system

Abstract

Provide a system. A means for inputting a specific keyword; a means for collecting data via the internet; A means of analyzing the collected data and extracting specific target name recognition and target demographic attribute information; A means for providing the analysis results to users; A system including:

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] Traditional methods for investigating the name recognition and awareness of companies and brands, as well as target audience demographic information, in real time required a great deal of time and effort. Furthermore, there was a lack of easy ways to obtain detailed target demographic data, which is necessary for effectively formulating marketing and sales strategies. A system that can solve these problems is needed. [Means for solving the problem]

[0005] This invention proposes a system that includes a means for inputting specific keywords, a means for collecting data via the Internet, a means for analyzing the collected data to extract specific target name recognition and attribute information for the target demographic, and a means for providing the analysis results to users. This allows users to easily obtain information on company and brand name recognition and recognition, as well as the target demographic's age distribution, gender distribution, and interests in real time. Furthermore, by utilizing social media APIs as a data collection method, data acquisition is achieved quickly and efficiently.

[0006] "Specific keywords" refer to proper nouns or related phrases entered by the user for the system to search.

[0007] "Means of collecting data via the Internet" refers to means of obtaining data related to specified keywords using technologies such as social media APIs and web crawlers.

[0008] "Means of analyzing collected data and extracting specific target name recognition and attribute information of the target demographic" refers to means of processing collected data and extracting name recognition scores, age distribution, gender distribution, and interests of the target demographic using statistical methods, etc.

[0009] "Means for providing analysis results to users" refers to an interface for displaying analyzed data to users and means for transmitting result data to users.

[0010] "Awareness" is an indicator that shows how well a company or brand associated with a particular keyword is known to the general public.

[0011] "Age distribution of the target demographic" is information that indicates the age ratio of users who are interested in the company or brand being surveyed.

[0012] "Gender distribution of target demographic" is information that indicates the gender ratio of users who are interested in the company or brand being surveyed.

[0013] "Interest information" is information that identifies the hobbies and interests of users who are interested in the company or brand being surveyed.

[0014] A "social media API" is an application program interface provided by a social media platform and is a technology used to obtain data related to specific keywords. [Brief explanation of the drawings]

[0015] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0016] 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.

[0017] First, the terms used in the following description will be explained.

[0018] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0019] 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.

[0020] 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.

[0021] 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.

[0022] 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."

[0023] [First embodiment]

[0024] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0025] 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.

[0026] 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).

[0027] 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.

[0028] 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.

[0029] 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.

[0030] 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.

[0031] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0036] The present invention is a system that includes a means for inputting specific keywords, a means for collecting data via the Internet, a means for analyzing the collected data and extracting specific target name recognition and attribute information of the target demographic, and a means for providing the analysis results to the user.

[0037] Program processing flow

[0038] 1. User Request Submission

[0039] A user enters a specific keyword into the system's interface (e.g., a web browser or a mobile application), then clicks a "Start Search" button on the interface to send a request to the server, which includes the keyword entered by the user.

[0040] 2. Server receives request and starts processing

[0041] The server receives a user request and calls the user_request_handler function. It extracts keywords from the request and gets them as keyword = request['keyword']. The server then calls the process_request function to start collecting data based on the keywords.

[0042] 3. Data Collection

[0043] The server uses the gather_data(keyword) function to gather relevant data from social media and the web. It uses social media APIs and web crawler technology to obtain data related to the specified keyword. Specifically, it sends an API request and receives the relevant data as a response.

[0044] 4. Data analysis and information extraction

[0045] The server passes the data obtained by the gather_data function to the analyze_data(data) function and performs the analysis. Based on the collected data, it uses statistical methods to analyze the awareness score, target demographic age distribution, gender distribution, and interests to extract the necessary attribute information. For example, the awareness score is calculated based on "mentions = data.get('mentions')", and awareness is calculated as "awareness = mentions / 1000".

[0046] Information about the target demographic includes the age distribution (target_age = { "20-30": 50, "30-40": 30, "40-50": 20}), the gender distribution (target_gender = { "male": 60, "female": 40}), and interests (interests = ["tech", "sports", "music"]).

[0047] 5. Providing results

[0048] The server formats the analysis results in JSON format and prepares them for the user. Next, it sends the results back to the user via the user_request_handler function, and the user receives the analysis results. Based on these results, the user can develop marketing and sales strategies.

[0049] Specific examples

[0050] For example, if a user starts a survey on "TestBrand," the server receives a request with "TestBrand" entered and collects data. Assume that data related to "TestBrand" is obtained through a social media API and the number of mentions is 850. For example, if you enter "data = {'mentions': 850}," the name recognition is calculated as "850 / 1000 = 0.85." The target demographic's age distribution, gender distribution, and interest information are also analyzed and returned as results. For example, information such as "50% are 20-30 years old, 60% are male, 40% are female, and their interests are technology, sports, and music" can be obtained.

[0051] This system allows users to quickly and easily obtain detailed attribute information about "TestBrand" and its target demographic, and based on this information, they can formulate appropriate marketing and sales strategies.

[0052] The processing flow will be explained below.

[0053] Step 1:

[0054] The user enters a proper noun. The user enters keywords for a specific company or brand into the system's interface. Then, the user clicks the "Start Search" button, which sends a request to the server. This request includes the keywords entered by the user.

[0055] Step 2:

[0056] The server receives the request. The server receives the user request and calls the user_request_handler function. It extracts keywords from the request and gets the keyword information with keyword = request['keyword'].

[0057] Step 3:

[0058] The server starts data collection. The server calls the process_request function to start collecting data based on the keyword. Specifically, it uses the gather_data(keyword) function to gather relevant data from social media and the web.

[0059] Step 4:

[0060] The server collects data over the Internet. The gather_data(keyword) function retrieves data related to the specified keyword using social media APIs or web crawlers. It sends an API request and receives the relevant data as a response.

[0061] Step 5:

[0062] The server analyzes the data. The server passes the data obtained by the gather_data function to the analyze_data(data) function and performs data analysis. Here, the collected data is used to statistically analyze the recognition of specific targets, the age distribution, gender distribution, and interest information of the target demographic.

[0063] Step 6:

[0064] The server calculates the popularity. For example, if the acquired data contains "mentions = 850", the popularity is calculated as "850 / 1000 = 0.85".

[0065] Step 7:

[0066] The server extracts the target demographic's attribute information. The target demographic's age distribution, gender distribution, and interest information are extracted from the data. For example, the age distribution would be "target_age = { "20-30": 50, "30-40": 30, "40-50": 20}", the gender distribution would be "target_gender = { "male": 60, "female": 40}", and the interests would be "interests = ["tech", "sports", "music"]".

[0067] Step 8:

[0068] The server formats the analysis results in JSON format and prepares them for delivery to the user. Specifically, it converts the results to JSON format using json.dumps(analysis_result).

[0069] Step 9:

[0070] The server returns the results to the user. The server returns the analysis results to the user via the user_request_handler function. The user can receive these results and use them to formulate marketing and sales strategies.

[0071] Example 1

[0072] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0073] In today's world, for companies to develop effective marketing and sales strategies, data such as demographic information on target demographics and the popularity of specific keywords is essential. However, there is a lack of efficient ways to collect and analyze this data, making it difficult to quickly and accurately obtain the information you want.

[0074] 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.

[0075] In this invention, the server includes a means for inputting specific keywords, a means including a social media API and a web crawler for collecting data via the Internet, a statistical analysis means for analyzing the collected data and extracting specific target name recognition, age distribution, gender distribution, and interest information of the target demographic, and a means for formatting the analysis results in JSON format and providing them to users. This enables companies to quickly and accurately obtain detailed attribute information and name recognition data of their target demographics and develop effective marketing and sales strategies.

[0076] The "means for entering specific keywords" refers to the interface (web browser or mobile application) through which users enter the keywords they wish to research.

[0077] "Methods for collecting data via the internet, including social media APIs and web crawlers" refers to technologies for automatically collecting relevant data from social media and web pages on the internet.

[0078] "Statistical analysis means for analyzing collected data and extracting the name recognition of specific targets, the age distribution, gender distribution, and interest information of the target demographic" refers to programs or algorithms for analyzing collected data and extracting the name recognition of specific targets and attribute information of the target demographic (age distribution, gender distribution, interest information) using statistical methods.

[0079] "Means for formatting the analysis results in JSON format and providing them to users" refers to a technology for formatting the analysis results in a structured data format (JSON: JavaScript (registered trademark) Object Notation) and providing it to users.

[0080] The present invention provides a system for allowing a user to input a specific keyword, collecting data related to the keyword via the Internet, and providing analysis results. The system comprises the following means.

[0081] First, the user enters the keywords to be investigated using the system interface (web browser or mobile application). The interface has a "Start Investigation" button, and when the user clicks this, the keywords are sent to the server.

[0082] The server receives a request from a user and extracts the keywords included in the request. The server then begins collecting data based on the specified keywords. Specifically, it uses social media APIs and web crawler technology on the Internet to collect related data. For example, social media APIs can be used to obtain post and comment data related to specific keywords. It is also possible to use web crawlers to scrape information from related web pages.

[0083] The collected data is analyzed on the server. During the analysis, specific target name recognition, age distribution, gender distribution, and interest information of the target demographic are extracted from the data. These analyses are performed using statistical methods to extract attribute information. For example, a name recognition score is calculated based on the number of mentions in the collected data, and age distribution, gender distribution, and interest information of the target demographic are also statistically organized.

[0084] Finally, the server formats the analysis results into JSON format and prepares them for delivery to the user. The analysis results are converted into a structured data format (JSON: JavaScript Object Notation) and sent back to the user. The user can check the analysis results on the interface and use them to develop marketing and sales strategies.

[0085] Specific examples

[0086] For example, if a user starts a survey on "TestBrand", the following will happen:

[0087] The user enters "TestBrand" into the system's web interface and clicks the "Start Survey" button.

[0088] The server receives this request and extracts keyword = 'TestBrand'.

[0089] The server calls the gather_data('TestBrand') function to gather data using social media APIs and web crawlers. For example, if there are 850 mentions, the server gets "data = {'mentions': 850}".

[0090] The server passes this data to the analyze_data(data) function, extracting a popularity score of 0.85 and target demographic attributes: target_age = { '20-30': 50, '30-40': 30, '40-50': 20}, target_gender = { 'male': 60, 'female': 40}, and interests = ['tech', 'sports', 'music'].

[0091] The server formats the analysis results into JSON format and returns them to the user, who can then use this information to develop specific marketing strategies.

[0092] This system allows users to quickly and easily obtain detailed information about the brand awareness of "TestBrand" and the attributes of their target demographic, and use this information to develop effective marketing and sales strategies.

[0093] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0094] Step 1:

[0095] The user opens the system interface (web browser or mobile application) and enters a specific keyword. After entering the keyword, the user clicks the "Start Search" button, which sends the request to the server. The input data is the specific keyword entered by the user. The output data is the request sent to the server.

[0096] Step 2:

[0097] The server receives a user request and extracts keywords from the request. In this process, the server executes keyword = request['keyword'] from the request. The input is the request sent by the user, and the output is the extracted keywords.

[0098] Step 3:

[0099] The server uses the extracted keywords to call the gather_data(keyword) function to gather related data from the Internet. This process involves using social media APIs and web crawler technology to obtain data. Specifically, it sends requests to social media APIs to obtain related post and comment data, and uses web crawlers to scrape related web pages. The input is the keywords, and the output is the collected related data.

[0100] Step 4:

[0101] The server passes the collected data to the analyze_data(data) function to perform data analysis. During the analysis, specific target awareness, age distribution, gender distribution, and interest information of the target demographic are extracted using statistical methods. For example, the awareness score is calculated based on "mentions = data.get('mentions')" and "awareness = mentions / 1000". In addition, age distribution, gender distribution, and interest information are statistically organized from the collected data. The input is the collected data, and the output is the analysis results.

[0102] Step 5:

[0103] The server formats the analysis results in JSON format and prepares them for delivery to the user. During this process, the server converts the analysis results into JSON format as follows: json_result = json.dumps(analysis_result) . The formatted JSON result is sent back to the user. The input is the analysis result, and the output is the analysis result in JSON format.

[0104] Step 6:

[0105] Users receive the analysis results provided through the system interface and use that data to develop marketing and sales strategies. The input is the analysis results in JSON format, and the output is the basis for the strategy developed by the user.

[0106] This specific processing flow enables users to quickly and accurately obtain detailed attribute information and name recognition data for their target demographic, and to formulate effective strategies based on this information.

[0107] (Application example 1)

[0108] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0109] While conventional systems were capable of collecting and analyzing brand awareness and target demographic information related to specific keywords, they lacked a way for users to easily check the results in real time. Furthermore, the analysis results were not sufficiently visualized, making it difficult for users to quickly and effectively utilize them in their marketing strategies. Therefore, there is a need for real-time visualization of collected data and for improvements in the method of providing analysis results through that visualization.

[0110] 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.

[0111] In this invention, the server includes a means for inputting specific keywords, a means for collecting data via the Internet, a means for analyzing the collected data and extracting specific target name recognition and target demographic attribute information, a means for providing the analysis results to the user, and a means for visualizing the results on a smart device. This allows the analysis results to be visually displayed on the smart device in real time, allowing the user to quickly and effectively formulate a marketing strategy.

[0112] "Specific keywords" are words or phrases that users enter into the system and select for analysis.

[0113] "Means of collecting data via the internet" refers to the functions and technologies used to obtain information from websites and social media.

[0114] "Means of analyzing collected data and extracting specific target name recognition and target demographic attribute information" refers to functions and technologies that use statistical methods based on collected data to derive name recognition scores and target demographic attributes (age, gender, interests).

[0115] "Means for providing analysis results to users" refers to the functions and technologies for notifying and displaying the analyzed information to users.

[0116] "Means for visualizing results on smart devices" refers to functions and technologies for graphically displaying analysis results on digital devices such as smartphones and tablets.

[0117] A "social media API" is a programmatic interface for retrieving data from social media platforms such as Twitter and Facebook.

[0118] "Display in real time" means that collected and analyzed data is displayed to the user immediately without delay.

[0119] This invention is a system that inputs specific keywords, collects data via the Internet, analyzes the data, extracts name recognition and target demographic attribute information, and finally provides the analysis results to users. Furthermore, this system includes a means for visualizing the results on a smart device.

[0120] Hardware

[0121] Server: High-performance cloud server (e.g., Amazon Web Services, Google Cloud Platform)

[0122] Smart device: Smartphone (ANDROID (registered trademark) or iOS)

[0123] software

[0124] Smartphone application: Swift (iOS), Kotlin (Android)

[0125] Data collection: Python, Requests library, social media APIs (e.g. Twitter API, Facebook Graph API)

[0126] Data analysis: Python, Pandas, NumPy, scikit-learn

[0127] Server-side framework: Django or Flask (Python)

[0128] Program Overview

[0129] The server provides an interface for entering specific keywords, and once the user enters the keywords, data collection begins. The server collects data using social media APIs and analyzes the data to extract name recognition scores and target demographic attribute information. The analysis results are visualized in real time on a smart device, allowing users to quickly develop marketing strategies based on the results.

[0130] Processing flow

[0131] 1. User submits request:

[0132] Using a smartphone application, a user inputs a specific keyword and clicks a button to start the analysis, and the request is sent to the server.

[0133] 2. The server receives the request and begins processing it:

[0134] The server calls the user_request_handler function to extract keywords from the request, then uses the process_request function to start collecting data.

[0135] 3. Data Collection:

[0136] The server uses the gather_data function to gather relevant data through social media APIs, for example, by using the Twitter API or the Facebook Graph API.

[0137] 4. Data analysis and information extraction:

[0138] The server analyzes the collected data using the analyze_data function, which uses statistical methods to analyze the popularity score and target demographic attributes (age, gender, interests) to extract the necessary information.

[0139] 5. Providing results:

[0140] The analysis results are formatted in JSON format and visualized in real time on a smart device.

[0141] Specific examples

[0142] For example, to analyze an advertising campaign for "TestBrand," a user enters "TestBrand" into the application. The server collects data related to "TestBrand" through social media APIs and determines that the number of mentions is 850. It calculates the name recognition as "850 / 1000 = 0.85" and analyzes the target demographic's age distribution, gender distribution, and interests to obtain the results. This allows the user to check "TestBrand"'s name recognition and detailed demographic information of the target demographic in real time, enabling them to quickly develop effective marketing strategies.

[0143] Prompt Sentence Examples

[0144] An example of a prompt is:

[0145] "Collect data from social media to analyze awareness and demographic information for the following keyword: 'TestBrand'."

[0146] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0147] Step 1:

[0148] A user opens a smartphone application, enters a specific keyword, and clicks a button to start the analysis. This action sends the keyword to the server as a request. (Input) The keyword entered by the user. (Output) The request to the server.

[0149] Step 2:

[0150] The server receives a user request and calls the user_request_handler function. This function extracts a keyword from the request and passes it to the process_request function to start data collection. (Input) User request (keyword). (Output) Collection start trigger (keyword).

[0151] Step 3:

[0152] The server uses the gather_data(keyword) function to gather data related to a keyword through social media APIs (e.g., Twitter API, Facebook Graph API). It sends a request appropriate to the API to be used and collects the data obtained in the response. (Input) Specific keyword. (Output) Collected social media data.

