System

Abstract

A system is provided.SOLUTION: A system comprising: means for receiving real-time local congress discussions; means for converting the received discussions into text data using a generation AI to generate summaries; means for delivering the generated summaries to citizen terminals via push notifications; means for providing an interface for citizens to "like" or post comments on the summaries; means for collecting and analyzing feedback from citizens; means for displaying local advertisements with the summaries; and means for generating reports to advertisers using the collected advertisement information.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] In modern society, citizens often have difficulty following the content of discussions in their local assemblies. This reduces citizens' interest in and willingness to participate in local government, making it difficult for the democratic process to function properly. Furthermore, there is no system in place to publicly disclose the content of local assembly discussions in real time, which creates the problem of citizens being unable to respond or express their opinions in real time. Furthermore, local governments face many financial constraints and need new sources of revenue. [Means for solving the problem]

[0005] In order to solve the above-mentioned problems, the present invention provides the following means: a system including means for receiving local assembly discussions in real time, means for converting the received discussions into text data using a generation AI and generating summaries, means for delivering the generated summaries to citizens' devices via push notifications, means for providing an interface for citizens to post "likes" and comments on the summaries, means for collecting and analyzing feedback from citizens, means for displaying local advertisements together with the summaries, and means for generating reports for advertisers using the collected advertising data.

[0006] Furthermore, by including a means to convert streaming data from local assemblies into text using a speech recognition API, and a means to record the results of feedback data analysis in a database and reflect them in real time on an analysis dashboard, the system will promote communication between local governments and citizens, increasing transparency in local administration and citizen participation.In addition, the effective distribution of local advertisements will provide a source of revenue to support local government finances.

[0007] A "local assembly" is a legislative body established in a local government to discuss and make decisions on various matters related to that area.

[0008] "Generative AI" is a system that uses artificial intelligence technology to generate and summarize appropriate information from large amounts of data.

[0009] "Text data" refers to data that expresses audio or video data as text information.

[0010] "Push notification" is a technology that transmits information from a server to a user terminal in real time.

[0011] A "citizen's device" is an electronic device owned by an individual citizen for receiving and viewing information, such as a smartphone, tablet, or computer.

[0012] "Like" is a button or feature that users use to indicate a positive rating for content.

[0013] A "comment" is text information that a user freely writes and posts to express their opinions and thoughts about content.

[0014] "Feedback" refers to information such as opinions, ratings, and comments collected from users.

[0015] "Interface" refers to the screen and operating means by which a user interacts with a system.

[0016] "Advertisement" means visual or textual content displayed to promote a product or service.

[0017] A "database" is a collection of information that organizes and manages collected data so that it can be searched and used efficiently.

[0018] A "report" is a report that summarizes collected and analyzed data and presents it visually or in writing.

[0019] An "analysis dashboard" is a tool that visually displays collected data in real time and can be used for management and decision-making. [Brief explanation of the drawings]

[0020] [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

[0021] 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.

[0022] First, the terms used in the following description will be explained.

[0023] 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).

[0024] 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.

[0025] 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.

[0026] 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.

[0027] 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."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 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.

[0031] 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).

[0032] 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.

[0033] 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.

[0034] 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.

[0035] 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.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 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.

[0038] 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.

[0039] 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.

[0040] 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."

[0041] This paper describes a system that provides local assembly discussions to citizens in real time, collects and analyzes their opinions on the discussions, and effectively distributes local advertisements. This system is realized through the interaction of a server, terminals, and users.

[0042] 1. Collection and text conversion of meeting minutes

[0043] The server receives real-time data from local assembly discussions. For example, it connects to the assembly's streaming URL and retrieves audio / video data using the RTMP or HLS protocol. The retrieved data is then converted into text data using a speech recognition API. For example, a cloud-based speech recognition service (e.g., Google Cloud Speech-to-Text) is used as the speech recognition API.

[0044] 2. Summary Generation

[0045] The server uses generative AI to analyze the acquired text data, extract the main points of discussion, and generate a summary. For example, the generative AI uses an advanced natural language processing model (e.g., OpenAI GPT-4) to extract important sentences and keywords and summarize them in short sentences.

[0046] 3. Summary Delivery

[0047] The server delivers the generated summary to the citizen's device via push notification. For example, it uses a notification service (e.g., Firebase Cloud Messaging) to send real-time notifications to the device of a pre-registered user.

[0048] 4. Providing interaction functions

[0049] The device displays the received summary on the screen and provides an interface that allows users to "like" or post comments. As a concrete example, a "like" button and a comment input field are placed on the UI of a mobile application along with the summary text.

[0050] 5. Feedback collection and analysis

[0051] Users can click "Like" on a summary or enter and submit a comment. The server receives the feedback sent by users and stores it in a database. The feedback data is analyzed and reflected in real time on an analysis dashboard. Based on the analysis results, citizens' opinions and reactions are visualized.

[0052] 6. Display of advertisements

[0053] The server also sends advertisements for local stores and businesses when delivering the summary. For example, it can set up a system to display banner advertisements from local sponsors in designated ad slots. The advertisements are delivered along with the summary and displayed on the user's device.

[0054] 7. Advertising effectiveness measurement and report generation

[0055] The server records the number of times the ad was displayed and the number of clicks, and periodically generates reports for the advertiser. For example, a weekly report compiling data such as the number of impressions, click-through rate, and regional response may be sent to the advertiser via email.

[0056] 8. User convenience

[0057] The terminal provides users with a display interface that allows for smooth operation. Users can express their interest in discussions in real time, increasing their motivation to participate in local government.

[0058] This system allows the contents of local assembly discussions to be communicated to citizens quickly and concisely, reflecting their feedback, while providing financial support through local advertising. This is expected to promote communication between local governments and citizens, and improve the transparency and citizen participation in local administration.

[0059] The processing flow will be explained below.

[0060] Step 1:

[0061] The server connects to the local council's streaming URL and retrieves audio / video data in real time, using the RTMP or HLS protocol for stable streaming.

[0062] Step 2:

[0063] The server sends the acquired audio data to a speech recognition API, which converts the audio data into text data. This speech recognition API uses cloud-based services such as Google Cloud Speech-to-Text and Amazon Transcribe.

[0064] Step 3:

[0065] The server inputs the generated text data into a generative AI, extracts key points of discussion, and generates a summary. The generative AI model uses OpenAI GPT-4 and other technologies, and uses natural language processing to extract important sentences and keywords.

[0066] Step 4:

[0067] The server sends the generated summary to registered users' devices via push notification, using a push notification service such as Firebase Cloud Messaging to deliver notifications to users' mobile devices in real time.

[0068] Step 5:

[0069] The device displays the received summary on the screen. Along with the summary text, it also provides an interface where users can post "likes" and comments. This interface includes a "like" button and a comment input field below the summary.

[0070] Step 6:

[0071] Users can publish their feedback by clicking the "Like" button on the summary or by entering a comment and clicking the submit button.

[0072] Step 7:

[0073] The server receives feedback from users (likes and comments) and records it in a database. This allows users' reactions and opinions to be collected and stored as data.

[0074] Step 8:

[0075] The server analyzes the collected feedback data and displays it in real time on an analytical dashboard, allowing users to instantly grasp the situation of local governments and councils.

[0076] Step 9:

[0077] The server sends advertisements along with the summary delivery. Advertisements from local stores and businesses are registered in the system and set to be displayed in designated ad slots.

[0078] Step 10:

[0079] The terminal displays local advertisements along with summary text, which the user can view and follow links to if desired.

[0080] Step 11:

[0081] The server records the number of times the advertisement is displayed and the number of clicks in a database and periodically generates a report for the advertiser, which summarizes data such as the number of times the advertisement is displayed, the click rate, and the user distribution, and provides the report to the advertiser.

[0082] Through these steps, a system will be created that provides citizens with real-time information about local assembly discussions, collects and analyzes citizen feedback, and delivers effective advertising.

[0083] Example 1

[0084] 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."

[0085] Traditional media and websites lack the real-time capabilities to quickly and concisely communicate the contents of local assembly discussions to citizens. It is also difficult to effectively collect and analyze citizen feedback, and to appropriately deliver advertisements for local businesses. A system that can solve these issues is needed.

[0086] 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.

[0087] In this invention, the server includes a means for receiving local assembly discussions in real time, a means for converting the received discussions into text data using a generation AI to generate summaries, and a means for delivering the generated summaries to citizens' devices via push notifications. This allows citizens to quickly and concisely understand the content of local assembly discussions and provide feedback on the content in real time. Furthermore, the effective delivery of local advertisements contributes to revitalizing the local economy.

[0088] "Local assembly discussions" refers to various debates and deliberations held in local government assemblies.

[0089] "Real-time receiving means" refers to devices or software that have the ability to simultaneously obtain data about ongoing discussions or debates.

[0090] "Generative AI" refers to artificial intelligence that uses machine learning models and algorithms to generate specific information from input data.

[0091] "Means for converting into text data" refers to the technology or method for converting data acquired in the form of audio, video, etc. into text information.

[0092] A "summary generation method" refers to a process or system that extracts important information from long text data and presents it in a compact form.

[0093] "Citizen's device" refers to an electronic device such as a personal computer, smartphone or tablet that a citizen uses to receive and display local council information.

[0094] "Means of delivering push notifications" refers to technology that notifies users of information in real time or at a specified time.

[0095] "Interface" refers to the screen and input / output means that allow a user to interact with and operate a system.

[0096] "Means for collecting and analyzing feedback" refers to the techniques and processes used to receive user opinions and responses and analyze that data.

[0097] "Local advertising" refers to advertising that promotes products, services, events, etc. that are relevant to a particular geographic area.

[0098] "Advertiser" refers to a company or individual that places an advertisement.

[0099] "Means for generating reports" means the process or system that generates reports or analyses based on the collected data and that are periodically sent to advertisers.

[0100] This invention relates to a system that provides local assembly discussions to citizens in real time, collects and analyzes their opinions on the discussions, and effectively distributes local advertisements. This system is realized through the interaction of a server, terminals, and users.

[0101] First, the server receives the local assembly discussions in real time. This involves connecting to the local assembly's streaming URL and obtaining the audio / video data using the RTMP or HLS protocol. The obtained data is then converted into text data using a speech recognition API (e.g., Google Cloud Speech-to-Text).

[0102] The server then analyzes the acquired text data using generative AI, extracts key discussion points, and generates a summary. Specifically, it uses a generative AI model (e.g., OpenAI GPT-4). An example of a prompt for generating a summary is "Please summarize the following minutes:"

[0103] The generated summary is delivered to the citizen's device via a push notification by the server. These notifications are delivered using Firebase Cloud Messaging. An example of the push notification content is "A new discussion summary is available."

[0104] The device displays the received summary to the user and provides an interface that allows the user to "like" or comment, including by placing a "like" button and a comment input field along with the summary text in the user interface of the mobile application.

[0105] Users can click "Like" on the summary or enter and submit a comment. The server receives the feedback submitted by users and stores it in a database (e.g., MySQL). The collected feedback data is analyzed in real time and displayed on an analysis dashboard. For the analysis, an analysis tool such as Tableau is used.

[0106] In addition, the server also sends advertisements for local businesses and stores along with the summary. The advertisements are set to be displayed as banner advertisements for local sponsors in designated ad slots. This allows the advertisements to be displayed on the user's device along with the summary.

[0107] The server also handles ad performance measurement and reporting. It records the number of ad impressions and clicks, and periodically generates weekly reports for advertisers. The reports include data such as impressions, click-through rates, and geographic response, and are sent to advertisers via email.

[0108] Finally, the device provides users with a display interface that allows for smooth operation, allowing them to reflect their interest in local assembly discussions in real time, increasing their motivation to participate in local government.

[0109] By combining these functions, it is possible to quickly and concisely convey the contents of local assembly discussions to citizens, incorporate their feedback, and provide financial support through local advertising. This is expected to promote communication between local governments and citizens, and improve the transparency and citizen participation of local government administration.

[0110] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0111] Step 1:

[0112] The server connects to the local council's live streaming URL and receives audio / video data using the RTMP or HLS protocol. Specifically, it retrieves data from the streaming URL (e.g., http: / / example-streaming-url.com) and calls a speech recognition API (e.g., Google Cloud Speech-to-Text) to convert the audio data into text data.

[0113] Input: Audio / video data via streaming URL

[0114] Output: Text data

[0115] Step 2:

[0116] The server inputs the converted text data into a generative AI model, extracts key discussion points, and generates a summary. Specifically, the server inputs the following prompt into the generative AI model (e.g., OpenAI GPT-4): "Please summarize the following minutes: 'Text data'." The server then saves the generated summary.

[0117] Input: Text data

[0118] Output: Summary data

[0119] Step 3:

[0120] The server uses Firebase Cloud Messaging to deliver the generated summary to citizens' devices via push notification. Specifically, it uses the Firebase Cloud Messaging API to send the summary along with the message "A new discussion summary is available."

[0121] Input: Summary data and user information

[0122] Output: Push notification sent

[0123] Step 4:

[0124] The device displays the received summary to the user and provides an interface that allows the user to "like" or post a comment. Specifically, a "like" button and a comment input field are placed on the UI of the mobile application along with the summary text, allowing the user to use these interfaces.

[0125] Input: Summary data

[0126] Output: User interface

[0127] Step 5:

[0128] Users can click "Like" on the displayed summary or enter and submit a comment. The server receives the feedback and stores it in a database. Specifically, it collects user feedback data (likes and comments) and stores them in a MySQL database.

[0129] Input: User feedback data

[0130] Output: Feedback data stored in a database

[0131] Step 6:

[0132] The server analyzes the collected feedback data in real time. Specifically, it uses an analytical tool (e.g., Tableau) to analyze the feedback data and display it on a dashboard. This analysis visualizes citizens' opinions and reactions.

[0133] Input: Feedback data

[0134] Output: Dashboard display of analysis results

[0135] Step 7:

[0136] The server selects advertising data and distributes it together with the summary in order to transmit advertisements of local sponsors together with the summary. Specifically, the server sets banner advertisements of local sponsors in designated advertising spaces and displays them on the user's terminal together with the summary.

[0137] Input: Summary data and advertising data

[0138] Output: Summary and advertisement displayed on user's device

[0139] Step 8:

[0140] The server records the number of times an ad is displayed and clicked, and compiles this data into a report that is sent to the advertiser periodically. Specifically, a weekly report is generated, compiling data such as the number of impressions, click-through rates, and regional responses, and sending it to the advertiser via email.

[0141] Input: Ad impressions and click data

[0142] Output: Report sent to advertiser

[0143] (Application example 1)

[0144] 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."

[0145] There is a lack of means to quickly and effectively communicate the contents of discussions in local assemblies to citizens, as well as to instantly collect and reflect citizen opinions. Furthermore, there is a need for a system that will facilitate smooth communication and economic activity between local governments, citizens, and local businesses by effectively distributing local advertising in conjunction with the information provided to citizens.

[0146] 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.

[0147] In this invention, the server includes: means for receiving local assembly discussions in real time; means for converting the received discussions into text data using a generative AI and generating summaries; means for distributing the generated summaries to citizens' devices via push notifications; means for providing an interface for citizens to post "likes" and comments on the summaries; means for collecting and analyzing feedback from citizens; means for displaying local advertisements along with the summaries; means for generating reports for advertisers using the collected advertisement data; means for live displaying streaming data on citizens' devices; means for collecting comments in real time based on the live-displayed discussions; and means for analyzing the collected comment data and summarizing using a generative AI model. This makes it possible to communicate the content of local assembly discussions to citizens in real time, immediately reflect citizen feedback, and effectively distribute local advertisements.

[0148] A "local assembly" is the legislative body of a local government, and is the body that deliberates and decides on important policies and budgets of local public entities.

[0149] "Real time" is a term that describes things happening nearly simultaneously or with very little delay.

[0150] "Generative AI" refers to artificial intelligence technology that automatically learns and generates text, audio, images, etc.

[0151] "Text data" is a data format consisting of characters and words, and is data that contains character strings that can be processed by a computer.

[0152] A "summary" is a short summary of the original content, intended to convey the main points concisely.

[0153] "Push notification" is a technology that sends information from a server to a user's device in real time, allowing the user to receive the information without taking any specific action.

[0154] "Interface" refers to the means and screen layout by which a user interacts with a system or application.

[0155] "Feedback" refers to reactions and opinions collected from users, and is information that is useful for improving and evaluating a system.

[0156] "Local advertising" refers to promotional activities of stores and businesses related to a specific area, and is advertising targeted at people living in that area.

[0157] "Streaming data" refers to audio and video data that is distributed in real time over the Internet.

[0158] "Live display" refers to displaying data or video to viewers in real time.

[0159] "Comment data" refers to opinions and impressions entered by users in text format.

[0160] A "generative AI model" is an algorithm that automatically generates text, audio, images, etc. using technologies such as machine learning and deep learning.

[0161] This invention includes a system that provides citizens with real-time information about local assembly discussions, collects and analyzes their opinions on the content, and effectively distributes local advertisements. This system is realized through the interaction of a server, terminals, and users.

[0162] First, the server receives the local assembly discussions in real time by connecting to the local assembly's streaming URL using the RTMP or HLS protocol. The received audio / video data is converted into text data using a speech recognition API (e.g., Google Cloud Speech-to-Text).

[0163] The server then uses a generative AI to analyze the converted text data, extract key discussion points, and generate a summary. The generative AI uses an advanced natural language processing model such as OpenAI GPT-4. For example, it uses the following prompt:

[0164] "Summarize the following text:\nThe council discussed a new public works project to build a new park in District A. This proposal has many merits..."

[0165] The generated summary is delivered to the citizen's device via a push notification from the server using a notification service such as Firebase Cloud Messaging. Citizens receive the summary on their device and are provided with an interface where they can "like" or post comments.

[0166] Next, citizen feedback is sent to a server and stored in a database. This feedback data is then reflected in a real-time analysis dashboard, visualizing citizen opinions and reactions.

[0167] Furthermore, the server also transmits local advertisements when delivering the summary. For example, it is set to display banner advertisements of local sponsors in the advertisement space. The advertisements are delivered together with the summary and displayed on the user's terminal.

[0168] Finally, the server records the number of impressions and clicks on the ads and periodically generates reports for the advertiser, summarizing data such as impressions, click-through rates, and geographic response, which are emailed to the advertiser.

[0169] This system allows the contents of local council discussions to be communicated to citizens quickly and concisely, allows for the collection and analysis of feedback from citizens, and promotes communication between local governments, citizens, and local businesses by effectively distributing local advertisements.

[0170] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0171] Step 1:

[0172] The server receives the local assembly discussions in real time by connecting to the local assembly's streaming URL using the RTMP or HLS protocol. The input data is an audio / video stream, and the output data is audio data for speech recognition.

[0173] Step 2:

[0174] The server converts the received audio data into text data using a speech recognition API (e.g., Google Cloud Speech-to-Text). The input data is audio data, and the output data is text data. In this step, the audio signal is analyzed and converted into text as a string.

[0175] Step 3:

[0176] The server uses a generative AI (e.g., OpenAI GPT-4) to analyze the converted text data, extract key discussion points, and generate a summary. The input data is the converted text data, and the output data is the summarized text. Specifically, the text data is input to the generative AI model, and the following prompt sentence is used:

[0177] "Summarize the following text:\nThe council discussed a new public works project to build a new park in District A. This proposal has many merits..."

[0178] Step 4:

[0179] The server delivers the generated summary to the citizen's device via a push notification. The input data is the summarized text, and the output data is a push notification sent to the citizen's device. This push notification uses a notification service such as Firebase Cloud Messaging. The summary is then displayed on the user's device.

[0180] Step 5:

[0181] The device displays the received summary on the screen and provides an interface where users can "like" or comment. The input data is a push notification from the server, and the output data is the user's feedback. Specifically, the device displays the summary text along with a "like" button and a comment input field.

[0182] Step 6:

[0183] The user clicks "Like" on the summary or enters a comment and submits it. The input data is the user's feedback, and the output data is the feedback data sent to the server.

[0184] Step 7:

[0185] The server receives the feedback sent by the user and stores it in a database. The input data is the feedback data, and the output data is the stored database entry. In this step, the feedback data is analyzed and reflected in the analysis dashboard in real time.

