System

Abstract

To provide a system.SOLUTION: A system includes: first means for collecting data on an advertising campaign; second means for generating a first prompt sentence for outputting an evaluation report for evaluating an effect of the advertising campaign on the basis of the data on the advertising campaign; third means for generating the evaluation report by inputting the generated first prompt sentence into a generative AI model; and fourth means for transmitting the generated evaluation report to a terminal of a user.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] It is generally difficult to independently evaluate the goodwill (value of brand and technology) of a target company during due diligence when considering investment, etc. To obtain a highly accurate estimate, it is necessary to entrust the work to a third-party specialist agency, which is expensive and time-consuming, but this does not match the speed required. [Means for solving the problem]

[0005] We provide a system that aggregates information on the market exposure and penetration of brand names, trademarks, etc. related to the investment target business, weights the contributions of corporate efforts, social media influencers, etc., and generates an evaluation report. This makes it possible to evaluate the target company's goodwill quickly and accurately without incurring large costs or time. [Brief explanation of the drawings]

[0006] [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. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13] FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment Example 2. [Figure 15] FIG. 10 is a sequence diagram showing the flow of processing in a data processing system according to a third embodiment of the third embodiment. [Figure 16] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0007] 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.

[0008] First, the terms used in the following description will be explained.

[0009] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (TENSOR PROCESSING UNIT (registered trademark)).

[0010] 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.

[0011] 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.

[0012] 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.

[0013] 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."

[0014] [First embodiment]

[0015] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0016] 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.

[0017] 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).

[0018] 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.

[0019] 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.

[0020] 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.

[0021] 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.

[0022] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0023] 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.

[0024] 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.

[0025] 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.

[0026] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0027] "Example 1"

[0028] One embodiment of the present invention is a system equipped with a means for aggregating information on the market exposure and penetration of brand names, trademarks, etc. related to investment target businesses. Specifically, the system collects information from the Internet and calculates the exposure and penetration of brand names, trademarks, etc. from that information. This calculation is performed based on information such as how often a brand name, trademark, etc. is mentioned on websites or social media, or how many users recognize the brand name, trademark, etc.

[0029] "Example 2"

[0030] Furthermore, it also has a means of weighting factors such as corporate efforts and those of social media influencers. Specifically, weighting is performed by taking into account the influence of corporate marketing and advertising activities, recommendations by social media influencers, etc., on the exposure and penetration of brand names and trademarks. This weighting is based on, for example, the scale of a company's advertising budget and marketing activities, the number of followers of social media influencers, and the number of engagements on their posts.

[0031] "Example 3"

[0032] It also has a means for generating an evaluation report. Specifically, it evaluates the value of brand names, trademarks, etc. based on the above exposure / penetration and weighting results, and outputs the results as a report. This report is used as reference information for investment decisions. For example, the report may include the exposure / penetration of brand names, trademarks, etc., the weighting results, and an evaluation score based on these.

[0033] The processing flow of each embodiment will be described below.

[0034] "Example 1"

[0035] Step 1: The system collects information from the internet by scraping data from websites and social media, obtaining data through APIs, etc.

[0036] Step 2: From the collected information, calculate the exposure and penetration of the brand name, trademark, etc. This calculation is based on information such as how often the brand name, trademark, etc. is mentioned on websites and social media, and how many users recognize the brand name, trademark, etc.

[0037] "Example 2"

[0038] Step 1: Weighting is performed on the exposure and penetration of brand names, trademarks, etc., taking into account the influence of a company's marketing and advertising activities, recommendations by social media influencers, etc. This weighting is based on factors such as the company's advertising budget and the scale of its marketing activities, the number of followers of social media influencers, and the number of engagements on their posts.

[0039] "Example 3"

[0040] Step 1: Based on the above exposure, penetration and weighting results, evaluate the value of the brand name, trademark, etc.

[0041] Step 2: The evaluation results are output as a report. This report can be used as reference information for investment decisions. The report includes the exposure and penetration of brand names and trademarks, weighting results, and an evaluation score based on these.

[0042] Example 1

[0043] Next, a description will be given of Example 1 of Form 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."

[0044] Previous methods for assessing the exposure and penetration of brand names, trademarks, etc. required manual data collection and analysis, which was time-consuming and labor-intensive. Furthermore, there was a lack of means to properly assess the influence of corporate efforts and influencers on social networking services, making accurate assessments difficult. This made it difficult to provide reliable information for investment decisions.

[0045] 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.

[0046] In this invention, the server includes means for receiving prompt text, means for collecting information on the Internet, means for analyzing the collected information, means for calculating the exposure and penetration of brand names, trademarks, etc., means for providing the calculation results, means for weighting factors such as those due to corporate efforts and influencers on social networking services, and means for generating an evaluation report. This makes it possible to automatically and accurately evaluate the exposure and penetration of brand names, trademarks, etc., and provide reliable information for investment decisions.

[0047] A "prompt sentence" is the text of an instruction or question that a user enters into a system.

[0048] "Information on the Internet" refers to data that is publicly available on the Internet, such as on websites and social networking services.

[0049] "Means of collection" refers to technology that automatically obtains information on the Internet using web crawlers and APIs.

[0050] "Means of analysis" refers to techniques that use natural language processing and data mining techniques to analyze collected information and extract meaning and patterns.

[0051] "Exposure and penetration of brand names, trademarks, etc." refers to the degree to which a particular brand name or trademark is mentioned and recognized on the Internet.

[0052] The "means of calculation" refers to the technology that quantifies the exposure and penetration of specific brand names and trademarks based on collected and analyzed data.

[0053] "Means of providing" refers to the technology for displaying the calculation results to the user or outputting them as a report.

[0054] "Corporate efforts" refer to the marketing and promotional activities that a company undertakes to increase brand awareness and reputation.

[0055] "Social networking service influencers" are individuals or organizations that have many followers on social media and have a strong ability to disseminate information.

[0056] "Weighting methods" are techniques that assign appropriate weights to the exposure and penetration of brand names and trademarks, taking into account the influence of corporate efforts and social media influencers.

[0057] An "evaluation report" is a document summarizing the evaluation results, which is created based on the exposure and penetration of brand names and trademarks and the weighting results.

[0058] This invention relates to a system for automatically evaluating the exposure and penetration of brand names, trademarks, etc. related to investment target businesses. This system includes elements of a server, a terminal, and a user.

[0059] First, the user inputs a prompt sentence using a terminal. For example, the prompt sentence is "Please calculate the exposure and penetration of ABC brand." This prompt sentence is sent to the server.

[0060] When the server receives the prompt, it launches a web crawler to collect information from websites and social networking services based on the specified keyword "ABC brand."

[0061] The collected data is analyzed by the server using a natural language processing (NLP) library. During the analysis process, mentions related to brand names, trademarks, etc. are extracted and the number of mentions is counted. Sentiment analysis is also performed and a rating is assigned as positive, negative, or neutral.

[0062] The server then calculates the exposure and penetration of brand names, trademarks, etc. based on the analysis results. The calculation uses the number of mentions and the results of sentiment analysis. In addition, weighting is performed taking into account the influence of corporate efforts and influencers on social networking services.

[0063] The calculation results are generated as an evaluation report. The evaluation report includes an evaluation score based on the exposure and penetration of the brand name, trademark, etc., and the weighting results. The server provides this evaluation report to the user. For example, the result displayed may be, "The exposure and penetration of ABC brand is 85 points."

[0064] This system allows users to automatically and accurately evaluate the exposure and penetration of brand names, trademarks, etc., providing reliable information for investment decisions.

[0065] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0066] Step 1:

[0067] The user uses a terminal to input a prompt sentence. For example, the user inputs the prompt sentence "Please calculate the exposure and penetration of ABC brand." The input prompt sentence is sent to the server. The input is the prompt sentence, and the output is the transmission of the prompt sentence to the server.

[0068] Step 2:

[0069] The server receives the prompt sentence, parses it, and extracts the specified keyword (in this case, "ABC brand"). The input is the prompt sentence, and the output is the extracted keyword.

[0070] Step 3:

[0071] The server launches a web crawler to collect information on the Internet based on the extracted keywords. Specifically, it collects data related to "ABC Brand" from websites and social networking services. The input is the extracted keywords, and the output is the collected data.

[0072] Step 4:

[0073] The server analyzes the collected data using a natural language processing (NLP) library. Specifically, it extracts mentions related to "ABC Brand" from the text data and counts the number of mentions. It also performs sentiment analysis and assigns a positive, negative, or neutral rating. The input is the collected data, and the output is the number of mentions and the results of the sentiment analysis.

[0074] Step 5:

[0075] The server calculates the exposure and penetration of brand names, trademarks, etc. based on the analysis results. The calculation uses the number of mentions and the results of sentiment analysis. In addition, weighting is performed taking into account the influence of corporate efforts and influencers on social networking services. The input is the number of mentions and the results of sentiment analysis, and the output is an exposure and penetration score.

[0076] Step 6:

[0077] The server generates a rating report based on the calculation results. The rating report includes a rating score based on the exposure and penetration of brand names, trademarks, etc. and the weighted results. The input is the exposure and penetration score, and the output is the rating report.

[0078] Step 7:

[0079] The server provides the generated evaluation report to the user. For example, it displays the result "The exposure and penetration of ABC brand is 85 points." The input is the evaluation report, and the output is providing the result to the user.

[0080] (Application example 1)

[0081] Next, a description will be given of Application Example 1 of Embodiment 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."

[0082] Conventional systems for assessing the exposure and penetration of brand names and trademarks have difficulty collecting information from the internet in real time and immediately understanding a brand's exposure and penetration. Furthermore, they lacked the ability to send notifications when exposure and penetration exceeded a certain threshold, making it difficult to quickly adapt marketing strategies. Furthermore, they lacked the ability to generate prompt messages using a generative AI model, leaving advertisers with a lack of guidance for taking specific actions.

[0083] 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.

[0084] In this invention, the server includes means for aggregating information on the market exposure and penetration of brand names, trademarks, etc. related to investment target businesses, means for weighting factors such as corporate efforts and social media influencers, means for generating evaluation reports, means for collecting information on the Internet, means for calculating the exposure and penetration of brand names, trademarks, etc., means for monitoring the exposure and penetration in real time, means for sending notifications when the exposure and penetration exceed a specific threshold, and means for generating prompt messages using a generative AI model. This enables brand exposure and penetration to be grasped in real time, enabling the rapid development and implementation of marketing strategies.

[0085] An "investment target business" is a business that aims to make a profit by investing funds.

[0086] A "brand name" is a name used to identify a particular product or service.

[0087] A "trademark" is a mark or logo that distinguishes a particular product or service from others.

[0088] "Exposure / penetration" refers to the degree to which a brand name or trademark is recognized in the market and by consumers.

[0089] "Corporate efforts" are the activities that companies undertake to penetrate their brands and products into the market.

[0090] A "SNS influencer" is an individual who has a large number of followers and influence on a social networking service.

[0091] "Weighting" refers to the numerical evaluation of the importance or influence of a particular element.

[0092] An "evaluation report" is a report summarizing the evaluation results regarding the exposure and penetration of a brand name or trademark.

[0093] "Information on the Internet" refers to data that exists on online platforms such as websites and social media.

[0094] "Real-time" means that data and information are processed immediately and provided without delay.

[0095] A "notification" is an alert or message sent to a user when a specific condition is met.

[0096] A "generative AI model" is an algorithm or program that uses artificial intelligence to automatically perform specific tasks.

[0097] A "prompt" is an instruction or question input to a generative AI model.

[0098] A system for carrying out this invention has the following configuration: A server includes means for aggregating information on the market exposure and penetration of brand names, trademarks, etc. related to investment target businesses, means for weighting factors such as corporate efforts and social media influencers, means for generating evaluation reports, means for collecting information on the Internet, means for calculating the exposure and penetration of brand names, trademarks, etc., means for monitoring the exposure and penetration in real time, means for sending a notification when the exposure and penetration exceeds a specific threshold, and means for generating prompt sentences using a generative AI model.

[0099] Program processing explanation

[0100] The server first collects information from the Internet. Specifically, it uses the requests library to obtain the content of the web page from the specified URL and extracts the text from the web page. Next, it uses regular expressions to count how often the brand name or trademark is mentioned in the extracted text. Based on this count, it calculates the exposure and penetration of the brand name or trademark.

[0101] The calculated exposure and penetration levels are monitored in real time, and if a certain threshold is exceeded, a notification is sent to the user, allowing them to take immediate action. Furthermore, a generative AI model is used to generate prompts and suggest specific actions to the user.

[0102] The hardware used is a server and a smartphone with internet connectivity. The software uses Python (registered trademark) and its libraries. The generative AI model used is, for example, OpenAI's (registered trademark) GPT-3 (registered trademark).

[0103] Specific examples

[0104] For example, when monitoring the exposure and penetration of Brand A, Brand B, and Brand C, the server collects and calculates in real time how often these brand names are mentioned on social media and websites. If the exposure and penetration exceeds a certain threshold, a notification is sent to the user's smartphone. Furthermore, a generative AI model is used to generate prompt sentences such as the following:

[0105] Prompt Sentence Examples

[0106] "Monitor Brand A's visibility and send a notification when it reaches 1000 social media mentions."

[0107] In this way, users can grasp the brand's exposure and penetration in real time, enabling them to quickly plan and execute marketing strategies.

[0108] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0109] Step 1:

[0110] The server retrieves the web page content from the specified URL. Specifically, it uses the requests library to send an HTTP request and retrieve the HTML data of the web page. The input is a list of URLs, and the output is the HTML data corresponding to each URL.

[0111] Step 2:

[0112] The server extracts text from the retrieved HTML data. Specifically, it parses the HTML and extracts the text content. The input is the HTML data, and the output is the extracted text.

[0113] Step 3:

[0114] The server counts how many times brand names and trademarks are mentioned in the extracted text. Specifically, it counts the number of times a brand name or trademark appears using regular expressions. The input is text data and a list of brand names, and the output is the number of times each brand name appears.

[0115] Step 4:

[0116] The server calculates the exposure and penetration of brand names and trademarks based on the counting results. Specifically, it quantifies the exposure and penetration based on the number of appearances. The input is the number of appearances of the brand name, and the output is the numerical value of the exposure and penetration.

[0117] Step 5:

[0118] The server monitors the calculated exposure and penetration in real time. Specifically, it sends a notification when the exposure and penetration exceeds a certain threshold. The input is the exposure and penetration value and the threshold, and the output is a notification message.

[0119] Step 6:

[0120] The server generates prompts using a generative AI model. Specifically, it generates prompts that suggest specific actions to the user based on exposure and penetration data. The input is exposure and penetration data, and the output is the generated prompt.

[0121] Step 7:

[0122] The user receives the notification and prompt text sent from the server and plans and executes an appropriate marketing strategy. Specifically, based on the notification message and prompt text, the user takes action according to the brand's exposure and penetration. The input is the notification message and prompt text, and the output is the user's action.

[0123] Example 2

[0124] Next, a description will be given of Example 2 of Form 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."

[0125] Conventional methods for assessing the exposure and penetration of brand names and trademarks do not adequately take into account factors such as a company's advertising budget, the scale of marketing activities, or the influence of social media influencers, making accurate assessments difficult. Furthermore, there was a lack of specific proposals for improving marketing strategies based on the assessment results.

[0126] 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.

[0127] In this invention, the server includes: means for aggregating information on the market exposure and penetration of brand names, trademarks, etc. related to the investment target business; means for collecting data such as a company's advertising budget and the scale of its marketing activities, and the number of followers and post engagements of social media influencers; means for analyzing the collected data and weighting the exposure and penetration of the brand names and trademarks; means for generating an evaluation report; and means for generating prompt sentences to be input into the generative AI model. This enables accurate brand evaluation that takes into account a company's advertising budget, the scale of its marketing activities, and the influence of social media influencers.

[0128] "Investment target business" refers to any business that aims to make a profit by investing funds.

[0129] "Brand name" refers to a name used to identify a particular product or service.

[0130] "Trademark" refers to a logo, symbol, design, etc. used to identify a particular product or service.

[0131] "Exposure and penetration" refers to the degree to which a brand name or trademark is recognized in the market and by consumers.

[0132] A "company's advertising budget" refers to the total amount of funds a company plans to spend on advertising activities.

[0133] The "scale of marketing activities" refers to the scope and influence of a company's marketing activities.

[0134] A "SNS influencer" refers to an individual who has a large number of followers and influence on a social networking service.

[0135] "Number of followers" refers to the number of users who follow a social media influencer's account.

[0136] "Engagement count" refers to the total number of user reactions (likes, comments, shares, etc.) to a social media influencer's post.

[0137] "Means of collecting data" refers to the methods and tools used to obtain the required data.

[0138] "Means of analyzing data" refers to the methods and tools used to process collected data and convert it into meaningful information.

[0139] "Weighting means" refers to a method or tool for assigning importance to a particular element.

[0140] "Means for generating an evaluation report" refers to methods and tools for creating a report summarizing the evaluation results based on the analysis results.

[0141] A "generative AI model" refers to a model that has been trained using artificial intelligence to perform a specific task.

[0142] A "prompt sentence" refers to an instruction sentence to be input into a generative AI model.

[0143] This invention is a system that generates an evaluation report by weighting the exposure and penetration of brand names and trademarks, taking into account the influence of corporate marketing activities and social media influencers. Specific embodiments of this system are described below.

[0144] System configuration

[0145] This system consists of three main components: a server, a terminal, and a user. The server collects data, analyzes it, calculates weights, and generates evaluation reports. The terminal provides an interface for users to access the system and check the results. The user operates the system and inputs the necessary data.

[0146] Hardware and software used

[0147] The server uses a specified API for data collection, a Python library for data analysis, and a tool for outputting data in JSON format and displaying it on a dashboard to generate an evaluation report.

[0148] Data collection

[0149] The server collects data such as a company's advertising budget and the scale of its marketing activities, as well as the number of followers and post engagements of social media influencers. Specifically, it calls an API to obtain the company's advertising campaign data and uses an API to obtain the number of followers and engagements of social media influencers.

[0150] Data analysis

[0151] The server analyzes the collected data. This analysis involves data cleansing (completion of missing values ​​and removal of outliers) and data normalization (scaling). Specifically, a Python library is used to create a data frame, complement missing values, and normalize the data.

[0152] Weighting Calculation

[0153] Based on the analyzed data, the server assigns weights to the exposure and penetration of brand names and trademarks. This weighting is calculated taking into account the company's advertising budget and the scale of its marketing activities, as well as the number of followers and engagement of social media influencers. The specific calculation formula is as follows:

[0154] Weight = (Advertising budget score 0.5) + (Marketing activity score 0.3) + (Social media influencer score 0.2)

[0155] Here, each score is a normalized value.

[0156] Generate an assessment report

[0157] The server generates a rating report based on the calculated weighting results. This rating report includes the exposure and penetration of the brand name or trademark and a rating score based on the weighting results. The rating report is output in JSON format and displayed on the dashboard.

[0158] Specific examples

[0159] For example, suppose that Company A has an annual advertising budget of 100 million yen, and Social Media Influencer B has 1 million followers and 100,000 engagements on its posts. In this case, the server would operate as follows:

[0160] 1. The server calls a specified API to obtain Company A's advertising campaign data.

[0161] 2. The server uses a specified API to obtain the number of followers and engagements of influencer B.

[0162] 3. The server analyzes the acquired data using the library, imputes missing values, and normalizes them using the library.

[0163] 4. The server uses a weighting formula to assign weights to the exposure and penetration of the brand name or trademark.

[0164] 5. The server outputs the calculation results in JSON format and displays them on the dashboard.

[0165] An example of a prompt to input to a generative AI model is as follows:

[0166] "Company A's annual advertising budget is 100 million yen, and social media influencer B has 1 million followers and 100,000 engagements on their posts. Based on this data, please assign weights to the exposure and penetration of brand names and trademarks."

[0167] In this way, the server provides a system that evaluates the exposure and penetration of brand names and trademarks by weighting the influence of corporate marketing activities and social media influencers.

[0168] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0169] Step 1:

[0170] The server collects data such as a company's advertising budget and the scale of its marketing activities, as well as the number of followers and post engagements of social media influencers. Specifically, it calls an API to obtain the company's advertising campaign data and uses an API to obtain the number of followers and engagements of social media influencers. The input is the raw data obtained from the API, and the output is the collected dataset.

[0171] Step 2:

[0172] The server analyzes the collected data. This analysis involves cleansing the data (filling in missing values ​​and removing outliers) and normalizing (scaling) it. Specifically, a Python library is used to create a data frame and fill in missing values. A Python library is also used to normalize the data. The input is the collected dataset, and the output is the cleansed and normalized data.

[0173] Step 3:

[0174] The server then assigns weights to the exposure and penetration of brand names and trademarks based on the analyzed data. The specific calculation formula is as follows:

[0175] Weight = (Advertising budget score 0.5) + (Marketing activity score 0.3) + (Social media influencer score 0.2)

[0176] Here, each score is a normalized value: the input is the cleansed and normalized data, and the output is a weighted evaluation score.

[0177] Step 4:

[0178] The server generates an evaluation report based on the calculated weighting results. The evaluation report is output in JSON format and displayed on a dashboard. Specifically, a report containing the evaluation scores is generated and made accessible to users. The input is the weighted evaluation score, and the output is the evaluation report.

[0179] Step 5:

[0180] The server generates prompts to be input to the generative AI model. Specifically, it generates prompts like the following based on data such as the company's advertising budget and the number of followers and engagement of social media influencers:

[0181] "Company A's annual advertising budget is 100 million yen, and social media influencer B has 1 million followers and 100,000 engagements on their posts. Based on this data, please assign weights to the exposure and penetration of brand names and trademarks."

[0182] The input is data about companies and social media influencers, and the output is the generated prompt sentence.

[0183] (Application example 2)

[0184] Next, a description will be given of Application Example 2 of Form 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."

[0185] Traditional methods for evaluating advertising campaigns make it difficult to comprehensively consider a company's advertising budget, the scale of its marketing activities, and the influence of social media influencers, resulting in insufficient optimization of advertising strategies. Real-time evaluation is also difficult, making it unsuitable for the modern marketing environment, which requires rapid strategic changes. This results in the inability to maximize advertising effectiveness and reduces the efficiency of a company's investment.

[0186] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0187] In this invention, the server includes means for aggregating information on the market exposure and penetration of brand names, trademarks, etc. related to the investment target business, means for weighting factors such as corporate efforts and SNS influencers, means for generating an evaluation report, means for evaluating the effectiveness of advertising campaigns in real time, and means for optimizing advertising strategies taking into account the influence of SNS influencers. This makes it possible to comprehensively evaluate the effectiveness of a company's advertising campaigns in real time and to formulate optimal advertising strategies taking into account the influence of SNS influencers.

[0188] An "investment target business" is a business in which a company invests funds in the hope of achieving growth and profits.

[0189] A "brand name" is a name used to identify a specific product or service, and serves to assure consumers of the reliability and quality of that product or service.

[0190] A "trademark" is a mark, logo, or symbol used by a company to distinguish its products or services from those of other companies.

[0191] "Exposure and penetration" indicates the degree to which a brand name or trademark is recognized and accepted by the market and consumers.

[0192] "Corporate efforts" refers to the marketing and advertising activities that companies undertake to increase awareness and sales of their products and services.

[0193] A "social media influencer" is someone who has a large number of followers on a social networking service and uses their influence to recommend specific products or services.

[0194] "Weighting" refers to the numerical evaluation of the importance or influence of a particular element or data.

[0195] An "evaluation report" is a report prepared based on specific data and information, and includes evaluation and analysis results.

[0196] An "advertising campaign" is a series of advertising activities undertaken to increase awareness and sales of a particular product or service.

[0197] "Real-time" refers to data and information being processed and analyzed as soon as it is generated.

[0198] An "advertising strategy" refers to the advertising policies and methods that a company plans to use to effectively promote its products and services in the market.

