system

Abstract

Provide a system. A means for acquiring a user's past call history; means for analyzing past call history and generating a call pattern; means for automatically generating new messages based on the message pattern; means for transmitting the generated message to a user's terminal and requesting confirmation; A means for retrieving a message that has been modified by the user; and means for posting the final confirmed message from the user's social media account.

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 today's world, social networking sites (SNS) have become an important communication tool for individuals and businesses. However, continuous and effective communication requires a certain amount of time and effort each day, which is a burden for many users. To solve this problem, automated systems are needed, but simple automated tools run the risk of disseminating content unintended by the user. Therefore, it is important to develop a system that allows safe and efficient communication on SNS. [Means for solving the problem]

[0005] This invention is a system that acquires and analyzes a user's past calling history to generate calling patterns, and provides a means for automatically generating new messages based on these calling patterns. Furthermore, the generated messages are sent to the user's device, and an interface is provided that allows the user to review and edit them. Finally, messages that have been reviewed and edited by the user can be posted from an SNS account, enabling safe and efficient SNS messaging.

[0006] Specifically, the system includes a means for acquiring past transmission history from the user's SNS account, a means for analyzing this history using natural language processing technology to generate transmission patterns, a means for automatically generating new transmission messages based on the transmission patterns, a means for sending the generated transmission messages to the user's device and requesting confirmation, a means for re-acquiring transmission messages corrected by the user, and a means for posting the final confirmed transmission message from the SNS account, thereby reducing the burden on the user and preventing transmission of unintended content.

[0007] "User" refers to any individual or organization that uses this system.

[0008] "Outgoing call history" refers to a record of content that a user has posted on SNS in the past.

[0009] "Analysis" refers to the process of extracting data trends and topics from collected communication history using natural language processing technology.

[0010] "Communication patterns" refers to information that indicates a user's past communication tendencies and themes based on data extracted through analysis.

[0011] "Automatic generation" refers to the process by which the system automatically creates new content based on analyzed patterns of communication.

[0012] "Message" refers to a single sentence or message posted on a social networking site.

[0013] "Terminal" refers to the device (e.g., smartphone or computer) used by the user to review and modify.

[0014] "Confirmation" refers to the act of the user confirming whether the generated message is appropriate.

[0015] "Modification" refers to the act of a user making changes to a generated message.

[0016] "Interface" refers to the operation screen or system that allows the user to check and correct.

[0017] "Posting" refers to the act of publishing the final message through the user's SNS account. [Brief explanation of the drawings]

[0018] [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

[0019] 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.

[0020] First, the terms used in the following description will be explained.

[0021] 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).

[0022] 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.

[0023] 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.

[0024] 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.

[0025] 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."

[0026] [First embodiment]

[0027] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0028] 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.

[0029] 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).

[0030] 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.

[0031] 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.

[0032] 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.

[0033] 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.

[0034] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0035] 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.

[0036] 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.

[0037] 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.

[0038] 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."

[0039] The present invention provides a system for preventing users from posting unintended content while improving the efficiency of posting on SNS. Specific embodiments of this system are described below.

[0040] System Overview

[0041] This system involves a series of operations: acquiring and analyzing a user's past call history to generate call patterns, automatically generating new messages based on these call patterns, prompting the user to confirm and revise the generated messages, and finally sending the confirmed content from the SNS account.

[0042] Program processing overview

[0043] 1. Get call history from user's SNS account:

[0044] The server accesses the user's social media account and uses the API to retrieve past postings, such as tweets, posts, and comments.

[0045] 2. Save call history:

[0046] The acquired posting history is saved in a database. Each posting history contains information such as the posting date and time, content, and reactions (number of likes, number of comments, etc.).

[0047] 3. Analysis of call history:

[0048] The server uses natural language processing (NLP) technology to analyze the posting history, extracting frequently occurring topics, keywords, and user posting trends.

[0049] 4. Generate call patterns:

[0050] Based on the analysis results, the server creates a calling pattern. For example, if there are many calls made on a particular day of the week or during a particular time period, it will extract that pattern.

[0051] 5. Automatic generation of new messages:

[0052] The server automatically generates new messages based on the user's posting patterns. For example, for a user who posts a lot of health-related information, the server generates the following message: "Today's small health habit: I recommend drinking a glass of water first thing in the morning."

[0053] 6. Request confirmation of message:

[0054] The generated message is sent to the user's terminal, and a confirmation message is displayed saying, "This message will be sent. Are you sure?"

[0055] 7. User Modifications and Verification:

[0056] The user checks the message and corrects it if necessary. The corrected message is then sent back to the server.

[0057] 8. Making the final call:

[0058] The server sends the message confirmed by the user from the SNS account, and notifies the user when the message is complete.

[0059] Specific examples

[0060] Example 1: Using a Twitter account

[0061] 1. User logs in:

[0062] A user accesses the system and logs in with their Twitter account. The system obtains permission to access the SNS account.

[0063] 2. Get past tweets:

[0064] The server uses the Twitter API to retrieve tweets from the past year, including the tweet content, posting date and time, and reaction status.

[0065] 3. Tweet analysis:

[0066] The server analyzes the collected tweet data using NLP techniques, including topic models (e.g., Latent Dirichlet Allocation) and keyword extraction.

[0067] 4. Creating a calling pattern:

[0068] The server generates a posting pattern from the analysis results. For example, if there are many tweets about "health," it identifies that pattern.

[0069] 5. Auto-generate new tweets:

[0070] The server automatically generates new tweets about "health." For example, the content generated is "Today's small health habit: I recommend drinking a glass of water first thing in the morning."

[0071] 6. User confirmation prompts:

[0072] The server sends the generated tweet to the user's device and displays the message, "This text will be sent. Is this OK?"

[0073] 7. User Modifications:

[0074] The user reviews the tweet and corrects it to "I recommend drinking a glass of water first thing in the morning!"

[0075] 8. Sending Tweets:

[0076] The server posts the corrected tweet from your Twitter account. After posting is complete, the server notifies the user that the tweet has been posted.

[0077] In this way, the present invention allows users to safely and efficiently send messages on SNS without feeling any burden. By obtaining analysis results from the user's past message history, automatically generating new messages and prompting the user for confirmation, the risk of sending unintended content is prevented.

[0078] The processing flow will be explained below.

[0079] Step 1:

[0080] A user accesses the system and logs in with their SNS account. The user then grants permission to access the system.

[0081] Step 2:

[0082] The server uses the SNS API to retrieve the user's past posting history (e.g., tweets and posts from the past year).

[0083] Step 3:

[0084] The server saves the acquired posting history in a database. The posting history includes information on the posting date and time, content, and reactions (number of likes, number of comments, etc.).

[0085] Step 4:

[0086] The server uses natural language processing (NLP) technology to analyze the saved call history and extract keywords, frequently occurring themes, and user trends.

[0087] Step 5:

[0088] The server generates a user's posting pattern based on the analysis results, which includes posting tendencies for specific topics and time periods.

[0089] Step 6:

[0090] The server automatically generates new messages based on the user's posting patterns and current trends. For example, if the user posts a lot of health-related information, it generates new health-related messages.

[0091] Step 7:

[0092] The server sends the generated message to the user's terminal and displays the message "This message will be sent. Is this OK?"

[0093] Step 8:

[0094] The user checks the message generated on the device, corrects the wording as necessary, and once corrections are complete, the user presses the approval button to send the confirmation.

[0095] Step 9:

[0096] The server receives the corrected message sent by the user and performs a final check.

[0097] Step 10:

[0098] The server posts the final confirmed message from the user's SNS account.

[0099] Step 11:

[0100] After the posting is complete, the server sends a notification to the user saying "Posting is complete."

[0101] In this way, each step reduces the burden on the user while preventing unintended transmission of content.

[0102] Example 1

[0103] 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."

[0104] In today's social networking sites, users frequently post, but it is difficult to maintain efficient, high-quality communication. There is also a risk of unintentionally posting inappropriate content. For example, users may forget the content and time of previous posts, making it difficult to generate new ideas. Furthermore, reviewing and revising posts takes time, placing a burden on users. The present invention aims to solve these problems and enable users to post on social networking sites efficiently and safely.

[0105] 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.

[0106] In this invention, the server includes means for obtaining authentication and access permission for the user's SNS account, means for obtaining the user's past transmission history, means for saving the transmission history in a database, means for using natural language processing technology to analyze the transmission history, means for generating transmission patterns, means for automatically generating new transmissions using a generative AI model, means for sending the generated transmissions to the user's device and requesting confirmation, means for re-obtaining transmissions modified by the user, and means for posting the final confirmed transmissions from the user's SNS account. This enables users to transmit efficiently and consistently based on past transmission content and patterns, reducing the risk of transmitting unintended content and enabling them to easily continue posting high-quality content.

[0107] "User" refers to an individual or corporation that has an SNS account and uses that account to conduct communication activities.

[0108] "SNS account" refers to an account used by a user on a social networking service (SNS), including accounts on services such as Twitter, Facebook, and Instagram.

[0109] "Outgoing communication history" refers to digital records of posts, tweets, comments, messages, etc. that a user has made in the past from their social media account.

[0110] A "database" refers to a digital system for efficiently storing, managing, and searching data such as call history and analysis results.

[0111] "Natural language processing technology" is a technology for analyzing, understanding, and generating human language using computers, and includes techniques such as topic modeling and keyword extraction.

[0112] "Calling pattern" refers to a pattern or tendency regarding a particular day of the week, time period, or content of calls, derived from an analysis of a user's past calling history.

[0113] "Generative AI model" refers to an algorithm or program that uses artificial intelligence to generate new messages, and specifically includes natural language generation models.

[0114] "New messages" refers to text content for posting on social media that is automatically generated based on the user's messaging patterns.

[0115] "User's device" refers to a digital device used by a user, such as a computer, smartphone, or tablet.

[0116] "Obtaining authentication and access permissions" refers to the process by which the server obtains the necessary authentication information and permissions to securely access a user's social networking account.

[0117] "Requesting confirmation" refers to the act of presenting the generated message to the user and requesting confirmation or correction of its contents.

[0118] "Modification" refers to a user making changes to a generated message to adjust its content.

[0119] "Final Reviewed Message" refers to the final content of the message after the user has reviewed it and made any necessary corrections.

[0120] "Posting" refers to the act of actually publishing a final, confirmed message from a user's social media account.

[0121] The present invention is a system that aims to improve the efficiency of users' SNS postings while preventing the posting of unintended content. This system involves a series of operations that acquires and analyzes the user's past posting history to generate posting patterns, and automatically generates new postings based on those patterns. Specific embodiments are described below.

[0122] System Overview

[0123] This system authenticates SNS accounts, acquires and saves call history, analyzes the history, generates call patterns, automatically generates new messages, allows users to confirm and edit them, and finally sends the message. These processes are performed by the server, the user's device, and the SNS account with appropriate authentication.

[0124] Hardware and software used

[0125] Server: A cloud server capable of high-performance processing and data storage (e.g., Amazon Web Services, Google Cloud Platform)

[0126] Devices: Computers, smartphones, and tablets that users use every day.

[0127] Database: Relational database management system such as MySQL (registered trademark), PostgreSQL, etc.

[0128] Natural language processing technology: Natural language processing libraries such as NLTK and spaCy

[0129] Generative AI models: Natural language generation models such as GPT-4 (registered trademark)

[0130] Details of data processing and calculation

[0131] 1. Authentication and Permissions:

[0132] A user accesses the system and logs in with a social networking account (e.g., Twitter). The server uses the OAuth protocol to obtain the authentication information and access permissions of the user's social networking account.

[0133] 2. Acquiring and saving call history:

[0134] The server retrieves the tweet history for the past year through the SNS API (e.g., Twitter API). The retrieved tweet history includes the tweet content, posting date and time, number of likes, number of comments, etc.

[0135] The server stores the retrieved data in a database.

[0136] 3. Analysis of call history:

[0137] The server analyzes the saved call history using natural language processing (NLP) techniques, such as topic modeling (e.g., Latent Dirichlet Allocation, LDA) and keyword extraction.

[0138] The analysis results identify frequently occurring topics, keywords, and communication trends.

[0139] 4. Generate call patterns:

[0140] The server then creates a calling pattern based on the analysis results. For example, if a user makes many calls on certain days of the week or during certain times of the day, it identifies that pattern.

[0141] 5. Automatic generation of new messages:

[0142] The server uses a generative AI model to generate new messages based on the message patterns and analysis results. For example, for a user who frequently talks about health, a message such as "Today's small health habit: I recommend drinking a glass of water first thing in the morning" may be generated.

[0143] 6. User Review and Correction:

[0144] The server sends the generated message to the user's terminal and asks for confirmation, "Is this message OK?"

[0145] The user checks the message and makes corrections if necessary, after which the corrected message is sent back to the server.

[0146] 7. Final Call:

[0147] The server then sends the message from the SNS account after the user has confirmed and corrected it. Once the message has been sent, the server notifies the user.

[0148] Examples of specific examples and prompts

[0149] Example: Using a Twitter account

[0150] 1. A user accesses the system and performs Twitter authentication.

[0151] 2. The server uses the Twitter API to retrieve tweets from the past year.

[0152] 3. The server stores the tweet data in a database.

[0153] 4. The server analyzes the tweet data using NLP technology, and finds results showing frequent health-related topics.

[0154] 5. The server creates a calling pattern related to "health."

[0155] 6. The server generates a new tweet saying, "Today's small health habit: I recommend drinking a glass of water first thing in the morning."

[0156] 7. The server sends the generated tweet to the user's device and asks for confirmation.

[0157] 8. The user checks and edits the message and sends the edited message to the server.

[0158] 9. The server sends the final confirmed tweet from the user's Twitter account and notifies the user that the tweet has been completed.

[0159] In this way, this system provides a series of steps necessary for users to post on SNS efficiently and safely. In particular, by analyzing past posting history and generating new posts based on the user's posting tendencies, the system can improve the consistency and quality of posts.

[0160] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0161] Step 1:

[0162] User logs in with social networking account

[0163] Input: Username and password, social media credentials

[0164] Action: The user accesses the system's login screen and enters their social network account credentials.

[0165] Output: Auth token and permissions to access social media accounts

[0166] The user clicks the "Login" button, and the server authenticates with the social network using the OAuth protocol, which gives the server permission to access the social network account from the user.

[0167] Step 2:

[0168] The server acquires the user's past call history

[0169] Input: Auth Token, SNS API

[0170] Process: The server sends a request to a social media API (e.g. Twitter API) using the obtained permissions.

[0171] Output: Tweet content, posting date and time, number of likes, number of comments, and other posting history data

[0172] The server retrieves tweet data from the social media account for the past year and receives it in JSON format.

[0173] Step 3:

[0174] The server saves the call history in a database

[0175] Input: Call history data

[0176] Processing: The server analyzes the received tweet data and stores the necessary information in a database.

[0177] Output: Call history stored in the database

[0178] The server connects to an SQL database (e.g., MySQL or PostgreSQL) and stores the extracted information in a table. This information includes the post date and time, content, and reactions (e.g., number of likes and comments).

[0179] Step 4:

[0180] The server analyzes the call history

[0181] Input: Call history stored in the database

[0182] Processing: The server analyzes the call history using natural language processing (NLP) techniques.

[0183] Output: Frequently appearing topics and keywords, user posting trends

[0184] Specifically, topic modeling (e.g., LDA) and keyword extraction are performed to identify whether topics such as "health" occur frequently.

[0185] Step 5:

[0186] The server generates the calling pattern

[0187] Input: Analysis results, frequently occurring topics and keywords

[0188] Processing: The server constructs a calling pattern based on the analysis results.

[0189] Output: Outgoing pattern

[0190] For example, it identifies a pattern, such as a user historically posting health-related tweets every Monday morning.

[0191] Step 6:

[0192] The server automatically generates a new message

[0193] Input: Transmission pattern, Generative AI model

[0194] Processing: The server generates a new message using a generative AI model based on the message pattern and analysis results.

[0195] Output: Auto-generated message

[0196] For example, based on a health-related topic, a message such as "Today's small health habit: It is recommended to drink a glass of water first thing in the morning" is generated.

[0197] Step 7:

[0198] The server sends a confirmation request to the user's device.

[0199] Input: Auto-generated message

[0200] Processing: The server sends the generated message to the user's terminal and displays a confirmation message saying, "This message will be sent. Are you sure?"

[0201] Output: User confirmation and correction requests

[0202] A notification is displayed on the user's device, and the user checks the message.

[0203] Step 8:

[0204] The user checks and edits the message

[0205] Input: Confirmation message, generated message

[0206] Action: The user checks the message displayed on the terminal and makes corrections if necessary.

[0207] Output: Corrected message

[0208] The user amends it to "I recommend drinking a glass of water first thing in the morning!" and resubmits it to the system.

[0209] Step 9:

[0210] The server makes the final call

[0211] Input: Corrected message

[0212] Processing: The server re-examines the revised message and sends it from the social media account.

[0213] Output: Update call history, notification of call completion

[0214] The final confirmed text is sent from the social media account, and the server notifies the user that the tweet has been completed.

[0215] (Application example 1)

[0216] 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."

[0217] In the past, users had to create, review, and post their own content on social media, which required a lot of time and effort. There was also the risk of posting unintended content or a lack of consistency in advertising. In addition, users had to come up with new copy each time they posted an ad, which was inefficient.

[0218] 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.

[0219] In this invention, the server includes means for acquiring a user's past transmission history, means for analyzing the past transmission history to generate a transmission pattern, means for automatically generating a new transmission based on the transmission pattern, means for sending the generated transmission to the user's terminal and requesting confirmation, means for re-acquiring a transmission modified by the user, means for posting the final confirmed transmission from the user's SNS account, means for acquiring the user's past advertising transmission history, means for analyzing the past advertising transmission history to generate a pattern related to an advertisement, means for automatically generating a new advertising copy using a generative AI model based on the advertising pattern, means for sending the generated advertising copy to the user's terminal and requesting confirmation, and for acquiring advertising copy modified by the user, and means for posting the final confirmed advertising copy from the user's SNS account. This reduces the burden on the user and enables efficient and safe management of SNS transmissions and advertising transmissions.

[0220] A "user" is a person who has an SNS account and uses the system to post messages and advertisements.

[0221] "Outgoing message history" is a record of messages sent by a user from their SNS account in the past, including information such as the date and time and responses.

[0222] The "calling pattern" refers to the regularity and tendency of a user's calls obtained by analyzing the past call history.

[0223] "Automatic generation" refers to the process by which the system generates new messaging or advertising copy without user intervention.

[0224] "Means for requesting confirmation" refers to a procedure for sending the generated message or advertisement copy to the user's terminal and prompting the user to confirm or correct it.

[0225] "SNS Account" means an account held by a User for the purpose of posting on an SNS platform.

[0226] "Natural language processing technology" refers to technology that enables systems to analyze, understand, and generate human language.

[0227] "Interface" means the user interface through which a user interacts with the system and modifies the generated messages and advertisements.

[0228] A "generative AI model" is a model that uses artificial intelligence and is used to automatically generate new messaging and advertising copy.

[0229] "Advertising history" is a record of the content of advertisements that a user has previously sent from their SNS account, including information such as the date and time and responses.

[0230] "Advertising patterns" refer to regularities and tendencies regarding a user's advertising that can be obtained by analyzing the past history of advertising transmissions.

[0231] This invention is a system for improving the efficiency of users' SNS and advertising activities and preventing the transmission of unintended content. This system acquires and analyzes the user's past communication history and advertising history to generate communication patterns and advertising patterns, and automatically generates new communication messages and advertising copies.

[0232] Hardware and software used

[0233] Hardware: User's smartphone, server

[0234] Software: Python, tweepy library, spacy library, generative AI model, database (e.g., PostgreSQL)

[0235] Processing steps

[0236] 1. Acquisition of the user's past call history and advertising call history

[0237] The server uses the API of the social media platform to obtain the user's past tweets and advertising history.

[0238] 2. Analysis of call history and advertising call history

[0239] The server stores the acquired call history and advertising call history in a database and analyzes them using natural language processing technology with the spacy library. Frequently occurring topics and keywords are extracted from the analysis results, and call patterns and advertising patterns are generated.

[0240] 3. Automatic generation of new messaging and advertising copy

[0241] The server uses a generative AI model to automatically generate new messaging and advertising copy based on the extracted patterns.

[0242] 4. User confirmation and correction

[0243] The generated message and advertisement copy are sent to the user's terminal, and a confirmation message such as "This message will be sent. Are you sure?" is displayed.

[0244] The user can modify the message and advertisement text through the interface, and the modified message and advertisement text are sent to the server for final confirmation.

[0245] 5. Making the final call

[0246] The message and advertisement confirmed by the user are sent from the SNS account via the server, and the server notifies the user when the message has been sent.

[0247] Specific examples

[0248] For example, if the user is on Twitter, it would look like this:

[0249] 1. A user logs in with their Twitter account: The server uses the Twitter API to retrieve tweets and advertising history from the past year.

[0250] 2. Analysis of tweet and advertising history: The server analyzes the data to extract frequently occurring keywords such as "health," "fitness," and "diet," and generates tweet and advertising patterns.

[0251] 3. Generate new Tweets and ad copy: Use generative AI models to automatically generate new tweets and ad copy, such as "Experience the latest health news now!"

[0252] 4. User confirmation: The user receives a message saying, "This message will be sent. Are you sure?" If necessary, the user can make corrections and send the message again to the server.

[0253] 5. Final Posting: The final, verified post and copy will be sent from your Twitter account and you will be notified.

[0254] Prompt Sentence Examples

[0255] "Analyze past tweets and extract frequently occurring keywords."

[0256] "Generate new ad text based on this keyword."

[0257] "Please have the user review the generated ad copy and then send it out as is."

[0258] In this way, this system helps users to efficiently manage their social media and advertising activities.

[0259] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0260] Step 1:

[0261] The server retrieves the user's past posting history and advertising posting history from the user's SNS account. Specifically, it retrieves the necessary data using the SNS platform's API. The input is the user's SNS account information, and the output is the retrieved past posting history.

[0262] Step 2:

[0263] The server saves the acquired calling history and ad sending history in a database. In this step, a database connection is established and the acquired data is saved in an appropriate format. The input is the acquired calling history and ad sending history, and the output is the saved database entry.

[0264] Step 3:

[0265] The server uses natural language processing technology to analyze the stored call history. Specifically, it uses the spacy library to extract frequently occurring topics and keywords. The input is the call history stored in the database, and the output is the extracted keywords and topics.

[0266] Step 4:

[0267] The server generates transmission patterns and advertising patterns based on the analysis results. Here, the user's transmission tendencies are identified based on the extracted keywords and topics. The input is the extracted keywords and topics, and the output is the generated transmission patterns and advertising patterns.