[0186] Step 8:

[0187] The server also sends local advertisements when delivering the summary. The input data is the summarized text and advertisement data, and the output data is the summary with advertisements sent to the citizen's device. Specifically, a banner advertisement from a local sponsor is displayed in the designated advertisement space.

[0188] Step 9:

[0189] The server records the number of times the ad was viewed and clicked, and periodically generates a report for the advertiser. The input data is the ad view and click data, and the output data is the generated report. This report compiles data such as the number of views, click rates, and regional responses.

[0190] 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.

[0191] This paper describes a system that provides citizens with real-time information about local assembly discussions and collects and analyzes their feedback by combining it with an emotion engine that recognizes users' emotions. This system is realized through the interaction of a server, terminals, and users.

[0192] 1. Collection and text conversion of meeting minutes

[0193] The server receives real-time data from local assembly discussions. For example, it connects to the assembly's streaming URL and retrieves audio / video data using the RTMP or HLS protocol. This data is then sent to a speech recognition API, which converts the speech into text. Cloud-based services such as Google Cloud Speech-to-Text and Amazon Transcribe are used for the speech recognition API.

[0194] 2. Summary Generation

[0195] The server uses generative AI to analyze the acquired text data, extract the main points of discussion, and generate a summary. For example, the generative AI uses an advanced natural language processing model (e.g., OpenAI GPT-4) to extract important sentences and keywords and summarize them in short sentences.

[0196] 3. Summary Delivery

[0197] The server sends the generated summary to the registered user's device as a push notification, for example, by using a notification service (e.g., Firebase Cloud Messaging) to deliver the notification in real time.

[0198] 4. Providing interaction functions

[0199] The device displays the received summary on the screen and provides an interface that allows users to "like" or post comments. As a concrete example, a "like" button and a comment input field are placed on the UI of a mobile application along with the summary text.

[0200] 5. Leveraging Emotional Engines

[0201] The server inputs the feedback data from the user into the emotion engine to recognize the user's emotions. The emotion engine analyzes the feedback (e.g., "likes" and comments) and generates emotion data (e.g., joy, sadness, anger, etc.).

[0202] 6. Feedback Collection and Analysis

[0203] The server records the recognized emotion data and feedback data in a database and displays it in real time on an analysis dashboard, visualizing citizens' opinions and reactions and enabling local assemblies and municipalities to understand citizens' feelings toward the content of discussions.

[0204] 7. Display and optimization of advertisements

[0205] The server displays advertisements for local stores and businesses when delivering summaries. Furthermore, it optimizes the display of advertisements based on the user's emotional data recognized by the emotion engine. For example, it can display a specific product advertisement to a user who shows positive emotions, and a different advertisement to a user who shows negative emotions.

[0206] 8. Advertising effectiveness measurement and report generation

[0207] The server records the number of impressions and clicks on the ads and periodically generates reports to the advertisers, which can include details such as impressions, click-through rates, user distribution, and recognized emotion data.

[0208] 9. User convenience

[0209] The terminal provides users with a display interface, allowing for smooth operation. Users can express their feelings and opinions on discussions in real time, increasing their willingness to participate in local government.

[0210] This system quickly and concisely conveys the contents of local assembly discussions to citizens, recognizes user sentiment and reflects their feedback, and provides financial support through local advertising. This is expected to promote communication between local governments and citizens, and improve transparency and citizen participation in local government administration.

[0211] The processing flow will be explained below.

[0212] Step 1:

[0213] The server connects to the local council's streaming URL and retrieves audio / video data in real time, maintaining stable streaming using RTMP or HLS protocols.

[0214] Step 2:

[0215] The server sends the acquired audio data to a speech recognition API, which converts the audio into text data in real time. For example, by using Google Cloud Speech-to-Text, highly accurate text conversion is possible.

[0216] Step 3:

[0217] The server analyzes the text data using generative AI, extracts key points of discussion, and generates summaries using natural language processing techniques such as OpenAI GPT-4 to extract important keywords and sentences.

[0218] Step 4:

[0219] The server then sends the generated summary to registered users' devices via push notification, using a push notification service such as Firebase Cloud Messaging to deliver the notification in real time.

[0220] Step 5:

[0221] The device displays the received summary on the screen and provides an interface with a "Like" button and a comment field to allow users to easily provide feedback.

[0222] Step 6:

[0223] Users can post feedback by clicking the "Like" button on the summary or by entering text in the comment field and clicking the submit button.

[0224] Step 7:

[0225] The server receives the feedback from the users and stores it in a database, thereby effectively managing the collected feedback data.

[0226] Step 8:

[0227] The server inputs the feedback data from the user into the emotion engine, which analyzes this data and recognizes the user's emotions (e.g., joy, sadness, anger).

[0228] Step 9:

[0229] The server records the recognized emotion data along with feedback data in a database, which is then reflected in a real-time analytics dashboard, allowing local councils and municipalities to visually understand citizen sentiment.

[0230] Step 10:

[0231] The server sends local ads along with the digests. The ads are optimized based on the emotional data recognized by the emotion engine. For example, a specific ad can be shown to users who show positive emotions, and a different ad can be shown to users who show negative emotions.

[0232] Step 11:

[0233] The terminal displays the advertisement along with the summary on the screen. The user can view the advertisement and click on the link if they are interested.

[0234] Step 12:

[0235] The server records the number of times an ad is displayed and clicked, and stores the data in a database. It periodically generates reports for advertisers to report on the effectiveness of their ads. The reports include the number of times an ad is displayed, click-through rates, and user sentiment data.

[0236] The above processing steps create a system that provides citizens with the content of local assembly discussions in real time, utilizes an emotion engine to collect and analyze citizen feedback, and provides optimized advertisements.

[0237] Example 2

[0238] 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."

[0239] The topics discussed in local assemblies are diverse, making it extremely difficult for citizens to understand everything. Furthermore, the lack of real-time information on discussions undermines the transparency of assemblies, leading to a decline in citizen interest and willingness to participate. Furthermore, the lack of means to instantly collect and analyze citizen feedback leads to a lack of two-way communication between the government and citizens. Conventional systems make it difficult to provide citizens with real-time information on local assembly discussions and effectively collect and analyze their reactions and opinions.

[0240] 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.

[0241] In this invention, the server includes: means for receiving local assembly discussions in real time; means for converting the acquired audio data into text data using a speech recognition API; and means for analyzing the received text data using a generation AI to generate summaries. This enables the contents of local assembly discussions to be quickly organized and summarized and provided to citizens. The server also includes means for delivering the generated summaries to citizens' devices via push notifications; means for providing an interface for citizens to post "likes" and comments on the summaries; means for using an emotion engine to collect and analyze feedback from citizens; and means for recording the analyzed emotion data and feedback data in a database. This enables the collection and analysis of citizen reactions in real time, enabling two-way communication between the government and citizens. The server also includes means for displaying advertising materials along with the summaries and means for generating reports for advertisers using the collected advertising data. This allows advertising revenue to be utilized to support system operations.

[0242] "Discussion" refers to the act of local assembly members and stakeholders exchanging opinions and making decisions about specific issues or policies.

[0243] "Real-time" refers to a situation in which data is processed and information is communicated almost simultaneously as the discussion progresses.

[0244] "Means" refers to the methods or techniques used to achieve a particular goal.

[0245] "Generative AI" is an artificial intelligence that performs natural language processing, and is a technology that has the ability to analyze and learn from large amounts of text data and generate summaries and new text.

[0246] A "speech recognition API" is an application programming interface that accepts voice data as input and converts it into text data.

[0247] "Text data" refers to digital information expressed as a string of characters, and is subject to natural language processing and analysis.

[0248] "Push notification" is a technology that allows messages and notifications to be sent instantly from the server to the user's device.

[0249] "Interface" refers to the contact points or means by which a user and a system interact with each other.

[0250] "Feedback" refers to reactions and opinions from users regarding particular information or services.

[0251] An "emotion engine" is a technology that analyzes text data and feedback and recognizes the emotions contained therein.

[0252] A "database" is a system for efficiently storing, managing, and retrieving data.

[0253] "Advertising Materials" means information content, such as text, images, and video, used to promote products and services.

[0254] A "report" is a document that summarizes collected data and analysis results, and provides organized information according to a specific purpose.

[0255] This invention describes a system that provides real-time information about local council discussions to citizens, recognizes user sentiment, and collects and analyzes feedback. This system is realized through the interaction of a server, terminals, and users.

[0256] Receiving and transcribing discussions

[0257] The server first receives real-time streaming from the local assembly. Specifically, it connects to the assembly's streaming URL using RTMP or HLS protocol to obtain audio / video data. This data is then sent to a speech recognition API such as Google Cloud Speech-to-Text or Amazon Transcribe, where the audio data is converted into text data.

[0258] Specific examples

[0259] Connect to the parliamentary streaming URL: http: / / example.com / stream using the RTMP protocol, obtain the audio data, and send it to the Google Cloud Speech-to-Text API.

[0260] Summary generation and summary delivery

[0261] The server analyzes the text data obtained from the speech recognition API and uses a generative AI model (e.g., OpenAI GPT-4) to summarize the text data. The summary extracts the main points of discussion and condenses them into short sentences.

[0262] Specific examples

[0263] Example prompt: Enter the following text data and summarize the main points of the discussion: Text: "{Congress discussion text}"

[0264] The generated summary is pushed to registered users' devices in real time using a notification service such as Firebase Cloud Messaging.

[0265] Gathering feedback and leveraging the emotion engine

[0266] The device displays the received summary on the screen and provides an interface where users can post "likes" and comments. The user's feedback is sent to the server, and the feedback data is input into the emotion engine. The emotion engine analyzes the feedback and generates emotion data (e.g., joy, sadness, anger, etc.).

[0267] Specific examples

[0268] Example prompt: Enter the following comment and analyze the sentiment: Comment: "{user comment}"

[0269] Data collection and analysis

[0270] The server records sentiment data and feedback data in a database and displays it in real time on an analysis dashboard, visualizing citizen opinions and reactions, allowing local assemblies and municipalities to understand citizen sentiment regarding the content of discussions.

[0271] Ad placement and optimization

[0272] The server displays advertisements for local stores and businesses when delivering summaries, and optimizes the display of advertisements based on the user's emotional data recognized by the emotion engine. Using the collected advertising data, reports can be generated for advertisers.

[0273] In this way, this system quickly and concisely conveys the contents of local assembly discussions to citizens, and by analyzing and utilizing user emotional data, promotes two-way communication between local governments and citizens.

[0274] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0275] Step 1:

[0276] Receive real-time discussions

[0277] The server connects to the local assembly's streaming URL via RTMP or HLS protocol and receives audio / video data in real time. This streaming data is the input, and the acquired audio / video data is the output. Specifically, the server connects to the streaming URL and receives assembly discussions in real time.

[0278] Specific actions

[0279] Connect to the streaming URL.

[0280] Retrieve audio data using the RTMP protocol.

[0281] Step 2:

[0282] Converting audio data to text

[0283] The server sends the acquired audio data to a speech recognition API (e.g., Google Cloud Speech-to-Text) and converts it into text data. This audio data is the input, and the converted text data is the output. Specifically, the server sends audio data to the API and receives text data from the API.

[0284] Specific actions

[0285] Send the audio data to the Google Cloud Speech-to-Text API.

[0286] Receive the generated text data.

[0287] Step 3:

[0288] Text data analysis and summary generation

[0289] The server inputs the text data obtained from the speech recognition API into a generative AI model (e.g., OpenAI GPT-4), extracts the main points of the discussion, and generates a summary. This text data is the input, and the generated summary is the output. Specifically, the server inputs the data along with the prompt "Please summarize this text" and generates a summary.

[0290] Specific actions

[0291] Input text data into GPT-4.

[0292] Set the prompt text.

[0293] Receive the output summary.

[0294] Step 4:

[0295] Summary Delivery

[0296] The server then pushes the generated summary to the registered user's device using a notification service such as Firebase Cloud Messaging. The summary is the input, and the pushed message is the output. Specifically, the summary is set as the body of the push notification and sent using the notification service.

[0297] Specific actions

[0298] Set the summary text as the body of the push notification.

[0299] Calls Firebase Cloud Messaging to send a notification to the user device.

[0300] Step 5:

[0301] Providing interaction functions

[0302] The device displays the received summary on the screen and provides an interface where the user can post likes and comments. This summary is the input, and the user's feedback is the output. Specifically, when the user opens the app, the latest summary text is displayed and feedback is possible.

[0303] Specific actions

[0304] Display summary text on screen.

[0305] Provide a "Like" button and a comment field.

[0306] Step 6:

[0307] Analysis by emotion engine

[0308] The server collects feedback data (likes and comments) from users and inputs it into the emotion engine to recognize emotions. This feedback data is the input, and the analyzed emotion data is the output. Specifically, the server sends the feedback data to the emotion engine and receives the emotion data.

[0309] Specific actions

[0310] Collect user comments and likes data.

[0311] Sending feedback data to the emotion engine.

[0312] Obtain emotion data.

[0313] Step 7:

[0314] Data collection and analysis

[0315] The server records the emotion data and feedback data in a database and reflects them in real time on the analysis dashboard. This emotion data and feedback data are the input, and the updated analysis dashboard is the output. Specifically, the server saves the data in the database and updates the dashboard.

[0316] Specific actions

[0317] Emotion data and feedback data are stored in a database.

[0318] Refresh your analytics dashboard.

[0319] Step 8:

[0320] Ad placement and optimization

[0321] The server displays local advertising materials when delivering summaries and optimizes the display of advertisements based on emotional data. The summaries and emotional data are input, and the optimized advertisement display is the output. Specifically, the server selects and displays appropriate advertisements along with the summaries.

[0322] Specific actions

[0323] Select ads that are suitable for the summary text.

[0324] Optimize your ads based on sentiment data.

[0325] Step 9:

[0326] Advertising effectiveness measurement and report generation

[0327] The server records the number of times the ad is displayed and the number of clicks, and generates an effectiveness measurement report for the advertiser. This advertising data is the input, and the generated report is the output. Specifically, data such as the number of times the ad is displayed and the click rate is collected, and reports are created periodically.

[0328] Specific actions

[0329] Record the number of impressions and clicks on your ads.

[0330] Generate reports to advertisers.

[0331] (Application example 2)

[0332] 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."

[0333] While the content of local assembly discussions is important information for citizens, it is difficult to grasp this information in real time, which has led to a decline in citizen participation and interest.In addition, when widely disseminating information about local assembly meetings to citizens, there is a need to effectively collect and analyze citizen opinions and emotions, and to optimize the provision of information and advertising display based on that information.

[0334] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving local assembly discussions in real time, means for converting the received discussions into text data using a generation AI and generating summaries, means for delivering the generated summaries to citizens' devices via push notifications, means for providing an interface for citizens to post "likes" and comments on the summaries, means for collecting and analyzing feedback from citizens, means for displaying local advertisements along with the summaries, means for generating reports for advertisers using the collected advertising data, means for inputting the feedback data into an emotion engine and analyzing citizen emotions, and means for optimizing advertisements using the emotion analysis data. This makes it possible to quickly and concisely communicate the content of local assembly discussions to citizens, effectively collect and analyze citizen opinions and emotions, promote communication between local governments and citizens, and optimize advertisements.

[0335] A "local assembly" is the decision-making body of a local government and the place where decisions are made by local public entities.

[0336] "Real time" refers to immediacy that corresponds to the timing of an event.

[0337] "Generative AI" refers to artificial intelligence that generates new data and information using natural language processing and machine learning techniques.

[0338] "Text data" refers to digital data that expresses information such as audio and video as a string of characters.

[0339] A "summary" is a short summary of the main points extracted from the original information.

[0340] A "terminal" is a device operated by a user, such as a smartphone or computer.

[0341] "Push notification" is a mechanism that automatically sends information from the server to the user's device.

[0342] An "interface" refers to the means or screen through which a user interacts with a system.

[0343] "Feedback" refers to the evaluations and opinions that users give to the system.

[0344] An "emotion engine" is a machine learning algorithm or technology that analyzes user feedback and behavior to recognize emotions.

[0345] "Local advertising" refers to advertising that promotes businesses or services related to a particular area.

[0346] "Advertiser" refers to a company or individual that places an advertisement.

[0347] A "report" is a document that compiles data and information.

[0348] "Emotion analysis data" refers to digital data generated as a result of analyzing a user's emotions.

[0349] "Optimization" means adjusting something to the most effective or efficient state depending on the conditions and purpose.

[0350] This invention is a system that provides citizens with real-time information about local assembly discussions and collects and analyzes their feedback by combining it with an emotion engine that recognizes users' emotions. This system is realized through the interaction of a server, terminals, and users.

[0351] The server receives local assembly discussions in real time. Specifically, it connects to the assembly's streaming URL and obtains audio / video data using the RTMP or HLS protocol. This data is then sent to a speech recognition API, which converts the speech into text data. Cloud-based speech recognition services such as Google Cloud Speech-to-Text and Amazon Transcribe are used for the speech recognition API. At this stage, the discussion content is stored as text data on the server.

[0352] The server then uses generative AI to analyze the acquired text data, extract key points of discussion, and generate a summary. For example, the generative AI uses an advanced natural language processing model (e.g., OpenAI GPT-4) to extract important sentences and keywords and summarize them into short sentences. This summary data is then stored on the server, ready to be sent to the user.

[0353] The generated summary is delivered to the user's device via push notification. The notification service uses Firebase Cloud Messaging (FCM). By using FCM, notifications can be sent to users in real time and the summary content can be displayed.

[0354] The user's device displays the received summary on the screen and provides an interface where the user can "like" or post comments. This interface is implemented as a mobile application, and includes a "like" button and a comment input field along with the summary text. Through this, users can input their own opinions and feelings in real time.

[0355] Furthermore, the server inputs feedback data from users into the emotion engine to analyze the user's emotions. The emotion engine analyzes the feedback (e.g., "likes" and comments) and generates emotion data (e.g., joy, sadness, anger, etc.). This emotion data is stored on the server and used for subsequent processing such as ad optimization.

[0356] The server also has the ability to display advertisements for local stores and businesses along with the summary. Based on the user's emotional data recognized by the emotion engine, the display of advertisements can be optimized. For example, a specific product advertisement can be displayed to a user who shows positive emotions, while a different advertisement can be displayed to a user who shows negative emotions.

[0357] The server records the number of times an advertisement is displayed and clicked, and periodically generates reports to advertisers. The reports include details such as the number of impressions, click-through rates, user distribution, and recognized emotion data. This allows advertisers to accurately understand the effectiveness of their advertisements and develop marketing strategies.

[0358] For example:

[0359] When a user receives a summary of a "local council's proposed new ordinance" and clicks "Like" on their smartphone, their behavior is collected and stored in a database as the user's positive emotion. The same user is then shown an advertisement featuring a new service from a relevant local store.

[0360] Example prompt sentence:

[0361] "Please summarize the latest discussions in the local council and notify users."

[0362] "Analyze user sentiment data and display the most appropriate ads."

[0363] As a result, it is possible to provide a system that can quickly and concisely convey the contents of discussions in local assemblies to citizens, effectively collect and analyze citizens' opinions and feelings, promote communication between local governments and citizens, and optimize advertising.

[0364] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0365] Step 1:

[0366] The server receives real-time local assembly discussions. Specifically, it connects to the assembly's streaming URL and obtains audio / video data using the RTMP or HLS protocol. Using this data as input, the server sends the data to a speech recognition API, which then obtains text data as output.

[0367] Step 2:

[0368] The server analyzes the acquired text data and generates a summary. Specifically, it uses generation AI to extract important sentences and keywords from the text data and summarize them into short sentences. The input here is text data, and the output is summarized text data.

[0369] Step 3:

[0370] The server sends the generated summary to the user's device via a push notification. The server uses Firebase Cloud Messaging (FCM) to send a push notification using the summarized text data as input, and the user's device receives the notification.

[0371] Step 4:

[0372] The device displays the received summary on the screen and provides an interface for users to "like" or post comments. Specifically, as a mobile application, a "like" button and a comment input field are displayed along with the summary text. The input is the summary text received via push notification, and the output is the interface operated by the user.

[0373] Step 5:

[0374] Users post "likes" and comments through the interface, which allows feedback data to be collected. The input is user actions (likes and comments), and the output is feedback data.