[0199] The system for implementing this invention consists of three main elements: a server, a terminal, and a user. The server includes a means for aggregating the extent of exposure and penetration of brand names and trademarks related to investment target businesses in the market, a means for weighting the influence of corporate efforts and SNS influencers, a means for generating evaluation reports, a means for evaluating the effectiveness of advertising campaigns in real time, and a means for optimizing advertising strategies taking into account the influence of SNS influencers.

[0200] Program processing explanation

[0201] The server first aggregates the exposure and penetration of brand names and trademarks. This is done using web scraping technology and social media analysis tools. Specific software used is Python and social media APIs.

[0202] Next, we weight the influence of corporate efforts and social media influencers. We do this based on the size of a company's advertising budget and marketing activities, as well as the number of followers and engagement of social media influencers. We use Python as a data analysis tool.

[0203] To generate an evaluation report, an evaluation score is calculated based on the aggregated data and weighted results, using a data visualization tool.

[0204] To evaluate the effectiveness of the advertising campaign in real time, the server uses real-time data processing techniques, specifically, a stream processing framework.

[0205] Finally, we optimize advertising strategies by taking into account the influence of social media influencers. To achieve this, we use machine learning models, specifically machine learning libraries such as TENSORFLOW (registered trademark).

[0206] Specific examples

[0207] For example, consider a case where the advertising budget is 5 million yen, the scale of marketing activities is 80, the number of followers of social media influencers is 200,000 and 150,000, and the engagement numbers are 5,000 and 3,000. Based on this data, the server calculates the weighting and optimizes the advertising strategy.

[0208] Example prompts to input to a generative AI model:

[0209] If the advertising budget is 5 million yen, the scale of marketing activities is 80, the number of followers of social media influencers is 200,000 and 150,000, and the engagement numbers are 5,000 and 3,000, calculate the weightings to optimize the advertising strategy.

[0210] In this way, the server comprehensively evaluates the effectiveness of a company's advertising campaign in real time and helps develop optimal advertising strategies that take into account the influence of social media influencers.

[0211] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0212] Step 1:

[0213] The server aggregates the exposure and penetration of brand names and trademarks. Specifically, it collects data from the internet using web scraping technology and social media analysis tools. It receives keywords related to brand names and trademarks as input and generates a list of web pages and social media posts containing those keywords as output.

[0214] Step 2:

[0215] The server uses the aggregated data to weight the influence of corporate efforts and social media influencers. Specifically, it receives inputs such as a company's advertising budget and the scale of its marketing activities, as well as the number of followers and engagement of social media influencers, and processes this data using Python. As output, it generates a weighted score for each factor.

[0216] Step 3:

[0217] The server generates an evaluation report based on the weighting results. Specifically, it receives the aggregated data and weighted scores as input, calculates the evaluation score using a data visualization tool, and generates an evaluation report as output, saved as a PDF file containing graphs and charts.

[0218] Step 4:

[0219] The server evaluates the effectiveness of the advertising campaign in real time. Specifically, it uses real-time data processing technology to monitor the progress and effectiveness of the advertising campaign. As input, it receives and processes the data stream of the advertising campaign. As output, it generates real-time evaluation results and displays them on a dashboard.

[0220] Step 5:

[0221] The server optimizes advertising strategies by taking into account the influence of social media influencers. Specifically, it uses a machine learning model to propose optimal advertising strategies. As input, it receives evaluation reports and real-time evaluation results, and trains the model using TensorFlow. As output, it generates an optimized advertising strategy and proposes it to the company.

[0222] In this way, the server comprehensively evaluates the effectiveness of a company's advertising campaign in real time and helps develop optimal advertising strategies that take into account the influence of social media influencers.

[0223] Example 3

[0224] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0225] There is a need to accurately evaluate the exposure and penetration of brand names and trademarks in the market and generate evaluation reports based on the results to serve as a reference for investment decisions. However, conventional methods often involve manual data collection and analysis, which is inefficient and lacks objectivity and accuracy in evaluation. Furthermore, there is also the issue of ambiguous weighting criteria, which results in low reliability of evaluation scores.

[0226] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0227] In this invention, the server includes a means for aggregating the market exposure and penetration of brand names, trademarks, etc., a means for analyzing collected data using natural language processing technology, a means for weighting based on the exposure and penetration, a means for calculating an evaluation score, and a means for generating an evaluation report. This automates the process from data collection to analysis and generation of an evaluation report, making it possible to efficiently and accurately evaluate brand value.

[0228] "Brand names, trademarks, etc." refer to names and marks used to identify specific products or services in the market.

[0229] "Exposure and penetration" refers to the degree to which a brand name or trademark is recognized and influenced by the market and consumers.

[0230] "Aggregation methods" refers to the methods and techniques used to collect data from multiple sources and compile it into a single dataset.

[0231] "Natural language processing technology" refers to technology that allows computers to analyze and understand human language.

[0232] "Means of analysis" refers to methods and techniques for analyzing collected data and extracting useful information.

[0233] "Weighting methods" refer to methods or techniques for assessing the importance or impact of data and assigning numerical weights based on that assessment.

[0234] "Evaluation score" refers to a number that indicates the value of a brand, calculated based on exposure, penetration, and weighting results.

[0235] "Evaluation Report" refers to a document summarizing the evaluation results, including the exposure and penetration of brand names and trademarks, weighting results, evaluation scores, etc.

[0236] This invention is a system that evaluates the exposure and penetration of brand names and trademarks in the market and generates an evaluation report based on the results. A specific embodiment of this system will be described below.

[0237] The server first collects data related to brand names and trademarks from the internet. This data is obtained from online sources such as social media, news articles, blogs, and forums. Web scraping technology and APIs are used to collect the data. Specifically, designated APIs can be used.

[0238] The server then analyzes the collected data. This analysis uses natural language processing (NLP) technology, specifically analyzing the sentiment of the text data and extracting keywords. This allows the exposure and penetration of brand names and trademarks to be calculated.

[0239] The server then assigns weights based on the analysis results. Weighting is an important step in assessing a brand's market value and influence. For example, a brand with high exposure receives a higher weight, while a brand with low penetration receives a lower weight. This results in an overall evaluation score.

[0240] Finally, the server generates a rating report based on the rating scores. This report includes the exposure and penetration of the brand name or trademark, the weighting results, and the rating scores. The report is output in PDF format and can be downloaded by users.

[0241] As a specific example, when generating a rating report for a brand "ABC," the server performs the following steps:

[0242] 1. The server collects online data about "ABC".

[0243] 2. The server analyzes the data and calculates exposure and penetration.

[0244] 3. The server calculates a rating score based on the weighting of exposure and penetration.

[0245] 4. The server generates an evaluation report based on the evaluation score and outputs it in PDF format.

[0246] Example prompts to input to a generative AI model:

[0247] "Evaluate the exposure and penetration of brand ABC and generate an evaluation report. The report should include exposure and penetration, weighting results, and evaluation score."

[0248] In this way, the user can obtain a detailed report for evaluating the value of the brand. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0249] Step 1: Data collection

[0250] The server collects data related to brand names and trademarks from the internet. As input, it receives keywords related to the brand names and trademarks. Specifically, it obtains data from online sources such as social media, news articles, blogs, and forums. It uses web scraping technology and APIs to collect the data. For example, it uses a specific API to collect related tweets and news articles. The output is the collected text data.

[0251] Step 2: Data analysis

[0252] The server analyzes the collected text data. As input, it receives the text data collected in step 1. This analysis uses natural language processing (NLP) technology. Specifically, it performs sentiment analysis and keyword extraction on the text data. For example, a tweet saying "Brand ABC is great" is analyzed as having a positive sentiment. As output, it obtains exposure and penetration data as the analysis results.

[0253] Step 3: Calculating weights and evaluation scores

[0254] The server assigns weights based on the analysis results. As input, it receives the exposure and penetration data obtained in step 2. Weighting is an important step in evaluating a brand's market value and influence. For example, if exposure is high, a high weight is assigned, and if penetration is low, a low weight is assigned. This is how an overall evaluation score is calculated. As output, the weighted result and evaluation score are obtained.

[0255] Step 4: Generate an assessment report

[0256] The server generates a rating report based on the rating scores. As input, it receives the weighting results and rating scores obtained in step 3. This report includes the exposure and penetration of the brand name or trademark, the weighting results, and the rating scores. Specifically, the report is generated in PDF format and made available for download by the user. As output, the rating report is obtained.

[0257] In this way, users can get detailed reports to assess the value of their brand.

[0258] (Application example 3)

[0259] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0260] Conventional brand name and trademark evaluation systems lack real-time calculations of exposure and penetration, making it difficult to immediately evaluate the effectiveness of advertising campaigns. Furthermore, when generating evaluation reports, the input of prompts using generative AI models is not taken into account, resulting in problems with reduced evaluation accuracy and efficiency. This resulted in a lack of reliability as reference information for investment decisions.

[0261] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0262] In this invention, the server includes means for aggregating information on the market exposure and penetration of brand names, trademarks, etc. related to the investment target business, means for weighting factors such as corporate efforts and social media influencers, means for generating an evaluation report, means for evaluating the effectiveness of the advertising campaign in real time, means for calculating the degree of exposure and penetration, means for calculating the weighted results, means for calculating an evaluation score, means for outputting the evaluation report, and means for inputting prompt sentences using a generative AI model. This makes it possible to evaluate the effectiveness of the advertising campaign in real time and quickly generate highly accurate evaluation reports.

[0263] "Investment target business" refers to the company or project that is the target of investment.

[0264] A "brand name" refers to a name used to identify a particular product or service.

[0265] A "trademark" refers to a mark or logo that identifies a particular product or service.

[0266] "Exposure" refers to an indicator that shows how often a brand name or trademark appears in the market or media.

[0267] "Penetration" refers to an indicator that shows how well a brand name or trademark is recognized in the market and among consumers.

[0268] "Corporate efforts" refers to the marketing and promotional activities that a company undertakes itself.

[0269] A "social media influencer" is an individual or organization that has a large following and influence on social media.

[0270] "Weighting" refers to a method for assigning importance to different elements.

[0271] An "evaluation report" refers to a report that summarizes the exposure and penetration of a brand name or trademark, weighting results, evaluation scores, etc.

[0272] An "advertising campaign" refers to a series of advertising activities to promote a particular brand or product.

[0273] "Real-time" refers to data and information being processed immediately.

[0274] A "generative AI model" refers to a model that uses artificial intelligence to generate data.

[0275] A "prompt" refers to an instruction sentence that is input into a generative AI model.

[0276] "Exposure" refers to an indicator of how many people see an advertisement or brand.

[0277] "Penetration" is an indicator that shows how many people are aware of an advertisement or brand.

[0278] "Weighted results" refers to results that reflect the weights assigned to different factors.

[0279] "Evaluation score" refers to a comprehensive evaluation value calculated based on exposure, penetration, and weighting results.

[0280] The system for implementing this invention consists of three main elements: a server, a terminal, and a user. The following explains how each element functions.

[0281] server

[0282] The server plays a central role in aggregating the exposure and penetration of brand names and trademarks and generating evaluation reports. Specifically, it performs the following processes:

[0283] 1. Data Collection and Aggregation:

[0284] The server collects advertising campaign data and calculates the exposure and penetration of brand names and trademarks, including data such as impressions, click-through rates, unique visitors, and total population.

[0285] 2. Calculating weights:

[0286] The server assigns weights based on the company's efforts and the exposure and penetration of social media influencers, and calculates weighted results that reflect the importance of each factor.

[0287] 3. Calculation of the rating score:

[0288] The server calculates a rating score based on the weighting results. The rating score is a comprehensive rating value that combines the exposure, penetration, and weighting results.

[0289] 4. Generate and print the evaluation report:

[0290] The server generates an evaluation report including the calculated evaluation scores and outputs it in a format such as a CSV file.

[0291] 5. Leveraging generative AI models:

[0292] The server uses a generative AI model to input prompt sentences and automate the generation of evaluation reports, thereby improving the accuracy and efficiency of evaluations.

[0293] Terminal

[0294] The terminal provides an interface for users to check the evaluation report and evaluate the effectiveness of the advertising campaign in real time. Specifically, it has the following functions:

[0295] 1. Displaying data:

[0296] The terminal displays the evaluation report sent from the server, which includes the brand name, exposure, penetration, weighting results, evaluation score, etc.

[0297] 2. Real-time evaluation:

[0298] The device provides an interface for evaluating the effectiveness of advertising campaigns in real time, allowing users to view real-time updated data and make quick decisions.

[0299] User

[0300] Users can check the evaluation report through their devices and evaluate the effectiveness of their advertising campaigns by performing the following operations:

[0301] 1. Review the assessment report:

[0302] Users can check the evaluation report sent from the server via their device, which allows them to understand the exposure and penetration of brand names and trademarks, weighting results, and evaluation scores.

[0303] 2. Enter the prompt:

[0304] The user inputs a prompt to the generative AI model to instruct it to generate an evaluation report. For example, the user might input a prompt such as, "Based on the advertising campaign data, please calculate the brand's exposure, penetration, weighting results, and evaluation score, and generate an evaluation report."

[0305] Hardware and software used

[0306] The following hardware and software are used to realize this system.

[0307] Hardware:

[0308] General PC or server

[0309] User devices (smartphones, tablets, PCs, etc.)

[0310] software:

[0311] Python

[0312] Data processing library

[0313] Numerical calculation library

[0314] Machine learning libraries

[0315] Generative AI models (e.g., GPT-3)

[0316] This makes it possible to evaluate the effectiveness of advertising campaigns in real time and quickly generate highly accurate evaluation reports.

[0317] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0318] Step 1:

[0319] The server collects ad campaign data, specifically reading data such as impressions, click-through rate, unique visitors, and total population from a CSV file. The input is the ad campaign data, and the output is the read data frame.

[0320] Step 2:

[0321] The server calculates exposure and penetration based on the collected data. Exposure is the product of the number of impressions and the click-through rate, and penetration is the number of unique visitors divided by the total population. The input is the data frame loaded in step 1, and the output is a data frame containing the calculated exposure and penetration.

[0322] Step 3:

[0323] The server weights the exposure and penetration based on the exposure and penetration. Specifically, it assigns a weight of 0.6 to the exposure and a weight of 0.4 to the penetration and sums them. The input is the exposure and penetration calculated in step 2, and the output is a data frame containing the weighted results.

[0324] Step 4:

[0325] The server calculates an evaluation score based on the weighted results, which is calculated by scaling the weighted results to a range from 0 to 1. The input is the weighted results obtained in step 3, and the output is a data frame containing the evaluation scores.

[0326] Step 5:

[0327] The server generates a rating report including the rating scores and outputs it as a CSV file. The input is the rating scores calculated in step 4, and the output is a CSV file of the rating report.

[0328] Step 6:

[0329] The server inputs a prompt using a generative AI model to automate the generation of an evaluation report. Specifically, the prompt input is, "Based on the advertising campaign data, please calculate the brand's exposure, penetration, weighting results, and evaluation score, and generate an evaluation report." The input is the prompt, and the output is the generated evaluation report.

[0330] Step 7:

[0331] The terminal displays the evaluation report sent from the server. The input is a CSV file of the evaluation report sent from the server, and the output is the evaluation report displayed on the terminal screen.

[0332] Step 8:

[0333] The user checks the evaluation report through the terminal and evaluates the effectiveness of the advertising campaign in real time. The input is the evaluation report displayed on the terminal, and the output is the user's evaluation result.

[0334] 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.

[0335] "Example 1"

[0336] One embodiment of the present invention is a system that incorporates an emotion engine. This system recognizes user emotions and aggregates the exposure and penetration of brand names, trademarks, etc., taking those emotions into consideration. Specifically, the emotion engine recognizes the emotions (joy, anger, surprise, sadness, etc.) that users express toward specific brand names, trademarks, etc., and reflects the intensity and direction of those emotions in the calculation of exposure and penetration. For example, if a user expresses strong emotions of joy toward a particular brand, the exposure and penetration of that brand will be highly rated.

[0337] "Example 2"

[0338] Weighting is also performed taking into account the user's emotions recognized by the emotion engine. Specifically, weighting is performed on the exposure and penetration of brand names, trademarks, etc., taking into account the strength and direction of the user's emotions. For example, if a user expresses strong feelings of joy toward a particular brand, the weighting for that brand will be high.

[0339] "Example 3"

[0340] Furthermore, the evaluation report includes an evaluation score that reflects the user's emotions recognized by the emotion engine. Specifically, an evaluation score for a brand name, trademark, etc. is calculated taking into account the strength and direction of the user's emotions, and the score is included in the evaluation report. For example, if a user expresses strong feelings of joy toward a particular brand, the evaluation score for that brand will be high.

[0341] The processing flow of each embodiment will be described below.

[0342] "Example 1"

[0343] Step 1: Users express their feelings about a particular brand name, trademark, etc.

[0344] Step 2: The emotion engine recognizes the user's emotions (joy, anger, surprise, sadness, etc.).

[0345] Step 3: The intensity and direction of the emotion recognized by the emotion engine is reflected in the calculation of the exposure and penetration of brand names, trademarks, etc.

[0346] Step 4: Aggregate the exposure and penetration of brand names, trademarks, etc., taking into account user emotions.

[0347] "Example 2"

[0348] Step 1: Users express their feelings about a particular brand name, trademark, etc.

[0349] Step 2: The emotion engine recognizes the user's emotions (joy, anger, surprise, sadness, etc.).

[0350] Step 3: The intensity and direction of the emotion recognized by the emotion engine is reflected in the weighting of the exposure and penetration of brand names, trademarks, etc.

[0351] "Example 3"

[0352] Step 1: Users express their feelings about a particular brand name, trademark, etc.

[0353] Step 2: The emotion engine recognizes the user's emotions (joy, anger, surprise, sadness, etc.).

[0354] Step 3: The intensity and direction of the emotions recognized by the emotion engine are reflected in the calculation of the evaluation score for the brand name, trademark, etc.

[0355] Step 4: Include the evaluation scores in the evaluation report.

[0356] Example 1

[0357] Next, a description will be given of Example 1 of Form 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."

[0358] With conventional systems, it was difficult to accurately evaluate the market exposure and penetration of brand names, trademarks, etc. related to investment target businesses. Furthermore, because the evaluation did not take into account user sentiment, it was not possible to grasp the true value of the brand. Furthermore, there was a lack of efficient means for analyzing collected data and generating evaluation reports.

[0359] 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.

[0360] In this invention, the server includes means for aggregating the market exposure and penetration of brand names, trademarks, etc. related to the investment target business, means for weighting factors such as corporate efforts and influencers on social networking services, means for generating an evaluation report, means for collecting information on the Internet, means for analyzing the collected information, means for recognizing user emotions and calculating the degree of exposure and penetration taking those emotions into consideration, and means for aggregating the exposure and penetration based on the analysis results. This makes it possible to accurately evaluate the market exposure and penetration of brand names, trademarks, etc., and to perform an evaluation that takes user emotions into consideration.

[0361] "Investment target business" refers to a business or project in which investment funds are being considered.

[0362] "Brand names, trademarks, etc." refers to names, logos, symbols, etc. that are used to identify specific products or services.

[0363] A "market" is an economic venue or environment in which products and services are traded.

[0364] "Exposure / penetration" refers to the degree to which a brand name, trademark, etc. is recognized and has influence in the market.

[0365] "Corporate efforts" refer to the various activities and measures that a company undertakes to make its products and services successful in the market.

[0366] A "social networking service influencer" is someone who has a large number of followers on a social networking site and whose opinions and actions have a significant influence on other users.

[0367] "Weighting" refers to assigning importance to a particular factor in an evaluation or calculation.

[0368] An "evaluation report" is a report prepared based on collected data and analysis results.

[0369] "Information on the Internet" refers to data and content that can be accessed via the Internet, such as websites and social media.

[0370] "Analysis" is the process of examining collected data in detail to find meaning and patterns.

[0371] "User emotions" refer to the psychological reactions and feelings that users have toward a particular brand name, trademark, etc.

[0372] "Calculating exposure and penetration while taking emotions into consideration" means reflecting the intensity and direction of the user's emotions in the evaluation.

[0373] "Aggregation" means combining multiple pieces of data or information into one.

[0374] This invention is a system that aggregates information on the market exposure and penetration of brand names, trademarks, etc. related to investment target businesses. The system operates in cooperation with three parties: a server, a terminal, and a user.

[0375] Data collection

[0376] The server collects information from the Internet. Specifically, it collects mentions of brand names, trademarks, etc. from websites and social networking services (SNS). The hardware used is a high-performance server, and the software used is a web scraping tool.

[0377] Data analysis

[0378] The server analyzes the collected data. Specifically, it uses natural language processing tools to calculate the exposure and penetration of brand names, trademarks, etc. The server tokenizes the text data and calculates the frequency of appearance of brand names, trademarks, etc. It also analyzes the co-occurrence of related keywords to determine whether users recognize the brand.

[0379] emotion recognition

[0380] The server uses an emotion engine to recognize the user's emotions. The server inputs the collected text data into the emotion engine and analyzes the emotions (happiness, anger, surprise, sadness, etc.) that the user expresses toward a specific brand. The intensity and direction of the emotion are quantified and stored in a database.

[0381] Exposure and penetration aggregation

[0382] The server aggregates the exposure and penetration of brand names, trademarks, etc. based on the analysis results. It also takes into account the strength and direction of emotions to calculate the overall exposure and penetration. The final evaluation results are displayed on the dashboard.

[0383] Specific examples

[0384] For example, when a new beverage brand is launched on the market, the server collects information from the internet and analyzes mentions on websites and social media. It then uses an emotion engine to recognize the emotions users express toward the brand. If users express a lot of positive emotions toward the brand, the server will rate the brand's exposure and penetration highly.

[0385] Prompt Sentence Examples

[0386] "A new beverage brand has been launched in the market. Collect information from the internet and analyze mentions on websites and social media to identify the sentiment expressed by users toward the brand, and incorporate the strength and direction of that sentiment into the calculation of exposure and penetration."

[0387] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0388] Step 1:

[0389] Data collection

[0390] The server collects information from the Internet. Specifically, it collects mentions of brand names, trademarks, etc. from websites and social networking services (SNS). The hardware used is a high-performance server, and the software used is a web scraping tool.

[0391] Input: Keywords related to specific brand names, trademarks, etc.

[0392] Output: Collected text data

[0393] Specific operation: The server launches the web scraping tool at a fixed time every day to collect the latest data, which is then stored in the database in real time.

[0394] Step 2:

[0395] Data analysis

[0396] The server analyzes the collected data, specifically using natural language processing tools to calculate the exposure and penetration of brand names, trademarks, etc.

[0397] Input: Collected text data

[0398] Output: Frequency of appearance and co-occurrence of brand names, trademarks, etc.

[0399] Specific operation: The server tokenizes the text data and calculates the frequency of appearance of brand names, trademarks, etc. It also analyzes the co-occurrence of related keywords to evaluate brand awareness.

[0400] Step 3:

[0401] emotion recognition

[0402] The server uses an emotion engine to recognize the user's emotion.

[0403] Input: Collected text data

[0404] Output: The intensity and direction of the user's emotion

[0405] Specific operation: The server inputs the collected text data into an emotion engine and analyzes the emotions (happiness, anger, surprise, sadness, etc.) expressed by the user toward a specific brand. The intensity and direction of the emotions are quantified and stored in a database.

[0406] Step 4:

[0407] Exposure and penetration aggregation

[0408] The server aggregates the exposure and penetration of brand names, trademarks, etc. based on the analysis results, and calculates the overall exposure and penetration, taking into account the strength and direction of emotions.

[0409] Input: Frequency of appearance of brand names, trademarks, etc., co-occurrence relationships, strength and direction of user emotions

[0410] Output: Overall exposure and penetration assessment score

[0411] Specific operation: Based on the analysis results, the server scores the exposure and penetration of brand names, trademarks, etc. The scoring results are updated in real time on the dashboard and are useful for investment decisions.

