 88.2.

[0460] 4. Display score:

[0461] Users can view this score on their device to assess the suitability of new creatives. For example, the "New Year Sale Campaign" will be shown with a score of 88.2.

[0462] This system shortens feedback time and enables the rapid production of innovative creatives. It also significantly reduces the time required for consensus building, allowing for the smooth development of new creatives and the implementation of new initiatives in digital advertising.

[0463] The processing flow will be explained below.

[0464] Step 1:

[0465] Database Connection

[0466] The server connects to a database management system such as SQLite by using sqlite3.connect to access the database file and obtain a connection object.

[0467] Step 2:

[0468] Table Creation

[0469] The server creates a table in the database to store the creative data, using the CREATE TABLE SQL statement to set up the table with columns for storing the title, description, and performance score.

[0470] Step 3:

[0471] Data Entry

[0472] The user enters the title and description of the new creative content on the device, for example, "New Year Sale Campaign" and "Join our New Year Sale and get up to 50% off!"

[0473] Step 4:

[0474] Inserting Data

[0475] The server inserts the newly entered creative data into the database using an INSERT INTO SQL statement, inserting the title, description, and initial score (e.g., -1 for unrated).

[0476] Step 5:

[0477] Obtaining past data

[0478] The server retrieves all previously accumulated creative content data from the database, using the SQL statement SELECT FROM Creatives to get a list of titles, descriptions, and performance scores.

[0479] Step 6:

[0480] Text Vectorization

[0481] The server vectorizes the descriptions of the new and past creatives. It converts each description into a numeric vector using the TF-IDF (Term Frequency-Inverse Document Frequency) algorithm. It uses TfidfVectorizer.

[0482] Step 7:

[0483] Similarity calculation

[0484] The server uses cosine similarity to calculate the similarity between the new creative description and the previous description. It uses cosine_similarity to get the similarity score between each resulting vector.

[0485] Step 8:

[0486] Aggregation of Similarity Scores

[0487] The server aggregates the calculated cosine similarity scores and calculates an average score for the new creative, which becomes the performance prediction score for the new creative.

[0488] Step 9:

[0489] Score database update

[0490] The server updates the database with the new creative's performance score using a SQL statement like UPDATE Creatives SET performance_score = ? WHERE id = ?

[0491] Step 10:

[0492] Displaying the score

[0493] On the device, the user sees the performance score for the new creative, specifically the "New Year Sale Campaign" which has a score of 88.2.

[0494] This allows users to quickly assess the relevance of new creative and decide on their next course of action.

[0495] Example 1

[0496] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0497] When creating creative content for digital advertising, there is a need for a method to effectively utilize past performance data and quickly and accurately evaluate the suitability of new content. However, the centralized management of huge amounts of data and the evaluation process using AI are complex, requiring a lot of time and resources.

[0498] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0499] In this invention, the server includes: means for compiling a database of performance data of past digital advertisements and campaigns; means for enabling related parties to centrally view and check the database; means for using artificial intelligence to score new creative content based on the performance data of past digital advertisements and campaigns and propose optimal solutions; means for using artificial intelligence to vectorize and calculate similarity of the new creative content using the TF-IDF method and cosine similarity and calculate its score; and means for storing the score of the new creative content in the database and allowing users to view it on their terminals. This enables the evaluation process of creative content for digital advertisements to be carried out quickly and efficiently.

[0500] "Digital advertising" refers to advertising content delivered via the Internet or digital media.

[0501] "Creative Content" means content created for an advertising campaign, consisting of titles, descriptions, images, videos, and other multimedia elements.

[0502] "Performance data" refers to records of the results and performance of campaigns and measures implemented in the past.

[0503] A "database" is an information system for efficiently storing and managing large amounts of data in a structured format.

[0504] "Artificial intelligence" refers to computer systems that mimic human intelligence and can learn and solve problems automatically.

[0505] "Scoring" is the process of quantifying something for the purposes of evaluation or comparison.

[0506] The "TF-IDF method" is a technique that calculates the importance of each word by combining the term frequency (TF) and inverse document frequency (IDF) of the word in a document.

[0507] "Cosine similarity" is a method for calculating the similarity between two vectors using the dot product and the magnitude of the vectors.

[0508] "Vectorization" is the process of converting text data into vectors of numbers.

[0509] A "terminal" is an electronic device such as a computer or smartphone that a user uses to input and output information.

[0510] The system of the present invention aims to efficiently evaluate the adequacy of creative production and new measures for digital advertising. Specific embodiments of this system are as follows.

[0511] System Overview

[0512] This system is operated by a server, terminals, and users. It also uses artificial intelligence (AI) to score creative content, centrally manages the data, and provides it to users.

[0513] Database construction and operation

[0514] The server first creates a database of performance data for past digital advertisements and campaigns. This database stores the titles, descriptions, and performance scores of creative content. The database management system used is SQLite.

[0515] Centralize and access your data

[0516] The server provides a web interface that allows all parties involved to access, view, and check the database in a centralized manner. Through this interface, users and stakeholders can easily access past data and obtain the information they need. This interface can be accessed through a standard web browser.

[0517] Scoring new creative content

[0518] The server uses artificial intelligence (AI) to score newly entered creative content. This AI scoring uses the TF-IDF method and cosine similarity. The TF-IDF method calculates the importance of each word, and cosine similarity is used to measure the similarity with past creative content.

[0519] Specific examples

[0520] 1. Data Entry:

[0521] The user enters the title "New Year Sale Campaign" and the description "Join our New Year Sale and get up to 50% off!" into the terminal.

[0522] 2. Data storage:

[0523] The server stores this in a database and retrieves past creative data.

[0524] 3. Scoring:

[0525] The server uses AI to calculate the score for the new creative. In this case, it uses the TF-IDF method and cosine similarity to compare it with past data and calculates a score of 88.2.

[0526] 4. Display score:

[0527] Users can view this score on their device to assess the suitability of new creatives. For example, the "New Year Sale Campaign" will be shown with a score of 88.2.

[0528] Prompt Sentence Examples

[0529] You can generate a prompt like this:

[0530] Based on the creative description for the digital ad "New Year Sale Campaign" - "Join our New Year Sale and get up to 50% off!" - calculate the similarity to historical data and assign it a new score.

[0531] This system shortens feedback time and enables the rapid production of innovative creatives. It also significantly reduces the time required for consensus building, allowing for the smooth development of new creatives and the implementation of new initiatives in digital advertising.

[0532] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0533] Step 1: Database Connection and Initial Configuration

[0534] When the server starts up, it first connects to the SQLite database management system and then creates a table structure to store the title, description, and performance score of the creative content.

[0535] Input: System startup, database connection request

[0536] Output: Database connection, table initialization

[0537] What happens: The server opens the SQLite database and creates the required table structure (including title, description, and score fields) if it doesn't exist.

[0538] Step 2: User enters new data

[0539] The user uses the device to input new creative content (e.g., title and description).

[0540] Input: User input form

[0541] Output: Input creative content data

[0542] Specific operation: The user enters the title "New Year Sale Campaign" and the description "Join our New Year Sale and get up to 50% off!" through the web interface.

[0543] Step 3: Save the data to a database

[0544] The server stores the new creative content data received from the user in a database.

[0545] Input: New creative data by user

[0546] Output: New creative data stored in the database

[0547] Specific operation: The server inserts the received new creative data (title and description) into the corresponding table in the SQLite database.

[0548] Step 4: Obtaining historical data

[0549] The server retrieves all past creative data from the database.

[0550] Input: A request to retrieve data from the database

[0551] Output: Obtained historical creative data

[0552] What happens: The server uses an SQL query to read the titles, descriptions, and scores of past creative content from a database.

[0553] Step 5: Score new data

[0554] The server vectorizes the description of the new creative using the TF-IDF method, calculates the cosine similarity, and compares it with past data. The result is used to calculate the score of the new creative.

[0555] Input: New creative description and description of past creative data

[0556] Output: New creative score

[0557] Specific operation: The server uses the TF-IDF vectorization tool to convert the new description into a numerical vector, and then calculates the cosine similarity with the previously obtained description data to calculate a score.

[0558] Step 6: Save the score to the database

[0559] The server stores the score of the new creative in a database.

[0560] Inputs: Calculated score, new creative title and description

[0561] Output: Scores stored in the database

[0562] What happens: The server updates the score of the new creative into an existing database record or inserts it into a new record.

[0563] Step 7: User checks score

[0564] The user uses the device to check the score of the new creative.

[0565] Input: Score display request

[0566] Output: Score of the new creative displayed on the device screen

[0567] What happens: Through the web interface, the user sees that the new creative, "New Year Sale Campaign," has a score of 88.2.

[0568] (Application example 1)

[0569] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0570] Creating and evaluating creative content for digital advertising requires a lot of time and effort. Furthermore, there is a lack of ways to quickly predict and optimize the effectiveness of newly created creative content, making it difficult for advertising planners and marketers to work efficiently. To solve this problem, there is a need for a system that utilizes past data to predict and display the performance of new creative content in real time.

[0571] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0572] In this invention, the server includes: means for creating a database of past creative content and performance data of measures; means for enabling related parties to centrally view and check the database; means for using AI to score new creative content based on the past creative content and performance data of measures and proposing optimal solutions; means for inputting the title and description of a new advertisement from a user terminal; and means for displaying the score in real time after the new advertisement is input. This makes it possible to quickly predict the effectiveness of advertising creatives and efficiently produce optimal creatives.

[0573] "Past creative content and campaign performance data" refers to data that records the results of previously created advertising creatives and related marketing campaigns.

[0574] A "database" is a digital information storage location for efficiently storing and managing past creative content and performance data of initiatives.

[0575] "AI" is an abbreviation for artificial intelligence, a technology that uses machine learning algorithms and natural language processing techniques to analyze and evaluate new creative content.

[0576] "Scoring" is the process of using AI to quantify and evaluate the performance of new creative content.

[0577] "Proposing optimal solutions" refers to AI evaluating the performance of new creative content and generating and proposing effective advertising creatives based on the evaluation results.

[0578] A "user terminal" is a device (e.g., a smartphone or tablet) used by advertising planners or marketers to input new advertising information.

[0579] "Real-time" refers to the process of displaying the evaluation results immediately after a new ad is entered.

[0580] A "title" is a concise expression of the main message or name of the creative content.

[0581] The "description" is the section that describes the detailed information and specific content of the creative content.

[0582] The system for implementing this invention compiles a database of past creative content and performance data of measures, predicts the performance of new creative content based on this data, and proposes optimal advertising creatives.

[0583] System configuration

[0584] Database

[0585] The server maintains a database that stores performance data for creative content created in the past and related measures. This database includes creative titles, descriptions, and performance scores. The database is managed using SQLite.

[0586] Centralized management and viewing of data

[0587] The server provides a web interface that allows stakeholders to view and check the database in a centralized manner. The web interface is built using the Flask framework, allowing stakeholders to easily access past data.

[0588] AI-based scoring

[0589] The server uses a generative AI model to score newly input creative content. This process uses the TF-IDF method and cosine similarity. The server uses the Sklearn library to vectorize the text data of the new creative and calculate the similarity with past data.

[0590] Program processing

[0591] Database connection and configuration

[0592] The server first connects to the SQLite database and creates a table structure to store the creative content data.

[0593] Inserting and Retrieving Data

[0594] The server receives the title and description of the new creative from the user terminal and stores them in the database, and also retrieves past creative data from the database.

[0595] Applying the scoring algorithm

[0596] The server uses the TF-IDF method to vectorize the description of new creative content and calculates the cosine similarity with past creative data. This score is evaluated on a scale of 100 and displayed to the user in real time.

[0597] Specific examples

[0598] For example, a user may enter a title such as "Spring Sale Campaign" and a description such as "Up to 50% off in the Spring Sale!" This input data is sent to the server and stored in a database. The server calculates the similarity between the previous data and the new creative and gives it a score of 85.5. This score is displayed in real time on the web interface on the user's device.

[0599] Prompt Sentence Examples

[0600] Ad Title: Spring Sale Campaign, Description: Up to 50% off in the Spring Sale!

[0601] This system enables advertising planners and marketers to quickly predict the effectiveness of new creatives and efficiently produce effective advertising creatives.

[0602] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0603] Step 1:

[0604] The server connects to the SQLite database and creates the necessary table structure, including tables to store the title, description, and performance score of past creative content. The input is the database structure definition, and the output is the creation of these tables.

[0605] Step 2:

[0606] The user inputs the title and description of the new creative content from the terminal. This input data is sent to the server. As input, details (title and description) of the new creative content are required, and as output, this data is received by the server.

[0607] Step 3:

[0608] The server stores the received new creative data in the database. The new creative details are inserted into the database. As input, it requires the data received from the user and as output, it registers this data in the database.

[0609] Step 4:

[0610] The server retrieves all past creative data from the database. As input, a query to the database is required, and as output, a list of past creative data is obtained.

[0611] Step 5:

[0612] The server uses the Sklearn library to apply the TF-IDF method to vectorize the description of the new creative. As input, it takes the descriptions of the new and previous creatives, and as output, it gets the vectorized descriptions.

[0613] Step 6:

[0614] The server calculates the cosine similarity to measure the similarity between the new creative and the previous creative. Based on this score, it calculates the performance score for the new creative. The input is the vectorized description, and the output is the similarity score and the performance score.

[0615] Step 7:

[0616] The server displays the calculated performance score on the user's device in real time. The user can check the score of the new creative on the device. The performance score is required as input, and the score is displayed on the user's device as output.

[0617] Prompt Sentence Examples

[0618] An example prompt sentence is "Ad title: Spring Sale Campaign, Description: Up to 50% off in the Spring Sale!"