[0268] Step 5:

[0269] The server automatically generates new message and advertising copy using a generative AI model. The model is provided with message and advertising patterns as input and generates appropriate text. The input is the message and advertising patterns, and the output is the generated new message and advertising copy.

[0270] Step 6:

[0271] The server sends the generated message and advertisement copy to the user's terminal and asks for confirmation. In this step, a confirmation message is displayed to the user. The input is the generated message and advertisement copy, and the output is a confirmation message displayed on the user's terminal.

[0272] Step 7:

[0273] The user uses an interface to modify the message and advertisement copy. The modified content is sent back to the server. The input is the message and advertisement copy modified by the user, and the output is the modified content.

[0274] Step 8:

[0275] The server retrieves the message and advertisement copy corrected by the user again and performs a final confirmation. In this step, the confirmed content is displayed to the user again and sent after confirmation. The input is the corrected message and advertisement copy, and the output is the final confirmed message and advertisement copy.

[0276] Step 9:

[0277] The server posts the final confirmed message and advertisement copy from the user's SNS account. Once the message is completed, the server sends a notification to the user. The input is the final confirmed message and advertisement copy, and the output is the content posted on the SNS platform and a notification to the user.

[0278] 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.

[0279] The present invention provides a system that improves the efficiency of users' SNS postings, prevents the posting of unintended content, and enables postings that reflect the user's emotions. Specific embodiments of this system are described below.

[0280] System Overview

[0281] This system involves a series of operations: acquiring and analyzing a user's past communication history to generate communication patterns, and automatically generating new messages based on these communication patterns. It also combines an emotion engine to recognize the user's emotions and reflect them in the messages, enabling more personal and emotionally rich messages. The generated messages are then requested to be confirmed and revised by the user, and the final confirmed content is sent from the SNS account.

[0282] Program processing overview

[0283] 1. Get call history from user's SNS account:

[0284] The server accesses the user's social media account and uses the API to retrieve past postings, such as tweets, posts, and comments.

[0285] 2. Save call history:

[0286] The acquired posting history is saved in a database. Each posting history includes the posting date and time, content, and reactions (number of likes, number of comments, etc.).

[0287] 3. Analysis of call history:

[0288] The server uses natural language processing (NLP) technology to analyze call history and extract keywords, frequently occurring themes, and user trends.

[0289] 4. Generate call patterns:

[0290] Based on the analysis results, the server creates a calling pattern. For example, if there are many calls made on a particular day of the week or during a particular time period, it will extract that pattern.

[0291] 5. Sentiment analysis using emotion engine:

[0292] The server uses an emotion engine to recognize the user's emotions from the call history and analyze the emotional trends.

[0293] 6. Automatic generation of new messages:

[0294] The server automatically generates new messages based on the results of the user's communication patterns and emotion analysis. For example, if a user has frequently sent messages expressing "fun" emotions in the past, the server will generate messages that reflect those emotions.

[0295] 7. Request confirmation of message:

[0296] The generated message is sent to the user's terminal, and a confirmation message is displayed saying, "This message will be sent. Are you sure?"

[0297] 8. User Modifications and Verification:

[0298] The user checks the message and corrects it if necessary. Once the corrections are complete, the user presses the approval button to send the confirmation.

[0299] 9. Making the final call:

[0300] The server sends the message confirmed by the user from the SNS account, and notifies the user when the message is complete.

[0301] Specific examples

[0302] Example 1: Using a Twitter account

[0303] 1. User logs in:

[0304] A user accesses the system and logs in with their Twitter account. The system obtains permission to access the SNS account.

[0305] 2. Get past tweets:

[0306] The server uses the Twitter API to retrieve tweets from the past year, including the tweet content, posting date and time, and reaction status.

[0307] 3. Tweet analysis:

[0308] The server analyzes the collected tweet data using NLP techniques, including topic models (e.g., Latent Dirichlet Allocation) and keyword extraction.

[0309] 4. Creating a calling pattern:

[0310] The server generates a posting pattern from the analysis results. For example, if there are many tweets about "health," it identifies that pattern.

[0311] 5. Emotion analysis:

[0312] The server uses an emotion engine to analyze the user's emotions from the content of past tweets and identify emotions such as joy, sadness, and excitement.

[0313] 6. Automatically generate new tweets:

[0314] The server generates new tweets that reflect the "fun" emotion based on the emotion and the sending pattern. For example, a tweet like "Today is another great day! My first walk of the morning was amazing."

[0315] 7. User confirmation prompts:

[0316] The server sends the generated tweet to the user's device and displays the message, "This text will be sent. Is this OK?"

[0317] 8. User Modifications:

[0318] The user checks the tweet and corrects it to "My first walk of the morning was amazing!"

[0319] 9. Sending Tweets:

[0320] The server posts the corrected tweet from your Twitter account. After posting is complete, the server notifies the user that the tweet has been posted.

[0321] In this way, the present invention allows users to safely and efficiently send messages on social networking sites without feeling any burden. By analyzing the user's past message history and emotions, automatically generating new messages and prompting the user for confirmation, the risk of sending unintended content is prevented. Furthermore, by generating messages that reflect the user's emotions, more personal and emotional communication is realized.

[0322] The processing flow will be explained below.

[0323] Step 1:

[0324] A user accesses the system and logs in with their SNS account. The user then grants permission to access the system.

[0325] Step 2:

[0326] The server uses the SNS API to retrieve the user's past posting history (e.g., tweets and posts from the past year).

[0327] Step 3:

[0328] The server saves the acquired posting history in a database. The posting history includes information on the posting date and time, content, and reactions (number of likes, number of comments, etc.).

[0329] Step 4:

[0330] The server uses natural language processing (NLP) technology to analyze the saved call history and extract keywords, frequently occurring themes, and user trends.

[0331] Step 5:

[0332] The server generates a user's posting pattern based on the analysis results, which includes posting tendencies for specific topics and time periods.

[0333] Step 6:

[0334] The server uses an emotion engine to recognize and analyze the user's emotions contained in the communication history. For example, if the past communication contains a lot of "fun" content, the emotion is identified.

[0335] Step 7:

[0336] The server automatically generates new messages based on the user's message patterns and the results of emotion analysis. For example, if a user posts a lot of health-related information and has a "happy" emotion, the server generates a message like this: "It's another great day! Drink a glass of water first thing in the morning and have a healthy day."

[0337] Step 8:

[0338] The server sends the generated message to the user's terminal and displays a confirmation message saying, "This message will be sent. Are you sure?"

[0339] Step 9:

[0340] The user checks the message generated on the device and modifies it as necessary. For example, they can modify it to "It's another great day today!" Once the modifications are complete, the user presses the approval button to send the confirmation.

[0341] Step 10:

[0342] The server receives the revised message sent by the user, performs a final check, and confirms the approved message as the final message.

[0343] Step 11:

[0344] The server posts the final confirmed message from the user's SNS account.

[0345] Step 12:

[0346] After the posting is complete, the server sends a notification to the user saying "Posting is complete." The user receives the notification and confirms that the posting has been completed successfully.

[0347] Example 2

[0348] 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."

[0349] In the conventional SNS posting process, users must manually consider what to post, which takes time and effort. There is also a risk of posting unintended content. Furthermore, it is difficult to post content that reflects the user's emotions. There is a need for a system that can solve these problems and enable users to post on SNS efficiently and safely.

[0350] 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.

[0351] In this invention, the server includes means for acquiring a user's past transmission history, means for analyzing the past transmission history to generate transmission patterns and emotional tendencies, means for automatically generating new transmission messages based on the transmission patterns and emotional tendencies, means for sending the generated transmission messages to the user's terminal and requesting confirmation, means for reacquiring transmission messages corrected by the user, and means for posting the final confirmed transmission message from the user's SNS account. This enables the user to efficiently generate new posts based on the past transmission history and emotional tendencies, check and correct them to prevent transmission of unintended content, and ultimately safely transmit transmission messages that reflect their emotions.

[0352] "A user's past posting history" refers to data such as the content posted by the user in the past through their social media account, the posting date and time, the number of likes, comments, and retweets.

[0353] "Analysis" refers to the process of analyzing communication history using natural language processing technology and an emotion engine to extract keywords, analyze topics, and score emotions.

[0354] "Communication patterns" refer to the frequency of posts on specific days or time periods, frequently occurring topics, and user posting tendencies extracted based on the user's past communication history that has been acquired and analyzed.

[0355] "Emotional tendency" is calculated by analyzing emotions from a user's past communication history using an emotion engine, and indicates the frequency and patterns of emotions such as positive, negative, and neutral.

[0356] "Automatic generation of new messages" refers to the process of automatically generating new social media post content using a generative AI model based on acquired and analyzed message patterns and emotional tendencies.

[0357] "Generative AI model" refers to an artificial intelligence model that generates sentences in natural language based on input prompts, including, for example, language models.

[0358] The "means for requesting confirmation" refers to a process of sending an automatically generated message to the user's terminal and providing an interface that prompts the user to confirm the message content.

[0359] The "means for re-obtaining the corrected message" refers to the process in which the server re-obtains the content of the message that the user has modified and then performs a final check.

[0360] "Final confirmed message" refers to the final message retrieved by the server after the user has confirmed and made any necessary corrections.

[0361] "SNS Account" refers to a personal or corporate account used by a User through registration and authentication on an SNS platform.

[0362] System Overview

[0363] This invention is a system that improves the efficiency of users' SNS posting, prevents the posting of unintended content, and enables posting that reflects the user's emotions. Specifically, this system analyzes the user's past posting history and automatically generates new messages based on their posting patterns and emotional tendencies. This system is operated through the interaction of a server, terminals, and users.

[0364] Hardware and Software Configuration

[0365] The server has the following main components:

[0366] Database: Used to store user call history, for example, using an RDBMS such as MySQL.

[0367] Natural language processing (NLP) engine: Analyzes call history using Python libraries such as nltk and spacy.

[0368] Emotion Engine: Uses libraries such as TextBlob and VADER to analyze user emotions.

[0369] Generative AI model: Generate new messages using a generative AI model (e.g., a language model).

[0370] The device is used by the user to check and edit messages sent, and a web browser or smartphone app is used.

[0371] Users are responsible for logging into the system, granting API access permissions, and reviewing and modifying generated messages.

[0372] Data processing and calculation

[0373] 1. Get call history:

[0374] The server uses the API of the SNS platform to obtain the user's past communication history.

[0375] For example, using the Twitter API, access the GET statuses / user_timeline endpoint.

[0376] 2. Save call history:

[0377] The acquired call history is saved in a database (such as MySQL).

[0378] Data such as the posting date and time of each message, content, number of likes, number of retweets, and number of comments are saved.

[0379] 3. Analysis of call history:

[0380] The server uses an NLP engine to analyze call history and perform keyword extraction and topic analysis.

[0381] Use Python's nltk and spacy libraries to tokenize the text and extract noun phrases.

[0382] 4. Generating communication patterns and sentiment trends:

[0383] The server generates communication patterns and emotional tendencies based on the analysis results.

[0384] Use a sentiment engine (TextBlob or VADER) to calculate a sentiment score for each call.

[0385] 5. Automatic generation of new messages:

[0386] The server automatically generates new messages using a generative AI model.

[0387] For example, a prompt sentence such as "The user has posted a lot of fun content in the past" is input into the generative AI model.

[0388] Specific examples

[0389] Example 1: Twitter account operation

[0390] 1. User logs in:

[0391] A user accesses the system and logs in with their Twitter account.

[0392] The system will ask for permission to access your social media account.

[0393] 2. Get past tweets:

[0394] The server uses the Twitter API to retrieve tweets from the past year.

[0395] The retrieved tweets include the tweet content, posting date and time, and reaction status.

[0396] 3. Tweet analysis:

[0397] The tweet data collected by the server is analyzed using NLP technology.

[0398] Analysis includes topic models (e.g., Latent Dirichlet Allocation) and keyword extraction.

[0399] 4. Building communication patterns and sentiment trends:

[0400] The server generates communication patterns and emotional tendencies from the analysis results.

[0401] For example, if emotions such as "health" or "fun" are common, patterns that reflect this can be identified.

[0402] 5. Auto-generate new tweets:

[0403] The server generates new tweets that reflect the emotion of "fun" based on the emotion and the sending pattern.

[0404] For example, by inputting the prompt sentence "The user has posted a lot of fun content in the past" into the generative AI model, it generates "Today is another wonderful day! The first walk of the morning was great."

[0405] 6. User confirmation prompts:

[0406] The server sends the generated tweet to the user's device and displays a confirmation message saying, "This text will be sent. Are you sure?"

[0407] 7. User Modifications:

[0408] The user checks the tweet and corrects it to "My first walk of the morning was amazing!"

[0409] 8. Sending Tweets:

[0410] The server posts the corrected tweet from your Twitter account.

[0411] After the posting is complete, the server notifies the user that the tweet has been posted.

[0412] As described above, this invention allows users to safely and efficiently send messages on social networking sites without feeling any burden. It analyzes the user's past message history and emotions, automatically generates new messages, and prompts the user for confirmation, preventing the risk of sending unintended content. Furthermore, by generating messages that reflect the user's emotions, it enables more personal and emotionally rich communication.

[0413] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0414] Step 1:

[0415] Acquiring call history

[0416] The server uses the SNS platform's API to obtain the user's past communication history.

[0417] Input: User credentials and API endpoint.

[0418] Specific operation: Accesses a social media API (e.g., Twitter API) and retrieves past tweet data from the GET statuses / user_timeline endpoint. The request includes an access token.

[0419] Output: The acquired posting history data (e.g. tweet content, posting date and time, number of likes, number of retweets, number of comments) is returned to the server.

[0420] Step 2:

[0421] Save call history

[0422] The server stores the acquired call history in a database.

[0423] Input: Call history data.

[0424] What it does: It connects to a database such as MySQL and executes a SQL query like INSERT INTO posts (date, content, likes, retweets, comments) VALUES (...) to store historical data.

[0425] Output: Each call history stored in the database.

[0426] Step 3:

[0427] Analysis of call history

[0428] The server analyzes the call history using a natural language processing (NLP) engine.

[0429] Input: Saved call history data.

[0430] How it works: It uses Python's nltk and spacy libraries to extract keywords, tokenize text, and extract noun phrases, and also applies algorithms such as Latent Dirichlet Allocation (LDA) to perform topic analysis.

[0431] Output: Keyword list, topic model, data on user posting habits.

[0432] Step 4:

[0433] Generating communication patterns and sentiment trends

[0434] The server generates communication patterns and emotional tendencies based on the analysis results.

[0435] Input: Analysis results (keyword list, topic model, etc.).

[0436] How it works: The server uses an emotion engine (such as TextBlob or VADER) to calculate the emotion score (positive, negative, neutral, etc.) of each post, and performs frequency and trend analysis. It also analyzes the frequency of posts by day of the week and time of day.

[0437] Output: Posting pattern data (e.g., frequency of posts on specific days or times), sentiment data (e.g., many positive posts).

[0438] Step 5:

[0439] Automatic generation of new messages

[0440] The server automatically generates new messages using a generative AI model.

[0441] Input: Call pattern and emotional tendency data, prompt sentence.

[0442] Specific operation: A prompt sentence is input into the generative AI model to generate a new message. For example, the prompt sentence can be "The user has posted many enjoyable messages in the past," and the model will generate a new sentence based on that.

[0443] Output: The new message generated.

[0444] Step 6:

[0445] Request confirmation of message

[0446] The server sends the generated message to the user's terminal and asks for confirmation.

[0447] Input: The generated message.

[0448] Specific operation: The generated message is sent to the user's device, and a confirmation message is displayed saying, "This message will be sent. Are you sure?"

[0449] Output: A confirmation message that is displayed on the user's terminal.

[0450] Step 7:

[0451] User correction and confirmation

[0452] The user checks the generated message and makes corrections as necessary.

[0453] Input: User feedback and corrections.

[0454] Specific operation: The user checks the message and, if they wish to modify it, enters the modifications in the input field and presses the approve button. The modified message is then sent to the server.

[0455] Output: Revised statement and final approval by the user.

[0456] Step 8:

[0457] Making the final call

[0458] The server posts the message confirmed by the user from the SNS account.

[0459] Input: Revised, last confirmed outgoing statement.

[0460] Specific operation: Send the revised message to the POST statuses / update endpoint of the SNS API (e.g., Twitter API) and execute the post.

[0461] Output: The message content published on the social media platform and notification of message completion.

[0462] (Application example 2)

[0463] 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."

[0464] In today's information-saturated society, users are overwhelmed by the amount of information available when using social networking services and content distribution services, making it difficult to send and receive content that is appropriate and emotionally appropriate. Furthermore, there is a lack of efficient ways to receive content that reflects one's own emotions or to obtain recommended content based on individual viewing history. Therefore, there is a need for a system that supports user-friendly, more personalized sending and content consumption.

[0465] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0466] In this invention, the server includes means for acquiring a user's past calling history, means for analyzing the past calling history to generate a calling pattern, means for automatically generating a new message based on the calling pattern, means for sending the new message to the user's terminal and requesting confirmation, means for reacquiring a message revised by the user, means for posting the final confirmed message from the user's SNS account, means for acquiring and analyzing the user's viewing history and emotion data to generate a new recommendation, means for sending the generated recommendation to the user's terminal and requesting confirmation, means for reacquiring a recommendation revised by the user, and means for saving the final confirmed recommendation. This enables users to efficiently make personalized calls and receive content recommendations based on their own emotions and viewing history.

[0467] "A user's past posting history" refers to a record of activities such as posts, comments, and shares that a user has made in the past on social media or other platforms.

[0468] "Communication patterns" are characteristic behavioral patterns, such as tendencies, frequently occurring themes, and posting timing, that are extracted by analyzing a user's past communication history.

[0469] A "new message" is a message that is automatically generated based on a message pattern and that the user will send in the future.

[0470] "Viewing history" is a record of videos, music, and other content that a user has viewed in the past.

[0471] "Emotion data" is information about emotions acquired from the user's facial expressions, reactions, feedback, etc. while watching.

[0472] A "recommendation" is a description of content recommended to a user, generated by analyzing viewing history and emotional data.

[0473] "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language.

[0474] An "interface" is the input and output means by which a user interacts with a system.

[0475] The present invention relates to a system for acquiring and analyzing a user's past sending history to generate new messages and recommendations. Specific embodiments will be described below.

[0476] Hardware and software used

[0477] This system mainly uses the following hardware and software:

[0478] Hardware: Smartphone, facial recognition camera (used to capture user emotion data)

[0479] Software: Python (programming language), natural language processing library "spaCy", sentiment analysis engine "Affectiva SDK", cloud database "Firebase"

[0480] System configuration

[0481] 1. Acquiring the user's past call history

[0482] The server obtains past call history from the user's SNS account.

[0483] This history is stored in a cloud database.

[0484] 2. Analysis of call history

[0485] The server analyzes the acquired call history using natural language processing technology (spaCy).

[0486] A call pattern is generated from the analysis results.

[0487] 3. Obtaining viewing history and emotion data

[0488] The server obtains the user's viewing history from their smartphone and collects emotional data using a facial recognition camera.

[0489] 4. Generating Recommendations

[0490] The server analyzes the viewing history and emotional data to generate new recommendations.

[0491] 5. Check the generated message and testimonials

[0492] The generated document is sent to the user's terminal and a confirmation message is displayed.

[0493] The user checks the document and makes corrections if necessary.

[0494] 6. Final confirmation and sending / saving

[0495] After the user has reviewed and corrected the document, it will be posted to the social media account after a final review, and the recommendation will be stored in a cloud database.

[0496] Data processing and calculation

[0497] Natural language processing: The server uses spaCy to analyze call history and extract keywords and frequently occurring themes.

[0498] Emotion analysis: The server uses the Affectiva SDK to analyze the facial recognition camera data of the user while watching to obtain emotional data.

[0499] Data storage and retrieval: We use the cloud database Firebase to store and manage user viewing history and generated documents.

[0500] Specific examples

[0501] Example 1: Using a Twitter account

[0502] 1. User logs in

[0503] A user accesses the system and logs in with a social networking account. The system obtains permission to access the social networking account.

[0504] 2. Obtain past activity history

[0505] The server uses the SNS API to obtain past call history.

[0506] 3. History Analysis

[0507] The call history collected by the server is analyzed using NLP technology.

[0508] 4. Generating Call Patterns

[0509] The server generates a transmission pattern from the analysis results.

[0510] 5. Emotion analysis

[0511] The server uses an emotion engine to analyze the user's emotions from the data from the facial recognition camera.

[0512] 6. Automatic generation of new messages

[0513] The server generates a new message based on the emotion and the message pattern.

[0514] 7. User Review of Documents

[0515] The generated document is sent to the user's terminal, and a message is displayed saying, "This document will be sent. Is this OK?"

[0516] 8. Transmission and storage

[0517] The document that the user has checked is posted via their social media account, and the recommendation is also saved in a cloud database.

[0518] Prompt Sentence Examples

[0519] Generate content recommendations for users based on their viewing history and emotional data. The viewing history is "e.g., frequently watches action movies, dramas, and comedies," and the emotional data is "e.g., smile, excitement, surprise."

[0520] By following the above procedure, users can efficiently send personal and emotional messages and recommend content.

[0521] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0522] Step 1:

[0523] The server retrieves past posting history from the user's SNS account. To do this, it uses the SNS's API and obtains account access permission with the user's consent. It receives SNS authentication information as input and retrieves posting history data as output. This data includes the content of the post, date and time, and reaction status (number of likes, number of comments, etc.).

[0524] Step 2:

[0525] The server stores the acquired call history in a cloud database to securely store the history data for later analysis. It receives the call history data as input and updates the database as output.

[0526] Step 3:

[0527] The server analyzes the saved call history using natural language processing technology (spaCy). It receives call history data as input, analyzes the data, and extracts keywords, frequently occurring themes, and the user's call trends as output. This analysis generates the user's call patterns.

[0528] Step 4:

[0529] The server acquires the user's viewing history and emotional data. It collects the viewing history from the user's smartphone and acquires the emotional data through a facial recognition camera. It receives the viewing history and the emotional data from the facial recognition camera as input and stores these data in a cloud database as output.

[0530] Step 5:

[0531] The server analyzes the viewing history and emotional data to generate new recommendations. It receives the viewing history and emotional data as input, analyzes them, and generates personalized recommendations as output. These recommendations are based on the user's interests and emotions.

[0532] Step 6:

[0533] The server sends the generated message and recommendation to the user's device and displays a confirmation message. It receives the generated message and recommendation as input and outputs them to the user's device. The message reads, "This message will be sent. Are you sure?"

[0534] Step 7:

[0535] The user checks the message and recommendation sent and makes corrections if necessary. The system receives the generated message and recommendation as input and outputs the corrected results.