[0412] Step 5:

[0413] Generate an assessment report

[0414] The server generates a rating report based on the overall exposure and penetration rating score.

[0415] Input: Overall exposure and penetration assessment score

[0416] Output: Evaluation report

[0417] Specific operation: Based on the evaluation scores, the server generates an evaluation report detailing the market performance of the brand name, trademark, etc. The evaluation report is output in PDF format and distributed to relevant parties.

[0418] (Application example 1)

[0419] Next, a description will be given of Application Example 1 of Embodiment 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."

[0420] Previous systems for evaluating the market exposure and penetration of brand names and trademarks only collected information from the Internet and did not take into account user sentiment. This made it difficult to accurately reflect the actual market evaluation of a brand. Furthermore, there was a lack of means to evaluate the effectiveness of advertising campaigns in real time, making it difficult to quickly change strategies.

[0421] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means for aggregating the market exposure and penetration of brand names, trademarks, etc. related to the investment target business, means for weighting factors such as corporate efforts and social media influencers, means for generating evaluation reports, means for collecting information on the Internet, means for recognizing user emotions and aggregating the exposure and penetration of brand names, trademarks, etc. taking those emotions into consideration, and means for evaluating the effectiveness of advertising campaigns in real time. This allows the market evaluation of the brand to be accurately reflected and advertising strategies to be changed quickly.

[0422] "Investment target business" refers to any business that aims to make a profit by investing funds.

[0423] A "brand name" is a name used to identify a specific product or service, and serves to assure consumers of the reliability and quality of that product or service.

[0424] A "trademark" is a logo or symbol used to identify a particular company or product, and is intellectual property protected by law.

[0425] "Market exposure" is an indicator of how many people in the market recognize a brand name or trademark.

[0426] "Penetration" is an indicator of how deeply a brand name or trademark has penetrated the market among consumers.

[0427] "Aggregation methods" refers to the methods and techniques used to collect data from multiple sources and compile it into a single assessment.

[0428] "Weighting methods" refer to methods or techniques for assigning importance to different elements or information and making evaluations based on that.

[0429] An "evaluation report" is a report prepared based on collected data and analysis results, and is intended to evaluate the market exposure and penetration of a brand name or trademark.

[0430] "Information on the Internet" refers to all information accessible via the Internet, such as websites, social media, and blogs.

[0431] "User emotions" refers to the emotions (joy, anger, surprise, sadness, etc.) that users show toward a particular brand name or trademark.

[0432] "Means for recognizing emotions" refers to methods and technologies for analyzing a user's emotions and identifying the type and intensity of those emotions.

[0433] "Real-time assessment means" refers to methods and technologies for instantly analyzing ongoing data and providing the results immediately.

[0434] An "advertising campaign" refers to a series of marketing activities conducted to promote a particular product or service.

[0435] A system for carrying out this invention has the following configuration: A server includes means for aggregating the degree of exposure and penetration in the market of brand names, trademarks, etc. related to investment target businesses, means for weighting factors such as those due to corporate efforts and those due to social media influencers, means for generating evaluation reports, means for collecting information on the Internet, means for recognizing user emotions and aggregating the degree of exposure and penetration of brand names, trademarks, etc. taking those emotions into consideration, and means for evaluating the effectiveness of advertising campaigns in real time.

[0436] Hardware and software used

[0437] Hardware: Servers, smartphones

[0438] Software: Python, TensorFlow, predefined APIs

[0439] Data collection and analysis

[0440] The server scrapes brand name and trademark mentions from websites and also collects mentions on social media using a designated API, allowing for efficient collection of information from the internet.

[0441] Emotion analysis

[0442] The server performs sentiment analysis on the collected text data, which allows it to recognize the user's emotions and identify the type and intensity of those emotions.

[0443] Exposure and penetration calculations

[0444] The server calculates the brand exposure and penetration level based on the collected mention frequency and sentiment data, allowing for an accurate assessment of the market penetration of a brand name or trademark.

[0445] Real-time evaluation

[0446] The server displays the calculation results in real time on a dashboard, allowing for immediate evaluation of the effectiveness of advertising campaigns, enabling quick changes to advertising strategies.

[0447] Specific examples

[0448] For example, when evaluating a brand's advertising campaign, the server first collects information from the Internet, then performs sentiment analysis. After that, it calculates exposure and penetration and displays the evaluation results in real time on a dashboard. This allows users to immediately understand the effectiveness of their advertising campaign and change their strategy if necessary.

[0449] Prompt Sentence Examples

[0450] Your task will be to create a program that calculates the market exposure and penetration of "ExampleBrand" and evaluates the effectiveness of its advertising campaign in real time, taking into account user sentiment. The technologies used will be Python, TensorFlow, and the specified API.

[0451] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0452] Step 1:

[0453] The server collects information from the internet. Specifically, it scrapes mentions of brand names and trademarks from websites and collects mentions on social media using a designated API. The server specifies the brand name or trademark as input and obtains the collected text data as output.

[0454] Step 2:

[0455] The server analyzes the collected text data. Specifically, it performs sentiment analysis on the text data. It uses the collected text data as input and obtains sentiment scores for each text as output.

[0456] Step 3:

[0457] The server calculates the brand exposure and penetration based on the sentiment score and mention frequency. Specifically, it calculates exposure and penetration by multiplying the average sentiment score by the mention frequency. It uses sentiment score and mention frequency as input and obtains an exposure and penetration score as output.

[0458] Step 4:

[0459] The server displays the calculation results in real time on a dashboard, specifically by generating graphs and charts to visualize the exposure and penetration scores and evaluate the effectiveness of advertising campaigns. It uses the exposure and penetration scores as input and obtains visualized evaluation results as output.

[0460] Step 5:

[0461] Users can check the effectiveness of their advertising campaigns through the dashboard and change their strategies as needed, specifically adjusting the content and timing of their ads based on the evaluation results.The visualized evaluation results are used as input, and a new advertising strategy is obtained as output.

[0462] Example 2

[0463] Next, a description will be given of Example 2 of Form 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."

[0464] Conventional brand evaluation systems do not adequately consider the influence of corporate advertising activities or social media influencers when assigning weighting, resulting in inaccurate evaluations of the exposure and penetration of brand names and trademarks. Furthermore, because weighting does not take user emotions into account, evaluations cannot reflect the strength or direction of user emotions. This makes it difficult to accurately evaluate the effectiveness of a company's marketing strategy and advertising activities.

[0465] 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.

[0466] In this invention, the server includes a means for aggregating information on the market exposure and penetration of brand names, trademarks, etc. related to the investment target business, a means for weighting based on the company's advertising budget and the scale of marketing activities, the number of followers of SNS influencers, and the number of engagements on posts, a means for analyzing user emotions using an emotion engine and adjusting the weighting taking into account the strength and direction of those emotions, and a means for generating an evaluation report. This makes it possible to comprehensively evaluate the influence of the company's advertising activities and SNS influencers, as well as user emotions, and accurately evaluate the exposure and penetration of brand names and trademarks.

[0467] An "investment target business" is a business in which a company invests funds in the hope of achieving growth and profits.

[0468] A "brand name" is a name used to identify a particular product or service.

[0469] A "trademark" is a logo or symbol used to identify a particular company or product.

[0470] "Exposure / penetration" refers to the degree to which a brand name or trademark is recognized in the market and by consumers.

[0471] A "company's advertising budget" refers to the total amount of funds a company allocates to its advertising activities.

[0472] The "scale of marketing activities" refers to the scope and influence of a company's marketing activities.

[0473] A "social media influencer" is an individual who has a large following and influence on social media.

[0474] "Number of followers" refers to the number of users who follow a social media influencer's account.

[0475] "Post engagements" refers to the total number of reactions to a social media influencer's post, such as likes, comments, and shares.

[0476] An "emotion engine" is software that analyzes a user's emotions from text data and recognizes their intensity and direction.

[0477] An "evaluation report" is a report that summarizes the exposure and penetration of brand names and trademarks, weighting results, evaluation scores, etc.

[0478] The "evaluation score" is a numerical representation of the overall evaluation of the exposure and penetration of a brand name or trademark.

[0479] MODE FOR CARRYING OUT THE INVENTION

[0480] This invention is a system that comprehensively evaluates the influence of corporate advertising activities and social media influencers, as well as user sentiment, to accurately evaluate the exposure and penetration of brand names and trademarks. Specific embodiments of this system are described below.

[0481] 1. Program Generation

[0482] The server generates a program that takes into account the influence of a company's marketing activities and social media influencers, and collects and analyzes data to evaluate the exposure and penetration of brand names and trademarks.

[0483] 2. Hardware and Software Used

[0484] The server processes and calculates data using the following hardware and software:

[0485] Hardware: High-performance servers

[0486] Software: Data analysis tools, sentiment analysis engine

[0487] 3. Data collection and preprocessing

[0488] The server collects data such as a company's advertising budget, the scale of marketing activities, the number of followers of social media influencers, and the number of post engagements. Specifically, the data is obtained from social media platforms and advertising management tools via APIs. The collected data is then used to create a data frame using Python libraries, which then performs missing value imputation, data normalization, and outlier detection and removal.

[0489] 4. Weighting calculation

[0490] The server calculates weights based on the preprocessed data. Specifically, weights are set according to the size of advertising budgets and marketing activities, and influence is evaluated based on the number of followers and engagement of social media influencers. For example, the larger the advertising budget, the higher the weight.

[0491] 5. Sentiment analysis

[0492] The server uses an emotion engine to analyze the user's emotions. Specifically, it analyzes text data from social media posts and reviews to recognize the strength and direction of the user's emotions. For example, a post saying "I love this product!" is recognized as a strong emotion of joy.

[0493] 6. Overall evaluation and result output

[0494] The server integrates the results of the weighting calculation and sentiment analysis to perform a comprehensive evaluation of the exposure and penetration of the brand name and trademark. Specifically, it adds up the weights of each element to calculate a final evaluation score. The evaluation score can be displayed on a dashboard or generated as a report. For example, brands with high evaluation scores can be displayed in a ranking format.

[0495] Examples of specific examples and prompts

[0496] As a concrete example, consider the following scenario.

[0497] Company A launches a new product and significantly increases its advertising budget. Social media influencer B endorses the product, with 1 million followers and 100,000 engagements on its posts.

[0498] User C gave the product a very high rating, and the emotion engine recognized User C's emotion as "strong delight."

[0499] In this case, the server takes into consideration the advertising activities of Company A and the influence of SNS influencer B, and also takes into account the feelings of User C, and sets a high weighting for Company A's brand.

[0500] Example prompt sentence:

[0501] Considering the advertising activities for Company A's new product and the influence of Social Media Influencer B, generate a program that weights brands based on User C's emotions. Company A's advertising budget is 50 million yen, Social Media Influencer B has 1 million followers, and its posts have 100,000 engagements. User C's emotion is recognized as "strong delight."

[0502] In this way, the server comprehensively evaluates a company's marketing activities, the influence of SNS influencers, and user sentiment, creating a system that accurately evaluates the exposure and penetration of brand names and trademarks.

[0503] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0504] Step 1: Data collection

[0505] The server collects data such as a company's advertising budget, the scale of its marketing activities, the number of followers of social media influencers, and the number of post engagements. Specifically, it uses a specified API to obtain the number of followers and engagements of social media influencers and collects the company's advertising budget data. The input is the raw data obtained from the API, and the output is the collected dataset.

[0506] Step 2: Data Preprocessing

[0507] The server preprocesses the collected data. Specifically, it uses Python libraries to create a data frame, impute missing values, normalize the data, and detect and remove outliers. For example, if the number of followers is missing, it is imputed with the average value. The input is the collected dataset, and the output is the preprocessed dataset.

[0508] Step 3: Calculate weights

[0509] The server calculates weights based on the preprocessed data. Specifically, weights are set according to the size of the advertising budget and marketing activities, and the influence is evaluated based on the number of followers and engagement of social media influencers. For example, if the advertising budget is 10 million yen, the weight is set to 0.8. The input is the preprocessed dataset, and the output is the weighted data.

[0510] Step 4: Sentiment analysis

[0511] The server uses an emotion engine to analyze user emotions. Specifically, it analyzes text data from social media posts and reviews to recognize the strength and direction of the user's emotions. For example, it analyzes a post that says, "I love this product!" and sets the emotion score to 0.9. The input is text data, and the output is an emotion score.

[0512] Step 5: Overall evaluation

[0513] The server combines the results of the weighting calculation and sentiment analysis to perform an overall evaluation of the exposure and penetration of the brand name and trademark. Specifically, it adds up the weights of each element to calculate a final evaluation score. For example, the advertising budget weight of 0.8, the influence of social media influencers of 0.7, and the user sentiment score of 0.9 are added together to arrive at an overall evaluation score of 2.4. The input is the weighted data and sentiment score, and the output is the overall evaluation score.

[0514] Step 6: Output the results

[0515] The server outputs the overall evaluation results. Specifically, it displays the evaluation scores on a dashboard or generates a report. For example, it displays the brands with the highest evaluation scores in a ranking format and generates a detailed report in PDF format. The input is the overall evaluation score, and the output is the dashboard display or PDF report.

[0516] (Application example 2)

[0517] Next, a description will be given of Application Example 2 of Form 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."

[0518] Conventional evaluation systems for brand name and trademark exposure and penetration only consider the influence of corporate marketing activities and social media influencers, and are unable to reflect user sentiment in real time. Therefore, there is a need for more accurate evaluations based on user sentiment.

[0519] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0520] In this invention, the server includes a means for aggregating information on the market exposure and penetration of brand names, trademarks, etc. related to the investment target business, a means for weighting factors such as corporate efforts and social media influencers, a means for analyzing user sentiment in real time, a means for weighting based on the analyzed sentiment, and a means for generating an evaluation report, thereby enabling more accurate brand evaluation that takes user sentiment into account.

[0521] An "investment target business" refers to a business or project in which funds are to be invested.

[0522] A "brand name" is a name used to identify a particular product or service and indicates to consumers the source of that product or service.

[0523] A "trademark" is a mark, logo or symbol used to distinguish goods or services from others.

[0524] "Exposure" refers to how frequently a brand name or trademark appears in the marketplace or media.

[0525] "Penetration" refers to the degree to which a brand name or trademark is recognized and accepted in the market and among consumers.

[0526] "Corporate efforts" refer to the marketing activities, advertising activities, and other efforts undertaken by a company.

[0527] A "SNS influencer" is someone who has a large number of followers on a social networking service and uses their influence to recommend products and services.

[0528] "Weighting" refers to the numerical evaluation of the importance or influence of a particular element.

[0529] "User emotions" refer to the emotions that users have toward a particular brand or trademark, and include emotions such as joy, sadness, and anger.

[0530] "Real-time" means that data and information are processed immediately and reflected without delay.

[0531] An "evaluation report" is a report of the evaluation results prepared based on the exposure and penetration of brand names and trademarks and the weighting results.

[0532] As an embodiment of the present invention, the following system is constructed.

[0533] System Configuration

[0534] The system consists of a server, user devices, and a database of social media influencers. The server aggregates the exposure and penetration of brand names and trademarks, and analyzes and weights the influence of corporate efforts and social media influencers, as well as user emotions, in real time. User devices are devices such as smartphones and tablets, and use cameras and microphones to capture user emotions in real time.

[0535] Hardware and software used

[0536] Hardware: Smartphone camera, microphone

[0537] software

[0538] Data processing and calculation

[0539] 1. Aggregation of brand name and trademark exposure and penetration:

[0540] The server collects data from the internet and analyzes the exposure of brand names and trademarks using web scraping technology and APIs.

[0541] 2. Weighting of corporate efforts and social media influencer influence:

[0542] The server assigns weights based on a company's marketing efforts, advertising budget, and the number of followers and engagement of social media influencers, including retrieving information from a database of social media influencers.

[0543] 3. Real-time analysis of user sentiment:

[0544] The user device captures the user's face and voice using a camera and microphone, analyzes their emotions using the library, and sends the analysis results to the server.

[0545] 4. Emotional weighting:

[0546] The server weights brand names and trademarks based on the results of user sentiment analysis. For example, if a user expresses joy toward a particular brand, the server weights that brand more highly.

[0547] 5. Generate assessment report:

[0548] The server generates a rating report based on the aggregated data and weighted results, which includes a rating score based on brand name and trademark exposure and penetration, company efforts, social media influencer influence, and user sentiment.

[0549] Specific examples

[0550] For example, if a user expresses the emotion of "joy" while using their smartphone, the server will weight a particular brand higher based on the emotion analysis results, which will result in more positive advertisements being displayed to the user.

[0551] Prompt Sentence Examples

[0552] "Develop an application that analyzes user sentiment in real time and displays optimal ads taking into account the influence of social media influencers. Use a library for sentiment analysis and obtain influencer influence from an API."

[0553] The above is a specific embodiment for carrying out the present invention.

[0554] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0555] Step 1:

[0556] The server collects data from the internet and analyzes the exposure of brand names and trademarks. Specifically, it uses web scraping technology and APIs to collect data related to brand names and trademarks from news articles, blogs, social media posts, etc. The input is text data from the internet, and the output is numerical data indicating the exposure of brand names and trademarks.

[0557] Step 2:

[0558] The server assigns weights based on the company's marketing activities and advertising budget, as well as the number of followers and engagement of social media influencers. Specifically, it obtains the number of followers and engagement from a database of social media influencers and calculates weights taking into account the scale of the company's advertising budget and marketing activities. The input is social media influencer data and the company's marketing data, and the output is weighted numerical data.

[0559] Step 3:

[0560] The user device captures the user's face and voice using a camera and microphone, and analyzes their emotions using the library. Specifically, while the user is using their smartphone, the camera takes a picture of their face, and the library analyzes their emotions in real time. The input is the user's face image and voice data, and the output is the emotion analysis results.

[0561] Step 4:

[0562] The server weights brand names and trademarks based on the results of user sentiment analysis. Specifically, it adjusts the weighting of a brand by taking into account the emotions (e.g., joy, sadness, anger, etc.) expressed by the user toward that brand. The input is the sentiment analysis result and initial weighting data for the brand name or trademark, and the output is weighting data adjusted based on the emotions.

[0563] Step 5:

[0564] The server generates an evaluation report based on the aggregated data and weighting results. Specifically, it creates a report that includes an evaluation score based on the exposure and penetration of brand names and trademarks, corporate efforts, the influence of social media influencers, and user sentiment. The inputs are exposure and penetration data, weighting data for companies and social media influencers, and sentiment-based weighting data, and the output is an evaluation report.

[0565] The above are the specific processing steps for carrying out the present invention.

[0566] Example 3

[0567] Next, a description will be given of a third embodiment of the third embodiment. 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."

[0568] Conventional brand evaluation systems have difficulty accurately assessing the exposure and penetration of brand names and trademarks, and do not reflect user sentiment. As a result, they are not very reliable as reference information for investment decisions.

[0569] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0570] In this invention, the server includes means for collecting data on brand names and trademarks from various sources on the Internet, means for analyzing the collected data using natural language processing technology, means for calculating the exposure and penetration of brand names and trademarks, means for weighting each data source according to its importance, means for analyzing user sentiment and reflecting the results in an evaluation score, and means for generating an evaluation report based on the final evaluation score. This makes it possible to accurately evaluate the exposure and penetration of brand names and trademarks and to calculate an evaluation score that reflects user sentiment.

[0571] "Various sources on the Internet" refers to information sources that are publicly available on the Internet, such as websites, social media, news articles, and blogs.

[0572] "Brand names and trademarks" refers to names, logos, and symbols used to identify particular products or services.

[0573] "Data collection methods" refers to the techniques and methods used to obtain the required data from sources on the Internet.

[0574] "Natural language processing technology" refers to computer technology for analyzing text data and understanding meaning and emotions.

[0575] "Exposure and penetration" refers to the degree to which a brand name or trademark is recognized and influenced by the market and consumers.

[0576] "Weighting methods" refers to methods or techniques for adjusting the degree to which each data source influences the evaluation according to its importance.

[0577] "Means for analyzing user emotions" refers to technology for analyzing the emotions that users express toward a particular brand and evaluating their strength and direction.

[0578] An "evaluation score" is an index that quantifies the value of a brand name or trademark.

[0579] "Means for generating an assessment report" refers to the technology or method for compiling assessment scores and other assessment results and outputting them in a report format.

[0580] MODE FOR CARRYING OUT THE INVENTION

[0581] This invention relates to a system for evaluating the exposure and penetration of brand names and trademarks and calculating an evaluation score that reflects user sentiment. Specific embodiments of this system will be described below.

[0582] Data collection

[0583] The server collects data on brand names and trademarks from various sources on the Internet, specifically, text data from websites, social media, news articles, blogs, etc. This collection is done using a Python library.

[0584] Data analysis

[0585] The server analyzes the collected text data using natural language processing technology, specifically using Python to tokenize the text data, perform sentiment analysis, and extract keywords.

[0586] Exposure and penetration calculations

[0587] The server calculates the exposure and penetration of brand names and trademarks based on the analyzed data. For example, it calculates how often a particular brand is mentioned on social media or how often it is featured in news articles. This calculation is performed using MySQL (registered trademark) as the database management system (DBMS).

[0588] Weighting and evaluation score calculation

[0589] The server calculates a reputation score for the brand name or trademark based on exposure and penetration, weighting each data source according to its importance. For example, social media posts may be given less weight than news articles. This weighting is done using machine learning algorithms.

[0590] Evaluation by Emotion Engine

[0591] The server uses an emotion engine to analyze the user's emotions and reflects the results in the evaluation score. The emotion engine takes into account the strength and direction of the emotion the user shows toward a particular brand. This emotion analysis uses a specified API.

[0592] Generate an assessment report

[0593] The server generates a rating report based on the final rating score. This report includes the exposure and penetration of the brand name and trademark, weighting results, and the rating score from the sentiment engine. The generated report is output in PDF format and can be used as reference information for investment decisions. A Python library is used for this.

[0594] Examples and prompts

[0595] Specific examples

[0596] For example, suppose a certain brand "XYZ" is frequently mentioned on social media and frequently featured in news articles. User sentiment analysis reveals that users express strong feelings of joy toward "XYZ." In this case, the server will highly evaluate the exposure and penetration of "XYZ" and calculate a high evaluation score based on the results of the emotion engine. The final evaluation report will include a high evaluation score for "XYZ."

[0597] Prompt Sentence Examples

[0598] "Evaluate the exposure and penetration of the brand name 'XYZ' and calculate a rating score that reflects user sentiment using a sentiment engine. Generate a final rating report in PDF format."

[0599] In this way, the server realizes a system that evaluates the value of a brand name or trademark and outputs the results as a report. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0600] Step 1:

[0601] The server collects data related to brand names and trademarks from various sources on the Internet. Specifically, it obtains text data from websites, social media, news articles, blogs, etc. A Python library is used for this collection. A list of URLs to be collected is required as input, and the collected text data is obtained as output. Specifically, the server cycles through the specified URL list, obtains HTML content, and extracts text data from the HTML.

[0602] Step 2:

[0603] The server analyzes the collected text data using natural language processing technology. Specifically, it uses Python to tokenize the text data, perform sentiment analysis, and extract keywords. The collected text data is required as input, and the analyzed sentiment score and keyword list are obtained as output. Specifically, the server tokenizes the collected text data, calculates the sentiment score for each token, and extracts keywords.

[0604] Step 3:

[0605] The server calculates the exposure and penetration of brand names and trademarks based on the analyzed data. Specifically, it calculates how often a particular brand is mentioned on social media and how often it is featured in news articles. This calculation uses MySQL as the database management system (DBMS). The inputs are the analyzed sentiment scores and keyword lists, and the output is the exposure and penetration of brand names and trademarks. Specifically, the server counts the number of times a brand name appears extracted from each data source and stores the results in a database.