[0153] Step 4:

[0154] The server passes the data obtained by the gather_data function to the analyze_data(data) function and performs data analysis. This function uses statistical methods to analyze the popularity score and target demographic attributes (age, gender, interests) based on the collected data, and extracts the necessary attribute information. (Input) Collected social media data. (Output) Analyzed popularity score and target demographic attribute information.

[0155] Step 5:

[0156] The server formats the analysis results in JSON format and returns them to the smart device via the user_request_handler function. The smartphone application displays the analysis results in real time based on the received JSON data. (Input) Analyzed popularity score and target demographic attribute information. (Output) Visualized analysis results on the smart device.

[0157] 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.

[0158] The present invention is a system that includes a means for inputting specific keywords, a means for collecting data via the Internet, a means for analyzing the collected data and extracting specific target popularity and target demographic attribute information, and a means for providing the analysis results to users. Furthermore, the system aims to improve the user experience by combining an emotion engine that recognizes the user's emotions, analyzing the user's emotional state, and adjusting the way the information is presented.

[0159] Program processing flow

[0160] 1. User Request Submission

[0161] The user enters a specific keyword into the system's interface (e.g., a web browser or a mobile application), then clicks the "Start Investigation" button, sending a request to the server. This request includes the keyword entered by the user, and the emotion engine also begins to operate.

[0162] 2. Server request reception and sentiment analysis

[0163] The server receives a user request and calls the user_request_handler function. It extracts keywords from the request and obtains the keyword information using keyword = request['keyword']. The server then uses an emotion engine to analyze the user's emotional state for the keywords. The emotional state can be determined using, for example, text analysis or natural language processing techniques.

[0164] 3. Data Collection

[0165] The server calls the process_request function to start collecting data based on the keywords and emotional state. Specifically, it uses the gather_data(keyword) function to gather relevant data from social media and the web. It uses social media APIs and web crawler technology to obtain data related to the specified keywords.

[0166] 4. Data analysis and information extraction

[0167] The server passes the data obtained by the gather_data function to the analyze_data(data) function for data analysis. Based on the collected data, the server uses statistical methods to analyze the specific target popularity, age distribution, gender distribution, and interest information of the target demographic, and extracts the necessary attribute information. For example, the popularity score is calculated based on the number of hits.

[0168] The target demographic information is analyzed as follows: age distribution: "target_age = { "20-30": 50, "30-40": 30, "40-50": 20}", gender distribution: "target_gender = { "male": 60, "female": 40}", and interests: "interests = ["tech", "sports", "music"]".

[0169] 5. Providing results

[0170] The server formats the analysis results in JSON format and prepares them for the user. It then sends the results back to the user through the user_request_handler function. The presentation of the analysis results is adjusted based on the user's emotional state. For example, if the user has a positive emotional state, the analysis results may be presented in detail. Conversely, if the user has a negative emotional state, the analysis results may be presented in a concise summary.

[0171] Specific examples

[0172] For example, if a user starts a survey on "SampleBrand," the server receives a request with "SampleBrand" entered and analyzes the user's emotional state using an emotion engine. Next, data related to "SampleBrand" is obtained through a social media API, and the number of mentions is assumed to be 1,500. In other words, if "data = {'mentions': 1,500}" is entered, the name recognition is calculated as "1,500 / 1,000 = 1.5." The target demographic's age distribution, gender distribution, and interest information are also analyzed and returned as results.

[0173] This system allows users to quickly and easily obtain detailed demographic information about "SampleBrand" and its target demographic, enabling them to formulate appropriate marketing and sales strategies. It also adjusts the way information is presented to users based on their emotional state, providing a better user experience.

[0174] The processing flow will be explained below.

[0175] Step 1:

[0176] The user enters a proper noun. The user enters keywords for a specific company or brand into the system's interface. Then, the user clicks the "Start Search" button, which sends a request to the server. This request includes the keywords entered by the user.

[0177] Step 2:

[0178] The server receives the request. The server receives the user request and calls the user_request_handler function. It extracts keywords from the request and gets the keyword information with keyword = request['keyword'].

[0179] Step 3:

[0180] The server launches an emotion engine to analyze the user's emotion. The server uses the emotion engine to analyze the user's emotional state in response to the input keywords. The emotion engine determines the emotional state using text analysis and natural language processing techniques.

[0181] Step 4:

[0182] The server starts data collection. The server calls the process_request function to start data collection based on keywords and emotional states. Specifically, the server uses the gather_data(keyword) function to gather relevant data from social media and the web.

[0183] Step 5:

[0184] The server collects data over the Internet. The gather_data(keyword) function retrieves data related to a specified keyword using social media APIs or web crawlers. For example, it sends an API request and receives the relevant data in response.

[0185] Step 6:

[0186] The server analyzes the data. The server passes the data obtained by the gather_data function to the analyze_data(data) function and performs data analysis. Based on the collected data, it uses statistical methods to analyze the recognition of specific targets, the age distribution, gender distribution, and interest information of the target demographic.

[0187] Step 7:

[0188] The server calculates the popularity. If the retrieved data includes "mentions = 850", the popularity is calculated as "850 / 1000 = 0.85".

[0189] Step 8:

[0190] The server extracts the target demographic's attribute information. The target demographic's age distribution, gender distribution, and interest information are extracted from the data. For example, the age distribution would be "target_age = { "20-30": 50, "30-40": 30, "40-50": 20}", the gender distribution would be "target_gender = { "male": 60, "female": 40}", and the interests would be "interests = ["tech", "sports", "music"]".

[0191] Step 9:

[0192] The server formats the analysis results in JSON format and prepares them for delivery to the user. Specifically, it converts the results to JSON format using json.dumps(analysis_result).

[0193] Step 10:

[0194] The server adjusts the results based on the user's emotions. Based on the analysis results of the emotion engine, the depth and format of the information presented can be adjusted. For example, detailed data can be displayed for a positive emotional state, and concise information can be displayed for a negative emotional state.

[0195] Step 11:

[0196] The server returns the analysis results to the user via the user_request_handler function. The user can receive the results and use them to formulate marketing and sales strategies.

[0197] Example 2

[0198] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0199] When users acquire brand awareness or target demographic attribute information based on specific keywords, conventional systems have had issues with extracting information and analyzing results that cannot flexibly adapt to the user's emotional state, resulting in a lack of improvement in the user experience. Additionally, the scope of information collected is limited, making comprehensive analysis of the data difficult.

[0200] 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.

[0201] In this invention, the server includes means for a user to input specific keywords, means for collecting data via the Internet, means for analyzing the collected data and extracting specific popularity and target demographic attribute information, means for performing analysis based on the collected data using an emotion engine that recognizes the user's emotional state, and means for adjusting and providing the analysis results based on the user's emotional state. This enables flexible information presentation that takes the user's emotional state into consideration, thereby improving the user experience.

[0202] A "user" is an individual or company that uses the system and enters keywords and obtains information.

[0203] "Keywords" are specific words or phrases that users enter into the system to specify the information they wish to search.

[0204] The "Internet" is an information and communications network made up of computer networks around the world, and is a means of collecting data and transmitting information.

[0205] "Data" refers to the information that is collected and analyzed, including in the form of text, images, video, etc. obtained from social media and websites.

[0206] "Famousness" is an indicator that shows how well-known an object (e.g., product, brand, service, etc.) related to a specific keyword is in society.

[0207] "Target demographic" refers to the group of people who are likely to consume or use the information being surveyed, and includes their demographic information (age, gender, interests, etc.).

[0208] An "emotion engine" is an algorithm or system that analyzes keywords and other text information entered by a user to recognize the user's emotional state (positive, negative, etc.).

[0209] "Social Media API" means an application programming interface provided by a social media platform, which is a means for obtaining data related to specific keywords.

[0210] "Web crawler technology" refers to programs and algorithms that automatically crawl web pages on the Internet and analyze their content.

[0211] "Analysis results" refers to information analyzed using statistical methods and algorithms based on collected data, and includes brand recognition and attribute information of the target demographic.

[0212] "JSON format" is an abbreviation for JavaScript Object Notation, and is a lightweight data format widely used for data exchange.

[0213] The "system" is a design having the overall structure and functions of the present invention, and is a platform consisting of multiple means (modules).

[0214] This invention is a system that allows users to input specific keywords, collect data via the Internet, analyze the collected data, and provide information on brand recognition and target demographic attributes.The system also aims to improve the user experience by using an emotion engine that recognizes the user's emotional state and adjusting the way the analysis results are presented based on the user's emotional state.

[0215] Specifically, a user first enters a specific keyword into the system interface via a web browser or mobile application and clicks the "Start Investigation" button, which sends a request to the server and simultaneously starts the emotion engine.

[0216] The server receives the request sent by the user and internally calls the user_request_handler function to extract keywords. The server then uses an emotion engine to analyze the user's emotional state. This emotion analysis uses text analysis and natural language processing techniques, such as the BERT model.

[0217] Next, the server calls the process_request function to start collecting data based on the keywords and sentiment state. Specifically, the gather_data(keyword) function uses social media APIs and web crawler technology to gather relevant data. For example, it uses the Twitter API and BeautifulSoup to retrieve related tweets and web page information.

[0218] The collected data is passed to the analyze_data(data) function and analyzed by the server. During the analysis, a popularity score is calculated based on the number of mentions and hashtag frequency of the collected data. In addition, the target demographic's age distribution, gender distribution, and interest information are analyzed using statistical methods to extract the necessary attribute information.

[0219] Finally, the server formats the analysis results into JSON format and returns them to the user via the user_request_handler function. The way the analysis results are presented is adjusted based on the user's emotional state: if the emotional state is positive, detailed analysis results are presented, and if the emotional state is negative, concise summary results are presented.

[0220] Specific examples

[0221] For example, if a user starts a search for "SampleBrand," the server receives a request containing the keyword "SampleBrand" and uses an emotion engine to analyze the user's emotional state. Next, data related to "SampleBrand" is retrieved through a social media API, and the number of mentions is assumed to be 1,500. Based on the number of mentions in the collected data, the awareness score is calculated as "1,500 / 1,000 = 1.5." The target demographic's age distribution and interest information are also analyzed and provided to the user.

[0222] This system allows users to quickly and easily obtain detailed attribute information about the "SampleBrand" brand and its target demographic, which can be used as a reference when formulating marketing and sales strategies. Furthermore, by providing information according to the user's emotional state, a better user experience is provided.

[0223] Specific examples of prompts to input to generative AI models

[0224] What is the overall flow when a user starts an investigation on "SampleBrand"? Please explain in detail how the user enters a keyword, a request is sent to the server, data is collected, analyzed, and the results are delivered based on the sentiment engine's analysis.

[0225] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0226] Step 1:

[0227] A user enters a specific keyword into the system's interface through a web browser or mobile application and clicks the "Start Investigation" button. This request includes the keyword entered by the user. The emotion engine also starts working at this point. The keyword is provided as input, and a request is sent to the server as output.

[0228] Step 2:

[0229] The server receives the request and calls the user_request_handler function internally to extract keywords. Specifically, keywords are obtained from the request in the format request['keyword']. Next, the server uses an emotion engine to analyze the user's emotional state for the obtained keywords. Natural language processing techniques such as the BERT model are used for emotion analysis. The keywords in the request are provided as input, and the emotional state is obtained as output.

[0230] Step 3:

[0231] The server calls the process_request function to start collecting data based on keywords and emotional states. The specific data collection is performed using the gather_data(keyword) function. This function uses social media APIs (e.g., Twitter API) or web crawler technology (e.g., BeautifulSoup) to gather data related to keywords. Keywords and emotional states are provided as input, and related data is collected as output.

[0232] Step 4:

[0233] The server passes the collected data to the analyze_data(data) function for analysis. Specifically, it statistically analyzes the number of mentions and hashtag frequency in the collected data to extract a popularity score and target demographic attribute information (age distribution, gender distribution, interests). The collected data is provided as input, and the analysis results are obtained as output. For example, the popularity score is calculated using the formula mentions_count / 1000.

[0234] Step 5:

[0235] The server formats the analysis results into JSON format and returns them to the user via the user_request_handler function. At this stage, the way the analysis results are presented is adjusted based on the user's emotional state. For example, a detailed analysis result is presented for a positive emotional state, while a concise summary is provided for a negative emotional state. The analysis results and the emotional state are provided as input, and the adjusted analysis results are obtained as output.

[0236] (Application example 2)

[0237] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0238] Conventional advertising systems provide a means to acquire target name recognition and attribute information, but do not adjust the display method to take into account the user's emotional state. As a result, the user experience is not sufficiently improved, and optimal advertising proposals cannot be presented.

[0239] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for inputting a specific keyword, a means for collecting data via the Internet, a means for analyzing the collected data and extracting specific target popularity and attribute information of the target demographic, a means for providing the analysis results to the user, and a means for recognizing the user's emotional state and adjusting the method of presenting the information to be provided. This enables flexible information presentation according to the user's emotional state.

[0240] 1. "Specific Keywords" refers to words or phrases that users enter to describe a particular subject or concept that interests them.

[0241] 2. "Means of collecting data via the Internet" refers to methods and technologies for automatically obtaining relevant data from various sources on the Internet.

[0242] 3. "Means of analyzing collected data and extracting specific target awareness and target demographic attribute information" refers to technology that processes collected data and derives the awareness of a target and the attributes of that target demographic (e.g., age, gender, interests).

[0243] 4. "Means for providing analysis results to users" refers to the technology and methods for displaying analyzed information in a format that is easy for users to understand.

[0244] 5. "Means for recognizing the user's emotional state and adjusting the way information is presented" refers to technology that analyzes and understands the user's emotions and appropriately changes the way information is displayed based on the results.

[0245] 6. "Social Media API" refers to a means of obtaining data related to specific keywords using an application programming interface (API) provided by a social media platform.

[0246] The present invention is a system that includes a means for inputting specific keywords, a means for collecting data via the Internet, a means for analyzing the collected data and extracting specific target popularity and target demographic attribute information, and a means for providing the analysis results to users.Furthermore, the system aims to improve the user experience by combining an emotion engine that recognizes the user's emotions, analyzing the user's emotional state, and adjusting the way the information is presented.

[0247] Overall system configuration and operation flow

[0248] Program processing overview

[0249] The server receives requests sent by users and collects relevant data based on specific keywords included in the request. The collected data is analyzed to extract specific target popularity and target demographic attribute information (age, gender, interests). Furthermore, the server analyzes the user's emotional state and adjusts the presentation of the information provided according to the user's emotional state.

[0250] Specific implementation description

[0251] 1. A user inputs a specific keyword into a device (smartphone or PC) and sends a request to the server. This request includes the specific keyword that the user is interested in and data to obtain the user's emotional state.

[0252] 2. The server is built using Python or a similar programming language. Upon receiving a user request, the server analyzes the user's emotional state using TextBlob or a similar natural language processing tool.

[0253] 3. The server uses social media APIs and web crawler technology to collect data related to the keywords over the internet. This step utilizes public social media APIs such as the Twitter API and Facebook Graph API.

[0254] 4. The collected data is analyzed on the server to extract specific target awareness and demographic information. Statistical methods and machine learning models are used for the analysis.

[0255] 5. The server formats the analysis results in JSON format and adjusts the presentation of information based on the user's emotional state: detailed information is provided if the user has a positive emotion, and concise information is provided if the user has a negative emotion.

[0256] 6. Finally, the server sends the analysis results back to the user, who can view the information. This information is used by advertisers to develop optimal advertising strategies for their target audience.

[0257] Examples of specific examples and prompts

[0258] For example, when a marketer wants to research the popularity of a particular brand, the system will collect relevant data from social media APIs based on the keyword "specific brand." The system will then analyze the popularity and target demographic information, and provide detailed information in a way that reflects the user's emotional state. This will make it easier for advertisers to develop optimal advertising strategies.

[0259] Example prompt sentence:

[0260] "The system collects data related to the keywords entered by the user, analyzes the popularity of the specified keywords and the demographic information of the target demographic, and provides the information. It also adjusts the way information is presented depending on the user's emotional state."

[0261] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0262] Step 1:

[0263] The user enters a specific keyword into a device (smartphone or PC) and sends a request to the server. This request includes the specific keyword and a text message to obtain the user's emotional state. The input is the user sending the keyword "specific brand" and a message indicating their emotion. The output is received by the server.

[0264] Step 2:

[0265] The server processes the received request using the user_request_handler function to extract keywords and user messages. Specifically, it uses a Python library to extract keywords (e.g., "specific brand") and user messages (e.g., "I want to know more about this brand") from the request. The input is the received request, which is the output of step 1. The output is the extracted keywords and user messages.

[0266] Step 3:

[0267] The server uses natural language processing techniques such as TextBlob to analyze the emotional state of the user message. The emotional state is classified as positive, negative, or neutral. For example, a positive emotion is detected from the message "I want to know more about this brand." The input is the user message extracted in step 2. The output is the analyzed emotional state.

[0268] Step 4:

[0269] The server uses the gather_data function to collect keyword-related data from the Internet (e.g., social media APIs). Specifically, it uses the Twitter API and Facebook Graph API to obtain posts related to a "specific brand." The input is the keywords extracted in step 2. The output is the collected data (e.g., posts from social media).

[0270] Step 5:

[0271] The collected data is analyzed using the analyze_data function to extract specific target name recognition and target demographic attribute information (age, gender, interests). Specifically, name recognition is calculated based on the number of collected posts, and age distribution, gender distribution, and interest information are analyzed using statistical methods. The input is the data collected in step 4. The output is the analysis results (e.g., name recognition score, age distribution, gender distribution, interest information).