[0375] Step 6:

[0376] The server inputs feedback data from the user into the emotion engine and analyzes the user's emotions. Specifically, the emotion engine analyzes the feedback data and generates the user's emotion data (e.g., joy, sadness, anger, etc.). The input is the feedback data, and the output is the emotion data.

[0377] Step 7:

[0378] The server uses the sentiment analysis data to optimize advertisements. Specifically, it displays a specific product advertisement to users who show positive emotions and a different advertisement to users who show negative emotions. The input is the sentiment analysis data, and the output is the optimized advertisement.

[0379] Step 8:

[0380] The server records the number of times an ad is displayed and clicked, and periodically generates a report for the advertiser. Specifically, it aggregates the number of times an ad is displayed, the click rate, user distribution, recognized emotion data, etc., and generates the report. The input is the ad data, and the output is the report.

[0381] 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.

[0382] 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.

[0383] 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.

[0384] [Second embodiment]

[0385] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0386] 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.

[0387] 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).

[0388] 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.

[0389] 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.

[0390] 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).

[0391] 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.

[0392] 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.

[0393] 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.

[0394] 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.

[0395] 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.

[0396] 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."

[0397] This paper describes a system that provides local assembly discussions to citizens in real time, collects and analyzes their opinions on the discussions, and effectively distributes local advertisements. This system is realized through the interaction of a server, terminals, and users.

[0398] 1. Collection and text conversion of meeting minutes

[0399] The server receives real-time data from local assembly discussions. For example, it connects to the assembly's streaming URL and retrieves audio / video data using the RTMP or HLS protocol. The retrieved data is then converted into text data using a speech recognition API. For example, a cloud-based speech recognition service (e.g., Google Cloud Speech-to-Text) is used as the speech recognition API.

[0400] 2. Summary Generation

[0401] The server uses generative AI to analyze the acquired text data, extract the main points of discussion, and generate a summary. For example, the generative AI uses an advanced natural language processing model (e.g., OpenAI GPT-4) to extract important sentences and keywords and summarize them in short sentences.

[0402] 3. Summary Delivery

[0403] The server delivers the generated summary to the citizen's device via push notification. For example, it uses a notification service (e.g., Firebase Cloud Messaging) to send real-time notifications to the device of a pre-registered user.

[0404] 4. Providing interaction functions

[0405] The device displays the received summary on the screen and provides an interface that allows users to "like" or post comments. As a concrete example, a "like" button and a comment input field are placed on the UI of a mobile application along with the summary text.

[0406] 5. Feedback collection and analysis

[0407] Users can click "Like" on a summary or enter and submit a comment. The server receives the feedback sent by users and stores it in a database. The feedback data is analyzed and reflected in real time on an analysis dashboard. Based on the analysis results, citizens' opinions and reactions are visualized.

[0408] 6. Display of advertisements

[0409] The server also sends advertisements for local stores and businesses when delivering the summary. For example, it can set up a system to display banner advertisements from local sponsors in designated ad slots. The advertisements are delivered along with the summary and displayed on the user's device.

[0410] 7. Advertising effectiveness measurement and report generation

[0411] The server records the number of times the ad was displayed and the number of clicks, and periodically generates reports for the advertiser. For example, a weekly report compiling data such as the number of impressions, click-through rate, and regional response may be sent to the advertiser via email.

[0412] 8. User convenience

[0413] The terminal provides users with a display interface that allows for smooth operation. Users can express their interest in discussions in real time, increasing their motivation to participate in local government.

[0414] This system allows the contents of local assembly discussions to be communicated to citizens quickly and concisely, reflecting their feedback, while providing financial support through local advertising. This is expected to promote communication between local governments and citizens, and improve the transparency and citizen participation in local administration.

[0415] The processing flow will be explained below.

[0416] Step 1:

[0417] The server connects to the local council's streaming URL and retrieves audio / video data in real time, using the RTMP or HLS protocol for stable streaming.

[0418] Step 2:

[0419] The server sends the acquired audio data to a speech recognition API, which converts the audio data into text data. This speech recognition API uses cloud-based services such as Google Cloud Speech-to-Text and Amazon Transcribe.

[0420] Step 3:

[0421] The server inputs the generated text data into a generative AI, extracts key points of discussion, and generates a summary. The generative AI model uses OpenAI GPT-4 and other technologies, and uses natural language processing to extract important sentences and keywords.

[0422] Step 4:

[0423] The server sends the generated summary to registered users' devices via push notification, using a push notification service such as Firebase Cloud Messaging to deliver notifications to users' mobile devices in real time.

[0424] Step 5:

[0425] The device displays the received summary on the screen. Along with the summary text, it also provides an interface where users can post "likes" and comments. This interface includes a "like" button and a comment input field below the summary.

[0426] Step 6:

[0427] Users can publish their feedback by clicking the "Like" button on the summary or by entering a comment and clicking the submit button.

[0428] Step 7:

[0429] The server receives feedback from users (likes and comments) and records it in a database. This allows users' reactions and opinions to be collected and stored as data.

[0430] Step 8:

[0431] The server analyzes the collected feedback data and displays it in real time on an analytical dashboard, allowing users to instantly grasp the situation of local governments and councils.

[0432] Step 9:

[0433] The server sends advertisements along with the summary delivery. Advertisements from local stores and businesses are registered in the system and set to be displayed in designated ad slots.

[0434] Step 10:

[0435] The terminal displays local advertisements along with summary text, which the user can view and follow links to if desired.

[0436] Step 11:

[0437] The server records the number of times the advertisement is displayed and the number of clicks in a database and periodically generates a report for the advertiser, which summarizes data such as the number of times the advertisement is displayed, the click rate, and the user distribution, and provides the report to the advertiser.

[0438] Through these steps, a system will be created that provides citizens with real-time information about local assembly discussions, collects and analyzes citizen feedback, and delivers effective advertising.

[0439] Example 1

[0440] 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."

[0441] Traditional media and websites lack the real-time capabilities to quickly and concisely communicate the contents of local assembly discussions to citizens. It is also difficult to effectively collect and analyze citizen feedback, and to appropriately deliver advertisements for local businesses. A system that can solve these issues is needed.

[0442] 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.

[0443] In this invention, the server includes a means for receiving local assembly discussions in real time, a means for converting the received discussions into text data using a generation AI to generate summaries, and a means for delivering the generated summaries to citizens' devices via push notifications. This allows citizens to quickly and concisely understand the content of local assembly discussions and provide feedback on the content in real time. Furthermore, the effective delivery of local advertisements contributes to revitalizing the local economy.

[0444] "Local assembly discussions" refers to various debates and deliberations held in local government assemblies.

[0445] "Real-time receiving means" refers to devices or software that have the ability to simultaneously obtain data about ongoing discussions or debates.

[0446] "Generative AI" refers to artificial intelligence that uses machine learning models and algorithms to generate specific information from input data.

[0447] "Means for converting into text data" refers to the technology or method for converting data acquired in the form of audio, video, etc. into text information.

[0448] A "summary generation method" refers to a process or system that extracts important information from long text data and presents it in a compact form.

[0449] "Citizen's device" refers to an electronic device such as a personal computer, smartphone or tablet that a citizen uses to receive and display local council information.

[0450] "Means of delivering push notifications" refers to technology that notifies users of information in real time or at a specified time.

[0451] "Interface" refers to the screen and input / output means that allow a user to interact with and operate a system.

[0452] "Means for collecting and analyzing feedback" refers to the techniques and processes used to receive user opinions and responses and analyze that data.

[0453] "Local advertising" refers to advertising that promotes products, services, events, etc. that are relevant to a particular geographic area.

[0454] "Advertiser" refers to a company or individual that places an advertisement.

[0455] "Means for generating reports" means the process or system that generates reports or analyses based on the collected data and that are periodically sent to advertisers.

[0456] This invention relates to a system that provides local assembly discussions to citizens in real time, collects and analyzes their opinions on the discussions, and effectively distributes local advertisements. This system is realized through the interaction of a server, terminals, and users.

[0457] First, the server receives the local assembly discussions in real time. This involves connecting to the local assembly's streaming URL and obtaining the audio / video data using the RTMP or HLS protocol. The obtained data is then converted into text data using a speech recognition API (e.g., Google Cloud Speech-to-Text).

[0458] The server then analyzes the acquired text data using generative AI, extracts key discussion points, and generates a summary. Specifically, it uses a generative AI model (e.g., OpenAI GPT-4). An example of a prompt for generating a summary is "Please summarize the following minutes:"

[0459] The generated summary is delivered to the citizen's device via a push notification by the server. These notifications are delivered using Firebase Cloud Messaging. An example of the push notification content is "A new discussion summary is available."

[0460] The device displays the received summary to the user and provides an interface that allows the user to "like" or comment, including by placing a "like" button and a comment input field along with the summary text in the user interface of the mobile application.

[0461] Users can click "Like" on the summary or enter and submit a comment. The server receives the feedback submitted by users and stores it in a database (e.g., MySQL). The collected feedback data is analyzed in real time and displayed on an analysis dashboard. For the analysis, an analysis tool such as Tableau is used.

[0462] In addition, the server also sends advertisements for local businesses and stores along with the summary. The advertisements are set to be displayed as banner advertisements for local sponsors in designated ad slots. This allows the advertisements to be displayed on the user's device along with the summary.

[0463] The server also handles ad performance measurement and reporting. It records the number of ad impressions and clicks, and periodically generates weekly reports for advertisers. The reports include data such as impressions, click-through rates, and geographic response, and are sent to advertisers via email.

[0464] Finally, the device provides users with a display interface that allows for smooth operation, allowing them to reflect their interest in local assembly discussions in real time, increasing their motivation to participate in local government.

[0465] By combining these functions, it is possible to quickly and concisely convey the contents of local assembly discussions to citizens, incorporate their feedback, and provide financial support through local advertising. This is expected to promote communication between local governments and citizens, and improve the transparency and citizen participation of local government administration.

[0466] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0467] Step 1:

[0468] The server connects to the local council's live streaming URL and receives audio / video data using the RTMP or HLS protocol. Specifically, it retrieves data from the streaming URL (e.g., http: / / example-streaming-url.com) and calls a speech recognition API (e.g., Google Cloud Speech-to-Text) to convert the audio data into text data.

[0469] Input: Audio / video data via streaming URL

[0470] Output: Text data

[0471] Step 2:

[0472] The server inputs the converted text data into a generative AI model, extracts key discussion points, and generates a summary. Specifically, the server inputs the following prompt into the generative AI model (e.g., OpenAI GPT-4): "Please summarize the following minutes: 'Text data'." The server then saves the generated summary.

[0473] Input: Text data

[0474] Output: Summary data

[0475] Step 3:

[0476] The server uses Firebase Cloud Messaging to deliver the generated summary to citizens' devices via push notification. Specifically, it uses the Firebase Cloud Messaging API to send the summary along with the message "A new discussion summary is available."

[0477] Input: Summary data and user information

[0478] Output: Push notification sent

[0479] Step 4:

[0480] The device displays the received summary to the user and provides an interface that allows the user to "like" or post a comment. Specifically, a "like" button and a comment input field are placed on the UI of the mobile application along with the summary text, allowing the user to use these interfaces.

[0481] Input: Summary data

[0482] Output: User interface

[0483] Step 5:

[0484] Users can click "Like" on the displayed summary or enter and submit a comment. The server receives the feedback and stores it in a database. Specifically, it collects user feedback data (likes and comments) and stores them in a MySQL database.

[0485] Input: User feedback data

[0486] Output: Feedback data stored in a database

[0487] Step 6:

[0488] The server analyzes the collected feedback data in real time. Specifically, it uses an analytical tool (e.g., Tableau) to analyze the feedback data and display it on a dashboard. This analysis visualizes citizens' opinions and reactions.

[0489] Input: Feedback data

[0490] Output: Dashboard display of analysis results

[0491] Step 7:

[0492] The server selects advertising data and distributes it together with the summary in order to transmit advertisements of local sponsors together with the summary. Specifically, the server sets banner advertisements of local sponsors in designated advertising spaces and displays them on the user's terminal together with the summary.

[0493] Input: Summary data and advertising data

[0494] Output: Summary and advertisement displayed on user's device

[0495] Step 8:

[0496] The server records the number of times an ad is displayed and clicked, and compiles this data into a report that is sent to the advertiser periodically. Specifically, a weekly report is generated, compiling data such as the number of impressions, click-through rates, and regional responses, and sending it to the advertiser via email.

[0497] Input: Ad impressions and click data

[0498] Output: Report sent to advertiser

[0499] (Application example 1)

[0500] 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."

[0501] There is a lack of means to quickly and effectively communicate the contents of discussions in local assemblies to citizens, as well as to instantly collect and reflect citizen opinions. Furthermore, there is a need for a system that will facilitate smooth communication and economic activity between local governments, citizens, and local businesses by effectively distributing local advertising in conjunction with the information provided to citizens.

[0502] 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.

[0503] In this invention, the server includes: means for receiving local assembly discussions in real time; means for converting the received discussions into text data using a generative AI and generating summaries; means for distributing the generated summaries to citizens' devices via push notifications; means for providing an interface for citizens to post "likes" and comments on the summaries; means for collecting and analyzing feedback from citizens; means for displaying local advertisements along with the summaries; means for generating reports for advertisers using the collected advertisement data; means for live displaying streaming data on citizens' devices; means for collecting comments in real time based on the live-displayed discussions; and means for analyzing the collected comment data and summarizing using a generative AI model. This makes it possible to communicate the content of local assembly discussions to citizens in real time, immediately reflect citizen feedback, and effectively distribute local advertisements.

[0504] A "local assembly" is the legislative body of a local government, and is the body that deliberates and decides on important policies and budgets of local public entities.

[0505] "Real time" is a term that describes things happening nearly simultaneously or with very little delay.

[0506] "Generative AI" refers to artificial intelligence technology that automatically learns and generates text, audio, images, etc.

[0507] "Text data" is a data format consisting of characters and words, and is data that contains character strings that can be processed by a computer.

[0508] A "summary" is a short summary of the original content, intended to convey the main points concisely.

[0509] "Push notification" is a technology that sends information from a server to a user's device in real time, allowing the user to receive the information without taking any specific action.

[0510] "Interface" refers to the means and screen layout by which a user interacts with a system or application.

[0511] "Feedback" refers to reactions and opinions collected from users, and is information that is useful for improving and evaluating a system.

[0512] "Local advertising" refers to promotional activities of stores and businesses related to a specific area, and is advertising targeted at people living in that area.

[0513] "Streaming data" refers to audio and video data that is distributed in real time over the Internet.

[0514] "Live display" refers to displaying data or video to viewers in real time.

[0515] "Comment data" refers to opinions and impressions entered by users in text format.

[0516] A "generative AI model" is an algorithm that automatically generates text, audio, images, etc. using technologies such as machine learning and deep learning.

[0517] This invention includes a system that provides citizens with real-time information about local assembly discussions, collects and analyzes their opinions on the content, and effectively distributes local advertisements. This system is realized through the interaction of a server, terminals, and users.

[0518] First, the server receives the local assembly discussions in real time by connecting to the local assembly's streaming URL using the RTMP or HLS protocol. The received audio / video data is converted into text data using a speech recognition API (e.g., Google Cloud Speech-to-Text).

[0519] The server then uses a generative AI to analyze the converted text data, extract key discussion points, and generate a summary. The generative AI uses an advanced natural language processing model such as OpenAI GPT-4. For example, it uses the following prompt:

[0520] "Summarize the following text:\nThe council discussed a new public works project to build a new park in District A. This proposal has many merits..."

[0521] The generated summary is delivered to the citizen's device via a push notification from the server using a notification service such as Firebase Cloud Messaging. Citizens receive the summary on their device and are provided with an interface where they can "like" or post comments.

[0522] Next, citizen feedback is sent to a server and stored in a database. This feedback data is then reflected in a real-time analysis dashboard, visualizing citizen opinions and reactions.

[0523] Furthermore, the server also transmits local advertisements when delivering the summary. For example, it is set to display banner advertisements of local sponsors in the advertisement space. The advertisements are delivered together with the summary and displayed on the user's terminal.

[0524] Finally, the server records the number of impressions and clicks on the ads and periodically generates reports for the advertiser, summarizing data such as impressions, click-through rates, and geographic response, which are emailed to the advertiser.

[0525] This system allows the contents of local council discussions to be communicated to citizens quickly and concisely, allows for the collection and analysis of feedback from citizens, and promotes communication between local governments, citizens, and local businesses by effectively distributing local advertisements.

[0526] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0527] Step 1:

[0528] The server receives the local assembly discussions in real time by connecting to the local assembly's streaming URL using the RTMP or HLS protocol. The input data is an audio / video stream, and the output data is audio data for speech recognition.

[0529] Step 2:

[0530] The server converts the received audio data into text data using a speech recognition API (e.g., Google Cloud Speech-to-Text). The input data is audio data, and the output data is text data. In this step, the audio signal is analyzed and converted into text as a string.

[0531] Step 3:

[0532] The server uses a generative AI (e.g., OpenAI GPT-4) to analyze the converted text data, extract key discussion points, and generate a summary. The input data is the converted text data, and the output data is the summarized text. Specifically, the text data is input to the generative AI model, and the following prompt sentence is used:

[0533] "Summarize the following text:\nThe council discussed a new public works project to build a new park in District A. This proposal has many merits..."

[0534] Step 4:

[0535] The server delivers the generated summary to the citizen's device via a push notification. The input data is the summarized text, and the output data is a push notification sent to the citizen's device. This push notification uses a notification service such as Firebase Cloud Messaging. The summary is then displayed on the user's device.

[0536] Step 5:

[0537] The device displays the received summary on the screen and provides an interface where users can "like" or comment. The input data is a push notification from the server, and the output data is the user's feedback. Specifically, the device displays the summary text along with a "like" button and a comment input field.

[0538] Step 6:

[0539] The user clicks "Like" on the summary or enters a comment and submits it. The input data is the user's feedback, and the output data is the feedback data sent to the server.

[0540] Step 7:

[0541] The server receives the feedback sent by the user and stores it in a database. The input data is the feedback data, and the output data is the stored database entry. In this step, the feedback data is analyzed and reflected in the analysis dashboard in real time.

[0542] Step 8:

[0543] The server also sends local advertisements when delivering the summary. The input data is the summarized text and advertisement data, and the output data is the summary with advertisements sent to the citizen's device. Specifically, a banner advertisement from a local sponsor is displayed in the designated advertisement space.

[0544] Step 9:

[0545] The server records the number of times the ad was viewed and clicked, and periodically generates a report for the advertiser. The input data is the ad view and click data, and the output data is the generated report. This report compiles data such as the number of views, click rates, and regional responses.

[0546] 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.

[0547] This paper describes a system that provides citizens with real-time information about local assembly discussions and collects and analyzes their feedback by combining it with an emotion engine that recognizes users' emotions. This system is realized through the interaction of a server, terminals, and users.

[0548] 1. Collection and text conversion of meeting minutes

[0549] The server receives real-time data from local assembly discussions. For example, it connects to the assembly's streaming URL and retrieves audio / video data using the RTMP or HLS protocol. This data is then sent to a speech recognition API, which converts the speech into text. Cloud-based services such as Google Cloud Speech-to-Text and Amazon Transcribe are used for the speech recognition API.

[0550] 2. Summary Generation

[0551] The server uses generative AI to analyze the acquired text data, extract the main points of discussion, and generate a summary. For example, the generative AI uses an advanced natural language processing model (e.g., OpenAI GPT-4) to extract important sentences and keywords and summarize them in short sentences.

[0552] 3. Summary Delivery

[0553] The server sends the generated summary to the registered user's device as a push notification, for example, by using a notification service (e.g., Firebase Cloud Messaging) to deliver the notification in real time.

[0554] 4. Providing interaction functions

[0555] The device displays the received summary on the screen and provides an interface that allows users to "like" or post comments. As a concrete example, a "like" button and a comment input field are placed on the UI of a mobile application along with the summary text.

[0556] 5. Leveraging Emotional Engines

[0557] The server inputs the feedback data from the user into the emotion engine to recognize the user's emotions. The emotion engine analyzes the feedback (e.g., "likes" and comments) and generates emotion data (e.g., joy, sadness, anger, etc.).

[0558] 6. Feedback Collection and Analysis

[0559] The server records the recognized emotion data and feedback data in a database and displays it in real time on an analysis dashboard, visualizing citizens' opinions and reactions and enabling local assemblies and municipalities to understand citizens' feelings toward the content of discussions.