[0606] Step 4:

[0607] The server calculates the reputation score for the brand name or trademark based on its exposure and penetration. At this time, it weights each data source according to its importance. For example, social media posts may be given less weight than news articles. This weighting is done using a machine learning algorithm. The input is the exposure and penetration of the brand name or trademark, and the output is a weighted reputation score. Specifically, the server sets the importance of each data source and calculates the overall reputation score by multiplying the exposure and penetration by the weight.

[0608] Step 5:

[0609] The server uses an emotion engine to analyze the user's emotions and reflects the results in the evaluation score. The emotion engine takes into account the strength and direction of the emotion the user expresses toward a particular brand. A specified API is used for this emotion analysis. The input is the user's emotion data, and the output is the emotion analysis result. Specifically, the server acquires the user's emotion data, calculates the emotion score using the emotion engine, and adds or subtracts that score from the evaluation score.

[0610] Step 6:

[0611] The server generates a rating report based on the final rating score. This report includes the exposure and penetration of the brand name and trademark, weighting results, and the rating score from the sentiment engine. The generated report is output in PDF format and used as reference information for investment decisions. A Python library is used for this. The final rating score is required as input, and a PDF rating report is obtained as output. Specifically, the server generates a report summarizing the rating scores and saves it in PDF format.

[0612] (Application example 3)

[0613] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0614] Conventional brand valuation systems were unable to fully reflect user sentiment when assessing the exposure and penetration of brand names and trademarks. This made it difficult to accurately assess the true value of a brand, and the system was unreliable as reference information for investment decisions. Furthermore, the generation of valuation reports did not involve advanced analysis using AI models, which led to issues with the accuracy and reliability of the valuation results.

[0615] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes means for aggregating information on the market exposure and penetration of brand names, trademarks, etc. related to the investment target business, means for weighting based on factors such as corporate efforts and influencers on social networking services, means for generating an evaluation report, means including a sentiment analysis engine for analyzing user sentiment, means for calculating an evaluation score reflecting user sentiment, and means for generating an evaluation report using a generative AI model. This enables accurate brand evaluation that reflects user sentiment, improving the reliability of the information as reference for investment decisions.

[0616] "Investment target business" refers to the company or project that is the target of investment.

[0617] "Brand names and trademarks" refer to names, logos, symbols, etc. that identify specific companies or products.

[0618] "Exposure / Penetration" is an indicator that shows how well a brand name or trademark is recognized by the market and consumers, or how widely it is spread.

[0619] "Corporate efforts" refers to the marketing and promotional activities that companies undertake to spread their brands and products in the market.

[0620] A "social networking service influencer" is someone who has a large number of followers on social media and whose words and actions have a significant impact on other users.

[0621] "Weighting" refers to assigning numerical values ​​to different elements or data based on their importance or influence.

[0622] An "evaluation report" refers to a report summarizing evaluation results based on the exposure and penetration of brand names and trademarks, weighting results, user sentiment, etc.

[0623] An "emotion analysis engine" refers to software or algorithms that analyze users' text data and behavioral data to identify their emotions.

[0624] An "evaluation score" is a numerical indicator of the value of a brand name or trademark, and is calculated based on exposure, penetration, and user sentiment.

[0625] "Generative AI model" means a model that uses artificial intelligence to analyze data and generate assessment reports or other outputs.

[0626] The system for implementing this invention consists of three main elements: a server, a terminal, and a user. The following explains how each element functions.

[0627] server

[0628] The server includes the following means:

[0629] 1. Data aggregation method: Aggregate information on the market exposure and penetration of brand names, trademarks, etc. related to the investment target business. This method involves collecting data using web scraping and APIs.

[0630] 2. Weighting method: Weighting is based on the company's efforts and the exposure and penetration of influencers on social networking services. For example, it evaluates how much engagement a particular influencer's post received.

[0631] 3. Sentiment Analysis Engine: Software for analyzing user sentiment, using natural language processing libraries.

[0632] 4. Evaluation score calculation method: Calculate an evaluation score that reflects the user's emotions. Calculate the brand's evaluation score based on the results of the sentiment analysis engine.

[0633] 5. Generative AI model: Generating evaluation reports using a generative AI model. For example, using a generative AI model such as GPT-3, we can automatically generate evaluation reports.

[0634] Terminal

[0635] A device is a device used by a user, such as a smartphone or tablet. A device includes the following features:

[0636] 1. Data entry function: Provides an interface for users to enter their feelings and feedback about the brand.

[0637] 2. Real-time analysis function: User input data is sent to the server in real time and sentiment analysis is performed.

[0638] User

[0639] Users are responsible for providing their feelings and feedback about the brand. Through their devices, users can:

[0640] 1. Emotional input: Enter your feelings and opinions about the brand in text format.

[0641] 2. Providing feedback: Providing feedback on the evaluation report to improve the accuracy of the system.

[0642] Specific examples

[0643] For example, if a user comments, "This brand is great!", the comment is sent to the server via the device. The server uses a sentiment analysis engine to analyze the comment and rate it as a positive sentiment. Then, it uses a generative AI model to generate a rating report that includes the rating results.

[0644] Prompt Sentence Examples

[0645] "Analyze the sentiment expressed by users towards a particular brand and generate a rating score for that brand. For example, if a user leaves a positive comment about a particular brand, calculate a rating score that reflects that sentiment."

[0646] In this way, accurate brand evaluation that reflects the user's feelings becomes possible, improving the reliability of the information as reference for investment decisions.

[0647] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0648] Step 1:

[0649] The server uses web scraping and APIs to aggregate information on the market exposure and penetration of brand names, trademarks, etc. related to the investment target business. Data collected from websites and social media is used as input, and exposure and penetration data for each brand is generated as output.

[0650] Step 2:

[0651] The server weights the company's efforts and influencers of social networking services based on the aggregated exposure and penetration data, using the exposure and penetration data and influencer engagement data as inputs and generating weighted exposure and penetration data as output.

[0652] Step 3:

[0653] Users input their feelings and feedback about the brand in text format through a terminal. The system uses the user's comments and feedback as input and generates text data as output.

[0654] Step 4:

[0655] The terminal transmits the user's input data to the server in real time, using the user's text data as input and generating the text data transmitted to the server as output.

[0656] Step 5:

[0657] The server uses a sentiment analysis engine to analyze the user's text data and identify its sentiment, using the user's text data as input and generating a sentiment score as output.

[0658] Step 6:

[0659] The server calculates a rating score that reflects the user's sentiment based on the sentiment score. It uses the sentiment score and weighted exposure and penetration data as inputs and generates a rating score as output.

[0660] Step 7:

[0661] The server uses a generative AI model to generate an evaluation report based on the evaluation scores, using the evaluation scores as input and generating the evaluation report as output.

[0662] Step 8:

[0663] The server transmits the generated evaluation report to the terminal and provides it to the user. The server uses the evaluation report as input and generates an evaluation report that is provided to the user as output.

[0664] 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.

[0665] 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> ) 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.

[0666] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[0667] 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.

[0668] [Second embodiment]

[0669] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0670] 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.

[0671] 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).

[0672] 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.

[0673] 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.

[0674] 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).

[0675] 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.

[0676] 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.

[0677] 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.

[0678] 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.

[0679] 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.

[0680] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0681] "Example 1"

[0682] One embodiment of the present invention is a system equipped with a means for aggregating information on the market exposure and penetration of brand names, trademarks, etc. related to investment target businesses. Specifically, the system collects information from the Internet and calculates the exposure and penetration of brand names, trademarks, etc. from that information. This calculation is performed based on information such as how often a brand name, trademark, etc. is mentioned on websites or social media, or how many users recognize the brand name, trademark, etc.

[0683] "Example 2"

[0684] Furthermore, it also has a means of weighting factors such as corporate efforts and those of social media influencers. Specifically, weighting is performed by taking into account the influence of corporate marketing and advertising activities, recommendations by social media influencers, etc., on the exposure and penetration of brand names and trademarks. This weighting is based on, for example, the scale of a company's advertising budget and marketing activities, the number of followers of social media influencers, and the number of engagements on their posts.

[0685] "Example 3"

[0686] It also has a means for generating an evaluation report. Specifically, it evaluates the value of brand names, trademarks, etc. based on the above exposure / penetration and weighting results, and outputs the results as a report. This report is used as reference information for investment decisions. For example, the report may include the exposure / penetration of brand names, trademarks, etc., the weighting results, and an evaluation score based on these.

[0687] The processing flow of each embodiment will be described below.

[0688] "Example 1"

[0689] Step 1: The system collects information from the internet by scraping data from websites and social media, obtaining data through APIs, etc.

[0690] Step 2: From the collected information, calculate the exposure and penetration of the brand name, trademark, etc. This calculation is based on information such as how often the brand name, trademark, etc. is mentioned on websites and social media, and how many users recognize the brand name, trademark, etc.

[0691] "Example 2"

[0692] Step 1: Weighting is performed on the exposure and penetration of brand names, trademarks, etc., taking into account the influence of corporate marketing and advertising activities, recommendations by social media influencers, etc.

[0693] This weighting is based on factors such as the company's advertising budget and the scale of its marketing activities, the number of followers the social media influencer has, and the number of engagements on their posts.

[0694] "Example 3"

[0695] Step 1: Based on the above exposure, penetration and weighting results, evaluate the value of the brand name, trademark, etc.

[0696] Step 2: The evaluation results are output as a report. This report can be used as reference information for investment decisions. The report includes the exposure and penetration of brand names and trademarks, weighting results, and an evaluation score based on these.

[0697] Example 1

[0698] Next, a description will be given of Example 1 of Form 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."

[0699] Previous methods for assessing the exposure and penetration of brand names, trademarks, etc. required manual data collection and analysis, which was time-consuming and labor-intensive. Furthermore, there was a lack of means to properly assess the influence of corporate efforts and influencers on social networking services, making accurate assessments difficult. This made it difficult to provide reliable information for investment decisions.

[0700] 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.

[0701] In this invention, the server includes means for receiving prompt text, means for collecting information on the Internet, means for analyzing the collected information, means for calculating the exposure and penetration of brand names, trademarks, etc., means for providing the calculation results, means for weighting factors such as those due to corporate efforts and influencers on social networking services, and means for generating an evaluation report. This makes it possible to automatically and accurately evaluate the exposure and penetration of brand names, trademarks, etc., and provide reliable information for investment decisions.

[0702] A "prompt sentence" is the text of an instruction or question that a user enters into a system.

[0703] "Information on the Internet" refers to data that is publicly available on the Internet, such as on websites and social networking services.

[0704] "Means of collection" refers to technology that automatically obtains information on the Internet using web crawlers and APIs.

[0705] "Means of analysis" refers to techniques that use natural language processing and data mining techniques to analyze collected information and extract meaning and patterns.

[0706] "Exposure and penetration of brand names, trademarks, etc." refers to the degree to which a particular brand name or trademark is mentioned and recognized on the Internet.

[0707] The "means of calculation" refers to the technology that quantifies the exposure and penetration of specific brand names and trademarks based on collected and analyzed data.

[0708] "Means of providing" refers to the technology for displaying the calculation results to the user or outputting them as a report.

[0709] "Corporate efforts" refer to the marketing and promotional activities that a company undertakes to increase brand awareness and reputation.

[0710] "Social networking service influencers" are individuals or organizations that have many followers on social media and have a strong ability to disseminate information.

[0711] "Weighting methods" are techniques that assign appropriate weights to the exposure and penetration of brand names and trademarks, taking into account the influence of corporate efforts and social media influencers.

[0712] An "evaluation report" is a document summarizing the evaluation results, which is created based on the exposure and penetration of brand names and trademarks and the weighting results.

[0713] This invention relates to a system for automatically evaluating the exposure and penetration of brand names, trademarks, etc. related to investment target businesses. This system includes elements of a server, a terminal, and a user.

[0714] First, the user inputs a prompt sentence using a terminal. For example, the prompt sentence is "Please calculate the exposure and penetration of ABC brand." This prompt sentence is sent to the server.

[0715] When the server receives the prompt, it launches a web crawler to collect information from websites and social networking services based on the specified keyword "ABC brand."

[0716] The collected data is analyzed by the server using a natural language processing (NLP) library. During the analysis process, mentions related to brand names, trademarks, etc. are extracted and the number of mentions is counted. Sentiment analysis is also performed and a rating is assigned as positive, negative, or neutral.

[0717] The server then calculates the exposure and penetration of brand names, trademarks, etc. based on the analysis results. The calculation uses the number of mentions and the results of sentiment analysis. In addition, weighting is performed taking into account the influence of corporate efforts and influencers on social networking services.

[0718] The calculation results are generated as an evaluation report. The evaluation report includes an evaluation score based on the exposure and penetration of the brand name, trademark, etc., and the weighting results. The server provides this evaluation report to the user. For example, the result displayed may be, "The exposure and penetration of ABC brand is 85 points."

[0719] This system allows users to automatically and accurately evaluate the exposure and penetration of brand names, trademarks, etc., providing reliable information for investment decisions.

[0720] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0721] Step 1:

[0722] The user uses a terminal to input a prompt sentence. For example, the user inputs the prompt sentence "Please calculate the exposure and penetration of ABC brand." The input prompt sentence is sent to the server. The input is the prompt sentence, and the output is the transmission of the prompt sentence to the server.

[0723] Step 2:

[0724] The server receives the prompt sentence, parses it, and extracts the specified keyword (in this case, "ABC brand"). The input is the prompt sentence, and the output is the extracted keyword.

[0725] Step 3:

[0726] The server launches a web crawler to collect information on the Internet based on the extracted keywords. Specifically, it collects data related to "ABC Brand" from websites and social networking services. The input is the extracted keywords, and the output is the collected data.

[0727] Step 4:

[0728] The server analyzes the collected data using a natural language processing (NLP) library. Specifically, it extracts mentions related to "ABC Brand" from the text data and counts the number of mentions. It also performs sentiment analysis and assigns a positive, negative, or neutral rating. The input is the collected data, and the output is the number of mentions and the results of the sentiment analysis.

[0729] Step 5:

[0730] The server calculates the exposure and penetration of brand names, trademarks, etc. based on the analysis results. The calculation uses the number of mentions and the results of sentiment analysis. In addition, weighting is performed taking into account the influence of corporate efforts and influencers on social networking services. The input is the number of mentions and the results of sentiment analysis, and the output is an exposure and penetration score.

[0731] Step 6:

[0732] The server generates a rating report based on the calculation results. The rating report includes a rating score based on the exposure and penetration of brand names, trademarks, etc. and the weighted results. The input is the exposure and penetration score, and the output is the rating report.

[0733] Step 7:

[0734] The server provides the generated evaluation report to the user. For example, it displays the result "The exposure and penetration of ABC brand is 85 points." The input is the evaluation report, and the output is providing the result to the user.

[0735] (Application example 1)

[0736] Next, a description will be given of Application Example 1 of Form 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."

[0737] Conventional systems for assessing the exposure and penetration of brand names and trademarks have difficulty collecting information from the internet in real time and immediately understanding a brand's exposure and penetration. Furthermore, they lacked the ability to send notifications when exposure and penetration exceeded a certain threshold, making it difficult to quickly adapt marketing strategies. Furthermore, they lacked the ability to generate prompt messages using a generative AI model, leaving advertisers with a lack of guidance for taking specific actions.

[0738] 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.

[0739] In this invention, the server includes means for aggregating information on the market exposure and penetration of brand names, trademarks, etc. related to investment target businesses, means for weighting factors such as corporate efforts and social media influencers, means for generating evaluation reports, means for collecting information on the Internet, means for calculating the exposure and penetration of brand names, trademarks, etc., means for monitoring the exposure and penetration in real time, means for sending notifications when the exposure and penetration exceed a specific threshold, and means for generating prompt messages using a generative AI model. This enables brand exposure and penetration to be grasped in real time, enabling the rapid development and implementation of marketing strategies.

[0740] An "investment target business" is a business that aims to make a profit by investing funds.

[0741] A "brand name" is a name used to identify a particular product or service.

[0742] A "trademark" is a mark or logo that distinguishes a particular product or service from others.

[0743] "Exposure / penetration" refers to the degree to which a brand name or trademark is recognized in the market and by consumers.

[0744] "Corporate efforts" are the activities that companies undertake to penetrate their brands and products into the market.

[0745] A "SNS influencer" is an individual who has a large number of followers and influence on a social networking service.

[0746] "Weighting" refers to the numerical evaluation of the importance or influence of a particular element.

[0747] An "evaluation report" is a report summarizing the evaluation results regarding the exposure and penetration of a brand name or trademark.

[0748] "Information on the Internet" refers to data that exists on online platforms such as websites and social media.

[0749] "Real-time" means that data and information are processed immediately and provided without delay.

[0750] A "notification" is an alert or message sent to a user when a specific condition is met.

[0751] A "generative AI model" is an algorithm or program that uses artificial intelligence to automatically perform specific tasks.

[0752] A "prompt" is an instruction or question input to a generative AI model.

[0753] A system for carrying out this invention has the following configuration: A server includes means for aggregating information on the market exposure and penetration of brand names, trademarks, etc. related to investment target businesses, means for weighting factors such as corporate efforts and social media influencers, means for generating evaluation reports, means for collecting information on the Internet, means for calculating the exposure and penetration of brand names, trademarks, etc., means for monitoring the exposure and penetration in real time, means for sending a notification when the exposure and penetration exceeds a specific threshold, and means for generating prompt sentences using a generative AI model.

[0754] Program processing explanation

[0755] The server first collects information from the Internet. Specifically, it uses the requests library to obtain the content of the web page from the specified URL and extracts the text from the web page. Next, it uses regular expressions to count how often the brand name or trademark is mentioned in the extracted text. Based on this count, it calculates the exposure and penetration of the brand name or trademark.

[0756] The calculated exposure and penetration levels are monitored in real time, and if a certain threshold is exceeded, a notification is sent to the user, allowing them to take immediate action. Furthermore, a generative AI model is used to generate prompts and suggest specific actions to the user.

[0757] The hardware used is a server and a smartphone with an internet connection, and the software uses Python and its libraries. The generative AI model used is, for example, OpenAI's GPT-3.

[0758] Specific examples

[0759] For example, when monitoring the exposure and penetration of Brand A, Brand B, and Brand C, the server collects and calculates in real time how often these brand names are mentioned on social media and websites. If the exposure and penetration exceeds a certain threshold, a notification is sent to the user's smartphone. Furthermore, a generative AI model is used to generate prompt sentences such as the following:

[0760] Prompt Sentence Examples

[0761] "Monitor Brand A's visibility and send a notification when it reaches 1000 social media mentions."

[0762] In this way, users can grasp the brand's exposure and penetration in real time, enabling them to quickly plan and execute marketing strategies.

[0763] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0764] Step 1:

[0765] The server retrieves the web page content from the specified URL. Specifically, it uses the requests library to send an HTTP request and retrieve the HTML data of the web page. The input is a list of URLs, and the output is the HTML data corresponding to each URL.

[0766] Step 2:

[0767] The server extracts text from the retrieved HTML data. Specifically, it parses the HTML and extracts the text content. The input is the HTML data, and the output is the extracted text.

[0768] Step 3:

[0769] The server counts how many times brand names and trademarks are mentioned in the extracted text. Specifically, it counts the number of times a brand name or trademark appears using regular expressions. The input is text data and a list of brand names, and the output is the number of times each brand name appears.

[0770] Step 4:

[0771] The server calculates the exposure and penetration of brand names and trademarks based on the counting results. Specifically, it quantifies the exposure and penetration based on the number of appearances. The input is the number of appearances of the brand name, and the output is the numerical value of the exposure and penetration.

[0772] Step 5:

[0773] The server monitors the calculated exposure and penetration in real time. Specifically, it sends a notification when the exposure and penetration exceeds a certain threshold. The input is the exposure and penetration value and the threshold, and the output is a notification message.

[0774] Step 6:

[0775] The server generates prompts using a generative AI model. Specifically, it generates prompts that suggest specific actions to the user based on exposure and penetration data. The input is exposure and penetration data, and the output is the generated prompt.

[0776] Step 7:

[0777] The user receives the notification and prompt text sent from the server and plans and executes an appropriate marketing strategy. Specifically, based on the notification message and prompt text, the user takes action according to the brand's exposure and penetration. The input is the notification message and prompt text, and the output is the user's action.

[0778] Example 2

[0779] Next, a description will be given of Example 2 of Form 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."

[0780] Conventional methods for assessing the exposure and penetration of brand names and trademarks do not adequately take into account factors such as a company's advertising budget, the scale of marketing activities, or the influence of social media influencers, making accurate assessments difficult. Furthermore, there was a lack of specific proposals for improving marketing strategies based on the assessment results.

[0781] 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.

[0782] In this invention, the server includes: means for aggregating information on the market exposure and penetration of brand names, trademarks, etc. related to the investment target business; means for collecting data such as a company's advertising budget and the scale of its marketing activities, and the number of followers and post engagements of social media influencers; means for analyzing the collected data and weighting the exposure and penetration of the brand names and trademarks; means for generating an evaluation report; and means for generating prompt sentences to be input into the generative AI model. This enables accurate brand evaluation that takes into account a company's advertising budget, the scale of its marketing activities, and the influence of social media influencers.

[0783] "Investment target business" refers to any business that aims to make a profit by investing funds.

[0784] "Brand name" refers to a name used to identify a particular product or service.

[0785] "Trademark" refers to a logo, symbol, design, etc. used to identify a particular product or service.

[0786] "Exposure and penetration" refers to the degree to which a brand name or trademark is recognized in the market and by consumers.

[0787] A "company's advertising budget" refers to the total amount of funds a company plans to spend on advertising activities.

[0788] The "scale of marketing activities" refers to the scope and influence of a company's marketing activities.

[0789] A "SNS influencer" refers to an individual who has a large number of followers and influence on a social networking service.

[0790] "Number of followers" refers to the number of users who follow a social media influencer's account.

[0791] "Engagement count" refers to the total number of user reactions (likes, comments, shares, etc.) to a social media influencer's post.

[0792] "Means of collecting data" refers to the methods and tools used to obtain the required data.

[0793] "Means of analyzing data" refers to the methods and tools used to process collected data and convert it into meaningful information.

[0794] "Weighting means" refers to a method or tool for assigning importance to a particular element.

[0795] "Means for generating an evaluation report" refers to methods and tools for creating a report summarizing the evaluation results based on the analysis results.

[0796] A "generative AI model" refers to a model that has been trained using artificial intelligence to perform a specific task.

[0797] A "prompt sentence" refers to an instruction sentence to be input into a generative AI model.

[0798] This invention is a system that generates an evaluation report by weighting the exposure and penetration of brand names and trademarks, taking into account the influence of corporate marketing activities and social media influencers. Specific embodiments of this system are described below.

[0799] System configuration

[0800] This system consists of three main components: a server, a terminal, and a user. The server collects data, analyzes it, calculates weights, and generates evaluation reports. The terminal provides an interface for users to access the system and check the results. The user operates the system and inputs the necessary data.

[0801] Hardware and software used

[0802] The server uses a specified API for data collection, a Python library for data analysis, and a tool for outputting data in JSON format and displaying it on a dashboard to generate an evaluation report.

[0803] Data collection

[0804] The server collects data such as a company's advertising budget and the scale of its marketing activities, as well as the number of followers and post engagements of social media influencers. Specifically, it calls an API to obtain the company's advertising campaign data and uses an API to obtain the number of followers and engagements of social media influencers.

[0805] Data analysis

[0806] The server analyzes the collected data. This analysis involves data cleansing (completion of missing values ​​and removal of outliers) and data normalization (scaling). Specifically, a Python library is used to create a data frame, complement missing values, and normalize the data.