[0272] Step 6:

[0273] The server formats the analysis results in JSON format and adjusts the way information is presented based on the user's emotional state. For example, it provides detailed information for a positive emotional state and concise information for a negative emotional state. The input is the emotional state from step 3 and the analysis results from step 5. The output is formatted data (e.g., the analysis results in JSON format).

[0274] Step 7:

[0275] Finally, the server returns the formatted analysis results to the user, who can view the results on their device. The input is the data formatted in step 6. The output is the analysis results displayed on the user's device, providing the user with the information they need to develop their advertising strategy.

[0276] 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.

[0277] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0278] 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.

[0279] [Second embodiment]

[0280] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0281] 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.

[0282] 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).

[0283] 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.

[0284] 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.

[0285] 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).

[0286] 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.

[0287] 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.

[0288] 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.

[0289] 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.

[0290] 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.

[0291] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0292] The present invention is a system that includes a means for inputting specific keywords, a means for collecting data via the Internet, a means for analyzing the collected data and extracting specific target name recognition and attribute information of the target demographic, and a means for providing the analysis results to the user.

[0293] Program processing flow

[0294] 1. User Request Submission

[0295] A user enters a specific keyword into the system's interface (e.g., a web browser or a mobile application), then clicks a "Start Search" button on the interface to send a request to the server, which includes the keyword entered by the user.

[0296] 2. Server receives request and starts processing

[0297] The server receives a user request and calls the user_request_handler function. It extracts keywords from the request and gets them as keyword = request['keyword']. The server then calls the process_request function to start collecting data based on the keywords.

[0298] 3. Data Collection

[0299] The server uses the gather_data(keyword) function to gather relevant data from social media and the web. It uses social media APIs and web crawler technology to obtain data related to the specified keyword. Specifically, it sends an API request and receives the relevant data as a response.

[0300] 4. Data analysis and information extraction

[0301] The server passes the data obtained by the gather_data function to the analyze_data(data) function and performs the analysis. Based on the collected data, it uses statistical methods to analyze the awareness score, target demographic age distribution, gender distribution, and interests to extract the necessary attribute information. For example, the awareness score is calculated based on "mentions = data.get('mentions')", and awareness is calculated as "awareness = mentions / 1000".

[0302] Information about the target demographic includes the age distribution (target_age = { "20-30": 50, "30-40": 30, "40-50": 20}), the gender distribution (target_gender = { "male": 60, "female": 40}), and interests (interests = ["tech", "sports", "music"]).

[0303] 5. Providing results

[0304] The server formats the analysis results in JSON format and prepares them for the user. Next, it sends the results back to the user via the user_request_handler function, and the user receives the analysis results. Based on these results, the user can develop marketing and sales strategies.

[0305] Specific examples

[0306] For example, if a user starts a survey on "TestBrand," the server receives a request with "TestBrand" entered and collects data. Assume that data related to "TestBrand" is obtained through a social media API and the number of mentions is 850. For example, if you enter "data = {'mentions': 850}," the name recognition is calculated as "850 / 1000 = 0.85." The target demographic's age distribution, gender distribution, and interest information are also analyzed and returned as results. For example, information such as "50% are 20-30 years old, 60% are male, 40% are female, and their interests are technology, sports, and music" can be obtained.

[0307] This system allows users to quickly and easily obtain detailed information about the brand awareness of "TestBrand" and the attributes of their target demographic, and based on this information, they can formulate appropriate marketing and sales strategies.

[0308] The processing flow will be explained below.

[0309] Step 1:

[0310] The user enters a proper noun. The user enters keywords for a specific company or brand into the system's interface. Then, the user clicks the "Start Search" button, which sends a request to the server. This request includes the keywords entered by the user.

[0311] Step 2:

[0312] The server receives the request. The server receives the user request and calls the user_request_handler function. It extracts keywords from the request and gets the keyword information with keyword = request['keyword'].

[0313] Step 3:

[0314] The server starts data collection. The server calls the process_request function to start collecting data based on the keyword. Specifically, it uses the gather_data(keyword) function to gather relevant data from social media and the web.

[0315] Step 4:

[0316] The server collects data over the Internet. The gather_data(keyword) function retrieves data related to the specified keyword using social media APIs or web crawlers. It sends an API request and receives the relevant data in response.

[0317] Step 5:

[0318] The server analyzes the data. The server passes the data obtained by the gather_data function to the analyze_data(data) function and performs data analysis. Here, the collected data is used to statistically analyze the recognition of specific targets, the age distribution, gender distribution, and interest information of the target demographic.

[0319] Step 6:

[0320] The server calculates the popularity. For example, if the acquired data contains "mentions = 850", the popularity is calculated as "850 / 1000 = 0.85".

[0321] Step 7:

[0322] The server extracts the target demographic's attribute information. The target demographic's age distribution, gender distribution, and interest information are extracted from the data. For example, the age distribution would be "target_age = { "20-30": 50, "30-40": 30, "40-50": 20}", the gender distribution would be "target_gender = { "male": 60, "female": 40}", and the interests would be "interests = ["tech", "sports", "music"]".

[0323] Step 8:

[0324] The server formats the analysis results in JSON format and prepares them for delivery to the user. Specifically, it converts the results to JSON format using json.dumps(analysis_result).

[0325] Step 9:

[0326] The server returns the results to the user. The server returns the analysis results to the user via the user_request_handler function. The user can receive these results and use them to formulate marketing and sales strategies.

[0327] Example 1

[0328] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0329] In today's world, for companies to develop effective marketing and sales strategies, data such as demographic information on target demographics and the popularity of specific keywords is essential. However, there is a lack of efficient ways to collect and analyze this data, making it difficult to quickly and accurately obtain the information you want.

[0330] 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.

[0331] In this invention, the server includes a means for inputting specific keywords, a means including a social media API and a web crawler for collecting data via the Internet, a statistical analysis means for analyzing the collected data and extracting specific target name recognition, age distribution, gender distribution, and interest information of the target demographic, and a means for formatting the analysis results in JSON format and providing them to users. This enables companies to quickly and accurately obtain detailed attribute information and name recognition data of their target demographics and develop effective marketing and sales strategies.

[0332] The "means for entering specific keywords" refers to the interface (web browser or mobile application) through which users enter the keywords they wish to research.

[0333] "Methods for collecting data via the internet, including social media APIs and web crawlers" refers to technologies for automatically collecting relevant data from social media and web pages on the internet.

[0334] "Statistical analysis means for analyzing collected data and extracting the name recognition of specific targets, the age distribution, gender distribution, and interest information of the target demographic" refers to programs or algorithms for analyzing collected data and extracting the name recognition of specific targets and attribute information of the target demographic (age distribution, gender distribution, interest information) using statistical methods.

[0335] "Means for formatting the analysis results in JSON format and providing them to users" refers to a technology for formatting the analysis results in a structured data format (JSON: JavaScript Object Notation) and providing it to users.

[0336] The present invention provides a system for allowing a user to input a specific keyword, collecting data related to the keyword via the Internet, and providing analysis results. The system comprises the following means.

[0337] First, the user enters the keywords to be investigated using the system interface (web browser or mobile application). The interface has a "Start Investigation" button, and when the user clicks this, the keywords are sent to the server.

[0338] The server receives a request from a user and extracts the keywords included in the request. The server then begins collecting data based on the specified keywords. Specifically, it uses social media APIs and web crawler technology on the Internet to collect related data. For example, social media APIs can be used to obtain post and comment data related to specific keywords. It is also possible to use web crawlers to scrape information from related web pages.

[0339] The collected data is analyzed on the server. During the analysis, specific target name recognition, age distribution, gender distribution, and interest information of the target demographic are extracted from the data. These analyses are performed using statistical methods to extract attribute information. For example, a name recognition score is calculated based on the number of mentions in the collected data, and age distribution, gender distribution, and interest information of the target demographic are also statistically organized.

[0340] Finally, the server formats the analysis results into JSON format and prepares them for delivery to the user. The analysis results are converted into a structured data format (JSON: JavaScript Object Notation) and sent back to the user. The user can check the analysis results on the interface and use them to develop marketing and sales strategies.

[0341] Specific examples

[0342] For example, if a user starts a survey on "TestBrand", the following will happen:

[0343] The user enters "TestBrand" into the system's web interface and clicks the "Start Survey" button.

[0344] The server receives this request and extracts keyword = 'TestBrand'.

[0345] The server calls the gather_data('TestBrand') function to gather data using social media APIs and web crawlers. For example, if there are 850 mentions, the server gets "data = {'mentions': 850}".

[0346] The server passes this data to the analyze_data(data) function, extracting a popularity score of 0.85 and target demographic attributes: target_age = { '20-30': 50, '30-40': 30, '40-50': 20}, target_gender = { 'male': 60, 'female': 40}, and interests = ['tech', 'sports', 'music'].

[0347] The server formats the analysis results into JSON format and returns them to the user, who can then use this information to develop specific marketing strategies.

[0348] This system allows users to quickly and easily obtain detailed information about the brand awareness of "TestBrand" and the attributes of their target demographic, and use this information to develop effective marketing and sales strategies.

[0349] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0350] Step 1:

[0351] The user opens the system interface (web browser or mobile application) and enters a specific keyword. After entering the keyword, the user clicks the "Start Search" button, which sends the request to the server. The input data is the specific keyword entered by the user. The output data is the request sent to the server.

[0352] Step 2:

[0353] The server receives a user request and extracts keywords from the request. In this process, the server executes keyword = request['keyword'] from the request. The input is the request sent by the user, and the output is the extracted keywords.

[0354] Step 3:

[0355] The server uses the extracted keywords to call the gather_data(keyword) function to gather related data from the Internet. This process involves using social media APIs and web crawler technology to obtain data. Specifically, it sends requests to social media APIs to obtain related post and comment data, and uses web crawlers to scrape related web pages. The input is the keywords, and the output is the collected related data.

[0356] Step 4:

[0357] The server passes the collected data to the analyze_data(data) function to perform data analysis. During the analysis, specific target awareness, age distribution, gender distribution, and interest information of the target demographic are extracted using statistical methods. For example, the awareness score is calculated based on "mentions = data.get('mentions')" and "awareness = mentions / 1000". In addition, age distribution, gender distribution, and interest information are statistically organized from the collected data. The input is the collected data, and the output is the analysis results.

[0358] Step 5:

[0359] The server formats the analysis results in JSON format and prepares them for delivery to the user. During this process, the server converts the analysis results into JSON format as follows: json_result = json.dumps(analysis_result) . The formatted JSON results are sent back to the user. The input is the analysis results, and the output is the analysis results in JSON format.

[0360] Step 6:

[0361] Users receive the analysis results provided through the system interface and use that data to develop marketing and sales strategies. The input is the analysis results in JSON format, and the output is the basis for the strategy developed by the user.

[0362] This specific processing flow enables users to quickly and accurately obtain detailed attribute information and name recognition data for their target demographic, and to formulate effective strategies based on this information.

[0363] (Application example 1)

[0364] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0365] While conventional systems were capable of collecting and analyzing brand awareness and target demographic information related to specific keywords, they lacked a way for users to easily check the results in real time. Furthermore, the analysis results were not sufficiently visualized, making it difficult for users to quickly and effectively utilize them in their marketing strategies. Therefore, there is a need for real-time visualization of collected data and for improvements in the method of providing analysis results through that visualization.

[0366] 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.

[0367] In this invention, the server includes a means for inputting specific keywords, a means for collecting data via the Internet, a means for analyzing the collected data and extracting specific target name recognition and target demographic attribute information, a means for providing the analysis results to the user, and a means for visualizing the results on a smart device. This allows the analysis results to be visually displayed on the smart device in real time, allowing the user to quickly and effectively formulate a marketing strategy.

[0368] "Specific keywords" are words or phrases that users enter into the system and select for analysis.

[0369] "Means of collecting data via the internet" refers to the functions and technologies used to obtain information from websites and social media.

[0370] "Means of analyzing collected data and extracting specific target name recognition and target demographic attribute information" refers to functions and technologies that use statistical methods based on collected data to derive name recognition scores and target demographic attributes (age, gender, interests).

[0371] "Means for providing analysis results to users" refers to the functions and technologies for notifying and displaying the analyzed information to users.

[0372] "Means for visualizing results on smart devices" refers to functions and technologies for graphically displaying analysis results on digital devices such as smartphones and tablets.

[0373] A "social media API" is a programmatic interface for retrieving data from social media platforms such as Twitter and Facebook.

[0374] "Display in real time" means that collected and analyzed data is displayed to the user immediately without delay.

[0375] This invention is a system that inputs specific keywords, collects data via the Internet, analyzes the data, extracts name recognition and target demographic attribute information, and finally provides the analysis results to users. Furthermore, this system includes a means for visualizing the results on a smart device.

[0376] Hardware

[0377] Server: High-performance cloud server (e.g., Amazon Web Services, Google Cloud Platform)

[0378] Smart device: Smartphone (Android or iOS)

[0379] software

[0380] Smartphone application: Swift (iOS), Kotlin (Android)

[0381] Data collection: Python, Requests library, social media APIs (e.g. Twitter API, Facebook Graph API)

[0382] Data analysis: Python, Pandas, NumPy, scikit-learn

[0383] Server-side framework: Django or Flask (Python)

[0384] Program Overview

[0385] The server provides an interface for entering specific keywords, and once the user enters the keywords, data collection begins. The server collects data using social media APIs and analyzes the data to extract name recognition scores and target demographic attribute information. The analysis results are visualized in real time on a smart device, allowing users to quickly develop marketing strategies based on the results.

[0386] Processing flow

[0387] 1. User submits request:

[0388] Using a smartphone application, a user inputs a specific keyword and clicks a button to start the analysis, and the request is sent to the server.

[0389] 2. The server receives the request and begins processing it:

[0390] The server calls the user_request_handler function to extract keywords from the request, then uses the process_request function to start collecting data.

[0391] 3. Data Collection:

[0392] The server uses the gather_data function to gather relevant data through social media APIs, for example, by using the Twitter API or the Facebook Graph API.

[0393] 4. Data analysis and information extraction:

[0394] The server analyzes the collected data using the analyze_data function, which uses statistical methods to analyze the popularity score and target demographic attributes (age, gender, interests) to extract the necessary information.

[0395] 5. Providing results:

[0396] The analysis results are formatted in JSON format and visualized in real time on a smart device.

[0397] Specific examples

[0398] For example, to analyze an advertising campaign for "TestBrand," a user enters "TestBrand" into the application. The server collects data related to "TestBrand" through social media APIs and determines that the number of mentions is 850. It calculates the name recognition as "850 / 1000 = 0.85" and analyzes the target demographic's age distribution, gender distribution, and interests to obtain the results. This allows the user to check "TestBrand"'s name recognition and detailed demographic information of the target demographic in real time, enabling them to quickly develop effective marketing strategies.

[0399] Prompt Sentence Examples

[0400] An example of a prompt is:

[0401] "Collect data from social media to analyze awareness and demographic information for the following keyword: 'TestBrand'."

[0402] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0403] Step 1:

[0404] A user opens a smartphone application, enters a specific keyword, and clicks a button to start the analysis. This action sends the keyword to the server as a request. (Input) The keyword entered by the user. (Output) The request to the server.

[0405] Step 2:

[0406] The server receives a user request and calls the user_request_handler function. This function extracts a keyword from the request and passes it to the process_request function to start data collection. (Input) User request (keyword). (Output) Collection start trigger (keyword).

[0407] Step 3:

[0408] The server uses the gather_data(keyword) function to gather data related to a keyword through social media APIs (e.g., Twitter API, Facebook Graph API). It sends a request appropriate to the API to be used and collects the data obtained in the response. (Input) Specific keyword. (Output) Collected social media data.

[0409] Step 4:

[0410] The server passes the data obtained by the gather_data function to the analyze_data(data) function and performs data analysis. This function uses statistical methods to analyze the popularity score and target demographic attributes (age, gender, interests) based on the collected data, and extracts the necessary attribute information. (Input) Collected social media data. (Output) Analyzed popularity score and target demographic attribute information.

[0411] Step 5:

[0412] The server formats the analysis results in JSON format and returns them to the smart device via the user_request_handler function. The smartphone application displays the analysis results in real time based on the received JSON data. (Input) Analyzed popularity score and target demographic attribute information. (Output) Visualized analysis results on the smart device.

[0413] 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.

[0414] The present invention is a system that includes a means for inputting specific keywords, a means for collecting data via the Internet, a means for analyzing the collected data and extracting specific target popularity and target demographic attribute information, and a means for providing the analysis results to users. Furthermore, the system aims to improve the user experience by combining an emotion engine that recognizes the user's emotions, analyzing the user's emotional state, and adjusting the way the information is presented.

[0415] Program processing flow

[0416] 1. User Request Submission

[0417] The user enters a specific keyword into the system's interface (e.g., a web browser or a mobile application), then clicks the "Start Investigation" button, sending a request to the server. This request includes the keyword entered by the user, and the emotion engine also begins to operate.

[0418] 2. Server request reception and sentiment analysis

[0419] The server receives a user request and calls the user_request_handler function. It extracts keywords from the request and obtains the keyword information using keyword = request['keyword']. The server then uses an emotion engine to analyze the user's emotional state for the keywords. The emotional state can be determined using, for example, text analysis or natural language processing techniques.