[0560] 7. Display and optimization of advertisements

[0561] The server displays advertisements for local stores and businesses when delivering summaries. Furthermore, it optimizes the display of advertisements based on the user's emotional data recognized by the emotion engine. For example, it can display a specific product advertisement to a user who shows positive emotions, and a different advertisement to a user who shows negative emotions.

[0562] 8. Advertising effectiveness measurement and report generation

[0563] The server records the number of impressions and clicks on the ads and periodically generates reports to the advertisers, which can include details such as impressions, click-through rates, user distribution, and recognized emotion data.

[0564] 9. User convenience

[0565] The terminal provides users with a display interface, allowing for smooth operation. Users can express their feelings and opinions on discussions in real time, increasing their willingness to participate in local government.

[0566] This system quickly and concisely conveys the contents of local assembly discussions to citizens, recognizes user sentiment and reflects their feedback, and provides financial support through local advertising. This is expected to promote communication between local governments and citizens, and improve transparency and citizen participation in local government administration.

[0567] The processing flow will be explained below.

[0568] Step 1:

[0569] The server connects to the local council's streaming URL and retrieves audio / video data in real time, maintaining stable streaming using RTMP or HLS protocols.

[0570] Step 2:

[0571] The server sends the acquired audio data to a speech recognition API, which converts the audio into text data in real time. For example, by using Google Cloud Speech-to-Text, highly accurate text conversion is possible.

[0572] Step 3:

[0573] The server analyzes the text data using generative AI, extracts key points of discussion, and generates summaries using natural language processing techniques such as OpenAI GPT-4 to extract important keywords and sentences.

[0574] Step 4:

[0575] The server then sends the generated summary to registered users' devices via push notification, using a push notification service such as Firebase Cloud Messaging to deliver the notification in real time.

[0576] Step 5:

[0577] The device displays the received summary on the screen and provides an interface with a "Like" button and a comment field to allow users to easily provide feedback.

[0578] Step 6:

[0579] Users can post feedback by clicking the "Like" button on the summary or by entering text in the comment field and clicking the submit button.

[0580] Step 7:

[0581] The server receives the feedback from the users and stores it in a database, thereby effectively managing the collected feedback data.

[0582] Step 8:

[0583] The server inputs the feedback data from the user into the emotion engine, which analyzes this data and recognizes the user's emotions (e.g., joy, sadness, anger).

[0584] Step 9:

[0585] The server records the recognized emotion data along with feedback data in a database, which is then reflected in a real-time analytics dashboard, allowing local councils and municipalities to visually understand citizen sentiment.

[0586] Step 10:

[0587] The server sends local ads along with the digests. The ads are optimized based on the emotional data recognized by the emotion engine. For example, a specific ad can be shown to users who show positive emotions, and a different ad can be shown to users who show negative emotions.

[0588] Step 11:

[0589] The terminal displays the advertisement along with the summary on the screen. The user can view the advertisement and click on the link if they are interested.

[0590] Step 12:

[0591] The server records the number of times an ad is displayed and clicked, and stores the data in a database. It periodically generates reports for advertisers to report on the effectiveness of their ads. The reports include the number of times an ad is displayed, click-through rates, and user sentiment data.

[0592] The above processing steps create a system that provides citizens with the content of local assembly discussions in real time, utilizes an emotion engine to collect and analyze citizen feedback, and provides optimized advertisements.

[0593] Example 2

[0594] 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."

[0595] The topics discussed in local assemblies are diverse, making it extremely difficult for citizens to understand everything. Furthermore, the lack of real-time information on discussions undermines the transparency of assemblies, leading to a decline in citizen interest and willingness to participate. Furthermore, the lack of means to instantly collect and analyze citizen feedback leads to a lack of two-way communication between the government and citizens. Conventional systems make it difficult to provide citizens with real-time information on local assembly discussions and effectively collect and analyze their reactions and opinions.

[0596] 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.

[0597] In this invention, the server includes: means for receiving local assembly discussions in real time; means for converting the acquired audio data into text data using a speech recognition API; and means for analyzing the received text data using a generation AI to generate summaries. This enables the contents of local assembly discussions to be quickly organized and summarized and provided to citizens. The server also includes means for delivering the generated summaries to citizens' devices via push notifications; means for providing an interface for citizens to post "likes" and comments on the summaries; means for using an emotion engine to collect and analyze feedback from citizens; and means for recording the analyzed emotion data and feedback data in a database. This enables the collection and analysis of citizen reactions in real time, enabling two-way communication between the government and citizens. The server also includes means for displaying advertising materials along with the summaries and means for generating reports for advertisers using the collected advertising data. This allows advertising revenue to be utilized to support system operations.

[0598] "Discussion" refers to the act of local assembly members and stakeholders exchanging opinions and making decisions about specific issues or policies.

[0599] "Real-time" refers to a situation in which data is processed and information is communicated almost simultaneously as the discussion progresses.

[0600] "Means" refers to the methods or techniques used to achieve a particular goal.

[0601] "Generative AI" is an artificial intelligence that performs natural language processing, and is a technology that has the ability to analyze and learn from large amounts of text data and generate summaries and new text.

[0602] A "speech recognition API" is an application programming interface that accepts voice data as input and converts it into text data.

[0603] "Text data" refers to digital information expressed as a string of characters, and is subject to natural language processing and analysis.

[0604] "Push notification" is a technology that allows messages and notifications to be sent instantly from the server to the user's device.

[0605] "Interface" refers to the contact points or means by which a user and a system interact with each other.

[0606] "Feedback" refers to reactions and opinions from users regarding particular information or services.

[0607] An "emotion engine" is a technology that analyzes text data and feedback and recognizes the emotions contained therein.

[0608] A "database" is a system for efficiently storing, managing, and retrieving data.

[0609] "Advertising Materials" means information content, such as text, images, and video, used to promote products and services.

[0610] A "report" is a document that summarizes collected data and analysis results, and provides organized information according to a specific purpose.

[0611] This invention describes a system that provides real-time information about local council discussions to citizens, recognizes user sentiment, and collects and analyzes feedback. This system is realized through the interaction of a server, terminals, and users.

[0612] Receiving and transcribing discussions

[0613] The server first receives real-time streaming from the local assembly. Specifically, it connects to the assembly's streaming URL using RTMP or HLS protocol to obtain audio / video data. This data is then sent to a speech recognition API such as Google Cloud Speech-to-Text or Amazon Transcribe, where the audio data is converted into text data.

[0614] Specific examples

[0615] Connect to the parliamentary streaming URL: http: / / example.com / stream using the RTMP protocol, obtain the audio data, and send it to the Google Cloud Speech-to-Text API.

[0616] Summary generation and summary delivery

[0617] The server analyzes the text data obtained from the speech recognition API and uses a generative AI model (e.g., OpenAI GPT-4) to summarize the text data. The summary extracts the main points of discussion and condenses them into short sentences.

[0618] Specific examples

[0619] Example prompt: Enter the following text data and summarize the main points of the discussion: Text: "{Congress discussion text}"

[0620] The generated summary is pushed to registered users' devices in real time using a notification service such as Firebase Cloud Messaging.

[0621] Gathering feedback and leveraging the emotion engine

[0622] The device displays the received summary on the screen and provides an interface where users can post "likes" and comments. The user's feedback is sent to the server, and the feedback data is input into the emotion engine. The emotion engine analyzes the feedback and generates emotion data (e.g., joy, sadness, anger, etc.).

[0623] Specific examples

[0624] Example prompt: Enter the following comment and analyze the sentiment: Comment: "{user comment}"

[0625] Data collection and analysis

[0626] The server records sentiment data and feedback data in a database and displays it in real time on an analysis dashboard, visualizing citizen opinions and reactions, allowing local assemblies and municipalities to understand citizen sentiment regarding the content of discussions.

[0627] Ad placement and optimization

[0628] The server displays advertisements for local stores and businesses when delivering summaries, and optimizes the display of advertisements based on the user's emotional data recognized by the emotion engine. Using the collected advertising data, reports can be generated for advertisers.

[0629] In this way, this system quickly and concisely conveys the contents of local assembly discussions to citizens, and by analyzing and utilizing user emotional data, promotes two-way communication between local governments and citizens.

[0630] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0631] Step 1:

[0632] Receive real-time discussions

[0633] The server connects to the local assembly's streaming URL via RTMP or HLS protocol and receives audio / video data in real time. This streaming data is the input, and the acquired audio / video data is the output. Specifically, the server connects to the streaming URL and receives assembly discussions in real time.

[0634] Specific actions

[0635] Connect to the streaming URL.

[0636] Retrieve audio data using the RTMP protocol.

[0637] Step 2:

[0638] Converting audio data to text

[0639] The server sends the acquired audio data to a speech recognition API (e.g., Google Cloud Speech-to-Text) and converts it into text data. This audio data is the input, and the converted text data is the output. Specifically, the server sends audio data to the API and receives text data from the API.

[0640] Specific actions

[0641] Send the audio data to the Google Cloud Speech-to-Text API.

[0642] Receive the generated text data.

[0643] Step 3:

[0644] Text data analysis and summary generation

[0645] The server inputs the text data obtained from the speech recognition API into a generative AI model (e.g., OpenAI GPT-4), extracts the main points of the discussion, and generates a summary. This text data is the input, and the generated summary is the output. Specifically, the server inputs the data along with the prompt "Please summarize this text" and generates a summary.

[0646] Specific actions

[0647] Input text data into GPT-4.

[0648] Set the prompt text.

[0649] Receive the output summary.

[0650] Step 4:

[0651] Summary Delivery

[0652] The server then pushes the generated summary to the registered user's device using a notification service such as Firebase Cloud Messaging. The summary is the input, and the pushed message is the output. Specifically, the summary is set as the body of the push notification and sent using the notification service.

[0653] Specific actions

[0654] Set the summary text as the body of the push notification.

[0655] Calls Firebase Cloud Messaging to send a notification to the user device.

[0656] Step 5:

[0657] Providing interaction functions

[0658] The device displays the received summary on the screen and provides an interface where the user can post likes and comments. This summary is the input, and the user's feedback is the output. Specifically, when the user opens the app, the latest summary text is displayed and feedback is possible.

[0659] Specific actions

[0660] Display summary text on screen.

[0661] Provide a "Like" button and a comment field.

[0662] Step 6:

[0663] Analysis by emotion engine

[0664] The server collects feedback data (likes and comments) from users and inputs it into the emotion engine to recognize emotions. This feedback data is the input, and the analyzed emotion data is the output. Specifically, the server sends the feedback data to the emotion engine and receives the emotion data.

[0665] Specific actions

[0666] Collect user comments and likes data.

[0667] Sending feedback data to the emotion engine.

[0668] Obtain emotion data.

[0669] Step 7:

[0670] Data collection and analysis

[0671] The server records the emotion data and feedback data in a database and reflects them in real time on the analysis dashboard. This emotion data and feedback data are the input, and the updated analysis dashboard is the output. Specifically, the server saves the data in the database and updates the dashboard.

[0672] Specific actions

[0673] Emotion data and feedback data are stored in a database.

[0674] Refresh your analytics dashboard.

[0675] Step 8:

[0676] Ad placement and optimization

[0677] The server displays local advertising materials when delivering summaries and optimizes the display of advertisements based on emotional data. The summaries and emotional data are input, and the optimized advertisement display is the output. Specifically, the server selects and displays appropriate advertisements along with the summaries.

[0678] Specific actions

[0679] Select ads that are suitable for the summary text.

[0680] Optimize your ads based on sentiment data.

[0681] Step 9:

[0682] Advertising effectiveness measurement and report generation

[0683] The server records the number of times the ad is displayed and the number of clicks, and generates an effectiveness measurement report for the advertiser. This advertising data is the input, and the generated report is the output. Specifically, data such as the number of times the ad is displayed and the click rate is collected, and reports are created periodically.

[0684] Specific actions

[0685] Record the number of impressions and clicks on your ads.

[0686] Generate reports to advertisers.

[0687] (Application example 2)

[0688] 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."

[0689] While the content of local assembly discussions is important information for citizens, it is difficult to grasp this information in real time, which has led to a decline in citizen participation and interest.In addition, when widely disseminating information about local assembly meetings to citizens, there is a need to effectively collect and analyze citizen opinions and emotions, and to optimize the provision of information and advertising display based on that information.

[0690] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving local assembly discussions in real time, means for converting the received discussions into text data using a generation AI and generating summaries, means for delivering the generated summaries to citizens' devices via push notifications, means for providing an interface for citizens to post "likes" and comments on the summaries, means for collecting and analyzing feedback from citizens, means for displaying local advertisements along with the summaries, means for generating reports for advertisers using the collected advertising data, means for inputting the feedback data into an emotion engine and analyzing citizen emotions, and means for optimizing advertisements using the emotion analysis data. This makes it possible to quickly and concisely communicate the content of local assembly discussions to citizens, effectively collect and analyze citizen opinions and emotions, promote communication between local governments and citizens, and optimize advertisements.

[0691] A "local assembly" is the decision-making body of a local government and the place where decisions are made by local public entities.

[0692] "Real time" refers to immediacy that corresponds to the timing of an event.

[0693] "Generative AI" refers to artificial intelligence that generates new data and information using natural language processing and machine learning techniques.

[0694] "Text data" refers to digital data that expresses information such as audio and video as a string of characters.

[0695] A "summary" is a short summary of the main points extracted from the original information.

[0696] A "terminal" is a device operated by a user, such as a smartphone or computer.

[0697] "Push notification" is a mechanism that automatically sends information from the server to the user's device.

[0698] An "interface" refers to the means or screen through which a user interacts with a system.

[0699] "Feedback" refers to the evaluations and opinions that users give to the system.

[0700] An "emotion engine" is a machine learning algorithm or technology that analyzes user feedback and behavior to recognize emotions.

[0701] "Local advertising" refers to advertising that promotes businesses or services related to a particular area.

[0702] "Advertiser" refers to a company or individual that places an advertisement.

[0703] A "report" is a document that compiles data and information.

[0704] "Emotion analysis data" refers to digital data generated as a result of analyzing a user's emotions.

[0705] "Optimization" means adjusting something to the most effective or efficient state depending on the conditions and purpose.

[0706] This invention is a system that provides citizens with real-time information about local assembly discussions and collects and analyzes their feedback by combining it with an emotion engine that recognizes users' emotions. This system is realized through the interaction of a server, terminals, and users.

[0707] The server receives local assembly discussions in real time. Specifically, it connects to the assembly's streaming URL and obtains audio / video data using the RTMP or HLS protocol. This data is then sent to a speech recognition API, which converts the speech into text data. Cloud-based speech recognition services such as Google Cloud Speech-to-Text and Amazon Transcribe are used for the speech recognition API. At this stage, the discussion content is stored as text data on the server.

[0708] The server then uses generative AI to analyze the acquired text data, extract key points of discussion, and generate a summary. For example, the generative AI uses an advanced natural language processing model (e.g., OpenAI GPT-4) to extract important sentences and keywords and summarize them into short sentences. This summary data is then stored on the server, ready to be sent to the user.

[0709] The generated summary is delivered to the user's device via push notification. The notification service uses Firebase Cloud Messaging (FCM). By using FCM, notifications can be sent to users in real time and the summary content can be displayed.

[0710] The user's device displays the received summary on the screen and provides an interface where the user can "like" or post comments. This interface is implemented as a mobile application, and includes a "like" button and a comment input field along with the summary text. Through this, users can input their own opinions and feelings in real time.

[0711] Furthermore, the server inputs feedback data from users into the emotion engine to analyze the user's emotions. The emotion engine analyzes the feedback (e.g., "likes" and comments) and generates emotion data (e.g., joy, sadness, anger, etc.). This emotion data is stored on the server and used for subsequent processing such as ad optimization.

[0712] The server also has the ability to display advertisements for local stores and businesses along with the summary. Based on the user's emotional data recognized by the emotion engine, the display of advertisements can be optimized. For example, a specific product advertisement can be displayed to a user who shows positive emotions, while a different advertisement can be displayed to a user who shows negative emotions.

[0713] The server records the number of times an advertisement is displayed and clicked, and periodically generates reports to advertisers. The reports include details such as the number of impressions, click-through rates, user distribution, and recognized emotion data. This allows advertisers to accurately understand the effectiveness of their advertisements and develop marketing strategies.

[0714] For example:

[0715] When a user receives a summary of a "local council's proposed new ordinance" and clicks "Like" on their smartphone, their behavior is collected and stored in a database as the user's positive emotion. The same user is then shown an advertisement featuring a new service from a relevant local store.

[0716] Example prompt sentence:

[0717] "Please summarize the latest discussions in the local council and notify users."

[0718] "Analyze user sentiment data and display the most appropriate ads."

[0719] As a result, it is possible to provide a system that can quickly and concisely convey the contents of discussions in local assemblies to citizens, effectively collect and analyze citizens' opinions and feelings, promote communication between local governments and citizens, and optimize advertising.

[0720] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0721] Step 1:

[0722] The server receives real-time local assembly discussions. Specifically, it connects to the assembly's streaming URL and obtains audio / video data using the RTMP or HLS protocol. Using this data as input, the server sends the data to a speech recognition API, which then obtains text data as output.

[0723] Step 2:

[0724] The server analyzes the acquired text data and generates a summary. Specifically, it uses generation AI to extract important sentences and keywords from the text data and summarize them into short sentences. The input here is text data, and the output is summarized text data.

[0725] Step 3:

[0726] The server sends the generated summary to the user's device via a push notification. The server uses Firebase Cloud Messaging (FCM) to send a push notification using the summarized text data as input, and the user's device receives the notification.

[0727] Step 4:

[0728] The device displays the received summary on the screen and provides an interface for users to "like" or post comments. Specifically, as a mobile application, a "like" button and a comment input field are displayed along with the summary text. The input is the summary text received via push notification, and the output is the interface operated by the user.

[0729] Step 5:

[0730] Users post "likes" and comments through the interface, which allows feedback data to be collected. The input is user actions (likes and comments), and the output is feedback data.

[0731] Step 6:

[0732] The server inputs feedback data from the user into the emotion engine and analyzes the user's emotions. Specifically, the emotion engine analyzes the feedback data and generates the user's emotion data (e.g., joy, sadness, anger, etc.). The input is the feedback data, and the output is the emotion data.

[0733] Step 7:

[0734] The server uses the sentiment analysis data to optimize advertisements. Specifically, it displays a specific product advertisement to users who show positive emotions and a different advertisement to users who show negative emotions. The input is the sentiment analysis data, and the output is the optimized advertisement.

[0735] Step 8:

[0736] The server records the number of times an ad is displayed and clicked, and periodically generates a report for the advertiser. Specifically, it aggregates the number of times an ad is displayed, the click rate, user distribution, recognized emotion data, etc., and generates the report. The input is the ad data, and the output is the report.

[0737] 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.

[0738] 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.

[0739] 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.

[0740] [Third embodiment]

[0741] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0742] 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.

[0743] 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).

[0744] 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.

[0745] 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.

[0746] 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).

[0747] 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.

[0748] 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.

[0749] 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.

[0750] 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.

[0751] 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.

[0752] 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."

[0753] This paper describes a system that provides local assembly discussions to citizens in real time, collects and analyzes their opinions on the discussions, and effectively distributes local advertisements. This system is realized through the interaction of a server, terminals, and users.

[0754] 1. Collection and text conversion of meeting minutes

[0755] The server receives real-time data from local assembly discussions. For example, it connects to the assembly's streaming URL and retrieves audio / video data using the RTMP or HLS protocol. The retrieved data is then converted into text data using a speech recognition API. For example, a cloud-based speech recognition service (e.g., Google Cloud Speech-to-Text) is used as the speech recognition API.

[0756] 2. Summary Generation

[0757] The server uses a generative AI to analyze the acquired text data, extract the main points of discussion, and generate a summary. For example, the generative AI uses an advanced natural language processing model (e.g., OpenAI GPT-4) to extract important sentences and keywords and summarize them in short sentences.

[0758] 3. Summary Delivery

[0759] The server delivers the generated summary to the citizen's device via push notification. For example, it uses a notification service (e.g., Firebase Cloud Messaging) to send real-time notifications to the device of a pre-registered user.