[0619] This series of steps enables advertising planners and marketers to quickly predict the effectiveness of new creatives and efficiently produce optimal advertising creatives.

[0620] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0621] The system of the present invention is designed to efficiently evaluate the creative production of digital advertising and the validity of new initiatives, and by combining it with an emotion engine that recognizes user emotions, it improves the evaluation of creative content. Specific embodiments of this system are described below.

[0622] System configuration

[0623] Database

[0624] The server stores a database of performance data for creative content and campaigns that have been executed in the past, including creative titles, descriptions, and performance scores.

[0625] Centralized management and viewing of data

[0626] The server provides a web interface that allows stakeholders to view and check the database in a centralized manner. Through this interface, users and stakeholders can access past data and obtain the information they need.

[0627] AI-based scoring

[0628] The server uses AI to score newly entered creative content. AI scoring uses the TF-IDF method and cosine similarity. The TF-IDF method calculates the importance of words based on the frequency of their occurrence in a document and their inverse document frequency, while cosine similarity measures the similarity of creative content.

[0629] Emotion engine configuration

[0630] The emotion engine analyzes the user's facial expressions and voice in real time to collect emotional data, which allows it to evaluate how the user feels about the creative content.

[0631] Program processing

[0632] Database Connection

[0633] The server first connects to a database management system, such as SQLite, and creates the necessary table structure that stores the creative title, description, and performance score.

[0634] Inserting and Retrieving Data

[0635] The server receives new creative content data and inserts it into the database, and also retrieves all past creative data from the database.

[0636] Applying the scoring algorithm

[0637] The server vectorizes the description of the new creative using the TF-IDF method, compares it with past data to calculate the cosine similarity, and calculates a score for the new creative based on this result.

[0638] Emotion data collection and analysis

[0639] The device collects emotional data from the user's facial expressions and voice, and the emotion engine analyzes this data in real time to evaluate the user's emotional state.

[0640] Emotional Data Integration

[0641] The server then integrates the user's emotional data obtained from the emotion engine into the evaluation of new creatives. By using the user's emotional data in addition to AI scoring, more accurate evaluations are possible.

[0642] Specific examples

[0643] 1. Data Entry:

[0644] The user enters the title "New Year Sale Campaign" and the description "Join our New Year Sale and get up to 50% off!" into the terminal.

[0645] 2. Data storage:

[0646] The server stores this data in a database and retrieves past creative data.

[0647] 3. Scoring:

[0648] The server uses AI to calculate the score for the new creative. In this case, it uses the TF-IDF method and cosine similarity to compare it with past data and calculates a score of 88.2.

[0649] 4. Collecting Emotional Data:

[0650] The emotion engine collects facial and voice data from the user's device via the device's camera and microphone. For example, if a positive facial expression or tone is detected, the data is evaluated as a favorable response.

[0651] 5. Evaluating Emotional Data:

[0652] The emotion engine sends real-time analyzed emotion data to the server, which then reflects this data in the score of the new creative. For example, if the emotion score is 90, that will affect the final score.

[0653] 6. Display score:

[0654] The device allows users to see the combined performance score of new creatives, showing, for example, that the "New Year Sale Campaign" had a final score of 89.6.

[0655] This system shortens feedback time and enables the rapid production of innovative creatives. It also significantly reduces the time required for consensus building, allowing for the smooth development of new creatives and the implementation of new initiatives in digital advertising. Furthermore, by integrating user emotional data, creative evaluations become more accurate and reliable.

[0656] The processing flow will be explained below.

[0657] Step 1:

[0658] Database Connection

[0659] The server connects to a database management system such as SQLite by using sqlite3.connect to access the database file and obtain a connection object.

[0660] Step 2:

[0661] Table Creation

[0662] The server creates a table in the database to store the creative data, using the CREATE TABLE SQL statement to set up the table with columns for storing the title, description, and performance score.

[0663] Step 3:

[0664] Data Entry

[0665] The user enters the title and description of the new creative content on the device, for example, "New Year Sale Campaign" and "Join our New Year Sale and get up to 50% off!"

[0666] Step 4:

[0667] Inserting Data

[0668] The server inserts the newly entered creative data into the database using an INSERT INTO SQL statement, inserting the title, description, and initial score (e.g., -1 for unrated).

[0669] Step 5:

[0670] Obtaining past data

[0671] The server retrieves all previously accumulated creative content data from the database, using the SQL statement SELECT FROM Creatives to get a list of titles, descriptions, and performance scores.

[0672] Step 6:

[0673] Text Vectorization

[0674] The server vectorizes the descriptions of the new and past creatives. It converts each description into a numeric vector using the TF-IDF (Term Frequency-Inverse Document Frequency) algorithm. It uses TfidfVectorizer.

[0675] Step 7:

[0676] Similarity calculation

[0677] The server uses cosine similarity to calculate the similarity between the new creative description and the previous description. It uses cosine_similarity to get the similarity score between each resulting vector.

[0678] Step 8:

[0679] Aggregation of Similarity Scores

[0680] The server aggregates the calculated cosine similarity scores and calculates an average score for the new creative, which becomes the performance prediction score for the new creative.

[0681] Step 9:

[0682] Collecting Emotional Data

[0683] The device collects facial and voice data in real time from the user's camera and microphone, and the emotion engine analyzes the user's facial muscle movements and tone of voice to determine their emotional state.

[0684] Step 10:

[0685] Emotional Data Analysis

[0686] The emotion engine analyzes the collected facial and voice data to determine whether the user is in a positive, negative, or neutral emotional state, and quantifies this emotional data as an emotion score.

[0687] Step 11:

[0688] Sending emotional data

[0689] The terminal transmits the emotion score obtained as a result of the analysis to the server.

[0690] Step 12:

[0691] Emotional Data Integration

[0692] The server integrates the AI ​​text scoring with the sentiment score received from the sentiment engine, which adjusts the final performance score.

[0693] Step 13:

[0694] Score database update

[0695] The server updates the database with the final combined score using a SQL statement such as UPDATE Creatives SET performance_score = ? WHERE id = ?

[0696] Step 14:

[0697] Displaying the score

[0698] On the device, the user sees the combined performance score of the new creative, for example showing that the "New Year Sale Campaign" has a final score of 89.6.

[0699] This allows users to quickly assess the relevance of new creative and decide on their next course of action.

[0700] Example 2

[0701] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0702] In the creative production and evaluation of digital advertising campaigns, there is a need for efficient utilization of past performance data for rapid and accurate evaluation. However, there is a lack of evaluation that takes user emotions into account, making it difficult to accurately evaluate creatives that reflect user reactions.

[0703] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0704] In this invention, the server includes: means for compiling a database of past electronic advertising content and performance data of measures; means for enabling related parties to centrally view and check the database; means for using artificial intelligence to score new electronic advertising content based on the performance data of past electronic advertising content and measures and proposing optimal solutions; and means for analyzing user facial expressions and voice data in real time and integrating data obtained from an emotion analysis engine that evaluates user emotions. This makes it possible to efficiently utilize past data while accurately evaluating creative content in consideration of user emotions.

[0705] "Electronic advertising content" refers to all advertising creatives distributed on digital platforms.

[0706] "Performance data" refers to data showing the results of past measures and creatives, and includes performance scores, titles, descriptions, etc.

[0707] A "database" refers to a system that systematically organizes information and stores and manages it electronically.

[0708] "Artificial intelligence" refers to the technology that allows machines and computers to simulate human intelligence and learn, reason, and make decisions.

[0709] An "emotion analysis engine" refers to technology that analyzes a user's facial expressions and voice and evaluates their emotional state in real time.

[0710] The "TF-IDF method" refers to a method for calculating the importance of words in a document using word frequency and inverse document frequency.

[0711] "Cosine similarity" refers to a method for measuring the similarity between two vectors in vector space based on the angle between them.

[0712] "Scoring" refers to the process of calculating a score for creative content based on specific evaluation criteria.

[0713] "User" refers to a user who views and evaluates electronic advertising content.

[0714] "Means for centralized viewing and checking" refers to an interface that allows multiple parties to access one central data storage and to view and check information.

[0715] MODE FOR CARRYING OUT THE INVENTION

[0716] The system of the present invention is designed to efficiently evaluate the creative production of electronic advertisements and the validity of new measures. In addition, by combining it with a sentiment analysis engine that recognizes user emotions, it improves the evaluation of creative content.

[0717] System configuration

[0718] Database

[0719] The server creates a database of past digital advertising content and performance data for campaigns. This database stores creative titles, descriptions, and performance scores. SQLite is used as the database.

[0720] Centralized management and viewing of data

[0721] The server provides a web interface that allows stakeholders to view and check the database in a centralized manner. Through this interface, users and stakeholders can access past data and obtain the information they need.

[0722] AI-based scoring

[0723] The server uses artificial intelligence to score newly entered digital advertising content. This scoring is performed using the TF-IDF method and cosine similarity. The TF-IDF method calculates the importance of words based on the frequency of their appearance in a document and their inverse document frequency, while the cosine similarity measures the similarity of creative content.

[0724] Sentiment analysis engine configuration

[0725] The device is equipped with an emotion analysis engine that analyzes the user's facial expressions and voice in real time, allowing it to evaluate how the user feels about the digital advertising content.

[0726] Program processing

[0727] Database Connection

[0728] The server first connects to a database management system, such as SQLite, and creates the necessary table structure that stores the creative title, description, and performance score.

[0729] Inserting and Retrieving Data

[0730] The server receives new electronic advertising content data and inserts it into the database, and also retrieves all past electronic advertising data from the database.

[0731] Applying the scoring algorithm

[0732] The server uses the TF-IDF method to vectorize the description of the new digital advertisement, compares it with past data to calculate the cosine similarity, and calculates a score for the new creative based on this result.

[0733] Emotion data collection and analysis

[0734] The device collects emotional data from the user's facial expressions and voice, and the emotion analysis engine analyzes this data in real time to evaluate the user's emotional state.

[0735] Emotional Data Integration

[0736] The server then integrates the user's emotional data obtained from the emotion analysis engine into the evaluation of the new creative. By using the user's emotional data in addition to the AI ​​scoring, a more accurate evaluation is possible.

[0737] Specific examples

[0738] Data Entry

[0739] The user enters the title "New Year Sale Campaign" and the description "Join our New Year Sale and get up to 50% off!" into the terminal.

[0740] Data storage

[0741] The server stores this data in a database and retrieves past creative data.

[0742] Scoring

[0743] The server uses artificial intelligence to calculate the score for the new creative. In this case, it uses the TF-IDF method and cosine similarity to compare it with past data and calculates a score of 88.2.

[0744] Collecting Emotional Data

[0745] The user's facial expression and voice data are collected by the emotion analysis engine through the device's camera and microphone. For example, if a positive expression or tone is detected, the data is evaluated as a favorable reaction.

[0746] Emotional Data Evaluation

[0747] The sentiment analysis engine sends the analyzed sentiment data in real time to the server, which then reflects this data in the score of the new creative. For example, if the sentiment score is 90, it will affect the final score.

[0748] Displaying the score

[0749] The device allows users to see the combined performance score of new creatives, showing, for example, that the "New Year Sale Campaign" had a final score of 89.6.

[0750] Example prompt sentence:

[0751] Enter the title and description of the digital ad creative below, and we'll use artificial intelligence to score it and collect user sentiment data to evaluate it.

[0752] Title: New Year Sale Campaign

[0753] Description: Join our New Year Sale and get up to 50% off!

[0754] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0755] Step 1:

[0756] The server connects to a database, such as SQLite, to store creative data and performance data for digital ads. First, a connection string is generated and used to connect to the database. Next, a table named "creatives_table" is created. The table has fields containing a title, description, and performance score. The input to this process is the database connection information held by the server, and the output is that the database and table are ready.

[0757] Step 2:

[0758] The server receives new electronic advertising content data from the terminal and inserts it into the database. For example, a user enters the title "New Year Sale Campaign" and the description "Join our New Year Sale and get up to 50% off!" The server saves this data in the database using the SQL INSERT statement. The input of this process is the advertising content data received from the user, and the output is the new data being inserted into the database.

[0759] Step 3:

[0760] The server retrieves all past digital advertising data from the database using an SQL SELECT statement. After the data is read, it is stored in memory. The input to this process is a specific query statement, and the output is the retrieved past digital advertising data.

[0761] Step 4:

[0762] The server vectorizes the description of the new digital ad using the TF-IDF method. First, the description is tokenized and the TF-IDF method is applied to calculate the importance of each word in the document. Next, the past creative data is similarly vectorized and the cosine similarity between that vector and the vector of the new data is calculated. A score is calculated based on this result. For example, a score of 88.2 is obtained for the new data. The inputs to this process are the new description and past data, and the output is the score for the new creative data.

[0763] Step 5:

[0764] The device collects the user's facial and voice data using the device's camera and microphone. The collected data is sent to an emotion analysis engine and analyzed in real time. The analysis results are evaluated in list form, including emotional states such as positive, negative, and neutral. The input of this process is the user's facial and voice data, and the output is analyzed emotional data.

[0765] Step 6:

[0766] The server receives the sentiment data from the sentiment analysis engine and integrates it into the final rating of the new creative. For example, if the sentiment score is 90, it will be reflected in the final score, which is expected to result in a final score of 89.6. The input of this process is the sentiment data from the sentiment analysis engine, and the output is the integrated final score.

[0767] Step 7:

[0768] The terminal displays the integrated final score to the user. For example, it shows that the final score for the "New Year Sale Campaign" is 89.6. This allows the user to check the evaluation results of the new creative. The input of this process is the final score, and the output is the result displayed in the user interface.