[0536] Step 8:

[0537] The server retrieves the message modified by the user again and performs a final check. It receives the message modified by the user as input, checks it, and saves the final checked message as output.

[0538] Step 9:

[0539] The server posts the finalized message from the user's SNS account and saves the recommendation in a cloud database. The server receives the finalized message and recommendation as input, posts the message to the SNS account, saves the recommendation in the database, and notifies the user of the result.

[0540] Through the above steps, users can efficiently send personal messages and receive content recommendations based on their own emotions and viewing history.

[0541] 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.

[0542] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0543] 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.

[0544] [Second embodiment]

[0545] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0546] 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.

[0547] 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).

[0548] 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.

[0549] 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.

[0550] 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).

[0551] 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.

[0552] 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.

[0553] 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.

[0554] 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.

[0555] In the smart glasses 214, 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.

[0556] 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."

[0557] The present invention provides a system for preventing users from posting unintended content while improving the efficiency of posting on SNS. Specific embodiments of this system are described below.

[0558] System Overview

[0559] This system involves a series of operations: acquiring and analyzing a user's past call history to generate call patterns, automatically generating new messages based on these call patterns, prompting the user to confirm and revise the generated messages, and finally sending the confirmed content from the SNS account.

[0560] Program processing overview

[0561] 1. Get call history from user's SNS account:

[0562] The server accesses the user's social media account and uses the API to retrieve past postings, such as tweets, posts, and comments.

[0563] 2. Save call history:

[0564] The acquired posting history is saved in a database. Each posting history contains information such as the posting date and time, content, and reactions (number of likes, number of comments, etc.).

[0565] 3. Analysis of call history:

[0566] The server uses natural language processing (NLP) technology to analyze the posting history, extracting frequently occurring topics, keywords, and user posting trends.

[0567] 4. Generate call patterns:

[0568] Based on the analysis results, the server creates a calling pattern. For example, if there are many calls made on a particular day of the week or during a particular time period, it will extract that pattern.

[0569] 5. Automatic generation of new messages:

[0570] The server automatically generates new messages based on the user's posting patterns. For example, for a user who posts a lot of health-related information, the server generates the following message: "Today's small health habit: I recommend drinking a glass of water first thing in the morning."

[0571] 6. Request confirmation of message:

[0572] The generated message is sent to the user's terminal, and a confirmation message is displayed saying, "This message will be sent. Are you sure?"

[0573] 7. User Modifications and Verification:

[0574] The user checks the message and corrects it if necessary. The corrected message is then sent back to the server.

[0575] 8. Making the final call:

[0576] The server sends the message confirmed by the user from the SNS account, and notifies the user when the message is complete.

[0577] Specific examples

[0578] Example 1: Using a Twitter account

[0579] 1. User logs in:

[0580] A user accesses the system and logs in with their Twitter account. The system obtains permission to access the SNS account.

[0581] 2. Get past tweets:

[0582] The server uses the Twitter API to retrieve tweets from the past year, including the tweet content, posting date and time, and reaction status.

[0583] 3. Tweet analysis:

[0584] The server analyzes the collected tweet data using NLP techniques, including topic models (e.g., Latent Dirichlet Allocation) and keyword extraction.

[0585] 4. Creating a calling pattern:

[0586] The server generates a posting pattern from the analysis results. For example, if there are many tweets about "health," it identifies that pattern.

[0587] 5. Auto-generate new tweets:

[0588] The server automatically generates new tweets about "health." For example, the content generated is "Today's small health habit: I recommend drinking a glass of water first thing in the morning."

[0589] 6. User confirmation prompts:

[0590] The server sends the generated tweet to the user's device and displays the message, "This text will be sent. Is this OK?"

[0591] 7. User Modifications:

[0592] The user reviews the tweet and corrects it to "I recommend drinking a glass of water first thing in the morning!"

[0593] 8. Sending Tweets:

[0594] The server posts the corrected tweet from your Twitter account. After posting is complete, the server notifies the user that the tweet has been posted.

[0595] In this way, the present invention allows users to safely and efficiently send messages on SNS without feeling any burden. By obtaining analysis results from the user's past message history, automatically generating new messages and prompting the user for confirmation, the risk of sending unintended content is prevented.

[0596] The processing flow will be explained below.

[0597] Step 1:

[0598] A user accesses the system and logs in with their SNS account. The user then grants permission to access the system.

[0599] Step 2:

[0600] The server uses the SNS API to retrieve the user's past posting history (e.g., tweets and posts from the past year).

[0601] Step 3:

[0602] The server saves the acquired posting history in a database. The posting history includes information on the posting date and time, content, and reactions (number of likes, number of comments, etc.).

[0603] Step 4:

[0604] The server uses natural language processing (NLP) technology to analyze the saved call history and extract keywords, frequently occurring themes, and user trends.

[0605] Step 5:

[0606] The server generates a user's posting pattern based on the analysis results, which includes posting tendencies for specific topics and time periods.

[0607] Step 6:

[0608] The server automatically generates new messages based on the user's posting patterns and current trends. For example, if the user posts a lot of health-related information, it generates new health-related messages.

[0609] Step 7:

[0610] The server sends the generated message to the user's terminal and displays the message "This message will be sent. Is this OK?"

[0611] Step 8:

[0612] The user checks the message generated on the device, corrects the wording as necessary, and once corrections are complete, the user presses the approval button to send the confirmation.

[0613] Step 9:

[0614] The server receives the corrected message sent by the user and performs a final check.

[0615] Step 10:

[0616] The server posts the final confirmed message from the user's SNS account.

[0617] Step 11:

[0618] After the posting is complete, the server sends a notification to the user saying "Posting is complete."

[0619] In this way, each step reduces the burden on the user while preventing unintended transmission of content.

[0620] Example 1

[0621] 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."

[0622] In today's social networking sites, users frequently post, but it is difficult to maintain efficient, high-quality communication. There is also a risk of unintentionally posting inappropriate content. For example, users may forget the content and time of previous posts, making it difficult to generate new ideas. Furthermore, reviewing and revising posts takes time, placing a burden on users. The present invention aims to solve these problems and enable users to post on social networking sites efficiently and safely.

[0623] 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.

[0624] In this invention, the server includes means for obtaining authentication and access permission for the user's SNS account, means for obtaining the user's past transmission history, means for saving the transmission history in a database, means for using natural language processing technology to analyze the transmission history, means for generating transmission patterns, means for automatically generating new transmissions using a generative AI model, means for sending the generated transmissions to the user's device and requesting confirmation, means for re-obtaining transmissions modified by the user, and means for posting the final confirmed transmissions from the user's SNS account. This enables users to transmit efficiently and consistently based on past transmission content and patterns, reducing the risk of transmitting unintended content and enabling them to easily continue posting high-quality content.

[0625] "User" refers to an individual or corporation that has an SNS account and uses that account to conduct communication activities.

[0626] "SNS account" refers to an account used by a user on a social networking service (SNS), including accounts on services such as Twitter, Facebook, and Instagram.

[0627] "Outgoing communication history" refers to digital records of posts, tweets, comments, messages, etc. that a user has made in the past from their social media account.

[0628] A "database" refers to a digital system for efficiently storing, managing, and searching data such as call history and analysis results.

[0629] "Natural language processing technology" is a technology for analyzing, understanding, and generating human language using computers, and includes techniques such as topic modeling and keyword extraction.

[0630] "Calling pattern" refers to a pattern or tendency regarding a particular day of the week, time period, or content of calls, derived from an analysis of a user's past calling history.

[0631] "Generative AI model" refers to an algorithm or program that uses artificial intelligence to generate new messages, and specifically includes natural language generation models.

[0632] "New messages" refers to text content for posting on social media that is automatically generated based on the user's messaging patterns.

[0633] "User's device" refers to a digital device used by a user, such as a computer, smartphone, or tablet.

[0634] "Obtaining authentication and access permissions" refers to the process by which the server obtains the necessary authentication information and permissions to securely access a user's social networking account.

[0635] "Requesting confirmation" refers to the act of presenting the generated message to the user and requesting confirmation or correction of its contents.

[0636] "Modification" refers to a user making changes to a generated message to adjust its content.

[0637] "Final Reviewed Message" refers to the final content of the message after the user has reviewed it and made any necessary corrections.

[0638] "Posting" refers to the act of actually publishing a final, confirmed message from a user's social media account.

[0639] The present invention is a system that aims to improve the efficiency of users' SNS postings while preventing the posting of unintended content. This system involves a series of operations that acquires and analyzes the user's past posting history to generate posting patterns, and automatically generates new postings based on those patterns. Specific embodiments are described below.

[0640] System Overview

[0641] This system authenticates SNS accounts, acquires and saves call history, analyzes the history, generates call patterns, automatically generates new messages, allows users to confirm and edit them, and finally sends the message. These processes are performed by the server, the user's device, and the SNS account with appropriate authentication.

[0642] Hardware and software used

[0643] Server: Cloud server for high-performance processing and data storage (e.g., Amazon Web Services, Google Cloud Platform)

[0644] Devices: Computers, smartphones, and tablets that users use every day.

[0645] Database: Relational database management system such as MySQL, PostgreSQL

[0646] Natural language processing technology: Natural language processing libraries such as NLTK and spaCy

[0647] Generative AI models: Natural language generation models such as GPT-4

[0648] Details of data processing and calculation

[0649] 1. Authentication and Permissions:

[0650] A user accesses the system and logs in with a social networking account (e.g., Twitter). The server uses the OAuth protocol to obtain the authentication information and access permissions of the user's social networking account.

[0651] 2. Acquiring and saving call history:

[0652] The server retrieves the tweet history for the past year through the SNS API (e.g., Twitter API). The retrieved tweet history includes the tweet content, posting date and time, number of likes, number of comments, etc.

[0653] The server stores the retrieved data in a database.

[0654] 3. Analysis of call history:

[0655] The server analyzes the saved call history using natural language processing (NLP) techniques, such as topic modeling (e.g., Latent Dirichlet Allocation, LDA) and keyword extraction.

[0656] The analysis results identify frequently occurring topics, keywords, and communication trends.

[0657] 4. Generate call patterns:

[0658] The server then creates a calling pattern based on the analysis results. For example, if a user makes many calls on certain days of the week or during certain times of the day, it identifies that pattern.

[0659] 5. Automatic generation of new messages:

[0660] The server uses a generative AI model to generate new messages based on the message patterns and analysis results. For example, for a user who frequently talks about health, a message such as "Today's small health habit: I recommend drinking a glass of water first thing in the morning" may be generated.

[0661] 6. User Review and Correction:

[0662] The server sends the generated message to the user's terminal and asks for confirmation, "Is this message OK?"

[0663] The user checks the message and makes corrections if necessary, after which the corrected message is sent back to the server.

[0664] 7. Final Call:

[0665] The server then sends the message from the SNS account after the user has confirmed and corrected it. Once the message has been sent, the server notifies the user.

[0666] Examples of specific examples and prompts

[0667] Example: Using a Twitter account

[0668] 1. A user accesses the system and performs Twitter authentication.

[0669] 2. The server uses the Twitter API to retrieve tweets from the past year.

[0670] 3. The server stores the tweet data in a database.

[0671] 4. The server analyzes the tweet data using NLP technology, and finds results showing frequent health-related topics.

[0672] 5. The server creates a calling pattern related to "health."

[0673] 6. The server generates a new tweet saying, "Today's small health habit: I recommend drinking a glass of water first thing in the morning."

[0674] 7. The server sends the generated tweet to the user's device and asks for confirmation.

[0675] 8. The user checks and edits the message and sends the edited message to the server.

[0676] 9. The server sends the final confirmed tweet from the user's Twitter account and notifies the user that the tweet has been completed.

[0677] In this way, this system provides a series of steps necessary for users to post on SNS efficiently and safely. In particular, by analyzing past posting history and generating new posts based on the user's posting tendencies, the system can improve the consistency and quality of posts.

[0678] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0679] Step 1:

[0680] User logs in with social networking account

[0681] Input: Username and password, social media credentials

[0682] Action: The user accesses the system's login screen and enters their social network account credentials.

[0683] Output: Auth token and permissions to access social media accounts

[0684] The user clicks the "Login" button, and the server authenticates with the social network using the OAuth protocol, which gives the server permission to access the social network account from the user.

[0685] Step 2:

[0686] The server acquires the user's past call history

[0687] Input: Auth Token, SNS API

[0688] Process: The server sends a request to a social media API (e.g. Twitter API) using the obtained permissions.

[0689] Output: Tweet content, posting date and time, number of likes, number of comments, and other posting history data

[0690] The server retrieves tweet data from the social media account for the past year and receives it in JSON format.

[0691] Step 3:

[0692] The server saves the call history in a database

[0693] Input: Call history data

[0694] Processing: The server analyzes the received tweet data and stores the necessary information in a database.

[0695] Output: Call history stored in the database

[0696] The server connects to an SQL database (e.g., MySQL or PostgreSQL) and stores the extracted information in a table. This information includes the post date and time, content, and reactions (e.g., number of likes and comments).

[0697] Step 4:

[0698] The server analyzes the call history

[0699] Input: Call history stored in the database

[0700] Processing: The server analyzes the call history using natural language processing (NLP) techniques.

[0701] Output: Frequently appearing topics and keywords, user posting trends

[0702] Specifically, topic modeling (e.g., LDA) and keyword extraction are performed to identify whether topics such as "health" occur frequently.

[0703] Step 5:

[0704] The server generates the calling pattern

[0705] Input: Analysis results, frequently occurring topics and keywords

[0706] Processing: The server constructs a calling pattern based on the analysis results.

[0707] Output: Outgoing pattern

[0708] For example, it identifies a pattern, such as a user historically posting health-related tweets every Monday morning.

[0709] Step 6:

[0710] The server automatically generates a new message

[0711] Input: Transmission pattern, Generative AI model

[0712] Processing: The server generates a new message using a generative AI model based on the message pattern and analysis results.

[0713] Output: Auto-generated message

[0714] For example, based on a health-related topic, a message such as "Today's small health habit: It is recommended to drink a glass of water first thing in the morning" is generated.

[0715] Step 7:

[0716] The server sends a confirmation request to the user's device.

[0717] Input: Auto-generated message

[0718] Processing: The server sends the generated message to the user's terminal and displays a confirmation message saying, "This message will be sent. Are you sure?"

[0719] Output: User confirmation and correction requests

[0720] A notification is displayed on the user's device, and the user checks the message.

[0721] Step 8:

[0722] The user checks and edits the message

[0723] Input: Confirmation message, generated message

[0724] Action: The user checks the message displayed on the terminal and makes corrections if necessary.

[0725] Output: Corrected message

[0726] The user amends it to "I recommend drinking a glass of water first thing in the morning!" and resubmits it to the system.

[0727] Step 9:

[0728] The server makes the final call

[0729] Input: Corrected message

[0730] Processing: The server re-examines the revised message and sends it from the social media account.

[0731] Output: Update call history, notification of call completion

[0732] The final confirmed text is sent from the social media account, and the server notifies the user that the tweet has been completed.

[0733] (Application example 1)

[0734] 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."

[0735] In the past, users had to create, review, and post their own content on social media, which required a lot of time and effort. There was also the risk of posting unintended content or a lack of consistency in advertising. In addition, users had to come up with new copy each time they posted an ad, which was inefficient.

[0736] 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.

[0737] In this invention, the server includes means for acquiring a user's past transmission history, means for analyzing the past transmission history to generate a transmission pattern, means for automatically generating a new transmission based on the transmission pattern, means for sending the generated transmission to the user's terminal and requesting confirmation, means for re-acquiring a transmission modified by the user, means for posting the final confirmed transmission from the user's SNS account, means for acquiring the user's past advertising transmission history, means for analyzing the past advertising transmission history to generate a pattern related to an advertisement, means for automatically generating a new advertising copy using a generative AI model based on the advertising pattern, means for sending the generated advertising copy to the user's terminal and requesting confirmation, and for acquiring advertising copy modified by the user, and means for posting the final confirmed advertising copy from the user's SNS account. This reduces the burden on the user and enables efficient and safe management of SNS transmissions and advertising transmissions.

[0738] A "user" is a person who has an SNS account and uses the system to post messages and advertisements.

[0739] "Outgoing message history" is a record of messages sent by a user from their SNS account in the past, including information such as the date and time and responses.

[0740] The "calling pattern" refers to the regularity and tendency of a user's calls obtained by analyzing the past call history.

[0741] "Automatic generation" refers to the process by which the system generates new messaging or advertising copy without user intervention.

[0742] "Means for requesting confirmation" refers to a procedure for sending the generated message or advertisement copy to the user's terminal and prompting the user to confirm or correct it.

[0743] "SNS Account" means an account held by a User for the purpose of posting on an SNS platform.

[0744] "Natural language processing technology" refers to technology that enables systems to analyze, understand, and generate human language.

[0745] "Interface" means the user interface through which a user interacts with the system and modifies the generated messages and advertisements.

[0746] A "generative AI model" is a model that uses artificial intelligence and is used to automatically generate new messaging and advertising copy.

[0747] "Advertising history" is a record of the content of advertisements that a user has previously sent from their SNS account, including information such as the date and time and responses.

[0748] "Advertising patterns" refer to regularities and tendencies regarding a user's advertising that can be obtained by analyzing the past history of advertising transmissions.

[0749] This invention is a system for improving the efficiency of users' SNS and advertising activities and preventing the transmission of unintended content. This system acquires and analyzes the user's past communication history and advertising history to generate communication patterns and advertising patterns, and automatically generates new communication messages and advertising copies.

[0750] Hardware and software used

[0751] Hardware: User's smartphone, server

[0752] Software: Python, tweepy library, spacy library, generative AI model, database (e.g., PostgreSQL)

[0753] Processing steps

[0754] 1. Acquisition of the user's past call history and advertising call history

[0755] The server uses the API of the social media platform to obtain the user's past tweets and advertising history.

[0756] 2. Analysis of call history and advertising call history

[0757] The server stores the acquired call history and advertising call history in a database and analyzes them using natural language processing technology with the spacy library. Frequently occurring topics and keywords are extracted from the analysis results, and call patterns and advertising patterns are generated.

[0758] 3. Automatic generation of new messaging and advertising copy

[0759] The server uses a generative AI model to automatically generate new messaging and advertising copy based on the extracted patterns.

[0760] 4. User confirmation and correction

[0761] The generated message and advertisement copy are sent to the user's terminal, and a confirmation message such as "This message will be sent. Are you sure?" is displayed.

[0762] The user can modify the message and advertisement text through the interface, and the modified message and advertisement text are sent to the server for final confirmation.

[0763] 5. Making the final call

[0764] The message and advertisement confirmed by the user are sent from the SNS account via the server, and the server notifies the user when the message has been sent.

[0765] Specific examples

[0766] For example, if the user is on Twitter, it would look like this:

[0767] 1. A user logs in with their Twitter account: The server uses the Twitter API to retrieve tweets and advertising history from the past year.

[0768] 2. Analysis of tweet and advertising history: The server analyzes the data to extract frequently occurring keywords such as "health," "fitness," and "diet," and generates tweet and advertising patterns.

[0769] 3. Generate new Tweets and ad copy: Use generative AI models to automatically generate new tweets and ad copy, such as "Experience the latest health news now!"

[0770] 4. User confirmation: The user receives a message saying, "This message will be sent. Are you sure?" If necessary, the user can make corrections and send the message again to the server.

[0771] 5. Final Posting: The final, verified post and copy will be sent from your Twitter account and you will be notified.

[0772] Prompt Sentence Examples

[0773] "Analyze past tweets and extract frequently occurring keywords."

[0774] "Generate new ad text based on this keyword."

[0775] "Please have the user review the generated ad copy and then send it out as is."

[0776] In this way, this system helps users to efficiently manage their social media and advertising activities.

[0777] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0778] Step 1:

[0779] The server retrieves the user's past posting history and advertising posting history from the user's SNS account. Specifically, it retrieves the necessary data using the SNS platform's API. The input is the user's SNS account information, and the output is the retrieved past posting history.

[0780] Step 2:

[0781] The server saves the acquired calling history and ad sending history in a database. In this step, a database connection is established and the acquired data is saved in an appropriate format. The input is the acquired calling history and ad sending history, and the output is the saved database entry.

[0782] Step 3:

[0783] The server uses natural language processing technology to analyze the stored call history. Specifically, it uses the spacy library to extract frequently occurring topics and keywords. The input is the call history stored in the database, and the output is the extracted keywords and topics.

[0784] Step 4:

[0785] The server generates transmission patterns and advertising patterns based on the analysis results. Here, the user's transmission tendencies are identified based on the extracted keywords and topics. The input is the extracted keywords and topics, and the output is the generated transmission patterns and advertising patterns.

[0786] Step 5:

[0787] The server automatically generates new message and advertising copy using a generative AI model. The model is provided with message and advertising patterns as input and generates appropriate text. The input is the message and advertising patterns, and the output is the generated new message and advertising copy.

[0788] Step 6:

[0789] The server sends the generated message and advertisement copy to the user's terminal and asks for confirmation. In this step, a confirmation message is displayed to the user. The input is the generated message and advertisement copy, and the output is a confirmation message displayed on the user's terminal.

[0790] Step 7:

[0791] The user uses an interface to modify the message and advertisement copy. The modified content is sent back to the server. The input is the message and advertisement copy modified by the user, and the output is the modified content.

[0792] Step 8:

[0793] The server retrieves the message and advertisement copy corrected by the user again and performs a final confirmation. In this step, the confirmed content is displayed to the user again and sent after confirmation. The input is the corrected message and advertisement copy, and the output is the final confirmed message and advertisement copy.

[0794] Step 9:

[0795] The server posts the final confirmed message and advertisement copy from the user's SNS account. Once the message is completed, the server sends a notification to the user. The input is the final confirmed message and advertisement copy, and the output is the content posted on the SNS platform and a notification to the user.

[0796] 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.

[0797] The present invention provides a system that improves the efficiency of users' SNS postings, prevents the posting of unintended content, and enables postings that reflect the user's emotions. Specific embodiments of this system are described below.

[0798] System Overview

[0799] This system involves a series of operations: acquiring and analyzing a user's past communication history to generate communication patterns, and automatically generating new messages based on these communication patterns. It also combines an emotion engine to recognize the user's emotions and reflect them in the messages, enabling more personal and emotionally rich messages. The generated messages are then requested to be confirmed and revised by the user, and the final confirmed content is sent from the SNS account.

[0800] Program processing overview

[0801] 1. Get call history from user's SNS account:

[0802] The server accesses the user's social media account and uses the API to retrieve past postings, such as tweets, posts, and comments.