[0760] 4. Providing interaction functions

[0761] The device displays the received summary on the screen and provides an interface that allows users to "like" or post comments. As a concrete example, a "like" button and a comment input field are placed on the UI of a mobile application along with the summary text.

[0762] 5. Feedback collection and analysis

[0763] Users can click "Like" on a summary or enter and submit a comment. The server receives the feedback sent by users and stores it in a database. The feedback data is analyzed and reflected in real time on an analysis dashboard. Based on the analysis results, citizens' opinions and reactions are visualized.

[0764] 6. Display of advertisements

[0765] The server also sends advertisements for local stores and businesses when delivering the summary. For example, it can set up a system to display banner advertisements from local sponsors in designated ad slots. The advertisements are delivered along with the summary and displayed on the user's device.

[0766] 7. Measuring advertising effectiveness and generating reports

[0767] The server records the number of times the ad was displayed and the number of clicks, and periodically generates reports for the advertiser. For example, a weekly report compiling data such as the number of impressions, click-through rate, and regional response may be sent to the advertiser via email.

[0768] 8. User convenience

[0769] The terminal provides users with a display interface that allows for smooth operation. Users can express their interest in discussions in real time, increasing their motivation to participate in local government.

[0770] This system allows the contents of local assembly discussions to be communicated to citizens quickly and concisely, allowing for feedback to be reflected, while financial support can be provided through local advertising. This is expected to promote communication between local governments and citizens, and improve the transparency and citizen participation in local administration.

[0771] The processing flow will be explained below.

[0772] Step 1:

[0773] The server connects to the local council's streaming URL and retrieves audio / video data in real time, using the RTMP or HLS protocol for stable streaming.

[0774] Step 2:

[0775] The server sends the acquired audio data to a speech recognition API, which converts the audio data into text data. This speech recognition API uses cloud-based services such as Google Cloud Speech-to-Text and Amazon Transcribe.

[0776] Step 3:

[0777] The server inputs the generated text data into a generative AI, extracts key points of discussion, and generates a summary. The generative AI model uses OpenAI GPT-4 and other technologies, and uses natural language processing to extract important sentences and keywords.

[0778] Step 4:

[0779] The server sends the generated summary to registered users' devices via push notification, using a push notification service such as Firebase Cloud Messaging to deliver notifications to users' mobile devices in real time.

[0780] Step 5:

[0781] The device displays the received summary on the screen. Along with the summary text, it also provides an interface where users can post "likes" and comments. This interface includes a "like" button and a comment input field below the summary.

[0782] Step 6:

[0783] Users can publish their feedback by clicking the "Like" button on the summary or by entering a comment and clicking the submit button.

[0784] Step 7:

[0785] The server receives feedback from users (likes and comments) and records it in a database. This allows users' reactions and opinions to be collected and stored as data.

[0786] Step 8:

[0787] The server analyzes the collected feedback data and displays it in real time on an analytical dashboard, allowing users to instantly grasp the situation of local governments and councils.

[0788] Step 9:

[0789] The server sends advertisements along with the summary delivery. Advertisements from local stores and businesses are registered in the system and set to be displayed in designated ad slots.

[0790] Step 10:

[0791] The terminal displays local advertisements along with summary text, which the user can view and follow links to if desired.

[0792] Step 11:

[0793] The server records the number of times the advertisement is displayed and the number of clicks in a database and periodically generates a report for the advertiser, which summarizes data such as the number of times the advertisement is displayed, the click rate, and the user distribution, and provides the report to the advertiser.

[0794] Through these steps, a system will be created that provides citizens with real-time information about local assembly discussions, collects and analyzes citizen feedback, and delivers effective advertising.

[0795] Example 1

[0796] 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."

[0797] Traditional media and websites lack the real-time capabilities to quickly and concisely communicate the contents of local assembly discussions to citizens. It is also difficult to effectively collect and analyze citizen feedback, and to appropriately deliver advertisements for local businesses. A system that can solve these issues is needed.

[0798] 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.

[0799] In this invention, the server includes a means for receiving local assembly discussions in real time, a means for converting the received discussions into text data using a generation AI to generate summaries, and a means for delivering the generated summaries to citizens' devices via push notifications. This allows citizens to quickly and concisely understand the content of local assembly discussions and provide feedback on the content in real time. Furthermore, the effective delivery of local advertisements contributes to revitalizing the local economy.

[0800] "Local assembly discussions" refers to various debates and deliberations held in local government assemblies.

[0801] "Real-time receiving means" refers to devices or software that have the ability to simultaneously obtain data about ongoing discussions or debates.

[0802] "Generative AI" refers to artificial intelligence that uses machine learning models and algorithms to generate specific information from input data.

[0803] "Means for converting into text data" refers to the technology or method for converting data acquired in the form of audio, video, etc. into text information.

[0804] A "summary generation method" refers to a process or system that extracts important information from long text data and presents it in a compact form.

[0805] "Citizen's device" refers to an electronic device such as a personal computer, smartphone or tablet that a citizen uses to receive and display local council information.

[0806] "Means of delivering push notifications" refers to technology that notifies users of information in real time or at a specified time.

[0807] "Interface" refers to the screen and input / output means that allow a user to interact with and operate a system.

[0808] "Means for collecting and analyzing feedback" refers to the techniques and processes used to receive user opinions and responses and analyze that data.

[0809] "Local advertising" refers to advertising that promotes products, services, events, etc. that are relevant to a particular geographic area.

[0810] "Advertiser" refers to a company or individual that places an advertisement.

[0811] "Means for generating reports" means the process or system that generates reports or analyses based on the collected data and that are periodically sent to advertisers.

[0812] This invention relates to a system that provides local assembly discussions to citizens in real time, collects and analyzes their opinions on the discussions, and effectively distributes local advertisements. This system is realized through the interaction of a server, terminals, and users.

[0813] First, the server receives the local assembly discussions in real time. This involves connecting to the local assembly's streaming URL and obtaining the audio / video data using the RTMP or HLS protocol. The obtained data is then converted into text data using a speech recognition API (e.g., Google Cloud Speech-to-Text).

[0814] The server then analyzes the acquired text data using generative AI, extracts key discussion points, and generates a summary. Specifically, it uses a generative AI model (e.g., OpenAI GPT-4). An example of a prompt for generating a summary is "Please summarize the following minutes:"

[0815] The generated summary is delivered to the citizen's device via a push notification by the server. These notifications are sent using Firebase Cloud Messaging. An example of the push notification content is "A new discussion summary is available."

[0816] The device displays the received summary to the user and provides an interface that allows the user to "like" or comment, including by placing a "like" button and a comment input field along with the summary text in the user interface of the mobile application.

[0817] Users can click "Like" on the summary or enter and submit a comment. The server receives the feedback submitted by users and stores it in a database (e.g., MySQL). The collected feedback data is analyzed in real time and displayed on an analysis dashboard. For the analysis, an analysis tool such as Tableau is used.

[0818] In addition, the server also sends advertisements for local businesses and stores along with the summary. The advertisements are set to be displayed as banner advertisements for local sponsors in designated ad slots. This allows the advertisements to be displayed on the user's device along with the summary.

[0819] The server also handles ad performance measurement and reporting. It records the number of ad impressions and clicks, and periodically generates weekly reports for advertisers. The reports include data such as impressions, click-through rates, and geographic response, and are sent to advertisers via email.

[0820] Finally, the device provides users with a display interface that allows for smooth operation, allowing them to reflect their interest in local assembly discussions in real time, increasing their motivation to participate in local government.

[0821] By combining these functions, it is possible to quickly and concisely convey the contents of local assembly discussions to citizens, incorporate their feedback, and provide financial support through local advertising. This is expected to promote communication between local governments and citizens, and improve the transparency and citizen participation of local government administration.

[0822] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0823] Step 1:

[0824] The server connects to the local council's live streaming URL and receives audio / video data using the RTMP or HLS protocol. Specifically, it retrieves data from the streaming URL (e.g., http: / / example-streaming-url.com) and calls a speech recognition API (e.g., Google Cloud Speech-to-Text) to convert the audio data into text data.

[0825] Input: Audio / video data via streaming URL

[0826] Output: Text data

[0827] Step 2:

[0828] The server inputs the converted text data into a generative AI model, extracts key discussion points, and generates a summary. Specifically, the server inputs the following prompt into the generative AI model (e.g., OpenAI GPT-4): "Please summarize the following minutes: 'Text data'." The server then saves the generated summary.

[0829] Input: Text data

[0830] Output: Summary data

[0831] Step 3:

[0832] The server uses Firebase Cloud Messaging to deliver the generated summary to citizens' devices via push notification. Specifically, it uses the Firebase Cloud Messaging API to send the summary along with the message "A new discussion summary is available."

[0833] Input: Summary data and user information

[0834] Output: Push notification sent

[0835] Step 4:

[0836] The device displays the received summary to the user and provides an interface that allows the user to "like" or post a comment. Specifically, a "like" button and a comment input field are placed on the UI of the mobile application along with the summary text, allowing the user to use these interfaces.

[0837] Input: Summary data

[0838] Output: User interface

[0839] Step 5:

[0840] Users can click "Like" on the displayed summary or enter and submit a comment. The server receives the feedback and stores it in a database. Specifically, it collects user feedback data (likes and comments) and stores them in a MySQL database.

[0841] Input: User feedback data

[0842] Output: Feedback data stored in a database

[0843] Step 6:

[0844] The server analyzes the collected feedback data in real time. Specifically, it uses an analytical tool (e.g., Tableau) to analyze the feedback data and display it on a dashboard. This analysis visualizes citizens' opinions and reactions.

[0845] Input: Feedback data

[0846] Output: Dashboard display of analysis results

[0847] Step 7:

[0848] The server selects advertising data and distributes it together with the summary in order to transmit advertisements of local sponsors together with the summary. Specifically, the server sets banner advertisements of local sponsors in designated advertising spaces and displays them on the user's terminal together with the summary.

[0849] Input: Summary data and advertising data

[0850] Output: Summary and advertisements displayed on the user's device

[0851] Step 8:

[0852] The server records the number of times an ad is displayed and clicked, and compiles this data into a report that is sent to the advertiser periodically. Specifically, a weekly report is generated, compiling data such as the number of impressions, click-through rates, and regional responses, and sending it to the advertiser via email.

[0853] Input: Ad impressions and click data

[0854] Output: Report sent to advertiser

[0855] (Application example 1)

[0856] 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."

[0857] There is a lack of means to quickly and effectively communicate the contents of discussions in local assemblies to citizens, as well as to instantly collect and reflect citizen opinions. Furthermore, there is a need for a system that will facilitate smooth communication and economic activity between local governments, citizens, and local businesses by effectively distributing local advertising in conjunction with the information provided to citizens.

[0858] 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.

[0859] In this invention, the server includes: means for receiving local assembly discussions in real time; means for converting the received discussions into text data using a generative AI and generating summaries; means for distributing the generated summaries to citizens' devices via push notifications; means for providing an interface for citizens to post "likes" and comments on the summaries; means for collecting and analyzing feedback from citizens; means for displaying local advertisements along with the summaries; means for generating reports for advertisers using the collected advertisement data; means for live displaying streaming data on citizens' devices; means for collecting comments in real time based on the live-displayed discussions; and means for analyzing the collected comment data and summarizing using a generative AI model. This makes it possible to communicate the content of local assembly discussions to citizens in real time, immediately reflect citizen feedback, and effectively distribute local advertisements.

[0860] A "local assembly" is the legislative body of a local government, and is the body that deliberates and decides on important policies and budgets of local public entities.

[0861] "Real time" is a term that describes things happening nearly simultaneously or with very little delay.

[0862] "Generative AI" refers to artificial intelligence technology that automatically learns and generates text, audio, images, etc.

[0863] "Text data" is a data format consisting of characters and words, and is data that contains character strings that can be processed by a computer.

[0864] A "summary" is a short summary of the original content, intended to convey the main points concisely.

[0865] "Push notification" is a technology that sends information from a server to a user's device in real time, allowing the user to receive the information without taking any specific action.

[0866] "Interface" refers to the means and screen layout by which a user interacts with a system or application.

[0867] "Feedback" refers to reactions and opinions collected from users, and is information that is useful for improving and evaluating a system.

[0868] "Local advertising" refers to promotional activities of stores and businesses related to a specific area, and is advertising targeted at people living in that area.

[0869] "Streaming data" refers to audio and video data that is distributed in real time over the Internet.

[0870] "Live display" refers to displaying data or video to viewers in real time.

[0871] "Comment data" refers to opinions and impressions entered by users in text format.

[0872] A "generative AI model" is an algorithm that automatically generates text, audio, images, etc. using technologies such as machine learning and deep learning.

[0873] This invention includes a system that provides citizens with real-time information about local assembly discussions, collects and analyzes their opinions on the content, and effectively distributes local advertisements. This system is realized through the interaction of a server, terminals, and users.

[0874] First, the server receives the local assembly discussions in real time by connecting to the local assembly's streaming URL using the RTMP or HLS protocol. The received audio / video data is converted into text data using a speech recognition API (e.g., Google Cloud Speech-to-Text).

[0875] The server then uses a generative AI to analyze the converted text data, extract key discussion points, and generate a summary. The generative AI uses an advanced natural language processing model such as OpenAI GPT-4. For example, it uses the following prompt:

[0876] "Summarize the following text:\nThe council discussed a new public works project to build a new park in District A. This proposal has many merits..."

[0877] The generated summary is delivered to the citizen's device via a push notification from the server using a notification service such as Firebase Cloud Messaging. Citizens receive the summary on their device and are provided with an interface where they can "like" or post comments.

[0878] Next, citizen feedback is sent to a server and stored in a database. This feedback data is then reflected in a real-time analysis dashboard, visualizing citizen opinions and reactions.

[0879] Furthermore, the server also transmits local advertisements when delivering the summary. For example, it is set to display banner advertisements of local sponsors in the advertisement space. The advertisements are delivered together with the summary and displayed on the user's terminal.

[0880] Finally, the server records the number of impressions and clicks on the ads and periodically generates reports for the advertiser, summarizing data such as impressions, click-through rates, and geographic response, which are emailed to the advertiser.

[0881] This system allows the contents of local council discussions to be communicated to citizens quickly and concisely, allows for the collection and analysis of feedback from citizens, and promotes communication between local governments, citizens, and local businesses by effectively distributing local advertisements.

[0882] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0883] Step 1:

[0884] The server receives the local assembly discussions in real time by connecting to the local assembly's streaming URL using the RTMP or HLS protocol. The input data is an audio / video stream, and the output data is audio data for speech recognition.

[0885] Step 2:

[0886] The server converts the received audio data into text data using a speech recognition API (e.g., Google Cloud Speech-to-Text). The input data is audio data, and the output data is text data. In this step, the audio signal is analyzed and converted into text as a string.

[0887] Step 3:

[0888] The server uses a generative AI (e.g., OpenAI GPT-4) to analyze the converted text data, extract key discussion points, and generate a summary. The input data is the converted text data, and the output data is the summarized text. Specifically, the text data is input to the generative AI model, and the following prompt sentence is used:

[0889] "Summarize the following text:\nThe council discussed a new public works project to build a new park in District A. This proposal has many merits..."

[0890] Step 4:

[0891] The server delivers the generated summary to the citizen's device via a push notification. The input data is the summarized text, and the output data is a push notification sent to the citizen's device. This push notification uses a notification service such as Firebase Cloud Messaging. The summary is then displayed on the user's device.

[0892] Step 5:

[0893] The device displays the received summary on the screen and provides an interface where users can "like" or comment. The input data is a push notification from the server, and the output data is the user's feedback. Specifically, the device displays the summary text along with a "like" button and a comment input field.

[0894] Step 6:

[0895] The user clicks "Like" on the summary or enters a comment and submits it. The input data is the user's feedback, and the output data is the feedback data sent to the server.

[0896] Step 7:

[0897] The server receives the feedback sent by the user and stores it in a database. The input data is the feedback data, and the output data is the stored database entry. In this step, the feedback data is analyzed and reflected in the analysis dashboard in real time.

[0898] Step 8:

[0899] The server also sends local advertisements when delivering the summary. The input data is the summarized text and advertisement data, and the output data is the summary with advertisements sent to the citizen's device. Specifically, a banner advertisement from a local sponsor is displayed in the designated advertisement space.

[0900] Step 9:

[0901] The server records the number of times the ad was viewed and clicked, and periodically generates a report for the advertiser. The input data is the ad view and click data, and the output data is the generated report. This report compiles data such as the number of views, click rates, and regional responses.

[0902] 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.

[0903] This paper describes a system that provides citizens with real-time information about local assembly discussions and collects and analyzes their feedback by combining it with an emotion engine that recognizes users' emotions. This system is realized through the interaction of a server, terminals, and users.

[0904] 1. Collection and text conversion of meeting minutes

[0905] The server receives real-time data from local assembly discussions. For example, it connects to the assembly's streaming URL and retrieves audio / video data using the RTMP or HLS protocol. This data is then sent to a speech recognition API, which converts the speech into text. Cloud-based services such as Google Cloud Speech-to-Text and Amazon Transcribe are used for the speech recognition API.

[0906] 2. Summary Generation

[0907] The server uses generative AI to analyze the acquired text data, extract the main points of discussion, and generate a summary. For example, the generative AI uses an advanced natural language processing model (e.g., OpenAI GPT-4) to extract important sentences and keywords and summarize them in short sentences.

[0908] 3. Summary Delivery

[0909] The server sends the generated summary to the registered user's device as a push notification, for example, by using a notification service (e.g., Firebase Cloud Messaging) to deliver the notification in real time.

[0910] 4. Providing interaction functions

[0911] The device displays the received summary on the screen and provides an interface that allows users to "like" or post comments. As a concrete example, a "like" button and a comment input field are placed on the UI of a mobile application along with the summary text.

[0912] 5. Leveraging Emotional Engines

[0913] The server inputs the feedback data from the user into the emotion engine to recognize the user's emotions. The emotion engine analyzes the feedback (e.g., "likes" and comments) and generates emotion data (e.g., joy, sadness, anger, etc.).

[0914] 6. Feedback Collection and Analysis

[0915] The server records the recognized emotion data and feedback data in a database and displays it in real time on an analysis dashboard, visualizing citizens' opinions and reactions and enabling local assemblies and municipalities to understand citizens' feelings toward the content of discussions.

[0916] 7. Display and optimization of advertisements

[0917] The server displays advertisements for local stores and businesses when delivering summaries. Furthermore, it optimizes the display of advertisements based on the user's emotional data recognized by the emotion engine. For example, it can display a specific product advertisement to a user who shows positive emotions, and a different advertisement to a user who shows negative emotions.

[0918] 8. Advertising effectiveness measurement and report generation

[0919] The server records the number of impressions and clicks on the ads and periodically generates reports to the advertisers, which can include details such as impressions, click-through rates, user distribution, and recognized emotion data.

[0920] 9. User convenience

[0921] The terminal provides users with a display interface, allowing for smooth operation. Users can express their feelings and opinions on discussions in real time, increasing their willingness to participate in local government.

[0922] This system quickly and concisely conveys the contents of local assembly discussions to citizens, recognizes user sentiment and reflects their feedback, and provides financial support through local advertising. This is expected to promote communication between local governments and citizens, and improve transparency and citizen participation in local government administration.

[0923] The processing flow will be explained below.

[0924] Step 1:

[0925] The server connects to the local council's streaming URL and retrieves audio / video data in real time, maintaining stable streaming using RTMP or HLS protocols.

[0926] Step 2:

[0927] The server sends the acquired audio data to a speech recognition API, which converts the audio into text data in real time. For example, by using Google Cloud Speech-to-Text, highly accurate text conversion is possible.

[0928] Step 3:

[0929] The server analyzes the text data using generative AI, extracts key points of discussion, and generates summaries using natural language processing techniques such as OpenAI GPT-4 to extract important keywords and sentences.

[0930] Step 4:

[0931] The server then sends the generated summary to registered users' devices via push notification, using a push notification service such as Firebase Cloud Messaging to deliver the notification in real time.

[0932] Step 5:

[0933] The device displays the received summary on the screen and provides an interface with a "Like" button and a comment field to allow users to easily provide feedback.

[0934] Step 6:

[0935] Users can post feedback by clicking the "Like" button on the summary or by entering text in the comment field and clicking the submit button.

[0936] Step 7:

[0937] The server receives the feedback from the users and stores it in a database, thereby effectively managing the collected feedback data.