[0420] 3. Data Collection

[0421] The server calls the process_request function to start collecting data based on the keywords and emotional state. Specifically, it uses the gather_data(keyword) function to gather relevant data from social media and the web. It uses social media APIs and web crawler technology to obtain data related to the specified keywords.

[0422] 4. Data analysis and information extraction

[0423] The server passes the data obtained by the gather_data function to the analyze_data(data) function for data analysis. Based on the collected data, the server uses statistical methods to analyze the specific target popularity, age distribution, gender distribution, and interest information of the target demographic, and extracts the necessary attribute information. For example, the popularity score is calculated based on the number of hits.

[0424] The target demographic information is analyzed as follows: age distribution: "target_age = { "20-30": 50, "30-40": 30, "40-50": 20}", gender distribution: "target_gender = { "male": 60, "female": 40}", and interests: "interests = ["tech", "sports", "music"]".

[0425] 5. Providing results

[0426] The server formats the analysis results in JSON format and prepares them for the user. It then sends the results back to the user through the user_request_handler function. The presentation of the analysis results is adjusted based on the user's emotional state. For example, if the user has a positive emotional state, the analysis results may be presented in detail. Conversely, if the user has a negative emotional state, the analysis results may be presented in a concise summary.

[0427] Specific examples

[0428] For example, if a user starts a survey on "SampleBrand," the server receives a request with "SampleBrand" entered and analyzes the user's emotional state using an emotion engine. Next, data related to "SampleBrand" is obtained through a social media API, and the number of mentions is assumed to be 1,500. In other words, if "data = {'mentions': 1,500}" is entered, the name recognition is calculated as "1,500 / 1,000 = 1.5." The target demographic's age distribution, gender distribution, and interest information are also analyzed and returned as results.

[0429] This system allows users to quickly and easily obtain detailed information about the brand's popularity and target demographics, enabling them to formulate appropriate marketing and sales strategies. It also adjusts the way information is presented to users based on their emotional state, providing a better user experience.

[0430] The processing flow will be explained below.

[0431] Step 1:

[0432] The user enters a proper noun. The user enters keywords for a specific company or brand into the system's interface. Then, the user clicks the "Start Search" button, which sends a request to the server. This request includes the keywords entered by the user.

[0433] Step 2:

[0434] The server receives the request. The server receives the user request and calls the user_request_handler function. It extracts keywords from the request and gets the keyword information with keyword = request['keyword'].

[0435] Step 3:

[0436] The server launches an emotion engine to analyze the user's emotion. The server uses the emotion engine to analyze the user's emotional state in response to the input keywords. The emotion engine determines the emotional state using text analysis and natural language processing techniques.

[0437] Step 4:

[0438] The server starts data collection. The server calls the process_request function to start data collection based on keywords and emotional states. Specifically, the server uses the gather_data(keyword) function to gather relevant data from social media and the web.

[0439] Step 5:

[0440] The server collects data over the Internet. The gather_data(keyword) function retrieves data related to a specified keyword using social media APIs or web crawlers. For example, it sends an API request and receives the relevant data in response.

[0441] Step 6:

[0442] The server analyzes the data. The server passes the data obtained by the gather_data function to the analyze_data(data) function and performs data analysis. Based on the collected data, it uses statistical methods to analyze the recognition of specific targets, the age distribution, gender distribution, and interest information of the target demographic.

[0443] Step 7:

[0444] The server calculates the popularity. If the retrieved data includes "mentions = 850", the popularity is calculated as "850 / 1000 = 0.85".

[0445] Step 8:

[0446] The server extracts the target demographic's attribute information. The target demographic's age distribution, gender distribution, and interest information are extracted from the data. For example, the age distribution would be "target_age = { "20-30": 50, "30-40": 30, "40-50": 20}", the gender distribution would be "target_gender = { "male": 60, "female": 40}", and the interests would be "interests = ["tech", "sports", "music"]".

[0447] Step 9:

[0448] The server formats the analysis results in JSON format and prepares them for delivery to the user. Specifically, it converts the results to JSON format using json.dumps(analysis_result).

[0449] Step 10:

[0450] The server adjusts the results based on the user's emotions. Based on the analysis results of the emotion engine, the depth and format of the information presented can be adjusted. For example, detailed data can be displayed for a positive emotional state, and concise information can be displayed for a negative emotional state.

[0451] Step 11:

[0452] The server returns the analysis results to the user via the user_request_handler function. The user can receive the results and use them to formulate marketing and sales strategies.

[0453] Example 2

[0454] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0455] When users acquire brand awareness or target demographic attribute information based on specific keywords, conventional systems have had issues with extracting information and analyzing results that cannot flexibly adapt to the user's emotional state, resulting in a lack of improvement in the user experience. Additionally, the scope of information collected is limited, making comprehensive analysis of the data difficult.

[0456] 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.

[0457] In this invention, the server includes a means for a user to input a specific keyword, a means for collecting data via the Internet, a means for analyzing the collected data and extracting specific popularity and target demographic attribute information, a means for performing analysis based on the collected data using an emotion engine that recognizes the user's emotional state, and a means for adjusting and providing the analysis results based on the user's emotional state. This enables flexible information presentation that takes the user's emotional state into consideration, thereby improving the user experience.

[0458] A "user" is an individual or company that uses the system and enters keywords and obtains information.

[0459] "Keywords" are specific words or phrases that users enter into the system to specify the information they wish to search.

[0460] The "Internet" is an information and communications network made up of computer networks around the world, and is a means of collecting data and transmitting information.

[0461] "Data" refers to the information that is collected and analyzed, including in the form of text, images, video, etc. obtained from social media and websites.

[0462] "Famousness" is an indicator that shows how well-known an object (e.g., product, brand, service, etc.) related to a specific keyword is in society.

[0463] "Target demographic" refers to the group of people who are likely to consume or use the information being surveyed, and includes their demographic information (age, gender, interests, etc.).

[0464] An "emotion engine" is an algorithm or system that analyzes keywords and other text information entered by a user to recognize the user's emotional state (positive, negative, etc.).

[0465] "Social Media API" means an application programming interface provided by a social media platform that allows users to retrieve data related to specific keywords.

[0466] "Web crawler technology" refers to programs and algorithms that automatically crawl web pages on the Internet and analyze their content.

[0467] "Analysis results" refers to information analyzed using statistical methods and algorithms based on collected data, and includes brand recognition and attribute information of the target demographic.

[0468] "JSON format" is an abbreviation for JavaScript Object Notation, and is a lightweight data format widely used for data exchange.

[0469] The "system" is a design having the overall structure and functions of the present invention, and is a platform consisting of multiple means (modules).

[0470] This invention is a system that allows users to input specific keywords, collect data via the Internet, analyze the collected data, and provide information on brand recognition and target demographic attributes.The system also aims to improve the user experience by using an emotion engine that recognizes the user's emotional state and adjusting the way the analysis results are presented based on the user's emotional state.

[0471] Specifically, a user first enters a specific keyword into the system interface via a web browser or mobile application and clicks the "Start Investigation" button, which sends a request to the server and simultaneously starts the emotion engine.

[0472] The server receives the request sent by the user and internally calls the user_request_handler function to extract keywords. The server then uses an emotion engine to analyze the user's emotional state. This emotion analysis uses text analysis and natural language processing techniques, such as the BERT model.

[0473] Next, the server calls the process_request function to start collecting data based on the keywords and sentiment state. Specifically, the gather_data(keyword) function uses social media APIs and web crawler technology to gather relevant data. For example, it uses the Twitter API and BeautifulSoup to retrieve related tweets and web page information.

[0474] The collected data is passed to the analyze_data(data) function and analyzed by the server. During the analysis, a popularity score is calculated based on the number of mentions and hashtag frequency of the collected data. In addition, the target demographic's age distribution, gender distribution, and interest information are analyzed using statistical methods to extract the necessary attribute information.

[0475] Finally, the server formats the analysis results into JSON format and returns them to the user via the user_request_handler function. The way the analysis results are presented is adjusted based on the user's emotional state: if the emotional state is positive, detailed analysis results are presented, and if the emotional state is negative, concise summary results are presented.

[0476] Specific examples

[0477] For example, if a user starts a search for "SampleBrand," the server receives a request containing the keyword "SampleBrand" and uses an emotion engine to analyze the user's emotional state. Next, data related to "SampleBrand" is retrieved through a social media API, and the number of mentions is assumed to be 1,500. Based on the number of mentions in the collected data, the awareness score is calculated as "1,500 / 1,000 = 1.5." The target demographic's age distribution and interest information are also analyzed and provided to the user.

[0478] This system allows users to quickly and easily obtain detailed attribute information about the "SampleBrand" brand and its target demographic, which can be used as a reference when formulating marketing and sales strategies. Furthermore, by providing information according to the user's emotional state, a better user experience is provided.

[0479] Specific examples of prompts to input to generative AI models

[0480] What is the overall flow when a user starts an investigation on "SampleBrand"? Please explain in detail how the user enters a keyword, a request is sent to the server, data is collected, analyzed, and the results are delivered based on the sentiment engine's analysis.

[0481] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0482] Step 1:

[0483] A user enters a specific keyword into the system's interface through a web browser or mobile application and clicks the "Start Investigation" button. This request includes the keyword entered by the user. The emotion engine also starts working at this point. The keyword is provided as input, and a request is sent to the server as output.

[0484] Step 2:

[0485] The server receives the request and calls the user_request_handler function internally to extract keywords. Specifically, keywords are obtained from the request in the format request['keyword']. Next, the server uses an emotion engine to analyze the user's emotional state for the obtained keywords. Natural language processing techniques such as the BERT model are used for emotion analysis. The keywords in the request are provided as input, and the emotional state is obtained as output.

[0486] Step 3:

[0487] The server calls the process_request function to start collecting data based on keywords and emotional states. The specific data collection is performed using the gather_data(keyword) function. This function uses social media APIs (e.g., Twitter API) or web crawler technology (e.g., BeautifulSoup) to gather data related to keywords. Keywords and emotional states are provided as input, and related data is collected as output.

[0488] Step 4:

[0489] The server passes the collected data to the analyze_data(data) function for analysis. Specifically, it statistically analyzes the number of mentions and hashtag frequency in the collected data to extract a popularity score and target demographic attribute information (age distribution, gender distribution, interests). The collected data is provided as input, and the analysis results are obtained as output. For example, the popularity score is calculated using the formula mentions_count / 1000.

[0490] Step 5:

[0491] The server formats the analysis results into JSON format and returns them to the user via the user_request_handler function. At this stage, the way the analysis results are presented is adjusted based on the user's emotional state. For example, a detailed analysis result is presented for a positive emotional state, while a concise summary is provided for a negative emotional state. The analysis results and the emotional state are provided as input, and the adjusted analysis results are obtained as output.

[0492] (Application example 2)

[0493] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0494] Conventional advertising systems provide a means to acquire target name recognition and attribute information, but do not adjust the display method to take into account the user's emotional state. As a result, the user experience is not sufficiently improved, and optimal advertising proposals cannot be presented.

[0495] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for inputting a specific keyword, a means for collecting data via the Internet, a means for analyzing the collected data and extracting specific target popularity and attribute information of the target demographic, a means for providing the analysis results to the user, and a means for recognizing the user's emotional state and adjusting the method of presenting the information to be provided. This enables flexible information presentation according to the user's emotional state.

[0496] 1. "Specific Keywords" refers to words or phrases that users enter to describe a particular subject or concept that interests them.

[0497] 2. "Means of collecting data via the Internet" refers to methods and technologies for automatically obtaining relevant data from various sources on the Internet.

[0498] 3. "Means of analyzing collected data and extracting specific target awareness and target demographic attribute information" refers to technology that processes collected data and derives the awareness of a target and the attributes of that target demographic (e.g., age, gender, interests).

[0499] 4. "Means for providing analysis results to users" refers to the technology and methods for displaying analyzed information in a format that is easy for users to understand.

[0500] 5. "Means for recognizing the user's emotional state and adjusting the way information is presented" refers to technology that analyzes and understands the user's emotions and appropriately changes the way information is displayed based on the results.

[0501] 6. "Social Media API" refers to a means of obtaining data related to specific keywords using an application programming interface (API) provided by a social media platform.

[0502] The present invention is a system that includes a means for inputting specific keywords, a means for collecting data via the Internet, a means for analyzing the collected data and extracting specific target popularity and target demographic attribute information, and a means for providing the analysis results to users.Furthermore, the system aims to improve the user experience by combining an emotion engine that recognizes the user's emotions, analyzing the user's emotional state, and adjusting the way the information is presented.

[0503] Overall system configuration and operation flow

[0504] Program processing overview

[0505] The server receives requests sent by users and collects relevant data based on specific keywords included in the request. The collected data is analyzed to extract specific target popularity and target demographic attribute information (age, gender, interests). Furthermore, the server analyzes the user's emotional state and adjusts the presentation of the information provided according to the user's emotional state.

[0506] Specific implementation description

[0507] 1. A user inputs a specific keyword into a device (smartphone or PC) and sends a request to the server. This request includes the specific keyword that the user is interested in and data to obtain the user's emotional state.

[0508] 2. The server is built using Python or a similar programming language. Upon receiving a user request, the server analyzes the user's emotional state using TextBlob or a similar natural language processing tool.

[0509] 3. The server uses social media APIs and web crawler technology to collect data related to the keywords over the internet. This step utilizes public social media APIs such as the Twitter API and Facebook Graph API.

[0510] 4. The collected data is analyzed on the server to extract specific target awareness and demographic information. Statistical methods and machine learning models are used for the analysis.

[0511] 5. The server formats the analysis results in JSON format and adjusts the presentation of information based on the user's emotional state: detailed information is provided if the user has a positive emotion, and concise information is provided if the user has a negative emotion.

[0512] 6. Finally, the server sends the analysis results back to the user, who can view the information. This information is used by advertisers to develop optimal advertising strategies for their target audience.

[0513] Examples of specific examples and prompts

[0514] For example, when a marketer wants to research the popularity of a particular brand, the system will collect relevant data from social media APIs based on the keyword "specific brand." The system will then analyze the popularity and target demographic information, and provide detailed information in a way that reflects the user's emotional state. This will make it easier for advertisers to develop optimal advertising strategies.

[0515] Example prompt sentence:

[0516] "The system collects data related to the keywords entered by the user, analyzes the popularity of the specified keywords and the demographic information of the target demographic, and provides the information. It also adjusts the way information is presented depending on the user's emotional state."

[0517] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0518] Step 1:

[0519] The user enters a specific keyword into a device (smartphone or PC) and sends a request to the server. This request includes the specific keyword and a text message to obtain the user's emotional state. The input is the user sending the keyword "specific brand" and a message indicating their emotion. The output is received by the server.

[0520] Step 2:

[0521] The server processes the received request using the user_request_handler function to extract keywords and user messages. Specifically, it uses a Python library to extract keywords (e.g., "specific brand") and user messages (e.g., "I want to know more about this brand") from the request. The input is the received request, which is the output of step 1. The output is the extracted keywords and user messages.

[0522] Step 3:

[0523] The server uses natural language processing techniques such as TextBlob to analyze the emotional state of the user message. The emotional state is classified as positive, negative, or neutral. For example, a positive emotion is detected from the message "I want to know more about this brand." The input is the user message extracted in step 2. The output is the analyzed emotional state.

[0524] Step 4:

[0525] The server uses the gather_data function to collect keyword-related data from the Internet (e.g., social media APIs). Specifically, it uses the Twitter API and Facebook Graph API to obtain posts related to a "specific brand." The input is the keywords extracted in step 2. The output is the collected data (e.g., posts from social media).

[0526] Step 5:

[0527] The collected data is analyzed using the analyze_data function to extract specific target name recognition and target demographic attribute information (age, gender, interests). Specifically, name recognition is calculated based on the number of collected posts, and age distribution, gender distribution, and interest information are analyzed using statistical methods. The input is the data collected in step 4. The output is the analysis results (e.g., name recognition score, age distribution, gender distribution, interest information).

[0528] Step 6:

[0529] The server formats the analysis results in JSON format and adjusts the way information is presented based on the user's emotional state. For example, it provides detailed information for a positive emotional state and concise information for a negative emotional state. The input is the emotional state from step 3 and the analysis results from step 5. The output is formatted data (e.g., the analysis results in JSON format).

[0530] Step 7:

[0531] Finally, the server returns the formatted analysis results to the user, who can view the results on their device. The input is the data formatted in step 6. The output is the analysis results displayed on the user's device, providing the user with the information they need to develop their advertising strategy.

[0532] 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.

[0533] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0534] 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.

[0535] [Third embodiment]

[0536] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0537] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0538] 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).

[0539] 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.

[0540] 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.

[0541] 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).

[0542] 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.

[0543] 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.

[0544] 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.

[0545] 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.

[0546] 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.

[0547] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0548] The present invention is a system that includes a means for inputting specific keywords, a means for collecting data via the Internet, a means for analyzing the collected data and extracting specific target name recognition and attribute information of the target demographic, and a means for providing the analysis results to the user.

[0549] Program processing flow

[0550] 1. User Request Submission

[0551] A user enters a specific keyword into the system's interface (e.g., a web browser or a mobile application), then clicks a "Start Search" button on the interface to send a request to the server, which includes the keyword entered by the user.

[0552] 2. Server receives request and starts processing

[0553] The server receives a user request and calls the user_request_handler function. It extracts keywords from the request and gets them as keyword = request['keyword']. The server then calls the process_request function to start collecting data based on the keywords.