[0769] (Application example 2)

[0770] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0771] When creating and evaluating creative content for digital advertising, there is a need to measure performance quickly and accurately. However, conventional methods mainly rely on past data for evaluation, making it difficult to reflect real-time user sentiment. This makes it impossible to accurately reflect actual user reactions.

[0772] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for compiling a database of past creative content and performance data of measures; means for enabling related parties to centrally view and check the database; means for using AI to score new creative content based on the performance data of past creative content and measures and proposing optimal solutions; means for analyzing the user's facial expressions and voice using a terminal to collect emotional data; means for integrating the emotional data into the scoring of the new creative content; and means for providing the user with an evaluation result based on the scoring and emotional data via an interface. This makes it possible to evaluate creative content in a way that reflects the user's real-time emotions.

[0773] "Means of creating a database" refers to a method for systematically organizing data on past creative content and performance of measures, and storing the information.

[0774] "A single point of access and check" means a method that allows all parties involved to efficiently review and audit the information in the database through a single interface.

[0775] "A method of using AI to score and propose optimal solutions" is a method that utilizes artificial intelligence technology to evaluate new creative content and derive optimal advertising measures.

[0776] "Means for analyzing a user's facial expressions and voice using a terminal and collecting emotional data" refers to a method for measuring a user's emotional state and acquiring data using a device equipped with a camera and microphone.

[0777] The "means for integrating emotional data into the scoring of new creative content" is a method for incorporating collected emotional data into the evaluation process of new creative content to perform a composite evaluation.

[0778] "Means for providing users with evaluation results based on scoring and emotional data via an interface" refers to a method for providing users with evaluation results based on scoring and emotional data via a user interface for displaying the evaluation results.

[0779] The system of the present invention is for quickly and accurately producing and evaluating creative content for digital advertising. Specific embodiments of this system will be described below.

[0780] System configuration

[0781] The system of the present invention includes the following major components:

[0782] 1. Database creation method:

[0783] The server stores historical creative content and performance data in a database, including creative titles, descriptions, and performance scores.

[0784] 2. Centralized viewing and checking:

[0785] The server provides a web interface that allows interested parties to centrally view and check the historical database.

[0786] 3. AI-based scoring and suggestion of optimal solutions:

[0787] The server uses AI to score newly input creative content using TF-IDF and cosine similarity.

[0788] 4. Using a device to analyze a user's facial expressions and voice to collect emotional data:

[0789] The device uses a camera and microphone to analyze the user's facial expressions and voice in real time to collect emotional data, using the DeepFace library for emotion analysis.

[0790] 5. Means of integrating sentiment data into scoring new creative content:

[0791] The server then integrates the emotion data obtained from the emotion engine into the evaluation of the new creative, enabling a more accurate evaluation that reflects the user's emotions.

[0792] 6. Means for providing users with evaluation results based on scoring and emotion data via an interface:

[0793] The server provides an interface for displaying the evaluation results to the user, which displays the evaluation results based on the emotion data along with the performance scores.

[0794] Hardware and software used

[0795] Hardware: Smartphone, head-mounted display, built-in camera, built-in microphone

[0796] Software: Python, OpenCV, DeepFace library, SQLite, scikit-learn

[0797] Specific examples

[0798] A user views a digital advertisement using a smartphone or head-mounted display. They enter "New Year Sale Campaign" as the title and "Join our New Year Sale and get up to 50% off!" as the description. The server stores this data in a database and uses AI to score it. For example, it calculates a score of 88.2 based on the TF-IDF method and cosine similarity.

[0799] Next, the device's camera and microphone are used to collect emotion data from the user's facial expressions and voice. The emotion engine analyzes this data in real time and sends the emotion data to the server. For example, if the user's emotion score is 90, this score will be included in the final performance evaluation.

[0800] Finally, the server provides the consolidated performance score to the user through the interface, where the user can see that the "New Year Sale Campaign" had a final score of 89.6.

[0801] Prompt Sentence Examples

[0802] "Use a camera and microphone to collect real-time sentiment data while users are viewing a commercial. Explain how you would use the sentiment data to calculate a performance score for the ad. Give a thumbs up if the viewer expresses positive sentiment and a thumbs down if the viewer expresses negative sentiment."

[0803] In this way, it becomes possible to evaluate creative content that reflects users' real-time emotions, improving the efficiency of creating and evaluating digital advertisements.

[0804] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0805] Step 1:

[0806] The server stores past creative content and performance data of initiatives in a database. It receives input data such as the title, description, and performance score of creative content provided by users, systematically organizes it, and records it in an SQLite database. This database storage allows for the creation of historical data that can be accessed later by relevant parties.

[0807] Step 2:

[0808] The server provides a web interface that allows stakeholders to centrally view and check past creative data in the database. Users or administrators can access the past data through the interface and review and evaluate the necessary information (e.g., title, description, performance score). This interface is built using common web technologies such as HTML, CSS, and JavaScript.

[0809] Step 3:

[0810] The server scores new creative content using the TF-IDF method and cosine similarity. It receives the description of the new creative content entered by the user and calculates the TF-IDF vector. It compares the calculated vector with vectors in the past database to calculate the cosine similarity and determines the score for the new creative. The output is a numerical score result (e.g., 88.2).

[0811] Step 4:

[0812] The device uses a camera and microphone to analyze the user's facial expressions and voice in real time to collect emotional data. The device analyzes facial expressions and voice as input data collected while the user is viewing advertisements and classifies them into emotions (joy, anger, sadness, happiness, etc.). The DeepFace library is used to perform the emotion analysis, and the analysis results are output as emotional data.

[0813] Step 5:

[0814] The server integrates the collected emotional data into the scoring of new creative content. It receives the emotional data sent from the device and adds it to the scoring results. For example, if the emotional score is positive, it adjusts it to improve the final score. It outputs the integrated final score (e.g., 89.6).

[0815] Step 6:

[0816] The server provides the user with the evaluation results based on the scoring and emotional data via an interface. The final score and emotional evaluation results calculated on the server side are displayed in a user-viewable interface. The user can check the performance evaluation results of the creative content through the interface, which can be used to improve subsequent advertising measures. Detailed feedback based on the scoring results and emotional data is provided as an output.

[0817] 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.

[0818] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. 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 voice, text data indicating text, and image data indicating an image is also input. 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.

[0819] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0820] [Third embodiment]

[0821] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0822] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0823] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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).

[0824] 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.

[0825] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0826] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0827] 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.

[0828] 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.

[0829] 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 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.

[0830] 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.

[0831] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0832] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0833] The system of the present invention is for efficiently evaluating the adequacy of creative production and new measures for digital advertising. A specific embodiment of this system will be described below.

[0834] System configuration

[0835] Database

[0836] The server first creates a database of performance data for creative content and campaigns that have been executed in the past, including creative titles, descriptions, and performance scores.

[0837] Centralized management and viewing of data

[0838] The server provides a web interface that allows stakeholders to view and check the database in a centralized manner. Through this interface, users and stakeholders can access past data and obtain the information they need.

[0839] AI-based scoring

[0840] The server uses AI to score newly entered creative content. This AI scoring uses the TF-IDF method and cosine similarity. The TF-IDF method calculates the importance of words based on the frequency of their appearance in a document and their inverse document frequency, while the cosine similarity measures the similarity of creative content.

[0841] Program processing

[0842] Database Connection

[0843] The server first connects to a database management system, such as SQLite, and creates the necessary table structure that stores the creative title, description, and performance score.

[0844] Inserting and Retrieving Data

[0845] The server receives new creative content data and inserts it into the database, and also retrieves all past creative data from the database.

[0846] Applying the scoring algorithm

[0847] The server vectorizes the description of the new creative using the TF-IDF method, compares it with past data to calculate the cosine similarity, and calculates a score for the new creative based on this result.

[0848] Specific examples

[0849] 1. Data Entry:

[0850] The user enters the title "New Year Sale Campaign" and the description "Join our New Year Sale and get up to 50% off!" into the terminal.

[0851] 2. Data storage:

[0852] The server stores this in a database and retrieves past creative data.

[0853] 3. Scoring:

[0854] The server uses AI to calculate the score for the new creative. In this case, it uses the TF-IDF method and cosine similarity to compare it with past data and calculates a score of 88.2.

[0855] 4. Display score:

[0856] Users can view this score on their device to assess the suitability of new creatives. For example, the "New Year Sale Campaign" will be shown with a score of 88.2.

[0857] This system shortens feedback time and enables the rapid production of innovative creatives. It also significantly reduces the time required for consensus building, allowing for the smooth development of new creatives and the implementation of new initiatives in digital advertising.

[0858] The processing flow will be explained below.

[0859] Step 1:

[0860] Database Connection

[0861] The server connects to a database management system such as SQLite by using sqlite3.connect to access the database file and obtain a connection object.

[0862] Step 2:

[0863] Table Creation

[0864] The server creates a table in the database to store the creative data, using the CREATE TABLE SQL statement to set up the table with columns for storing the title, description, and performance score.

[0865] Step 3:

[0866] Data Entry

[0867] The user enters the title and description of the new creative content on the device, for example, "New Year Sale Campaign" and "Join our New Year Sale and get up to 50% off!"

[0868] Step 4:

[0869] Inserting Data

[0870] The server inserts the newly entered creative data into the database using an INSERT INTO SQL statement, inserting the title, description, and initial score (e.g., -1 for unrated).

[0871] Step 5:

[0872] Obtaining past data

[0873] The server retrieves all previously accumulated creative content data from the database, using the SQL statement SELECT FROM Creatives to get a list of titles, descriptions, and performance scores.

[0874] Step 6:

[0875] Text Vectorization

[0876] The server vectorizes the descriptions of the new and past creatives. It converts each description into a numeric vector using the TF-IDF (Term Frequency-Inverse Document Frequency) algorithm. It uses TfidfVectorizer.

[0877] Step 7:

[0878] Similarity calculation

[0879] The server uses cosine similarity to calculate the similarity between the new creative description and the previous description. It uses cosine_similarity to get the similarity score between each resulting vector.

[0880] Step 8:

[0881] Aggregation of Similarity Scores

[0882] The server aggregates the calculated cosine similarity scores and calculates an average score for the new creative, which becomes the performance prediction score for the new creative.

[0883] Step 9:

[0884] Score database update

[0885] The server updates the database with the new creative's performance score using a SQL statement like UPDATE Creatives SET performance_score = ? WHERE id = ?

[0886] Step 10:

[0887] Displaying the score

[0888] On the device, the user sees the performance score for the new creative, specifically the "New Year Sale Campaign" which has a score of 88.2.

[0889] This allows users to quickly assess the relevance of new creative and decide on their next course of action.

[0890] Example 1

[0891] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0892] When creating creative content for digital advertising, there is a need for a method to effectively utilize past performance data and quickly and accurately evaluate the suitability of new content. However, the centralized management of huge amounts of data and the evaluation process using AI are complex, requiring a lot of time and resources.

[0893] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0894] In this invention, the server includes: means for compiling a database of performance data of past digital advertisements and campaigns; means for enabling related parties to centrally view and check the database; means for using artificial intelligence to score new creative content based on the performance data of past digital advertisements and campaigns and propose optimal solutions; means for using artificial intelligence to vectorize and calculate similarity of the new creative content using the TF-IDF method and cosine similarity and calculate its score; and means for storing the score of the new creative content in the database and allowing users to view it on their terminals. This enables the evaluation process of creative content for digital advertisements to be carried out quickly and efficiently.

[0895] "Digital advertising" refers to advertising content delivered via the Internet or digital media.

[0896] "Creative Content" means content created for an advertising campaign, consisting of titles, descriptions, images, videos, and other multimedia elements.

[0897] "Performance data" refers to records of the results and performance of campaigns and measures implemented in the past.

[0898] A "database" is an information system for efficiently storing and managing large amounts of data in a structured format.

[0899] "Artificial intelligence" refers to computer systems that mimic human intelligence and can learn and solve problems automatically.

[0900] "Scoring" is the process of quantifying something for the purposes of evaluation or comparison.

[0901] The "TF-IDF method" is a technique that calculates the importance of each word by combining the term frequency (TF) and inverse document frequency (IDF) of the word in a document.

[0902] "Cosine similarity" is a method for calculating the similarity between two vectors using the dot product and the magnitude of the vectors.

[0903] "Vectorization" is the process of converting text data into vectors of numbers.

[0904] A "terminal" is an electronic device such as a computer or smartphone that a user uses to input and output information.

[0905] The system of the present invention aims to efficiently evaluate the adequacy of creative production and new measures for digital advertising. Specific embodiments of this system are as follows.

[0906] System Overview

[0907] This system is operated by a server, terminals, and users. It also uses artificial intelligence (AI) to score creative content, centrally manages the data, and provides it to users.

[0908] Database construction and operation

[0909] The server first creates a database of performance data for past digital advertisements and campaigns. This database stores the titles, descriptions, and performance scores of creative content. The database management system used is SQLite.

[0910] Centralize and access your data

[0911] The server provides a web interface that allows all parties involved to access, view, and check the database in a centralized manner. Through this interface, users and stakeholders can easily access past data and obtain the information they need. This interface can be accessed through a standard web browser.

[0912] Scoring new creative content

[0913] The server uses artificial intelligence (AI) to score newly entered creative content. This AI scoring uses the TF-IDF method and cosine similarity. The TF-IDF method calculates the importance of each word, and cosine similarity is used to measure the similarity with past creative content.

[0914] Specific examples

[0915] 1. Data Entry:

[0916] The user enters the title "New Year Sale Campaign" and the description "Join our New Year Sale and get up to 50% off!" into the terminal.

[0917] 2. Data storage:

[0918] The server stores this in a database and retrieves past creative data.