[0803] 2. Save call history:

[0804] The acquired posting history is saved in a database. Each posting history includes the posting date and time, content, and reactions (number of likes, number of comments, etc.).

[0805] 3. Analysis of call history:

[0806] The server uses natural language processing (NLP) technology to analyze call history and extract keywords, frequently occurring themes, and user trends.

[0807] 4. Generate call patterns:

[0808] Based on the analysis results, the server creates a calling pattern. For example, if there are many calls made on a particular day of the week or during a particular time period, it will extract that pattern.

[0809] 5. Sentiment analysis using emotion engine:

[0810] The server uses an emotion engine to recognize the user's emotions from the call history and analyze the emotional trends.

[0811] 6. Automatic generation of new messages:

[0812] The server automatically generates new messages based on the results of the user's communication patterns and emotion analysis. For example, if a user has frequently sent messages expressing "fun" emotions in the past, the server will generate messages that reflect those emotions.

[0813] 7. Request confirmation of message:

[0814] The generated message is sent to the user's terminal, and a confirmation message is displayed saying, "This message will be sent. Are you sure?"

[0815] 8. User Modifications and Verification:

[0816] The user checks the message and corrects it if necessary. Once the corrections are complete, the user presses the approval button to send the confirmation.

[0817] 9. Making the final call:

[0818] The server sends the message confirmed by the user from the SNS account, and notifies the user when the message is complete.

[0819] Specific examples

[0820] Example 1: Using a Twitter account

[0821] 1. User logs in:

[0822] A user accesses the system and logs in with their Twitter account. The system obtains permission to access the SNS account.

[0823] 2. Get past tweets:

[0824] The server uses the Twitter API to retrieve tweets from the past year, including the tweet content, posting date and time, and reaction status.

[0825] 3. Tweet analysis:

[0826] The server analyzes the collected tweet data using NLP techniques, including topic models (e.g., Latent Dirichlet Allocation) and keyword extraction.

[0827] 4. Creating a calling pattern:

[0828] The server generates a posting pattern from the analysis results. For example, if there are many tweets about "health," it identifies that pattern.

[0829] 5. Emotion analysis:

[0830] The server uses an emotion engine to analyze the user's emotions from the content of past tweets and identify emotions such as joy, sadness, and excitement.

[0831] 6. Automatically generate new tweets:

[0832] The server generates new tweets that reflect the "fun" emotion based on the emotion and the sending pattern. For example, a tweet like "Today is another great day! My first walk of the morning was amazing."

[0833] 7. User confirmation prompts:

[0834] The server sends the generated tweet to the user's device and displays the message, "This text will be sent. Is this OK?"

[0835] 8. User Modifications:

[0836] The user checks the tweet and corrects it to "My first walk of the morning was amazing!"

[0837] 9. Sending Tweets:

[0838] The server posts the corrected tweet from your Twitter account. After posting is complete, the server notifies the user that the tweet has been posted.

[0839] In this way, the present invention allows users to safely and efficiently send messages on social networking sites without feeling any burden. By analyzing the user's past message history and emotions, automatically generating new messages and prompting the user for confirmation, the risk of sending unintended content is prevented. Furthermore, by generating messages that reflect the user's emotions, more personal and emotional communication is realized.

[0840] The processing flow will be explained below.

[0841] Step 1:

[0842] A user accesses the system and logs in with their SNS account. The user then grants permission to access the system.

[0843] Step 2:

[0844] The server uses the SNS API to retrieve the user's past posting history (e.g., tweets and posts from the past year).

[0845] Step 3:

[0846] The server saves the acquired posting history in a database. The posting history includes information on the posting date and time, content, and reactions (number of likes, number of comments, etc.).

[0847] Step 4:

[0848] The server uses natural language processing (NLP) technology to analyze the saved call history and extract keywords, frequently occurring themes, and user trends.

[0849] Step 5:

[0850] The server generates a user's posting pattern based on the analysis results, which includes posting tendencies for specific topics and time periods.

[0851] Step 6:

[0852] The server uses an emotion engine to recognize and analyze the user's emotions contained in the communication history. For example, if the past communication contains a lot of "fun" content, the emotion is identified.

[0853] Step 7:

[0854] The server automatically generates new messages based on the user's message patterns and the results of emotion analysis. For example, if a user posts a lot of health-related information and has a "happy" emotion, the server generates a message like this: "It's another great day! Drink a glass of water first thing in the morning and have a healthy day."

[0855] Step 8:

[0856] The server sends the generated message to the user's terminal and displays a confirmation message saying, "This message will be sent. Are you sure?"

[0857] Step 9:

[0858] The user checks the message generated on the device and modifies it as necessary. For example, they can modify it to "It's another great day today!" Once the modifications are complete, the user presses the approval button to send the confirmation.

[0859] Step 10:

[0860] The server receives the revised message sent by the user, performs a final check, and confirms the approved message as the final message.

[0861] Step 11:

[0862] The server posts the final confirmed message from the user's SNS account.

[0863] Step 12:

[0864] After the posting is complete, the server sends a notification to the user saying "Posting is complete." The user receives the notification and confirms that the posting has been completed successfully.

[0865] Example 2

[0866] 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."

[0867] In the conventional SNS posting process, users must manually consider what to post, which takes time and effort. There is also a risk of posting unintended content. Furthermore, it is difficult to post content that reflects the user's emotions. There is a need for a system that can solve these problems and enable users to post on SNS efficiently and safely.

[0868] 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.

[0869] In this invention, the server includes means for acquiring a user's past transmission history, means for analyzing the past transmission history to generate transmission patterns and emotional tendencies, means for automatically generating new transmission messages based on the transmission patterns and emotional tendencies, means for sending the generated transmission messages to the user's terminal and requesting confirmation, means for reacquiring transmission messages corrected by the user, and means for posting the final confirmed transmission message from the user's SNS account. This enables the user to efficiently generate new posts based on the past transmission history and emotional tendencies, check and correct them to prevent transmission of unintended content, and ultimately safely transmit transmission messages that reflect their emotions.

[0870] "A user's past posting history" refers to data such as the content posted by the user in the past through their social media account, the posting date and time, the number of likes, comments, and retweets.

[0871] "Analysis" refers to the process of analyzing communication history using natural language processing technology and an emotion engine to extract keywords, analyze topics, and score emotions.

[0872] "Communication patterns" refer to the frequency of posts on specific days or time periods, frequently occurring topics, and user posting tendencies extracted based on the user's past communication history that has been acquired and analyzed.

[0873] "Emotional tendency" is calculated by analyzing emotions from a user's past communication history using an emotion engine, and indicates the frequency and patterns of emotions such as positive, negative, and neutral.

[0874] "Automatic generation of new messages" refers to the process of automatically generating new social media post content using a generative AI model based on acquired and analyzed message patterns and emotional tendencies.

[0875] "Generative AI model" refers to an artificial intelligence model that generates sentences in natural language based on input prompts, including, for example, language models.

[0876] The "means for requesting confirmation" refers to a process of sending an automatically generated message to the user's terminal and providing an interface that prompts the user to confirm the message content.

[0877] The "means for re-obtaining the corrected message" refers to the process in which the server re-obtains the content of the message that the user has modified and then performs a final check.

[0878] "Final confirmed message" refers to the final message retrieved by the server after the user has confirmed and made any necessary corrections.

[0879] "SNS Account" refers to a personal or corporate account used by a User through registration and authentication on an SNS platform.

[0880] System Overview

[0881] This invention is a system that improves the efficiency of users' SNS posting, prevents the posting of unintended content, and enables posting that reflects the user's emotions. Specifically, this system analyzes the user's past posting history and automatically generates new messages based on their posting patterns and emotional tendencies. This system is operated through the interaction of a server, terminals, and users.

[0882] Hardware and Software Configuration

[0883] The server has the following main components:

[0884] Database: Used to store user call history, for example, using an RDBMS such as MySQL.

[0885] Natural language processing (NLP) engine: Analyzes call history using Python libraries such as nltk and spacy.

[0886] Emotion Engine: Uses libraries such as TextBlob and VADER to analyze user emotions.

[0887] Generative AI model: Generate new messages using a generative AI model (e.g., a language model).

[0888] The device is used by the user to check and edit messages sent, and a web browser or smartphone app is used.

[0889] Users are responsible for logging into the system, granting API access permissions, and reviewing and modifying generated messages.

[0890] Data processing and calculation

[0891] 1. Get call history:

[0892] The server uses the API of the SNS platform to obtain the user's past communication history.

[0893] For example, using the Twitter API, access the GET statuses / user_timeline endpoint.

[0894] 2. Save call history:

[0895] The acquired call history is saved in a database (such as MySQL).

[0896] Data such as the posting date and time of each message, content, number of likes, number of retweets, and number of comments are saved.

[0897] 3. Analysis of call history:

[0898] The server uses an NLP engine to analyze call history and perform keyword extraction and topic analysis.

[0899] Use Python's nltk and spacy libraries to tokenize the text and extract noun phrases.

[0900] 4. Generating communication patterns and sentiment trends:

[0901] The server generates communication patterns and emotional tendencies based on the analysis results.

[0902] Use a sentiment engine (TextBlob or VADER) to calculate a sentiment score for each call.

[0903] 5. Automatic generation of new messages:

[0904] The server automatically generates new messages using a generative AI model.

[0905] For example, a prompt sentence such as "The user has posted a lot of fun content in the past" is input into the generative AI model.

[0906] Specific examples

[0907] Example 1: Twitter account operation

[0908] 1. User logs in:

[0909] A user accesses the system and logs in with their Twitter account.

[0910] The system will ask for permission to access your social media account.

[0911] 2. Get past tweets:

[0912] The server uses the Twitter API to retrieve tweets from the past year.

[0913] The retrieved tweets include the tweet content, posting date and time, and reaction status.

[0914] 3. Tweet analysis:

[0915] The tweet data collected by the server is analyzed using NLP technology.

[0916] Analysis includes topic models (e.g., Latent Dirichlet Allocation) and keyword extraction.

[0917] 4. Building communication patterns and sentiment trends:

[0918] The server generates communication patterns and emotional tendencies from the analysis results.

[0919] For example, if emotions such as "health" or "fun" are common, patterns that reflect this can be identified.

[0920] 5. Auto-generate new tweets:

[0921] The server generates new tweets that reflect the emotion of "fun" based on the emotion and the sending pattern.

[0922] For example, by inputting the prompt sentence "The user has posted a lot of fun content in the past" into the generative AI model, it generates "Today is another wonderful day! The first walk of the morning was great."

[0923] 6. User confirmation prompts:

[0924] The server sends the generated tweet to the user's device and displays a confirmation message saying, "This text will be sent. Are you sure?"

[0925] 7. User Modifications:

[0926] The user checks the tweet and corrects it to "My first walk of the morning was amazing!"

[0927] 8. Sending Tweets:

[0928] The server posts the corrected tweet from your Twitter account.

[0929] After the posting is complete, the server notifies the user that the tweet has been posted.

[0930] As described above, this invention allows users to safely and efficiently send messages on social networking sites without feeling any burden. It analyzes the user's past message history and emotions, automatically generates new messages, and prompts the user for confirmation, preventing the risk of sending unintended content. Furthermore, by generating messages that reflect the user's emotions, it enables more personal and emotionally rich communication.

[0931] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0932] Step 1:

[0933] Acquiring call history

[0934] The server uses the SNS platform's API to obtain the user's past communication history.

[0935] Input: User credentials and API endpoint.

[0936] Specific operation: Accesses a social media API (e.g., Twitter API) and retrieves past tweet data from the GET statuses / user_timeline endpoint. The request includes an access token.

[0937] Output: The acquired posting history data (e.g. tweet content, posting date and time, number of likes, number of retweets, number of comments) is returned to the server.

[0938] Step 2:

[0939] Save call history

[0940] The server stores the acquired call history in a database.

[0941] Input: Call history data.

[0942] What it does: It connects to a database such as MySQL and executes a SQL query like INSERT INTO posts (date, content, likes, retweets, comments) VALUES (...) to store historical data.

[0943] Output: Each call history stored in the database.

[0944] Step 3:

[0945] Analysis of call history

[0946] The server analyzes the call history using a natural language processing (NLP) engine.

[0947] Input: Saved call history data.

[0948] How it works: It uses Python's nltk and spacy libraries to extract keywords, tokenize text, and extract noun phrases, and also applies algorithms such as Latent Dirichlet Allocation (LDA) to perform topic analysis.

[0949] Output: Keyword list, topic model, data on user posting habits.

[0950] Step 4:

[0951] Generating communication patterns and sentiment trends

[0952] The server generates communication patterns and emotional tendencies based on the analysis results.

[0953] Input: Analysis results (keyword list, topic model, etc.).

[0954] How it works: The server uses an emotion engine (such as TextBlob or VADER) to calculate the emotion score (positive, negative, neutral, etc.) of each post, and performs frequency and trend analysis. It also analyzes the frequency of posts by day of the week and time of day.

[0955] Output: Posting pattern data (e.g., frequency of posts on specific days or times), sentiment data (e.g., many positive posts).

[0956] Step 5:

[0957] Automatic generation of new messages

[0958] The server automatically generates new messages using a generative AI model.

[0959] Input: Call pattern and emotional tendency data, prompt sentence.

[0960] Specific operation: A prompt sentence is input into the generative AI model to generate a new message. For example, the prompt sentence can be "The user has posted many enjoyable messages in the past," and the model will generate a new sentence based on that.

[0961] Output: The new message generated.

[0962] Step 6:

[0963] Request confirmation of message

[0964] The server sends the generated message to the user's terminal and asks for confirmation.

[0965] Input: The generated message.

[0966] Specific operation: The generated message is sent to the user's device, and a confirmation message is displayed saying, "This message will be sent. Are you sure?"

[0967] Output: A confirmation message that is displayed on the user's terminal.

[0968] Step 7:

[0969] User correction and confirmation

[0970] The user checks the generated message and makes corrections as necessary.

[0971] Input: User feedback and corrections.

[0972] Specific operation: The user checks the message and, if they wish to modify it, enters the modifications in the input field and presses the approve button. The modified message is then sent to the server.

[0973] Output: Revised statement and final approval by the user.

[0974] Step 8:

[0975] Making the final call

[0976] The server posts the message confirmed by the user from the SNS account.

[0977] Input: Revised, last confirmed outgoing statement.

[0978] Specific operation: Send the revised message to the POST statuses / update endpoint of the SNS API (e.g., Twitter API) and execute the post.

[0979] Output: The message content published on the social media platform and notification of message completion.

[0980] (Application example 2)

[0981] 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."

[0982] In today's information-saturated society, users are overwhelmed by the amount of information available when using social networking services and content distribution services, making it difficult to send and receive content that is appropriate and emotionally appropriate. Furthermore, there is a lack of efficient ways to receive content that reflects one's own emotions or to obtain recommended content based on individual viewing history. Therefore, there is a need for a system that supports user-friendly, more personalized sending and content consumption.

[0983] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0984] In this invention, the server includes means for acquiring a user's past calling history, means for analyzing the past calling history to generate a calling pattern, means for automatically generating a new message based on the calling pattern, means for sending the new message to the user's terminal and requesting confirmation, means for reacquiring a message revised by the user, means for posting the final confirmed message from the user's SNS account, means for acquiring and analyzing the user's viewing history and emotion data to generate a new recommendation, means for sending the generated recommendation to the user's terminal and requesting confirmation, means for reacquiring a recommendation revised by the user, and means for saving the final confirmed recommendation. This enables users to efficiently make personalized calls and receive content recommendations based on their own emotions and viewing history.

[0985] "A user's past posting history" refers to a record of activities such as posts, comments, and shares that a user has made in the past on social media or other platforms.

[0986] "Communication patterns" are characteristic behavioral patterns, such as tendencies, frequently occurring themes, and posting timing, that are extracted by analyzing a user's past communication history.

[0987] A "new message" is a message that is automatically generated based on a message pattern and that the user will send in the future.

[0988] "Viewing history" is a record of videos, music, and other content that a user has viewed in the past.

[0989] "Emotion data" is information about emotions acquired from the user's facial expressions, reactions, feedback, etc. while watching.

[0990] A "recommendation" is a description of content recommended to a user, generated by analyzing viewing history and emotional data.

[0991] "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language.

[0992] An "interface" is the input and output means by which a user interacts with a system.

[0993] The present invention relates to a system for acquiring and analyzing a user's past sending history to generate new messages and recommendations. Specific embodiments will be described below.

[0994] Hardware and software used

[0995] This system mainly uses the following hardware and software:

[0996] Hardware: Smartphone, facial recognition camera (used to capture user emotion data)

[0997] Software: Python (programming language), natural language processing library "spaCy", sentiment analysis engine "Affectiva SDK", cloud database "Firebase"

[0998] System configuration

[0999] 1. Acquiring the user's past call history

[1000] The server obtains past call history from the user's SNS account.

[1001] This history is stored in a cloud database.

[1002] 2. Analysis of call history

[1003] The server analyzes the acquired call history using natural language processing technology (spaCy).

[1004] A call pattern is generated from the analysis results.

[1005] 3. Obtaining viewing history and emotion data

[1006] The server obtains the user's viewing history from their smartphone and collects emotional data using a facial recognition camera.

[1007] 4. Generating Recommendations

[1008] The server analyzes the viewing history and emotional data to generate new recommendations.

[1009] 5. Check the generated message and testimonials

[1010] The generated document is sent to the user's terminal and a confirmation message is displayed.

[1011] The user checks the document and makes corrections if necessary.

[1012] 6. Final confirmation and sending / saving

[1013] After the user has reviewed and corrected the document, it will be posted to the social media account after a final review, and the recommendation will be stored in a cloud database.

[1014] Data processing and calculation

[1015] Natural language processing: The server uses spaCy to analyze call history and extract keywords and frequently occurring themes.

[1016] Emotion analysis: The server uses the Affectiva SDK to analyze the facial recognition camera data of the user while watching to obtain emotional data.

[1017] Data storage and retrieval: We use the cloud database Firebase to store and manage user viewing history and generated documents.

[1018] Specific examples

[1019] Example 1: Using a Twitter account

[1020] 1. User logs in

[1021] A user accesses the system and logs in with a social networking account. The system obtains permission to access the social networking account.

[1022] 2. Obtain past activity history

[1023] The server uses the SNS API to obtain past call history.

[1024] 3. History Analysis

[1025] The call history collected by the server is analyzed using NLP technology.

[1026] 4. Generating Call Patterns

[1027] The server generates a transmission pattern from the analysis results.

[1028] 5. Emotion analysis

[1029] The server uses an emotion engine to analyze the user's emotions from the data from the facial recognition camera.

[1030] 6. Automatic generation of new messages

[1031] The server generates a new message based on the emotion and the message pattern.

[1032] 7. User Review of Documents

[1033] The generated document is sent to the user's terminal, and a message is displayed saying, "This document will be sent. Is this OK?"

[1034] 8. Transmission and storage

[1035] The document that the user has checked is posted via their social media account, and the recommendation is also saved in a cloud database.

[1036] Prompt Sentence Examples

[1037] Generate content recommendations for users based on their viewing history and emotional data. The viewing history is "e.g., frequently watches action movies, dramas, and comedies," and the emotional data is "e.g., smile, excitement, surprise."

[1038] By following the above procedure, users can efficiently send personal and emotional messages and recommend content.

[1039] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1040] Step 1:

[1041] The server retrieves past posting history from the user's SNS account. To do this, it uses the SNS's API and obtains account access permission with the user's consent. It receives SNS authentication information as input and retrieves posting history data as output. This data includes the content of the post, date and time, and reaction status (number of likes, number of comments, etc.).

[1042] Step 2:

[1043] The server stores the acquired call history in a cloud database to securely store the history data for later analysis. It receives the call history data as input and updates the database as output.

[1044] Step 3:

[1045] The server analyzes the saved call history using natural language processing technology (spaCy). It receives call history data as input, analyzes the data, and extracts keywords, frequently occurring themes, and the user's call trends as output. This analysis generates the user's call patterns.

[1046] Step 4:

[1047] The server acquires the user's viewing history and emotional data. It collects the viewing history from the user's smartphone and acquires the emotional data through a facial recognition camera. It receives the viewing history and the emotional data from the facial recognition camera as input and stores these data in a cloud database as output.

[1048] Step 5:

[1049] The server analyzes the viewing history and emotional data to generate new recommendations. It receives the viewing history and emotional data as input, analyzes them, and generates personalized recommendations as output. These recommendations are based on the user's interests and emotions.

[1050] Step 6:

[1051] The server sends the generated message and recommendation to the user's device and displays a confirmation message. It receives the generated message and recommendation as input and outputs them to the user's device. The message reads, "This message will be sent. Are you sure?"

[1052] Step 7:

[1053] The user checks the message and recommendation sent and makes corrections if necessary. The system receives the generated message and recommendation as input and outputs the corrected results.

[1054] Step 8:

[1055] The server retrieves the message modified by the user again and performs a final check. It receives the message modified by the user as input, checks it, and saves the final checked message as output.

[1056] Step 9:

[1057] The server posts the finalized message from the user's SNS account and saves the recommendation in a cloud database. The server receives the finalized message and recommendation as input, posts the message to the SNS account, saves the recommendation in the database, and notifies the user of the result.

[1058] Through the above steps, users can efficiently send personal messages and receive content recommendations based on their own emotions and viewing history.

[1059] 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.

[1060] 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.

[1061] 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.

[1062] [Third embodiment]

[1063] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1064] 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.

[1065] 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).

[1066] 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.

[1067] 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.

[1068] 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).

[1069] 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.

[1070] 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.

[1071] 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.

[1072] 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.

[1073] 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.

[1074] 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."

[1075] The present invention provides a system for preventing users from posting unintended content while improving the efficiency of posting on SNS. Specific embodiments of this system are described below.

[1076] System Overview

[1077] This system involves a series of operations: acquiring and analyzing a user's past call history to generate call patterns, automatically generating new messages based on these call patterns, prompting the user to confirm and revise the generated messages, and finally sending the confirmed content from the SNS account.

[1078] Program processing overview

[1079] 1. Get call history from user's SNS account:

[1080] The server accesses the user's social media account and uses the API to retrieve past postings, such as tweets, posts, and comments.

[1081] 2. Save call history:

[1082] The acquired posting history is saved in a database. Each posting history contains information such as the posting date and time, content, and reactions (number of likes, number of comments, etc.).

[1083] 3. Analysis of call history:

[1084] The server uses natural language processing (NLP) technology to analyze the posting history, extracting frequently occurring topics, keywords, and user posting trends.

[1085] 4. Generate call patterns:

[1086] Based on the analysis results, the server creates a calling pattern. For example, if there are many calls made on a particular day of the week or during a particular time period, it will extract that pattern.