[0554] 3. Data Collection

[0555] The server uses the gather_data(keyword) function to gather relevant data from social media and the web. It uses social media APIs and web crawler technology to obtain data related to the specified keyword. Specifically, it sends an API request and receives the relevant data as a response.

[0556] 4. Data analysis and information extraction

[0557] The server passes the data obtained by the gather_data function to the analyze_data(data) function and performs the analysis. Based on the collected data, it uses statistical methods to analyze the awareness score, target demographic age distribution, gender distribution, and interests to extract the necessary attribute information. For example, the awareness score is calculated based on "mentions = data.get('mentions')", and awareness is calculated as "awareness = mentions / 1000".

[0558] Information about the target demographic includes the age distribution (target_age = { "20-30": 50, "30-40": 30, "40-50": 20}), the gender distribution (target_gender = { "male": 60, "female": 40}), and interests (interests = ["tech", "sports", "music"]).

[0559] 5. Providing results

[0560] The server formats the analysis results in JSON format and prepares them for the user. Next, it sends the results back to the user via the user_request_handler function, and the user receives the analysis results. Based on these results, the user can develop marketing and sales strategies.

[0561] Specific examples

[0562] For example, if a user starts a survey on "TestBrand," the server receives a request with "TestBrand" entered and collects data. Assume that data related to "TestBrand" is obtained through a social media API and the number of mentions is 850. For example, if you enter "data = {'mentions': 850}," the name recognition is calculated as "850 / 1000 = 0.85." The target demographic's age distribution, gender distribution, and interest information are also analyzed and returned as results. For example, information such as "50% are 20-30 years old, 60% are male, 40% are female, and their interests are technology, sports, and music" can be obtained.

[0563] This system allows users to quickly and easily obtain detailed information about the brand awareness of "TestBrand" and the attributes of their target demographic, and based on this information, they can formulate appropriate marketing and sales strategies.

[0564] The processing flow will be explained below.

[0565] Step 1:

[0566] The user enters a proper noun. The user enters keywords for a specific company or brand into the system's interface. Then, the user clicks the "Start Search" button, which sends a request to the server. This request includes the keywords entered by the user.

[0567] Step 2:

[0568] The server receives the request. The server receives the user request and calls the user_request_handler function. It extracts keywords from the request and gets the keyword information with keyword = request['keyword'].

[0569] Step 3:

[0570] The server starts data collection. The server calls the process_request function to start collecting data based on the keyword. Specifically, it uses the gather_data(keyword) function to gather relevant data from social media and the web.

[0571] Step 4:

[0572] The server collects data over the Internet. The gather_data(keyword) function retrieves data related to the specified keyword using social media APIs or web crawlers. It sends an API request and receives the relevant data in response.

[0573] Step 5:

[0574] The server analyzes the data. The server passes the data obtained by the gather_data function to the analyze_data(data) function and performs data analysis. Here, the collected data is used to statistically analyze the recognition of specific targets, the age distribution, gender distribution, and interest information of the target demographic.

[0575] Step 6:

[0576] The server calculates the popularity. For example, if the acquired data contains "mentions = 850", the popularity is calculated as "850 / 1000 = 0.85".

[0577] Step 7:

[0578] The server extracts the target demographic's attribute information. The target demographic's age distribution, gender distribution, and interest information are extracted from the data. For example, the age distribution would be "target_age = { "20-30": 50, "30-40": 30, "40-50": 20}", the gender distribution would be "target_gender = { "male": 60, "female": 40}", and the interests would be "interests = ["tech", "sports", "music"]".

[0579] Step 8:

[0580] The server formats the analysis results in JSON format and prepares them for delivery to the user. Specifically, it converts the results to JSON format using json.dumps(analysis_result).

[0581] Step 9:

[0582] The server returns the results to the user. The server returns the analysis results to the user via the user_request_handler function. The user can receive these results and use them to formulate marketing and sales strategies.

[0583] Example 1

[0584] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0585] In today's world, for companies to develop effective marketing and sales strategies, data such as demographic information on target demographics and the popularity of specific keywords is essential. However, there is a lack of efficient ways to collect and analyze this data, making it difficult to quickly and accurately obtain the information you want.

[0586] 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.

[0587] In this invention, the server includes a means for inputting specific keywords, a means including a social media API and a web crawler for collecting data via the Internet, a statistical analysis means for analyzing the collected data and extracting specific target name recognition, age distribution, gender distribution, and interest information of the target demographic, and a means for formatting the analysis results in JSON format and providing them to users. This enables companies to quickly and accurately obtain detailed attribute information and name recognition data of their target demographics and develop effective marketing and sales strategies.

[0588] The "means for entering specific keywords" refers to the interface (web browser or mobile application) through which users enter the keywords they wish to research.

[0589] "Methods for collecting data via the internet, including social media APIs and web crawlers" refers to technologies for automatically collecting relevant data from social media and web pages on the internet.

[0590] "Statistical analysis means for analyzing collected data and extracting the name recognition of specific targets, the age distribution, gender distribution, and interest information of the target demographic" refers to programs or algorithms for analyzing collected data and extracting the name recognition of specific targets and attribute information of the target demographic (age distribution, gender distribution, interest information) using statistical methods.

[0591] "Means for formatting the analysis results in JSON format and providing them to users" refers to a technology for formatting the analysis results in a structured data format (JSON: JavaScript Object Notation) and providing it to users.

[0592] The present invention provides a system for allowing a user to input a specific keyword, collecting data related to the keyword via the Internet, and providing analysis results. The system comprises the following means.

[0593] First, the user enters the keywords to be investigated using the system interface (web browser or mobile application). The interface has a "Start Investigation" button, and when the user clicks this, the keywords are sent to the server.

[0594] The server receives a request from a user and extracts the keywords included in the request. The server then begins collecting data based on the specified keywords. Specifically, it uses social media APIs and web crawler technology on the Internet to collect related data. For example, social media APIs can be used to obtain post and comment data related to specific keywords. It is also possible to use web crawlers to scrape information from related web pages.

[0595] The collected data is analyzed on the server. During the analysis, specific target name recognition, age distribution, gender distribution, and interest information of the target demographic are extracted from the data. These analyses are performed using statistical methods to extract attribute information. For example, a name recognition score is calculated based on the number of mentions in the collected data, and age distribution, gender distribution, and interest information of the target demographic are also statistically organized.

[0596] Finally, the server formats the analysis results into JSON format and prepares them for delivery to the user. The analysis results are converted into a structured data format (JSON: JavaScript Object Notation) and sent back to the user. The user can check the analysis results on the interface and use them to develop marketing and sales strategies.

[0597] Specific examples

[0598] For example, if a user starts a survey on "TestBrand", the following will happen:

[0599] The user enters "TestBrand" into the system's web interface and clicks the "Start Survey" button.

[0600] The server receives this request and extracts keyword = 'TestBrand'.

[0601] The server calls the gather_data('TestBrand') function to gather data using social media APIs and web crawlers. For example, if there are 850 mentions, the server gets "data = {'mentions': 850}".

[0602] The server passes this data to the analyze_data(data) function, extracting a popularity score of 0.85 and target demographic attributes: target_age = { '20-30': 50, '30-40': 30, '40-50': 20}, target_gender = { 'male': 60, 'female': 40}, and interests = ['tech', 'sports', 'music'].

[0603] The server formats the analysis results into JSON format and returns them to the user, who can then use this information to develop specific marketing strategies.

[0604] This system allows users to quickly and easily obtain detailed information about the brand awareness of "TestBrand" and the attributes of their target demographic, and use this information to develop effective marketing and sales strategies.

[0605] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0606] Step 1:

[0607] The user opens the system interface (web browser or mobile application) and enters a specific keyword. After entering the keyword, the user clicks the "Start Search" button, which sends the request to the server. The input data is the specific keyword entered by the user. The output data is the request sent to the server.

[0608] Step 2:

[0609] The server receives a user request and extracts keywords from the request. In this process, the server executes keyword = request['keyword'] from the request. The input is the request sent by the user, and the output is the extracted keywords.

[0610] Step 3:

[0611] The server uses the extracted keywords to call the gather_data(keyword) function to gather related data from the Internet. This process involves using social media APIs and web crawler technology to obtain data. Specifically, it sends requests to social media APIs to obtain related post and comment data, and uses web crawlers to scrape related web pages. The input is the keywords, and the output is the collected related data.

[0612] Step 4:

[0613] The server passes the collected data to the analyze_data(data) function to perform data analysis. During the analysis, specific target awareness, age distribution, gender distribution, and interest information of the target demographic are extracted using statistical methods. For example, the awareness score is calculated based on "mentions = data.get('mentions')" and "awareness = mentions / 1000". In addition, age distribution, gender distribution, and interest information are statistically organized from the collected data. The input is the collected data, and the output is the analysis results.

[0614] Step 5:

[0615] The server formats the analysis results in JSON format and prepares them for delivery to the user. During this process, the server converts the analysis results into JSON format as follows: json_result = json.dumps(analysis_result) . The formatted JSON results are sent back to the user. The input is the analysis results, and the output is the analysis results in JSON format.

[0616] Step 6:

[0617] Users receive the analysis results provided through the system interface and use that data to develop marketing and sales strategies. The input is the analysis results in JSON format, and the output is the basis for the strategy developed by the user.

[0618] This specific processing flow enables users to quickly and accurately obtain detailed attribute information and name recognition data for their target demographic, and to formulate effective strategies based on this information.

[0619] (Application example 1)

[0620] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0621] While conventional systems were capable of collecting and analyzing brand awareness and target demographic information related to specific keywords, they lacked a way for users to easily check the results in real time. Furthermore, the analysis results were not sufficiently visualized, making it difficult for users to quickly and effectively utilize them in their marketing strategies. Therefore, there is a need for real-time visualization of collected data and for improvements in the method of providing analysis results through that visualization.

[0622] 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.

[0623] In this invention, the server includes a means for inputting specific keywords, a means for collecting data via the Internet, a means for analyzing the collected data and extracting specific target name recognition and target demographic attribute information, a means for providing the analysis results to the user, and a means for visualizing the results on a smart device. This allows the analysis results to be visually displayed on the smart device in real time, allowing the user to quickly and effectively formulate a marketing strategy.

[0624] "Specific keywords" are words or phrases that users enter into the system and select for analysis.

[0625] "Means of collecting data via the internet" refers to the functions and technologies used to obtain information from websites and social media.

[0626] "Means of analyzing collected data and extracting specific target name recognition and target demographic attribute information" refers to functions and technologies that use statistical methods based on collected data to derive name recognition scores and target demographic attributes (age, gender, interests).

[0627] "Means for providing analysis results to users" refers to the functions and technologies for notifying and displaying the analyzed information to users.

[0628] "Means for visualizing results on smart devices" refers to functions and technologies for graphically displaying analysis results on digital devices such as smartphones and tablets.

[0629] A "social media API" is a programmatic interface for retrieving data from social media platforms such as Twitter and Facebook.

[0630] "Display in real time" means that collected and analyzed data is displayed to the user immediately without delay.

[0631] This invention is a system that inputs specific keywords, collects data via the Internet, analyzes the data, extracts name recognition and target demographic attribute information, and finally provides the analysis results to users. Furthermore, this system includes a means for visualizing the results on a smart device.

[0632] Hardware

[0633] Server: High-performance cloud server (e.g., Amazon Web Services, Google Cloud Platform)

[0634] Smart device: Smartphone (Android or iOS)

[0635] software

[0636] Smartphone application: Swift (iOS), Kotlin (Android)

[0637] Data collection: Python, Requests library, social media APIs (e.g. Twitter API, Facebook Graph API)

[0638] Data analysis: Python, Pandas, NumPy, scikit-learn

[0639] Server-side framework: Django or Flask (Python)

[0640] Program Overview

[0641] The server provides an interface for entering specific keywords, and once the user enters the keywords, data collection begins. The server collects data using social media APIs and analyzes the data to extract name recognition scores and target demographic attribute information. The analysis results are visualized in real time on a smart device, allowing users to quickly develop marketing strategies based on the results.

[0642] Processing flow

[0643] 1. User submits request:

[0644] Using a smartphone application, a user inputs a specific keyword and clicks a button to start the analysis, and the request is sent to the server.

[0645] 2. The server receives the request and begins processing it:

[0646] The server calls the user_request_handler function to extract keywords from the request, then uses the process_request function to start collecting data.

[0647] 3. Data Collection:

[0648] The server uses the gather_data function to gather relevant data through social media APIs, for example, by using the Twitter API or the Facebook Graph API.

[0649] 4. Data analysis and information extraction:

[0650] The server analyzes the collected data using the analyze_data function, which uses statistical methods to analyze the popularity score and target demographic attributes (age, gender, interests) to extract the necessary information.

[0651] 5. Providing results:

[0652] The analysis results are formatted in JSON format and visualized in real time on a smart device.

[0653] Specific examples

[0654] For example, to analyze an advertising campaign for "TestBrand," a user enters "TestBrand" into the application. The server collects data related to "TestBrand" through social media APIs and determines that the number of mentions is 850. It calculates the name recognition as "850 / 1000 = 0.85" and analyzes the target demographic's age distribution, gender distribution, and interests to obtain the results. This allows the user to check "TestBrand"'s name recognition and detailed demographic information of the target demographic in real time, enabling them to quickly develop effective marketing strategies.

[0655] Prompt Sentence Examples

[0656] An example of a prompt is:

[0657] "Collect data from social media to analyze awareness and demographic information for the following keyword: 'TestBrand'."

[0658] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0659] Step 1:

[0660] A user opens a smartphone application, enters a specific keyword, and clicks a button to start the analysis. This action sends the keyword to the server as a request. (Input) The keyword entered by the user. (Output) The request to the server.

[0661] Step 2:

[0662] The server receives a user request and calls the user_request_handler function. This function extracts a keyword from the request and passes it to the process_request function to start data collection. (Input) User request (keyword). (Output) Collection start trigger (keyword).

[0663] Step 3:

[0664] The server uses the gather_data(keyword) function to gather data related to a keyword through social media APIs (e.g., Twitter API, Facebook Graph API). It sends a request appropriate to the API to be used and collects the data obtained in the response. (Input) Specific keyword. (Output) Collected social media data.

[0665] Step 4:

[0666] The server passes the data obtained by the gather_data function to the analyze_data(data) function and performs data analysis. This function uses statistical methods to analyze the popularity score and target demographic attributes (age, gender, interests) based on the collected data, and extracts the necessary attribute information. (Input) Collected social media data. (Output) Analyzed popularity score and target demographic attribute information.

[0667] Step 5:

[0668] The server formats the analysis results in JSON format and returns them to the smart device via the user_request_handler function. The smartphone application displays the analysis results in real time based on the received JSON data. (Input) Analyzed popularity score and target demographic attribute information. (Output) Visualized analysis results on the smart device.

[0669] 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.

[0670] The present invention is a system that includes a means for inputting specific keywords, a means for collecting data via the Internet, a means for analyzing the collected data and extracting specific target popularity and target demographic attribute information, and a means for providing the analysis results to users. Furthermore, the system aims to improve the user experience by combining an emotion engine that recognizes the user's emotions, analyzing the user's emotional state, and adjusting the way the information is presented.

[0671] Program processing flow

[0672] 1. User Request Submission

[0673] The user enters a specific keyword into the system's interface (e.g., a web browser or a mobile application), then clicks the "Start Investigation" button, sending a request to the server. This request includes the keyword entered by the user, and the emotion engine also begins to operate.

[0674] 2. Server request reception and sentiment analysis

[0675] The server receives a user request and calls the user_request_handler function. It extracts keywords from the request and obtains the keyword information using keyword = request['keyword']. The server then uses an emotion engine to analyze the user's emotional state for the keywords. The emotional state can be determined using, for example, text analysis or natural language processing techniques.

[0676] 3. Data Collection

[0677] The server calls the process_request function to start collecting data based on the keywords and emotional state. Specifically, it uses the gather_data(keyword) function to gather relevant data from social media and the web. It uses social media APIs and web crawler technology to obtain data related to the specified keywords.

[0678] 4. Data analysis and information extraction

[0679] The server passes the data obtained by the gather_data function to the analyze_data(data) function for data analysis. Based on the collected data, the server uses statistical methods to analyze the specific target popularity, age distribution, gender distribution, and interest information of the target demographic, and extracts the necessary attribute information. For example, the popularity score is calculated based on the number of hits.

[0680] The target demographic information is analyzed as follows: age distribution: "target_age = { "20-30": 50, "30-40": 30, "40-50": 20}", gender distribution: "target_gender = { "male": 60, "female": 40}", and interests: "interests = ["tech", "sports", "music"]".

[0681] 5. Providing results

[0682] The server formats the analysis results in JSON format and prepares them for the user. It then sends the results back to the user through the user_request_handler function. The presentation of the analysis results is adjusted based on the user's emotional state. For example, if the user has a positive emotional state, the analysis results may be presented in detail. Conversely, if the user has a negative emotional state, the analysis results may be presented in a concise summary.

[0683] Specific examples

[0684] For example, if a user starts a survey on "SampleBrand," the server receives a request with "SampleBrand" entered and analyzes the user's emotional state using an emotion engine. Next, data related to "SampleBrand" is obtained through a social media API, and the number of mentions is assumed to be 1,500. In other words, if "data = {'mentions': 1,500}" is entered, the name recognition is calculated as "1,500 / 1,000 = 1.5." The target demographic's age distribution, gender distribution, and interest information are also analyzed and returned as results.