[0919] 3. Scoring:

[0920] The server uses AI to calculate the score for the new creative. In this case, it uses the TF-IDF method and cosine similarity to compare it with past data and calculates a score of 88.2.

[0921] 4. Display score:

[0922] Users can view this score on their device to assess the suitability of new creatives. For example, the "New Year Sale Campaign" will be shown with a score of 88.2.

[0923] Prompt Sentence Examples

[0924] You can generate a prompt like this:

[0925] Based on the creative description for the digital ad "New Year Sale Campaign" - "Join our New Year Sale and get up to 50% off!" - calculate the similarity to historical data and assign it a new score.

[0926] This system shortens feedback time and enables the rapid production of innovative creatives. It also significantly reduces the time required for consensus building, allowing for the smooth development of new creatives and the implementation of new initiatives in digital advertising.

[0927] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0928] Step 1: Database Connection and Initial Configuration

[0929] When the server starts up, it first connects to the SQLite database management system and then creates a table structure to store the title, description, and performance score of the creative content.

[0930] Input: System startup, database connection request

[0931] Output: Database connection, table initialization

[0932] What happens: The server opens the SQLite database and creates the required table structure (including title, description, and score fields) if it doesn't exist.

[0933] Step 2: User enters new data

[0934] The user uses the device to input new creative content (e.g., title and description).

[0935] Input: User input form

[0936] Output: Input creative content data

[0937] Specific operation: The user enters the title "New Year Sale Campaign" and the description "Join our New Year Sale and get up to 50% off!" through the web interface.

[0938] Step 3: Save the data to a database

[0939] The server stores the new creative content data received from the user in a database.

[0940] Input: New creative data by user

[0941] Output: New creative data stored in the database

[0942] Specific operation: The server inserts the received new creative data (title and description) into the corresponding table in the SQLite database.

[0943] Step 4: Obtaining historical data

[0944] The server retrieves all past creative data from the database.

[0945] Input: A request to retrieve data from the database

[0946] Output: Obtained historical creative data

[0947] What happens: The server uses an SQL query to read the titles, descriptions, and scores of past creative content from a database.

[0948] Step 5: Score new data

[0949] The server vectorizes the description of the new creative using the TF-IDF method, calculates the cosine similarity, and compares it with past data. The result is used to calculate the score of the new creative.

[0950] Input: New creative description and description of past creative data

[0951] Output: New creative score

[0952] Specific operation: The server uses the TF-IDF vectorization tool to convert the new description into a numerical vector, and then calculates the cosine similarity with the previously obtained description data to calculate a score.

[0953] Step 6: Save the score to the database

[0954] The server stores the score of the new creative in a database.

[0955] Inputs: Calculated score, new creative title and description

[0956] Output: Scores stored in the database

[0957] What happens: The server updates the score of the new creative into an existing database record or inserts it into a new record.

[0958] Step 7: User checks score

[0959] The user uses the device to check the score of the new creative.

[0960] Input: Score display request

[0961] Output: Score of the new creative displayed on the device screen

[0962] What happens: Through the web interface, the user sees that the new creative, "New Year Sale Campaign," has a score of 88.2.

[0963] (Application example 1)

[0964] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0965] Creating and evaluating creative content for digital advertising requires a lot of time and effort. Furthermore, there is a lack of ways to quickly predict and optimize the effectiveness of newly created creative content, making it difficult for advertising planners and marketers to work efficiently. To solve this problem, there is a need for a system that utilizes past data to predict and display the performance of new creative content in real time.

[0966] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0967] In this invention, the server includes: means for creating a database of past creative content and performance data of measures; means for enabling related parties to centrally view and check the database; means for using AI to score new creative content based on the past creative content and performance data of measures and proposing optimal solutions; means for inputting the title and description of a new advertisement from a user terminal; and means for displaying the score in real time after the new advertisement is input. This makes it possible to quickly predict the effectiveness of advertising creatives and efficiently produce optimal creatives.

[0968] "Past creative content and campaign performance data" refers to data that records the results of previously created advertising creatives and related marketing campaigns.

[0969] A "database" is a digital information storage location for efficiently storing and managing past creative content and performance data of initiatives.

[0970] "AI" is an abbreviation for artificial intelligence, a technology that uses machine learning algorithms and natural language processing techniques to analyze and evaluate new creative content.

[0971] "Scoring" is the process of using AI to quantify and evaluate the performance of new creative content.

[0972] "Proposing optimal solutions" refers to AI evaluating the performance of new creative content and generating and proposing effective advertising creatives based on the evaluation results.

[0973] A "user terminal" is a device (e.g., a smartphone or tablet) used by advertising planners or marketers to input new advertising information.

[0974] "Real-time" refers to the process of displaying the evaluation results immediately after a new ad is entered.

[0975] A "title" is a concise expression of the main message or name of the creative content.

[0976] The "description" is the section that describes the detailed information and specific content of the creative content.

[0977] The system for implementing this invention compiles a database of past creative content and performance data of measures, predicts the performance of new creative content based on this data, and proposes optimal advertising creatives.

[0978] System configuration

[0979] Database

[0980] The server maintains a database that stores performance data for creative content created in the past and related measures. This database includes creative titles, descriptions, and performance scores. The database is managed using SQLite.

[0981] Centralized management and viewing of data

[0982] The server provides a web interface that allows stakeholders to view and check the database in a centralized manner. The web interface is built using the Flask framework, allowing stakeholders to easily access past data.

[0983] AI-based scoring

[0984] The server uses a generative AI model to score newly input creative content. This process uses the TF-IDF method and cosine similarity. The server uses the Sklearn library to vectorize the text data of the new creative and calculate the similarity with past data.

[0985] Program processing

[0986] Database connection and configuration

[0987] The server first connects to the SQLite database and creates a table structure to store the creative content data.

[0988] Inserting and Retrieving Data

[0989] The server receives the title and description of the new creative from the user terminal and stores them in the database, and also retrieves past creative data from the database.

[0990] Applying the scoring algorithm

[0991] The server uses the TF-IDF method to vectorize the description of new creative content and calculates the cosine similarity with past creative data. This score is evaluated on a scale of 100 and displayed to the user in real time.

[0992] Specific examples

[0993] For example, a user may enter a title such as "Spring Sale Campaign" and a description such as "Up to 50% off in the Spring Sale!" This input data is sent to the server and stored in a database. The server calculates the similarity between the previous data and the new creative and gives it a score of 85.5. This score is displayed in real time on the web interface on the user's device.

[0994] Prompt Sentence Examples

[0995] Ad Title: Spring Sale Campaign, Description: Up to 50% off in the Spring Sale!

[0996] This system enables advertising planners and marketers to quickly predict the effectiveness of new creatives and efficiently produce effective advertising creatives.

[0997] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0998] Step 1:

[0999] The server connects to the SQLite database and creates the necessary table structure, including tables to store the title, description, and performance score of past creative content. The input is the database structure definition, and the output is the creation of these tables.

[1000] Step 2:

[1001] The user inputs the title and description of the new creative content from the terminal. This input data is sent to the server. As input, details (title and description) of the new creative content are required, and as output, this data is received by the server.

[1002] Step 3:

[1003] The server stores the received new creative data in the database. The new creative details are inserted into the database. As input, it requires the data received from the user and as output, it registers this data in the database.

[1004] Step 4:

[1005] The server retrieves all past creative data from the database. As input, a query to the database is required, and as output, a list of past creative data is obtained.

[1006] Step 5:

[1007] The server uses the Sklearn library to apply the TF-IDF method to vectorize the description of the new creative. As input, it takes the descriptions of the new and previous creatives, and as output, it gets the vectorized descriptions.

[1008] Step 6:

[1009] The server calculates the cosine similarity to measure the similarity between the new creative and the previous creative. Based on this score, it calculates the performance score for the new creative. The input is the vectorized description, and the output is the similarity score and the performance score.

[1010] Step 7:

[1011] The server displays the calculated performance score on the user's device in real time. The user can check the score of the new creative on the device. The performance score is required as input, and the score is displayed on the user's device as output.

[1012] Prompt Sentence Examples

[1013] An example prompt sentence is "Ad title: Spring Sale Campaign, Description: Up to 50% off in the Spring Sale!"

[1014] This series of steps enables advertising planners and marketers to quickly predict the effectiveness of new creatives and efficiently produce optimal advertising creatives.

[1015] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1016] The system of the present invention is designed to efficiently evaluate the creative production of digital advertising and the validity of new initiatives, and by combining it with an emotion engine that recognizes user emotions, it improves the evaluation of creative content. Specific embodiments of this system are described below.

[1017] System configuration

[1018] Database

[1019] The server stores a database of performance data for creative content and campaigns that have been executed in the past, including creative titles, descriptions, and performance scores.

[1020] Centralized management and viewing of data

[1021] The server provides a web interface that allows stakeholders to view and check the database in a centralized manner. Through this interface, users and stakeholders can access past data and obtain the information they need.

[1022] AI-based scoring

[1023] The server uses AI to score newly entered creative content. AI scoring uses the TF-IDF method and cosine similarity. The TF-IDF method calculates the importance of words based on the frequency of their occurrence in a document and their inverse document frequency, while cosine similarity measures the similarity of creative content.

[1024] Emotion engine configuration

[1025] The emotion engine analyzes the user's facial expressions and voice in real time to collect emotional data, which allows it to evaluate how the user feels about the creative content.

[1026] Program processing

[1027] Database Connection

[1028] The server first connects to a database management system, such as SQLite, and creates the necessary table structure that stores the creative title, description, and performance score.

[1029] Inserting and Retrieving Data

[1030] The server receives new creative content data and inserts it into the database, and also retrieves all past creative data from the database.

[1031] Applying the scoring algorithm

[1032] The server vectorizes the description of the new creative using the TF-IDF method, compares it with past data to calculate the cosine similarity, and calculates a score for the new creative based on this result.

[1033] Emotion data collection and analysis

[1034] The device collects emotional data from the user's facial expressions and voice, and the emotion engine analyzes this data in real time to evaluate the user's emotional state.

[1035] Emotional Data Integration

[1036] The server then integrates the user's emotional data obtained from the emotion engine into the evaluation of new creatives. By using the user's emotional data in addition to AI scoring, more accurate evaluations are possible.

[1037] Specific examples

[1038] 1. Data Entry:

[1039] The user enters the title "New Year Sale Campaign" and the description "Join our New Year Sale and get up to 50% off!" into the terminal.

[1040] 2. Data storage:

[1041] The server stores this data in a database and retrieves past creative data.

[1042] 3. Scoring:

[1043] The server uses AI to calculate the score for the new creative. In this case, it uses the TF-IDF method and cosine similarity to compare it with past data and calculates a score of 88.2.

[1044] 4. Collecting Emotional Data:

[1045] The emotion engine collects facial and voice data from the user's device via the device's camera and microphone. For example, if a positive facial expression or tone is detected, the data is evaluated as a favorable response.

[1046] 5. Evaluating Emotional Data:

[1047] The emotion engine sends real-time analyzed emotion data to the server, which then reflects this data in the score of the new creative. For example, if the emotion score is 90, that will affect the final score.

[1048] 6. Display score:

[1049] The device allows users to see the combined performance score of new creatives, showing, for example, that the "New Year Sale Campaign" had a final score of 89.6.

[1050] This system shortens feedback time and enables the rapid production of innovative creatives. It also significantly reduces the time required for consensus building, allowing for the smooth development of new creatives and the implementation of new initiatives in digital advertising. Furthermore, by integrating user emotional data, creative evaluations become more accurate and reliable.

[1051] The processing flow will be explained below.

[1052] Step 1:

[1053] Database Connection

[1054] The server connects to a database management system such as SQLite by using sqlite3.connect to access the database file and obtain a connection object.

[1055] Step 2:

[1056] Table Creation

[1057] The server creates a table in the database to store the creative data, using the CREATE TABLE SQL statement to set up the table with columns for storing the title, description, and performance score.

[1058] Step 3:

[1059] Data Entry

[1060] The user enters the title and description of the new creative content on the device, for example, "New Year Sale Campaign" and "Join our New Year Sale and get up to 50% off!"

[1061] Step 4:

[1062] Inserting Data

[1063] The server inserts the newly entered creative data into the database using an INSERT INTO SQL statement, inserting the title, description, and initial score (e.g., -1 for unrated).

[1064] Step 5:

[1065] Obtaining past data

[1066] The server retrieves all previously accumulated creative content data from the database, using the SQL statement SELECT FROM Creatives to get a list of titles, descriptions, and performance scores.

[1067] Step 6:

[1068] Text Vectorization

[1069] The server vectorizes the descriptions of the new and past creatives. It converts each description into a numeric vector using the TF-IDF (Term Frequency-Inverse Document Frequency) algorithm. It uses TfidfVectorizer.

[1070] Step 7:

[1071] Similarity calculation

[1072] The server uses cosine similarity to calculate the similarity between the new creative description and the previous description. It uses cosine_similarity to get the similarity score between each resulting vector.

[1073] Step 8:

[1074] Aggregation of Similarity Scores

[1075] The server aggregates the calculated cosine similarity scores and calculates an average score for the new creative, which becomes the performance prediction score for the new creative.

[1076] Step 9:

[1077] Collecting Emotional Data

[1078] The device collects facial and voice data in real time from the user's camera and microphone, and the emotion engine analyzes the user's facial muscle movements and tone of voice to determine their emotional state.

[1079] Step 10:

[1080] Emotional Data Analysis

[1081] The emotion engine analyzes the collected facial and voice data to determine whether the user is in a positive, negative, or neutral emotional state, and quantifies this emotional data as an emotion score.

[1082] Step 11:

[1083] Sending emotional data

[1084] The terminal transmits the emotion score obtained as a result of the analysis to the server.

