System

Abstract

A system is provided.SOLUTION: A system comprising: means for collecting past post data of a user; means for training a generative model that learns a style of the user based on the past post data; means for automatically generating a daily outgoing content using the generative model; means for presenting the automatically generated outgoing content to the user and allowing the user to make a modification; and means for posting the modified outgoing content to a predetermined social networking service.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Modern social networking services (SNS) require users to post frequently, but maintaining daily updates can be a significant burden for many users. For users who want to build a large following, maintaining a consistent daily update requires a significant amount of time and effort. Furthermore, regularly posting interesting content requires users to continually provide new ideas, which can also put pressure on users. As a result, the quality of updates declines, making it difficult to maintain follower interest. In response, there is a demand for a solution that automates regular daily updates, allowing users to focus on the messages and creative content they truly want to share. [Means for solving the problem]

[0005] The present invention provides a system including: means for collecting a user's past posting data; means for training a generative model that learns the user's writing style based on the past posting data; means for automatically generating daily posts using the generative model; means for presenting the automatically generated posts to the user and allowing the user to make revisions; and means for posting the revised posts to a specified social networking service. This system allows users to automatically generate natural-looking posts based on past posting data, and further allows users to review and modify the generated content to post posts in line with their intentions. This eliminates the need for daily posting and enables users to continuously provide content that attracts their followers' attention. Furthermore, the system includes means for scheduling the generated posts so that they are presented to the user at specific times; means for learning popular topics; means for automatically generating text suggestions to match the content of images; and means for simultaneously posting the revised posts to multiple social networking accounts, thereby achieving efficient social networking management and effective communication for users.

[0006] "User" means an individual or organization that posts using a social networking service.

[0007] "Past posting data" refers to information such as text, images, and videos that a user previously posted on a social networking service.

[0008] A "generative model" refers to an algorithm or program that uses machine learning techniques to automatically generate text.

[0009] "Training" refers to the process by which the generative model learns a user's writing style and manner of writing based on past posting data.

[0010] "Daily content" refers to the content of regular posts on social networking services.

[0011] "Auto-generation" is the process by which a generative model automatically creates new text based on input data.

[0012] "Presenting" refers to displaying the generated transmission content to the user.

[0013] "Modification" refers to a user manually making changes to the submitted content.

[0014] "Specified social networking service" refers to a specific social networking platform on which users post on a daily basis.

[0015] "Schedule management" refers to the process of managing events and tasks to be automatically executed at specific times.

[0016] A "hot topic" is a topic or theme that is attracting a lot of attention at a particular time or place.

[0017] "Image content" refers to the visual information contained in an image posted to a social networking service.

[0018] "Multiple social networking accounts" refers to accounts held by a user on two or more different social networking sites. [Brief explanation of the drawings]

[0019] [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

[0020] 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.

[0021] First, the terms used in the following description will be explained.

[0022] 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).

[0023] 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.

[0024] 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.

[0025] 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.

[0026] 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."

[0027] [First embodiment]

[0028] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0029] 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.

[0030] 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).

[0031] 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.

[0032] 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.

[0033] 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.

[0034] 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.

[0035] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0036] 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.

[0037] 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.

[0038] 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.

[0039] 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."

[0040] This invention relates to a system that automatically generates daily posts by collecting data on users' past posts on social networking services (SNS), training a generative model that learns writing styles and trends based on that data, and presenting the generated posts to the user, who can then make any necessary edits and finally post the posts to the SNS.

[0041] System configuration

[0042] The system consists of the following main components:

[0043] 1. Server: Responsible for collecting data, training generative models, and automatically generating dissemination content.

[0044] 2. Terminal: Presents the generated transmission content to the user and provides an interface for editing.

[0045] 3. User: A user of the SNS who makes final confirmations and corrections to the content posted.

[0046] System Operation

[0047] 1. Collection of past posting data

[0048] The server uses the SNS API to collect users' past posting data, including the content of posts, images, videos, and metadata.

[0049] 2. Training the generative model

[0050] The server uses the collected data to train a generative model (e.g., GPT-3), which learns the user's writing style and the phrases they use.

[0051] 3. Automatic generation of daily posting content

[0052] The server uses a trained generative model to automatically generate daily posts, which contain natural-sounding sentences based on past posting data.

[0053] 4. Check and correct the content of the message

[0054] The automatically generated message is presented to the user via the terminal, who can then check it and make any necessary corrections.

[0055] 5. Final call processing

[0056] Once the corrections are complete, the server posts the final message via the SNS API.

[0057] Specific examples

[0058] Example 1:

[0059] Let's say a user frequently posts "Good morning! Let's do our best today!" every morning. In this case, the system works as follows:

[0060] The server collects past posting data and creates a dataset that includes other morning greeting posts from this user.

[0061] The server trains a generative model to learn the user's writing style and frequently used phrases.

[0062] Every morning at a set time, the server automatically generates a new "good morning" message using this model.

[0063] This message is sent to the device and the user modifies it to say, "Good morning. I have a feeling today will be a special day!"

[0064] Finally, the server posts this modified message to the social networking site.

[0065] Example 2:

[0066] If a user frequently posts about the weather, such as "It looks like it's going to rain today. Be careful!":

[0067] The server collects past weather-related posts and uses them to train a generative model.

[0068] Weather forecast data is also used as a reference, so that the automatically generated text will include content appropriate for the weather on that day.