[0807] Weighting Calculation

[0808] Based on the analyzed data, the server assigns weights to the exposure and penetration of brand names and trademarks. This weighting is calculated taking into account the company's advertising budget and the scale of its marketing activities, as well as the number of followers and engagement of social media influencers. The specific calculation formula is as follows:

[0809] Weight = (Advertising budget score 0.5) + (Marketing activity score 0.3) + (Social media influencer score 0.2)

[0810] Here, each score is a normalized value.

[0811] Generate an assessment report

[0812] The server generates a rating report based on the calculated weighting results. This rating report includes the exposure and penetration of the brand name or trademark and a rating score based on the weighting results. The rating report is output in JSON format and displayed on the dashboard.

[0813] Specific examples

[0814] For example, suppose that Company A has an annual advertising budget of 100 million yen, and Social Media Influencer B has 1 million followers and 100,000 engagements on its posts. In this case, the server would operate as follows:

[0815] 1. The server calls a specified API to obtain Company A's advertising campaign data.

[0816] 2. The server uses a specified API to obtain the number of followers and engagements of influencer B.

[0817] 3. The server analyzes the acquired data using the library, imputes missing values, and normalizes them using the library.

[0818] 4. The server uses a weighting formula to assign weights to the exposure and penetration of the brand name or trademark.

[0819] 5. The server outputs the calculation results in JSON format and displays them on the dashboard.

[0820] An example of a prompt to input to a generative AI model is as follows:

[0821] "Company A's annual advertising budget is 100 million yen, and social media influencer B has 1 million followers and 100,000 engagements on their posts. Based on this data, please assign weights to the exposure and penetration of brand names and trademarks."

[0822] In this way, the server provides a system that evaluates the exposure and penetration of brand names and trademarks by weighting the influence of corporate marketing activities and social media influencers.

[0823] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0824] Step 1:

[0825] The server collects data such as a company's advertising budget and the scale of its marketing activities, as well as the number of followers and post engagements of social media influencers. Specifically, it calls an API to obtain the company's advertising campaign data and uses an API to obtain the number of followers and engagements of social media influencers. The input is the raw data obtained from the API, and the output is the collected dataset.

[0826] Step 2:

[0827] The server analyzes the collected data. This analysis involves cleansing the data (filling in missing values ​​and removing outliers) and normalizing (scaling) it. Specifically, a Python library is used to create a data frame and fill in missing values. A Python library is also used to normalize the data. The input is the collected dataset, and the output is the cleansed and normalized data.

[0828] Step 3:

[0829] The server then assigns weights to the exposure and penetration of brand names and trademarks based on the analyzed data. The specific calculation formula is as follows:

[0830] Weight = (Advertising budget score 0.5) + (Marketing activity score 0.3) + (Social media influencer score 0.2)

[0831] Here, each score is a normalized value: the input is the cleansed and normalized data, and the output is a weighted evaluation score.

[0832] Step 4:

[0833] The server generates an evaluation report based on the calculated weighting results. The evaluation report is output in JSON format and displayed on a dashboard. Specifically, a report containing the evaluation scores is generated and made accessible to users. The input is the weighted evaluation score, and the output is the evaluation report.

[0834] Step 5:

[0835] The server generates prompts to be input to the generative AI model. Specifically, it generates prompts like the following based on data such as the company's advertising budget and the number of followers and engagement of social media influencers:

[0836] "Company A's annual advertising budget is 100 million yen, and social media influencer B has 1 million followers and 100,000 engagements on their posts. Based on this data, please assign weights to the exposure and penetration of brand names and trademarks."

[0837] The input is data about companies and social media influencers, and the output is the generated prompt sentence.

[0838] (Application example 2)

[0839] Next, a description will be given of Application Example 2 of Form 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."

[0840] Traditional methods for evaluating advertising campaigns make it difficult to comprehensively consider a company's advertising budget, the scale of its marketing activities, and the influence of social media influencers, resulting in insufficient optimization of advertising strategies. Real-time evaluation is also difficult, making it unsuitable for the modern marketing environment, which requires rapid strategic changes. This results in the inability to maximize advertising effectiveness and reduces the efficiency of a company's investment.

[0841] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0842] In this invention, the server includes means for aggregating information on the market exposure and penetration of brand names, trademarks, etc. related to the investment target business, means for weighting factors such as corporate efforts and SNS influencers, means for generating an evaluation report, means for evaluating the effectiveness of advertising campaigns in real time, and means for optimizing advertising strategies taking into account the influence of SNS influencers. This makes it possible to comprehensively evaluate the effectiveness of a company's advertising campaigns in real time and to formulate optimal advertising strategies taking into account the influence of SNS influencers.

[0843] An "investment target business" is a business in which a company invests funds in the hope of achieving growth and profits.

[0844] A "brand name" is a name used to identify a specific product or service, and serves to assure consumers of the reliability and quality of that product or service.

[0845] A "trademark" is a mark, logo, or symbol used by a company to distinguish its products or services from those of other companies.

[0846] "Exposure and penetration" indicates the degree to which a brand name or trademark is recognized and accepted by the market and consumers.

[0847] "Corporate efforts" refers to the marketing and advertising activities that companies undertake to increase awareness and sales of their products and services.

[0848] A "social media influencer" is someone who has a large number of followers on a social networking service and uses their influence to recommend specific products or services.

[0849] "Weighting" refers to the numerical evaluation of the importance or influence of a particular element or data.

[0850] An "evaluation report" is a report prepared based on specific data and information, and includes evaluation and analysis results.

[0851] An "advertising campaign" is a series of advertising activities undertaken to increase awareness and sales of a particular product or service.

[0852] "Real-time" refers to data and information being processed and analyzed as soon as it is generated.

[0853] An "advertising strategy" refers to the advertising policies and methods that a company plans to use to effectively promote its products and services in the market.

[0854] The system for implementing this invention consists of three main elements: a server, a terminal, and a user. The server includes a means for aggregating the extent of exposure and penetration of brand names and trademarks related to investment target businesses in the market, a means for weighting the influence of corporate efforts and SNS influencers, a means for generating evaluation reports, a means for evaluating the effectiveness of advertising campaigns in real time, and a means for optimizing advertising strategies taking into account the influence of SNS influencers.

[0855] Program processing explanation

[0856] The server first aggregates the exposure and penetration of brand names and trademarks. This is done using web scraping technology and social media analysis tools. Specific software used is Python and social media APIs.

[0857] Next, we weight the influence of corporate efforts and social media influencers. We do this based on the size of a company's advertising budget and marketing activities, as well as the number of followers and engagement of social media influencers. We use Python as a data analysis tool.

[0858] To generate an evaluation report, an evaluation score is calculated based on the aggregated data and weighted results, using a data visualization tool.

[0859] To evaluate the effectiveness of the advertising campaign in real time, the server uses real-time data processing techniques, specifically, a stream processing framework.

[0860] Finally, we optimize advertising strategies by taking into account the influence of social media influencers, using machine learning models and machine learning libraries such as TensorFlow.

[0861] Specific examples

[0862] For example, consider a case where the advertising budget is 5 million yen, the scale of marketing activities is 80, the number of followers of social media influencers is 200,000 and 150,000, and the engagement numbers are 5,000 and 3,000. Based on this data, the server calculates the weighting and optimizes the advertising strategy.

[0863] Example prompts to input to a generative AI model:

[0864] If the advertising budget is 5 million yen, the scale of marketing activities is 80, the number of followers of social media influencers is 200,000 and 150,000, and the engagement numbers are 5,000 and 3,000, calculate the weightings to optimize the advertising strategy.

[0865] In this way, the server comprehensively evaluates the effectiveness of a company's advertising campaign in real time and helps develop optimal advertising strategies that take into account the influence of social media influencers.

[0866] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0867] Step 1:

[0868] The server aggregates the exposure and penetration of brand names and trademarks. Specifically, it collects data from the internet using web scraping technology and social media analysis tools. It receives keywords related to brand names and trademarks as input and generates a list of web pages and social media posts containing those keywords as output.

[0869] Step 2:

[0870] The server uses the aggregated data to weight the influence of corporate efforts and social media influencers. Specifically, it receives inputs such as a company's advertising budget and the scale of its marketing activities, as well as the number of followers and engagement of social media influencers, and processes this data using Python. As output, it generates a weighted score for each factor.

[0871] Step 3:

[0872] The server generates an evaluation report based on the weighting results. Specifically, it receives the aggregated data and weighted scores as input, calculates the evaluation score using a data visualization tool, and generates an evaluation report as output, saved as a PDF file containing graphs and charts.

[0873] Step 4:

[0874] The server evaluates the effectiveness of the advertising campaign in real time. Specifically, it uses real-time data processing technology to monitor the progress and effectiveness of the advertising campaign. As input, it receives and processes the data stream of the advertising campaign. As output, it generates real-time evaluation results and displays them on a dashboard.

[0875] Step 5:

[0876] The server optimizes advertising strategies by taking into account the influence of social media influencers. Specifically, it uses a machine learning model to propose optimal advertising strategies. As input, it receives evaluation reports and real-time evaluation results, and trains the model using TensorFlow. As output, it generates an optimized advertising strategy and proposes it to the company.

[0877] In this way, the server comprehensively evaluates the effectiveness of a company's advertising campaign in real time and helps develop optimal advertising strategies that take into account the influence of social media influencers.

[0878] Example 3

[0879] Next, a description will be given of Example 3 of Form Example 3. 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."

[0880] There is a need to accurately evaluate the exposure and penetration of brand names and trademarks in the market and generate evaluation reports based on the results to serve as a reference for investment decisions. However, conventional methods often involve manual data collection and analysis, which is inefficient and lacks objectivity and accuracy in evaluation. Furthermore, there is also the issue of ambiguous weighting criteria, which results in low reliability of evaluation scores.

[0881] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0882] In this invention, the server includes a means for aggregating the market exposure and penetration of brand names, trademarks, etc., a means for analyzing collected data using natural language processing technology, a means for weighting based on the exposure and penetration, a means for calculating an evaluation score, and a means for generating an evaluation report. This automates the process from data collection to analysis and generation of an evaluation report, making it possible to efficiently and accurately evaluate brand value.

[0883] "Brand names, trademarks, etc." refer to names and marks used to identify specific products or services in the market.

[0884] "Exposure and penetration" refers to the degree to which a brand name or trademark is recognized and influenced by the market and consumers.

[0885] "Aggregation methods" refers to the methods and techniques used to collect data from multiple sources and compile it into a single dataset.

[0886] "Natural language processing technology" refers to technology that allows computers to analyze and understand human language.

[0887] "Means of analysis" refers to methods and techniques for analyzing collected data and extracting useful information.

[0888] "Weighting methods" refer to methods or techniques for assessing the importance or impact of data and assigning numerical weights based on that assessment.

[0889] "Evaluation score" refers to a number that indicates the value of a brand, calculated based on exposure, penetration, and weighting results.

[0890] "Evaluation Report" refers to a document summarizing the evaluation results, including the exposure and penetration of brand names and trademarks, weighting results, evaluation scores, etc.

[0891] This invention is a system that evaluates the exposure and penetration of brand names and trademarks in the market and generates an evaluation report based on the results. A specific embodiment of this system will be described below.

[0892] The server first collects data related to brand names and trademarks from the internet. This data is obtained from online sources such as social media, news articles, blogs, and forums. Web scraping technology and APIs are used to collect the data. Specifically, designated APIs can be used.

[0893] The server then analyzes the collected data. This analysis uses natural language processing (NLP) technology, specifically analyzing the sentiment of the text data and extracting keywords. This allows the exposure and penetration of brand names and trademarks to be calculated.

[0894] The server then assigns weights based on the analysis results. Weighting is an important step in assessing a brand's market value and influence. For example, a brand with high exposure receives a higher weight, while a brand with low penetration receives a lower weight. This results in an overall evaluation score.

[0895] Finally, the server generates a rating report based on the rating scores. This report includes the exposure and penetration of the brand name or trademark, the weighting results, and the rating scores. The report is output in PDF format and can be downloaded by users.

[0896] As a specific example, when generating a rating report for a brand "ABC," the server performs the following steps:

[0897] 1. The server collects online data about "ABC".

[0898] 2. The server analyzes the data and calculates exposure and penetration.

[0899] 3. The server calculates a rating score based on the weighting of exposure and penetration.

[0900] 4. The server generates an evaluation report based on the evaluation score and outputs it in PDF format.

[0901] Example prompts to input to a generative AI model:

[0902] "Evaluate the exposure and penetration of brand ABC and generate an evaluation report. The report should include exposure and penetration, weighting results, and evaluation score."

[0903] In this way, the user can obtain a detailed report for evaluating the value of the brand. The flow of the identification process in the third embodiment will be described with reference to FIG.

[0904] Step 1: Data collection

[0905] The server collects data related to brand names and trademarks from the internet. As input, it receives keywords related to the brand names and trademarks. Specifically, it obtains data from online sources such as social media, news articles, blogs, and forums. It uses web scraping technology and APIs to collect the data. For example, it uses a specific API to collect related tweets and news articles. The output is the collected text data.

[0906] Step 2: Data analysis

[0907] The server analyzes the collected text data. As input, it receives the text data collected in step 1. This analysis uses natural language processing (NLP) technology. Specifically, it performs sentiment analysis and keyword extraction on the text data. For example, a tweet saying "Brand ABC is great" is analyzed as having a positive sentiment. As output, it obtains exposure and penetration data as the analysis results.

[0908] Step 3: Calculating weights and evaluation scores

[0909] The server assigns weights based on the analysis results. As input, it receives the exposure and penetration data obtained in step 2. Weighting is an important step in evaluating a brand's market value and influence. For example, if exposure is high, a high weight is assigned, and if penetration is low, a low weight is assigned. This is how an overall evaluation score is calculated. As output, the weighted result and evaluation score are obtained.

[0910] Step 4: Generate an assessment report

[0911] The server generates a rating report based on the rating scores. As input, it receives the weighting results and rating scores obtained in step 3. This report includes the exposure and penetration of the brand name or trademark, the weighting results, and the rating scores. Specifically, the report is generated in PDF format and made available for download by the user. As output, the rating report is obtained.

[0912] In this way, users can get detailed reports to assess the value of their brand.

[0913] (Application example 3)

[0914] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[0915] Conventional brand name and trademark evaluation systems lack real-time calculations of exposure and penetration, making it difficult to immediately evaluate the effectiveness of advertising campaigns. Furthermore, when generating evaluation reports, the input of prompts using generative AI models is not taken into account, resulting in problems with reduced evaluation accuracy and efficiency. This resulted in a lack of reliability as reference information for investment decisions.

[0916] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0917] In this invention, the server includes means for aggregating information on the market exposure and penetration of brand names, trademarks, etc. related to the investment target business, means for weighting factors such as corporate efforts and social media influencers, means for generating an evaluation report, means for evaluating the effectiveness of the advertising campaign in real time, means for calculating the degree of exposure and penetration, means for calculating the weighted results, means for calculating an evaluation score, means for outputting the evaluation report, and means for inputting prompt sentences using a generative AI model. This makes it possible to evaluate the effectiveness of the advertising campaign in real time and quickly generate highly accurate evaluation reports.

[0918] "Investment target business" refers to the company or project that is the target of investment.

[0919] A "brand name" refers to a name used to identify a particular product or service.

[0920] A "trademark" refers to a mark or logo that identifies a particular product or service.

[0921] "Exposure" refers to an indicator that shows how often a brand name or trademark appears in the market or media.

[0922] "Penetration" refers to an indicator that shows how well a brand name or trademark is recognized in the market and among consumers.

[0923] "Corporate efforts" refers to the marketing and promotional activities that a company undertakes itself.

[0924] A "social media influencer" is an individual or organization that has a large following and influence on social media.

[0925] "Weighting" refers to a method for assigning importance to different elements.

[0926] An "evaluation report" refers to a report that summarizes the exposure and penetration of a brand name or trademark, weighting results, evaluation scores, etc.

[0927] An "advertising campaign" refers to a series of advertising activities to promote a particular brand or product.

[0928] "Real-time" refers to data and information being processed immediately.

[0929] A "generative AI model" refers to a model that uses artificial intelligence to generate data.

[0930] A "prompt" refers to an instruction sentence that is input into a generative AI model.

[0931] "Exposure" refers to an indicator of how many people see an advertisement or brand.

[0932] "Penetration" is an indicator that shows how many people are aware of an advertisement or brand.

[0933] "Weighted results" refers to results that reflect the weights assigned to different factors.

[0934] "Evaluation score" refers to a comprehensive evaluation value calculated based on exposure, penetration, and weighting results.

[0935] The system for implementing this invention consists of three main elements: a server, a terminal, and a user. The following explains how each element functions.

[0936] server

[0937] The server plays a central role in aggregating the exposure and penetration of brand names and trademarks and generating evaluation reports. Specifically, it performs the following processes:

[0938] 1. Data Collection and Aggregation:

[0939] The server collects advertising campaign data and calculates the exposure and penetration of brand names and trademarks, including data such as impressions, click-through rates, unique visitors, and total population.

[0940] 2. Calculating weights:

[0941] The server assigns weights based on the company's efforts and the exposure and penetration of social media influencers, and calculates weighted results that reflect the importance of each factor.

[0942] 3. Calculation of the rating score:

[0943] The server calculates a rating score based on the weighting results. The rating score is a comprehensive rating value that combines the exposure, penetration, and weighting results.

[0944] 4. Generate and print the evaluation report:

[0945] The server generates an evaluation report including the calculated evaluation scores and outputs it in a format such as a CSV file.

[0946] 5. Leveraging generative AI models:

[0947] The server uses a generative AI model to input prompt sentences and automate the generation of evaluation reports, thereby improving the accuracy and efficiency of evaluations.

[0948] Terminal

[0949] The terminal provides an interface for users to check the evaluation report and evaluate the effectiveness of the advertising campaign in real time. Specifically, it has the following functions:

[0950] 1. Displaying data:

[0951] The terminal displays the evaluation report sent from the server, which includes the brand name, exposure, penetration, weighting results, evaluation score, etc.

[0952] 2. Real-time evaluation:

[0953] The device provides an interface for evaluating the effectiveness of advertising campaigns in real time, allowing users to view real-time updated data and make quick decisions.

[0954] User

[0955] Users can check the evaluation report through their devices and evaluate the effectiveness of their advertising campaigns by performing the following operations:

[0956] 1. Review the assessment report:

[0957] Users can check the evaluation report sent from the server via their device, which allows them to understand the exposure and penetration of brand names and trademarks, weighting results, and evaluation scores.

[0958] 2. Enter the prompt:

[0959] The user inputs a prompt to the generative AI model to instruct it to generate an evaluation report. For example, the user might input a prompt such as, "Based on the advertising campaign data, please calculate the brand's exposure, penetration, weighting results, and evaluation score, and generate an evaluation report."

[0960] Hardware and software used

[0961] The following hardware and software are used to realize this system.

[0962] Hardware:

[0963] General PC or server

[0964] User devices (smartphones, tablets, PCs, etc.)

[0965] software:

[0966] Python

[0967] Data processing library

[0968] Numerical calculation library

[0969] Machine learning libraries

[0970] Generative AI models (e.g., GPT-3)

[0971] This makes it possible to evaluate the effectiveness of advertising campaigns in real time and quickly generate highly accurate evaluation reports.

[0972] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0973] Step 1:

[0974] The server collects ad campaign data, specifically reading data such as impressions, click-through rate, unique visitors, and total population from a CSV file. The input is the ad campaign data, and the output is the read data frame.

[0975] Step 2:

[0976] The server calculates exposure and penetration based on the collected data. Exposure is the product of the number of impressions and the click-through rate, and penetration is the number of unique visitors divided by the total population. The input is the data frame loaded in step 1, and the output is a data frame containing the calculated exposure and penetration.

[0977] Step 3:

[0978] The server weights the exposure and penetration based on the exposure and penetration. Specifically, it assigns a weight of 0.6 to the exposure and a weight of 0.4 to the penetration and sums them. The input is the exposure and penetration calculated in step 2, and the output is a data frame containing the weighted results.

[0979] Step 4:

[0980] The server calculates an evaluation score based on the weighted results, which is calculated by scaling the weighted results to a range from 0 to 1. The input is the weighted results obtained in step 3, and the output is a data frame containing the evaluation scores.

[0981] Step 5:

[0982] The server generates a rating report including the rating scores and outputs it as a CSV file. The input is the rating scores calculated in step 4, and the output is a CSV file of the rating report.

[0983] Step 6:

[0984] The server inputs a prompt using a generative AI model to automate the generation of an evaluation report. Specifically, the prompt input is, "Based on the advertising campaign data, please calculate the brand's exposure, penetration, weighting results, and evaluation score, and generate an evaluation report." The input is the prompt, and the output is the generated evaluation report.

[0985] Step 7:

[0986] The terminal displays the evaluation report sent from the server. The input is a CSV file of the evaluation report sent from the server, and the output is the evaluation report displayed on the terminal screen.

[0987] Step 8:

[0988] The user checks the evaluation report through the terminal and evaluates the effectiveness of the advertising campaign in real time. The input is the evaluation report displayed on the terminal, and the output is the user's evaluation result.

[0989] 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.

[0990] "Example 1"

[0991] One embodiment of the present invention is a system that incorporates an emotion engine. This system recognizes user emotions and aggregates the exposure and penetration of brand names, trademarks, etc., taking those emotions into consideration. Specifically, the emotion engine recognizes the emotions (joy, anger, surprise, sadness, etc.) that users express toward specific brand names, trademarks, etc., and reflects the intensity and direction of those emotions in the calculation of exposure and penetration. For example, if a user expresses strong emotions of joy toward a particular brand, the exposure and penetration of that brand will be highly rated.

[0992] "Example 2"

[0993] Weighting is also performed taking into account the user's emotions recognized by the emotion engine. Specifically, weighting is performed on the exposure and penetration of brand names, trademarks, etc., taking into account the strength and direction of the user's emotions. For example, if a user expresses strong feelings of joy toward a particular brand, the weighting for that brand will be high.

[0994] "Example 3"

[0995] Furthermore, the evaluation report includes an evaluation score that reflects the user's emotions recognized by the emotion engine. Specifically, an evaluation score for a brand name, trademark, etc. is calculated taking into account the strength and direction of the user's emotions, and the score is included in the evaluation report. For example, if a user expresses strong feelings of joy toward a particular brand, the evaluation score for that brand will be high.

[0996] The processing flow of each embodiment will be described below.

[0997] "Example 1"

[0998] Step 1: Users express their feelings about a particular brand name, trademark, etc.

[0999] Step 2: The emotion engine recognizes the user's emotions (joy, anger, surprise, sadness, etc.).

[1000] Step 3: The intensity and direction of the emotion recognized by the emotion engine is reflected in the calculation of the exposure and penetration of brand names, trademarks, etc.

[1001] Step 4: Aggregate the exposure and penetration of brand names, trademarks, etc., taking into account user emotions.

[1002] "Example 2"

[1003] Step 1: Users express their feelings about a particular brand name, trademark, etc.

[1004] Step 2: The emotion engine recognizes the user's emotions (joy, anger, surprise, sadness, etc.).

[1005] Step 3: The intensity and direction of the emotion recognized by the emotion engine is reflected in the weighting of the exposure and penetration of brand names, trademarks, etc.

[1006] "Example 3"

[1007] Step 1: Users express their feelings about a particular brand name, trademark, etc.

[1008] Step 2: The emotion engine recognizes the user's emotions (joy, anger, surprise, sadness, etc.).

[1009] Step 3: The intensity and direction of the emotions recognized by the emotion engine are reflected in the calculation of the evaluation score for the brand name, trademark, etc.

[1010] Step 4: Include the evaluation scores in the evaluation report.

[1011] Example 1

[1012] Next, a description will be given of Example 1 of Form 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."

[1013] With conventional systems, it was difficult to accurately evaluate the market exposure and penetration of brand names, trademarks, etc. related to investment target businesses. Furthermore, because the evaluation did not take into account user sentiment, it was not possible to grasp the true value of the brand. Furthermore, there was a lack of efficient means for analyzing collected data and generating evaluation reports.