[0938] Step 8:

[0939] The server inputs the feedback data from the user into the emotion engine, which analyzes this data and recognizes the user's emotions (e.g., joy, sadness, anger).

[0940] Step 9:

[0941] The server records the recognized emotion data along with feedback data in a database, which is then reflected in a real-time analytics dashboard, allowing local councils and municipalities to visually understand citizen sentiment.

[0942] Step 10:

[0943] The server sends local ads along with the digests. The ads are optimized based on the emotional data recognized by the emotion engine. For example, a specific ad can be shown to users who show positive emotions, and a different ad can be shown to users who show negative emotions.

[0944] Step 11:

[0945] The terminal displays the advertisement along with the summary on the screen. The user can view the advertisement and click on the link if they are interested.

[0946] Step 12:

[0947] The server records the number of times an ad is displayed and clicked, and stores the data in a database. It periodically generates reports for advertisers to report on the effectiveness of their ads. The reports include the number of times an ad is displayed, click-through rates, and user sentiment data.

[0948] The above processing steps create a system that provides citizens with the content of local assembly discussions in real time, utilizes an emotion engine to collect and analyze citizen feedback, and provides optimized advertisements.

[0949] Example 2

[0950] 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."

[0951] The topics discussed in local assemblies are diverse, making it extremely difficult for citizens to understand everything. Furthermore, the lack of real-time information on discussions undermines the transparency of assemblies, leading to a decline in citizen interest and willingness to participate. Furthermore, the lack of means to instantly collect and analyze citizen feedback leads to a lack of two-way communication between the government and citizens. Conventional systems make it difficult to provide citizens with real-time information on local assembly discussions and effectively collect and analyze their reactions and opinions.

[0952] 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.

[0953] In this invention, the server includes: means for receiving local assembly discussions in real time; means for converting the acquired audio data into text data using a speech recognition API; and means for analyzing the received text data using a generation AI to generate summaries. This enables the contents of local assembly discussions to be quickly organized and summarized and provided to citizens. The server also includes means for delivering the generated summaries to citizens' devices via push notifications; means for providing an interface for citizens to post "likes" and comments on the summaries; means for using an emotion engine to collect and analyze feedback from citizens; and means for recording the analyzed emotion data and feedback data in a database. This enables the collection and analysis of citizen reactions in real time, enabling two-way communication between the government and citizens. The server also includes means for displaying advertising materials along with the summaries and means for generating reports for advertisers using the collected advertising data. This allows advertising revenue to be utilized to support system operations.

[0954] "Discussion" refers to the act of local assembly members and stakeholders exchanging opinions and making decisions about specific issues or policies.

[0955] "Real-time" refers to a situation in which data is processed and information is communicated almost simultaneously as the discussion progresses.

[0956] "Means" refers to the methods or techniques used to achieve a particular goal.

[0957] "Generative AI" is an artificial intelligence that performs natural language processing, and is a technology that has the ability to analyze and learn from large amounts of text data and generate summaries and new text.

[0958] A "speech recognition API" is an application programming interface that accepts voice data as input and converts it into text data.

[0959] "Text data" refers to digital information expressed as a string of characters, and is subject to natural language processing and analysis.

[0960] "Push notification" is a technology that allows messages and notifications to be sent instantly from the server to the user's device.

[0961] "Interface" refers to the contact points or means by which a user and a system interact with each other.

[0962] "Feedback" refers to reactions and opinions from users regarding particular information or services.

[0963] An "emotion engine" is a technology that analyzes text data and feedback and recognizes the emotions contained therein.

[0964] A "database" is a system for efficiently storing, managing, and retrieving data.

[0965] "Advertising Materials" means information content, such as text, images, and video, used to promote products and services.

[0966] A "report" is a document that summarizes collected data and analysis results, and provides organized information according to a specific purpose.

[0967] This invention describes a system that provides real-time information about local council discussions to citizens, recognizes user sentiment, and collects and analyzes feedback. This system is realized through the interaction of a server, terminals, and users.

[0968] Receiving and transcribing discussions

[0969] The server first receives real-time streaming from the local assembly. Specifically, it connects to the assembly's streaming URL using RTMP or HLS protocol to obtain audio / video data. This data is then sent to a speech recognition API such as Google Cloud Speech-to-Text or Amazon Transcribe, where the audio data is converted into text data.

[0970] Specific examples

[0971] Connect to the parliamentary streaming URL: http: / / example.com / stream using the RTMP protocol, obtain the audio data, and send it to the Google Cloud Speech-to-Text API.

[0972] Summary generation and summary delivery

[0973] The server analyzes the text data obtained from the speech recognition API and uses a generative AI model (e.g., OpenAI GPT-4) to summarize the text data. The summary extracts the main points of discussion and condenses them into short sentences.

[0974] Specific examples

[0975] Example prompt: Enter the following text data and summarize the main points of the discussion: Text: "{Congress discussion text}"

[0976] The generated summary is pushed to registered users' devices in real time using a notification service such as Firebase Cloud Messaging.

[0977] Gathering feedback and leveraging the emotion engine

[0978] The device displays the received summary on the screen and provides an interface where users can post "likes" and comments. The user's feedback is sent to the server, and the feedback data is input into the emotion engine. The emotion engine analyzes the feedback and generates emotion data (e.g., joy, sadness, anger, etc.).

[0979] Specific examples

[0980] Example prompt: Enter the following comment and analyze the sentiment: Comment: "{user comment}"

[0981] Data collection and analysis

[0982] The server records sentiment data and feedback data in a database and displays it in real time on an analysis dashboard, visualizing citizen opinions and reactions, allowing local assemblies and municipalities to understand citizen sentiment regarding the content of discussions.

[0983] Ad placement and optimization

[0984] The server displays advertisements for local stores and businesses when delivering summaries, and optimizes the display of advertisements based on the user's emotional data recognized by the emotion engine. Using the collected advertising data, reports can be generated for advertisers.

[0985] In this way, this system quickly and concisely conveys the contents of local assembly discussions to citizens, and by analyzing and utilizing user emotional data, promotes two-way communication between local governments and citizens.

[0986] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0987] Step 1:

[0988] Receive real-time discussions

[0989] The server connects to the local assembly's streaming URL via RTMP or HLS protocol and receives audio / video data in real time. This streaming data is the input, and the acquired audio / video data is the output. Specifically, the server connects to the streaming URL and receives assembly discussions in real time.

[0990] Specific actions

[0991] Connect to the streaming URL.

[0992] Retrieve audio data using the RTMP protocol.

[0993] Step 2:

[0994] Converting audio data to text

[0995] The server sends the acquired audio data to a speech recognition API (e.g., Google Cloud Speech-to-Text) and converts it into text data. This audio data is the input, and the converted text data is the output. Specifically, the server sends audio data to the API and receives text data from the API.

[0996] Specific actions

[0997] Send the audio data to the Google Cloud Speech-to-Text API.

[0998] Receive the generated text data.

[0999] Step 3:

[1000] Text data analysis and summary generation

[1001] The server inputs the text data obtained from the speech recognition API into a generative AI model (e.g., OpenAI GPT-4), extracts the main points of the discussion, and generates a summary. This text data is the input, and the generated summary is the output. Specifically, the server inputs the data along with the prompt "Please summarize this text" and generates a summary.

[1002] Specific actions

[1003] Input text data into GPT-4.

[1004] Set the prompt text.

[1005] Receive the output summary.

[1006] Step 4:

[1007] Summary Delivery

[1008] The server then pushes the generated summary to the registered user's device using a notification service such as Firebase Cloud Messaging. The summary is the input, and the pushed message is the output. Specifically, the summary is set as the body of the push notification and sent using the notification service.

[1009] Specific actions

[1010] Set the summary text as the body of the push notification.

[1011] Calls Firebase Cloud Messaging to send a notification to the user device.

[1012] Step 5:

[1013] Providing interaction functions

[1014] The device displays the received summary on the screen and provides an interface where the user can post likes and comments. This summary is the input, and the user's feedback is the output. Specifically, when the user opens the app, the latest summary text is displayed and feedback is possible.

[1015] Specific actions

[1016] Display summary text on screen.

[1017] Provide a "Like" button and a comment field.

[1018] Step 6:

[1019] Analysis by emotion engine

[1020] The server collects feedback data (likes and comments) from users and inputs it into the emotion engine to recognize emotions. This feedback data is the input, and the analyzed emotion data is the output. Specifically, the server sends the feedback data to the emotion engine and receives the emotion data.

[1021] Specific actions

[1022] Collect user comments and likes data.

[1023] Sending feedback data to the emotion engine.

[1024] Obtain emotion data.

[1025] Step 7:

[1026] Data collection and analysis

[1027] The server records the emotion data and feedback data in a database and reflects them in real time on the analysis dashboard. This emotion data and feedback data are the input, and the updated analysis dashboard is the output. Specifically, the server saves the data in the database and updates the dashboard.

[1028] Specific actions

[1029] Emotion data and feedback data are stored in a database.

[1030] Refresh your analytics dashboard.

[1031] Step 8:

[1032] Ad placement and optimization

[1033] The server displays local advertising materials when delivering summaries and optimizes the display of advertisements based on emotional data. The summaries and emotional data are input, and the optimized advertisement display is the output. Specifically, the server selects and displays appropriate advertisements along with the summaries.

[1034] Specific actions

[1035] Select ads that are suitable for the summary text.

[1036] Optimize your ads based on sentiment data.

[1037] Step 9:

[1038] Advertising effectiveness measurement and report generation

[1039] The server records the number of times the ad is displayed and the number of clicks, and generates an effectiveness measurement report for the advertiser. This advertising data is the input, and the generated report is the output. Specifically, data such as the number of times the ad is displayed and the click rate is collected, and reports are created periodically.

[1040] Specific actions

[1041] Record the number of impressions and clicks on your ads.

[1042] Generate reports to advertisers.

[1043] (Application example 2)

[1044] 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."

[1045] While the content of local assembly discussions is important information for citizens, it is difficult to grasp this information in real time, which has led to a decline in citizen participation and interest.In addition, when widely disseminating information about local assembly meetings to citizens, there is a need to effectively collect and analyze citizen opinions and emotions, and to optimize the provision of information and advertising display based on that information.

[1046] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving local assembly discussions in real time, means for converting the received discussions into text data using a generation AI and generating summaries, means for delivering the generated summaries to citizens' devices via push notifications, means for providing an interface for citizens to post "likes" and comments on the summaries, means for collecting and analyzing feedback from citizens, means for displaying local advertisements along with the summaries, means for generating reports for advertisers using the collected advertising data, means for inputting the feedback data into an emotion engine and analyzing citizen emotions, and means for optimizing advertisements using the emotion analysis data. This makes it possible to quickly and concisely communicate the content of local assembly discussions to citizens, effectively collect and analyze citizen opinions and emotions, promote communication between local governments and citizens, and optimize advertisements.

[1047] A "local assembly" is the decision-making body of a local government and the place where decisions are made by local public entities.

[1048] "Real time" refers to immediacy that corresponds to the timing of an event.

[1049] "Generative AI" refers to artificial intelligence that generates new data and information using natural language processing and machine learning techniques.

[1050] "Text data" refers to digital data that expresses information such as audio and video as a string of characters.

[1051] A "summary" is a short summary of the main points extracted from the original information.

[1052] A "terminal" is a device operated by a user, such as a smartphone or computer.

[1053] "Push notification" is a mechanism that automatically sends information from the server to the user's device.

[1054] An "interface" refers to the means or screen through which a user interacts with a system.

[1055] "Feedback" refers to the evaluations and opinions that users give to the system.

[1056] An "emotion engine" is a machine learning algorithm or technology that analyzes user feedback and behavior to recognize emotions.

[1057] "Local advertising" refers to advertising that promotes businesses or services related to a particular area.

[1058] "Advertiser" refers to a company or individual that places an advertisement.

[1059] A "report" is a document that compiles data and information.

[1060] "Emotion analysis data" refers to digital data generated as a result of analyzing a user's emotions.

[1061] "Optimization" means adjusting something to the most effective or efficient state depending on the conditions and purpose.

[1062] This invention is a system that provides citizens with real-time information about local assembly discussions and collects and analyzes their feedback by combining it with an emotion engine that recognizes users' emotions. This system is realized through the interaction of a server, terminals, and users.

[1063] The server receives local assembly discussions in real time. Specifically, it connects to the assembly's streaming URL and obtains audio / video data using the RTMP or HLS protocol. This data is then sent to a speech recognition API, which converts the speech into text data. Cloud-based speech recognition services such as Google Cloud Speech-to-Text and Amazon Transcribe are used for the speech recognition API. At this stage, the discussion content is stored as text data on the server.

[1064] The server then uses generative AI to analyze the acquired text data, extract key points of discussion, and generate a summary. For example, the generative AI uses an advanced natural language processing model (e.g., OpenAI GPT-4) to extract important sentences and keywords and summarize them into short sentences. This summary data is then stored on the server, ready to be sent to the user.

[1065] The generated summary is delivered to the user's device via push notification. The notification service uses Firebase Cloud Messaging (FCM). By using FCM, notifications can be sent to users in real time and the summary content can be displayed.

[1066] The user's device displays the received summary on the screen and provides an interface where the user can "like" or post comments. This interface is implemented as a mobile application, and includes a "like" button and a comment input field along with the summary text. Through this, users can input their own opinions and feelings in real time.

[1067] Furthermore, the server inputs feedback data from users into the emotion engine to analyze the user's emotions. The emotion engine analyzes the feedback (e.g., "likes" and comments) and generates emotion data (e.g., joy, sadness, anger, etc.). This emotion data is stored on the server and used for subsequent processing such as ad optimization.

[1068] The server also has the ability to display advertisements for local stores and businesses along with the summary. Based on the user's emotional data recognized by the emotion engine, the display of advertisements can be optimized. For example, a specific product advertisement can be displayed to a user who shows positive emotions, while a different advertisement can be displayed to a user who shows negative emotions.

[1069] The server records the number of times an advertisement is displayed and clicked, and periodically generates reports to advertisers. The reports include details such as the number of impressions, click-through rates, user distribution, and recognized emotion data. This allows advertisers to accurately understand the effectiveness of their advertisements and develop marketing strategies.

[1070] For example:

[1071] When a user receives a summary of a "local council's proposed new ordinance" and clicks "Like" on their smartphone, their behavior is collected and stored in a database as the user's positive emotion. The same user is then shown an advertisement featuring a new service from a relevant local store.

[1072] Example prompt sentence:

[1073] "Please summarize the latest discussions in the local council and notify users."

[1074] "Analyze user sentiment data and display the most appropriate ads."

[1075] As a result, it is possible to provide a system that can quickly and concisely convey the contents of discussions in local assemblies to citizens, effectively collect and analyze citizens' opinions and feelings, promote communication between local governments and citizens, and optimize advertising.

[1076] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1077] Step 1:

[1078] The server receives real-time local assembly discussions. Specifically, it connects to the assembly's streaming URL and obtains audio / video data using the RTMP or HLS protocol. Using this data as input, the server sends the data to a speech recognition API, which then obtains text data as output.

[1079] Step 2:

[1080] The server analyzes the acquired text data and generates a summary. Specifically, it uses generation AI to extract important sentences and keywords from the text data and summarize them into short sentences. The input here is text data, and the output is summarized text data.

[1081] Step 3:

[1082] The server sends the generated summary to the user's device via a push notification. The server uses Firebase Cloud Messaging (FCM) to send a push notification using the summarized text data as input, and the user's device receives the notification.

[1083] Step 4:

[1084] The device displays the received summary on the screen and provides an interface for users to "like" or post comments. Specifically, as a mobile application, a "like" button and a comment input field are displayed along with the summary text. The input is the summary text received via push notification, and the output is the interface operated by the user.

[1085] Step 5:

[1086] Users post "likes" and comments through the interface, which allows feedback data to be collected. The input is user actions (likes and comments), and the output is feedback data.

[1087] Step 6:

[1088] The server inputs feedback data from the user into the emotion engine and analyzes the user's emotions. Specifically, the emotion engine analyzes the feedback data and generates the user's emotion data (e.g., joy, sadness, anger, etc.). The input is the feedback data, and the output is the emotion data.

[1089] Step 7:

[1090] The server uses the sentiment analysis data to optimize advertisements. Specifically, it displays a specific product advertisement to users who show positive emotions and a different advertisement to users who show negative emotions. The input is the sentiment analysis data, and the output is the optimized advertisement.

[1091] Step 8:

[1092] The server records the number of times an ad is displayed and clicked, and periodically generates a report for the advertiser. Specifically, it aggregates the number of times an ad is displayed, the click rate, user distribution, recognized emotion data, etc., and generates the report. The input is the ad data, and the output is the report.

[1093] 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.

[1094] 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.

[1095] 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.

[1096] [Fourth embodiment]

[1097] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1098] 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.

[1099] 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).

[1100] 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.

[1101] 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.

[1102] 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).

[1103] 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.

[1104] 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.

[1105] 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.

[1106] 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.

[1107] 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.

[1108] 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.

[1109] 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."

[1110] This paper describes a system that provides local assembly discussions to citizens in real time, collects and analyzes their opinions on the discussions, and effectively distributes local advertisements. This system is realized through the interaction of a server, terminals, and users.

[1111] 1. Collection and text conversion of meeting minutes

[1112] The server receives real-time data from local assembly discussions. For example, it connects to the assembly's streaming URL and retrieves audio / video data using the RTMP or HLS protocol. The retrieved data is then converted into text data using a speech recognition API. For example, a cloud-based speech recognition service (e.g., Google Cloud Speech-to-Text) is used as the speech recognition API.

[1113] 2. Summary Generation

[1114] The server uses a generative AI to analyze the acquired text data, extract the main points of discussion, and generate a summary. For example, the generative AI uses an advanced natural language processing model (e.g., OpenAI GPT-4) to extract important sentences and keywords and summarize them in short sentences.

[1115] 3. Summary Delivery

[1116] The server delivers the generated summary to the citizen's device via push notification. For example, it uses a notification service (e.g., Firebase Cloud Messaging) to send real-time notifications to the device of a pre-registered user.

[1117] 4. Providing interaction functions

[1118] The device displays the received summary on the screen and provides an interface that allows users to "like" or post comments. As a concrete example, a "like" button and a comment input field are placed on the UI of a mobile application along with the summary text.

[1119] 5. Feedback collection and analysis

[1120] Users can click "Like" on a summary or enter and submit a comment. The server receives the feedback sent by users and stores it in a database. The feedback data is analyzed and reflected in real time on an analysis dashboard. Based on the analysis results, citizens' opinions and reactions are visualized.

[1121] 6. Display of advertisements

[1122] The server also sends advertisements for local stores and businesses when delivering the summary. For example, it can set up a system to display banner advertisements from local sponsors in designated ad slots. The advertisements are delivered along with the summary and displayed on the user's device.

[1123] 7. Measuring advertising effectiveness and generating reports

[1124] The server records the number of times the ad was displayed and the number of clicks, and periodically generates reports for the advertiser. For example, a weekly report compiling data such as the number of impressions, click-through rate, and regional response may be sent to the advertiser via email.

[1125] 8. User convenience

[1126] The terminal provides users with a display interface that allows for smooth operation. Users can express their interest in discussions in real time, increasing their motivation to participate in local government.

[1127] This system allows the contents of local assembly discussions to be communicated to citizens quickly and concisely, allowing for feedback to be reflected, while financial support can be provided through local advertising. This is expected to promote communication between local governments and citizens, and improve the transparency and citizen participation in local administration.

[1128] The processing flow will be explained below.

[1129] Step 1:

[1130] The server connects to the local council's streaming URL and retrieves audio / video data in real time, using the RTMP or HLS protocol for stable streaming.

[1131] Step 2:

[1132] The server sends the acquired audio data to a speech recognition API, which converts the audio data into text data. This speech recognition API uses cloud-based services such as Google Cloud Speech-to-Text and Amazon Transcribe.

[1133] Step 3:

[1134] The server inputs the generated text data into a generative AI, extracts key points of discussion, and generates a summary. The generative AI model uses OpenAI GPT-4 and other technologies, and uses natural language processing to extract important sentences and keywords.

[1135] Step 4:

[1136] The server sends the generated summary to registered users' devices via push notification, using a push notification service such as Firebase Cloud Messaging to deliver notifications to users' mobile devices in real time.