[0069] The generated message is "It looks like it's going to rain today. Don't forget your umbrella!" and is presented to the user via the terminal.

[0070] The user corrects the situation by saying, "It's forecast to rain heavily today. Don't forget your umbrella when you go out!", and the server then posts the message to social media.

[0071] This system generates natural content based on past posting data, saving users time and effort while enabling high-quality daily posting.

[0072] The processing flow will be explained below.

[0073] Step 1:

[0074] The server collects past posting data from the user's SNS account. To do this, it uses the SNS's API and obtains the posting data with the user's permission. The data includes posted text, images, videos, and the timing of posting. This allows the user's past posting history to be stored in a database.

[0075] Step 2:

[0076] The server organizes the collected data into a dataset, extracts important information (post text, hashtags, tagged images and videos) and converts it into a format that can be used by the generative model. This dataset is used to train the generative model.

[0077] Step 3:

[0078] The server uses the dataset organized in the previous step to train a text generation model (e.g., GPT-3). The generative model learns the user's writing style and prepares to generate future posts in a natural manner. This training process takes different amounts of time depending on the amount and complexity of the data collected.

[0079] Step 4:

[0080] The server uses the trained generative model to automatically generate the content to be posted that day. To prepare the automatically generated content for a specific time, the server issues commands to the generative model. The text generated at this stage is appropriate based on past posts and trend information.

[0081] Step 5:

[0082] The server sends the automatically generated message to a device (such as the user's smartphone or PC). The device displays the message to the user and provides an interface for prompting confirmation and correction. The user checks the presented text and corrects the text as necessary. This correction is made before the message is finalized.

[0083] Step 6:

[0084] The user checks the automatically generated text and makes any necessary corrections. Once the corrections are complete, the user presses a button to confirm the corrected message content and finalizes it. If there are no corrections to be made, the message can be confirmed as is.

[0085] Step 7:

[0086] The server retrieves the finalized message content and posts it to the designated SNS platform using the SNS API. If the post is successful, the information is notified to the device and the user. This completes the daily regular message.

[0087] This series of processes allows users to minimize the effort required for regular daily calls and maintain high quality of the content of their calls. In addition, manual corrections can be made as needed, so calls can be made in line with the user's intentions.

[0088] Example 1

[0089] 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."

[0090] In recent years, the number of users of social networking services (SNS) has increased, creating a need for continuous management of the content posted daily. However, it takes a lot of effort for users to come up with new content to post every day, resulting in a decline in the consistency and quality of posts. Furthermore, while there are systems that learn writing style and trends from past posts and automatically generate new posts in a natural way, it is often difficult to completely eliminate the user's effort. There is a need for a method to solve these issues and enable users to post high-quality content on a continuous basis.

[0091] 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.

[0092] In this invention, the server includes a means for collecting past posting data of users, a means for training a generative model that learns the user's writing style based on the past posting data, and a means for automatically generating daily posting content using the generative model, thereby making it possible to generate natural, consistent, and high-quality posting content while reducing the user's effort.

[0093] "User" means an individual or organization that posts using a social networking service.

[0094] "Past posting data" refers to all content (text, images, videos, metadata, etc.) that a user has previously posted on a social networking service.

[0095] "Means of collection" refers to the technology and devices used to obtain and store data using the APIs of social networking services.

[0096] A "generative model" refers to a mathematical model that uses machine learning algorithms to learn from specific data and generate new data based on that data.

[0097] "Training means" refers to the techniques and methods used to train a generative model using previously posted data.

[0098] "Means for automatic generation" refers to technologies and methods for automatically generating new user posts using a trained generative model.

[0099] "Means for presentation" refers to the technology and method for displaying the generated transmission content to the user and enabling confirmation and correction.

[0100] "Means enabling modification" refers to interfaces or technologies that allow users to change or modify automatically generated content.

[0101] "Specified social networking services" refers to online platforms such as Twitter, Facebook, and Instagram where users can post content.

[0102] "Means of posting" refers to the technology or method for posting the modified content online via the API of a social networking service.

[0103] "Means for managing schedule" refers to techniques and methods for managing time so that the generated transmission content is presented to the user at a specific time.

[0104] "Trending topics" refers to themes and topics that are currently attracting the interest of many people on the Internet and social networking services.

[0105] "Means of learning and incorporating it into generated communications" refers to the technology and methods for training a generative model to learn about popular topics in society and then generating communications that include those topics.

[0106] This invention relates to a system that automatically generates daily posts by collecting data on users' past posts on social networking services (SNS), training a generative AI model that learns writing styles and trends based on that data, and presenting the generated posts to the user, who can then make any necessary edits and finally post the posts to the SNS.

[0107] System configuration

[0108] The system consists of the following main components:

[0109] 1. Server: Responsible for collecting data, training generative models, and automatically generating dissemination content.

[0110] 2. Terminal: Presents the generated transmission content to the user and provides an interface for editing.

[0111] 3. User: A user of the SNS who makes final confirmations and corrections to the content posted.

[0112] Server Processing

[0113] The server first uses the SNS API to collect data on users' past posts. This data includes text data, image data, video data, and metadata such as posting time and location information. For example, past tweets can be obtained using the Twitter API.

[0114] The collected data is preprocessed and then used to train a generative AI model (e.g., GPT-3). Preprocessing includes text cleaning, tokenization, and conversion to multidimensional vectors. The result of training is a generative model that learns the user's writing style and the phrases they use.