[0685] This system allows users to quickly and easily obtain detailed information about the brand's popularity and target demographics, enabling them to formulate appropriate marketing and sales strategies. It also adjusts the way information is presented to users based on their emotional state, providing a better user experience.

[0686] The processing flow will be explained below.

[0687] Step 1:

[0688] The user enters a proper noun. The user enters keywords for a specific company or brand into the system's interface. Then, the user clicks the "Start Search" button, which sends a request to the server. This request includes the keywords entered by the user.

[0689] Step 2:

[0690] The server receives the request. The server receives the user request and calls the user_request_handler function. It extracts keywords from the request and gets the keyword information with keyword = request['keyword'].

[0691] Step 3:

[0692] The server launches an emotion engine to analyze the user's emotion. The server uses the emotion engine to analyze the user's emotional state in response to the input keywords. The emotion engine determines the emotional state using text analysis and natural language processing techniques.

[0693] Step 4:

[0694] The server starts data collection. The server calls the process_request function to start data collection based on keywords and emotional states. Specifically, the server uses the gather_data(keyword) function to gather relevant data from social media and the web.

[0695] Step 5:

[0696] The server collects data over the Internet. The gather_data(keyword) function retrieves data related to a specified keyword using social media APIs or web crawlers. For example, it sends an API request and receives the relevant data in response.

[0697] Step 6:

[0698] The server analyzes the data. The server passes the data obtained by the gather_data function to the analyze_data(data) function and performs data analysis. Based on the collected data, it uses statistical methods to analyze the recognition of specific targets, the age distribution, gender distribution, and interest information of the target demographic.

[0699] Step 7:

[0700] The server calculates the popularity. If the retrieved data includes "mentions = 850", the popularity is calculated as "850 / 1000 = 0.85".

[0701] Step 8:

[0702] The server extracts the target demographic's attribute information. The target demographic's age distribution, gender distribution, and interest information are extracted from the data. For example, the age distribution would be "target_age = { "20-30": 50, "30-40": 30, "40-50": 20}", the gender distribution would be "target_gender = { "male": 60, "female": 40}", and the interests would be "interests = ["tech", "sports", "music"]".

[0703] Step 9:

[0704] The server formats the analysis results in JSON format and prepares them for delivery to the user. Specifically, it converts the results to JSON format using json.dumps(analysis_result).

[0705] Step 10:

[0706] The server adjusts the results based on the user's emotions. Based on the analysis results of the emotion engine, the depth and format of the information presented can be adjusted. For example, detailed data can be displayed for a positive emotional state, and concise information can be displayed for a negative emotional state.

[0707] Step 11:

[0708] The server returns the analysis results to the user via the user_request_handler function. The user can receive the results and use them to formulate marketing and sales strategies.

[0709] Example 2

[0710] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0711] When users acquire brand awareness or target demographic attribute information based on specific keywords, conventional systems have had issues with extracting information and analyzing results that cannot flexibly adapt to the user's emotional state, resulting in a lack of improvement in the user experience. Additionally, the scope of information collected is limited, making comprehensive analysis of the data difficult.

[0712] 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.

[0713] In this invention, the server includes a means for a user to input a specific keyword, a means for collecting data via the Internet, a means for analyzing the collected data and extracting specific popularity and target demographic attribute information, a means for performing analysis based on the collected data using an emotion engine that recognizes the user's emotional state, and a means for adjusting and providing the analysis results based on the user's emotional state. This enables flexible information presentation that takes the user's emotional state into consideration, thereby improving the user experience.

[0714] A "user" is an individual or company that uses the system and enters keywords and obtains information.

[0715] "Keywords" are specific words or phrases that users enter into the system to specify the information they wish to search.

[0716] The "Internet" is an information and communications network made up of computer networks around the world, and is a means of collecting data and transmitting information.

[0717] "Data" refers to the information that is collected and analyzed, including in the form of text, images, video, etc. obtained from social media and websites.

[0718] "Famousness" is an indicator that shows how well-known an object (e.g., product, brand, service, etc.) related to a specific keyword is in society.

[0719] "Target demographic" refers to the group of people who are likely to consume or use the information being surveyed, and includes their demographic information (age, gender, interests, etc.).

[0720] An "emotion engine" is an algorithm or system that analyzes keywords and other text information entered by a user to recognize the user's emotional state (positive, negative, etc.).

[0721] "Social Media API" means an application programming interface provided by a social media platform that allows users to retrieve data related to specific keywords.

[0722] "Web crawler technology" refers to programs and algorithms that automatically crawl web pages on the Internet and analyze their content.

[0723] "Analysis results" refers to information analyzed using statistical methods and algorithms based on collected data, and includes brand recognition and attribute information of the target demographic.

[0724] "JSON format" is an abbreviation for JavaScript Object Notation, and is a lightweight data format widely used for data exchange.

[0725] The "system" is a design having the overall structure and functions of the present invention, and is a platform consisting of multiple means (modules).

[0726] This invention is a system that allows users to input specific keywords, collect data via the Internet, analyze the collected data, and provide information on brand recognition and target demographic attributes.The system also aims to improve the user experience by using an emotion engine that recognizes the user's emotional state and adjusting the way the analysis results are presented based on the user's emotional state.

[0727] Specifically, a user first enters a specific keyword into the system interface via a web browser or mobile application and clicks the "Start Investigation" button, which sends a request to the server and simultaneously starts the emotion engine.

[0728] The server receives the request sent by the user and internally calls the user_request_handler function to extract keywords. The server then uses an emotion engine to analyze the user's emotional state. This emotion analysis uses text analysis and natural language processing techniques, such as the BERT model.

[0729] Next, the server calls the process_request function to start collecting data based on the keywords and sentiment state. Specifically, the gather_data(keyword) function uses social media APIs and web crawler technology to gather relevant data. For example, it uses the Twitter API and BeautifulSoup to retrieve related tweets and web page information.

[0730] The collected data is passed to the analyze_data(data) function and analyzed by the server. During the analysis, a popularity score is calculated based on the number of mentions and hashtag frequency of the collected data. In addition, the target demographic's age distribution, gender distribution, and interest information are analyzed using statistical methods to extract the necessary attribute information.

[0731] Finally, the server formats the analysis results into JSON format and returns them to the user via the user_request_handler function. The way the analysis results are presented is adjusted based on the user's emotional state: if the emotional state is positive, detailed analysis results are presented, and if the emotional state is negative, concise summary results are presented.

[0732] Specific examples

[0733] For example, if a user starts a search for "SampleBrand," the server receives a request containing the keyword "SampleBrand" and uses an emotion engine to analyze the user's emotional state. Next, data related to "SampleBrand" is retrieved through a social media API, and the number of mentions is assumed to be 1,500. Based on the number of mentions in the collected data, the awareness score is calculated as "1,500 / 1,000 = 1.5." The target demographic's age distribution and interest information are also analyzed and provided to the user.

[0734] This system allows users to quickly and easily obtain detailed attribute information about the "SampleBrand" brand and its target demographic, which can be used as a reference when formulating marketing and sales strategies. Furthermore, by providing information according to the user's emotional state, a better user experience is provided.

[0735] Specific examples of prompts to input to generative AI models

[0736] What is the overall flow when a user starts an investigation on "SampleBrand"? Please explain in detail how the user enters a keyword, a request is sent to the server, data is collected, analyzed, and the results are delivered based on the sentiment engine's analysis.

[0737] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0738] Step 1:

[0739] A user enters a specific keyword into the system's interface through a web browser or mobile application and clicks the "Start Investigation" button. This request includes the keyword entered by the user. The emotion engine also starts working at this point. The keyword is provided as input, and a request is sent to the server as output.

[0740] Step 2:

[0741] The server receives the request and calls the user_request_handler function internally to extract keywords. Specifically, keywords are obtained from the request in the format request['keyword']. Next, the server uses an emotion engine to analyze the user's emotional state for the obtained keywords. Natural language processing techniques such as the BERT model are used for emotion analysis. The keywords in the request are provided as input, and the emotional state is obtained as output.

[0742] Step 3:

[0743] The server calls the process_request function to start collecting data based on keywords and emotional states. The specific data collection is performed using the gather_data(keyword) function. This function uses social media APIs (e.g., Twitter API) or web crawler technology (e.g., BeautifulSoup) to gather data related to keywords. Keywords and emotional states are provided as input, and related data is collected as output.

[0744] Step 4:

[0745] The server passes the collected data to the analyze_data(data) function for analysis. Specifically, it statistically analyzes the number of mentions and hashtag frequency in the collected data to extract a popularity score and target demographic attribute information (age distribution, gender distribution, interests). The collected data is provided as input, and the analysis results are obtained as output. For example, the popularity score is calculated using the formula mentions_count / 1000.

[0746] Step 5:

[0747] The server formats the analysis results into JSON format and returns them to the user via the user_request_handler function. At this stage, the way the analysis results are presented is adjusted based on the user's emotional state. For example, a detailed analysis result is presented for a positive emotional state, while a concise summary is provided for a negative emotional state. The analysis results and the emotional state are provided as input, and the adjusted analysis results are obtained as output.

[0748] (Application example 2)

[0749] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0750] Conventional advertising systems provide a means to acquire target name recognition and attribute information, but do not adjust the display method to take into account the user's emotional state. As a result, the user experience is not sufficiently improved, and optimal advertising proposals cannot be presented.

[0751] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for inputting a specific keyword, a means for collecting data via the Internet, a means for analyzing the collected data and extracting specific target popularity and attribute information of the target demographic, a means for providing the analysis results to the user, and a means for recognizing the user's emotional state and adjusting the method of presenting the information to be provided. This enables flexible information presentation according to the user's emotional state.

[0752] 1. "Specific Keywords" refers to words or phrases that users enter to describe a particular subject or concept that interests them.

[0753] 2. "Means of collecting data via the Internet" refers to methods and technologies for automatically obtaining relevant data from various sources on the Internet.

[0754] 3. "Means of analyzing collected data and extracting specific target awareness and target demographic attribute information" refers to technology that processes collected data and derives the awareness of a target and the attributes of that target demographic (e.g., age, gender, interests).

[0755] 4. "Means for providing analysis results to users" refers to the technology and methods for displaying analyzed information in a format that is easy for users to understand.

[0756] 5. "Means for recognizing the user's emotional state and adjusting the way information is presented" refers to technology that analyzes and understands the user's emotions and appropriately changes the way information is displayed based on the results.

[0757] 6. "Social Media API" refers to a means of obtaining data related to specific keywords using an application programming interface (API) provided by a social media platform.

[0758] The present invention is a system that includes a means for inputting specific keywords, a means for collecting data via the Internet, a means for analyzing the collected data and extracting specific target popularity and target demographic attribute information, and a means for providing the analysis results to users.Furthermore, the system aims to improve the user experience by combining an emotion engine that recognizes the user's emotions, analyzing the user's emotional state, and adjusting the way the information is presented.

[0759] Overall system configuration and operation flow

[0760] Program processing overview

[0761] The server receives requests sent by users and collects relevant data based on specific keywords included in the request. The collected data is analyzed to extract specific target popularity and target demographic attribute information (age, gender, interests). Furthermore, the server analyzes the user's emotional state and adjusts the presentation of the information provided according to the user's emotional state.

[0762] Specific implementation description

[0763] 1. A user inputs a specific keyword into a device (smartphone or PC) and sends a request to the server. This request includes the specific keyword that the user is interested in and data to obtain the user's emotional state.

[0764] 2. The server is built using Python or a similar programming language. Upon receiving a user request, the server analyzes the user's emotional state using TextBlob or a similar natural language processing tool.

[0765] 3. The server uses social media APIs and web crawler technology to collect data related to the keywords over the internet. This step utilizes public social media APIs such as the Twitter API and Facebook Graph API.

[0766] 4. The collected data is analyzed on the server to extract specific target awareness and demographic information. Statistical methods and machine learning models are used for the analysis.

[0767] 5. The server formats the analysis results in JSON format and adjusts the presentation of information based on the user's emotional state: detailed information is provided if the user has a positive emotion, and concise information is provided if the user has a negative emotion.

[0768] 6. Finally, the server sends the analysis results back to the user, who can view the information. This information is used by advertisers to develop optimal advertising strategies for their target audience.

[0769] Examples of concrete examples and prompts

[0770] For example, when a marketer wants to research the popularity of a particular brand, the system will collect relevant data from social media APIs based on the keyword "specific brand." The system will then analyze the popularity and target demographic information, and provide detailed information in a way that reflects the user's emotional state. This will make it easier for advertisers to develop optimal advertising strategies.

[0771] Example prompt sentence:

[0772] "The system collects data related to the keywords entered by the user, analyzes the popularity of the specified keywords and the demographic information of the target demographic, and provides it. It also adjusts the way information is presented depending on the user's emotional state."

[0773] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0774] Step 1:

[0775] The user enters a specific keyword into a device (smartphone or PC) and sends a request to the server. This request includes the specific keyword and a text message to obtain the user's emotional state. The input is the user sending the keyword "specific brand" and a message indicating their emotion. The output is received by the server.

[0776] Step 2:

[0777] The server processes the received request using the user_request_handler function to extract keywords and user messages. Specifically, it uses a Python library to extract keywords (e.g., "specific brand") and user messages (e.g., "I want to know more about this brand") from the request. The input is the received request, which is the output of step 1. The output is the extracted keywords and user messages.

[0778] Step 3:

[0779] The server uses natural language processing techniques such as TextBlob to analyze the emotional state of the user message. The emotional state is classified as positive, negative, or neutral. For example, a positive emotion is detected from the message "I want to know more about this brand." The input is the user message extracted in step 2. The output is the analyzed emotional state.

[0780] Step 4:

[0781] The server uses the gather_data function to collect keyword-related data from the Internet (e.g., social media APIs). Specifically, it uses the Twitter API and Facebook Graph API to obtain posts related to a "specific brand." The input is the keywords extracted in step 2. The output is the collected data (e.g., posts from social media).

[0782] Step 5:

[0783] The collected data is analyzed using the analyze_data function to extract specific target name recognition and target demographic attribute information (age, gender, interests). Specifically, name recognition is calculated based on the number of collected posts, and age distribution, gender distribution, and interest information are analyzed using statistical methods. The input is the data collected in step 4. The output is the analysis results (e.g., name recognition score, age distribution, gender distribution, interest information).

[0784] Step 6:

[0785] The server formats the analysis results in JSON format and adjusts the way information is presented based on the user's emotional state. For example, it provides detailed information for a positive emotional state and concise information for a negative emotional state. The input is the emotional state from step 3 and the analysis results from step 5. The output is formatted data (e.g., the analysis results in JSON format).

[0786] Step 7:

[0787] Finally, the server returns the formatted analysis results to the user, who can view the results on their device. The input is the data formatted in step 6. The output is the analysis results displayed on the user's device, providing the user with the information they need to develop their advertising strategy.

[0788] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0789] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0790] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[0791] [Fourth embodiment]

[0792] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0793] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0794] 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).

[0795] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0796] 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.

[0797] 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).

[0798] 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.

[0799] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0800] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0801] 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.

[0802] 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.

[0803] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0804] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0805] The present invention is a system that includes a means for inputting specific keywords, a means for collecting data via the Internet, a means for analyzing the collected data and extracting specific target name recognition and attribute information of the target demographic, and a means for providing the analysis results to the user.

[0806] Program processing flow

[0807] 1. User Request Submission

[0808] A user enters a specific keyword into the system's interface (e.g., a web browser or a mobile application), then clicks a "Start Search" button on the interface to send a request to the server, which includes the keyword entered by the user.

[0809] 2. Server receives request and starts processing

[0810] The server receives a user request and calls the user_request_handler function. It extracts keywords from the request and gets them as keyword = request['keyword']. The server then calls the process_request function to start collecting data based on the keywords.

[0811] 3. Data Collection

[0812] The server uses the gather_data(keyword) function to gather relevant data from social media and the web. It uses social media APIs and web crawler technology to obtain data related to the specified keyword. Specifically, it sends an API request and receives the relevant data as a response.

[0813] 4. Data analysis and information extraction

[0814] The server passes the data obtained by the gather_data function to the analyze_data(data) function and performs the analysis. Based on the collected data, it uses statistical methods to analyze the awareness score, target demographic age distribution, gender distribution, and interests to extract the necessary attribute information. For example, the awareness score is calculated based on "mentions = data.get('mentions')", and awareness is calculated as "awareness = mentions / 1000".

[0815] Information about the target demographic includes the age distribution (target_age = { "20-30": 50, "30-40": 30, "40-50": 20}), the gender distribution (target_gender = { "male": 60, "female": 40}), and interests (interests = ["tech", "sports", "music"]).

[0816] 5. Providing results

[0817] The server formats the analysis results in JSON format and prepares them for the user. Next, it sends the results back to the user via the user_request_handler function, and the user receives the analysis results. Based on these results, the user can develop marketing and sales strategies.

[0818] Specific examples

[0819] For example, if a user starts a survey on "TestBrand," the server receives a request with "TestBrand" entered and collects data. Assume that data related to "TestBrand" is obtained through a social media API and the number of mentions is 850. For example, if you enter "data = {'mentions': 850}," the name recognition is calculated as "850 / 1000 = 0.85." The target demographic's age distribution, gender distribution, and interest information are also analyzed and returned as results. For example, information such as "50% are 20-30 years old, 60% are male, 40% are female, and their interests are technology, sports, and music" can be obtained.