[1014] 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.

[1015] In this invention, the server includes means for aggregating the market exposure and penetration of brand names, trademarks, etc. related to the investment target business, means for weighting factors such as corporate efforts and influencers on social networking services, means for generating an evaluation report, means for collecting information on the Internet, means for analyzing the collected information, means for recognizing user emotions and calculating the degree of exposure and penetration taking those emotions into consideration, and means for aggregating the exposure and penetration based on the analysis results. This makes it possible to accurately evaluate the market exposure and penetration of brand names, trademarks, etc., and to perform an evaluation that takes user emotions into consideration.

[1016] "Investment target business" refers to a business or project in which investment funds are being considered.

[1017] "Brand names, trademarks, etc." refers to names, logos, symbols, etc. that are used to identify specific products or services.

[1018] A "market" is an economic venue or environment in which products and services are traded.

[1019] "Exposure / penetration" refers to the degree to which a brand name, trademark, etc. is recognized and has influence in the market.

[1020] "Corporate efforts" refer to the various activities and measures that a company undertakes to make its products and services successful in the market.

[1021] A "social networking service influencer" is someone who has a large number of followers on a social networking site and whose opinions and actions have a significant influence on other users.

[1022] "Weighting" refers to assigning importance to a particular factor in an evaluation or calculation.

[1023] An "evaluation report" is a report prepared based on collected data and analysis results.

[1024] "Information on the Internet" refers to data and content that can be accessed via the Internet, such as websites and social media.

[1025] "Analysis" is the process of examining collected data in detail to find meaning and patterns.

[1026] "User emotions" refer to the psychological reactions and feelings that users have toward a particular brand name, trademark, etc.

[1027] "Calculating exposure and penetration while taking emotions into consideration" means reflecting the intensity and direction of the user's emotions in the evaluation.

[1028] "Aggregation" means combining multiple pieces of data or information into one.

[1029] This invention is a system that aggregates information on the market exposure and penetration of brand names, trademarks, etc. related to investment target businesses. The system operates in cooperation with three parties: a server, a terminal, and a user.

[1030] Data collection

[1031] The server collects information from the Internet. Specifically, it collects mentions of brand names, trademarks, etc. from websites and social networking services (SNS). The hardware used is a high-performance server, and the software used is a web scraping tool.

[1032] Data analysis

[1033] The server analyzes the collected data. Specifically, it uses natural language processing tools to calculate the exposure and penetration of brand names, trademarks, etc. The server tokenizes the text data and calculates the frequency of appearance of brand names, trademarks, etc. It also analyzes the co-occurrence of related keywords to determine whether users recognize the brand.

[1034] emotion recognition

[1035] The server uses an emotion engine to recognize the user's emotions. The server inputs the collected text data into the emotion engine and analyzes the emotions (happiness, anger, surprise, sadness, etc.) that the user expresses toward a specific brand. The intensity and direction of the emotion are quantified and stored in a database.

[1036] Exposure and penetration aggregation

[1037] The server aggregates the exposure and penetration of brand names, trademarks, etc. based on the analysis results. It also takes into account the strength and direction of emotions to calculate the overall exposure and penetration. The final evaluation results are displayed on the dashboard.

[1038] Specific examples

[1039] For example, when a new beverage brand is launched on the market, the server collects information from the internet and analyzes mentions on websites and social media. It then uses an emotion engine to recognize the emotions users express toward the brand. If users express a lot of positive emotions toward the brand, the server will rate the brand's exposure and penetration highly.

[1040] Prompt Sentence Examples

[1041] "A new beverage brand has been launched in the market. Collect information from the internet and analyze mentions on websites and social media to identify the sentiment expressed by users toward the brand, and incorporate the strength and direction of that sentiment into the calculation of exposure and penetration."

[1042] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1043] Step 1:

[1044] Data collection

[1045] The server collects information from the Internet. Specifically, it collects mentions of brand names, trademarks, etc. from websites and social networking services (SNS). The hardware used is a high-performance server, and the software used is a web scraping tool.

[1046] Input: Keywords related to specific brand names, trademarks, etc.

[1047] Output: Collected text data

[1048] Specific operation: The server launches the web scraping tool at a fixed time every day to collect the latest data, which is then stored in the database in real time.

[1049] Step 2:

[1050] Data analysis

[1051] The server analyzes the collected data, specifically using natural language processing tools to calculate the exposure and penetration of brand names, trademarks, etc.

[1052] Input: Collected text data

[1053] Output: Frequency of appearance and co-occurrence of brand names, trademarks, etc.

[1054] Specific operation: The server tokenizes the text data and calculates the frequency of appearance of brand names, trademarks, etc. It also analyzes the co-occurrence of related keywords to evaluate brand awareness.

[1055] Step 3:

[1056] emotion recognition

[1057] The server uses an emotion engine to recognize the user's emotion.

[1058] Input: Collected text data

[1059] Output: The intensity and direction of the user's emotion

[1060] Specific operation: The server inputs the collected text data into an emotion engine and analyzes the emotions (happiness, anger, surprise, sadness, etc.) expressed by the user toward a specific brand. The intensity and direction of the emotions are quantified and stored in a database.

[1061] Step 4:

[1062] Exposure and penetration aggregation

[1063] The server aggregates the exposure and penetration of brand names, trademarks, etc. based on the analysis results, and calculates the overall exposure and penetration, taking into account the strength and direction of emotions.

[1064] Input: Frequency of appearance of brand names, trademarks, etc., co-occurrence relationships, strength and direction of user emotions

[1065] Output: Overall exposure and penetration assessment score

[1066] Specific operation: Based on the analysis results, the server scores the exposure and penetration of brand names, trademarks, etc. The scoring results are updated in real time on the dashboard and are useful for investment decisions.

[1067] Step 5:

[1068] Generate an assessment report

[1069] The server generates a rating report based on the overall exposure and penetration rating score.

[1070] Input: Overall exposure and penetration assessment score

[1071] Output: Evaluation report

[1072] Specific operation: Based on the evaluation scores, the server generates an evaluation report detailing the market performance of the brand name, trademark, etc. The evaluation report is output in PDF format and distributed to relevant parties.

[1073] (Application example 1)

[1074] Next, a description will be given of Application Example 1 of Form 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."

[1075] Previous systems for evaluating the market exposure and penetration of brand names and trademarks only collected information from the Internet and did not take into account user sentiment. This made it difficult to accurately reflect the actual market evaluation of a brand. Furthermore, there was a lack of means to evaluate the effectiveness of advertising campaigns in real time, making it difficult to quickly change strategies.

[1076] The specification processing by the specification processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means for aggregating the market exposure and penetration of brand names, trademarks, etc. related to the investment target business, means for weighting factors such as corporate efforts and social media influencers, means for generating evaluation reports, means for collecting information on the Internet, means for recognizing user emotions and aggregating the exposure and penetration of brand names, trademarks, etc. taking those emotions into consideration, and means for evaluating the effectiveness of advertising campaigns in real time. This allows the market evaluation of the brand to be accurately reflected and advertising strategies to be changed quickly.

[1077] "Investment target business" refers to any business that aims to make a profit by investing funds.

[1078] A "brand name" is a name used to identify a specific product or service, and serves to assure consumers of the reliability and quality of that product or service.

[1079] A "trademark" is a logo or symbol used to identify a particular company or product, and is intellectual property protected by law.

[1080] "Market exposure" is an indicator of how many people in the market recognize a brand name or trademark.

[1081] "Penetration" is an indicator of how deeply a brand name or trademark has penetrated the market among consumers.

[1082] "Aggregation methods" refers to the methods and techniques used to collect data from multiple sources and compile it into a single assessment.

[1083] "Weighting methods" refer to methods or techniques for assigning importance to different elements or information and making evaluations based on that.

[1084] An "evaluation report" is a report prepared based on collected data and analysis results, and is intended to evaluate the market exposure and penetration of a brand name or trademark.

[1085] "Information on the Internet" refers to all information accessible via the Internet, such as websites, social media, and blogs.

[1086] "User emotions" refers to the emotions (joy, anger, surprise, sadness, etc.) that users show toward a particular brand name or trademark.

[1087] "Means for recognizing emotions" refers to methods and technologies for analyzing a user's emotions and identifying the type and intensity of those emotions.

[1088] "Real-time assessment means" refers to methods and technologies for instantly analyzing ongoing data and providing the results immediately.

[1089] An "advertising campaign" refers to a series of marketing activities conducted to promote a particular product or service.

[1090] A system for carrying out this invention has the following configuration: A server includes means for aggregating the degree of exposure and penetration in the market of brand names, trademarks, etc. related to investment target businesses, means for weighting factors such as those due to corporate efforts and those due to social media influencers, means for generating evaluation reports, means for collecting information on the Internet, means for recognizing user emotions and aggregating the degree of exposure and penetration of brand names, trademarks, etc. taking those emotions into consideration, and means for evaluating the effectiveness of advertising campaigns in real time.

[1091] Hardware and software used

[1092] Hardware: Servers, smartphones

[1093] Software: Python, TensorFlow, predefined APIs

[1094] Data collection and analysis

[1095] The server scrapes brand name and trademark mentions from websites and also collects mentions on social media using a designated API, allowing for efficient collection of information from the internet.

[1096] Emotion analysis

[1097] The server performs sentiment analysis on the collected text data, which allows it to recognize the user's emotions and identify the type and intensity of those emotions.

[1098] Exposure and penetration calculations

[1099] The server calculates the brand exposure and penetration level based on the collected mention frequency and sentiment data, allowing for an accurate assessment of the market penetration of a brand name or trademark.

[1100] Real-time evaluation

[1101] The server displays the calculation results in real time on a dashboard, allowing for immediate evaluation of the effectiveness of advertising campaigns, enabling quick changes to advertising strategies.

[1102] Specific examples

[1103] For example, when evaluating a brand's advertising campaign, the server first collects information from the Internet, then performs sentiment analysis. After that, it calculates exposure and penetration and displays the evaluation results in real time on a dashboard. This allows users to immediately understand the effectiveness of their advertising campaign and change their strategy if necessary.

[1104] Prompt Sentence Examples

[1105] Your task will be to create a program that calculates the market exposure and penetration of "ExampleBrand" and evaluates the effectiveness of its advertising campaign in real time, taking into account user sentiment. The technologies used will be Python, TensorFlow, and the specified API.

[1106] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1107] Step 1:

[1108] The server collects information from the internet. Specifically, it scrapes mentions of brand names and trademarks from websites and collects mentions on social media using a designated API. The server specifies the brand name or trademark as input and obtains the collected text data as output.

[1109] Step 2:

[1110] The server analyzes the collected text data. Specifically, it performs sentiment analysis on the text data. It uses the collected text data as input and obtains sentiment scores for each text as output.

[1111] Step 3:

[1112] The server calculates the brand exposure and penetration based on the sentiment score and mention frequency. Specifically, it calculates exposure and penetration by multiplying the average sentiment score by the mention frequency. It uses sentiment score and mention frequency as input and obtains an exposure and penetration score as output.

[1113] Step 4:

[1114] The server displays the calculation results in real time on a dashboard, specifically by generating graphs and charts to visualize the exposure and penetration scores and evaluate the effectiveness of advertising campaigns. It uses the exposure and penetration scores as input and obtains visualized evaluation results as output.

[1115] Step 5:

[1116] Users can check the effectiveness of their advertising campaigns through the dashboard and change their strategies as needed, specifically adjusting the content and timing of their ads based on the evaluation results.The visualized evaluation results are used as input, and a new advertising strategy is obtained as output.

[1117] Example 2

[1118] Next, a description will be given of Example 2 of Form 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."

[1119] Conventional brand evaluation systems do not adequately consider the influence of corporate advertising activities or social media influencers when assigning weighting, resulting in inaccurate evaluations of the exposure and penetration of brand names and trademarks. Furthermore, because weighting does not take user emotions into account, evaluations cannot reflect the strength or direction of user emotions. This makes it difficult to accurately evaluate the effectiveness of a company's marketing strategy and advertising activities.

[1120] 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.

[1121] In this invention, the server includes a means for aggregating information on the market exposure and penetration of brand names, trademarks, etc. related to the investment target business, a means for weighting based on the company's advertising budget and the scale of marketing activities, the number of followers of SNS influencers, and the number of engagements on posts, a means for analyzing user emotions using an emotion engine and adjusting the weighting taking into account the strength and direction of those emotions, and a means for generating an evaluation report. This makes it possible to comprehensively evaluate the influence of the company's advertising activities and SNS influencers, as well as user emotions, and accurately evaluate the exposure and penetration of brand names and trademarks.

[1122] An "investment target business" is a business in which a company invests funds in the hope of achieving growth and profits.

[1123] A "brand name" is a name used to identify a particular product or service.

[1124] A "trademark" is a logo or symbol used to identify a particular company or product.

[1125] "Exposure / penetration" refers to the degree to which a brand name or trademark is recognized in the market and by consumers.

[1126] A "company's advertising budget" refers to the total amount of funds a company allocates to its advertising activities.

[1127] The "scale of marketing activities" refers to the scope and influence of a company's marketing activities.

[1128] A "social media influencer" is an individual who has a large following and influence on social media.

[1129] "Number of followers" refers to the number of users who follow a social media influencer's account.

[1130] "Post engagements" refers to the total number of reactions to a social media influencer's post, such as likes, comments, and shares.

[1131] An "emotion engine" is software that analyzes a user's emotions from text data and recognizes their intensity and direction.

[1132] An "evaluation report" is a report that summarizes the exposure and penetration of brand names and trademarks, weighting results, evaluation scores, etc.

[1133] The "evaluation score" is a numerical representation of the overall evaluation of the exposure and penetration of a brand name or trademark.

[1134] MODE FOR CARRYING OUT THE INVENTION

[1135] This invention is a system that comprehensively evaluates the influence of corporate advertising activities and social media influencers, as well as user sentiment, to accurately evaluate the exposure and penetration of brand names and trademarks. Specific embodiments of this system are described below.

[1136] 1. Program Generation

[1137] The server generates a program that takes into account the influence of a company's marketing activities and social media influencers, and collects and analyzes data to evaluate the exposure and penetration of brand names and trademarks.

[1138] 2. Hardware and Software Used

[1139] The server processes and calculates data using the following hardware and software:

[1140] Hardware: High-performance servers

[1141] Software: Data analysis tools, sentiment analysis engine

[1142] 3. Data collection and preprocessing

[1143] The server collects data such as a company's advertising budget, the scale of marketing activities, the number of followers of social media influencers, and the number of post engagements. Specifically, the data is obtained from social media platforms and advertising management tools via APIs. The collected data is then used to create a data frame using Python libraries, which then performs missing value imputation, data normalization, and outlier detection and removal.

[1144] 4. Weighting calculation

[1145] The server calculates weights based on the preprocessed data. Specifically, weights are set according to the size of advertising budgets and marketing activities, and influence is evaluated based on the number of followers and engagement of social media influencers. For example, the larger the advertising budget, the higher the weight.

[1146] 5. Sentiment analysis

[1147] The server uses an emotion engine to analyze the user's emotions. Specifically, it analyzes text data from social media posts and reviews to recognize the strength and direction of the user's emotions. For example, a post saying "I love this product!" is recognized as a strong emotion of joy.

[1148] 6. Overall evaluation and result output

[1149] The server integrates the results of the weighting calculation and sentiment analysis to perform a comprehensive evaluation of the exposure and penetration of the brand name and trademark. Specifically, it adds up the weights of each element to calculate a final evaluation score. The evaluation score can be displayed on a dashboard or generated as a report. For example, brands with high evaluation scores can be displayed in a ranking format.

[1150] Examples of specific examples and prompts

[1151] As a concrete example, consider the following scenario.

[1152] Company A launches a new product and significantly increases its advertising budget. Social media influencer B endorses the product, with 1 million followers and 100,000 engagements on its posts.

[1153] User C gave the product a very high rating, and the emotion engine recognized User C's emotion as "strong delight."

[1154] In this case, the server takes into consideration the advertising activities of Company A and the influence of SNS influencer B, and also takes into account the feelings of User C, and sets a high weighting for Company A's brand.

[1155] Example prompt sentence:

[1156] Considering the advertising activities for Company A's new product and the influence of Social Media Influencer B, generate a program that weights brands based on User C's emotions. Company A's advertising budget is 50 million yen, Social Media Influencer B has 1 million followers, and its posts have 100,000 engagements. User C's emotion is recognized as "strong delight."

[1157] In this way, the server comprehensively evaluates a company's marketing activities, the influence of SNS influencers, and user sentiment, creating a system that accurately evaluates the exposure and penetration of brand names and trademarks.

[1158] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1159] Step 1: Data collection

[1160] The server collects data such as a company's advertising budget, the scale of its marketing activities, the number of followers of social media influencers, and the number of post engagements. Specifically, it uses a specified API to obtain the number of followers and engagements of social media influencers and collects the company's advertising budget data. The input is the raw data obtained from the API, and the output is the collected dataset.

[1161] Step 2: Data Preprocessing

[1162] The server preprocesses the collected data. Specifically, it uses Python libraries to create a data frame, impute missing values, normalize the data, and detect and remove outliers. For example, if the number of followers is missing, it is imputed with the average value. The input is the collected dataset, and the output is the preprocessed dataset.

[1163] Step 3: Calculate weights

[1164] The server calculates weights based on the preprocessed data. Specifically, weights are set according to the size of the advertising budget and marketing activities, and the influence is evaluated based on the number of followers and engagement of social media influencers. For example, if the advertising budget is 10 million yen, the weight is set to 0.8. The input is the preprocessed dataset, and the output is the weighted data.

[1165] Step 4: Sentiment analysis

[1166] The server uses an emotion engine to analyze user emotions. Specifically, it analyzes text data from social media posts and reviews to recognize the strength and direction of the user's emotions. For example, it analyzes a post that says, "I love this product!" and sets the emotion score to 0.9. The input is text data, and the output is an emotion score.

[1167] Step 5: Overall evaluation

[1168] The server combines the results of the weighting calculation and sentiment analysis to perform an overall evaluation of the exposure and penetration of the brand name and trademark. Specifically, it adds up the weights of each element to calculate a final evaluation score. For example, the advertising budget weight of 0.8, the influence of social media influencers of 0.7, and the user sentiment score of 0.9 are added together to arrive at an overall evaluation score of 2.4. The input is the weighted data and sentiment score, and the output is the overall evaluation score.

[1169] Step 6: Output the results

[1170] The server outputs the overall evaluation results. Specifically, it displays the evaluation scores on a dashboard or generates a report. For example, it displays the brands with the highest evaluation scores in a ranking format and generates a detailed report in PDF format. The input is the overall evaluation score, and the output is the dashboard display or PDF report.

[1171] (Application example 2)

[1172] Next, a description will be given of Application Example 2 of Form 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."

[1173] Conventional evaluation systems for brand name and trademark exposure and penetration only consider the influence of corporate marketing activities and social media influencers, and are unable to reflect user sentiment in real time. Therefore, there is a need for more accurate evaluations based on user sentiment.

[1174] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1175] In this invention, the server includes a means for aggregating information on the market exposure and penetration of brand names, trademarks, etc. related to the investment target business, a means for weighting factors such as corporate efforts and social media influencers, a means for analyzing user sentiment in real time, a means for weighting based on the analyzed sentiment, and a means for generating an evaluation report, thereby enabling more accurate brand evaluation that takes user sentiment into account.

[1176] An "investment target business" refers to a business or project in which funds are to be invested.

[1177] A "brand name" is a name used to identify a particular product or service and indicates to consumers the source of that product or service.

[1178] A "trademark" is a mark, logo or symbol used to distinguish goods or services from others.

[1179] "Exposure" refers to how frequently a brand name or trademark appears in the marketplace or media.

[1180] "Penetration" refers to the degree to which a brand name or trademark is recognized and accepted in the market and among consumers.

[1181] "Corporate efforts" refer to the marketing activities, advertising activities, and other efforts undertaken by a company.

[1182] A "SNS influencer" is someone who has a large number of followers on a social networking service and uses their influence to recommend products and services.

[1183] "Weighting" refers to the numerical evaluation of the importance or influence of a particular element.

[1184] "User emotions" refer to the emotions that users have toward a particular brand or trademark, and include emotions such as joy, sadness, and anger.

[1185] "Real-time" means that data and information are processed immediately and reflected without delay.

[1186] An "evaluation report" is a report of the evaluation results prepared based on the exposure and penetration of brand names and trademarks and the weighting results.

[1187] As an embodiment of the present invention, the following system is constructed.

[1188] System Configuration

[1189] The system consists of a server, user devices, and a database of social media influencers. The server aggregates the exposure and penetration of brand names and trademarks, and analyzes and weights the influence of corporate efforts and social media influencers, as well as user emotions, in real time. User devices are devices such as smartphones and tablets, and use cameras and microphones to capture user emotions in real time.

[1190] Hardware and software used

[1191] Hardware: Smartphone camera, microphone

[1192] software

[1193] Data processing and calculation

[1194] 1. Aggregation of brand name and trademark exposure and penetration:

[1195] The server collects data from the internet and analyzes the exposure of brand names and trademarks using web scraping technology and APIs.

[1196] 2. Weighting of corporate efforts and social media influencer influence:

[1197] The server assigns weights based on a company's marketing efforts, advertising budget, and the number of followers and engagement of social media influencers, including retrieving information from a database of social media influencers.

[1198] 3. Real-time analysis of user sentiment:

[1199] The user device captures the user's face and voice using a camera and microphone, analyzes their emotions using the library, and sends the analysis results to the server.

[1200] 4. Emotional weighting:

[1201] The server weights brand names and trademarks based on the results of user sentiment analysis. For example, if a user expresses joy toward a particular brand, the server weights that brand more highly.

[1202] 5. Generate assessment report:

[1203] The server generates a rating report based on the aggregated data and weighted results, which includes a rating score based on brand name and trademark exposure and penetration, company efforts, social media influencer influence, and user sentiment.

[1204] Specific examples

[1205] For example, if a user expresses the emotion of "joy" while using their smartphone, the server will weight a particular brand higher based on the emotion analysis results, which will result in more positive advertisements being displayed to the user.

[1206] Prompt Sentence Examples

[1207] "Develop an application that analyzes user sentiment in real time and displays optimal ads taking into account the influence of social media influencers. Use a library for sentiment analysis and obtain influencer influence from an API."

[1208] The above is a specific embodiment for carrying out the present invention.

[1209] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1210] Step 1:

[1211] The server collects data from the internet and analyzes the exposure of brand names and trademarks. Specifically, it uses web scraping technology and APIs to collect data related to brand names and trademarks from news articles, blogs, social media posts, etc. The input is text data from the internet, and the output is numerical data indicating the exposure of brand names and trademarks.

[1212] Step 2:

[1213] The server assigns weights based on the company's marketing activities and advertising budget, as well as the number of followers and engagement of social media influencers. Specifically, it obtains the number of followers and engagement from a database of social media influencers and calculates weights taking into account the scale of the company's advertising budget and marketing activities. The input is social media influencer data and the company's marketing data, and the output is weighted numerical data.

[1214] Step 3:

[1215] The user device captures the user's face and voice using a camera and microphone, and analyzes their emotions using the library. Specifically, while the user is using their smartphone, the camera takes a picture of their face, and the library analyzes their emotions in real time. The input is the user's face image and voice data, and the output is the emotion analysis results.

[1216] Step 4:

[1217] The server weights brand names and trademarks based on the results of user sentiment analysis. Specifically, it adjusts the weighting of a brand by taking into account the emotions (e.g., joy, sadness, anger, etc.) expressed by the user toward that brand. The input is the sentiment analysis result and initial weighting data for the brand name or trademark, and the output is weighting data adjusted based on the emotions.