[1137] Step 5:

[1138] The device displays the received summary on the screen. Along with the summary text, it also provides an interface where users can post "likes" and comments. This interface includes a "like" button and a comment input field below the summary.

[1139] Step 6:

[1140] Users can publish their feedback by clicking the "Like" button on the summary or by entering a comment and clicking the submit button.

[1141] Step 7:

[1142] The server receives feedback from users (likes and comments) and records it in a database. This allows users' reactions and opinions to be collected and stored as data.

[1143] Step 8:

[1144] The server analyzes the collected feedback data and displays it in real time on an analytical dashboard, allowing users to instantly grasp the situation of local governments and councils.

[1145] Step 9:

[1146] The server sends advertisements along with the summary delivery. Advertisements from local stores and businesses are registered in the system and set to be displayed in designated ad slots.

[1147] Step 10:

[1148] The terminal displays local advertisements along with summary text, which the user can view and follow links to if desired.

[1149] Step 11:

[1150] The server records the number of times the advertisement is displayed and the number of clicks in a database and periodically generates a report for the advertiser, which summarizes data such as the number of times the advertisement is displayed, the click rate, and the user distribution, and provides the report to the advertiser.

[1151] Through these steps, a system will be created that provides citizens with real-time information about local assembly discussions, collects and analyzes citizen feedback, and delivers effective advertising.

[1152] Example 1

[1153] 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."

[1154] Traditional media and websites lack the real-time capabilities to quickly and concisely communicate the contents of local assembly discussions to citizens. It is also difficult to effectively collect and analyze citizen feedback, and to appropriately deliver advertisements for local businesses. A system that can solve these issues is needed.

[1155] 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.

[1156] In this invention, the server includes a means for receiving local assembly discussions in real time, a means for converting the received discussions into text data using a generation AI to generate summaries, and a means for delivering the generated summaries to citizens' devices via push notifications. This allows citizens to quickly and concisely understand the content of local assembly discussions and provide feedback on the content in real time. Furthermore, the effective delivery of local advertisements contributes to revitalizing the local economy.

[1157] "Local assembly discussions" refers to various debates and deliberations held in local government assemblies.

[1158] "Real-time receiving means" refers to devices or software that have the ability to simultaneously obtain data about ongoing discussions or debates.

[1159] "Generative AI" refers to artificial intelligence that uses machine learning models and algorithms to generate specific information from input data.

[1160] "Means for converting into text data" refers to the technology or method for converting data acquired in the form of audio, video, etc. into text information.

[1161] A "summary generation method" refers to a process or system that extracts important information from long text data and presents it in a compact form.

[1162] "Citizen's device" refers to an electronic device such as a personal computer, smartphone or tablet that a citizen uses to receive and display local council information.

[1163] "Means of delivering push notifications" refers to technology that notifies users of information in real time or at a specified time.

[1164] "Interface" refers to the screen and input / output means that allow a user to interact with and operate a system.

[1165] "Means for collecting and analyzing feedback" refers to the techniques and processes used to receive user opinions and responses and analyze that data.

[1166] "Local advertising" refers to advertising that promotes products, services, events, etc. that are relevant to a particular geographic area.

[1167] "Advertiser" refers to a company or individual that places an advertisement.

[1168] "Means for generating reports" means the process or system that generates reports or analyses based on the collected data and that are periodically sent to advertisers.

[1169] This invention relates to a system that provides local assembly discussions to citizens in real time, collects and analyzes their opinions on the discussions, and effectively distributes local advertisements. This system is realized through the interaction of a server, terminals, and users.

[1170] First, the server receives the local assembly discussions in real time. This involves connecting to the local assembly's streaming URL and obtaining the audio / video data using the RTMP or HLS protocol. The obtained data is then converted into text data using a speech recognition API (e.g., Google Cloud Speech-to-Text).

[1171] The server then analyzes the acquired text data using generative AI, extracts key discussion points, and generates a summary. Specifically, it uses a generative AI model (e.g., OpenAI GPT-4). An example of a prompt for generating a summary is "Please summarize the following minutes:"

[1172] The generated summary is delivered to the citizen's device via a push notification by the server. These notifications are sent using Firebase Cloud Messaging. An example of the push notification content is "A new discussion summary is available."

[1173] The device displays the received summary to the user and provides an interface that allows the user to "like" or comment, including by placing a "like" button and a comment input field along with the summary text in the user interface of the mobile application.

[1174] Users can click "Like" on the summary or enter and submit a comment. The server receives the feedback submitted by users and stores it in a database (e.g., MySQL). The collected feedback data is analyzed in real time and displayed on an analysis dashboard. For the analysis, an analysis tool such as Tableau is used.

[1175] In addition, the server also sends advertisements for local businesses and stores along with the summary. The advertisements are set to be displayed as banner advertisements for local sponsors in designated ad slots. This allows the advertisements to be displayed on the user's device along with the summary.

[1176] The server also handles ad performance measurement and reporting. It records the number of ad impressions and clicks, and periodically generates weekly reports for advertisers. The reports include data such as impressions, click-through rates, and geographic response, and are sent to advertisers via email.

[1177] Finally, the device provides users with a display interface that allows for smooth operation, allowing them to reflect their interest in local assembly discussions in real time, increasing their motivation to participate in local government.

[1178] By combining these functions, it is possible to quickly and concisely convey the contents of local assembly discussions to citizens, incorporate their feedback, and provide financial support through local advertising. This is expected to promote communication between local governments and citizens, and improve the transparency and citizen participation of local government administration.

[1179] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1180] Step 1:

[1181] The server connects to the local council's live streaming URL and receives audio / video data using the RTMP or HLS protocol. Specifically, it retrieves data from the streaming URL (e.g., http: / / example-streaming-url.com) and calls a speech recognition API (e.g., Google Cloud Speech-to-Text) to convert the audio data into text data.

[1182] Input: Audio / video data via streaming URL

[1183] Output: Text data

[1184] Step 2:

[1185] The server inputs the converted text data into a generative AI model, extracts key discussion points, and generates a summary. Specifically, the server inputs the following prompt into the generative AI model (e.g., OpenAI GPT-4): "Please summarize the following minutes: 'Text data'." The server then saves the generated summary.

[1186] Input: Text data

[1187] Output: Summary data

[1188] Step 3:

[1189] The server uses Firebase Cloud Messaging to deliver the generated summary to citizens' devices via push notification. Specifically, it uses the Firebase Cloud Messaging API to send the summary along with the message "A new discussion summary is available."

[1190] Input: Summary data and user information

[1191] Output: Push notification sent

[1192] Step 4:

[1193] The device displays the received summary to the user and provides an interface that allows the user to "like" or post a comment. Specifically, a "like" button and a comment input field are placed on the UI of the mobile application along with the summary text, allowing the user to use these interfaces.

[1194] Input: Summary data

[1195] Output: User interface

[1196] Step 5:

[1197] Users can click "Like" on the displayed summary or enter and submit a comment. The server receives the feedback and stores it in a database. Specifically, it collects user feedback data (likes and comments) and stores them in a MySQL database.

[1198] Input: User feedback data

[1199] Output: Feedback data stored in a database

[1200] Step 6:

[1201] The server analyzes the collected feedback data in real time. Specifically, it uses an analytical tool (e.g., Tableau) to analyze the feedback data and display it on a dashboard. This analysis visualizes citizens' opinions and reactions.

[1202] Input: Feedback data

[1203] Output: Dashboard display of analysis results

[1204] Step 7:

[1205] The server selects advertising data and distributes it together with the summary in order to transmit advertisements of local sponsors together with the summary. Specifically, the server sets banner advertisements of local sponsors in designated advertising spaces and displays them on the user's terminal together with the summary.

[1206] Input: Summary data and advertising data

[1207] Output: Summary and advertisements displayed on the user's device

[1208] Step 8:

[1209] The server records the number of times an ad is displayed and clicked, and compiles this data into a report that is sent to the advertiser periodically. Specifically, a weekly report is generated, compiling data such as the number of impressions, click-through rates, and geographical responses, and sending it to the advertiser via email.

[1210] Input: Ad impressions and click data

[1211] Output: Report sent to advertiser

[1212] (Application example 1)

[1213] 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."

[1214] There is a lack of means to quickly and effectively communicate the contents of discussions in local assemblies to citizens, as well as to instantly collect and reflect citizen opinions. Furthermore, there is a need for a system that will facilitate smooth communication and economic activity between local governments, citizens, and local businesses by effectively distributing local advertising in conjunction with the information provided to citizens.

[1215] 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.

[1216] In this invention, the server includes: means for receiving local assembly discussions in real time; means for converting the received discussions into text data using a generative AI and generating summaries; means for distributing the generated summaries to citizens' devices via push notifications; means for providing an interface for citizens to post "likes" and comments on the summaries; means for collecting and analyzing feedback from citizens; means for displaying local advertisements together with the summaries; means for generating reports for advertisers using the collected advertisement data; means for live displaying streaming data on citizens' devices; means for collecting comments in real time based on the live-displayed discussions; and means for analyzing the collected comment data and summarizing using a generative AI model. This makes it possible to communicate the content of local assembly discussions to citizens in real time, immediately reflect citizen feedback, and effectively distribute local advertisements.

[1217] A "local assembly" is the legislative body of a local government, and is the body that deliberates and decides on important policies and budgets of local public entities.

[1218] "Real time" is a term that describes things happening nearly simultaneously or with very little delay.

[1219] "Generative AI" refers to artificial intelligence technology that automatically learns and generates text, audio, images, etc.

[1220] "Text data" is a data format consisting of characters and words, and is data that contains character strings that can be processed by a computer.

[1221] A "summary" is a short summary of the original content, intended to convey the main points concisely.

[1222] "Push notification" is a technology that sends information from a server to a user's device in real time, allowing the user to receive the information without taking any specific action.

[1223] "Interface" refers to the means and screen layout by which a user interacts with a system or application.

[1224] "Feedback" refers to reactions and opinions collected from users, and is information that is useful for improving and evaluating a system.

[1225] "Local advertising" refers to promotional activities of stores and businesses related to a specific area, and is advertising targeted at people living in that area.

[1226] "Streaming data" refers to audio and video data that is distributed in real time over the Internet.

[1227] "Live display" refers to displaying data or video to viewers in real time.

[1228] "Comment data" refers to opinions and impressions entered by users in text format.

[1229] A "generative AI model" is an algorithm that automatically generates text, audio, images, etc. using technologies such as machine learning and deep learning.

[1230] This invention includes a system that provides citizens with real-time information about local assembly discussions, collects and analyzes their opinions on the content, and effectively distributes local advertisements. This system is realized through the interaction of a server, terminals, and users.

[1231] First, the server receives the local assembly discussions in real time by connecting to the local assembly's streaming URL using the RTMP or HLS protocol. The received audio / video data is converted into text data using a speech recognition API (e.g., Google Cloud Speech-to-Text).

[1232] The server then uses a generative AI to analyze the converted text data, extract key discussion points, and generate a summary. The generative AI uses an advanced natural language processing model such as OpenAI GPT-4. For example, it uses the following prompt:

[1233] "Summarize the following text:\nThe council discussed a new public works project to build a new park in District A. This proposal has many merits..."

[1234] The generated summary is delivered to the citizen's device via a push notification from the server using a notification service such as Firebase Cloud Messaging. Citizens receive the summary on their device and are provided with an interface where they can "like" or post comments.

[1235] Next, citizen feedback is sent to a server and stored in a database. This feedback data is then reflected in a real-time analysis dashboard, visualizing citizen opinions and reactions.

[1236] Furthermore, the server also transmits local advertisements when delivering the summary. For example, it is set to display banner advertisements of local sponsors in the advertisement space. The advertisements are delivered together with the summary and displayed on the user's terminal.

[1237] Finally, the server records the number of impressions and clicks on the ads and periodically generates reports for the advertiser, summarizing data such as impressions, click-through rates, and geographic response, which are emailed to the advertiser.

[1238] This system allows the contents of local council discussions to be communicated to citizens quickly and concisely, allows for the collection and analysis of feedback from citizens, and promotes communication between local governments, citizens, and local businesses by effectively distributing local advertisements.

[1239] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1240] Step 1:

[1241] The server receives the local assembly discussions in real time by connecting to the local assembly's streaming URL using the RTMP or HLS protocol. The input data is an audio / video stream, and the output data is audio data for speech recognition.

[1242] Step 2:

[1243] The server converts the received audio data into text data using a speech recognition API (e.g., Google Cloud Speech-to-Text). The input data is audio data, and the output data is text data. In this step, the audio signal is analyzed and converted into text as a string.

[1244] Step 3:

[1245] The server uses a generative AI (e.g., OpenAI GPT-4) to analyze the converted text data, extract key discussion points, and generate a summary. The input data is the converted text data, and the output data is the summarized text. Specifically, the text data is input to the generative AI model, and the following prompt sentence is used:

[1246] "Summarize the following text:\nThe council discussed a new public works project to build a new park in District A. This proposal has many merits..."

[1247] Step 4:

[1248] The server delivers the generated summary to the citizen's device via a push notification. The input data is the summarized text, and the output data is a push notification sent to the citizen's device. This push notification uses a notification service such as Firebase Cloud Messaging. The summary is then displayed on the user's device.

[1249] Step 5:

[1250] The device displays the received summary on the screen and provides an interface where users can "like" or comment. The input data is a push notification from the server, and the output data is the user's feedback. Specifically, the device displays the summary text along with a "like" button and a comment input field.

[1251] Step 6:

[1252] The user clicks "Like" on the summary or enters a comment and submits it. The input data is the user's feedback, and the output data is the feedback data sent to the server.

[1253] Step 7:

[1254] The server receives the feedback sent by the user and stores it in a database. The input data is the feedback data, and the output data is the stored database entry. In this step, the feedback data is analyzed and reflected in the analysis dashboard in real time.

[1255] Step 8:

[1256] The server also sends local advertisements when delivering the summary. The input data is the summarized text and advertisement data, and the output data is the summary with advertisements sent to the citizen's device. Specifically, a banner advertisement from a local sponsor is displayed in the designated advertisement space.

[1257] Step 9:

[1258] The server records the number of times the ad was viewed and clicked, and periodically generates a report for the advertiser. The input data is the ad view and click data, and the output data is the generated report. This report compiles data such as the number of views, click rates, and regional responses.

[1259] 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.

[1260] This paper describes a system that provides citizens with real-time information about local assembly discussions and collects and analyzes their feedback by combining it with an emotion engine that recognizes users' emotions. This system is realized through the interaction of a server, terminals, and users.

[1261] 1. Collection and text conversion of meeting minutes

[1262] The server receives real-time data from local assembly discussions. For example, it connects to the assembly's streaming URL and retrieves audio / video data using the RTMP or HLS protocol. This data is then sent to a speech recognition API, which converts the speech into text. Cloud-based services such as Google Cloud Speech-to-Text and Amazon Transcribe are used for the speech recognition API.

[1263] 2. Summary Generation

[1264] The server uses a generative AI to analyze the acquired text data, extract the main points of discussion, and generate a summary. For example, the generative AI uses an advanced natural language processing model (e.g., OpenAI GPT-4) to extract important sentences and keywords and summarize them in short sentences.

[1265] 3. Summary Delivery

[1266] The server sends the generated summary to the registered user's device as a push notification, for example, by using a notification service (e.g., Firebase Cloud Messaging) to deliver the notification in real time.

[1267] 4. Providing interaction functions

[1268] The device displays the received summary on the screen and provides an interface that allows users to "like" or post comments. As a concrete example, a "like" button and a comment input field are placed on the UI of a mobile application along with the summary text.

[1269] 5. Leveraging Emotional Engines

[1270] The server inputs the feedback data from the user into the emotion engine to recognize the user's emotions. The emotion engine analyzes the feedback (e.g., "likes" and comments) and generates emotion data (e.g., joy, sadness, anger, etc.).

[1271] 6. Feedback Collection and Analysis

[1272] The server records the recognized emotion data and feedback data in a database and displays it in real time on an analysis dashboard, visualizing citizens' opinions and reactions and enabling local assemblies and municipalities to understand citizens' feelings toward the content of discussions.

[1273] 7. Display and optimization of advertisements

[1274] The server displays advertisements for local stores and businesses when delivering summaries. Furthermore, it optimizes the display of advertisements based on the user's emotional data recognized by the emotion engine. For example, it can display a specific product advertisement to a user who shows positive emotions, and a different advertisement to a user who shows negative emotions.

[1275] 8. Advertising effectiveness measurement and report generation

[1276] The server records the number of impressions and clicks on the ads and periodically generates reports to the advertisers, which can include details such as impressions, click-through rates, user distribution, and recognized emotion data.

[1277] 9. User convenience

[1278] The terminal provides users with a display interface, allowing for smooth operation. Users can express their feelings and opinions on discussions in real time, increasing their willingness to participate in local government.

[1279] This system quickly and concisely conveys the contents of local assembly discussions to citizens, recognizes user sentiment and reflects their feedback, and provides financial support through local advertising. This is expected to promote communication between local governments and citizens, and improve transparency and citizen participation in local government administration.

[1280] The processing flow will be explained below.

[1281] Step 1:

[1282] The server connects to the local council's streaming URL and retrieves audio / video data in real time, maintaining stable streaming using the RTMP or HLS protocol.

[1283] Step 2:

[1284] The server sends the acquired audio data to a speech recognition API, which converts the audio into text data in real time. For example, by using Google Cloud Speech-to-Text, highly accurate text conversion is possible.

[1285] Step 3:

[1286] The server uses generative AI to analyze the text data, extract key points of discussion, and generate summaries. The generative AI uses natural language processing technologies such as OpenAI GPT-4 to extract important keywords and sentences.

[1287] Step 4:

[1288] The server then sends the generated summary to registered users' devices via push notification, using a push notification service such as Firebase Cloud Messaging to deliver the notification in real time.

[1289] Step 5:

[1290] The device displays the received summary on the screen and provides an interface with a "Like" button and a comment field to allow users to easily provide feedback.

[1291] Step 6:

[1292] Users can post feedback by clicking the "Like" button on the summary or by entering text in the comment field and clicking the submit button.

[1293] Step 7:

[1294] The server receives the feedback from the users and stores it in a database, thereby effectively managing the collected feedback data.

[1295] Step 8:

[1296] The server inputs the feedback data from the user into the emotion engine, which analyzes this data and recognizes the user's emotions (e.g., joy, sadness, anger).

[1297] Step 9:

[1298] The server records the recognized emotion data along with feedback data in a database, which is then reflected in a real-time analytics dashboard, allowing local councils and municipalities to visually understand citizen sentiment.

[1299] Step 10:

[1300] The server sends local ads along with the digests. The ads are optimized based on the emotional data recognized by the emotion engine. For example, a specific ad can be shown to users who show positive emotions, and a different ad can be shown to users who show negative emotions.

[1301] Step 11:

[1302] The terminal displays the advertisement along with the summary on the screen. The user can view the advertisement and click on the link if they are interested.

[1303] Step 12:

[1304] The server records the number of times an ad is displayed and clicked, and stores the data in a database. It periodically generates reports for advertisers to report on the effectiveness of their ads. The reports include the number of times an ad is displayed, click-through rates, and user sentiment data.

[1305] The above processing steps create a system that provides citizens with the content of local assembly discussions in real time, utilizes an emotion engine to collect and analyze citizen feedback, and provides optimized advertisements.

[1306] Example 2

[1307] 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."

[1308] The topics discussed in local assemblies are diverse, making it extremely difficult for citizens to understand everything. Furthermore, the lack of real-time information on discussions undermines the transparency of assemblies, leading to a decline in citizen interest and willingness to participate. Furthermore, the lack of means to instantly collect and analyze citizen feedback leads to a lack of two-way communication between the government and citizens. Conventional systems make it difficult to provide citizens with real-time information on local assembly discussions and effectively collect and analyze their reactions and opinions.

[1309] 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.

[1310] In this invention, the server includes: means for receiving local assembly discussions in real time; means for converting the acquired audio data into text data using a speech recognition API; and means for analyzing the received text data using a generation AI to generate summaries. This enables the contents of local assembly discussions to be quickly organized and summarized and provided to citizens. The server also includes means for delivering the generated summaries to citizens' devices via push notifications; means for providing an interface for citizens to post "likes" and comments on the summaries; means for using an emotion engine to collect and analyze feedback from citizens; and means for recording the analyzed emotion data and feedback data in a database. This enables the collection and analysis of citizen reactions in real time, enabling two-way communication between the government and citizens. The server also includes means for displaying advertising materials along with the summaries and means for generating reports for advertisers using the collected advertising data. This allows advertising revenue to be utilized to support system operations.