[0820] This system allows users to quickly and easily obtain detailed information about the brand awareness of "TestBrand" and the attributes of their target demographic, and based on this information, they can formulate appropriate marketing and sales strategies.

[0821] The processing flow will be explained below.

[0822] Step 1:

[0823] The user enters a proper noun. The user enters keywords for a specific company or brand into the system's interface. Then, the user clicks the "Start Search" button, which sends a request to the server. This request includes the keywords entered by the user.

[0824] Step 2:

[0825] The server receives the request. The server receives the user request and calls the user_request_handler function. It extracts keywords from the request and gets the keyword information with keyword = request['keyword'].

[0826] Step 3:

[0827] The server starts data collection. The server calls the process_request function to start collecting data based on the keyword. Specifically, it uses the gather_data(keyword) function to gather relevant data from social media and the web.

[0828] Step 4:

[0829] The server collects data over the Internet. The gather_data(keyword) function retrieves data related to the specified keyword using social media APIs or web crawlers. It sends an API request and receives the relevant data in response.

[0830] Step 5:

[0831] The server analyzes the data. The server passes the data obtained by the gather_data function to the analyze_data(data) function and performs data analysis. Here, the collected data is used to statistically analyze the recognition of specific targets, the age distribution, gender distribution, and interest information of the target demographic.

[0832] Step 6:

[0833] The server calculates the popularity. For example, if the acquired data contains "mentions = 850", the popularity is calculated as "850 / 1000 = 0.85".

[0834] Step 7:

[0835] The server extracts the target demographic's attribute information. The target demographic's age distribution, gender distribution, and interest information are extracted from the data. For example, the age distribution would be "target_age = { "20-30": 50, "30-40": 30, "40-50": 20}", the gender distribution would be "target_gender = { "male": 60, "female": 40}", and the interests would be "interests = ["tech", "sports", "music"]".

[0836] Step 8:

[0837] The server formats the analysis results in JSON format and prepares them for delivery to the user. Specifically, it converts the results to JSON format using json.dumps(analysis_result).

[0838] Step 9:

[0839] The server returns the results to the user. The server returns the analysis results to the user via the user_request_handler function. The user can receive these results and use them to formulate marketing and sales strategies.

[0840] Example 1

[0841] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0842] In today's world, for companies to develop effective marketing and sales strategies, data such as demographic information on target demographics and the popularity of specific keywords is essential. However, there is a lack of efficient ways to collect and analyze this data, making it difficult to quickly and accurately obtain the information you want.

[0843] 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.

[0844] In this invention, the server includes a means for inputting specific keywords, a means including a social media API and a web crawler for collecting data via the Internet, a statistical analysis means for analyzing the collected data and extracting specific target name recognition, age distribution, gender distribution, and interest information of the target demographic, and a means for formatting the analysis results in JSON format and providing them to users. This enables companies to quickly and accurately obtain detailed attribute information and name recognition data of their target demographics and develop effective marketing and sales strategies.

[0845] The "means for entering specific keywords" refers to the interface (web browser or mobile application) through which users enter the keywords they wish to research.

[0846] "Methods for collecting data via the internet, including social media APIs and web crawlers" refers to technologies for automatically collecting relevant data from social media and web pages on the internet.

[0847] "Statistical analysis means for analyzing collected data and extracting the name recognition of specific targets, the age distribution, gender distribution, and interest information of the target demographic" refers to programs or algorithms for analyzing collected data and extracting the name recognition of specific targets and attribute information of the target demographic (age distribution, gender distribution, interest information) using statistical methods.

[0848] "Means for formatting the analysis results in JSON format and providing them to users" refers to a technology for formatting the analysis results in a structured data format (JSON: JavaScript Object Notation) and providing it to users.

[0849] The present invention provides a system for allowing a user to input a specific keyword, collecting data related to the keyword via the Internet, and providing analysis results. The system comprises the following means.

[0850] First, the user enters the keywords to be investigated using the system interface (web browser or mobile application). The interface has a "Start Investigation" button, and when the user clicks this, the keywords are sent to the server.

[0851] The server receives a request from a user and extracts the keywords included in the request. The server then begins collecting data based on the specified keywords. Specifically, it uses social media APIs and web crawler technology on the Internet to collect related data. For example, social media APIs can be used to obtain post and comment data related to specific keywords. It is also possible to use web crawlers to scrape information from related web pages.

[0852] The collected data is analyzed on the server. During the analysis, specific target name recognition, age distribution, gender distribution, and interest information of the target demographic are extracted from the data. These analyses are performed using statistical methods to extract attribute information. For example, a name recognition score is calculated based on the number of mentions in the collected data, and age distribution, gender distribution, and interest information of the target demographic are also statistically organized.

[0853] Finally, the server formats the analysis results into JSON format and prepares them for delivery to the user. The analysis results are converted into a structured data format (JSON: JavaScript Object Notation) and sent back to the user. The user can check the analysis results on the interface and use them to develop marketing and sales strategies.

[0854] Specific examples

[0855] For example, if a user starts a survey on "TestBrand", the following will happen:

[0856] The user enters "TestBrand" into the system's web interface and clicks the "Start Survey" button.

[0857] The server receives this request and extracts keyword = 'TestBrand'.

[0858] The server calls the gather_data('TestBrand') function to gather data using social media APIs and web crawlers. For example, if there are 850 mentions, the server gets "data = {'mentions': 850}".

[0859] The server passes this data to the analyze_data(data) function, extracting a popularity score of 0.85 and target demographic attributes: target_age = { '20-30': 50, '30-40': 30, '40-50': 20}, target_gender = { 'male': 60, 'female': 40}, and interests = ['tech', 'sports', 'music'].

[0860] The server formats the analysis results into JSON format and returns them to the user, who can then use this information to develop specific marketing strategies.

[0861] This system allows users to quickly and easily obtain detailed information about the brand awareness of "TestBrand" and the attributes of their target demographic, and use this information to develop effective marketing and sales strategies.

[0862] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0863] Step 1:

[0864] The user opens the system interface (web browser or mobile application) and enters a specific keyword. After entering the keyword, the user clicks the "Start Search" button, which sends the request to the server. The input data is the specific keyword entered by the user. The output data is the request sent to the server.

[0865] Step 2:

[0866] The server receives a user request and extracts keywords from the request. In this process, the server executes keyword = request['keyword'] from the request. The input is the request sent by the user, and the output is the extracted keywords.

[0867] Step 3:

[0868] The server uses the extracted keywords to call the gather_data(keyword) function to gather related data from the Internet. This process involves using social media APIs and web crawler technology to obtain data. Specifically, it sends requests to social media APIs to obtain related post and comment data, and uses web crawlers to scrape related web pages. The input is the keywords, and the output is the collected related data.

[0869] Step 4:

[0870] The server passes the collected data to the analyze_data(data) function to perform data analysis. During the analysis, specific target awareness, age distribution, gender distribution, and interest information of the target demographic are extracted using statistical methods. For example, the awareness score is calculated based on "mentions = data.get('mentions')" and "awareness = mentions / 1000". In addition, age distribution, gender distribution, and interest information are statistically organized from the collected data. The input is the collected data, and the output is the analysis results.

[0871] Step 5:

[0872] The server formats the analysis results in JSON format and prepares them for delivery to the user. During this process, the server converts the analysis results into JSON format as follows: json_result = json.dumps(analysis_result) . The formatted JSON results are sent back to the user. The input is the analysis results, and the output is the analysis results in JSON format.

[0873] Step 6:

[0874] Users receive the analysis results provided through the system interface and use that data to develop marketing and sales strategies. The input is the analysis results in JSON format, and the output is the basis for the strategy developed by the user.

[0875] This specific processing flow enables users to quickly and accurately obtain detailed attribute information and name recognition data for their target demographic, and to formulate effective strategies based on this information.

[0876] (Application example 1)

[0877] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0878] While conventional systems were capable of collecting and analyzing brand awareness and target demographic information related to specific keywords, they lacked a way for users to easily check the results in real time. Furthermore, the analysis results were not sufficiently visualized, making it difficult for users to quickly and effectively utilize them in their marketing strategies. Therefore, there is a need for real-time visualization of collected data and for improvements in the method of providing analysis results through that visualization.

[0879] 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.

[0880] In this invention, the server includes a means for inputting specific keywords, a means for collecting data via the Internet, a means for analyzing the collected data and extracting specific target name recognition and target demographic attribute information, a means for providing the analysis results to the user, and a means for visualizing the results on a smart device. This allows the analysis results to be visually displayed on the smart device in real time, allowing the user to quickly and effectively formulate a marketing strategy.

[0881] "Specific keywords" are words or phrases that users enter into the system and select for analysis.

[0882] "Means of collecting data via the internet" refers to the functions and technologies used to obtain information from websites and social media.

[0883] "Means of analyzing collected data and extracting specific target name recognition and target demographic attribute information" refers to functions and technologies that use statistical methods based on collected data to derive name recognition scores and target demographic attributes (age, gender, interests).

[0884] "Means for providing analysis results to users" refers to the functions and technologies for notifying and displaying the analyzed information to users.

[0885] "Means for visualizing results on smart devices" refers to functions and technologies for graphically displaying analysis results on digital devices such as smartphones and tablets.

[0886] A "social media API" is a programmatic interface for retrieving data from social media platforms such as Twitter and Facebook.

[0887] "Display in real time" means that collected and analyzed data is displayed to the user immediately without delay.

[0888] This invention is a system that inputs specific keywords, collects data via the Internet, analyzes the data, extracts name recognition and target demographic attribute information, and finally provides the analysis results to users. Furthermore, this system includes a means for visualizing the results on a smart device.

[0889] Hardware

[0890] Server: High-performance cloud server (e.g., Amazon Web Services, Google Cloud Platform)

[0891] Smart device: Smartphone (Android or iOS)

[0892] software

[0893] Smartphone application: Swift (iOS), Kotlin (Android)

[0894] Data collection: Python, Requests library, social media APIs (e.g. Twitter API, Facebook Graph API)

[0895] Data analysis: Python, Pandas, NumPy, scikit-learn

[0896] Server-side framework: Django or Flask (Python)

[0897] Program Overview

[0898] The server provides an interface for entering specific keywords, and once the user enters the keywords, data collection begins. The server collects data using social media APIs and analyzes the data to extract name recognition scores and target demographic attribute information. The analysis results are visualized in real time on a smart device, allowing users to quickly develop marketing strategies based on the results.

[0899] Processing flow

[0900] 1. User submits request:

[0901] Using a smartphone application, a user inputs a specific keyword and clicks a button to start the analysis, and the request is sent to the server.

[0902] 2. The server receives the request and begins processing it:

[0903] The server calls the user_request_handler function to extract keywords from the request, then uses the process_request function to start collecting data.

[0904] 3. Data Collection:

[0905] The server uses the gather_data function to gather relevant data through social media APIs, for example, by using the Twitter API or the Facebook Graph API.

[0906] 4. Data analysis and information extraction:

[0907] The server analyzes the collected data using the analyze_data function, which uses statistical methods to analyze the popularity score and target demographic attributes (age, gender, interests) to extract the necessary information.

[0908] 5. Providing results:

[0909] The analysis results are formatted in JSON format and visualized in real time on a smart device.

[0910] Specific examples

[0911] For example, to analyze an advertising campaign for "TestBrand," a user enters "TestBrand" into the application. The server collects data related to "TestBrand" through social media APIs and determines that the number of mentions is 850. It calculates the name recognition as "850 / 1000 = 0.85" and analyzes the target demographic's age distribution, gender distribution, and interests to obtain the results. This allows the user to check "TestBrand"'s name recognition and detailed demographic information of the target demographic in real time, enabling them to quickly develop effective marketing strategies.

[0912] Prompt Sentence Examples

[0913] An example of a prompt is:

[0914] "Collect data from social media to analyze awareness and demographic information for the following keyword: 'TestBrand'."

[0915] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0916] Step 1:

[0917] A user opens a smartphone application, enters a specific keyword, and clicks a button to start the analysis. This action sends the keyword to the server as a request. (Input) The keyword entered by the user. (Output) The request to the server.

[0918] Step 2:

[0919] The server receives a user request and calls the user_request_handler function. This function extracts a keyword from the request and passes it to the process_request function to start data collection. (Input) User request (keyword). (Output) Collection start trigger (keyword).

[0920] Step 3:

[0921] The server uses the gather_data(keyword) function to gather data related to a keyword through social media APIs (e.g., Twitter API, Facebook Graph API). It sends a request appropriate to the API to be used and collects the data obtained in the response. (Input) Specific keyword. (Output) Collected social media data.

[0922] Step 4:

[0923] The server passes the data obtained by the gather_data function to the analyze_data(data) function and performs data analysis. This function uses statistical methods to analyze the popularity score and target demographic attributes (age, gender, interests) based on the collected data, and extracts the necessary attribute information. (Input) Collected social media data. (Output) Analyzed popularity score and target demographic attribute information.

[0924] Step 5:

[0925] The server formats the analysis results in JSON format and returns them to the smart device via the user_request_handler function. The smartphone application displays the analysis results in real time based on the received JSON data. (Input) Analyzed popularity score and target demographic attribute information. (Output) Visualized analysis results on the smart device.

[0926] 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.

[0927] The present invention is a system that includes a means for inputting specific keywords, a means for collecting data via the Internet, a means for analyzing the collected data and extracting specific target popularity and target demographic attribute information, and a means for providing the analysis results to users. Furthermore, the system aims to improve the user experience by combining an emotion engine that recognizes the user's emotions, analyzing the user's emotional state, and adjusting the way the information is presented.

[0928] Program processing flow

[0929] 1. User Request Submission

[0930] The user enters a specific keyword into the system's interface (e.g., a web browser or a mobile application), then clicks the "Start Investigation" button, sending a request to the server. This request includes the keyword entered by the user, and the emotion engine also begins to operate.

[0931] 2. Server request reception and sentiment analysis

[0932] The server receives a user request and calls the user_request_handler function. It extracts keywords from the request and obtains the keyword information using keyword = request['keyword']. The server then uses an emotion engine to analyze the user's emotional state for the keywords. The emotional state can be determined using, for example, text analysis or natural language processing techniques.

[0933] 3. Data Collection

[0934] The server calls the process_request function to start collecting data based on the keywords and emotional state. Specifically, it uses the gather_data(keyword) function to gather relevant data from social media and the web. It uses social media APIs and web crawler technology to obtain data related to the specified keywords.

[0935] 4. Data analysis and information extraction

[0936] The server passes the data obtained by the gather_data function to the analyze_data(data) function for data analysis. Based on the collected data, the server uses statistical methods to analyze the specific target popularity, age distribution, gender distribution, and interest information of the target demographic, and extracts the necessary attribute information. For example, the popularity score is calculated based on the number of hits.

[0937] The target demographic information is analyzed as follows: age distribution: "target_age = { "20-30": 50, "30-40": 30, "40-50": 20}", gender distribution: "target_gender = { "male": 60, "female": 40}", and interests: "interests = ["tech", "sports", "music"]".

[0938] 5. Providing results

[0939] The server formats the analysis results in JSON format and prepares them for the user. It then sends the results back to the user through the user_request_handler function. The presentation of the analysis results is adjusted based on the user's emotional state. For example, if the user has a positive emotional state, the analysis results may be presented in detail. Conversely, if the user has a negative emotional state, the analysis results may be presented in a concise summary.

[0940] Specific examples

[0941] For example, if a user starts a survey on "SampleBrand," the server receives a request with "SampleBrand" entered and analyzes the user's emotional state using an emotion engine. Next, data related to "SampleBrand" is obtained through a social media API, and the number of mentions is assumed to be 1,500. In other words, if "data = {'mentions': 1,500}" is entered, the name recognition is calculated as "1,500 / 1,000 = 1.5." The target demographic's age distribution, gender distribution, and interest information are also analyzed and returned as results.

[0942] This system allows users to quickly and easily obtain detailed information about the brand's popularity and target demographics, enabling them to formulate appropriate marketing and sales strategies. It also adjusts the way information is presented to users based on their emotional state, providing a better user experience.

[0943] The processing flow will be explained below.

[0944] Step 1:

[0945] The user enters a proper noun. The user enters keywords for a specific company or brand into the system's interface. Then, the user clicks the "Start Search" button, which sends a request to the server. This request includes the keywords entered by the user.

[0946] Step 2:

[0947] The server receives the request. The server receives the user request and calls the user_request_handler function. It extracts keywords from the request and gets the keyword information with keyword = request['keyword'].

[0948] Step 3:

[0949] The server launches an emotion engine to analyze the user's emotion. The server uses the emotion engine to analyze the user's emotional state in response to the input keywords. The emotion engine determines the emotional state using text analysis and natural language processing techniques.

[0950] Step 4:

[0951] The server starts data collection. The server calls the process_request function to start data collection based on keywords and emotional states. Specifically, the server uses the gather_data(keyword) function to gather relevant data from social media and the web.

[0952] Step 5:

[0953] The server collects data over the Internet. The gather_data(keyword) function retrieves data related to a specified keyword using social media APIs or web crawlers. For example, it sends an API request and receives the relevant data in response.

[0954] Step 6:

[0955] The server analyzes the data. The server passes the data obtained by the gather_data function to the analyze_data(data) function and performs data analysis. Based on the collected data, it uses statistical methods to analyze the recognition of specific targets, the age distribution, gender distribution, and interest information of the target demographic.