[1087] 5. Automatic generation of new messages:

[1088] The server automatically generates new messages based on the user's posting patterns. For example, for a user who posts a lot of health-related information, the server generates the following message: "Today's small health habit: I recommend drinking a glass of water first thing in the morning."

[1089] 6. Request confirmation of message:

[1090] The generated message is sent to the user's terminal, and a confirmation message is displayed saying, "This message will be sent. Are you sure?"

[1091] 7. User Modifications and Verification:

[1092] The user checks the message and corrects it if necessary. The corrected message is then sent back to the server.

[1093] 8. Making the final call:

[1094] The server sends the message confirmed by the user from the SNS account, and notifies the user when the message is complete.

[1095] Specific examples

[1096] Example 1: Using a Twitter account

[1097] 1. User logs in:

[1098] A user accesses the system and logs in with their Twitter account. The system obtains permission to access the SNS account.

[1099] 2. Get past tweets:

[1100] The server uses the Twitter API to retrieve tweets from the past year, including the tweet content, posting date and time, and reaction status.

[1101] 3. Tweet analysis:

[1102] The server analyzes the collected tweet data using NLP techniques, including topic models (e.g., Latent Dirichlet Allocation) and keyword extraction.

[1103] 4. Creating a calling pattern:

[1104] The server generates a posting pattern from the analysis results. For example, if there are many tweets about "health," it identifies that pattern.

[1105] 5. Auto-generate new tweets:

[1106] The server automatically generates new tweets about "health." For example, the content generated is "Today's small health habit: I recommend drinking a glass of water first thing in the morning."

[1107] 6. User confirmation prompts:

[1108] The server sends the generated tweet to the user's device and displays the message, "This text will be sent. Is this OK?"

[1109] 7. User Modifications:

[1110] The user reviews the tweet and corrects it to "I recommend drinking a glass of water first thing in the morning!"

[1111] 8. Sending Tweets:

[1112] The server posts the corrected tweet from your Twitter account. After posting is complete, the server notifies the user that the tweet has been posted.

[1113] In this way, the present invention allows users to safely and efficiently send messages on SNS without feeling any burden. By obtaining analysis results from the user's past message history, automatically generating new messages and prompting the user for confirmation, the risk of sending unintended content is prevented.

[1114] The processing flow will be explained below.

[1115] Step 1:

[1116] A user accesses the system and logs in with their SNS account. The user then grants permission to access the system.

[1117] Step 2:

[1118] The server uses the SNS API to retrieve the user's past posting history (e.g., tweets and posts from the past year).

[1119] Step 3:

[1120] The server saves the acquired posting history in a database. The posting history includes information on the posting date and time, content, and reactions (number of likes, number of comments, etc.).

[1121] Step 4:

[1122] The server uses natural language processing (NLP) technology to analyze the saved call history and extract keywords, frequently occurring themes, and user trends.

[1123] Step 5:

[1124] The server generates a user's posting pattern based on the analysis results, which includes posting tendencies for specific topics and time periods.

[1125] Step 6:

[1126] The server automatically generates new messages based on the user's posting patterns and current trends. For example, if the user posts a lot of health-related information, it generates new health-related messages.

[1127] Step 7:

[1128] The server sends the generated message to the user's terminal and displays the message "This message will be sent. Is this OK?"

[1129] Step 8:

[1130] The user checks the message generated on the device, corrects the wording as necessary, and once corrections are complete, the user presses the approval button to send the confirmation.

[1131] Step 9:

[1132] The server receives the corrected message sent by the user and performs a final check.

[1133] Step 10:

[1134] The server posts the final confirmed message from the user's SNS account.

[1135] Step 11:

[1136] After the posting is complete, the server sends a notification to the user saying "Posting is complete."

[1137] In this way, each step reduces the burden on the user while preventing unintended transmission of content.

[1138] Example 1

[1139] 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."

[1140] In today's social networking sites, users frequently post, but it is difficult to maintain efficient, high-quality communication. There is also a risk of unintentionally posting inappropriate content. For example, users may forget the content and time of previous posts, making it difficult to generate new ideas. Furthermore, reviewing and revising posts takes time, placing a burden on users. The present invention aims to solve these problems and enable users to post on social networking sites efficiently and safely.

[1141] 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.

[1142] In this invention, the server includes means for obtaining authentication and access permission for the user's SNS account, means for obtaining the user's past transmission history, means for saving the transmission history in a database, means for using natural language processing technology to analyze the transmission history, means for generating transmission patterns, means for automatically generating new transmissions using a generative AI model, means for sending the generated transmissions to the user's device and requesting confirmation, means for re-obtaining transmissions modified by the user, and means for posting the final confirmed transmissions from the user's SNS account. This enables users to transmit efficiently and consistently based on past transmission content and patterns, reducing the risk of transmitting unintended content and enabling them to easily continue posting high-quality content.

[1143] "User" refers to an individual or corporation that has an SNS account and uses that account to conduct communication activities.

[1144] "SNS account" refers to an account used by a user on a social networking service (SNS), including accounts on services such as Twitter, Facebook, and Instagram.

[1145] "Outgoing communication history" refers to digital records of posts, tweets, comments, messages, etc. that a user has made in the past from their social media account.

[1146] A "database" refers to a digital system for efficiently storing, managing, and searching data such as call history and analysis results.

[1147] "Natural language processing technology" is a technology for analyzing, understanding, and generating human language using computers, and includes techniques such as topic modeling and keyword extraction.

[1148] "Calling pattern" refers to a pattern or tendency regarding a particular day of the week, time period, or content of calls, derived from an analysis of a user's past calling history.

[1149] "Generative AI model" refers to an algorithm or program that uses artificial intelligence to generate new messages, and specifically includes natural language generation models.

[1150] "New messages" refers to text content for posting on social media that is automatically generated based on the user's messaging patterns.

[1151] "User's device" refers to a digital device used by a user, such as a computer, smartphone, or tablet.

[1152] "Obtaining authentication and access permissions" refers to the process by which the server obtains the necessary authentication information and permissions to securely access a user's social networking account.

[1153] "Requesting confirmation" refers to the act of presenting the generated message to the user and requesting confirmation or correction of its contents.

[1154] "Modification" refers to a user making changes to a generated message to adjust its content.

[1155] "Final Reviewed Message" refers to the final content of the message after the user has reviewed it and made any necessary corrections.

[1156] "Posting" refers to the act of actually publishing a final, confirmed message from a user's social media account.

[1157] The present invention is a system that aims to improve the efficiency of users' SNS postings while preventing the posting of unintended content. This system involves a series of operations that acquires and analyzes the user's past posting history to generate posting patterns, and automatically generates new postings based on those patterns. Specific embodiments are described below.

[1158] System Overview

[1159] This system authenticates SNS accounts, acquires and saves call history, analyzes the history, generates call patterns, automatically generates new messages, allows users to confirm and edit them, and finally sends the message. These processes are performed by the server, the user's device, and the SNS account with appropriate authentication.

[1160] Hardware and software used

[1161] Server: Cloud server for high-performance processing and data storage (e.g., Amazon Web Services, Google Cloud Platform)

[1162] Devices: Computers, smartphones, and tablets that users use every day.

[1163] Database: Relational database management system such as MySQL, PostgreSQL

[1164] Natural language processing technology: Natural language processing libraries such as NLTK and spaCy

[1165] Generative AI models: Natural language generation models such as GPT-4

[1166] Details of data processing and calculation

[1167] 1. Authentication and Permissions:

[1168] A user accesses the system and logs in with a social networking account (e.g., Twitter). The server uses the OAuth protocol to obtain the authentication information and access permissions of the user's social networking account.

[1169] 2. Acquiring and saving call history:

[1170] The server retrieves the tweet history for the past year through the SNS API (e.g., Twitter API). The retrieved tweet history includes the tweet content, posting date and time, number of likes, number of comments, etc.

[1171] The server stores the retrieved data in a database.

[1172] 3. Analysis of call history:

[1173] The server analyzes the saved call history using natural language processing (NLP) techniques, such as topic modeling (e.g., Latent Dirichlet Allocation, LDA) and keyword extraction.

[1174] The analysis results identify frequently occurring topics, keywords, and communication trends.

[1175] 4. Generate call patterns:

[1176] The server then creates a calling pattern based on the analysis results. For example, if a user makes many calls on certain days of the week or during certain times of the day, it identifies that pattern.

[1177] 5. Automatic generation of new messages:

[1178] The server uses a generative AI model to generate new messages based on the message patterns and analysis results. For example, for a user who frequently talks about health, a message such as "Today's small health habit: I recommend drinking a glass of water first thing in the morning" may be generated.

[1179] 6. User Review and Correction:

[1180] The server sends the generated message to the user's terminal and asks for confirmation, "Is this message OK?"

[1181] The user checks the message and makes corrections if necessary, after which the corrected message is sent back to the server.

[1182] 7. Final Call:

[1183] The server then sends the message from the SNS account after the user has confirmed and corrected it. Once the message has been sent, the server notifies the user.

[1184] Examples of specific examples and prompts

[1185] Example: Using a Twitter account

[1186] 1. A user accesses the system and performs Twitter authentication.

[1187] 2. The server uses the Twitter API to retrieve tweets from the past year.

[1188] 3. The server stores the tweet data in a database.

[1189] 4. The server analyzes the tweet data using NLP technology, and finds results showing frequent health-related topics.

[1190] 5. The server creates a calling pattern related to "health."

[1191] 6. The server generates a new tweet saying, "Today's small health habit: I recommend drinking a glass of water first thing in the morning."

[1192] 7. The server sends the generated tweet to the user's device and asks for confirmation.

[1193] 8. The user checks and edits the message and sends the edited message to the server.

[1194] 9. The server sends the final confirmed tweet from the user's Twitter account and notifies the user that the tweet has been completed.

[1195] In this way, this system provides a series of steps necessary for users to post on SNS efficiently and safely. In particular, by analyzing past posting history and generating new posts based on the user's posting tendencies, the system can improve the consistency and quality of posts.

[1196] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1197] Step 1:

[1198] User logs in with social networking account

[1199] Input: Username and password, social media credentials

[1200] Action: The user accesses the system's login screen and enters their social network account credentials.

[1201] Output: Auth token and permissions to access social media accounts

[1202] The user clicks the "Login" button, and the server authenticates with the social network using the OAuth protocol, which gives the server permission to access the social network account from the user.

[1203] Step 2:

[1204] The server acquires the user's past call history

[1205] Input: Auth Token, SNS API

[1206] Process: The server sends a request to a social media API (e.g. Twitter API) using the obtained permissions.

[1207] Output: Tweet content, posting date and time, number of likes, number of comments, and other posting history data

[1208] The server retrieves tweet data from the social media account for the past year and receives it in JSON format.

[1209] Step 3:

[1210] The server saves the call history in a database

[1211] Input: Call history data

[1212] Processing: The server analyzes the received tweet data and stores the necessary information in a database.

[1213] Output: Call history stored in the database

[1214] The server connects to an SQL database (e.g., MySQL or PostgreSQL) and stores the extracted information in a table. This information includes the post date and time, content, and reactions (e.g., number of likes and comments).

[1215] Step 4:

[1216] The server analyzes the call history

[1217] Input: Call history stored in the database

[1218] Processing: The server analyzes the call history using natural language processing (NLP) techniques.

[1219] Output: Frequently appearing topics and keywords, user posting trends

[1220] Specifically, topic modeling (e.g., LDA) and keyword extraction are performed to identify whether topics such as "health" occur frequently.

[1221] Step 5:

[1222] The server generates the calling pattern

[1223] Input: Analysis results, frequently occurring topics and keywords

[1224] Processing: The server constructs a calling pattern based on the analysis results.

[1225] Output: Outgoing pattern

[1226] For example, it identifies a pattern, such as a user historically posting health-related tweets every Monday morning.

[1227] Step 6:

[1228] The server automatically generates a new message

[1229] Input: Transmission pattern, Generative AI model

[1230] Processing: The server generates a new message using a generative AI model based on the message pattern and analysis results.

[1231] Output: Auto-generated message

[1232] For example, based on a health-related topic, a message such as "Today's small health habit: It is recommended to drink a glass of water first thing in the morning" is generated.

[1233] Step 7:

[1234] The server sends a confirmation request to the user's device.

[1235] Input: Auto-generated message

[1236] Processing: The server sends the generated message to the user's terminal and displays a confirmation message saying, "This message will be sent. Are you sure?"

[1237] Output: User confirmation and correction requests

[1238] A notification is displayed on the user's device, and the user checks the message.

[1239] Step 8:

[1240] The user checks and edits the message

[1241] Input: Confirmation message, generated message

[1242] Action: The user checks the message displayed on the terminal and makes corrections if necessary.

[1243] Output: Corrected message

[1244] The user amends it to "I recommend drinking a glass of water first thing in the morning!" and resubmits it to the system.

[1245] Step 9:

[1246] The server makes the final call

[1247] Input: Corrected message

[1248] Processing: The server re-examines the revised message and sends it from the social media account.

[1249] Output: Update call history, notification of call completion

[1250] The final confirmed text is sent from the social media account, and the server notifies the user that the tweet has been completed.

[1251] (Application example 1)

[1252] 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."

[1253] In the past, users had to create, review, and post their own content on social media, which required a lot of time and effort. There was also the risk of posting unintended content or a lack of consistency in advertising. In addition, users had to come up with new copy each time they posted an ad, which was inefficient.

[1254] 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.

[1255] In this invention, the server includes means for acquiring a user's past transmission history, means for analyzing the past transmission history to generate a transmission pattern, means for automatically generating a new transmission based on the transmission pattern, means for sending the generated transmission to the user's terminal and requesting confirmation, means for re-acquiring a transmission modified by the user, means for posting the final confirmed transmission from the user's SNS account, means for acquiring the user's past advertising transmission history, means for analyzing the past advertising transmission history to generate a pattern related to an advertisement, means for automatically generating a new advertising copy using a generative AI model based on the advertising pattern, means for sending the generated advertising copy to the user's terminal and requesting confirmation, and for acquiring advertising copy modified by the user, and means for posting the final confirmed advertising copy from the user's SNS account. This reduces the burden on the user and enables efficient and safe management of SNS transmissions and advertising transmissions.

[1256] A "user" is a person who has an SNS account and uses the system to post messages and advertisements.

[1257] "Outgoing message history" is a record of messages sent by a user from their SNS account in the past, including information such as the date and time and responses.

[1258] The "calling pattern" refers to the regularity and tendency of a user's calls obtained by analyzing the past call history.

[1259] "Automatic generation" refers to the process by which the system generates new messaging or advertising copy without user intervention.

[1260] "Means for requesting confirmation" refers to a procedure for sending the generated message or advertisement copy to the user's terminal and prompting the user to confirm or correct it.

[1261] "SNS Account" means an account held by a User for the purpose of posting on an SNS platform.

[1262] "Natural language processing technology" refers to technology that enables systems to analyze, understand, and generate human language.

[1263] "Interface" means the user interface through which a user interacts with the system and modifies the generated messages and advertisements.

[1264] A "generative AI model" is a model that uses artificial intelligence and is used to automatically generate new messaging and advertising copy.

[1265] "Advertising history" is a record of the content of advertisements that a user has previously sent from their SNS account, including information such as the date and time and responses.

[1266] "Advertising patterns" refer to regularities and tendencies regarding a user's advertising that can be obtained by analyzing the past history of advertising transmissions.

[1267] This invention is a system for improving the efficiency of users' SNS and advertising activities and preventing the transmission of unintended content. This system acquires and analyzes the user's past communication history and advertising history to generate communication patterns and advertising patterns, and automatically generates new communication messages and advertising copies.

[1268] Hardware and software used

[1269] Hardware: User's smartphone, server

[1270] Software: Python, tweepy library, spacy library, generative AI model, database (e.g., PostgreSQL)

[1271] Processing steps

[1272] 1. Acquisition of the user's past call history and advertising call history

[1273] The server uses the API of the social media platform to obtain the user's past tweets and advertising history.

[1274] 2. Analysis of call history and advertising call history

[1275] The server stores the acquired call history and advertising call history in a database and analyzes them using natural language processing technology with the spacy library. Frequently occurring topics and keywords are extracted from the analysis results, and call patterns and advertising patterns are generated.

[1276] 3. Automatic generation of new messaging and advertising copy

[1277] The server uses a generative AI model to automatically generate new messaging and advertising copy based on the extracted patterns.

[1278] 4. User confirmation and correction

[1279] The generated message and advertisement copy are sent to the user's terminal, and a confirmation message such as "This message will be sent. Are you sure?" is displayed.

[1280] The user can modify the message and advertisement text through the interface, and the modified message and advertisement text are sent to the server for final confirmation.

[1281] 5. Making the final call

[1282] The message and advertisement confirmed by the user are sent from the SNS account via the server, and the server notifies the user when the message has been sent.

[1283] Specific examples

[1284] For example, if the user is on Twitter, it would look like this:

[1285] 1. A user logs in with their Twitter account: The server uses the Twitter API to retrieve tweets and advertising history from the past year.

[1286] 2. Analysis of tweet and advertising history: The server analyzes the data to extract frequently occurring keywords such as "health," "fitness," and "diet," and generates tweet and advertising patterns.

[1287] 3. Generate new Tweets and ad copy: Use generative AI models to automatically generate new tweets and ad copy, such as "Experience the latest health news now!"

[1288] 4. User confirmation: The user receives a message saying, "This message will be sent. Are you sure?" If necessary, the user can make corrections and send the message again to the server.

[1289] 5. Final Posting: The final, verified post and copy will be sent from your Twitter account and you will be notified.

[1290] Prompt Sentence Examples

[1291] "Analyze past tweets and extract frequently occurring keywords."

[1292] "Generate new ad text based on this keyword."

[1293] "Please have the user review the generated ad copy and then send it out as is."

[1294] In this way, this system helps users to efficiently manage their social media and advertising activities.

[1295] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1296] Step 1:

[1297] The server retrieves the user's past posting history and advertising posting history from the user's SNS account. Specifically, it retrieves the necessary data using the SNS platform's API. The input is the user's SNS account information, and the output is the retrieved past posting history.

[1298] Step 2:

[1299] The server saves the acquired calling history and ad sending history in a database. In this step, a database connection is established and the acquired data is saved in an appropriate format. The input is the acquired calling history and ad sending history, and the output is the saved database entry.

[1300] Step 3:

[1301] The server uses natural language processing technology to analyze the stored call history. Specifically, it uses the spacy library to extract frequently occurring topics and keywords. The input is the call history stored in the database, and the output is the extracted keywords and topics.

[1302] Step 4:

[1303] The server generates transmission patterns and advertising patterns based on the analysis results. Here, the user's transmission tendencies are identified based on the extracted keywords and topics. The input is the extracted keywords and topics, and the output is the generated transmission patterns and advertising patterns.

[1304] Step 5:

[1305] The server automatically generates new message and advertising copy using a generative AI model. The model is provided with message and advertising patterns as input and generates appropriate text. The input is the message and advertising patterns, and the output is the generated new message and advertising copy.

[1306] Step 6:

[1307] The server sends the generated message and advertisement copy to the user's terminal and asks for confirmation. In this step, a confirmation message is displayed to the user. The input is the generated message and advertisement copy, and the output is a confirmation message displayed on the user's terminal.

[1308] Step 7:

[1309] The user uses an interface to modify the message and advertisement copy. The modified content is sent back to the server. The input is the message and advertisement copy modified by the user, and the output is the modified content.

[1310] Step 8:

[1311] The server retrieves the message and advertisement copy corrected by the user again and performs a final confirmation. In this step, the confirmed content is displayed to the user again and sent after confirmation. The input is the corrected message and advertisement copy, and the output is the final confirmed message and advertisement copy.

[1312] Step 9:

[1313] The server posts the final confirmed message and advertisement copy from the user's SNS account. Once the message is completed, the server sends a notification to the user. The input is the final confirmed message and advertisement copy, and the output is the content posted on the SNS platform and a notification to the user.

[1314] 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.

[1315] The present invention provides a system that improves the efficiency of users' SNS postings, prevents the posting of unintended content, and enables postings that reflect the user's emotions. Specific embodiments of this system are described below.

[1316] System Overview

[1317] This system involves a series of operations: acquiring and analyzing a user's past communication history to generate communication patterns, and automatically generating new messages based on these communication patterns. It also combines an emotion engine to recognize the user's emotions and reflect them in the messages, enabling more personal and emotionally rich messages. The generated messages are then requested to be confirmed and revised by the user, and the final confirmed content is sent from the SNS account.

[1318] Program processing overview

[1319] 1. Get call history from user's SNS account:

[1320] The server accesses the user's social media account and uses the API to retrieve past postings, such as tweets, posts, and comments.

[1321] 2. Save call history:

[1322] The acquired posting history is saved in a database. Each posting history includes the posting date and time, content, and reactions (number of likes, number of comments, etc.).

[1323] 3. Analysis of call history:

[1324] The server uses natural language processing (NLP) technology to analyze call history and extract keywords, frequently occurring themes, and user trends.

[1325] 4. Generate call patterns:

[1326] Based on the analysis results, the server creates a calling pattern. For example, if there are many calls made on a particular day of the week or during a particular time period, it will extract that pattern.

[1327] 5. Sentiment analysis using emotion engine:

[1328] The server uses an emotion engine to recognize the user's emotions from the call history and analyze the emotional trends.

[1329] 6. Automatic generation of new messages:

[1330] The server automatically generates new messages based on the results of the user's communication patterns and emotion analysis. For example, if a user has frequently sent messages expressing "fun" emotions in the past, the server will generate messages that reflect those emotions.

[1331] 7. Request confirmation of message:

[1332] The generated message is sent to the user's terminal, and a confirmation message is displayed saying, "This message will be sent. Are you sure?"

[1333] 8. User Modifications and Verification:

[1334] The user checks the message and corrects it if necessary. Once the corrections are complete, the user presses the approval button to send the confirmation.

[1335] 9. Making the final call:

[1336] The server sends the message confirmed by the user from the SNS account, and notifies the user when the message is complete.

[1337] Specific examples

[1338] Example 1: Using a Twitter account

[1339] 1. User logs in:

[1340] A user accesses the system and logs in with their Twitter account. The system obtains permission to access the SNS account.

[1341] 2. Get past tweets:

[1342] The server uses the Twitter API to retrieve tweets from the past year, including the tweet content, posting date and time, and reaction status.

[1343] 3. Tweet analysis:

[1344] The server analyzes the collected tweet data using NLP techniques, including topic models (e.g., Latent Dirichlet Allocation) and keyword extraction.

[1345] 4. Creating a calling pattern:

[1346] The server generates a posting pattern from the analysis results. For example, if there are many tweets about "health," it identifies that pattern.