[1085] Step 12:

[1086] Emotional Data Integration

[1087] The server integrates the AI ​​text scoring with the sentiment score received from the sentiment engine, which adjusts the final performance score.

[1088] Step 13:

[1089] Score database update

[1090] The server updates the database with the final combined score using a SQL statement such as UPDATE Creatives SET performance_score = ? WHERE id = ?

[1091] Step 14:

[1092] Displaying the score

[1093] On the device, the user sees the combined performance score of the new creative, for example showing that the "New Year Sale Campaign" has a final score of 89.6.

[1094] This allows users to quickly assess the relevance of new creative and decide on their next course of action.

[1095] Example 2

[1096] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1097] In the creative production and evaluation of digital advertising campaigns, there is a need for efficient utilization of past performance data for rapid and accurate evaluation. However, there is a lack of evaluation that takes user emotions into account, making it difficult to accurately evaluate creatives that reflect user reactions.

[1098] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1099] In this invention, the server includes: means for compiling a database of past electronic advertising content and performance data of measures; means for enabling related parties to centrally view and check the database; means for using artificial intelligence to score new electronic advertising content based on the performance data of past electronic advertising content and measures and proposing optimal solutions; and means for analyzing user facial expressions and voice data in real time and integrating data obtained from an emotion analysis engine that evaluates user emotions. This makes it possible to efficiently utilize past data while accurately evaluating creative content in consideration of user emotions.

[1100] "Electronic advertising content" refers to all advertising creatives distributed on digital platforms.

[1101] "Performance data" refers to data showing the results of past measures and creatives, and includes performance scores, titles, descriptions, etc.

[1102] A "database" refers to a system that systematically organizes information and stores and manages it electronically.

[1103] "Artificial intelligence" refers to the technology that allows machines and computers to simulate human intelligence and learn, reason, and make decisions.

[1104] An "emotion analysis engine" refers to technology that analyzes a user's facial expressions and voice and evaluates their emotional state in real time.

[1105] The "TF-IDF method" refers to a method for calculating the importance of words in a document using word frequency and inverse document frequency.

[1106] "Cosine similarity" refers to a method for measuring the similarity between two vectors in vector space based on the angle between them.

[1107] "Scoring" refers to the process of calculating a score for creative content based on specific evaluation criteria.

[1108] "User" refers to a user who views and evaluates electronic advertising content.

[1109] "Means for centralized viewing and checking" refers to an interface that allows multiple parties to access one central data storage and to view and check information.

[1110] MODE FOR CARRYING OUT THE INVENTION

[1111] The system of the present invention is designed to efficiently evaluate the creative production of electronic advertisements and the validity of new measures. In addition, by combining it with a sentiment analysis engine that recognizes user emotions, it improves the evaluation of creative content.

[1112] System configuration

[1113] Database

[1114] The server creates a database of past digital advertising content and performance data for campaigns. This database stores creative titles, descriptions, and performance scores. SQLite is used as the database.

[1115] Centralized management and viewing of data

[1116] The server provides a web interface that allows stakeholders to view and check the database in a centralized manner. Through this interface, users and stakeholders can access past data and obtain the information they need.

[1117] AI-based scoring

[1118] The server uses artificial intelligence to score newly entered digital advertising content. This scoring is performed using the TF-IDF method and cosine similarity. The TF-IDF method calculates the importance of words based on the frequency of their appearance in a document and their inverse document frequency, while the cosine similarity measures the similarity of creative content.

[1119] Sentiment analysis engine configuration

[1120] The device is equipped with an emotion analysis engine that analyzes the user's facial expressions and voice in real time, allowing it to evaluate how the user feels about the digital advertising content.

[1121] Program processing

[1122] Database Connection

[1123] The server first connects to a database management system, such as SQLite, and creates the necessary table structure that stores the creative title, description, and performance score.

[1124] Inserting and Retrieving Data

[1125] The server receives new electronic advertising content data and inserts it into the database, and also retrieves all past electronic advertising data from the database.

[1126] Applying the scoring algorithm

[1127] The server uses the TF-IDF method to vectorize the description of the new digital advertisement, compares it with past data to calculate the cosine similarity, and calculates a score for the new creative based on this result.

[1128] Emotion data collection and analysis

[1129] The device collects emotional data from the user's facial expressions and voice, and the emotion analysis engine analyzes this data in real time to evaluate the user's emotional state.

[1130] Emotional Data Integration

[1131] The server then integrates the user's emotional data obtained from the emotion analysis engine into the evaluation of the new creative. By using the user's emotional data in addition to the AI ​​scoring, a more accurate evaluation is possible.

[1132] Specific examples

[1133] Data Entry

[1134] The user enters the title "New Year Sale Campaign" and the description "Join our New Year Sale and get up to 50% off!" into the terminal.

[1135] Data storage

[1136] The server stores this data in a database and retrieves past creative data.

[1137] Scoring

[1138] The server uses artificial intelligence to calculate the score for the new creative. In this case, it uses the TF-IDF method and cosine similarity to compare it with past data and calculates a score of 88.2.

[1139] Collecting Emotional Data

[1140] The user's facial expression and voice data are collected by the emotion analysis engine through the device's camera and microphone. For example, if a positive expression or tone is detected, the data is evaluated as a favorable reaction.

[1141] Emotional Data Evaluation

[1142] The sentiment analysis engine sends the analyzed sentiment data in real time to the server, which then reflects this data in the score of the new creative. For example, if the sentiment score is 90, it will affect the final score.

[1143] Displaying the score

[1144] The device allows users to see the combined performance score of new creatives, showing, for example, that the "New Year Sale Campaign" had a final score of 89.6.

[1145] Example prompt sentence:

[1146] Enter the title and description of the digital ad creative below, and we'll use artificial intelligence to score it and collect user sentiment data to evaluate it.

[1147] Title: New Year Sale Campaign

[1148] Description: Join our New Year Sale and get up to 50% off!

[1149] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1150] Step 1:

[1151] The server connects to a database, such as SQLite, to store creative data and performance data for digital ads. First, a connection string is generated and used to connect to the database. Next, a table named "creatives_table" is created. The table has fields containing a title, description, and performance score. The input to this process is the database connection information held by the server, and the output is that the database and table are ready.

[1152] Step 2:

[1153] The server receives new electronic advertising content data from the terminal and inserts it into the database. For example, a user enters the title "New Year Sale Campaign" and the description "Join our New Year Sale and get up to 50% off!" The server saves this data in the database using the SQL INSERT statement. The input of this process is the advertising content data received from the user, and the output is the new data being inserted into the database.

[1154] Step 3:

[1155] The server retrieves all past digital advertising data from the database using an SQL SELECT statement. After the data is read, it is stored in memory. The input to this process is a specific query statement, and the output is the retrieved past digital advertising data.

[1156] Step 4:

[1157] The server vectorizes the description of the new digital ad using the TF-IDF method. First, the description is tokenized and the TF-IDF method is applied to calculate the importance of each word in the document. Next, the past creative data is similarly vectorized and the cosine similarity between that vector and the vector of the new data is calculated. A score is calculated based on this result. For example, a score of 88.2 is obtained for the new data. The inputs to this process are the new description and past data, and the output is the score for the new creative data.

[1158] Step 5:

[1159] The device collects the user's facial and voice data using the device's camera and microphone. The collected data is sent to an emotion analysis engine and analyzed in real time. The analysis results are evaluated in list form, including emotional states such as positive, negative, and neutral. The input of this process is the user's facial and voice data, and the output is analyzed emotional data.

[1160] Step 6:

[1161] The server receives the sentiment data from the sentiment analysis engine and integrates it into the final rating of the new creative. For example, if the sentiment score is 90, it will be reflected in the final score, which is expected to result in a final score of 89.6. The input of this process is the sentiment data from the sentiment analysis engine, and the output is the integrated final score.

[1162] Step 7:

[1163] The terminal displays the integrated final score to the user. For example, it shows that the final score for the "New Year Sale Campaign" is 89.6. This allows the user to check the evaluation results of the new creative. The input of this process is the final score, and the output is the result displayed in the user interface.

[1164] (Application example 2)

[1165] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1166] When creating and evaluating creative content for digital advertising, there is a need to measure performance quickly and accurately. However, conventional methods mainly rely on past data for evaluation, making it difficult to reflect real-time user sentiment. This makes it impossible to accurately reflect actual user reactions.

[1167] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for compiling a database of past creative content and performance data of measures; means for enabling related parties to centrally view and check the database; means for using AI to score new creative content based on the performance data of past creative content and measures and proposing optimal solutions; means for analyzing the user's facial expressions and voice using a terminal to collect emotional data; means for integrating the emotional data into the scoring of the new creative content; and means for providing the user with an evaluation result based on the scoring and emotional data via an interface. This makes it possible to evaluate creative content in a way that reflects the user's real-time emotions.

[1168] "Means of creating a database" refers to a method for systematically organizing data on past creative content and performance of measures, and storing the information.

[1169] "A single point of access and check" means a method that allows all parties involved to efficiently review and audit the information in the database through a single interface.

[1170] "A method of using AI to score and propose optimal solutions" is a method that utilizes artificial intelligence technology to evaluate new creative content and derive optimal advertising measures.

[1171] "Means for analyzing a user's facial expressions and voice using a terminal and collecting emotional data" refers to a method for measuring a user's emotional state and acquiring data using a device equipped with a camera and microphone.

[1172] The "means for integrating emotional data into the scoring of new creative content" is a method for incorporating collected emotional data into the evaluation process of new creative content to perform a composite evaluation.

[1173] "Means for providing users with evaluation results based on scoring and emotional data via an interface" refers to a method for providing users with evaluation results based on scoring and emotional data via a user interface for displaying the evaluation results.

[1174] The system of the present invention is for quickly and accurately producing and evaluating creative content for digital advertising. Specific embodiments of this system will be described below.

[1175] System configuration

[1176] The system of the present invention includes the following major components:

[1177] 1. Database creation method:

[1178] The server stores historical creative content and performance data in a database, including creative titles, descriptions, and performance scores.

[1179] 2. Centralized viewing and checking:

[1180] The server provides a web interface that allows interested parties to centrally view and check the historical database.

[1181] 3. AI-based scoring and suggestion of optimal solutions:

[1182] The server uses AI to score newly input creative content using TF-IDF and cosine similarity.

[1183] 4. Using a device to analyze a user's facial expressions and voice to collect emotional data:

[1184] The device uses a camera and microphone to analyze the user's facial expressions and voice in real time to collect emotional data, using the DeepFace library for emotion analysis.

[1185] 5. Means of integrating sentiment data into scoring new creative content:

[1186] The server then integrates the emotion data obtained from the emotion engine into the evaluation of the new creative, enabling a more accurate evaluation that reflects the user's emotions.

[1187] 6. Means for providing users with evaluation results based on scoring and emotion data via an interface:

[1188] The server provides an interface for displaying the evaluation results to the user, which displays the evaluation results based on the emotion data along with the performance scores.

[1189] Hardware and software used

[1190] Hardware: Smartphone, head-mounted display, built-in camera, built-in microphone

[1191] Software: Python, OpenCV, DeepFace library, SQLite, scikit-learn

[1192] Specific examples

[1193] A user views a digital advertisement using a smartphone or head-mounted display. They enter "New Year Sale Campaign" as the title and "Join our New Year Sale and get up to 50% off!" as the description. The server stores this data in a database and uses AI to score it. For example, it calculates a score of 88.2 based on the TF-IDF method and cosine similarity.

[1194] Next, the device's camera and microphone are used to collect emotion data from the user's facial expressions and voice. The emotion engine analyzes this data in real time and sends the emotion data to the server. For example, if the user's emotion score is 90, this score will be included in the final performance evaluation.

[1195] Finally, the server provides the consolidated performance score to the user through the interface, where the user can see that the "New Year Sale Campaign" had a final score of 89.6.

[1196] Prompt Sentence Examples

[1197] "Use a camera and microphone to collect real-time sentiment data while users are viewing a commercial. Explain how you would use the sentiment data to calculate a performance score for the ad. Give a thumbs up if the viewer expresses positive sentiment and a thumbs down if the viewer expresses negative sentiment."

[1198] In this way, it becomes possible to evaluate creative content that reflects users' real-time emotions, improving the efficiency of creating and evaluating digital advertisements.

[1199] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1200] Step 1:

[1201] The server stores past creative content and performance data of initiatives in a database. It receives input data such as the title, description, and performance score of creative content provided by users, systematically organizes it, and records it in an SQLite database. This database storage allows for the creation of historical data that can be accessed later by relevant parties.

[1202] Step 2:

[1203] The server provides a web interface that allows stakeholders to centrally view and check past creative data in the database. Users or administrators can access the past data through the interface and review and evaluate the necessary information (e.g., title, description, performance score). This interface is built using common web technologies such as HTML, CSS, and JavaScript.

[1204] Step 3:

[1205] The server scores new creative content using the TF-IDF method and cosine similarity. It receives the description of the new creative content entered by the user and calculates the TF-IDF vector. It compares the calculated vector with vectors in the past database to calculate the cosine similarity and determines the score for the new creative. The output is a numerical score result (e.g., 88.2).

[1206] Step 4:

[1207] The device uses a camera and microphone to analyze the user's facial expressions and voice in real time to collect emotional data. The device analyzes facial expressions and voice as input data collected while the user is viewing advertisements and classifies them into emotions (joy, anger, sadness, happiness, etc.). The DeepFace library is used to perform the emotion analysis, and the analysis results are output as emotional data.

[1208] Step 5:

[1209] The server integrates the collected emotional data into the scoring of new creative content. It receives the emotional data sent from the device and adds it to the scoring results. For example, if the emotional score is positive, it adjusts it to improve the final score. It outputs the integrated final score (e.g., 89.6).