[0115] Using a trained generative model, the server automatically generates daily posts. By inputting a prompt into the generative model, natural-sounding sentences are generated based on past posting patterns. For example, a prompt such as "Good morning! Let's do our best today!" can be used.

[0116] Terminal handling

[0117] The generated message is presented to the user via their device. A user interface similar to the posting field of an SNS is displayed on the device, allowing the user to review and edit the generated message. Once the user has finished editing, the edited message is sent back to the server.

[0118] User Action

[0119] The user can check the message displayed on the device and make corrections as necessary. For example, the generated message "Good morning. I feel like today is going to be a great day!" can be corrected to "Good morning. I feel like today is going to be a special day!"

[0120] Final call processing

[0121] The final revised content is posted via the server using the SNS API. For example, a tweet can be sent using the Twitter API.

[0122] This system allows users to generate natural, consistent, and high-quality posts based on past writing styles and patterns, saving them time and effort. It also allows users to schedule posts to be posted at specific times, and incorporates popular topics to attract more attention.

[0123] Specific examples

[0124] Example 1:

[0125] If a user frequently posts "Good morning! Let's do our best today!" every morning, the system will work as follows:

[0126] The server collects past posting data and creates a dataset that includes other morning greeting posts from this user.

[0127] The server trains a generative model to learn the user's writing style and frequently used phrases.

[0128] Every morning at a set time, the server automatically generates a new "good morning" message using this model.

[0129] This message is sent to the device and the user modifies it to say, "Good morning. I have a feeling today will be a special day!"

[0130] Finally, the server posts this modified message to the social networking site.

[0131] Example 2:

[0132] If a user frequently posts about the weather, such as "It looks like it's going to rain today. Be careful!":

[0133] The server collects past weather-related posts and uses them to train a generative model.

[0134] Weather forecast data is also used as a reference, and the automatically generated text includes content appropriate to the weather on that day.

[0135] The generated message is "It looks like it's going to rain today. Don't forget your umbrella!" and is presented to the user via the terminal.

[0136] The user corrects the situation by saying, "It's forecast to rain heavily today. Don't forget your umbrella when you go out!", and the server then posts the message to social media.

[0137] This allows users to generate natural content based on past posting data, saving them time and effort, and enabling them to continue to post high-quality content on a daily basis.

[0138] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0139] Step 1: Collect past posting data

[0140] Input: Social networking service API key and user ID

[0141] Operation:

[0142] The server uses the SNS API to collect data on users' past posts. This data includes metadata such as text, images, videos, posting times, and location information. It first authenticates the user using the API key and user ID, and then sends the appropriate request to the SNS API.

[0143] Output: A dataset of collected historical posting data

[0144] Step 2: Training the generative model

[0145] Input: A dataset of collected historical posting data

[0146] Operation:

[0147] The server preprocesses the collected data, which includes cleaning the text, tokenizing it, and converting it into multidimensional vectors. Once preprocessing is complete, a training dataset is created. A generative AI model (e.g., GPT-3) is then trained on this dataset. During this process, the model learns the user's writing style, the phrases they use, and their posting patterns.

[0148] Output: A trained generative AI model

[0149] Step 3: Automatically generate daily content

[0150] Input: A trained generative AI model, a prompt

[0151] Operation:

[0152] The server inputs the prompt sentences into a generative AI model to automatically generate daily posting content. The prompt sentences are generated based on the user's past posting patterns. The generative AI model then generates natural-sounding sentences based on these prompt sentences.

[0153] Output: Automatically generated call content

[0154] Step 4: Present the message

[0155] Input: Auto-generated call content

[0156] Operation:

[0157] The terminal receives the transmitted content sent from the server and presents it to the user. The user can check the content displayed on the terminal and make corrections as necessary. A user interface for this purpose is provided on the terminal.

[0158] Output: The message that the user confirmed and corrected

[0159] Step 5: Edit the message

[0160] Input: User feedback and corrections

[0161] Operation:

[0162] The user checks the message displayed on the terminal and makes corrections as necessary. For example, the generated message "Good morning. I feel like today is going to be a great day!" can be corrected to "Good morning. I feel like today is going to be a special day!". The corrected message is then sent back to the server.

[0163] Output: Modified outgoing message

[0164] Step 6: Final call processing

[0165] Input: Corrected call content

[0166] Operation:

[0167] The server receives the modified content and posts it to the designated social networking service using the SNS API. During this process, the server authenticates the user using the API key again and sends the appropriate request.

[0168] Output: Posted content on a specified social networking service

[0169] These processing steps allow users to automatically generate natural, high-quality content every day based on their own past posts, and easily post it to SNS after making any necessary edits.

[0170] (Application example 1)

[0171] 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."

[0172] Today's businesses need to efficiently and effectively run advertising campaigns using social networking services (SNS). However, consistently generating daily posting content is time-consuming, and it is difficult to reflect past posting patterns and trends. Managing posting at the right time is also a challenge. There is a need for a system that can solve these issues and enable businesses to effectively utilize SNS.

[0173] 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.

[0174] In this invention, the server includes means for collecting past posting data of users, means for training a generative model that learns the user's writing style based on the past posting data, means for automatically generating daily posting content using the generative model, means for automatically generating the automatically generated posting content as advertisements for products and services, and means for posting the corrected posting content to a predetermined communication network. This enables the automatic generation of high-quality advertising content based on past data and the implementation of efficient SNS campaigns.