[1347] 5. Emotion analysis:

[1348] The server uses an emotion engine to analyze the user's emotions from the content of past tweets and identify emotions such as joy, sadness, and excitement.

[1349] 6. Automatically generate new tweets:

[1350] The server generates new tweets that reflect the "fun" emotion based on the emotion and the sending pattern. For example, a tweet like "Today is another great day! My first walk of the morning was amazing."

[1351] 7. User confirmation prompts:

[1352] The server sends the generated tweet to the user's device and displays the message, "This text will be sent. Is this OK?"

[1353] 8. User Modifications:

[1354] The user checks the tweet and corrects it to "My first walk of the morning was amazing!"

[1355] 9. Sending Tweets:

[1356] The server posts the corrected tweet from your Twitter account. After posting is complete, the server notifies the user that the tweet has been posted.

[1357] In this way, the present invention allows users to safely and efficiently send messages on social networking sites without feeling any burden. By analyzing the user's past message history and emotions, automatically generating new messages and prompting the user for confirmation, the risk of sending unintended content is prevented. Furthermore, by generating messages that reflect the user's emotions, more personal and emotional communication is realized.

[1358] The processing flow will be explained below.

[1359] Step 1:

[1360] A user accesses the system and logs in with their SNS account. The user then grants permission to access the system.

[1361] Step 2:

[1362] The server uses the SNS API to retrieve the user's past posting history (e.g., tweets and posts from the past year).

[1363] Step 3:

[1364] The server saves the acquired posting history in a database. The posting history includes information on the posting date and time, content, and reactions (number of likes, number of comments, etc.).

[1365] Step 4:

[1366] The server uses natural language processing (NLP) technology to analyze the saved call history and extract keywords, frequently occurring themes, and user trends.

[1367] Step 5:

[1368] The server generates a user's posting pattern based on the analysis results, which includes posting tendencies for specific topics and time periods.

[1369] Step 6:

[1370] The server uses an emotion engine to recognize and analyze the user's emotions contained in the communication history. For example, if the past communication contains a lot of "fun" content, the emotion is identified.

[1371] Step 7:

[1372] The server automatically generates new messages based on the user's message patterns and the results of emotion analysis. For example, if a user posts a lot of health-related information and has a "happy" emotion, the server generates a message like this: "It's another great day! Drink a glass of water first thing in the morning and have a healthy day."

[1373] Step 8:

[1374] The server sends the generated message to the user's terminal and displays a confirmation message saying, "This message will be sent. Are you sure?"

[1375] Step 9:

[1376] The user checks the message generated on the device and modifies it as necessary. For example, they can modify it to "It's another great day today!" Once the modifications are complete, the user presses the approval button to send the confirmation.

[1377] Step 10:

[1378] The server receives the revised message sent by the user, performs a final check, and confirms the approved message as the final message.

[1379] Step 11:

[1380] The server posts the final confirmed message from the user's SNS account.

[1381] Step 12:

[1382] After the posting is complete, the server sends a notification to the user saying "Posting is complete." The user receives the notification and confirms that the posting has been completed successfully.

[1383] Example 2

[1384] 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."

[1385] In the conventional SNS posting process, users must manually consider what to post, which takes time and effort. There is also a risk of posting unintended content. Furthermore, it is difficult to post content that reflects the user's emotions. There is a need for a system that can solve these problems and enable users to post on SNS efficiently and safely.

[1386] 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.

[1387] In this invention, the server includes means for acquiring a user's past transmission history, means for analyzing the past transmission history to generate transmission patterns and emotional tendencies, means for automatically generating new transmission messages based on the transmission patterns and emotional tendencies, means for sending the generated transmission messages to the user's terminal and requesting confirmation, means for reacquiring transmission messages corrected by the user, and means for posting the final confirmed transmission message from the user's SNS account. This enables the user to efficiently generate new posts based on the past transmission history and emotional tendencies, check and correct them to prevent transmission of unintended content, and ultimately safely transmit transmission messages that reflect their emotions.

[1388] "A user's past posting history" refers to data such as the content posted by the user in the past through their social media account, the posting date and time, the number of likes, comments, and retweets.

[1389] "Analysis" refers to the process of analyzing communication history using natural language processing technology and an emotion engine to extract keywords, analyze topics, and score emotions.

[1390] "Communication patterns" refer to the frequency of posts on specific days or time periods, frequently occurring topics, and user posting tendencies extracted based on the user's past communication history that has been acquired and analyzed.

[1391] "Emotional tendency" is calculated by analyzing emotions from a user's past communication history using an emotion engine, and indicates the frequency and patterns of emotions such as positive, negative, and neutral.

[1392] "Automatic generation of new messages" refers to the process of automatically generating new social media post content using a generative AI model based on acquired and analyzed message patterns and emotional tendencies.

[1393] "Generative AI model" refers to an artificial intelligence model that generates sentences in natural language based on input prompts, including, for example, language models.

[1394] The "means for requesting confirmation" refers to a process of sending an automatically generated message to the user's terminal and providing an interface that prompts the user to confirm the message content.

[1395] The "means for re-obtaining the corrected message" refers to the process in which the server re-obtains the content of the message that the user has modified and then performs a final check.

[1396] "Final confirmed message" refers to the final message retrieved by the server after the user has confirmed and made any necessary corrections.

[1397] "SNS Account" refers to a personal or corporate account used by a User through registration and authentication on an SNS platform.

[1398] System Overview

[1399] This invention is a system that improves the efficiency of users' SNS posting, prevents the posting of unintended content, and enables posting that reflects the user's emotions. Specifically, this system analyzes the user's past posting history and automatically generates new messages based on their posting patterns and emotional tendencies. This system is operated through the interaction of a server, terminals, and users.

[1400] Hardware and Software Configuration

[1401] The server has the following main components:

[1402] Database: Used to store user call history, for example, using an RDBMS such as MySQL.

[1403] Natural language processing (NLP) engine: Analyzes call history using Python libraries such as nltk and spacy.

[1404] Emotion Engine: Uses libraries such as TextBlob and VADER to analyze user emotions.

[1405] Generative AI model: Generate new messages using a generative AI model (e.g., a language model).

[1406] The device is used by the user to check and edit messages sent, and a web browser or smartphone app is used.

[1407] Users are responsible for logging into the system, granting API access permissions, and reviewing and modifying generated messages.

[1408] Data processing and calculation

[1409] 1. Get call history:

[1410] The server uses the API of the SNS platform to obtain the user's past communication history.

[1411] For example, using the Twitter API, access the GET statuses / user_timeline endpoint.

[1412] 2. Save call history:

[1413] The acquired call history is saved in a database (such as MySQL).

[1414] Data such as the posting date and time of each message, content, number of likes, number of retweets, and number of comments are saved.

[1415] 3. Analysis of call history:

[1416] The server uses an NLP engine to analyze call history and perform keyword extraction and topic analysis.

[1417] Use Python's nltk and spacy libraries to tokenize the text and extract noun phrases.

[1418] 4. Generating communication patterns and sentiment trends:

[1419] The server generates communication patterns and emotional tendencies based on the analysis results.

[1420] Use a sentiment engine (TextBlob or VADER) to calculate a sentiment score for each call.

[1421] 5. Automatic generation of new messages:

[1422] The server automatically generates new messages using a generative AI model.

[1423] For example, a prompt sentence such as "The user has posted a lot of fun content in the past" is input into the generative AI model.

[1424] Specific examples

[1425] Example 1: Twitter account operation

[1426] 1. User logs in:

[1427] A user accesses the system and logs in with their Twitter account.

[1428] The system will ask for permission to access your social media account.

[1429] 2. Get past tweets:

[1430] The server uses the Twitter API to retrieve tweets from the past year.

[1431] The retrieved tweets include the tweet content, posting date and time, and reaction status.

[1432] 3. Tweet analysis:

[1433] The tweet data collected by the server is analyzed using NLP technology.

[1434] Analysis includes topic models (e.g., Latent Dirichlet Allocation) and keyword extraction.

[1435] 4. Building communication patterns and sentiment trends:

[1436] The server generates communication patterns and emotional tendencies from the analysis results.

[1437] For example, if emotions such as "health" or "fun" are common, patterns that reflect this can be identified.

[1438] 5. Auto-generate new tweets:

[1439] The server generates new tweets that reflect the emotion of "fun" based on the emotion and the sending pattern.

[1440] For example, by inputting the prompt sentence "The user has posted a lot of fun content in the past" into the generative AI model, it generates "Today is another wonderful day! The first walk of the morning was great."

[1441] 6. User confirmation prompts:

[1442] The server sends the generated tweet to the user's device and displays a confirmation message saying, "This text will be sent. Are you sure?"

[1443] 7. User Modifications:

[1444] The user checks the tweet and corrects it to "My first walk of the morning was amazing!"

[1445] 8. Sending Tweets:

[1446] The server posts the corrected tweet from your Twitter account.

[1447] After the posting is complete, the server notifies the user that the tweet has been posted.

[1448] As described above, this invention allows users to safely and efficiently send messages on social networking sites without feeling any burden. It analyzes the user's past message history and emotions, automatically generates new messages, and prompts the user for confirmation, preventing the risk of sending unintended content. Furthermore, by generating messages that reflect the user's emotions, it enables more personal and emotionally rich communication.

[1449] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1450] Step 1:

[1451] Acquiring call history

[1452] The server uses the SNS platform's API to obtain the user's past communication history.

[1453] Input: User credentials and API endpoint.

[1454] Specific operation: Accesses a social media API (e.g., Twitter API) and retrieves past tweet data from the GET statuses / user_timeline endpoint. The request includes an access token.

[1455] Output: The acquired posting history data (e.g. tweet content, posting date and time, number of likes, number of retweets, number of comments) is returned to the server.

[1456] Step 2:

[1457] Save call history

[1458] The server stores the acquired call history in a database.

[1459] Input: Call history data.

[1460] What it does: It connects to a database such as MySQL and executes a SQL query like INSERT INTO posts (date, content, likes, retweets, comments) VALUES (...) to store historical data.

[1461] Output: Each call history stored in the database.

[1462] Step 3:

[1463] Analysis of call history

[1464] The server analyzes the call history using a natural language processing (NLP) engine.

[1465] Input: Saved call history data.

[1466] How it works: It uses Python's nltk and spacy libraries to extract keywords, tokenize text, and extract noun phrases, and also applies algorithms such as Latent Dirichlet Allocation (LDA) to perform topic analysis.

[1467] Output: Keyword list, topic model, data on user posting habits.

[1468] Step 4:

[1469] Generating communication patterns and sentiment trends

[1470] The server generates communication patterns and emotional tendencies based on the analysis results.

[1471] Input: Analysis results (keyword list, topic model, etc.).

[1472] How it works: The server uses an emotion engine (such as TextBlob or VADER) to calculate the emotion score (positive, negative, neutral, etc.) of each post, and performs frequency and trend analysis. It also analyzes the frequency of posts by day of the week and time of day.

[1473] Output: Posting pattern data (e.g., frequency of posts on specific days or times), sentiment data (e.g., many positive posts).

[1474] Step 5:

[1475] Automatic generation of new messages

[1476] The server automatically generates new messages using a generative AI model.

[1477] Input: Call pattern and emotional tendency data, prompt sentence.

[1478] Specific operation: A prompt sentence is input into the generative AI model to generate a new message. For example, the prompt sentence can be "The user has posted many enjoyable messages in the past," and the model will generate a new sentence based on that.

[1479] Output: The new message generated.

[1480] Step 6:

[1481] Request confirmation of message

[1482] The server sends the generated message to the user's terminal and asks for confirmation.

[1483] Input: The generated message.

[1484] Specific operation: The generated message is sent to the user's device, and a confirmation message is displayed saying, "This message will be sent. Are you sure?"

[1485] Output: A confirmation message that is displayed on the user's terminal.

[1486] Step 7:

[1487] User correction and confirmation

[1488] The user checks the generated message and makes corrections as necessary.

[1489] Input: User feedback and corrections.

[1490] Specific operation: The user checks the message and, if they wish to modify it, enters the modifications in the input field and presses the approve button. The modified message is then sent to the server.

[1491] Output: Revised statement and final approval by the user.

[1492] Step 8:

[1493] Making the final call

[1494] The server posts the message confirmed by the user from the SNS account.

[1495] Input: Revised, last confirmed outgoing statement.

[1496] Specific operation: Send the revised message to the POST statuses / update endpoint of the SNS API (e.g., Twitter API) and execute the post.

[1497] Output: The message content published on the social media platform and notification of message completion.

[1498] (Application example 2)

[1499] 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."

[1500] In today's information-saturated society, users are overwhelmed by the amount of information available when using social networking services and content distribution services, making it difficult to send and receive content that is appropriate and emotionally appropriate. Furthermore, there is a lack of efficient ways to receive content that reflects one's own emotions or to obtain recommended content based on individual viewing history. Therefore, there is a need for a system that supports user-friendly, more personalized sending and content consumption.

[1501] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1502] In this invention, the server includes means for acquiring a user's past calling history, means for analyzing the past calling history to generate a calling pattern, means for automatically generating a new message based on the calling pattern, means for sending the new message to the user's terminal and requesting confirmation, means for reacquiring a message revised by the user, means for posting the final confirmed message from the user's SNS account, means for acquiring and analyzing the user's viewing history and emotion data to generate a new recommendation, means for sending the generated recommendation to the user's terminal and requesting confirmation, means for reacquiring a recommendation revised by the user, and means for saving the final confirmed recommendation. This enables users to efficiently make personalized calls and receive content recommendations based on their own emotions and viewing history.

[1503] "A user's past posting history" refers to a record of activities such as posts, comments, and shares that a user has made in the past on social media or other platforms.

[1504] "Communication patterns" are characteristic behavioral patterns, such as tendencies, frequently occurring themes, and posting timing, that are extracted by analyzing a user's past communication history.

[1505] A "new message" is a message that is automatically generated based on a message pattern and that the user will send in the future.

[1506] "Viewing history" is a record of videos, music, and other content that a user has viewed in the past.

[1507] "Emotion data" is information about emotions acquired from the user's facial expressions, reactions, feedback, etc. while watching.

[1508] A "recommendation" is a description of content recommended to a user, generated by analyzing viewing history and emotional data.

[1509] "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language.

[1510] An "interface" is the input and output means by which a user interacts with a system.

[1511] The present invention relates to a system for acquiring and analyzing a user's past sending history to generate new messages and recommendations. Specific embodiments will be described below.

[1512] Hardware and software used

[1513] This system mainly uses the following hardware and software:

[1514] Hardware: Smartphone, facial recognition camera (used to capture user emotion data)

[1515] Software: Python (programming language), natural language processing library "spaCy", sentiment analysis engine "Affectiva SDK", cloud database "Firebase"

[1516] System configuration

[1517] 1. Acquiring the user's past call history

[1518] The server obtains past call history from the user's SNS account.

[1519] This history is stored in a cloud database.

[1520] 2. Analysis of call history

[1521] The server analyzes the acquired call history using natural language processing technology (spaCy).

[1522] A call pattern is generated from the analysis results.

[1523] 3. Obtaining viewing history and emotion data

[1524] The server obtains the user's viewing history from their smartphone and collects emotional data using a facial recognition camera.

[1525] 4. Generating Recommendations

[1526] The server analyzes the viewing history and emotional data to generate new recommendations.

[1527] 5. Check the generated message and testimonials

[1528] The generated document is sent to the user's terminal and a confirmation message is displayed.

[1529] The user checks the document and makes corrections if necessary.

[1530] 6. Final confirmation and sending / saving

[1531] After the user has reviewed and corrected the document, it will be posted to the social media account after a final review, and the recommendation will be stored in a cloud database.

[1532] Data processing and calculation

[1533] Natural language processing: The server uses spaCy to analyze call history and extract keywords and frequently occurring themes.

[1534] Emotion analysis: The server uses the Affectiva SDK to analyze the facial recognition camera data of the user while watching to obtain emotional data.

[1535] Data storage and retrieval: We use the cloud database Firebase to store and manage user viewing history and generated documents.

[1536] Specific examples

[1537] Example 1: Using a Twitter account

[1538] 1. User logs in

[1539] A user accesses the system and logs in with a social networking account. The system obtains permission to access the social networking account.

[1540] 2. Obtain past activity history

[1541] The server uses the SNS API to obtain past call history.

[1542] 3. History Analysis

[1543] The call history collected by the server is analyzed using NLP technology.

[1544] 4. Generating Call Patterns

[1545] The server generates a transmission pattern from the analysis results.

[1546] 5. Emotion analysis

[1547] The server uses an emotion engine to analyze the user's emotions from the data from the facial recognition camera.

[1548] 6. Automatic generation of new messages

[1549] The server generates a new message based on the emotion and the message pattern.

[1550] 7. User Review of Documents

[1551] The generated document is sent to the user's terminal, and a message is displayed saying, "This document will be sent. Is this OK?"

[1552] 8. Transmission and storage

[1553] The document that the user has checked is posted via their social media account, and the recommendation is also saved in a cloud database.

[1554] Prompt Sentence Examples

[1555] Generate content recommendations for users based on their viewing history and emotional data. The viewing history is "e.g., frequently watches action movies, dramas, and comedies," and the emotional data is "e.g., smile, excitement, surprise."

[1556] By following the above procedure, users can efficiently send personal and emotional messages and recommend content.

[1557] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1558] Step 1:

[1559] The server retrieves past posting history from the user's SNS account. To do this, it uses the SNS's API and obtains account access permission with the user's consent. It receives SNS authentication information as input and retrieves posting history data as output. This data includes the content of the post, date and time, and reaction status (number of likes, number of comments, etc.).

[1560] Step 2:

[1561] The server stores the acquired call history in a cloud database to securely store the history data for later analysis. It receives the call history data as input and updates the database as output.

[1562] Step 3:

[1563] The server analyzes the saved call history using natural language processing technology (spaCy). It receives call history data as input, analyzes the data, and extracts keywords, frequently occurring themes, and the user's call trends as output. This analysis generates the user's call patterns.

[1564] Step 4:

[1565] The server acquires the user's viewing history and emotional data. It collects the viewing history from the user's smartphone and acquires the emotional data through a facial recognition camera. It receives the viewing history and the emotional data from the facial recognition camera as input and stores these data in a cloud database as output.

[1566] Step 5:

[1567] The server analyzes the viewing history and emotional data to generate new recommendations. It receives the viewing history and emotional data as input, analyzes them, and generates personalized recommendations as output. These recommendations are based on the user's interests and emotions.

[1568] Step 6:

[1569] The server sends the generated message and recommendation to the user's device and displays a confirmation message. It receives the generated message and recommendation as input and outputs them to the user's device. The message reads, "This message will be sent. Are you sure?"

[1570] Step 7:

[1571] The user checks the message and recommendation sent and makes corrections if necessary. The system receives the generated message and recommendation as input and outputs the corrected results.

[1572] Step 8:

[1573] The server retrieves the message modified by the user again and performs a final check. It receives the message modified by the user as input, checks it, and saves the final checked message as output.

[1574] Step 9:

[1575] The server posts the finalized message from the user's SNS account and saves the recommendation in a cloud database. The server receives the finalized message and recommendation as input, posts the message to the SNS account, saves the recommendation in the database, and notifies the user of the result.

[1576] Through the above steps, users can efficiently send personal messages and receive content recommendations based on their own emotions and viewing history.

[1577] 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.

[1578] 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.

[1579] 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.

[1580] [Fourth embodiment]

[1581] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1582] 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.

[1583] 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).

[1584] 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.

[1585] 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.

[1586] 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).

[1587] 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.

[1588] 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.

[1589] 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.

[1590] 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.

[1591] 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.

[1592] 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.

[1593] 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."

[1594] The present invention provides a system for preventing users from posting unintended content while improving the efficiency of posting on SNS. Specific embodiments of this system are described below.

[1595] System Overview

[1596] This system involves a series of operations: acquiring and analyzing a user's past call history to generate call patterns, automatically generating new messages based on these call patterns, prompting the user to confirm and revise the generated messages, and finally sending the confirmed content from the SNS account.

[1597] Program processing overview

[1598] 1. Get call history from user's SNS account:

[1599] The server accesses the user's social media account and uses the API to retrieve past postings, such as tweets, posts, and comments.

[1600] 2. Save call history:

[1601] The acquired posting history is saved in a database. Each posting history contains information such as the posting date and time, content, and reactions (number of likes, number of comments, etc.).

[1602] 3. Analysis of call history:

[1603] The server uses natural language processing (NLP) technology to analyze the posting history, extracting frequently occurring topics, keywords, and user posting trends.

[1604] 4. Generate call patterns:

[1605] Based on the analysis results, the server creates a calling pattern. For example, if there are many calls made on a particular day of the week or during a particular time period, it will extract that pattern.

[1606] 5. Automatic generation of new messages:

[1607] The server automatically generates new messages based on the user's posting patterns. For example, for a user who posts a lot of health-related information, the server generates the following message: "Today's small health habit: I recommend drinking a glass of water first thing in the morning."

[1608] 6. Request confirmation of message:

[1609] The generated message is sent to the user's terminal, and a confirmation message is displayed saying, "This message will be sent. Are you sure?"

[1610] 7. User Modifications and Verification:

[1611] The user checks the message and corrects it if necessary. The corrected message is then sent back to the server.

[1612] 8. Making the final call:

[1613] The server sends the message confirmed by the user from the SNS account, and notifies the user when the message is complete.

[1614] Specific examples

[1615] Example 1: Using a Twitter account

[1616] 1. User logs in:

[1617] A user accesses the system and logs in with their Twitter account. The system obtains permission to access the SNS account.

[1618] 2. Get past tweets:

[1619] The server uses the Twitter API to retrieve tweets from the past year, including the tweet content, posting date and time, and reaction status.

[1620] 3. Tweet analysis:

[1621] The server analyzes the collected tweet data using NLP techniques, including topic models (e.g., Latent Dirichlet Allocation) and keyword extraction.

[1622] 4. Creating a calling pattern:

[1623] The server generates a posting pattern from the analysis results. For example, if there are many tweets about "health," it identifies that pattern.

[1624] 5. Auto-generate new tweets:

[1625] The server automatically generates new tweets about "health." For example, the content generated is "Today's small health habit: I recommend drinking a glass of water first thing in the morning."

[1626] 6. User confirmation prompts:

[1627] The server sends the generated tweet to the user's device and displays the message, "This text will be sent. Is this OK?"

[1628] 7. User Modifications:

[1629] The user reviews the tweet and corrects it to "I recommend drinking a glass of water first thing in the morning!"

[1630] 8. Sending Tweets:

[1631] The server posts the corrected tweet from your Twitter account. After posting is complete, the server notifies the user that the tweet has been posted.