[1311] "Discussion" refers to the act of local assembly members and stakeholders exchanging opinions and making decisions about specific issues or policies.

[1312] "Real-time" refers to a situation in which data is processed and information is communicated almost simultaneously as the discussion progresses.

[1313] "Means" refers to the methods or techniques used to achieve a particular goal.

[1314] "Generative AI" is an artificial intelligence that performs natural language processing, and is a technology that has the ability to analyze and learn from large amounts of text data and generate summaries and new text.

[1315] A "speech recognition API" is an application programming interface that accepts voice data as input and converts it into text data.

[1316] "Text data" refers to digital information expressed as a string of characters, and is subject to natural language processing and analysis.

[1317] "Push notification" is a technology that allows messages and notifications to be sent instantly from the server to the user's device.

[1318] "Interface" refers to the contact points or means by which a user and a system interact with each other.

[1319] "Feedback" refers to reactions and opinions from users regarding particular information or services.

[1320] An "emotion engine" is a technology that analyzes text data and feedback and recognizes the emotions contained therein.

[1321] A "database" is a system for efficiently storing, managing, and retrieving data.

[1322] "Advertising Materials" means information content, such as text, images, and video, used to promote products and services.

[1323] A "report" is a document that summarizes collected data and analysis results, and provides organized information according to a specific purpose.

[1324] This invention describes a system that provides real-time information about local council discussions to citizens, recognizes user sentiment, and collects and analyzes feedback. This system is realized through the interaction of a server, terminals, and users.

[1325] Receiving and transcribing discussions

[1326] The server first receives real-time streaming from the local assembly. Specifically, it connects to the assembly's streaming URL using RTMP or HLS protocol to obtain audio / video data. This data is then sent to a speech recognition API such as Google Cloud Speech-to-Text or Amazon Transcribe, where the audio data is converted into text data.

[1327] Specific examples

[1328] Connect to the parliamentary streaming URL: http: / / example.com / stream using the RTMP protocol, obtain the audio data, and send it to the Google Cloud Speech-to-Text API.

[1329] Summary generation and summary delivery

[1330] The server analyzes the text data obtained from the speech recognition API and uses a generative AI model (e.g., OpenAI GPT-4) to summarize the text data. The summary extracts the main points of discussion and condenses them into short sentences.

[1331] Specific examples

[1332] Example prompt: Enter the following text data and summarize the main points of the discussion: Text: "{Congress discussion text}"

[1333] The generated summary is pushed to registered users' devices in real time using a notification service such as Firebase Cloud Messaging.

[1334] Gathering feedback and leveraging the emotion engine

[1335] The device displays the received summary on the screen and provides an interface where users can post "likes" and comments. The user's feedback is sent to the server, and the feedback data is input into the emotion engine. The emotion engine analyzes the feedback and generates emotion data (e.g., joy, sadness, anger, etc.).

[1336] Specific examples

[1337] Example prompt: Enter the following comment and analyze the sentiment: Comment: "{user comment}"

[1338] Data collection and analysis

[1339] The server records sentiment data and feedback data in a database and displays it in real time on an analysis dashboard, visualizing citizens' opinions and reactions and allowing local assemblies and municipalities to understand citizens' feelings toward the content of discussions.

[1340] Ad placement and optimization

[1341] The server displays advertisements for local stores and businesses when delivering summaries, and optimizes the display of advertisements based on the user's emotional data recognized by the emotion engine. Using the collected advertising data, reports can be generated for advertisers.

[1342] In this way, this system quickly and concisely conveys the contents of local assembly discussions to citizens, and by analyzing and utilizing user emotional data, promotes two-way communication between local governments and citizens.

[1343] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1344] Step 1:

[1345] Receive real-time discussions

[1346] The server connects to the local assembly's streaming URL via RTMP or HLS protocol and receives audio / video data in real time. This streaming data is the input, and the acquired audio / video data is the output. Specifically, the server connects to the streaming URL and receives assembly discussions in real time.

[1347] Specific actions

[1348] Connect to the streaming URL.

[1349] Retrieve audio data using the RTMP protocol.

[1350] Step 2:

[1351] Converting audio data to text

[1352] The server sends the acquired audio data to a speech recognition API (e.g., Google Cloud Speech-to-Text) and converts it into text data. This audio data is the input, and the converted text data is the output. Specifically, the server sends audio data to the API and receives text data from the API.

[1353] Specific actions

[1354] Send the audio data to the Google Cloud Speech-to-Text API.

[1355] Receive the generated text data.

[1356] Step 3:

[1357] Text data analysis and summary generation

[1358] The server inputs the text data obtained from the speech recognition API into a generative AI model (e.g., OpenAI GPT-4), extracts the main points of the discussion, and generates a summary. This text data is the input, and the generated summary is the output. Specifically, the server inputs the data along with the prompt "Please summarize this text" and generates a summary.

[1359] Specific actions

[1360] Input text data into GPT-4.

[1361] Set the prompt text.

[1362] Receive the output summary.

[1363] Step 4:

[1364] Summary Delivery

[1365] The server then pushes the generated summary to the registered user's device using a notification service such as Firebase Cloud Messaging. The summary is the input, and the pushed message is the output. Specifically, the summary is set as the body of the push notification and sent using the notification service.

[1366] Specific actions

[1367] Set the summary text as the body of the push notification.

[1368] Calls Firebase Cloud Messaging to send a notification to the user device.

[1369] Step 5:

[1370] Providing interaction functions

[1371] The device displays the received summary on the screen and provides an interface where the user can post likes and comments. This summary is the input, and the user's feedback is the output. Specifically, when the user opens the app, the latest summary text is displayed and feedback is possible.

[1372] Specific actions

[1373] Display summary text on screen.

[1374] Provide a "Like" button and a comment field.

[1375] Step 6:

[1376] Analysis by emotion engine

[1377] The server collects feedback data (likes and comments) from users and inputs it into the emotion engine to recognize emotions. This feedback data is the input, and the analyzed emotion data is the output. Specifically, the server sends the feedback data to the emotion engine and receives the emotion data.

[1378] Specific actions

[1379] Collect user comments and likes data.

[1380] Sending feedback data to the emotion engine.

[1381] Obtain emotion data.

[1382] Step 7:

[1383] Data collection and analysis

[1384] The server records the emotion data and feedback data in a database and reflects them in real time on the analysis dashboard. This emotion data and feedback data are the input, and the updated analysis dashboard is the output. Specifically, the server saves the data in the database and updates the dashboard.

[1385] Specific actions

[1386] Emotion data and feedback data are stored in a database.

[1387] Refresh your analytics dashboard.

[1388] Step 8:

[1389] Ad placement and optimization

[1390] The server displays local advertising materials when delivering summaries and optimizes the display of advertisements based on emotional data. The summaries and emotional data are input, and the optimized advertisement display is the output. Specifically, the server selects and displays appropriate advertisements along with the summaries.

[1391] Specific actions

[1392] Select ads that are suitable for the summary text.

[1393] Optimize your ads based on sentiment data.

[1394] Step 9:

[1395] Advertising effectiveness measurement and report generation

[1396] The server records the number of times the ad is displayed and the number of clicks, and generates an effectiveness measurement report for the advertiser. This advertising data is the input, and the generated report is the output. Specifically, data such as the number of times the ad is displayed and the click rate is collected, and reports are created periodically.

[1397] Specific actions

[1398] Record the number of impressions and clicks on your ads.

[1399] Generate reports to advertisers.

[1400] (Application example 2)

[1401] 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."

[1402] While the content of local assembly discussions is important information for citizens, it is difficult to grasp this information in real time, which has led to a decline in citizen participation and interest.In addition, when widely disseminating information about local assembly meetings to citizens, there is a need to effectively collect and analyze citizen opinions and emotions, and to optimize the provision of information and advertising display based on that information.

[1403] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for receiving local assembly discussions in real time, means for converting the received discussions into text data using a generation AI and generating summaries, means for delivering the generated summaries to citizens' devices via push notifications, means for providing an interface for citizens to post "likes" and comments on the summaries, means for collecting and analyzing feedback from citizens, means for displaying local advertisements along with the summaries, means for generating reports for advertisers using the collected advertising data, means for inputting the feedback data into an emotion engine and analyzing citizen emotions, and means for optimizing advertisements using the emotion analysis data. This makes it possible to quickly and concisely communicate the content of local assembly discussions to citizens, effectively collect and analyze citizen opinions and emotions, promote communication between local governments and citizens, and optimize advertisements.

[1404] A "local assembly" is the decision-making body of a local government and the place where decisions are made by local public entities.

[1405] "Real time" refers to immediacy that corresponds to the timing of an event.

[1406] "Generative AI" refers to artificial intelligence that generates new data and information using natural language processing and machine learning techniques.

[1407] "Text data" refers to digital data that expresses information such as audio and video as a string of characters.

[1408] A "summary" is a short summary of the main points extracted from the original information.

[1409] A "terminal" is a device operated by a user, such as a smartphone or computer.

[1410] "Push notification" is a mechanism that automatically sends information from the server to the user's device.

[1411] An "interface" refers to the means or screen through which a user interacts with a system.

[1412] "Feedback" refers to the evaluations and opinions that users give to the system.

[1413] An "emotion engine" is a machine learning algorithm or technology that analyzes user feedback and behavior to recognize emotions.

[1414] "Local advertising" refers to advertising that promotes businesses or services related to a particular area.

[1415] "Advertiser" refers to a company or individual that places an advertisement.

[1416] A "report" is a document that compiles data and information.

[1417] "Emotion analysis data" refers to digital data generated as a result of analyzing a user's emotions.

[1418] "Optimization" means adjusting something to the most effective or efficient state depending on the conditions and purpose.

[1419] This invention is a system that provides citizens with real-time information about local assembly discussions and collects and analyzes their feedback by combining it with an emotion engine that recognizes users' emotions. This system is realized through the interaction of a server, terminals, and users.

[1420] The server receives local assembly discussions in real time. Specifically, it connects to the assembly's streaming URL and obtains audio / video data using the RTMP or HLS protocol. This data is then sent to a speech recognition API, which converts the speech into text data. Cloud-based speech recognition services such as Google Cloud Speech-to-Text and Amazon Transcribe are used for the speech recognition API. At this stage, the discussion content is stored as text data on the server.

[1421] The server then uses generative AI to analyze the acquired text data, extract key points of discussion, and generate a summary. For example, the generative AI uses an advanced natural language processing model (e.g., OpenAI GPT-4) to extract important sentences and keywords and summarize them into short sentences. This summary data is then stored on the server, ready to be sent to the user.

[1422] The generated summary is delivered to the user's device via push notification. The notification service uses Firebase Cloud Messaging (FCM). By using FCM, notifications can be sent to users in real time and the summary content can be displayed.

[1423] The user's device displays the received summary on the screen and provides an interface where the user can "like" or post comments. This interface is implemented as a mobile application, and includes a "like" button and a comment input field along with the summary text. Through this, users can input their own opinions and feelings in real time.

[1424] Furthermore, the server inputs feedback data from users into the emotion engine to analyze the user's emotions. The emotion engine analyzes the feedback (e.g., "likes" and comments) and generates emotion data (e.g., joy, sadness, anger, etc.). This emotion data is stored on the server and used for subsequent processing such as ad optimization.

[1425] The server also has the ability to display advertisements for local stores and businesses along with the summary. Based on the user's emotional data recognized by the emotion engine, the display of advertisements can be optimized. For example, a specific product advertisement can be displayed to a user who shows positive emotions, while a different advertisement can be displayed to a user who shows negative emotions.

[1426] The server records the number of times an advertisement is displayed and clicked, and periodically generates reports to advertisers. The reports include details such as the number of impressions, click-through rates, user distribution, and recognized emotion data. This allows advertisers to accurately understand the effectiveness of their advertisements and develop marketing strategies.

[1427] For example:

[1428] When a user receives a summary of a "local council's proposed new ordinance" and clicks "Like" on their smartphone, their behavior is collected and stored in a database as the user's positive emotion. The same user is then shown an advertisement featuring a new service from a relevant local store.

[1429] Example prompt sentence:

[1430] "Please summarize the latest discussions in the local council and notify users."

[1431] "Analyze user sentiment data and display the most appropriate ads."

[1432] As a result, it is possible to provide a system that can quickly and concisely convey the contents of discussions in local assemblies to citizens, effectively collect and analyze citizens' opinions and feelings, promote communication between local governments and citizens, and optimize advertising.

[1433] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1434] Step 1:

[1435] The server receives the local assembly discussions in real time. Specifically, the server connects to the assembly's streaming URL and obtains audio / video data using the RTMP or HLS protocol. Using this data as input, the server sends the data to a speech recognition API and obtains text data as output.

[1436] Step 2:

[1437] The server analyzes the acquired text data and generates a summary. Specifically, it uses generation AI to extract important sentences and keywords from the text data and summarize them into short sentences. The input here is text data, and the output is summarized text data.

[1438] Step 3:

[1439] The server sends the generated summary to the user's device via a push notification. The server uses Firebase Cloud Messaging (FCM) to send a push notification using the summarized text data as input, and the user's device receives the notification.

[1440] Step 4:

[1441] The device displays the received summary on the screen and provides an interface for users to "like" or post comments. Specifically, as a mobile application, a "like" button and a comment input field are displayed along with the summary text. The input is the summary text received via push notification, and the output is the interface operated by the user.

[1442] Step 5:

[1443] Users post "likes" and comments through the interface, which allows feedback data to be collected. The input is user actions (likes and comments), and the output is feedback data.

[1444] Step 6:

[1445] The server inputs feedback data from the user into the emotion engine and analyzes the user's emotions. Specifically, the emotion engine analyzes the feedback data and generates the user's emotion data (e.g., joy, sadness, anger, etc.). The input is the feedback data, and the output is the emotion data.

[1446] Step 7:

[1447] The server uses the sentiment analysis data to optimize advertisements. Specifically, it displays a specific product advertisement to users who show positive emotions and a different advertisement to users who show negative emotions. The input is the sentiment analysis data, and the output is the optimized advertisement.

[1448] Step 8:

[1449] The server records the number of times an ad is displayed and clicked, and periodically generates a report for the advertiser. Specifically, it aggregates the number of times an ad is displayed, the click rate, user distribution, recognized emotion data, etc., and generates the report. The input is the ad data, and the output is the report.

[1450] 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.

[1451] 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.

[1452] 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.

[1453] 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.

[1454] 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.

[1455] 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.

[1456] 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).

[1457] 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.

[1458] 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."

[1459] 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.

[1460] 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).

[1461] 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.

[1462] 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.

[1463] 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.

[1464] 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.

[1465] 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.

[1466] 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.

[1467] 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.

[1468] 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.

[1469] 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.

[1470] 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.

[1471] The following is further disclosed regarding the above embodiment.

[1472] (Claim 1)

[1473] A means of receiving local assembly discussions in real time,

[1474] A means for converting received discussions into text data using a generative AI to generate summaries;

[1475] A means to deliver the generated summary to citizens' devices via push notification;

[1476] A means to provide an interface for citizens to post likes and comments on the summaries;

[1477] a means of collecting and analyzing citizen feedback;

[1478] a means of displaying local advertisements along with the summary;

[1479] means for generating reports to advertisers using the collected advertising data;

[1480] A system including:

[1481] (Claim 2)

[1482] 10. The system of claim 1, further comprising means for converting streaming data from the local council into text using a speech recognition API.

[1483] (Claim 3)

[1484] 10. The system according to claim 1, further comprising means for recording the analysis results of the feedback data in a database and reflecting them in real time on an analysis dashboard.

[1485] "Example 1"

[1486] (Claim 1)

[1487] A means of receiving local assembly discussions in real time,

[1488] A means for converting received discussions into text data using a generative AI to generate summaries;

[1489] A means to deliver the generated summary to citizens' devices via push notification;

[1490] A means to provide an interface for citizens to post likes and comments on the summaries;

[1491] a means of collecting and analyzing citizen feedback;

[1492] a means of displaying local advertisements along with the summary;

[1493] means for generating reports to advertisers using the collected advertising data;

[1494] A system including:

[1495] (Claim 2)

[1496] 10. The system of claim 1, further comprising means for converting streaming data from the local council into text using a speech recognition API.

[1497] (Claim 3)

[1498] 10. The system according to claim 1, further comprising means for recording the analysis results of the feedback data in a database and reflecting them in real time on an analysis dashboard.

[1499] "Application Example 1"

[1500] (Claim 1)

[1501] A means of receiving local assembly discussions in real time,

[1502] A means for converting received discussions into text data using a generative AI to generate summaries;

[1503] A means to deliver the generated summary to citizens' devices via push notification;

[1504] A means to provide an interface for citizens to post likes and comments on the summaries;

[1505] a means of collecting and analyzing citizen feedback;

[1506] a means for displaying local advertisements along with the summary;

[1507] means for generating reports to advertisers using the collected advertising data;

[1508] A means to display live streaming data on citizens' devices;

[1509] a means for collecting comments in real time based on the live displayed discussion;

[1510] A means for analyzing collected comment data and summarizing it using a generative AI model;

[1511] A system including:

[1512] (Claim 2)

[1513] 10. The system of claim 1, further comprising means for converting streaming data from the local council into text using a speech recognition API.

[1514] (Claim 3)

[1515] 10. The system according to claim 1, further comprising means for recording the analysis results of the feedback data in a database and reflecting them in real time on an analysis dashboard.

[1516] "Example 2: Combining Emotion Engines"

[1517] (Claim 1)

[1518] A means of receiving local assembly discussions in real time,

[1519] A means for converting the acquired audio data into text data using a speech recognition API;

[1520] A means for analyzing received text data using a generative AI to generate a summary;

[1521] A means to deliver the generated summary to citizens' devices via push notification;

[1522] A means to provide an interface for citizens to post likes and comments on the summaries;

[1523] a means of using an emotion engine to collect and analyze citizen feedback;

[1524] means for recording the analyzed emotion data and feedback data in a database;

[1525] means for displaying advertising material together with the summary;

[1526] means for generating reports to advertisers using the collected advertising data;

[1527] A system including:

[1528] (Claim 2)

[1529] 10. The system of claim 1, further comprising means for receiving streaming data from the local council using a network protocol and converting the data to text using a speech recognition API.

[1530] (Claim 3)

[1531] 10. The system of claim 1, further comprising means for reflecting the feedback data and sentiment analysis data in real time on an analytics dashboard.

[1532] "Application example 2 when combining emotion engines"

[1533] (Claim 1)

[1534] A means of receiving local assembly discussions in real time,

[1535] A means for converting received discussions into text data using a generative AI to generate summaries;

[1536] A means to deliver the generated summary to citizens' devices via push notification;

[1537] A means to provide an interface for citizens to post likes and comments on the summaries;

[1538] a means of collecting and analyzing citizen feedback;

[1539] a means of displaying local advertisements along with the summary;

[1540] means for generating reports to advertisers using the collected advertising data;

[1541] A means of inputting feedback data into an emotion engine to analyze citizen emotions;

[1542] a means for optimizing advertisements using sentiment analysis data;

[1543] A system including:

[1544] (Claim 2)

[1545] 10. The system of claim 1, further comprising means for converting streaming data from the local council into text using a speech recognition API.

[1546] (Claim 3)

[1547] 10. The system according to claim 1, further comprising means for recording the analysis results of the feedback data in a database and reflecting them in real time on an analysis dashboard. [Explanation of symbols]

[1548] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of receiving local assembly discussions in real time, A means for converting received discussions into text data using a generative AI to generate summaries; A means to deliver the generated summary to citizens' devices via push notification; A means to provide an interface for citizens to post likes and comments on summaries; a means of collecting and analyzing citizen feedback; a means of displaying local advertisements along with the summary; means for generating reports to advertisers using the collected advertising data; A system including:

2. 10. The system of claim 1, further comprising means for converting streaming data from the local council into text using a speech recognition API.

3. The system according to claim 1, further comprising means for recording the analysis results of the feedback data in a database and reflecting them in real time on an analysis dashboard.

Images