[0956] Step 7:

[0957] The server calculates the popularity. If the retrieved data includes "mentions = 850", the popularity is calculated as "850 / 1000 = 0.85".

[0958] Step 8:

[0959] The server extracts the target demographic's attribute information. The target demographic's age distribution, gender distribution, and interest information are extracted from the data. For example, the age distribution would be "target_age = { "20-30": 50, "30-40": 30, "40-50": 20}", the gender distribution would be "target_gender = { "male": 60, "female": 40}", and the interests would be "interests = ["tech", "sports", "music"]".

[0960] Step 9:

[0961] The server formats the analysis results in JSON format and prepares them for delivery to the user. Specifically, it converts the results to JSON format using json.dumps(analysis_result).

[0962] Step 10:

[0963] The server adjusts the results based on the user's emotions. Based on the analysis results of the emotion engine, the depth and format of the information presented can be adjusted. For example, detailed data can be displayed for a positive emotional state, and concise information can be displayed for a negative emotional state.

[0964] Step 11:

[0965] The server returns the analysis results to the user via the user_request_handler function. The user can receive the results and use them to formulate marketing and sales strategies.

[0966] Example 2

[0967] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[0968] When users acquire brand awareness or target demographic attribute information based on specific keywords, conventional systems have had issues with extracting information and analyzing results that cannot flexibly adapt to the user's emotional state, resulting in a lack of improvement in the user experience. Additionally, the scope of information collected is limited, making comprehensive analysis of the data difficult.

[0969] 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.

[0970] In this invention, the server includes a means for a user to input a specific keyword, a means for collecting data via the Internet, a means for analyzing the collected data and extracting specific popularity and target demographic attribute information, a means for performing analysis based on the collected data using an emotion engine that recognizes the user's emotional state, and a means for adjusting and providing the analysis results based on the user's emotional state. This enables flexible information presentation that takes the user's emotional state into consideration, thereby improving the user experience.

[0971] A "user" is an individual or company that uses the system and enters keywords and obtains information.

[0972] "Keywords" are specific words or phrases that users enter into the system to specify the information they wish to search.

[0973] The "Internet" is an information and communications network made up of computer networks around the world, and is a means of collecting data and transmitting information.

[0974] "Data" refers to the information that is collected and analyzed, including in the form of text, images, video, etc. obtained from social media and websites.

[0975] "Famousness" is an indicator that shows how well-known an object (e.g., product, brand, service, etc.) related to a specific keyword is in society.

[0976] "Target demographic" refers to the group of people who are likely to consume or use the information being surveyed, and includes their demographic information (age, gender, interests, etc.).

[0977] An "emotion engine" is an algorithm or system that analyzes keywords and other text information entered by a user to recognize the user's emotional state (positive, negative, etc.).

[0978] "Social Media API" means an application programming interface provided by a social media platform that allows users to retrieve data related to specific keywords.

[0979] "Web crawler technology" refers to programs and algorithms that automatically crawl web pages on the Internet and analyze their content.

[0980] "Analysis results" refers to information analyzed using statistical methods and algorithms based on collected data, and includes brand recognition and attribute information of the target demographic.

[0981] "JSON format" is an abbreviation for JavaScript Object Notation, and is a lightweight data format widely used for data exchange.

[0982] The "system" is a design having the overall structure and functions of the present invention, and is a platform consisting of multiple means (modules).

[0983] This invention is a system that allows users to input specific keywords, collect data via the Internet, analyze the collected data, and provide information on brand recognition and target demographic attributes.The system also aims to improve the user experience by using an emotion engine that recognizes the user's emotional state and adjusting the way the analysis results are presented based on the user's emotional state.

[0984] Specifically, a user first enters a specific keyword into the system interface via a web browser or mobile application and clicks the "Start Investigation" button, which sends a request to the server and simultaneously starts the emotion engine.

[0985] The server receives the request sent by the user and internally calls the user_request_handler function to extract keywords. The server then uses an emotion engine to analyze the user's emotional state. This emotion analysis uses text analysis and natural language processing techniques, such as the BERT model.

[0986] Next, the server calls the process_request function to start collecting data based on the keywords and sentiment state. Specifically, the gather_data(keyword) function uses social media APIs and web crawler technology to gather relevant data. For example, it uses the Twitter API and BeautifulSoup to retrieve related tweets and web page information.

[0987] The collected data is passed to the analyze_data(data) function and analyzed by the server. During the analysis, a popularity score is calculated based on the number of mentions and hashtag frequency of the collected data. In addition, the target demographic's age distribution, gender distribution, and interest information are analyzed using statistical methods to extract the necessary attribute information.

[0988] Finally, the server formats the analysis results into JSON format and returns them to the user via the user_request_handler function. The way the analysis results are presented is adjusted based on the user's emotional state: if the emotional state is positive, detailed analysis results are presented, and if the emotional state is negative, concise summary results are presented.

[0989] Specific examples

[0990] For example, if a user starts a search for "SampleBrand," the server receives a request containing the keyword "SampleBrand" and uses an emotion engine to analyze the user's emotional state. Next, data related to "SampleBrand" is retrieved through a social media API, and the number of mentions is assumed to be 1,500. Based on the number of mentions in the collected data, the awareness score is calculated as "1,500 / 1,000 = 1.5." The target demographic's age distribution and interest information are also analyzed and provided to the user.

[0991] This system allows users to quickly and easily obtain detailed attribute information about the "SampleBrand" brand and its target demographic, which can be used as a reference when formulating marketing and sales strategies. Furthermore, by providing information according to the user's emotional state, a better user experience is provided.

[0992] Specific examples of prompts to input to generative AI models

[0993] What is the overall flow when a user starts an investigation on "SampleBrand"? Please explain in detail how the user enters a keyword, a request is sent to the server, data is collected, analyzed, and the results are delivered based on the sentiment engine's analysis.

[0994] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0995] Step 1:

[0996] A user enters a specific keyword into the system's interface through a web browser or mobile application and clicks the "Start Investigation" button. This request includes the keyword entered by the user. The emotion engine also starts working at this point. The keyword is provided as input, and a request is sent to the server as output.

[0997] Step 2:

[0998] The server receives the request and calls the user_request_handler function internally to extract keywords. Specifically, keywords are obtained from the request in the format request['keyword']. Next, the server uses an emotion engine to analyze the user's emotional state for the obtained keywords. Natural language processing techniques such as the BERT model are used for emotion analysis. The keywords in the request are provided as input, and the emotional state is obtained as output.

[0999] Step 3:

[1000] The server calls the process_request function to start collecting data based on keywords and emotional states. The specific data collection is performed using the gather_data(keyword) function. This function uses social media APIs (e.g., Twitter API) or web crawler technology (e.g., BeautifulSoup) to gather data related to keywords. Keywords and emotional states are provided as input, and related data is collected as output.

[1001] Step 4:

[1002] The server passes the collected data to the analyze_data(data) function for analysis. Specifically, it statistically analyzes the number of mentions and hashtag frequency in the collected data to extract a popularity score and target demographic attribute information (age distribution, gender distribution, interests). The collected data is provided as input, and the analysis results are obtained as output. For example, the popularity score is calculated using the formula mentions_count / 1000.

[1003] Step 5:

[1004] The server formats the analysis results into JSON format and returns them to the user via the user_request_handler function. At this stage, the way the analysis results are presented is adjusted based on the user's emotional state. For example, a detailed analysis result is presented for a positive emotional state, while a concise summary is provided for a negative emotional state. The analysis results and the emotional state are provided as input, and the adjusted analysis results are obtained as output.

[1005] (Application example 2)

[1006] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1007] Conventional advertising systems provide a means to acquire target name recognition and attribute information, but do not adjust the display method to take into account the user's emotional state. As a result, the user experience is not sufficiently improved, and optimal advertising proposals cannot be presented.

[1008] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a means for inputting a specific keyword, a means for collecting data via the Internet, a means for analyzing the collected data and extracting specific target popularity and attribute information of the target demographic, a means for providing the analysis results to the user, and a means for recognizing the user's emotional state and adjusting the method of presenting the information to be provided. This enables flexible information presentation according to the user's emotional state.

[1009] 1. "Specific Keywords" refers to words or phrases that users enter to describe a particular subject or concept that interests them.

[1010] 2. "Means of collecting data via the Internet" refers to methods and technologies for automatically obtaining relevant data from various sources on the Internet.

[1011] 3. "Means of analyzing collected data and extracting specific target awareness and target demographic attribute information" refers to technology that processes collected data and derives the awareness of a target and the attributes of that target demographic (e.g., age, gender, interests).

[1012] 4. "Means for providing analysis results to users" refers to the technology and methods for displaying analyzed information in a format that is easy for users to understand.

[1013] 5. "Means for recognizing the user's emotional state and adjusting the way information is presented" refers to technology that analyzes and understands the user's emotions and appropriately changes the way information is displayed based on the results.

[1014] 6. "Social Media API" refers to a means of obtaining data related to specific keywords using an application programming interface (API) provided by a social media platform.

[1015] The present invention is a system that includes a means for inputting specific keywords, a means for collecting data via the Internet, a means for analyzing the collected data and extracting specific target popularity and target demographic attribute information, and a means for providing the analysis results to users.Furthermore, the system aims to improve the user experience by combining an emotion engine that recognizes the user's emotions, analyzing the user's emotional state, and adjusting the way the information is presented.

[1016] Overall system configuration and operation flow

[1017] Program processing overview

[1018] The server receives requests sent by users and collects relevant data based on specific keywords included in the request. The collected data is analyzed to extract specific target popularity and target demographic attribute information (age, gender, interests). Furthermore, the server analyzes the user's emotional state and adjusts the presentation of the information provided according to the user's emotional state.

[1019] Specific implementation description

[1020] 1. A user inputs a specific keyword into a device (smartphone or PC) and sends a request to the server. This request includes the specific keyword that the user is interested in and data to obtain the user's emotional state.

[1021] 2. The server is built using Python or a similar programming language. Upon receiving a user request, the server analyzes the user's emotional state using TextBlob or a similar natural language processing tool.

[1022] 3. The server uses social media APIs and web crawler technology to collect data related to the keywords over the internet. This step utilizes public social media APIs such as the Twitter API and Facebook Graph API.

[1023] 4. The collected data is analyzed on the server to extract specific target awareness and demographic information. Statistical methods and machine learning models are used for the analysis.

[1024] 5. The server formats the analysis results in JSON format and adjusts the presentation of information based on the user's emotional state: detailed information is provided if the user has a positive emotion, and concise information is provided if the user has a negative emotion.

[1025] 6. Finally, the server sends the analysis results back to the user, who can view the information. This information is used by advertisers to develop optimal advertising strategies for their target audience.

[1026] Examples of concrete examples and prompts

[1027] For example, when a marketer wants to research the popularity of a particular brand, the system will collect relevant data from social media APIs based on the keyword "specific brand." The system will then analyze the popularity and target demographic information, and provide detailed information in a way that reflects the user's emotional state. This will make it easier for advertisers to develop optimal advertising strategies.

[1028] Example prompt sentence:

[1029] "The system collects data related to the keywords entered by the user, analyzes the popularity of the specified keywords and the demographic information of the target demographic, and provides it. It also adjusts the way information is presented depending on the user's emotional state."

[1030] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1031] Step 1:

[1032] The user enters a specific keyword into a device (smartphone or PC) and sends a request to the server. This request includes the specific keyword and a text message to obtain the user's emotional state. The input is the user sending the keyword "specific brand" and a message indicating their emotion. The output is received by the server.

[1033] Step 2:

[1034] The server processes the received request using the user_request_handler function to extract keywords and user messages. Specifically, it uses a Python library to extract keywords (e.g., "specific brand") and user messages (e.g., "I want to know more about this brand") from the request. The input is the received request, which is the output of step 1. The output is the extracted keywords and user messages.

[1035] Step 3:

[1036] The server uses natural language processing techniques such as TextBlob to analyze the emotional state of the user message. The emotional state is classified as positive, negative, or neutral. For example, a positive emotion is detected from the message "I want to know more about this brand." The input is the user message extracted in step 2. The output is the analyzed emotional state.

[1037] Step 4:

[1038] The server uses the gather_data function to collect keyword-related data from the Internet (e.g., social media APIs). Specifically, it uses the Twitter API and Facebook Graph API to obtain posts related to a "specific brand." The input is the keywords extracted in step 2. The output is the collected data (e.g., posts from social media).

[1039] Step 5:

[1040] The collected data is analyzed using the analyze_data function to extract specific target name recognition and target demographic attribute information (age, gender, interests). Specifically, name recognition is calculated based on the number of collected posts, and age distribution, gender distribution, and interest information are analyzed using statistical methods. The input is the data collected in step 4. The output is the analysis results (e.g., name recognition score, age distribution, gender distribution, interest information).

[1041] Step 6:

[1042] The server formats the analysis results in JSON format and adjusts the way information is presented based on the user's emotional state. For example, it provides detailed information for a positive emotional state and concise information for a negative emotional state. The input is the emotional state from step 3 and the analysis results from step 5. The output is formatted data (e.g., the analysis results in JSON format).

[1043] Step 7:

[1044] Finally, the server returns the formatted analysis results to the user, who can view the results on their device. The input is the data formatted in step 6. The output is the analysis results displayed on the user's device, providing the user with the information they need to develop their advertising strategy.

[1045] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1046] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1047] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1048] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1049] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1050] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1051] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1052] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1053] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1054] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1055] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1056] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1057] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1058] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1059] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1060] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1061] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1062] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[1063] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[1064] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[1065] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference.

[1066] The following is further disclosed regarding the above embodiment.

[1067] (Claim 1)

[1068] a means for inputting specific keywords;

[1069] a means for collecting data via the internet;

[1070] A means of analyzing the collected data and extracting specific target name recognition and target demographic attribute information;

[1071] A means for providing the analysis results to users;

[1072] A system including:

[1073] (Claim 2)

[1074] The system according to claim 1, wherein the analysis results provide target name recognition, age distribution of the target demographic, gender distribution, and interest information.

[1075] (Claim 3)

[1076] 10. The system of claim 1, wherein the system utilizes social media APIs as a means of data collection.

[1077] "Example 1"

[1078] (Claim 1)

[1079] a means for inputting specific keywords;

[1080] means for collecting data via the internet, including social media APIs and web crawlers;

[1081] Statistical analysis means for analyzing the collected data and extracting specific target name recognition, age distribution, gender distribution, and interest information of the target demographic;

[1082] A means to format the analysis results in JSON format and provide them to users,

[1083] A system including:

[1084] (Claim 2)

[1085] The system according to claim 1, wherein the analysis results provide target name recognition, age distribution of the target demographic, gender distribution, and interest information.

[1086] (Claim 3)

[1087] The system of claim 1, wherein the data collection means utilizes social media APIs and web crawler technology.

[1088] "Application Example 1"

[1089] (Claim 1)

[1090] a means for inputting specific keywords;

[1091] a means for collecting data via the internet;

[1092] A means of analyzing the collected data and extracting specific target name recognition and target demographic attribute information;

[1093] A means for providing the analysis results to users;

[1094] A means to visualize the results on a smart device,

[1095] A system including:

[1096] (Claim 2)

[1097] The system of claim 1 provides target name recognition, age distribution of the target demographic, gender distribution, and interest information as analysis results, and displays them in real time on a smart device.

[1098] (Claim 3)

[1099] 10. The system of claim 1, wherein the system utilizes social media APIs as a means of collecting data and displays the results on a smart device.

[1100] "Example 2: Combining Emotion Engines"

[1101] (Claim 1)

[1102] a means for a user to input a specific keyword;

[1103] a means for collecting data via the internet;

[1104] A means of analyzing the collected data and extracting specific name recognition and target demographic attribute information;

[1105] means for performing analysis based on the collected data using an emotion engine that recognizes the user's emotional state;

[1106] a means for adjusting and providing the analysis results based on the emotional state of the user;

[1107] A system including:

[1108] (Claim 2)

[1109] The system of claim 1, wherein the analysis results provide specific name recognition, age distribution of the target demographic, gender distribution, and interest information.

[1110] (Claim 3)

[1111] 10. The system of claim 1, wherein the system utilizes social media APIs and web crawler technology as data collection means.

[1112] "Application example 2 when combining emotion engines"

[1113] (Claim 1)

[1114] a means for inputting specific keywords;

[1115] a means for collecting data via the internet;

[1116] A means of analyzing the collected data and extracting specific target name recognition and target demographic attribute information;

[1117] A means for providing the analysis results to users;

[1118] means for recognizing the emotional state of the user and adjusting the presentation of the information provided;

[1119] A system including:

[1120] (Claim 2)

[1121] The system according to claim 1, wherein the analysis results provide target name recognition, age distribution of the target demographic, gender distribution, and interest information.

[1122] (Claim 3)

[1123] 10. The system of claim 1, wherein the system utilizes social media APIs as a means of data collection. [Explanation of symbols]

[1124] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. a means for inputting specific keywords; a means for collecting data via the internet; A means of analyzing the collected data and extracting specific target name recognition and target demographic attribute information; A means for providing the analysis results to users; A system including:

2. The system according to claim 1, wherein the analysis results provide information on target popularity, age distribution, gender distribution, and interests of the target demographic.

3. The system of claim 1 , wherein the data collection means utilizes social media APIs.

Images