[0175] "Past posting data" refers to a record of all information, such as text, images, and videos, that a user has previously made public on social networking services, etc.

[0176] A "generative model" is an artificial intelligence model that can learn from collected data and make predictions and generate results.

[0177] "Training" is the process of using data to adjust the parameters of a generative model to improve the model's performance.

[0178] "Auto-generation" refers to the use of pre-trained generative models to generate new content without human intervention.

[0179] "Communication network" is a general term for communication infrastructure for sending and receiving data, including the Internet.

[0180] "Advertising" is the act of disseminating information with the aim of promoting product sales or raising awareness of services.

[0181] System configuration

[0182] A system for implementing this invention comprises the following main components: a server, a terminal, and a user.

[0183] 1. Server

[0184] The server is responsible for collecting data, training generative models, and automatically generating content. Specifically, it uses the following hardware and software:

[0185] Hardware: High-performance processors, memory, and storage devices

[0186] Software: Social media API (Twitter API, Instagram Graph API), database (MySQL or MongoDB), generative model (OpenAI GPT-4)

[0187] The server first uses the SNS API to collect the user's past posting data (text, images, videos, etc.). The collected data is stored in a database. Next, a generative model (e.g., GPT-4) is trained using the past posting data. This allows the server to learn the user's writing style and frequently used phrases.

[0188] 2. Terminal

[0189] The terminal is used to present the generated transmission content to the user and to provide an interface for making corrections.

[0190] Hardware: Smartphones, tablets, PCs

[0191] Software: Front-end application (React Native)

[0192] The automatically generated message is presented to the user through the terminal and can be edited. The intuitive user interface allows the user to easily check, edit, and finally confirm the generated message.

[0193] 3. Users

[0194] The user plays a key role in making final confirmations and corrections.

[0195] System operation example

[0196] 1. Data collection: The server uses the SNS API to collect data on past company posts.

[0197] 2. Training the generative model: Train a generative model (OpenAI GPT-4) based on the collected data.

[0198] 3. Auto-generation: Use the trained model to generate new ad posts.

[0199] 4. Confirm and edit: The automatically generated post is presented to the user via their device, and the user can edit it as necessary.

[0200] 5. Posting: The server posts the final content to the SNS via the communication network.

[0201] Specific examples

[0202] For example, if a clothing brand is announcing a new product:

[0203] The server collects past posting data and uses it to train a generative model. Let's say a new product announcement is automatically generated, with the following content: "Look stylish this fall with our brand's new collection." The user then reviews it and modifies it to read, "Look stylish this fall with our new collection. Check the link for details!"

[0204] The server posts the finalized content to the social networking site.

[0205] Prompt Sentence Examples

[0206] "Generate social media posts to promote new products based on past posting data. Use keywords like 'autumn,' 'collection,' and 'brand.' The content should convey the charm of autumn."

[0207] In this way, the system of the present invention can efficiently generate high-quality and consistent SNS posts for advertising campaigns and support corporate marketing activities.

[0208] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0209] Step 1:

[0210] The server uses the SNS API to collect data on users' past posts. This data includes text, images, videos, etc. and is stored in a database. The input is data obtained from the SNS API, and the output is organized post data that is stored in the database.

[0211] Step 2:

[0212] The server trains a generative model (such as OpenAI GPT-4) based on the collected data. During this training process, it learns the writing style and phrases used in past posts. The input is the collected data, and the output is the trained generative model.

[0213] Step 3:

[0214] The server uses the trained generative model to automatically generate new posts, which are ad copy that reflect past posting patterns and trends. The input is the trained generative model, and the output is the automatically generated post.

[0215] Step 4:

[0216] The server sends the automatically generated message content to the terminal. The terminal presents this content to the user so that the user can confirm it. The input is the automatically generated message content, and the output is the content displayed on the terminal.

[0217] Step 5:

[0218] The user checks the presented message content and makes corrections as necessary. The corrected message content is sent back to the server via the terminal. The input is the content corrected by the user, and the corrected message content is sent to the server as output.

[0219] Step 6:

[0220] The server posts the revised content via the SNS API, which makes the final content available to the SNS. The input is the revised content, and the output is the content posted to the SNS.

[0221] 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.

[0222] This invention relates to a system that automatically generates daily posts by collecting data on users' past posts on social networking services (SNS), training a generative model that learns writing styles and tendencies based on that data, and combining it with an emotion engine that recognizes the user's emotions. This system includes a process in which the generated posts are presented to the user, who can then make any necessary edits and finally post the posts to the SNS.

[0223] System configuration

[0224] The system consists of the following main components:

[0225] 1. Server: Responsible for collecting data, training the generative model and emotion engine, and automatically generating dissemination content.

[0226] 2. Terminal: Presents the generated transmission content to the user and provides an interface for editing.

[0227] 3. User: A user of the SNS who makes final confirmations and corrections to the content posted.

[0228] 4. Emotion engine: Analyzes emotions from users' past posting data and real-time input data, and reflects them in the output of the generative model.

[0229] System Operation

[0230] 1. Collection of past posting data

[0231] The server uses the SNS API to collect users' past posting data, including the content of posts, images, videos, and posting timing, and stores the data in a database.

[0232] 2. Training the generative model and emotion engine

[0233] The server uses the collected past posting data to train a generative model (e.g., GPT-3) and an emotion engine. The generative model learns writing style, and the emotion engine is used to analyze user emotions from past posting data.