[1210] Step 6:

[1211] The server provides the user with the evaluation results based on the scoring and emotional data via an interface. The final score and emotional evaluation results calculated on the server side are displayed in a user-viewable interface. The user can check the performance evaluation results of the creative content through the interface, which can be used to improve subsequent advertising measures. Detailed feedback based on the scoring results and emotional data is provided as an output.

[1212] 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.

[1213] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. 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 voice, text data indicating text, and image data indicating an image is also input. 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.

[1214] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1215] [Fourth embodiment]

[1216] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1217] 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.

[1218] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. 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).

[1219] 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.

[1220] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1221] 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 surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1222] 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.

[1223] The control object 443 includes a display device, LEDs in the eyes, and motors for driving 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.

[1224] 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.

[1225] 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 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.

[1226] 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.

[1227] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1228] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1229] The system of the present invention is for efficiently evaluating the adequacy of creative production and new measures for digital advertising. A specific embodiment of this system will be described below.

[1230] System configuration

[1231] Database

[1232] The server first creates a database of performance data for creative content and campaigns that have been executed in the past, including creative titles, descriptions, and performance scores.

[1233] Centralized management and viewing of data

[1234] The server provides a web interface that allows stakeholders to view and check the database in a centralized manner. Through this interface, users and stakeholders can access past data and obtain the information they need.

[1235] AI-based scoring

[1236] The server uses AI to score newly entered creative content. This AI scoring uses the TF-IDF method and cosine similarity. The TF-IDF method calculates the importance of words based on the frequency of their appearance in a document and their inverse document frequency, while the cosine similarity measures the similarity of creative content.

[1237] Program processing

[1238] Database Connection

[1239] The server first connects to a database management system, such as SQLite, and creates the necessary table structure that stores the creative title, description, and performance score.

[1240] Inserting and Retrieving Data

[1241] The server receives new creative content data and inserts it into the database, and also retrieves all past creative data from the database.

[1242] Applying the scoring algorithm

[1243] The server vectorizes the description of the new creative using the TF-IDF method, compares it with past data to calculate the cosine similarity, and calculates a score for the new creative based on this result.

[1244] Specific examples

[1245] 1. Data Entry:

[1246] The user enters the title "New Year Sale Campaign" and the description "Join our New Year Sale and get up to 50% off!" into the terminal.

[1247] 2. Data storage:

[1248] The server stores this in a database and retrieves past creative data.

[1249] 3. Scoring:

[1250] The server uses AI to calculate the score for the new creative. In this case, it uses the TF-IDF method and cosine similarity to compare it with past data and calculates a score of 88.2.

[1251] 4. Display score:

[1252] Users can view this score on their device to assess the suitability of new creatives. For example, the "New Year Sale Campaign" will be shown with a score of 88.2.

[1253] This system shortens feedback time and enables the rapid production of innovative creatives. It also significantly reduces the time required for consensus building, allowing for the smooth development of new creatives and the implementation of new initiatives in digital advertising.

[1254] The processing flow will be explained below.

[1255] Step 1:

[1256] Database Connection

[1257] The server connects to a database management system such as SQLite by using sqlite3.connect to access the database file and obtain a connection object.

[1258] Step 2:

[1259] Table Creation

[1260] The server creates a table in the database to store the creative data, using the CREATE TABLE SQL statement to set up the table with columns for storing the title, description, and performance score.

[1261] Step 3:

[1262] Data Entry

[1263] The user enters the title and description of the new creative content on the device, for example, "New Year Sale Campaign" and "Join our New Year Sale and get up to 50% off!"

[1264] Step 4:

[1265] Inserting Data

[1266] The server inserts the newly entered creative data into the database using an INSERT INTO SQL statement, inserting the title, description, and initial score (e.g., -1 for unrated).

[1267] Step 5:

[1268] Obtaining past data

[1269] The server retrieves all previously accumulated creative content data from the database, using the SQL statement SELECT FROM Creatives to get a list of titles, descriptions, and performance scores.

[1270] Step 6:

[1271] Text Vectorization

[1272] The server vectorizes the descriptions of the new and past creatives. It converts each description into a numeric vector using the TF-IDF (Term Frequency-Inverse Document Frequency) algorithm. It uses TfidfVectorizer.

[1273] Step 7:

[1274] Similarity calculation

[1275] The server uses cosine similarity to calculate the similarity between the new creative description and the previous description. It uses cosine_similarity to get the similarity score between each resulting vector.

[1276] Step 8:

[1277] Aggregation of Similarity Scores

[1278] The server aggregates the calculated cosine similarity scores and calculates an average score for the new creative, which becomes the performance prediction score for the new creative.

[1279] Step 9:

[1280] Score database update

[1281] The server updates the database with the new creative's performance score using a SQL statement like UPDATE Creatives SET performance_score = ? WHERE id = ?

[1282] Step 10:

[1283] Displaying the score

[1284] On the device, the user sees the performance score for the new creative, specifically the "New Year Sale Campaign" which has a score of 88.2.

[1285] This allows users to quickly assess the relevance of new creative and decide on their next course of action.

[1286] Example 1

[1287] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1288] When creating creative content for digital advertising, there is a need for a method to effectively utilize past performance data and quickly and accurately evaluate the suitability of new content. However, the centralized management of huge amounts of data and the evaluation process using AI are complex, requiring a lot of time and resources.

[1289] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1290] In this invention, the server includes: means for compiling a database of performance data of past digital advertisements and campaigns; means for enabling related parties to centrally view and check the database; means for using artificial intelligence to score new creative content based on the performance data of past digital advertisements and campaigns and propose optimal solutions; means for using artificial intelligence to vectorize and calculate similarity of the new creative content using the TF-IDF method and cosine similarity and calculate its score; and means for storing the score of the new creative content in the database and allowing users to view it on their terminals. This enables the evaluation process of creative content for digital advertisements to be carried out quickly and efficiently.

[1291] "Digital advertising" refers to advertising content delivered via the Internet or digital media.

[1292] "Creative Content" means content created for an advertising campaign, consisting of titles, descriptions, images, videos, and other multimedia elements.

[1293] "Performance data" refers to records of the results and performance of campaigns and measures implemented in the past.

[1294] A "database" is an information system for efficiently storing and managing large amounts of data in a structured format.

[1295] "Artificial intelligence" refers to computer systems that mimic human intelligence and can learn and solve problems automatically.

[1296] "Scoring" is the process of quantifying something for the purposes of evaluation or comparison.

[1297] The "TF-IDF method" is a technique that calculates the importance of each word by combining the term frequency (TF) and inverse document frequency (IDF) of the word in a document.

[1298] "Cosine similarity" is a method for calculating the similarity between two vectors using the dot product and the magnitude of the vectors.

[1299] "Vectorization" is the process of converting text data into vectors of numbers.

[1300] A "terminal" is an electronic device such as a computer or smartphone that a user uses to input and output information.

[1301] The system of the present invention aims to efficiently evaluate the adequacy of creative production and new measures for digital advertising. Specific embodiments of this system are as follows.

[1302] System Overview

[1303] This system is operated by a server, terminals, and users. It also uses artificial intelligence (AI) to score creative content, centrally manages the data, and provides it to users.

[1304] Database construction and operation

[1305] The server first creates a database of performance data for past digital advertisements and campaigns. This database stores the titles, descriptions, and performance scores of creative content. The database management system used is SQLite.

[1306] Centralize and access your data

[1307] The server provides a web interface that allows all parties involved to access, view, and check the database in a centralized manner. Through this interface, users and stakeholders can easily access past data and obtain the information they need. This interface can be accessed through a standard web browser.

[1308] Scoring new creative content

[1309] The server uses artificial intelligence (AI) to score newly entered creative content. This AI scoring uses the TF-IDF method and cosine similarity. The TF-IDF method calculates the importance of each word, and cosine similarity is used to measure the similarity with past creative content.

[1310] Specific examples

[1311] 1. Data Entry:

[1312] The user enters the title "New Year Sale Campaign" and the description "Join our New Year Sale and get up to 50% off!" into the terminal.

[1313] 2. Data storage:

[1314] The server stores this in a database and retrieves past creative data.

[1315] 3. Scoring:

[1316] The server uses AI to calculate the score for the new creative. In this case, it uses the TF-IDF method and cosine similarity to compare it with past data and calculates a score of 88.2.

[1317] 4. Display score:

[1318] Users can view this score on their device to assess the suitability of new creatives. For example, the "New Year Sale Campaign" will be shown with a score of 88.2.

[1319] Prompt Sentence Examples

[1320] You can generate a prompt like this:

[1321] Based on the creative description for the digital ad "New Year Sale Campaign" - "Join our New Year Sale and get up to 50% off!" - calculate the similarity to historical data and assign it a new score.

[1322] This system shortens feedback time and enables the rapid production of innovative creatives. It also significantly reduces the time required for consensus building, allowing for the smooth development of new creatives and the implementation of new initiatives in digital advertising.

[1323] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1324] Step 1: Database Connection and Initial Configuration

[1325] When the server starts up, it first connects to the SQLite database management system and then creates a table structure to store the title, description, and performance score of the creative content.

[1326] Input: System startup, database connection request

[1327] Output: Database connection, table initialization

[1328] What happens: The server opens the SQLite database and creates the required table structure (including title, description, and score fields) if it doesn't exist.

[1329] Step 2: User enters new data

[1330] The user uses the device to input new creative content (e.g., title and description).

[1331] Input: User input form

[1332] Output: Input creative content data

[1333] Specific operation: The user enters the title "New Year Sale Campaign" and the description "Join our New Year Sale and get up to 50% off!" through the web interface.

[1334] Step 3: Save the data to a database

[1335] The server stores the new creative content data received from the user in a database.

[1336] Input: New creative data by user

[1337] Output: New creative data stored in the database

[1338] Specific operation: The server inserts the received new creative data (title and description) into the corresponding table in the SQLite database.

[1339] Step 4: Obtaining historical data

[1340] The server retrieves all past creative data from the database.

[1341] Input: A request to retrieve data from the database

[1342] Output: Obtained historical creative data

[1343] What happens: The server uses an SQL query to read the titles, descriptions, and scores of past creative content from a database.

[1344] Step 5: Score new data

[1345] The server vectorizes the description of the new creative using the TF-IDF method, calculates the cosine similarity, and compares it with past data. The result is used to calculate the score of the new creative.

[1346] Input: New creative description and description of past creative data

[1347] Output: New creative score

[1348] Specific operation: The server uses the TF-IDF vectorization tool to convert the new description into a numerical vector, and then calculates the cosine similarity with the previously obtained description data to calculate a score.

[1349] Step 6: Save the score to the database

[1350] The server stores the score of the new creative in a database.

[1351] Inputs: Calculated score, new creative title and description

[1352] Output: Scores stored in the database

[1353] What happens: The server updates the score of the new creative into an existing database record or inserts it into a new record.

[1354] Step 7: User checks score

[1355] The user uses the device to check the score of the new creative.

[1356] Input: Score display request

[1357] Output: Score of the new creative displayed on the device screen

[1358] What happens: Through the web interface, the user sees that the new creative, "New Year Sale Campaign," has a score of 88.2.

[1359] (Application example 1)

[1360] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1361] Creating and evaluating creative content for digital advertising requires a lot of time and effort. Furthermore, there is a lack of ways to quickly predict and optimize the effectiveness of newly created creative content, making it difficult for advertising planners and marketers to work efficiently. To solve this problem, there is a need for a system that utilizes past data to predict and display the performance of new creative content in real time.

[1362] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1363] In this invention, the server includes: means for creating a database of past creative content and performance data of measures; means for enabling related parties to centrally view and check the database; means for using AI to score new creative content based on the past creative content and performance data of measures and proposing optimal solutions; means for inputting the title and description of a new advertisement from a user terminal; and means for displaying the score in real time after the new advertisement is input. This makes it possible to quickly predict the effectiveness of advertising creatives and efficiently produce optimal creatives.

[1364] "Past creative content and campaign performance data" refers to data that records the results of previously created advertising creatives and related marketing campaigns.

[1365] A "database" is a digital information storage location for efficiently storing and managing past creative content and performance data of initiatives.

[1366] "AI" is an abbreviation for artificial intelligence, a technology that uses machine learning algorithms and natural language processing techniques to analyze and evaluate new creative content.

[1367] "Scoring" is the process of using AI to quantify and evaluate the performance of new creative content.

[1368] "Proposing optimal solutions" refers to AI evaluating the performance of new creative content and generating and proposing effective advertising creatives based on the evaluation results.

[1369] A "user terminal" is a device (e.g., a smartphone or tablet) used by advertising planners or marketers to input new advertising information.

[1370] "Real-time" refers to the process of displaying the evaluation results immediately after a new ad is entered.

[1371] A "title" is a concise expression of the main message or name of the creative content.

[1372] The "description" is the section that describes the detailed information and specific content of the creative content.

[1373] The system for implementing this invention compiles a database of past creative content and performance data of measures, predicts the performance of new creative content based on this data, and proposes optimal advertising creatives.

[1374] System configuration

[1375] Database

[1376] The server maintains a database that stores performance data for creative content created in the past and related measures. This database includes creative titles, descriptions, and performance scores. The database is managed using SQLite.

[1377] Centralized management and viewing of data

[1378] The server provides a web interface that allows stakeholders to view and check the database in a centralized manner. The web interface is built using the Flask framework, allowing stakeholders to easily access past data.

[1379] AI-based scoring

[1380] The server uses a generative AI model to score newly input creative content. This process uses the TF-IDF method and cosine similarity. The server uses the Sklearn library to vectorize the text data of the new creative and calculate the similarity with past data.