[1218] Step 5:

[1219] The server generates an evaluation report based on the aggregated data and weighting results. Specifically, it creates a report that includes an evaluation score based on the exposure and penetration of brand names and trademarks, corporate efforts, the influence of social media influencers, and user sentiment. The inputs are exposure and penetration data, weighting data for companies and social media influencers, and sentiment-based weighting data, and the output is an evaluation report.

[1220] The above are the specific processing steps for carrying out the present invention.

[1221] Example 3

[1222] Next, a description will be given of Example 3 of Form Example 3. 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."

[1223] Conventional brand evaluation systems have difficulty accurately assessing the exposure and penetration of brand names and trademarks, and do not reflect user sentiment. As a result, they are not very reliable as reference information for investment decisions.

[1224] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1225] In this invention, the server includes means for collecting data on brand names and trademarks from various sources on the Internet, means for analyzing the collected data using natural language processing technology, means for calculating the exposure and penetration of brand names and trademarks, means for weighting each data source according to its importance, means for analyzing user sentiment and reflecting the results in an evaluation score, and means for generating an evaluation report based on the final evaluation score. This makes it possible to accurately evaluate the exposure and penetration of brand names and trademarks and to calculate an evaluation score that reflects user sentiment.

[1226] "Various sources on the Internet" refers to information sources that are publicly available on the Internet, such as websites, social media, news articles, and blogs.

[1227] "Brand names and trademarks" refers to names, logos, and symbols used to identify particular products or services.

[1228] "Data collection methods" refers to the techniques and methods used to obtain the required data from sources on the Internet.

[1229] "Natural language processing technology" refers to computer technology for analyzing text data and understanding meaning and emotions.

[1230] "Exposure and penetration" refers to the degree to which a brand name or trademark is recognized and influenced by the market and consumers.

[1231] "Weighting methods" refers to methods or techniques for adjusting the degree to which each data source influences the evaluation according to its importance.

[1232] "Means for analyzing user emotions" refers to technology for analyzing the emotions that users express toward a particular brand and evaluating their strength and direction.

[1233] An "evaluation score" is an index that quantifies the value of a brand name or trademark.

[1234] "Means for generating an assessment report" refers to the technology or method for compiling assessment scores and other assessment results and outputting them in a report format.

[1235] MODE FOR CARRYING OUT THE INVENTION

[1236] This invention relates to a system for evaluating the exposure and penetration of brand names and trademarks and calculating an evaluation score that reflects user sentiment. Specific embodiments of this system will be described below.

[1237] Data collection

[1238] The server collects data on brand names and trademarks from various sources on the Internet, specifically, text data from websites, social media, news articles, blogs, etc. This collection is done using a Python library.

[1239] Data analysis

[1240] The server analyzes the collected text data using natural language processing technology, specifically using Python to tokenize the text data, perform sentiment analysis, and extract keywords.

[1241] Exposure and penetration calculations

[1242] The server calculates the exposure and penetration of brand names and trademarks based on the analyzed data. For example, it calculates how often a particular brand is mentioned on social media or how often it is featured in news articles. This calculation is performed using MySQL as the database management system (DBMS).

[1243] Weighting and evaluation score calculation

[1244] The server calculates a reputation score for the brand name or trademark based on exposure and penetration, weighting each data source according to its importance. For example, social media posts may be given less weight than news articles. This weighting is done using machine learning algorithms.

[1245] Evaluation by Emotion Engine

[1246] The server uses an emotion engine to analyze the user's emotions and reflects the results in the evaluation score. The emotion engine takes into account the strength and direction of the emotion the user shows toward a particular brand. This emotion analysis uses a specified API.

[1247] Generate an assessment report

[1248] The server generates a rating report based on the final rating score. This report includes the exposure and penetration of the brand name and trademark, weighting results, and the rating score from the sentiment engine. The generated report is output in PDF format and can be used as reference information for investment decisions. A Python library is used for this.

[1249] Examples and prompts

[1250] Specific examples

[1251] For example, suppose a certain brand "XYZ" is frequently mentioned on social media and frequently featured in news articles. User sentiment analysis reveals that users express strong feelings of joy toward "XYZ." In this case, the server will highly evaluate the exposure and penetration of "XYZ" and calculate a high evaluation score based on the results of the emotion engine. The final evaluation report will include a high evaluation score for "XYZ."

[1252] Prompt Sentence Examples

[1253] "Evaluate the exposure and penetration of the brand name 'XYZ' and calculate a rating score that reflects user sentiment using a sentiment engine. Generate a final rating report in PDF format."

[1254] In this way, the server realizes a system that evaluates the value of a brand name or trademark and outputs the results as a report. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1255] Step 1:

[1256] The server collects data related to brand names and trademarks from various sources on the Internet. Specifically, it obtains text data from websites, social media, news articles, blogs, etc. A Python library is used for this collection. A list of URLs to be collected is required as input, and the collected text data is obtained as output. Specifically, the server cycles through the specified URL list, obtains HTML content, and extracts text data from the HTML.

[1257] Step 2:

[1258] The server analyzes the collected text data using natural language processing technology. Specifically, it uses Python to tokenize the text data, perform sentiment analysis, and extract keywords. The collected text data is required as input, and the analyzed sentiment score and keyword list are obtained as output. Specifically, the server tokenizes the collected text data, calculates the sentiment score for each token, and extracts keywords.

[1259] Step 3:

[1260] The server calculates the exposure and penetration of brand names and trademarks based on the analyzed data. Specifically, it calculates how often a particular brand is mentioned on social media and how often it is featured in news articles. This calculation uses MySQL as the database management system (DBMS). The inputs are the analyzed sentiment scores and keyword lists, and the output is the exposure and penetration of brand names and trademarks. Specifically, the server counts the number of times a brand name appears extracted from each data source and stores the results in a database.

[1261] Step 4:

[1262] The server calculates the reputation score for the brand name or trademark based on its exposure and penetration. At this time, it weights each data source according to its importance. For example, social media posts may be given less weight than news articles. This weighting is done using a machine learning algorithm. The input is the exposure and penetration of the brand name or trademark, and the output is a weighted reputation score. Specifically, the server sets the importance of each data source and calculates the overall reputation score by multiplying the exposure and penetration by the weight.

[1263] Step 5:

[1264] The server uses an emotion engine to analyze the user's emotions and reflects the results in the evaluation score. The emotion engine takes into account the strength and direction of the emotion the user expresses toward a particular brand. A specified API is used for this emotion analysis. The input is the user's emotion data, and the output is the emotion analysis result. Specifically, the server acquires the user's emotion data, calculates the emotion score using the emotion engine, and adds or subtracts that score from the evaluation score.

[1265] Step 6:

[1266] The server generates a rating report based on the final rating score. This report includes the exposure and penetration of the brand name and trademark, weighting results, and the rating score from the sentiment engine. The generated report is output in PDF format and used as reference information for investment decisions. A Python library is used for this. The final rating score is required as input, and a PDF rating report is obtained as output. Specifically, the server generates a report summarizing the rating scores and saves it in PDF format.

[1267] (Application example 3)

[1268] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1269] Conventional brand valuation systems were unable to fully reflect user sentiment when assessing the exposure and penetration of brand names and trademarks. This made it difficult to accurately assess the true value of a brand, and the system was unreliable as reference information for investment decisions. Furthermore, the generation of valuation reports did not involve advanced analysis using AI models, which led to issues with the accuracy and reliability of the valuation results.

[1270] The identification processing by the identification processing unit 290 of the data processing device 12 in Application Example 3 is realized by the following means. In this invention, the server includes means for aggregating information on the market exposure and penetration of brand names, trademarks, etc. related to the investment target business, means for weighting based on factors such as corporate efforts and influencers on social networking services, means for generating an evaluation report, means including a sentiment analysis engine for analyzing user sentiment, means for calculating an evaluation score reflecting user sentiment, and means for generating an evaluation report using a generative AI model. This enables accurate brand evaluation that reflects user sentiment, improving the reliability of the information as reference for investment decisions.

[1271] "Investment target business" refers to the company or project that is the target of investment.

[1272] "Brand names and trademarks" refer to names, logos, symbols, etc. that identify specific companies or products.

[1273] "Exposure / Penetration" is an indicator that shows how well a brand name or trademark is recognized by the market and consumers, or how widely it is spread.

[1274] "Corporate efforts" refers to the marketing and promotional activities that companies undertake to spread their brands and products in the market.

[1275] A "social networking service influencer" is someone who has a large number of followers on social media and whose words and actions have a significant impact on other users.

[1276] "Weighting" refers to assigning numerical values ​​to different elements or data based on their importance or influence.

[1277] An "evaluation report" refers to a report summarizing evaluation results based on the exposure and penetration of brand names and trademarks, weighting results, user sentiment, etc.

[1278] An "emotion analysis engine" refers to software or algorithms that analyze users' text data and behavioral data to identify their emotions.

[1279] An "evaluation score" is a numerical indicator of the value of a brand name or trademark, and is calculated based on exposure, penetration, and user sentiment.

[1280] "Generative AI model" means a model that uses artificial intelligence to analyze data and generate assessment reports or other outputs.

[1281] The system for implementing this invention consists of three main elements: a server, a terminal, and a user. The following explains how each element functions.

[1282] server

[1283] The server includes the following means:

[1284] 1. Data aggregation method: Aggregate information on the market exposure and penetration of brand names, trademarks, etc. related to the investment target business. This method involves collecting data using web scraping and APIs.

[1285] 2. Weighting method: Weighting is based on the company's efforts and the exposure and penetration of influencers on social networking services. For example, it evaluates how much engagement a particular influencer's post received.

[1286] 3. Sentiment Analysis Engine: Software for analyzing user sentiment, using natural language processing libraries.

[1287] 4. Evaluation score calculation method: Calculate an evaluation score that reflects the user's emotions. Calculate the brand's evaluation score based on the results of the sentiment analysis engine.

[1288] 5. Generative AI model: Generating evaluation reports using a generative AI model. For example, using a generative AI model such as GPT-3, we can automatically generate evaluation reports.

[1289] Terminal

[1290] A device is a device used by a user, such as a smartphone or tablet. A device includes the following features:

[1291] 1. Data entry function: Provides an interface for users to enter their feelings and feedback about the brand.

[1292] 2. Real-time analysis function: User input data is sent to the server in real time and sentiment analysis is performed.

[1293] User

[1294] Users are responsible for providing their feelings and feedback about the brand. Through their devices, users can:

[1295] 1. Emotional input: Enter your feelings and opinions about the brand in text format.

[1296] 2. Providing feedback: Providing feedback on the evaluation report to improve the accuracy of the system.

[1297] Specific examples

[1298] For example, if a user comments, "This brand is great!", the comment is sent to the server via the device. The server uses a sentiment analysis engine to analyze the comment and rate it as a positive sentiment. Then, it uses a generative AI model to generate a rating report that includes the rating results.

[1299] Prompt Sentence Examples

[1300] "Analyze the sentiment expressed by users towards a particular brand and generate a rating score for that brand. For example, if a user leaves a positive comment about a particular brand, calculate a rating score that reflects that sentiment."

[1301] In this way, accurate brand evaluation that reflects the user's feelings becomes possible, improving the reliability of the information as reference for investment decisions.

[1302] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1303] Step 1:

[1304] The server uses web scraping and APIs to aggregate information on the market exposure and penetration of brand names, trademarks, etc. related to the investment target business. Data collected from websites and social media is used as input, and exposure and penetration data for each brand is generated as output.

[1305] Step 2:

[1306] The server weights the company's efforts and influencers of social networking services based on the aggregated exposure and penetration data, using the exposure and penetration data and influencer engagement data as inputs and generating weighted exposure and penetration data as output.

[1307] Step 3:

[1308] Users input their feelings and feedback about the brand in text format through a terminal. The system uses the user's comments and feedback as input and generates text data as output.

[1309] Step 4:

[1310] The terminal transmits the user's input data to the server in real time, using the user's text data as input and generating the text data transmitted to the server as output.

[1311] Step 5:

[1312] The server uses a sentiment analysis engine to analyze the user's text data and identify its sentiment, using the user's text data as input and generating a sentiment score as output.

[1313] Step 6:

[1314] The server calculates a rating score that reflects the user's sentiment based on the sentiment score. It uses the sentiment score and weighted exposure and penetration data as inputs and generates a rating score as output.

[1315] Step 7:

[1316] The server uses a generative AI model to generate an evaluation report based on the evaluation scores, using the evaluation scores as input and generating the evaluation report as output.

[1317] Step 8:

[1318] The server transmits the generated evaluation report to the terminal and provides it to the user. The server uses the evaluation report as input and generates an evaluation report that is provided to the user as output.

[1319] 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.

[1320] 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> ) 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.

[1321] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are listed.

[1322] 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.

[1323] [Third embodiment]

[1324] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1325] 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.

[1326] 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).

[1327] 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.

[1328] 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.

[1329] 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).

[1330] 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.

[1331] 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.

[1332] 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.

[1333] 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.

[1334] 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.

[1335] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1336] "Example 1"

[1337] One embodiment of the present invention is a system equipped with a means for aggregating information on the market exposure and penetration of brand names, trademarks, etc. related to investment target businesses. Specifically, the system collects information from the Internet and calculates the exposure and penetration of brand names, trademarks, etc. from that information. This calculation is performed based on information such as how often a brand name, trademark, etc. is mentioned on websites or social media, or how many users recognize the brand name, trademark, etc.

[1338] "Example 2"

[1339] Furthermore, it also has a means of weighting factors such as corporate efforts and those of social media influencers. Specifically, weighting is performed by taking into account the influence of corporate marketing and advertising activities, recommendations by social media influencers, etc., on the exposure and penetration of brand names and trademarks. This weighting is based on, for example, the scale of a company's advertising budget and marketing activities, the number of followers of social media influencers, and the number of engagements on their posts.

[1340] "Example 3"

[1341] It also has a means for generating an evaluation report. Specifically, it evaluates the value of brand names, trademarks, etc. based on the above exposure / penetration and weighting results, and outputs the results as a report. This report is used as reference information for investment decisions. For example, the report may include the exposure / penetration of brand names, trademarks, etc., the weighting results, and an evaluation score based on these.

[1342] The processing flow of each embodiment will be described below.

[1343] "Example 1"

[1344] Step 1: The system collects information from the internet by scraping data from websites and social media, obtaining data through APIs, etc.

[1345] Step 2: From the collected information, calculate the exposure and penetration of the brand name, trademark, etc. This calculation is based on information such as how often the brand name, trademark, etc. is mentioned on websites and social media, and how many users recognize the brand name, trademark, etc.

[1346] "Example 2"

[1347] Step 1: Weighting is performed on the exposure and penetration of brand names, trademarks, etc., taking into account the influence of a company's marketing and advertising activities, recommendations by social media influencers, etc. This weighting is based on factors such as the company's advertising budget and the scale of its marketing activities, the number of followers of social media influencers, and the number of engagements on their posts.

[1348] "Example 3"

[1349] Step 1: Based on the above exposure, penetration and weighting results, evaluate the value of the brand name, trademark, etc.

[1350] Step 2: The evaluation results are output as a report. This report can be used as reference information for investment decisions. The report includes the exposure and penetration of brand names and trademarks, weighting results, and an evaluation score based on these.

[1351] Example 1

[1352] Next, a description will be given of Example 1 of Form 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."

[1353] Previous methods for assessing the exposure and penetration of brand names, trademarks, etc. required manual data collection and analysis, which was time-consuming and labor-intensive. Furthermore, there was a lack of means to properly assess the influence of corporate efforts and influencers on social networking services, making accurate assessments difficult. This made it difficult to provide reliable information for investment decisions.

[1354] 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.

[1355] In this invention, the server includes means for receiving prompt text, means for collecting information on the Internet, means for analyzing the collected information, means for calculating the exposure and penetration of brand names, trademarks, etc., means for providing the calculation results, means for weighting factors such as those due to corporate efforts and influencers on social networking services, and means for generating an evaluation report. This makes it possible to automatically and accurately evaluate the exposure and penetration of brand names, trademarks, etc., and provide reliable information for investment decisions.

[1356] A "prompt sentence" is the text of an instruction or question that a user enters into a system.

[1357] "Information on the Internet" refers to data that is publicly available on the Internet, such as on websites and social networking services.

[1358] "Means of collection" refers to technology that automatically obtains information on the Internet using web crawlers and APIs.

[1359] "Means of analysis" refers to techniques that use natural language processing and data mining techniques to analyze collected information and extract meaning and patterns.

[1360] "Exposure and penetration of brand names, trademarks, etc." refers to the degree to which a particular brand name or trademark is mentioned and recognized on the Internet.

[1361] The "means of calculation" refers to the technology that quantifies the exposure and penetration of specific brand names and trademarks based on collected and analyzed data.

[1362] "Means of providing" refers to the technology for displaying the calculation results to the user or outputting them as a report.

[1363] "Corporate efforts" refer to the marketing and promotional activities that a company undertakes to increase brand awareness and reputation.

[1364] "Social networking service influencers" are individuals or organizations that have many followers on social media and have a strong ability to disseminate information.

[1365] "Weighting methods" are techniques that assign appropriate weights to the exposure and penetration of brand names and trademarks, taking into account the influence of corporate efforts and social media influencers.

[1366] An "evaluation report" is a document summarizing the evaluation results, which is created based on the exposure and penetration of brand names and trademarks and the weighting results.

[1367] This invention relates to a system for automatically evaluating the exposure and penetration of brand names, trademarks, etc. related to investment target businesses. This system includes elements of a server, a terminal, and a user.

[1368] First, the user inputs a prompt sentence using a terminal. For example, the prompt sentence is "Please calculate the exposure and penetration of ABC brand." This prompt sentence is sent to the server.

[1369] When the server receives the prompt, it launches a web crawler to collect information from websites and social networking services based on the specified keyword "ABC brand."

[1370] The collected data is analyzed by the server using a natural language processing (NLP) library. During the analysis process, mentions related to brand names, trademarks, etc. are extracted and the number of mentions is counted. Sentiment analysis is also performed and a rating is assigned as positive, negative, or neutral.

[1371] The server then calculates the exposure and penetration of brand names, trademarks, etc. based on the analysis results. The calculation uses the number of mentions and the results of sentiment analysis. In addition, weighting is performed taking into account the influence of corporate efforts and influencers on social networking services.

[1372] The calculation results are generated as an evaluation report. The evaluation report includes an evaluation score based on the exposure and penetration of the brand name, trademark, etc., and the weighting results. The server provides this evaluation report to the user. For example, the result displayed may be, "The exposure and penetration of ABC brand is 85 points."

[1373] This system allows users to automatically and accurately evaluate the exposure and penetration of brand names, trademarks, etc., providing reliable information for investment decisions.

[1374] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1375] Step 1:

[1376] The user uses a terminal to input a prompt sentence. For example, the user inputs the prompt sentence "Please calculate the exposure and penetration of ABC brand." The input prompt sentence is sent to the server. The input is the prompt sentence, and the output is the transmission of the prompt sentence to the server.

[1377] Step 2:

[1378] The server receives the prompt sentence, parses it, and extracts the specified keyword (in this case, "ABC brand"). The input is the prompt sentence, and the output is the extracted keyword.

[1379] Step 3:

[1380] The server launches a web crawler to collect information on the Internet based on the extracted keywords. Specifically, it collects data related to "ABC Brand" from websites and social networking services. The input is the extracted keywords, and the output is the collected data.

[1381] Step 4:

[1382] The server analyzes the collected data using a natural language processing (NLP) library. Specifically, it extracts mentions related to "ABC Brand" from the text data and counts the number of mentions. It also performs sentiment analysis and assigns a positive, negative, or neutral rating. The input is the collected data, and the output is the number of mentions and the results of the sentiment analysis.

[1383] Step 5:

[1384] The server calculates the exposure and penetration of brand names, trademarks, etc. based on the analysis results. The calculation uses the number of mentions and the results of sentiment analysis. In addition, weighting is performed taking into account the influence of corporate efforts and influencers on social networking services. The input is the number of mentions and the results of sentiment analysis, and the output is an exposure and penetration score.

[1385] Step 6:

[1386] The server generates a rating report based on the calculation results. The rating report includes a rating score based on the exposure and penetration of brand names, trademarks, etc. and the weighted results. The input is the exposure and penetration score, and the output is the rating report.

[1387] Step 7:

[1388] The server provides the generated evaluation report to the user. For example, it displays the result "The exposure and penetration of ABC brand is 85 points." The input is the evaluation report, and the output is providing the result to the user.

[1389] (Application example 1)

[1390] Next, a description will be given of Application Example 1 of Form 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."

[1391] Conventional systems for assessing the exposure and penetration of brand names and trademarks have difficulty collecting information from the internet in real time and immediately understanding a brand's exposure and penetration. Furthermore, they lacked the ability to send notifications when exposure and penetration exceeded a certain threshold, making it difficult to quickly adapt marketing strategies. Furthermore, they lacked the ability to generate prompt messages using a generative AI model, leaving advertisers with a lack of guidance for taking specific actions.

[1392] 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.

[1393] In this invention, the server includes means for aggregating information on the market exposure and penetration of brand names, trademarks, etc. related to investment target businesses, means for weighting factors such as corporate efforts and social media influencers, means for generating evaluation reports, means for collecting information on the Internet, means for calculating the exposure and penetration of brand names, trademarks, etc., means for monitoring the exposure and penetration in real time, means for sending notifications when the exposure and penetration exceed a specific threshold, and means for generating prompt messages using a generative AI model. This enables brand exposure and penetration to be grasped in real time, enabling the rapid development and implementation of marketing strategies.

[1394] An "investment target business" is a business that aims to make a profit by investing funds.

[1395] A "brand name" is a name used to identify a particular product or service.

[1396] A "trademark" is a mark or logo that distinguishes a particular product or service from others.

[1397] "Exposure / penetration" refers to the degree to which a brand name or trademark is recognized in the market and by consumers.

[1398] "Corporate efforts" are the activities that companies undertake to penetrate their brands and products into the market.

[1399] A "SNS influencer" is an individual who has a large number of followers and influence on a social networking service.

[1400] "Weighting" refers to the numerical evaluation of the importance or influence of a particular element.

[1401] An "evaluation report" is a report summarizing the evaluation results regarding the exposure and penetration of a brand name or trademark.

[1402] "Information on the Internet" refers to data that exists on online platforms such as websites and social media.

[1403] "Real-time" means that data and information are processed immediately and provided without delay.

[1404] A "notification" is an alert or message sent to a user when a specific condition is met.

[1405] A "generative AI model" is an algorithm or program that uses artificial intelligence to automatically perform specific tasks.

[1406] A "prompt" is an instruction or question input to a generative AI model.

[1407] A system for carrying out this invention has the following configuration: A server includes means for aggregating information on the market exposure and penetration of brand names, trademarks, etc. related to investment target businesses, means for weighting factors such as corporate efforts and social media influencers, means for generating evaluation reports, means for collecting information on the Internet, means for calculating the exposure and penetration of brand names, trademarks, etc., means for monitoring the exposure and penetration in real time, means for sending a notification when the exposure and penetration exceeds a specific threshold, and means for generating prompt sentences using a generative AI model.

[1408] Program processing explanation

[1409] The server first collects information from the Internet. Specifically, it uses the requests library to obtain the content of the web page from the specified URL and extracts the text from the web page. Next, it uses regular expressions to count how often the brand name or trademark is mentioned in the extracted text. Based on this count, it calculates the exposure and penetration of the brand name or trademark.

[1410] The calculated exposure and penetration levels are monitored in real time, and if a certain threshold is exceeded, a notification is sent to the user, allowing them to take immediate action. Furthermore, a generative AI model is used to generate prompts and suggest specific actions to the user.

[1411] The hardware used is a server and a smartphone with an internet connection, and the software uses Python and its libraries. The generative AI model used is, for example, OpenAI's GPT-3.