[0234] 3. Automatic generation of daily posting content

[0235] The server uses the trained generative model and emotion engine to automatically generate the message for the day, and the tone and style of the message are generated based on the output of the emotion engine, depending on the user's emotional state.

[0236] 4. Modifications based on sentiment analysis

[0237] The automatically generated message is based on the user's emotional state and is presented to the user via the terminal. The user can review the presented text and modify it as necessary.

[0238] 5. Final call processing

[0239] Once the corrections are complete, the server posts the finalized message content via the SNS API. If the post is successful, the information is notified to the device and the user.

[0240] Specific examples

[0241] Example 1:

[0242] Suppose a user frequently posts "Good morning! Let's do our best today!". In this case, the system behaves as follows:

[0243] The server collects past posting data and uses this data to train the generative model and emotion engine.

[0244] Every morning, the server uses the generative model and emotion engine to automatically generate a new "good morning" message. For example, if the user was tired the night before, the emotion engine can suggest something like, "Take it easy today."

[0245] This message is sent to the device, and the user can modify it to say, "Maybe today is a good day to take it easy."

[0246] Finally, the server posts this modified message to the social networking site.

[0247] Example 2:

[0248] If a user frequently posts about the weather, such as "It looks like it's going to rain today. Be careful!":

[0249] The server collects past weather-related post data and uses it to train the generative model and emotion engine.

[0250] The emotion engine analyzes how users feel on rainy days, so if a user is typically inactive on rainy days, the generated messages will have a more subdued tone to match that emotion.

[0251] The generated message will be "It looks like it's going to rain today. Take it easy," and will be presented to the user via the device.

[0252] The user modifies the message to "Let's relax at home on a rainy day!", and the server then posts the message to social media.

[0253] This system generates natural-sounding messages based on the user's past posting data and emotions, saving the user time and effort while enabling high-quality daily messages. Furthermore, manual corrections can be made as needed, so messages can be sent in line with the user's intentions.

[0254] The processing flow will be explained below.

[0255] Step 1:

[0256] The server collects past posting data from users' SNS accounts. To do this, it uses the SNS's API and obtains the posting data with the user's permission. The data includes posted text, images, videos, and the timing of posting. This data is then stored in a database.

[0257] Step 2:

[0258] The server organizes the collected data into a dataset, extracts important information (post text, hashtags, tagged image and video information), and converts it into a format that can be used by the generative model and emotion engine. This dataset is used to train the generative model and emotion engine.

[0259] Step 3:

[0260] The server uses the organized dataset to train a text generation model (e.g., GPT-3). The generation model learns the user's writing style and the phrases they use, and prepares to generate future posts in a natural way.

[0261] Step 4:

[0262] The server also trains the emotion engine, which analyzes emotions from users' past posting data and reflects the results in the output of the generative model. This generates content that reflects the user's emotional state.

[0263] Step 5:

[0264] The server uses the trained generative model and emotion engine to automatically generate the message for the day, with the tone and style corresponding to the user's emotional state based on the output of the emotion engine.

[0265] Step 6:

[0266] The server sends the generated message to the terminal. The terminal displays the generated text to the user and provides an interface for confirmation and correction. The user can check the generated text and make corrections as necessary.

[0267] Step 7:

[0268] The user checks the automatically generated text and makes corrections as necessary. After completing the corrections, the user presses a button to confirm the corrected message content for final confirmation. If there are no corrections to be made, the user can confirm the message directly.

[0269] Step 8:

[0270] The server retrieves the finalized message content and posts it to the designated SNS platform using the SNS API. If the post is completed successfully, the information is notified to the device and the user. This completes the daily regular message.

[0271] The above processing steps allow users to minimize the effort required for regular daily calls and maintain high quality of the content of their calls. In addition, manual corrections can be made as needed, allowing calls to be made in line with the user's intentions.

[0272] Example 2

[0273] 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."

[0274] In modern social networking services (SNS), users spend a great deal of time and effort maintaining their daily posts. In particular, it is difficult for users to post high-quality content that reflects their personal style and emotions. This has led to problems such as a decline in user engagement and a decrease in the efficiency of SNS use.

[0275] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting past posting data, means for training a generative model and an emotion engine based on the past posting data, means for automatically generating daily posts using the generative model and emotion engine, means for presenting the generated posts to a user and allowing the user to modify them, and means for posting the modified posts to a predetermined social networking service. This enables the automatic generation and modification of high-quality posts based on the user's past posting style and emotions, thereby reducing user effort and improving engagement.

[0276] "Past posting data" refers to information such as all previous postings, images, videos, and posting timing made by a user on a social networking service.

[0277] A "generative model" refers to an AI model that learns writing style and idiom based on past posting data and automatically generates text.

[0278] An "emotion engine" refers to an algorithm that analyzes emotions from users' past posting data and reflects that information in a generative model.

[0279] "Means for automatic generation" refers to the function of automatically creating daily content using a trained generative model and emotion engine.

[0280] The "presentation means" refers to an interface that displays the generated transmission content to the user and allows the user to modify it.

[0281] "Modified Submission" means the final version that reflects any changes or edits made by the user to the presented auto-generated content.

[0282] "Social Networking Service" means an online platform that enables users to create profiles, share messages, photos, videos, etc., and communicate with other users.