[1381] Program processing

[1382] Database connection and configuration

[1383] The server first connects to the SQLite database and creates a table structure to store the creative content data.

[1384] Inserting and Retrieving Data

[1385] The server receives the title and description of the new creative from the user terminal and stores them in the database, and also retrieves past creative data from the database.

[1386] Applying the scoring algorithm

[1387] The server uses the TF-IDF method to vectorize the description of new creative content and calculates the cosine similarity with past creative data. This score is evaluated on a scale of 100 and displayed to the user in real time.

[1388] Specific examples

[1389] For example, a user may enter a title such as "Spring Sale Campaign" and a description such as "Up to 50% off in the Spring Sale!" This input data is sent to the server and stored in a database. The server calculates the similarity between the previous data and the new creative and gives it a score of 85.5. This score is displayed in real time on the web interface on the user's device.

[1390] Prompt Sentence Examples

[1391] Ad Title: Spring Sale Campaign, Description: Up to 50% off in the Spring Sale!

[1392] This system enables advertising planners and marketers to quickly predict the effectiveness of new creatives and efficiently produce effective advertising creatives.

[1393] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1394] Step 1:

[1395] The server connects to the SQLite database and creates the necessary table structure, including tables to store the title, description, and performance score of past creative content. The input is the database structure definition, and the output is the creation of these tables.

[1396] Step 2:

[1397] The user inputs the title and description of the new creative content from the terminal. This input data is sent to the server. As input, details (title and description) of the new creative content are required, and as output, this data is received by the server.

[1398] Step 3:

[1399] The server stores the received new creative data in the database. The new creative details are inserted into the database. As input, it requires the data received from the user and as output, it registers this data in the database.

[1400] Step 4:

[1401] The server retrieves all past creative data from the database. As input, a query to the database is required, and as output, a list of past creative data is obtained.

[1402] Step 5:

[1403] The server uses the Sklearn library to apply the TF-IDF method to vectorize the description of the new creative. As input, it takes the descriptions of the new and previous creatives, and as output, it gets the vectorized descriptions.

[1404] Step 6:

[1405] The server calculates the cosine similarity to measure the similarity between the new creative and the previous creative. Based on this score, it calculates the performance score for the new creative. The input is the vectorized description, and the output is the similarity score and the performance score.

[1406] Step 7:

[1407] The server displays the calculated performance score on the user's device in real time. The user can check the score of the new creative on the device. The performance score is required as input, and the score is displayed on the user's device as output.

[1408] Prompt Sentence Examples

[1409] An example prompt sentence is "Ad title: Spring Sale Campaign, Description: Up to 50% off in the Spring Sale!"

[1410] This series of steps enables advertising planners and marketers to quickly predict the effectiveness of new creatives and efficiently produce optimal advertising creatives.

[1411] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1412] The system of the present invention is designed to efficiently evaluate the creative production of digital advertising and the validity of new initiatives, and by combining it with an emotion engine that recognizes user emotions, it improves the evaluation of creative content. Specific embodiments of this system are described below.

[1413] System configuration

[1414] Database

[1415] The server stores a database of performance data for creative content and campaigns that have been executed in the past, including creative titles, descriptions, and performance scores.

[1416] Centralized management and viewing of data

[1417] The server provides a web interface that allows stakeholders to view and check the database in a centralized manner. Through this interface, users and stakeholders can access past data and obtain the information they need.

[1418] AI-based scoring

[1419] The server uses AI to score newly entered creative content. AI scoring uses the TF-IDF method and cosine similarity. The TF-IDF method calculates the importance of words based on the frequency of their occurrence in a document and their inverse document frequency, while cosine similarity measures the similarity of creative content.

[1420] Emotion engine configuration

[1421] The emotion engine analyzes the user's facial expressions and voice in real time to collect emotional data, which allows it to evaluate how the user feels about the creative content.

[1422] Program processing

[1423] Database Connection

[1424] The server first connects to a database management system, such as SQLite, and creates the necessary table structure that stores the creative title, description, and performance score.

[1425] Inserting and Retrieving Data

[1426] The server receives new creative content data and inserts it into the database, and also retrieves all past creative data from the database.

[1427] Applying the scoring algorithm

[1428] The server vectorizes the description of the new creative using the TF-IDF method, compares it with past data to calculate the cosine similarity, and calculates a score for the new creative based on this result.

[1429] Emotion data collection and analysis

[1430] The device collects emotional data from the user's facial expressions and voice, and the emotion engine analyzes this data in real time to evaluate the user's emotional state.

[1431] Emotional Data Integration

[1432] The server then integrates the user's emotional data obtained from the emotion engine into the evaluation of new creatives. By using the user's emotional data in addition to AI scoring, more accurate evaluations are possible.

[1433] Specific examples

[1434] 1. Data Entry:

[1435] The user enters the title "New Year Sale Campaign" and the description "Join our New Year Sale and get up to 50% off!" into the terminal.

[1436] 2. Data storage:

[1437] The server stores this data in a database and retrieves past creative data.

[1438] 3. Scoring:

[1439] The server uses AI to calculate the score for the new creative. In this case, it uses the TF-IDF method and cosine similarity to compare it with past data and calculates a score of 88.2.

[1440] 4. Collecting Emotional Data:

[1441] The emotion engine collects facial and voice data from the user's device via the device's camera and microphone. For example, if a positive facial expression or tone is detected, the data is evaluated as a favorable response.

[1442] 5. Evaluating Emotional Data:

[1443] The emotion engine sends real-time analyzed emotion data to the server, which then reflects this data in the score of the new creative. For example, if the emotion score is 90, that will affect the final score.

[1444] 6. Display score:

[1445] The device allows users to see the combined performance score of new creatives, showing, for example, that the "New Year Sale Campaign" had a final score of 89.6.

[1446] This system shortens feedback time and enables the rapid production of innovative creatives. It also significantly reduces the time required for consensus building, allowing for the smooth development of new creatives and the implementation of new initiatives in digital advertising. Furthermore, by integrating user emotional data, creative evaluations become more accurate and reliable.

[1447] The processing flow will be explained below.

[1448] Step 1:

[1449] Database Connection

[1450] The server connects to a database management system such as SQLite by using sqlite3.connect to access the database file and obtain a connection object.

[1451] Step 2:

[1452] Table Creation

[1453] The server creates a table in the database to store the creative data, using the CREATE TABLE SQL statement to set up the table with columns for storing the title, description, and performance score.

[1454] Step 3:

[1455] Data Entry

[1456] The user enters the title and description of the new creative content on the device, for example, "New Year Sale Campaign" and "Join our New Year Sale and get up to 50% off!"

[1457] Step 4:

[1458] Inserting Data

[1459] The server inserts the newly entered creative data into the database using an INSERT INTO SQL statement, inserting the title, description, and initial score (e.g., -1 for unrated).

[1460] Step 5:

[1461] Obtaining past data

[1462] The server retrieves all previously accumulated creative content data from the database, using the SQL statement SELECT FROM Creatives to get a list of titles, descriptions, and performance scores.

[1463] Step 6:

[1464] Text Vectorization

[1465] The server vectorizes the descriptions of the new and past creatives. It converts each description into a numeric vector using the TF-IDF (Term Frequency-Inverse Document Frequency) algorithm. It uses TfidfVectorizer.

[1466] Step 7:

[1467] Similarity calculation

[1468] The server uses cosine similarity to calculate the similarity between the new creative description and the previous description. It uses cosine_similarity to get the similarity score between each resulting vector.

[1469] Step 8:

[1470] Aggregation of Similarity Scores

[1471] The server aggregates the calculated cosine similarity scores and calculates an average score for the new creative, which becomes the performance prediction score for the new creative.

[1472] Step 9:

[1473] Collecting Emotional Data

[1474] The device collects facial and voice data in real time from the user's camera and microphone, and the emotion engine analyzes the user's facial muscle movements and tone of voice to determine their emotional state.

[1475] Step 10:

[1476] Emotional Data Analysis

[1477] The emotion engine analyzes the collected facial and voice data to determine whether the user is in a positive, negative, or neutral emotional state, and quantifies this emotional data as an emotion score.

[1478] Step 11:

[1479] Sending emotional data

[1480] The terminal transmits the emotion score obtained as a result of the analysis to the server.

[1481] Step 12:

[1482] Emotional Data Integration

[1483] The server integrates the AI ​​text scoring with the sentiment score received from the sentiment engine, which adjusts the final performance score.

[1484] Step 13:

[1485] Score database update

[1486] The server updates the database with the final combined score using a SQL statement such as UPDATE Creatives SET performance_score = ? WHERE id = ?

[1487] Step 14:

[1488] Displaying the score

[1489] On the device, the user sees the combined performance score of the new creative, for example showing that the "New Year Sale Campaign" has a final score of 89.6.

[1490] This allows users to quickly assess the relevance of new creative and decide on their next course of action.

[1491] Example 2

[1492] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1493] In the creative production and evaluation of digital advertising campaigns, there is a need for efficient utilization of past performance data for rapid and accurate evaluation. However, there is a lack of evaluation that takes user emotions into account, making it difficult to accurately evaluate creatives that reflect user reactions.

[1494] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1495] In this invention, the server includes: means for compiling a database of past electronic advertising content and performance data of measures; means for enabling related parties to centrally view and check the database; means for using artificial intelligence to score new electronic advertising content based on the performance data of past electronic advertising content and measures and proposing optimal solutions; and means for analyzing user facial expressions and voice data in real time and integrating data obtained from an emotion analysis engine that evaluates user emotions. This makes it possible to efficiently utilize past data while accurately evaluating creative content in consideration of user emotions.

[1496] "Electronic advertising content" refers to all advertising creatives distributed on digital platforms.

[1497] "Performance data" refers to data showing the results of past measures and creatives, and includes performance scores, titles, descriptions, etc.

[1498] A "database" refers to a system that systematically organizes information and stores and manages it electronically.

[1499] "Artificial intelligence" refers to the technology that allows machines and computers to simulate human intelligence and learn, reason, and make decisions.

[1500] An "emotion analysis engine" refers to technology that analyzes a user's facial expressions and voice and evaluates their emotional state in real time.

[1501] The "TF-IDF method" refers to a method for calculating the importance of words in a document using word frequency and inverse document frequency.

[1502] "Cosine similarity" refers to a method for measuring the similarity between two vectors in vector space based on the angle between them.

[1503] "Scoring" refers to the process of calculating a score for creative content based on specific evaluation criteria.

[1504] "User" refers to a user who views and evaluates electronic advertising content.

[1505] "Means for centralized viewing and checking" refers to an interface that allows multiple parties to access one central data storage and to view and check information.

[1506] MODE FOR CARRYING OUT THE INVENTION

[1507] The system of the present invention is designed to efficiently evaluate the creative production of electronic advertisements and the validity of new measures. In addition, by combining it with a sentiment analysis engine that recognizes user emotions, it improves the evaluation of creative content.

[1508] System configuration

[1509] Database

[1510] The server creates a database of past digital advertising content and performance data for campaigns. This database stores creative titles, descriptions, and performance scores. SQLite is used as the database.

[1511] Centralized management and viewing of data

[1512] The server provides a web interface that allows stakeholders to view and check the database in a centralized manner. Through this interface, users and stakeholders can access past data and obtain the information they need.

[1513] AI-based scoring

[1514] The server uses artificial intelligence to score newly entered digital advertising content. This scoring is performed using the TF-IDF method and cosine similarity. The TF-IDF method calculates the importance of words based on the frequency of their appearance in a document and their inverse document frequency, while the cosine similarity measures the similarity of creative content.

[1515] Sentiment analysis engine configuration

[1516] The device is equipped with an emotion analysis engine that analyzes the user's facial expressions and voice in real time, allowing it to evaluate how the user feels about the digital advertising content.

[1517] Program processing

[1518] Database Connection

[1519] The server first connects to a database management system, such as SQLite, and creates the necessary table structure that stores the creative title, description, and performance score.

[1520] Inserting and Retrieving Data

[1521] The server receives new electronic advertising content data and inserts it into the database, and also retrieves all past electronic advertising data from the database.

[1522] Applying the scoring algorithm

[1523] The server uses the TF-IDF method to vectorize the description of the new digital advertisement, compares it with past data to calculate the cosine similarity, and calculates a score for the new creative based on this result.

[1524] Emotion data collection and analysis

[1525] The device collects emotional data from the user's facial expressions and voice, and the emotion analysis engine analyzes this data in real time to evaluate the user's emotional state.

[1526] Emotional Data Integration

[1527] The server then integrates the user's emotional data obtained from the emotion analysis engine into the evaluation of the new creative. By using the user's emotional data in addition to the AI ​​scoring, a more accurate evaluation is possible.

[1528] Specific examples

[1529] Data Entry

[1530] The user enters the title "New Year Sale Campaign" and the description "Join our New Year Sale and get up to 50% off!" into the terminal.

[1531] Data storage

[1532] The server stores this data in a database and retrieves past creative data.

[1533] Scoring

[1534] The server uses artificial intelligence to calculate the score for the new creative. In this case, it uses the TF-IDF method and cosine similarity to compare it with past data and calculates a score of 88.2.

[1535] Collecting Emotional Data

[1536] The user's facial expression and voice data are collected by the emotion analysis engine through the device's camera and microphone. For example, if a positive expression or tone is detected, the data is evaluated as a favorable reaction.

[1537] Emotional Data Evaluation

[1538] The sentiment analysis engine sends the analyzed sentiment data in real time to the server, which then reflects this data in the score of the new creative. For example, if the sentiment score is 90, it will affect the final score.

[1539] Displaying the score

[1540] The device allows users to see the combined performance score of new creatives, showing, for example, that the "New Year Sale Campaign" had a final score of 89.6.