[1632] In this way, the present invention allows users to safely and efficiently send messages on SNS without feeling any burden. By obtaining analysis results from the user's past message history, automatically generating new messages and prompting the user for confirmation, the risk of sending unintended content is prevented.

[1633] The processing flow will be explained below.

[1634] Step 1:

[1635] A user accesses the system and logs in with their SNS account. The user then grants permission to access the system.

[1636] Step 2:

[1637] The server uses the SNS API to retrieve the user's past posting history (e.g., tweets and posts from the past year).

[1638] Step 3:

[1639] The server saves the acquired posting history in a database. The posting history includes information on the posting date and time, content, and reactions (number of likes, number of comments, etc.).

[1640] Step 4:

[1641] The server uses natural language processing (NLP) technology to analyze the saved call history and extract keywords, frequently occurring themes, and user trends.

[1642] Step 5:

[1643] The server generates a user's posting pattern based on the analysis results, which includes posting tendencies for specific topics and time periods.

[1644] Step 6:

[1645] The server automatically generates new messages based on the user's posting patterns and current trends. For example, if the user posts a lot of health-related information, it generates new health-related messages.

[1646] Step 7:

[1647] The server sends the generated message to the user's terminal and displays the message "This message will be sent. Is this OK?"

[1648] Step 8:

[1649] The user checks the message generated on the device, corrects the wording as necessary, and once corrections are complete, the user presses the approval button to send the confirmation.

[1650] Step 9:

[1651] The server receives the corrected message sent by the user and performs a final check.

[1652] Step 10:

[1653] The server posts the final confirmed message from the user's SNS account.

[1654] Step 11:

[1655] After the posting is complete, the server sends a notification to the user saying "Posting is complete."

[1656] In this way, each step reduces the burden on the user while preventing unintended transmission of content.

[1657] Example 1

[1658] 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."

[1659] In today's social networking sites, users frequently post, but it is difficult to maintain efficient, high-quality communication. There is also a risk of unintentionally posting inappropriate content. For example, users may forget the content and time of previous posts, making it difficult to generate new ideas. Furthermore, reviewing and revising posts takes time, placing a burden on users. The present invention aims to solve these problems and enable users to post on social networking sites efficiently and safely.

[1660] 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.

[1661] In this invention, the server includes means for obtaining authentication and access permission for the user's SNS account, means for obtaining the user's past transmission history, means for saving the transmission history in a database, means for using natural language processing technology to analyze the transmission history, means for generating transmission patterns, means for automatically generating new transmissions using a generative AI model, means for sending the generated transmissions to the user's device and requesting confirmation, means for re-obtaining transmissions modified by the user, and means for posting the final confirmed transmissions from the user's SNS account. This enables users to transmit efficiently and consistently based on past transmission content and patterns, reducing the risk of transmitting unintended content and enabling them to easily continue posting high-quality content.

[1662] "User" refers to an individual or corporation that has an SNS account and uses that account to conduct communication activities.

[1663] "SNS account" refers to an account used by a user on a social networking service (SNS), including accounts on services such as Twitter, Facebook, and Instagram.

[1664] "Outgoing communication history" refers to digital records of posts, tweets, comments, messages, etc. that a user has made in the past from their social media account.

[1665] A "database" refers to a digital system for efficiently storing, managing, and searching data such as call history and analysis results.

[1666] "Natural language processing technology" is a technology for analyzing, understanding, and generating human language using computers, and includes techniques such as topic modeling and keyword extraction.

[1667] "Calling pattern" refers to a pattern or tendency regarding a particular day of the week, time period, or content of calls, derived from an analysis of a user's past calling history.

[1668] "Generative AI model" refers to an algorithm or program that uses artificial intelligence to generate new messages, and specifically includes natural language generation models.

[1669] "New messages" refers to text content for posting on social media that is automatically generated based on the user's messaging patterns.

[1670] "User's device" refers to a digital device used by a user, such as a computer, smartphone, or tablet.

[1671] "Obtaining authentication and access permissions" refers to the process by which the server obtains the necessary authentication information and permissions to securely access a user's social networking account.

[1672] "Requesting confirmation" refers to the act of presenting the generated message to the user and requesting confirmation or correction of its contents.

[1673] "Modification" refers to a user making changes to a generated message to adjust its content.

[1674] "Final Reviewed Message" refers to the final content of the message after the user has reviewed it and made any necessary corrections.

[1675] "Posting" refers to the act of actually publishing a final, confirmed message from a user's social media account.

[1676] The present invention is a system that aims to improve the efficiency of users' SNS postings while preventing the posting of unintended content. This system involves a series of operations that acquires and analyzes the user's past posting history to generate posting patterns, and automatically generates new postings based on those patterns. Specific embodiments are described below.

[1677] System Overview

[1678] This system authenticates SNS accounts, acquires and saves call history, analyzes the history, generates call patterns, automatically generates new messages, allows users to confirm and edit them, and finally sends the message. These processes are performed by the server, the user's device, and the SNS account with appropriate authentication.

[1679] Hardware and software used

[1680] Server: Cloud server for high-performance processing and data storage (e.g., Amazon Web Services, Google Cloud Platform)

[1681] Devices: Computers, smartphones, and tablets that users use every day.

[1682] Database: Relational database management system such as MySQL, PostgreSQL

[1683] Natural language processing technology: Natural language processing libraries such as NLTK and spaCy

[1684] Generative AI models: Natural language generation models such as GPT-4

[1685] Details of data processing and calculation

[1686] 1. Authentication and Permissions:

[1687] A user accesses the system and logs in with a social networking account (e.g., Twitter). The server uses the OAuth protocol to obtain the authentication information and access permissions of the user's social networking account.

[1688] 2. Acquiring and saving call history:

[1689] The server retrieves the tweet history for the past year through the SNS API (e.g., Twitter API). The retrieved tweet history includes the tweet content, posting date and time, number of likes, number of comments, etc.

[1690] The server stores the retrieved data in a database.

[1691] 3. Analysis of call history:

[1692] The server analyzes the saved call history using natural language processing (NLP) techniques, such as topic modeling (e.g., Latent Dirichlet Allocation, LDA) and keyword extraction.

[1693] The analysis results identify frequently occurring topics, keywords, and communication trends.

[1694] 4. Generate call patterns:

[1695] The server then creates a calling pattern based on the analysis results. For example, if a user makes many calls on certain days of the week or during certain times of the day, it identifies that pattern.

[1696] 5. Automatic generation of new messages:

[1697] The server uses a generative AI model to generate new messages based on the message patterns and analysis results. For example, for a user who frequently talks about health, a message such as "Today's small health habit: I recommend drinking a glass of water first thing in the morning" may be generated.

[1698] 6. User Review and Correction:

[1699] The server sends the generated message to the user's terminal and asks for confirmation, "Is this message OK?"

[1700] The user checks the message and makes corrections if necessary, after which the corrected message is sent back to the server.

[1701] 7. Final Call:

[1702] The server then sends the message from the SNS account after the user has confirmed and corrected it. Once the message has been sent, the server notifies the user.

[1703] Examples of specific examples and prompts

[1704] Example: Using a Twitter account

[1705] 1. A user accesses the system and performs Twitter authentication.

[1706] 2. The server uses the Twitter API to retrieve tweets from the past year.

[1707] 3. The server stores the tweet data in a database.

[1708] 4. The server analyzes the tweet data using NLP technology, and finds results showing frequent health-related topics.

[1709] 5. The server creates a calling pattern related to "health."

[1710] 6. The server generates a new tweet saying, "Today's small health habit: I recommend drinking a glass of water first thing in the morning."

[1711] 7. The server sends the generated tweet to the user's device and asks for confirmation.

[1712] 8. The user checks and edits the message and sends the edited message to the server.

[1713] 9. The server sends the final confirmed tweet from the user's Twitter account and notifies the user that the tweet has been completed.

[1714] In this way, this system provides a series of steps necessary for users to post on SNS efficiently and safely. In particular, by analyzing past posting history and generating new posts based on the user's posting tendencies, the system can improve the consistency and quality of posts.

[1715] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1716] Step 1:

[1717] User logs in with social networking account

[1718] Input: Username and password, social media credentials

[1719] Action: The user accesses the system's login screen and enters their social network account credentials.

[1720] Output: Auth token and permissions to access social media accounts

[1721] The user clicks the "Login" button, and the server authenticates with the social network using the OAuth protocol, which gives the server permission to access the social network account from the user.

[1722] Step 2:

[1723] The server acquires the user's past call history

[1724] Input: Auth Token, SNS API

[1725] Process: The server sends a request to a social media API (e.g. Twitter API) using the obtained permissions.

[1726] Output: Tweet content, posting date and time, number of likes, number of comments, and other posting history data

[1727] The server retrieves tweet data from the social media account for the past year and receives it in JSON format.

[1728] Step 3:

[1729] The server saves the call history in a database

[1730] Input: Call history data

[1731] Processing: The server analyzes the received tweet data and stores the necessary information in a database.

[1732] Output: Call history stored in the database

[1733] The server connects to an SQL database (e.g., MySQL or PostgreSQL) and stores the extracted information in a table. This information includes the post date and time, content, and reactions (e.g., number of likes and comments).

[1734] Step 4:

[1735] The server analyzes the call history

[1736] Input: Call history stored in the database

[1737] Processing: The server analyzes the call history using natural language processing (NLP) techniques.

[1738] Output: Frequently appearing topics and keywords, user posting trends

[1739] Specifically, topic modeling (e.g., LDA) and keyword extraction are performed to identify whether topics such as "health" occur frequently.

[1740] Step 5:

[1741] The server generates the calling pattern

[1742] Input: Analysis results, frequently occurring topics and keywords

[1743] Processing: The server constructs a calling pattern based on the analysis results.

[1744] Output: Outgoing pattern

[1745] For example, it identifies a pattern, such as a user historically posting health-related tweets every Monday morning.

[1746] Step 6:

[1747] The server automatically generates a new message

[1748] Input: Transmission pattern, Generative AI model

[1749] Processing: The server generates a new message using a generative AI model based on the message pattern and analysis results.

[1750] Output: Auto-generated message

[1751] For example, based on a health-related topic, a message such as "Today's small health habit: It is recommended to drink a glass of water first thing in the morning" is generated.

[1752] Step 7:

[1753] The server sends a confirmation request to the user's device.

[1754] Input: Auto-generated message

[1755] Processing: The server sends the generated message to the user's terminal and displays a confirmation message saying, "This message will be sent. Are you sure?"

[1756] Output: User confirmation and correction requests

[1757] A notification is displayed on the user's device, and the user checks the message.

[1758] Step 8:

[1759] The user checks and edits the message

[1760] Input: Confirmation message, generated message

[1761] Action: The user checks the message displayed on the terminal and makes corrections if necessary.

[1762] Output: Corrected message

[1763] The user amends it to "I recommend drinking a glass of water first thing in the morning!" and resubmits it to the system.

[1764] Step 9:

[1765] The server makes the final call

[1766] Input: Corrected message

[1767] Processing: The server re-examines the revised message and sends it from the social media account.

[1768] Output: Update call history, notification of call completion

[1769] The final confirmed text is sent from the social media account, and the server notifies the user that the tweet has been completed.

[1770] (Application example 1)

[1771] 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."

[1772] In the past, users had to create, review, and post their own content on social media, which required a lot of time and effort. There was also the risk of posting unintended content or a lack of consistency in advertising. In addition, users had to come up with new copy each time they posted an ad, which was inefficient.

[1773] 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.

[1774] In this invention, the server includes means for acquiring a user's past transmission history, means for analyzing the past transmission history to generate a transmission pattern, means for automatically generating a new transmission based on the transmission pattern, means for sending the generated transmission to the user's terminal and requesting confirmation, means for re-acquiring a transmission modified by the user, means for posting the final confirmed transmission from the user's SNS account, means for acquiring the user's past advertising transmission history, means for analyzing the past advertising transmission history to generate a pattern related to an advertisement, means for automatically generating a new advertising copy using a generative AI model based on the advertising pattern, means for sending the generated advertising copy to the user's terminal and requesting confirmation, and for acquiring advertising copy modified by the user, and means for posting the final confirmed advertising copy from the user's SNS account. This reduces the burden on the user and enables efficient and safe management of SNS transmissions and advertising transmissions.

[1775] A "user" is a person who has an SNS account and uses the system to post messages and advertisements.

[1776] "Outgoing message history" is a record of messages sent by a user from their SNS account in the past, including information such as the date and time and responses.

[1777] The "calling pattern" refers to the regularity and tendency of a user's calls obtained by analyzing the past call history.

[1778] "Automatic generation" refers to the process by which the system generates new messaging or advertising copy without user intervention.

[1779] "Means for requesting confirmation" refers to a procedure for sending the generated message or advertisement copy to the user's terminal and prompting the user to confirm or correct it.

[1780] "SNS Account" means an account held by a User for the purpose of posting on an SNS platform.

[1781] "Natural language processing technology" refers to technology that enables systems to analyze, understand, and generate human language.

[1782] "Interface" means the user interface through which a user interacts with the system and modifies the generated messages and advertisements.

[1783] A "generative AI model" is a model that uses artificial intelligence and is used to automatically generate new messaging and advertising copy.

[1784] "Advertising history" is a record of the content of advertisements that a user has previously sent from their SNS account, including information such as the date and time and responses.

[1785] "Advertising patterns" refer to regularities and tendencies regarding a user's advertising that can be obtained by analyzing the past history of advertising transmissions.

[1786] This invention is a system for improving the efficiency of users' SNS and advertising activities and preventing the transmission of unintended content. This system acquires and analyzes the user's past communication history and advertising history to generate communication patterns and advertising patterns, and automatically generates new communication messages and advertising copies.

[1787] Hardware and software used

[1788] Hardware: User's smartphone, server

[1789] Software: Python, tweepy library, spacy library, generative AI model, database (e.g., PostgreSQL)

[1790] Processing steps

[1791] 1. Acquisition of the user's past call history and advertising call history

[1792] The server uses the API of the social media platform to obtain the user's past tweets and advertising history.

[1793] 2. Analysis of call history and advertising call history

[1794] The server stores the acquired call history and advertising call history in a database and analyzes them using natural language processing technology with the spacy library. Frequently occurring topics and keywords are extracted from the analysis results, and call patterns and advertising patterns are generated.

[1795] 3. Automatic generation of new messaging and advertising copy

[1796] The server uses a generative AI model to automatically generate new messaging and advertising copy based on the extracted patterns.

[1797] 4. User confirmation and correction

[1798] The generated message and advertisement copy are sent to the user's terminal, and a confirmation message such as "This message will be sent. Are you sure?" is displayed.

[1799] The user can modify the message and advertisement text through the interface, and the modified message and advertisement text are sent to the server for final confirmation.

[1800] 5. Making the final call

[1801] The message and advertisement confirmed by the user are sent from the SNS account via the server, and the server notifies the user when the message has been sent.

[1802] Specific examples

[1803] For example, if the user is on Twitter, it would look like this:

[1804] 1. A user logs in with their Twitter account: The server uses the Twitter API to retrieve tweets and advertising history from the past year.

[1805] 2. Analysis of tweet and advertising history: The server analyzes the data to extract frequently occurring keywords such as "health," "fitness," and "diet," and generates tweet and advertising patterns.

[1806] 3. Generate new Tweets and ad copy: Use generative AI models to automatically generate new tweets and ad copy, such as "Experience the latest health news now!"

[1807] 4. User confirmation: The user receives a message saying, "This message will be sent. Are you sure?" If necessary, the user can make corrections and send the message again to the server.

[1808] 5. Final Posting: The final, verified post and copy will be sent from your Twitter account and you will be notified.

[1809] Prompt Sentence Examples

[1810] "Analyze past tweets and extract frequently occurring keywords."

[1811] "Generate new ad text based on this keyword."

[1812] "Please have the user review the generated ad copy and then send it out as is."

[1813] In this way, this system helps users to efficiently manage their social media and advertising activities.

[1814] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1815] Step 1:

[1816] The server retrieves the user's past posting history and advertising posting history from the user's SNS account. Specifically, it retrieves the necessary data using the SNS platform's API. The input is the user's SNS account information, and the output is the retrieved past posting history.

[1817] Step 2:

[1818] The server saves the acquired calling history and ad sending history in a database. In this step, a database connection is established and the acquired data is saved in an appropriate format. The input is the acquired calling history and ad sending history, and the output is the saved database entry.

[1819] Step 3:

[1820] The server uses natural language processing technology to analyze the stored call history. Specifically, it uses the spacy library to extract frequently occurring topics and keywords. The input is the call history stored in the database, and the output is the extracted keywords and topics.

[1821] Step 4:

[1822] The server generates transmission patterns and advertising patterns based on the analysis results. Here, the user's transmission tendencies are identified based on the extracted keywords and topics. The input is the extracted keywords and topics, and the output is the generated transmission patterns and advertising patterns.

[1823] Step 5:

[1824] The server automatically generates new message and advertising copy using a generative AI model. The model is provided with message and advertising patterns as input and generates appropriate text. The input is the message and advertising patterns, and the output is the generated new message and advertising copy.

[1825] Step 6:

[1826] The server sends the generated message and advertisement copy to the user's terminal and asks for confirmation. In this step, a confirmation message is displayed to the user. The input is the generated message and advertisement copy, and the output is a confirmation message displayed on the user's terminal.

[1827] Step 7:

[1828] The user uses an interface to modify the message and advertisement copy. The modified content is sent back to the server. The input is the message and advertisement copy modified by the user, and the output is the modified content.

[1829] Step 8:

[1830] The server retrieves the message and advertisement copy corrected by the user again and performs a final confirmation. In this step, the confirmed content is displayed to the user again and sent after confirmation. The input is the corrected message and advertisement copy, and the output is the final confirmed message and advertisement copy.

[1831] Step 9:

[1832] The server posts the final confirmed message and advertisement copy from the user's SNS account. Once the message is completed, the server sends a notification to the user. The input is the final confirmed message and advertisement copy, and the output is the content posted on the SNS platform and a notification to the user.

[1833] 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.

[1834] The present invention provides a system that improves the efficiency of users' SNS postings, prevents the posting of unintended content, and enables postings that reflect the user's emotions. Specific embodiments of this system are described below.

[1835] System Overview

[1836] This system involves a series of operations: acquiring and analyzing a user's past communication history to generate communication patterns, and automatically generating new messages based on these communication patterns. It also combines an emotion engine to recognize the user's emotions and reflect them in the messages, enabling more personal and emotionally rich messages. The generated messages are then requested to be confirmed and revised by the user, and the final confirmed content is sent from the SNS account.

[1837] Program processing overview

[1838] 1. Get call history from user's SNS account:

[1839] The server accesses the user's social media account and uses the API to retrieve past postings, such as tweets, posts, and comments.

[1840] 2. Save call history:

[1841] The acquired posting history is saved in a database. Each posting history includes the posting date and time, content, and reactions (number of likes, number of comments, etc.).

[1842] 3. Analysis of call history:

[1843] The server uses natural language processing (NLP) technology to analyze call history and extract keywords, frequently occurring themes, and user trends.

[1844] 4. Generate call patterns:

[1845] Based on the analysis results, the server creates a calling pattern. For example, if there are many calls made on a particular day of the week or during a particular time period, it will extract that pattern.

[1846] 5. Sentiment analysis using emotion engine:

[1847] The server uses an emotion engine to recognize the user's emotions from the call history and analyze the emotional trends.

[1848] 6. Automatic generation of new messages:

[1849] The server automatically generates new messages based on the results of the user's communication patterns and emotion analysis. For example, if a user has frequently sent messages expressing "fun" emotions in the past, the server will generate messages that reflect those emotions.

[1850] 7. Request confirmation of message:

[1851] The generated message is sent to the user's terminal, and a confirmation message is displayed saying, "This message will be sent. Are you sure?"

[1852] 8. User Modifications and Verification:

[1853] The user checks the message and corrects it if necessary. Once the corrections are complete, the user presses the approval button to send the confirmation.

[1854] 9. Making the final call:

[1855] The server sends the message confirmed by the user from the SNS account, and notifies the user when the message is complete.

[1856] Specific examples

[1857] Example 1: Using a Twitter account

[1858] 1. User logs in:

[1859] A user accesses the system and logs in with their Twitter account. The system obtains permission to access the SNS account.

[1860] 2. Get past tweets:

[1861] The server uses the Twitter API to retrieve tweets from the past year, including the tweet content, posting date and time, and reaction status.

[1862] 3. Tweet analysis:

[1863] The server analyzes the collected tweet data using NLP techniques, including topic models (e.g., Latent Dirichlet Allocation) and keyword extraction.

[1864] 4. Creating a calling pattern:

[1865] The server generates a posting pattern from the analysis results. For example, if there are many tweets about "health," it identifies that pattern.

[1866] 5. Emotion analysis:

[1867] The server uses an emotion engine to analyze the user's emotions from the content of past tweets and identify emotions such as joy, sadness, and excitement.

[1868] 6. Automatically generate new tweets:

[1869] The server generates new tweets that reflect the "fun" emotion based on the emotion and the sending pattern. For example, a tweet like "Today is another great day! My first walk of the morning was amazing."

[1870] 7. User confirmation prompts:

[1871] The server sends the generated tweet to the user's device and displays the message, "This text will be sent. Is this OK?"

[1872] 8. User Modifications:

[1873] The user checks the tweet and corrects it to "My first walk of the morning was amazing!"

[1874] 9. Sending Tweets:

[1875] The server posts the corrected tweet from your Twitter account. After posting is complete, the server notifies the user that the tweet has been posted.

[1876] In this way, the present invention allows users to safely and efficiently send messages on social networking sites without feeling any burden. By analyzing the user's past message history and emotions, automatically generating new messages and prompting the user for confirmation, the risk of sending unintended content is prevented. Furthermore, by generating messages that reflect the user's emotions, more personal and emotional communication is realized.

[1877] The processing flow will be explained below.

[1878] Step 1:

[1879] A user accesses the system and logs in with their SNS account. The user then grants permission to access the system.

[1880] Step 2:

[1881] The server uses the SNS API to retrieve the user's past posting history (e.g., tweets and posts from the past year).

[1882] Step 3:

[1883] The server saves the acquired posting history in a database. The posting history includes information on the posting date and time, content, and reactions (number of likes, number of comments, etc.).

[1884] Step 4:

[1885] The server uses natural language processing (NLP) technology to analyze the saved call history and extract keywords, frequently occurring themes, and user trends.

[1886] Step 5:

[1887] The server generates a user's posting pattern based on the analysis results, which includes posting tendencies for specific topics and time periods.

[1888] Step 6:

[1889] The server uses an emotion engine to recognize and analyze the user's emotions contained in the communication history. For example, if the past communication contains a lot of "fun" content, the emotion is identified.