[0283] The "schedule management means" refers to a function for making the generated transmission content be presented to the user at a specific time.

[0284] "Hot topics" refer to topics or themes that are currently attracting the interest of many people in society or communities and are being discussed.

[0285] This system collects data on users' past posts on social networking services (SNS), and uses that data to train a generative model and emotion engine to automatically generate daily posts, present them to users, and allow them to modify them. It also includes a process for posting the final modified posts to the SNS.

[0286] First, the server collects data on users' past posts through the social networking service's API. This data includes the post content, images, videos, and timing of posts. For example, the server calls the "GET / posts" endpoint to retrieve post data from the past year. This data is stored in a database using the SQL query "INSERT INTO posts (user_id, content, image_url, video_url, timestamp) VALUES ...".

[0287] Next, the server trains a generative AI model (e.g., GPT-3) and sentiment engine based on the post data stored in the database. For training, the "train.py" script is used, inputting the past 5,000 posts. The generative model learns writing style, and the sentiment engine extracts sentiment from the post data.

[0288] The server then uses the trained generative model and emotion engine to automatically generate the message content for that day. Based on the results output by the emotion engine, a prompt sentence is input into the generative model, and text is generated. Specifically, the "generate.py" script is executed to input a prompt sentence based on the output of the emotion engine into the generative AI model.

[0289] The generated message content is presented to the user via the device. The device calls the API endpoint " / getGeneratedContent" to obtain the generated text and displays it to the user. The user checks the displayed text and makes any necessary corrections. These corrections are sent from the device to the server. For example, if the user corrects it to "Maybe today is a good day to take it easy" and clicks the "submitChanges" button, the corrections are sent to the server.

[0290] Finally, the server checks the revised content and posts it to the specified SNS. The server calls "POST / finalPost" to post the revised text to the SNS. The "POST / notification" endpoint is then used to notify the user and device that the post has been completed.

[0291] Examples of concrete examples and prompts

[0292] Example 1:

[0293] If a user frequently posts "Good morning. Let's do our best today!", the server collects past posting data and trains a generative model and emotion engine. Every morning, the server uses the generative model and emotion engine to generate a new "Good morning" message. For example, if the user is tired the night before, the emotion engine will suggest "Let's take it easy today." In response, the user can modify the message by saying "Maybe today is a good day to take it easy," and the server will finally post the revised message to the SNS.

[0294] Example prompt sentence:

[0295] "Generate this morning's post based on past posting data. If the user was tired the night before, make the post reflect that emotion."

[0296] Example 2:

[0297] If a user frequently posts about the weather, such as "It looks like it's going to rain today. Be careful!", the server collects past weather-related posting data and uses it to train a generative model and emotion engine. The emotion engine analyzes the user's emotions on rainy days and generates messages with a more subdued tone. The generated message is "It looks like it's going to rain today. Take it easy," and is presented to the user via their device. The user then modifies it to "Take it easy at home on a rainy day!", after which the server posts it to the SNS.

[0298] Example prompt sentence:

[0299] "Generate a post about today's weather. Please keep the tone muted and based on rainy day emotions."

[0300] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0301] System program processing flow

[0302] Step 1: Collect past posting data

[0303] The server collects the user's past posting data through the SNS API. The input is the user's authentication information and the SNS API endpoint, and the output is the retrieved posting data. For example, calling the "GET / posts" endpoint retrieves the user's posting data from the past year. This data includes the post content, images, videos, and posting date and time.

[0304] Step 2: Saving to the database

[0305] The server saves the collected post data in a database. The input is the acquired post data, and the output is the completion of registration in the database. Specifically, it executes the SQL query "INSERT INTO posts (user_id, content, image_url, video_url, timestamp) VALUES ..." to save the data.

[0306] Step 3: Training the generative model and emotion engine

[0307] The server trains a generative AI model (e.g., GPT-3) and emotion engine based on the posted data stored in the database. The input is past posted data, and the output is the trained generative model and emotion engine. Specifically, the "train.py" script is run to train using the past 5,000 posted data.

[0308] Step 4: Automatic generation of daily postings

[0309] The server uses the trained generative model and emotion engine to automatically generate the message content for the day. The input is the output data of the emotion engine, and the output is the generated message content. Specifically, the "generate.py" script is executed, and a prompt sentence based on the output of the emotion engine is input to the generative AI model to generate text.

[0310] Step 5: Present the message

[0311] The terminal presents the generated call content to the user. The input is the generated call content, and the output is the text to be displayed to the user. Specifically, the terminal calls the API endpoint " / getGeneratedContent" to obtain the generated text and display it to the user.

[0312] Step 6: Edit the message

[0313] The user checks the presented message and makes corrections if necessary. The input is the generated message, and the output is the text corrected by the user. The user makes corrections on the screen and clicks the "submitChanges" button, and the corrections are sent to the server.

[0314] Step 7: Final call processing

[0315] The server performs a final check of the message content amended by the user and posts it to the SNS. The input is the text amended by the user, and the output is a notification that the post has been completed to the SNS. Specifically, it calls "POST / finalPost" to post the amended text to the SNS. It then uses the "POST / notification" endpoint to send a notification that the post has been completed to the user and their device.

[0316] (Application example 2)

[0317] 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."

[0318] Currently, it is difficult for users to think of what to post on social networking services (SNS) every day. It is also time-consuming to generate personalized content based on each user's interests and emotions and share it on other platforms. Furthermore, manual editing is required to improve the quality of the generated content, which often leaves users feeling overwhelmed. The present invention aims to solve these problems and provide users with an easy and natural sharing experience.