[1541] Example prompt sentence:

[1542] Enter the title and description of the digital ad creative below, and we'll use artificial intelligence to score it and collect user sentiment data to evaluate it.

[1543] Title: New Year Sale Campaign

[1544] Description: Join our New Year Sale and get up to 50% off!

[1545] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1546] Step 1:

[1547] The server connects to a database, such as SQLite, to store creative data and performance data for digital ads. First, a connection string is generated and used to connect to the database. Next, a table named "creatives_table" is created. The table has fields containing a title, description, and performance score. The input to this process is the database connection information held by the server, and the output is that the database and table are ready.

[1548] Step 2:

[1549] The server receives new electronic advertising content data from the terminal and inserts it into the database. For example, a user enters the title "New Year Sale Campaign" and the description "Join our New Year Sale and get up to 50% off!" The server saves this data in the database using the SQL INSERT statement. The input of this process is the advertising content data received from the user, and the output is the new data being inserted into the database.

[1550] Step 3:

[1551] The server retrieves all past digital advertising data from the database using an SQL SELECT statement. After the data is read, it is stored in memory. The input to this process is a specific query statement, and the output is the retrieved past digital advertising data.

[1552] Step 4:

[1553] The server vectorizes the description of the new digital ad using the TF-IDF method. First, the description is tokenized and the TF-IDF method is applied to calculate the importance of each word in the document. Next, the past creative data is similarly vectorized and the cosine similarity between that vector and the vector of the new data is calculated. A score is calculated based on this result. For example, a score of 88.2 is obtained for the new data. The inputs to this process are the new description and past data, and the output is the score for the new creative data.

[1554] Step 5:

[1555] The device collects the user's facial and voice data using the device's camera and microphone. The collected data is sent to an emotion analysis engine and analyzed in real time. The analysis results are evaluated in list form, including emotional states such as positive, negative, and neutral. The input of this process is the user's facial and voice data, and the output is analyzed emotional data.

[1556] Step 6:

[1557] The server receives the sentiment data from the sentiment analysis engine and integrates it into the final rating of the new creative. For example, if the sentiment score is 90, it will be reflected in the final score, which is expected to result in a final score of 89.6. The input of this process is the sentiment data from the sentiment analysis engine, and the output is the integrated final score.

[1558] Step 7:

[1559] The terminal displays the integrated final score to the user. For example, it shows that the final score for the "New Year Sale Campaign" is 89.6. This allows the user to check the evaluation results of the new creative. The input of this process is the final score, and the output is the result displayed in the user interface.

[1560] (Application example 2)

[1561] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1562] When creating and evaluating creative content for digital advertising, there is a need to measure performance quickly and accurately. However, conventional methods mainly rely on past data for evaluation, making it difficult to reflect real-time user sentiment. This makes it impossible to accurately reflect actual user reactions.

[1563] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for compiling a database of past creative content and performance data of measures; means for enabling related parties to centrally view and check the database; means for using AI to score new creative content based on the performance data of past creative content and measures and proposing optimal solutions; means for analyzing the user's facial expressions and voice using a terminal to collect emotional data; means for integrating the emotional data into the scoring of the new creative content; and means for providing the user with an evaluation result based on the scoring and emotional data via an interface. This makes it possible to evaluate creative content in a way that reflects the user's real-time emotions.

[1564] "Means of creating a database" refers to a method for systematically organizing data on past creative content and performance of measures, and storing the information.

[1565] "A single point of access and check" means a method that allows all parties involved to efficiently review and audit the information in the database through a single interface.

[1566] "A method of using AI to score and propose optimal solutions" is a method that utilizes artificial intelligence technology to evaluate new creative content and derive optimal advertising measures.

[1567] "Means for analyzing a user's facial expressions and voice using a terminal and collecting emotional data" refers to a method for measuring a user's emotional state and acquiring data using a device equipped with a camera and microphone.

[1568] The "means for integrating emotional data into the scoring of new creative content" is a method for incorporating collected emotional data into the evaluation process of new creative content to perform a composite evaluation.

[1569] "Means for providing users with evaluation results based on scoring and emotional data via an interface" refers to a method for providing users with evaluation results based on scoring and emotional data via a user interface for displaying the evaluation results.

[1570] The system of the present invention is for quickly and accurately producing and evaluating creative content for digital advertising. Specific embodiments of this system will be described below.

[1571] System configuration

[1572] The system of the present invention includes the following major components:

[1573] 1. Database creation method:

[1574] The server stores historical creative content and performance data in a database, including creative titles, descriptions, and performance scores.

[1575] 2. Centralized viewing and checking:

[1576] The server provides a web interface that allows interested parties to centrally view and check the historical database.

[1577] 3. AI-based scoring and suggestion of optimal solutions:

[1578] The server uses AI to score newly input creative content using TF-IDF and cosine similarity.

[1579] 4. Using a device to analyze a user's facial expressions and voice to collect emotional data:

[1580] The device uses a camera and microphone to analyze the user's facial expressions and voice in real time to collect emotional data, using the DeepFace library for emotion analysis.

[1581] 5. Means of integrating sentiment data into scoring new creative content:

[1582] The server then integrates the emotion data obtained from the emotion engine into the evaluation of the new creative, enabling a more accurate evaluation that reflects the user's emotions.

[1583] 6. Means for providing users with evaluation results based on scoring and emotion data via an interface:

[1584] The server provides an interface for displaying the evaluation results to the user, which displays the evaluation results based on the emotion data along with the performance scores.

[1585] Hardware and software used

[1586] Hardware: Smartphone, head-mounted display, built-in camera, built-in microphone

[1587] Software: Python, OpenCV, DeepFace library, SQLite, scikit-learn

[1588] Specific examples

[1589] A user views a digital advertisement using a smartphone or head-mounted display. They enter "New Year Sale Campaign" as the title and "Join our New Year Sale and get up to 50% off!" as the description. The server stores this data in a database and uses AI to score it. For example, it calculates a score of 88.2 based on the TF-IDF method and cosine similarity.

[1590] Next, the device's camera and microphone are used to collect emotion data from the user's facial expressions and voice. The emotion engine analyzes this data in real time and sends the emotion data to the server. For example, if the user's emotion score is 90, this score will be included in the final performance evaluation.

[1591] Finally, the server provides the consolidated performance score to the user through the interface, where the user can see that the "New Year Sale Campaign" had a final score of 89.6.

[1592] Prompt Sentence Examples

[1593] "Use a camera and microphone to collect real-time sentiment data while users are viewing a commercial. Explain how you would use the sentiment data to calculate a performance score for the ad. Give a thumbs up if the viewer expresses positive sentiment and a thumbs down if the viewer expresses negative sentiment."

[1594] In this way, it becomes possible to evaluate creative content that reflects users' real-time emotions, improving the efficiency of creating and evaluating digital advertisements.

[1595] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1596] Step 1:

[1597] The server stores past creative content and performance data of initiatives in a database. It receives input data such as the title, description, and performance score of creative content provided by users, systematically organizes it, and records it in an SQLite database. This database storage allows for the creation of historical data that can be accessed later by relevant parties.

[1598] Step 2:

[1599] The server provides a web interface that allows stakeholders to centrally view and check past creative data in the database. Users or administrators can access the past data through the interface and review and evaluate the necessary information (e.g., title, description, performance score). This interface is built using common web technologies such as HTML, CSS, and JavaScript.

[1600] Step 3:

[1601] The server scores new creative content using the TF-IDF method and cosine similarity. It receives the description of the new creative content entered by the user and calculates the TF-IDF vector. It compares the calculated vector with vectors in the past database to calculate the cosine similarity and determines the score for the new creative. The output is a numerical score result (e.g., 88.2).

[1602] Step 4:

[1603] The device uses a camera and microphone to analyze the user's facial expressions and voice in real time to collect emotional data. The device analyzes facial expressions and voice as input data collected while the user is viewing advertisements and classifies them into emotions (joy, anger, sadness, happiness, etc.). The DeepFace library is used to perform the emotion analysis, and the analysis results are output as emotional data.

[1604] Step 5:

[1605] The server integrates the collected emotional data into the scoring of new creative content. It receives the emotional data sent from the device and adds it to the scoring results. For example, if the emotional score is positive, it adjusts it to improve the final score. It outputs the integrated final score (e.g., 89.6).

[1606] Step 6:

[1607] The server provides the user with the evaluation results based on the scoring and emotional data via an interface. The final score and emotional evaluation results calculated on the server side are displayed in a user-viewable interface. The user can check the performance evaluation results of the creative content through the interface, which can be used to improve subsequent advertising measures. Detailed feedback based on the scoring results and emotional data is provided as an output.

[1608] 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.

[1609] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. 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 voice, text data indicating text, and image data indicating an image is also input. 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.

[1610] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1611] 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.

[1612] FIG. 9 is a diagram illustrating 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 actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect 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.

[1613] 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.

[1614] 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).

[1615] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1616] 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."

[1617] 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.

[1618] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1619] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1620] 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.

[1621] 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.

[1622] 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.

[1623] The hardware resource for executing a specific process can be any of the following processors: An example of a processor 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. Another example of a processor is 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.

[1624] The hardware resource that executes the specific processing 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 processing may be a single processor.

[1625] 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.

[1626] 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.

[1627] 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.

[1628] 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.

[1629] The following is further disclosed regarding the above embodiment.

[1630] (Claim 1)

[1631] A means of creating a database of past creative content and performance data of measures,

[1632] A means for enabling relevant parties to centrally view and check the database;

[1633] Based on past creative content and performance data of measures, we use AI to score new creative content and propose optimal solutions.

[1634] A system including:

[1635] (Claim 2)

[1636] The system of claim 1, wherein the AI ​​scores new creative content using TF-IDF and cosine similarity.

[1637] (Claim 3)

[1638] 10. The system of claim 1, wherein the past creative content and campaign performance data includes a description, a title, and a performance score.

[1639] "Example 1"

[1640] (Claim 1)

[1641] A means of creating a database of past digital advertising and campaign performance data, and

[1642] A means for enabling relevant parties to centrally view and check the database;

[1643] Based on past performance data of digital advertising and initiatives, we will use artificial intelligence to score new creative content and propose optimal solutions.

[1644] A means for vectorizing and calculating the similarity of new creative content using the TF-IDF method and cosine similarity using artificial intelligence, and calculating the score thereof;

[1645] means for storing the scores of said new creative content in a database and allowing the user to view them on a terminal;

[1646] A system including:

[1647] (Claim 2)

[1648] 2. The system of claim 1, wherein the artificial intelligence scores new creative content using TF-IDF and cosine similarity.

[1649] (Claim 3)

[1650] 10. The system of claim 1, wherein the historical digital advertising and campaign performance data includes a description, a title, and a performance score.

[1651] "Application Example 1"

[1652] (Claim 1)

[1653] A means of creating a database of past creative content and performance data of measures,

[1654] A means for enabling relevant parties to centrally view and check the database;

[1655] Based on past creative content and performance data of measures, we use AI to score new creative content and propose optimal solutions.

[1656] means for inputting a title and description of a new advertisement from a user terminal;

[1657] A means to display the score in real time after a new ad is entered;

[1658] A system including:

[1659] (Claim 2)

[1660] The system of claim 1, wherein the AI ​​scores new creative content using TF-IDF and cosine similarity.

[1661] (Claim 3)

[1662] 10. The system of claim 1, wherein the past creative content and campaign performance data includes a description, a title, and a performance score.

[1663] "Example 2: Combining Emotion Engines"

[1664] (Claim 1)

[1665] A means for creating a database of past electronic advertising content and performance data of measures;

[1666] A means for enabling relevant parties to centrally view and check the database;

[1667] A method for using artificial intelligence to score new electronic advertising content based on past data on electronic advertising content and measures, and proposing optimal solutions;

[1668] a means for integrating data obtained from an emotion analysis engine that analyzes the user's facial expressions and voice data in real time and evaluates the user's emotions;

[1669] A system including:

[1670] (Claim 2)

[1671] 2. The system of claim 1, wherein the artificial intelligence scores new electronic advertising content using the TF-IDF method and cosine similarity.

[1672] (Claim 3)

[1673] 2. The system according to claim 1, wherein the performance data of the past electronic advertising content and campaigns includes a description, a title, and a performance score.

[1674] "Application example 2 when combining emotion engines"

[1675] (Claim 1)

[1676] A means of creating a database of past creative content and performance data of measures,

[1677] A means for enabling relevant parties to centrally view and check the database;

[1678] Based on past creative content and performance data of measures, we use AI to score new creative content and propose optimal solutions.

[1679] A means for analyzing a user's facial expression and voice using a terminal to collect emotion data;

[1680] means for integrating said emotional data into the scoring of said new creative content;

[1681] means for providing a user with an evaluation result based on the scoring and emotion data via an interface;

[1682] A system including:

[1683] (Claim 2)

[1684] The system described in claim 1, characterized in that the AI ​​scores new creative content using the TF-IDF method and cosine similarity, and analyzes emotional data from the user's facial expressions and voice and reflects this in the evaluation.

[1685] (Claim 3)

[1686] 10. The system of claim 1, wherein the past creative content and campaign performance data includes a description, a title, and a performance score. [Explanation of symbols]

[1687] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of creating a database of past creative content and performance data of measures, A means for enabling relevant parties to centrally view and check the database; Based on past creative content and performance data of measures, we use AI to score new creative content and propose optimal solutions. A system including:

2. The system of claim 1, wherein the AI ​​scores new creative content using TF-IDF and cosine similarity.

3. 2. The system of claim 1, wherein the past creative content and initiative performance data includes a description, a title, and a performance score.

Images