[1890] Step 7:

[1891] The server automatically generates new messages based on the user's message patterns and the results of emotion analysis. For example, if a user posts a lot of health-related information and has a "happy" emotion, the server generates a message like this: "It's another great day! Drink a glass of water first thing in the morning and have a healthy day."

[1892] Step 8:

[1893] The server sends the generated message to the user's terminal and displays a confirmation message saying, "This message will be sent. Are you sure?"

[1894] Step 9:

[1895] The user checks the message generated on the device and modifies it as necessary. For example, they can modify it to "It's another great day today!" Once the modifications are complete, the user presses the approval button to send the confirmation.

[1896] Step 10:

[1897] The server receives the revised message sent by the user, performs a final check, and confirms the approved message as the final message.

[1898] Step 11:

[1899] The server posts the final confirmed message from the user's SNS account.

[1900] Step 12:

[1901] After the posting is complete, the server sends a notification to the user saying "Posting is complete." The user receives the notification and confirms that the posting has been completed successfully.

[1902] Example 2

[1903] 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."

[1904] In the conventional SNS posting process, users must manually consider what to post, which takes time and effort. There is also a risk of posting unintended content. Furthermore, it is difficult to post content that reflects the user's emotions. There is a need for a system that can solve these problems and enable users to post on SNS efficiently and safely.

[1905] 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.

[1906] In this invention, the server includes means for acquiring a user's past transmission history, means for analyzing the past transmission history to generate transmission patterns and emotional tendencies, means for automatically generating new transmission messages based on the transmission patterns and emotional tendencies, means for sending the generated transmission messages to the user's terminal and requesting confirmation, means for reacquiring transmission messages corrected by the user, and means for posting the final confirmed transmission message from the user's SNS account. This enables the user to efficiently generate new posts based on the past transmission history and emotional tendencies, check and correct them to prevent transmission of unintended content, and ultimately safely transmit transmission messages that reflect their emotions.

[1907] "A user's past posting history" refers to data such as the content posted by the user in the past through their social media account, the posting date and time, the number of likes, comments, and retweets.

[1908] "Analysis" refers to the process of analyzing communication history using natural language processing technology and an emotion engine to extract keywords, analyze topics, and score emotions.

[1909] "Communication patterns" refer to the frequency of posts on specific days or time periods, frequently occurring topics, and user posting tendencies extracted based on the user's past communication history that has been acquired and analyzed.

[1910] "Emotional tendency" is calculated by analyzing emotions from a user's past communication history using an emotion engine, and indicates the frequency and patterns of emotions such as positive, negative, and neutral.

[1911] "Automatic generation of new messages" refers to the process of automatically generating new social media post content using a generative AI model based on acquired and analyzed message patterns and emotional tendencies.

[1912] "Generative AI model" refers to an artificial intelligence model that generates sentences in natural language based on input prompts, including, for example, language models.

[1913] The "means for requesting confirmation" refers to a process of sending an automatically generated message to the user's terminal and providing an interface that prompts the user to confirm the message content.

[1914] The "means for re-obtaining the corrected message" refers to the process in which the server re-obtains the content of the message that the user has modified and then performs a final check.

[1915] "Final confirmed message" refers to the final message retrieved by the server after the user has confirmed and made any necessary corrections.

[1916] "SNS Account" refers to a personal or corporate account used by a User through registration and authentication on an SNS platform.

[1917] System Overview

[1918] This invention is a system that improves the efficiency of users' SNS posting, prevents the posting of unintended content, and enables posting that reflects the user's emotions. Specifically, this system analyzes the user's past posting history and automatically generates new messages based on their posting patterns and emotional tendencies. This system is operated through the interaction of a server, terminals, and users.

[1919] Hardware and Software Configuration

[1920] The server has the following main components:

[1921] Database: Used to store user call history, for example, using an RDBMS such as MySQL.

[1922] Natural language processing (NLP) engine: Analyzes call history using Python libraries such as nltk and spacy.

[1923] Emotion Engine: Uses libraries such as TextBlob and VADER to analyze user emotions.

[1924] Generative AI model: Generate new messages using a generative AI model (e.g., a language model).

[1925] The device is used by the user to check and edit messages sent, and a web browser or smartphone app is used.

[1926] Users are responsible for logging into the system, granting API access permissions, and reviewing and modifying generated messages.

[1927] Data processing and calculation

[1928] 1. Get call history:

[1929] The server uses the API of the SNS platform to obtain the user's past communication history.

[1930] For example, using the Twitter API, access the GET statuses / user_timeline endpoint.

[1931] 2. Save call history:

[1932] The acquired call history is saved in a database (such as MySQL).

[1933] Data such as the posting date and time of each message, content, number of likes, number of retweets, and number of comments are saved.

[1934] 3. Analysis of call history:

[1935] The server uses an NLP engine to analyze call history and perform keyword extraction and topic analysis.

[1936] Use Python's nltk and spacy libraries to tokenize the text and extract noun phrases.

[1937] 4. Generating communication patterns and sentiment trends:

[1938] The server generates communication patterns and emotional tendencies based on the analysis results.

[1939] Use a sentiment engine (TextBlob or VADER) to calculate a sentiment score for each call.

[1940] 5. Automatic generation of new messages:

[1941] The server automatically generates new messages using a generative AI model.

[1942] For example, a prompt sentence such as "The user has posted a lot of fun content in the past" is input into the generative AI model.

[1943] Specific examples

[1944] Example 1: Twitter account operation

[1945] 1. User logs in:

[1946] A user accesses the system and logs in with their Twitter account.

[1947] The system will ask for permission to access your social media account.

[1948] 2. Get past tweets:

[1949] The server uses the Twitter API to retrieve tweets from the past year.

[1950] The retrieved tweets include the tweet content, posting date and time, and reaction status.

[1951] 3. Tweet analysis:

[1952] The tweet data collected by the server is analyzed using NLP technology.

[1953] Analysis includes topic models (e.g., Latent Dirichlet Allocation) and keyword extraction.

[1954] 4. Building communication patterns and sentiment trends:

[1955] The server generates communication patterns and emotional tendencies from the analysis results.

[1956] For example, if emotions such as "health" or "fun" are common, patterns that reflect this can be identified.

[1957] 5. Auto-generate new tweets:

[1958] The server generates new tweets that reflect the emotion of "fun" based on the emotion and the sending pattern.

[1959] For example, by inputting the prompt sentence "The user has posted a lot of fun content in the past" into the generative AI model, it generates "Today is another wonderful day! The first walk of the morning was great."

[1960] 6. User confirmation prompts:

[1961] The server sends the generated tweet to the user's device and displays a confirmation message saying, "This text will be sent. Are you sure?"

[1962] 7. User Modifications:

[1963] The user checks the tweet and corrects it to "My first walk of the morning was amazing!"

[1964] 8. Sending Tweets:

[1965] The server posts the corrected tweet from your Twitter account.

[1966] After the posting is complete, the server notifies the user that the tweet has been posted.

[1967] As described above, this invention allows users to safely and efficiently send messages on social networking sites without feeling any burden. It analyzes the user's past message history and emotions, automatically generates new messages, and prompts the user for confirmation, preventing the risk of sending unintended content. Furthermore, by generating messages that reflect the user's emotions, it enables more personal and emotionally rich communication.

[1968] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1969] Step 1:

[1970] Acquiring call history

[1971] The server uses the SNS platform's API to obtain the user's past communication history.

[1972] Input: User credentials and API endpoint.

[1973] Specific operation: Accesses a social media API (e.g., Twitter API) and retrieves past tweet data from the GET statuses / user_timeline endpoint. The request includes an access token.

[1974] Output: The acquired posting history data (e.g. tweet content, posting date and time, number of likes, number of retweets, number of comments) is returned to the server.

[1975] Step 2:

[1976] Save call history

[1977] The server stores the acquired call history in a database.

[1978] Input: Call history data.

[1979] What it does: It connects to a database such as MySQL and executes a SQL query like INSERT INTO posts (date, content, likes, retweets, comments) VALUES (...) to store historical data.

[1980] Output: Each call history stored in the database.

[1981] Step 3:

[1982] Analysis of call history

[1983] The server analyzes the call history using a natural language processing (NLP) engine.

[1984] Input: Saved call history data.

[1985] How it works: It uses Python's nltk and spacy libraries to extract keywords, tokenize text, and extract noun phrases, and also applies algorithms such as Latent Dirichlet Allocation (LDA) to perform topic analysis.

[1986] Output: Keyword list, topic model, data on user posting habits.

[1987] Step 4:

[1988] Generating communication patterns and sentiment trends

[1989] The server generates communication patterns and emotional tendencies based on the analysis results.

[1990] Input: Analysis results (keyword list, topic model, etc.).

[1991] How it works: The server uses an emotion engine (such as TextBlob or VADER) to calculate the emotion score (positive, negative, neutral, etc.) of each post, and performs frequency and trend analysis. It also analyzes the frequency of posts by day of the week and time of day.

[1992] Output: Posting pattern data (e.g., frequency of posts on specific days or times), sentiment data (e.g., many positive posts).

[1993] Step 5:

[1994] Automatic generation of new messages

[1995] The server automatically generates new messages using a generative AI model.

[1996] Input: Call pattern and emotional tendency data, prompt sentence.

[1997] Specific operation: A prompt sentence is input into the generative AI model to generate a new message. For example, the prompt sentence can be "The user has posted many enjoyable messages in the past," and the model will generate a new sentence based on that.

[1998] Output: The new message generated.

[1999] Step 6:

[2000] Request confirmation of message

[2001] The server sends the generated message to the user's terminal and asks for confirmation.

[2002] Input: The generated message.

[2003] Specific operation: The generated message is sent to the user's device, and a confirmation message is displayed saying, "This message will be sent. Are you sure?"

[2004] Output: A confirmation message that is displayed on the user's terminal.

[2005] Step 7:

[2006] User correction and confirmation

[2007] The user checks the generated message and makes corrections as necessary.

[2008] Input: User feedback and corrections.

[2009] Specific operation: The user checks the message and, if they wish to modify it, enters the modifications in the input field and presses the approve button. The modified message is then sent to the server.

[2010] Output: Revised statement and final approval by the user.

[2011] Step 8:

[2012] Making the final call

[2013] The server posts the message confirmed by the user from the SNS account.

[2014] Input: Revised, last confirmed outgoing statement.

[2015] Specific operation: Send the revised message to the POST statuses / update endpoint of the SNS API (e.g., Twitter API) and execute the post.

[2016] Output: The message content published on the social media platform and notification of message completion.

[2017] (Application example 2)

[2018] 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."

[2019] In today's information-saturated society, users are overwhelmed by the amount of information available when using social networking services and content distribution services, making it difficult to send and receive content that is appropriate and emotionally appropriate. Furthermore, there is a lack of efficient ways to receive content that reflects one's own emotions or to obtain recommended content based on individual viewing history. Therefore, there is a need for a system that supports user-friendly, more personalized sending and content consumption.

[2020] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[2021] In this invention, the server includes means for acquiring a user's past calling history, means for analyzing the past calling history to generate a calling pattern, means for automatically generating a new message based on the calling pattern, means for sending the new message to the user's terminal and requesting confirmation, means for reacquiring a message revised by the user, means for posting the final confirmed message from the user's SNS account, means for acquiring and analyzing the user's viewing history and emotion data to generate a new recommendation, means for sending the generated recommendation to the user's terminal and requesting confirmation, means for reacquiring a recommendation revised by the user, and means for saving the final confirmed recommendation. This enables users to efficiently make personalized calls and receive content recommendations based on their own emotions and viewing history.

[2022] "A user's past posting history" refers to a record of activities such as posts, comments, and shares that a user has made in the past on social media or other platforms.

[2023] "Communication patterns" are characteristic behavioral patterns, such as tendencies, frequently occurring themes, and posting timing, that are extracted by analyzing a user's past communication history.

[2024] A "new message" is a message that is automatically generated based on a message pattern and that the user will send in the future.

[2025] "Viewing history" is a record of videos, music, and other content that a user has viewed in the past.

[2026] "Emotion data" is information about emotions acquired from the user's facial expressions, reactions, feedback, etc. while watching.

[2027] A "recommendation" is a description of content recommended to a user, generated by analyzing viewing history and emotional data.

[2028] "Natural language processing technology" is a technology that enables computers to understand, analyze, and generate human language.

[2029] An "interface" is the input and output means by which a user interacts with a system.

[2030] The present invention relates to a system for acquiring and analyzing a user's past sending history to generate new messages and recommendations. Specific embodiments will be described below.

[2031] Hardware and software used

[2032] This system mainly uses the following hardware and software:

[2033] Hardware: Smartphone, facial recognition camera (used to capture user emotion data)

[2034] Software: Python (programming language), natural language processing library "spaCy", sentiment analysis engine "Affectiva SDK", cloud database "Firebase"

[2035] System configuration

[2036] 1. Acquiring the user's past call history

[2037] The server obtains past call history from the user's SNS account.

[2038] This history is stored in a cloud database.

[2039] 2. Analysis of call history

[2040] The server analyzes the acquired call history using natural language processing technology (spaCy).

[2041] A call pattern is generated from the analysis results.

[2042] 3. Obtaining viewing history and emotion data

[2043] The server obtains the user's viewing history from their smartphone and collects emotional data using a facial recognition camera.

[2044] 4. Generating Recommendations

[2045] The server analyzes the viewing history and emotional data to generate new recommendations.

[2046] 5. Check the generated message and testimonials

[2047] The generated document is sent to the user's terminal and a confirmation message is displayed.

[2048] The user checks the document and makes corrections if necessary.

[2049] 6. Final confirmation and sending / saving

[2050] After the user has reviewed and corrected the document, it will be posted to the social media account after a final review, and the recommendation will be stored in a cloud database.

[2051] Data processing and calculation

[2052] Natural language processing: The server uses spaCy to analyze call history and extract keywords and frequently occurring themes.

[2053] Emotion analysis: The server uses the Affectiva SDK to analyze the facial recognition camera data of the user while watching to obtain emotional data.

[2054] Data storage and retrieval: We use the cloud database Firebase to store and manage user viewing history and generated documents.

[2055] Specific examples

[2056] Example 1: Using a Twitter account

[2057] 1. User logs in

[2058] A user accesses the system and logs in with a social networking account. The system obtains permission to access the social networking account.

[2059] 2. Obtain past activity history

[2060] The server uses the SNS API to obtain past call history.

[2061] 3. History Analysis

[2062] The call history collected by the server is analyzed using NLP technology.

[2063] 4. Generating Call Patterns

[2064] The server generates a transmission pattern from the analysis results.

[2065] 5. Emotion analysis

[2066] The server uses an emotion engine to analyze the user's emotions from the data from the facial recognition camera.

[2067] 6. Automatic generation of new messages

[2068] The server generates a new message based on the emotion and the message pattern.

[2069] 7. User Review of Documents

[2070] The generated document is sent to the user's terminal, and a message is displayed saying, "This document will be sent. Is this OK?"

[2071] 8. Transmission and storage

[2072] The document that the user has checked is posted via their social media account, and the recommendation is also saved in a cloud database.

[2073] Prompt Sentence Examples

[2074] Generate content recommendations for users based on their viewing history and emotional data. The viewing history is "e.g., frequently watches action movies, dramas, and comedies," and the emotional data is "e.g., smile, excitement, surprise."

[2075] By following the above procedure, users can efficiently send personal and emotional messages and recommend content.

[2076] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[2077] Step 1:

[2078] The server retrieves past posting history from the user's SNS account. To do this, it uses the SNS's API and obtains account access permission with the user's consent. It receives SNS authentication information as input and retrieves posting history data as output. This data includes the content of the post, date and time, and reaction status (number of likes, number of comments, etc.).

[2079] Step 2:

[2080] The server stores the acquired call history in a cloud database to securely store the history data for later analysis. It receives the call history data as input and updates the database as output.

[2081] Step 3:

[2082] The server analyzes the saved call history using natural language processing technology (spaCy). It receives call history data as input, analyzes the data, and extracts keywords, frequently occurring themes, and the user's call trends as output. This analysis generates the user's call patterns.

[2083] Step 4:

[2084] The server acquires the user's viewing history and emotional data. It collects the viewing history from the user's smartphone and acquires the emotional data through a facial recognition camera. It receives the viewing history and the emotional data from the facial recognition camera as input and stores these data in a cloud database as output.

[2085] Step 5:

[2086] The server analyzes the viewing history and emotional data to generate new recommendations. It receives the viewing history and emotional data as input, analyzes them, and generates personalized recommendations as output. These recommendations are based on the user's interests and emotions.

[2087] Step 6:

[2088] The server sends the generated message and recommendation to the user's device and displays a confirmation message. It receives the generated message and recommendation as input and outputs them to the user's device. The message reads, "This message will be sent. Are you sure?"

[2089] Step 7:

[2090] The user checks the message and recommendation sent and makes corrections if necessary. The system receives the generated message and recommendation as input and outputs the corrected results.

[2091] Step 8:

[2092] The server retrieves the message modified by the user again and performs a final check. It receives the message modified by the user as input, checks it, and saves the final checked message as output.

[2093] Step 9:

[2094] The server posts the finalized message from the user's SNS account and saves the recommendation in a cloud database. The server receives the finalized message and recommendation as input, posts the message to the SNS account, saves the recommendation in the database, and notifies the user of the result.

[2095] Through the above steps, users can efficiently send personal messages and receive content recommendations based on their own emotions and viewing history.

[2096] 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.

[2097] 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.

[2098] 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 robot 414.

[2099] 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.

[2100] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion 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.

[2101] 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.

[2102] 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).

[2103] 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.

[2104] 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."

[2105] 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.

[2106] 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).

[2107] 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.

[2108] 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.

[2109] 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.

[2110] 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.

[2111] 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.

[2112] 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.

[2113] 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.

[2114] 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.

[2115] 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.

[2116] 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.

[2117] The following is further disclosed regarding the above embodiment.

[2118] (Claim 1)

[2119] A means for acquiring a user's past call history;

[2120] means for analyzing past call history and generating a call pattern;

[2121] means for automatically generating new messages based on the message pattern;

[2122] means for transmitting the generated message to a user's terminal and requesting confirmation;

[2123] A means for retrieving a message that has been modified by the user;

[2124] The system includes a means for posting a final confirmed message from a user's social media account.

[2125] (Claim 2)

[2126] 2. The system according to claim 1, wherein the user's call history is analyzed using natural language processing technology.

[2127] (Claim 3)

[2128] 10. The system of claim 1, further comprising an interface for a user to make corrections to the generated message.

[2129] "Example 1"

[2130] (Claim 1)

[2131] A means for acquiring a user's past call history;

[2132] means for analyzing past call history and generating a call pattern;

[2133] means for automatically generating new messages based on the message pattern;

[2134] means for transmitting the generated message to a user's terminal and requesting confirmation;

[2135] A means for retrieving a message that has been modified by the user;

[2136] A means for posting the final confirmed message from the user's social media account;

[2137] A means for obtaining authentication and access permissions for a user's social networking account;

[2138] A means for storing the call history in a database;

[2139] A means for using natural language processing technology to analyze the call history;

[2140] A system that includes a means for automatically generating new messages using a generative AI model.

[2141] (Claim 2)

[2142] 2. The system according to claim 1, wherein the system analyzes the user's call history using natural language processing technology to extract frequently occurring topics and keywords.

[2143] (Claim 3)

[2144] 10. The system of claim 1, further comprising an interface for a user to make corrections to the generated message.

[2145] "Application Example 1"

[2146] (Claim 1)

[2147] A means for acquiring a user's past call history;

[2148] means for analyzing past call history and generating a call pattern;

[2149] means for automatically generating new messages based on the message pattern;

[2150] means for transmitting the generated message to a user's terminal and requesting confirmation;

[2151] A means for retrieving a message that has been modified by the user;

[2152] A means for posting the final confirmed message from the user's social media account;

[2153] A means for acquiring a user's past advertisement transmission history;

[2154] A means for analyzing a history of past advertisement transmissions to generate patterns related to advertisements;

[2155] A means of automatically generating new ad copy using an AI model based on ad patterns;

[2156] means for transmitting the generated advertisement copy to a user's terminal for confirmation and for acquiring advertisement copy modified by the user;

[2157] The system includes a means for posting the final, verified advertising copy from a user's social media account.

[2158] (Claim 2)

[2159] 2. The system according to claim 1, wherein the user's call history is analyzed using natural language processing technology.

[2160] (Claim 3)

[2161] 10. The system of claim 1, further comprising an interface for allowing a user to make modifications to the generated messages and advertisements.

[2162] "Example 2: Combining Emotion Engines"

[2163] (Claim 1)

[2164] A means for acquiring a user's past call history;

[2165] A means for analyzing past call history to generate call patterns and emotional tendencies;

[2166] A means for automatically generating new messages based on the message patterns and emotional tendencies;

[2167] means for transmitting the generated message to a user's terminal and requesting confirmation;

[2168] A means for retrieving a message that has been modified by the user;

[2169] The system includes a means for posting a final confirmed message from a user's social media account.

[2170] (Claim 2)

[2171] 10. The system of claim 1, wherein the user's call history is analyzed using natural language processing technology and an emotion engine.

[2172] (Claim 3)

[2173] 10. The system of claim 1, further comprising an interface for a user to make corrections to the generated message.

[2174] "Application example 2 when combining emotion engines"

[2175] (Claim 1)

[2176] A means for acquiring a user's past call history;

[2177] means for analyzing past call history and generating a call pattern;

[2178] means for automatically generating new messages based on the message pattern;

[2179] means for transmitting the generated message to a user's terminal and requesting confirmation;

[2180] A means for retrieving a message that has been modified by the user;

[2181] A means for posting the final confirmed message from the user's social media account;

[2182] A means for acquiring and analyzing a user's viewing history and emotional data to generate new recommendations;

[2183] means for transmitting the generated recommendation to a user's device for confirmation;

[2184] a means for retrieving the user's revised recommendation;

[2185] The system includes a means for storing final verified testimonials.

[2186] (Claim 2)

[2187] 2. The system according to claim 1, wherein the user's call history is analyzed using natural language processing technology.

[2188] (Claim 3)

[2189] 10. The system of claim 1, further comprising an interface for a user to make corrections to the generated message. [...

Claims

1. A means for acquiring a user's past call history; means for analyzing past call history and generating a call pattern; means for automatically generating new messages based on the message pattern; means for transmitting the generated message to a user's terminal and requesting confirmation; A means for retrieving a message that has been modified by the user; and means for posting the final confirmed message from the user's social media account.

2. 2. The system according to claim 1, wherein the user's call history is analyzed using natural language processing technology.

3. 10. The system of claim 1, further comprising an interface for allowing a user to make corrections to the generated message.

Images