[1412] Specific examples

[1413] For example, when monitoring the exposure and penetration of Brand A, Brand B, and Brand C, the server collects and calculates in real time how often these brand names are mentioned on social media and websites. If the exposure and penetration exceeds a certain threshold, a notification is sent to the user's smartphone. Furthermore, a generative AI model is used to generate prompt sentences such as the following:

[1414] Prompt Sentence Examples

[1415] "Monitor Brand A's visibility and send a notification when it reaches 1000 social media mentions."

[1416] In this way, users can grasp the brand's exposure and penetration in real time, enabling them to quickly plan and execute marketing strategies.

[1417] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1418] Step 1:

[1419] The server retrieves the web page content from the specified URL. Specifically, it uses the requests library to send an HTTP request and retrieve the HTML data of the web page. The input is a list of URLs, and the output is the HTML data corresponding to each URL.

[1420] Step 2:

[1421] The server extracts text from the retrieved HTML data. Specifically, it parses the HTML and extracts the text content. The input is the HTML data, and the output is the extracted text.

[1422] Step 3:

[1423] The server counts how many times brand names and trademarks are mentioned in the extracted text. Specifically, it counts the number of times a brand name or trademark appears using regular expressions. The input is text data and a list of brand names, and the output is the number of times each brand name appears.

[1424] Step 4:

[1425] The server calculates the exposure and penetration of brand names and trademarks based on the counting results. Specifically, it quantifies the exposure and penetration based on the number of appearances. The input is the number of appearances of the brand name, and the output is the numerical value of the exposure and penetration.

[1426] Step 5:

[1427] The server monitors the calculated exposure and penetration in real time. Specifically, it sends a notification when the exposure and penetration exceeds a certain threshold. The input is the exposure and penetration value and the threshold, and the output is a notification message.

[1428] Step 6:

[1429] The server generates prompts using a generative AI model. Specifically, it generates prompts that suggest specific actions to the user based on exposure and penetration data. The input is exposure and penetration data, and the output is the generated prompt.

[1430] Step 7:

[1431] The user receives the notification and prompt text sent from the server and plans and executes an appropriate marketing strategy. Specifically, based on the notification message and prompt text, the user takes action according to the brand's exposure and penetration. The input is the notification message and prompt text, and the output is the user's action.

[1432] Example 2

[1433] Next, a description will be given of Example 2 of Form 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."

[1434] Conventional methods for assessing the exposure and penetration of brand names and trademarks do not adequately take into account factors such as a company's advertising budget, the scale of marketing activities, or the influence of social media influencers, making accurate assessments difficult. Furthermore, there was a lack of specific proposals for improving marketing strategies based on the assessment results.

[1435] 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.

[1436] In this invention, the server includes: means for aggregating information on the market exposure and penetration of brand names, trademarks, etc. related to the investment target business; means for collecting data such as a company's advertising budget and the scale of its marketing activities, and the number of followers and post engagements of social media influencers; means for analyzing the collected data and weighting the exposure and penetration of the brand names and trademarks; means for generating an evaluation report; and means for generating prompt sentences to be input into the generative AI model. This enables accurate brand evaluation that takes into account a company's advertising budget, the scale of its marketing activities, and the influence of social media influencers.

[1437] "Investment target business" refers to any business that aims to make a profit by investing funds.

[1438] "Brand name" refers to a name used to identify a particular product or service.

[1439] "Trademark" refers to a logo, symbol, design, etc. used to identify a particular product or service.

[1440] "Exposure and penetration" refers to the degree to which a brand name or trademark is recognized in the market and by consumers.

[1441] A "company's advertising budget" refers to the total amount of funds a company plans to spend on advertising activities.

[1442] The "scale of marketing activities" refers to the scope and influence of a company's marketing activities.

[1443] A "SNS influencer" refers to an individual who has a large number of followers and influence on a social networking service.

[1444] "Number of followers" refers to the number of users who follow a social media influencer's account.

[1445] "Engagement count" refers to the total number of user reactions (likes, comments, shares, etc.) to a social media influencer's post.

[1446] "Means of collecting data" refers to the methods and tools used to obtain the required data.

[1447] "Means of analyzing data" refers to the methods and tools used to process collected data and convert it into meaningful information.

[1448] "Weighting means" refers to a method or tool for assigning importance to a particular element.

[1449] "Means for generating an evaluation report" refers to methods and tools for creating a report summarizing the evaluation results based on the analysis results.

[1450] A "generative AI model" refers to a model that has been trained using artificial intelligence to perform a specific task.

[1451] A "prompt sentence" refers to an instruction sentence to be input into a generative AI model.

[1452] This invention is a system that generates an evaluation report by weighting the exposure and penetration of brand names and trademarks, taking into account the influence of corporate marketing activities and social media influencers. Specific embodiments of this system are described below.

[1453] System configuration

[1454] This system consists of three main components: a server, a terminal, and a user. The server collects data, analyzes it, calculates weights, and generates evaluation reports. The terminal provides an interface for users to access the system and check the results. The user operates the system and inputs the necessary data.

[1455] Hardware and software used

[1456] The server uses a specified API for data collection, a Python library for data analysis, and a tool for outputting data in JSON format and displaying it on a dashboard to generate an evaluation report.

[1457] Data collection

[1458] The server collects data such as a company's advertising budget and the scale of its marketing activities, as well as the number of followers and post engagements of social media influencers. Specifically, it calls an API to obtain the company's advertising campaign data and uses an API to obtain the number of followers and engagements of social media influencers.

[1459] Data analysis

[1460] The server analyzes the collected data. This analysis involves data cleansing (completion of missing values ​​and removal of outliers) and data normalization (scaling). Specifically, a Python library is used to create a data frame, complement missing values, and normalize the data.

[1461] Weighting Calculation

[1462] Based on the analyzed data, the server assigns weights to the exposure and penetration of brand names and trademarks. This weighting is calculated taking into account the company's advertising budget and the scale of its marketing activities, as well as the number of followers and engagement of social media influencers. The specific calculation formula is as follows:

[1463] Weight = (Advertising budget score 0.5) + (Marketing activity score 0.3) + (Social media influencer score 0.2)

[1464] Here, each score is a normalized value.

[1465] Generate an assessment report

[1466] The server generates a rating report based on the calculated weighting results. This rating report includes the exposure and penetration of the brand name or trademark and a rating score based on the weighting results. The rating report is output in JSON format and displayed on the dashboard.

[1467] Specific examples

[1468] For example, suppose that Company A has an annual advertising budget of 100 million yen, and Social Media Influencer B has 1 million followers and 100,000 engagements on its posts. In this case, the server would operate as follows:

[1469] 1. The server calls a specified API to obtain Company A's advertising campaign data.

[1470] 2. The server uses a specified API to obtain the number of followers and engagements of influencer B.

[1471] 3. The server analyzes the acquired data using the library, imputes missing values, and normalizes them using the library.

[1472] 4. The server uses a weighting formula to assign weights to the exposure and penetration of the brand name or trademark.

[1473] 5. The server outputs the calculation results in JSON format and displays them on the dashboard.

[1474] An example of a prompt to input to a generative AI model is as follows:

[1475] "Company A's annual advertising budget is 100 million yen, and social media influencer B has 1 million followers and 100,000 engagements on their posts. Based on this data, please assign weights to the exposure and penetration of brand names and trademarks."

[1476] In this way, the server provides a system that evaluates the exposure and penetration of brand names and trademarks by weighting the influence of corporate marketing activities and social media influencers.

[1477] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1478] Step 1:

[1479] The server collects data such as a company's advertising budget and the scale of its marketing activities, as well as the number of followers and post engagements of social media influencers. Specifically, it calls an API to obtain the company's advertising campaign data and uses an API to obtain the number of followers and engagements of social media influencers. The input is the raw data obtained from the API, and the output is the collected dataset.

[1480] Step 2:

[1481] The server analyzes the collected data. This analysis involves cleansing the data (filling in missing values ​​and removing outliers) and normalizing (scaling) it. Specifically, a Python library is used to create a data frame and fill in missing values. A Python library is also used to normalize the data. The input is the collected dataset, and the output is the cleansed and normalized data.

[1482] Step 3:

[1483] The server then assigns weights to the exposure and penetration of brand names and trademarks based on the analyzed data. The specific calculation formula is as follows:

[1484] Weight = (Advertising budget score 0.5) + (Marketing activity score 0.3) + (Social media influencer score 0.2)

[1485] Here, each score is a normalized value: the input is the cleansed and normalized data, and the output is a weighted evaluation score.

[1486] Step 4:

[1487] The server generates an evaluation report based on the calculated weighting results. The evaluation report is output in JSON format and displayed on a dashboard. Specifically, a report containing the evaluation scores is generated and made accessible to users. The input is the weighted evaluation score, and the output is the evaluation report.

[1488] Step 5:

[1489] The server generates prompts to be input to the generative AI model. Specifically, it generates prompts like the following based on data such as the company's advertising budget and the number of followers and engagement of social media influencers:

[1490] "Company A's annual advertising budget is 100 million yen, and social media influencer B has 1 million followers and 100,000 engagements on their posts. Based on this data, please assign weights to the exposure and penetration of brand names and trademarks."

[1491] The input is data about companies and social media influencers, and the output is the generated prompt sentence.

[1492] (Application example 2)

[1493] Next, a description will be given of Application Example 2 of Form 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."

[1494] Traditional methods for evaluating advertising campaigns make it difficult to comprehensively consider a company's advertising budget, the scale of its marketing activities, and the influence of social media influencers, resulting in insufficient optimization of advertising strategies. Real-time evaluation is also difficult, making it unsuitable for the modern marketing environment, which requires rapid strategic changes. This results in the inability to maximize advertising effectiveness and reduces the efficiency of a company's investment.

[1495] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1496] In this invention, the server includes means for aggregating information on the market exposure and penetration of brand names, trademarks, etc. related to the investment target business, means for weighting factors such as corporate efforts and SNS influencers, means for generating an evaluation report, means for evaluating the effectiveness of advertising campaigns in real time, and means for optimizing advertising strategies taking into account the influence of SNS influencers. This makes it possible to comprehensively evaluate the effectiveness of a company's advertising campaigns in real time and to formulate optimal advertising strategies taking into account the influence of SNS influencers.

[1497] An "investment target business" is a business in which a company invests funds in the hope of achieving growth and profits.

[1498] A "brand name" is a name used to identify a specific product or service, and serves to assure consumers of the reliability and quality of that product or service.

[1499] A "trademark" is a mark, logo, or symbol used by a company to distinguish its products or services from those of other companies.

[1500] "Exposure and penetration" indicates the degree to which a brand name or trademark is recognized and accepted by the market and consumers.

[1501] "Corporate efforts" refers to the marketing and advertising activities that companies undertake to increase awareness and sales of their products and services.

[1502] A "social media influencer" is someone who has a large number of followers on a social networking service and uses their influence to recommend specific products or services.

[1503] "Weighting" refers to the numerical evaluation of the importance or influence of a particular element or data.

[1504] An "evaluation report" is a report prepared based on specific data and information, and includes evaluation and analysis results.

[1505] An "advertising campaign" is a series of advertising activities undertaken to increase awareness and sales of a particular product or service.

[1506] "Real-time" refers to data and information being processed and analyzed as soon as it is generated.

[1507] An "advertising strategy" refers to the advertising policies and methods that a company plans to use to effectively promote its products and services in the market.

[1508] The system for implementing this invention consists of three main elements: a server, a terminal, and a user. The server includes a means for aggregating the extent of exposure and penetration of brand names and trademarks related to investment target businesses in the market, a means for weighting the influence of corporate efforts and SNS influencers, a means for generating evaluation reports, a means for evaluating the effectiveness of advertising campaigns in real time, and a means for optimizing advertising strategies taking into account the influence of SNS influencers.

[1509] Program processing explanation

[1510] The server first aggregates the exposure and penetration of brand names and trademarks. This is done using web scraping technology and social media analysis tools. Specific software used is Python and social media APIs.

[1511] Next, we weight the influence of corporate efforts and social media influencers. We do this based on the size of a company's advertising budget and marketing activities, as well as the number of followers and engagement of social media influencers. We use Python as a data analysis tool.

[1512] To generate an evaluation report, an evaluation score is calculated based on the aggregated data and weighted results, using a data visualization tool.

[1513] To evaluate the effectiveness of the advertising campaign in real time, the server uses real-time data processing techniques, specifically, a stream processing framework.

[1514] Finally, we optimize advertising strategies by taking into account the influence of social media influencers, using machine learning models and machine learning libraries such as TensorFlow.

[1515] Specific examples

[1516] For example, consider a case where the advertising budget is 5 million yen, the scale of marketing activities is 80, the number of followers of social media influencers is 200,000 and 150,000, and the engagement numbers are 5,000 and 3,000. Based on this data, the server calculates the weighting and optimizes the advertising strategy.

[1517] Example prompts to input to a generative AI model:

[1518] If the advertising budget is 5 million yen, the scale of marketing activities is 80, the number of followers of social media influencers is 200,000 and 150,000, and the engagement numbers are 5,000 and 3,000, calculate the weightings to optimize the advertising strategy.

[1519] In this way, the server comprehensively evaluates the effectiveness of a company's advertising campaign in real time and helps develop optimal advertising strategies that take into account the influence of social media influencers.

[1520] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1521] Step 1:

[1522] The server aggregates the exposure and penetration of brand names and trademarks. Specifically, it collects data from the internet using web scraping technology and social media analysis tools. It receives keywords related to brand names and trademarks as input and generates a list of web pages and social media posts containing those keywords as output.

[1523] Step 2:

[1524] The server uses the aggregated data to weight the influence of corporate efforts and social media influencers. Specifically, it receives inputs such as a company's advertising budget and the scale of its marketing activities, as well as the number of followers and engagement of social media influencers, and processes this data using Python. As output, it generates a weighted score for each factor.

[1525] Step 3:

[1526] The server generates an evaluation report based on the weighting results. Specifically, it receives the aggregated data and weighted scores as input, calculates the evaluation score using a data visualization tool, and generates an evaluation report as output, saved as a PDF file containing graphs and charts.

[1527] Step 4:

[1528] The server evaluates the effectiveness of the advertising campaign in real time. Specifically, it uses real-time data processing technology to monitor the progress and effectiveness of the advertising campaign. As input, it receives and processes the data stream of the advertising campaign. As output, it generates real-time evaluation results and displays them on a dashboard.

[1529] Step 5:

[1530] The server optimizes advertising strategies by taking into account the influence of social media influencers. Specifically, it uses a machine learning model to propose optimal advertising strategies. As input, it receives evaluation reports and real-time evaluation results, and trains the model using TensorFlow. As output, it generates an optimized advertising strategy and proposes it to the company.

[1531] In this way, the server comprehensively evaluates the effectiveness of a company's advertising campaign in real time and helps develop optimal advertising strategies that take into account the influence of social media influencers.

[1532] Example 3

[1533] Next, a third embodiment of the third embodiment will be described. 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."

[1534] There is a need to accurately evaluate the exposure and penetration of brand names and trademarks in the market and generate evaluation reports based on the results to serve as a reference for investment decisions. However, conventional methods often involve manual data collection and analysis, which is inefficient and lacks objectivity and accuracy in evaluation. Furthermore, there is also the issue of ambiguous weighting criteria, which results in low reliability of evaluation scores.

[1535] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1536] In this invention, the server includes a means for aggregating the market exposure and penetration of brand names, trademarks, etc., a means for analyzing collected data using natural language processing technology, a means for weighting based on the exposure and penetration, a means for calculating an evaluation score, and a means for generating an evaluation report. This automates the process from data collection to analysis and generation of an evaluation report, making it possible to efficiently and accurately evaluate brand value.

[1537] "Brand names, trademarks, etc." refer to names and marks used to identify specific products or services in the market.

[1538] "Exposure and penetration" refers to the degree to which a brand name or trademark is recognized and influenced by the market and consumers.

[1539] "Aggregation methods" refers to the methods and techniques used to collect data from multiple sources and compile it into a single dataset.

[1540] "Natural language processing technology" refers to technology that allows computers to analyze and understand human language.

[1541] "Means of analysis" refers to methods and techniques for analyzing collected data and extracting useful information.

[1542] "Weighting methods" refer to methods or techniques for assessing the importance or impact of data and assigning numerical weights based on that assessment.

[1543] "Evaluation score" refers to a number that indicates the value of a brand, calculated based on exposure, penetration, and weighting results.

[1544] "Evaluation Report" refers to a document summarizing the evaluation results, including the exposure and penetration of brand names and trademarks, weighting results, evaluation scores, etc.

[1545] This invention is a system that evaluates the exposure and penetration of brand names and trademarks in the market and generates an evaluation report based on the results. A specific embodiment of this system will be described below.

[1546] The server first collects data related to brand names and trademarks from the internet. This data is obtained from online sources such as social media, news articles, blogs, and forums. Web scraping technology and APIs are used to collect the data. Specifically, designated APIs can be used.

[1547] The server then analyzes the collected data. This analysis uses natural language processing (NLP) technology, specifically analyzing the sentiment of the text data and extracting keywords. This allows the exposure and penetration of brand names and trademarks to be calculated.

[1548] The server then assigns weights based on the analysis results. Weighting is an important step in assessing a brand's market value and influence. For example, a brand with high exposure receives a higher weight, while a brand with low penetration receives a lower weight. This results in an overall evaluation score.

[1549] Finally, the server generates a rating report based on the rating scores. This report includes the exposure and penetration of the brand name or trademark, the weighting results, and the rating scores. The report is output in PDF format and can be downloaded by users.

[1550] As a specific example, when generating a rating report for a brand "ABC," the server performs the following steps:

[1551] 1. The server collects online data about "ABC".

[1552] 2. The server analyzes the data and calculates exposure and penetration.

[1553] 3. The server calculates a rating score based on the weighting of exposure and penetration.

[1554] 4. The server generates an evaluation report based on the evaluation score and outputs it in PDF format.

[1555] Example prompts to input to a generative AI model:

[1556] "Evaluate the exposure and penetration of brand ABC and generate an evaluation report. The report should include exposure and penetration, weighting results, and evaluation score."

[1557] In this way, the user can obtain a detailed report for evaluating the value of the brand. The flow of the identification process in the third embodiment will be described with reference to FIG.

[1558] Step 1: Data collection

[1559] The server collects data related to brand names and trademarks from the internet. As input, it receives keywords related to the brand names and trademarks. Specifically, it obtains data from online sources such as social media, news articles, blogs, and forums. It uses web scraping technology and APIs to collect the data. For example, it uses a specific API to collect related tweets and news articles. The output is the collected text data.

[1560] Step 2: Data analysis

[1561] The server analyzes the collected text data. As input, it receives the text data collected in step 1. This analysis uses natural language processing (NLP) technology. Specifically, it performs sentiment analysis and keyword extraction on the text data. For example, a tweet saying "Brand ABC is great" is analyzed as having a positive sentiment. As output, it obtains exposure and penetration data as the analysis results.

[1562] Step 3: Calculating weights and evaluation scores

[1563] The server assigns weights based on the analysis results. As input, it receives the exposure and penetration data obtained in step 2. Weighting is an important step in evaluating a brand's market value and influence. For example, if exposure is high, a high weight is assigned, and if penetration is low, a low weight is assigned. This is how an overall evaluation score is calculated. As output, the weighted result and evaluation score are obtained.

[1564] Step 4: Generate an assessment report

[1565] The server generates a rating report based on the rating scores. As input, it receives the weighting results and rating scores obtained in step 3. This report includes the exposure and penetration of the brand name or trademark, the weighting results, and the rating scores. Specifically, the report is generated in PDF format and made available for download by the user. As output, the rating report is obtained.

[1566] In this way, users can get detailed reports to assess the value of their brand.

[1567] (Application example 3)

[1568] Next, a description will be given of Application Example 3 of Form Example 3. 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."

[1569] Conventional brand name and trademark evaluation systems lack real-time calculations of exposure and penetration, making it difficult to immediately evaluate the effectiveness of advertising campaigns. Furthermore, when generating evaluation reports, the input of prompts using generative AI models is not taken into account, resulting in problems with reduced evaluation accuracy and efficiency. This resulted in a lack of reliability as reference information for investment decisions.

[1570] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1571] In this invention, the server includes means for aggregating information on the market exposure and penetration of brand names, trademarks, etc. related to the investment target business, means for weighting factors such as corporate efforts and social media influencers, means for generating an evaluation report, means for evaluating the effectiveness of the advertising campaign in real time, means for calculating the degree of exposure and penetration, means for calculating the weighted results, means for calculating an evaluation score, means for outputting the evaluation report, and means for inputting prompt sentences using a generative AI model. This makes it possible to evaluate the effectiveness of the advertising campaign in real time and quickly generate highly accurate evaluation reports.

[1572] "Investment target business" refers to the company or project that is the target of investment.

[1573] A "brand name" refers to a name used to identify a particular product or service.

[1574] A "trademark" refers to a mark or logo that identifies a particular product or service.

[1575] "Exposure" refers to an indicator that shows how often a brand name or trademark appears in the market or media.

[1576] "Penetration" refers to an indicator that shows how well a brand name or trademark is recognized in the market and among consumers.

[1577] "Corporate efforts" refers to the marketing and promotional activities that a company undertakes itself.

[1578] A "social media influencer" is an individual or organization that has a large following and influence on social media.

[1579] "Weighting" refers to a method for assigning importance to different elements.

[1580] An "evaluation report" refers to a report that summarizes the exposure and penetration of a brand name or trademark, weighting results, evaluation scores, etc.

[1581] An "advertising campaign" refers to a series of advertising activities to promote a particular brand or product.

[1582] "Real-time" refers to data and information being processed immediately.

[1583] A "generative AI model" refers to a model that uses artificial intelligence to generate data.

[1584] A "prompt" refers to an instruction sentence that is input into a generative AI model.

[1585] "Exposure" refers to an indicator of how many people see an advertisement or brand.

[1586] "Penetration" is an indicator that shows how many people are aware of an advertisement or brand.

[1587] "Weighted results" refers to results that reflect the weights assigned to different factors.

[1588] "Evaluation score" refers to a comprehensive evaluation value calculated based on exposure, penetration, and weighting results.

[1589] The system for implementing this invention consists of three main elements: a server, a terminal, and a user. The following explains how each element functions.

[1590] server

[1591] The server plays a central role in aggregating the exposure and penetration of brand names and trademarks and generating evaluation reports. Specifically, it performs the following processes:

[1592] 1. Data Collection and Aggregation:

[1593] The server collects advertising campaign data and calculates the exposure and penetration of brand names and trademarks, including data such as impressions, click-through rates, unique visitors, and total population.

[1594] 2. Calculating weights:

[1595] The server assigns weights based on the company's efforts and the exposure and penetration of social media influencers, and calculates weighted results that reflect the importance of each factor.

[1596] 3. Calculation of the rating score:

[1597] The server calculates a rating score based on the weighting results. The rating score is a comprehensive rating value that combines the exposure, penetration, and weighting results.

[1598] 4. Generate an...

Claims

1. A first means for collecting advertising campaign data; a second means for generating a first prompt sentence for outputting an evaluation report for evaluating the effectiveness of the advertising campaign based on the data of the advertising campaign; a third means for inputting the generated first prompt sentence into a generative AI model to generate the evaluation report; A fourth means for transmitting the generated evaluation report to a user terminal; A system including:

2. A fifth means of collecting information on the Internet; and a sixth means for calculating an exposure level of the predetermined brand name based on a count result of how many times the predetermined brand name is mentioned on the Internet from the information on the Internet, The second means generates a second prompt sentence for sending a notification to the user's terminal when the exposure of the specified brand name on the SNS exceeds a certain threshold, based on the exposure of the specified brand name. The system of claim 1 .

3. and a seventh means for sending a notification to the user's terminal when the exposure of the predetermined brand name on the SNS exceeds a specific threshold. The system of claim 2.

Images