[0319] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting past posting data of users, means for training a generative model that learns the user's writing style based on the past posting data, and means for automatically generating daily posting content using the generative model. This enables means for generating personalized content based on the user's interests, means for sharing the generated content on other platforms, means for presenting the automatically generated posting content to the user and allowing the user to make corrections, and means for posting the corrected posting content to a predetermined social networking service.

[0320] "User's past posting data" refers to information such as text, images, videos, and the timing of posts made by the user in the past on social networking services.

[0321] A "generative model that learns writing style" is a model that can learn a user's unique writing style from their past posting data and generate new text based on this.

[0322] "Daily posts" refer to the text and content that users post on social networking services on a daily basis.

[0323] "Automatic generation means" refers to a method or device that uses a specific algorithm or program to generate text or content without human intervention.

[0324] "Means for user presentation and modification" refers to a method or interface that allows users to view system-generated content and change it as needed.

[0325] "Means for posting to designated social networking services" refers to a method or mechanism for automatically posting modified content to designated social networking platforms according to schedules or conditions.

[0326] "Means for generating personalized content" refers to algorithms or systems that generate individualized content based on the user's interests and concerns.

[0327] "Means of sharing to other platforms" refers to the methods and mechanisms for posting and distributing the generated content to websites, applications, etc. other than social networking services.

[0328] This invention is a system that automatically generates personalized posts for users by collecting data on past posts on social networking services (SNS), training a generative model based on that data, and combining it with a sentiment analysis engine. This system includes a process that presents the generated posts to the user, and then the user makes any edits before finally posting.

[0329] Components

[0330] The system consists of the following main components:

[0331] 1. Server: Responsible for collecting data, training generative models and emotion engines, automatically generating messages, and generating personalized content.

[0332] 2. Terminal: Presents the generated transmission content to the user and provides a user interface for editing.

[0333] 3. User: A user of the SNS who makes final confirmations and corrections to the content posted.

[0334] Hardware and Software

[0335] The server uses the following technology stack:

[0336] Data collection: Use Python (requests, BeautifulSoup, Tweepy, etc.) to retrieve data using SNS APIs.

[0337] Generative model: We use OpenAI GPT-3 via API to train the generative model.

[0338] Sentiment analysis: Sentiment analysis is performed using Microsoft Azure Cognitive Services.

[0339] Backend: Django is used, and the database is PostgreSQL.

[0340] Front-end: Use React Native to build the user interface.

[0341] Processing flow

[0342] 1. Collection of past posting data

[0343] The server collects users' past posting data through the SNS's API. This data includes the text, images, videos, and timing of posts. The collected data is stored in a database.

[0344] 2. Training the generative model and emotion engine

[0345] The server trains a generative model using OpenAI GPT-3 based on collected past posting data, and also uses Microsoft Azure Cognitive Services to train an emotion engine capable of analyzing users' emotional states.

[0346] 3. Daily posting and personalized content generation

[0347] The server uses a trained generative model and emotion engine to automatically generate personalized content based on the user's interests every day, resulting in natural, useful content tailored to the user.

[0348] 4. User Presentation and Modification

[0349] The generated message is presented to the user via the terminal, who can check the text and make corrections as necessary.

[0350] 5. Final Content Delivery

[0351] The revised content is automatically posted to the specified social networking service and other platforms via the server.

[0352] Specific examples

[0353] If a user frequently posts about the weather, such as "It looks like it's going to rain today. Be careful!", the system will act as follows:

[0354] The server collects past weather-related posting data and uses it to train the generative model and emotion engine.

[0355] The emotion engine analyzes how users feel on rainy days and reflects this in the messages they generate.

[0356] The generated message will be "It looks like it's going to rain today. Take it easy," and will be displayed to the user via their device.

[0357] The user modifies the message to "Let's stay home and relax on a rainy day!", after which the server posts it to social media and other platforms.

[0358] Example prompts for generative AI models

[0359] "Based on your posting history, today we will post the following:

[0360] Morning greeting: "Good morning. Today I have some special news for you."

[0361] About the weather: "The weather is sunny today. Let's enjoy a nice day."

[0362] Sentiment analysis correction:

[0363] "You seem to be tired lately. Let's not push ourselves too hard."

[0364] In this way, personalized, high-quality messages can be sent while reducing the burden on users.

[0365] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0366] Step 1:

[0367] The server uses the SNS API to collect data on users' past posts. The collected data includes the content of the post, images, videos, and the timing of the post. This collected data is stored in a database. The input is the post data obtained from the API, and the output is the formatted data stored in the database.

[0368] Step 2:

[0369] The server uses the previously posted data stored in the database to train a generative model (e.g., OpenAI GPT-3). Specifically, it trains the model to learn the user's writing style from this data. The input is the previously posted data, and the output is the trained generative model.

[0370] Step 3:

[0371] The server uses Microsoft Azure Cognitive Services to train the emotion engine. This emotion engine analyzes emotions in past posting data and learns what emotions appear in what situations. The input is the past posting data, and the output is the trained emotion engine.

[0372] Step 4:

[0373] The server automatically generates daily posts using a trained generative model and emotion engine, taking into account the user's past activities and current emotional state to generate content appropriate for the user. The input is the trained model and emotion engine, and the output is the automatically generated posts.

[0374] Step 5:

[0375] The automatically generated message content is presented to the user via the terminal. The user checks the presented content and makes corrections as necessary. The input is the generated message content, and the output is the message content corrected by the user.

[0376] Step 6:

[0377] The modified message is posted to a specified social networking service via the server. The server posts the generated message to the specified SNS platform. The input is the message modified by the user, and the output is the message posted to the SNS.

[0378] Step 7:

[0379] When personalized content generation is required, the server generates content based on the user's interests. This can be specialized for news articles or content related to a particular topic. The input is the user's past interest data, and the output is personalized content.

[0380] Step 8:

[0381] The generated personalized content is presented to the user through their device and shared to other platforms. The user can review it, modify it as necessary, and then share it across multiple platforms. The input is the personalized content, and the output is the content shared to other platforms.

[0382] 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.

[0383] 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.

[0384] 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.

[0385] [Second embodiment]

[0386] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0387] 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.

[0388] 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).

[0389] 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.

[0390] 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.

[0391] 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).

[0392] 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.

[0393] 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.

[0394] 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.

[0395] 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.

[0396] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0397] 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."

[0398] This invention relates to a system that automatically generates daily posts by collecting data on users' past posts on social networking services (SNS), training a generative model that learns writing styles and trends based on that data, and presenting the generated posts to the user, who can then make any necessary edits and finally post the posts to the SNS.

[0399] System configuration

[0400] The system consists of the following main components:

[0401] 1. Server: Responsible for collecting data, training generative models, and automatically generating dissemination content.

[0402] 2. Terminal: Presents the generated transmission content to the user and provides an interface for editing.

[0403] 3. User: A user of the SNS who makes final confirmations and corrections to the content posted.

[0404] System Operation

[0405] 1. Collection of past posting data

[0406] The server uses the SNS API to collect users' past posting data, including the content of posts, images, videos, and metadata.

[0407] 2. Training the generative model

[0408] The server uses the collected data to train a generative model (e.g., GPT-3), which learns the user's writing style and the phrases they use.

[0409] 3. Automatic generation of daily posting content

[0410] The server uses a trained generative model to automatically generate daily posts, which contain natural-sounding sentences based on past posting data.

[0411] 4. Check and correct the content of the message

[0412] The automatically generated message is presented to the user via the terminal, who can then check it and make any necessary corrections.

[0413] 5. Final call processing

[0414] Once the corrections are complete, the server posts the final message via the SNS API.

[0415] Specific examples

[0416] Example 1:

[0417] Let's say a user frequently posts "Good morning! Let's do our best today!" every morning. In this case, the system works as follows:

[0418] The server collects past posting data and creates a dataset that includes other morning greeting posts from this user.

[0419] The server trains a generative model to learn the user's writing style and frequently used phrases.

[0420] Every morning at a set time, the server automatically generates a new "good morning" message using this model.

[0421] This message is sent to the device and the user modifies it to say, "Good morning. I have a feeling today will be a special day!"

[0422] Finally, the server posts this modified message to the social networking site.

[0423] Example 2:

[0424] If a user frequently posts about the weather, such as "It looks like it's going to rain today. Be careful!":

[0425] The server collects past weather-related posts and uses them to train a generative model.

[0426] Weather forecast data is also used as a reference, so that the automatically generated text will include content appropriate for the weather on that day.

[0427] The generated message is "It looks like it's going to rain today. Don't forget your umbrella!" and is presented to the user via the terminal.

[0428] The user corrects the situation by saying, "It's forecast to rain heavily today. Don't forget your umbrella when you go out!", and the server then posts the message to social media.

[0429] This system generates natural content based on past posting data, saving users time and effort while enabling high-quality daily posting.

[0430] The processing flow will be explained below.

[0431] Step 1:

[0432] The server collects past posting data from the user's SNS account. To do this, it uses the SNS's API and obtains the posting data with the user's permission. The data includes posted text, images, videos, and the timing of posting. This allows the user's past posting history to be stored in a database.

[0433] Step 2:

[0434] The server organizes the collected data into a dataset, extracts important information (post text, hashtags, tagged images and videos) and converts it into a format that can be used by the generative model. This dataset is used to train the generative model.

[0435] Step 3:

[0436] The server uses the dataset organized in the previous step to train a text generation model (e.g., GPT-3). The generative model learns the user's writing style and prepares to generate future posts in a natural manner. This training process takes different amounts of time depending on the amount and complexity of the data collected.

[0437] Step 4:

[0438] The server uses the trained generative model to automatically generate the content to be posted that day. To prepare the automatically generated content for a specific time, the server issues commands to the generative model. The text generated at this stage is appropriate based on past posts and trend information.

[0439] Step 5:

[0440] The server sends the automatically generated message to a device (such as the user's smartphone or PC). The device displays the message to the user and provides an interface for prompting confirmation and correction. The user checks the presented text and corrects the text as necessary. This correction is made before the message is finalized.

[0441] Step 6:

[0442] The user checks the automatically generated text and makes any necessary corrections. Once the corrections are complete, the user presses a button to confirm the corrected message content and finalizes it. If there are no corrections to be made, the message can be confirmed as is.

[0443] Step 7:

[0444] The server retrieves the finalized message content and posts it to the designated SNS platform using the SNS API. If the post is successful, the information is notified to the device and the user. This completes the daily regular message.

[0445] This series of processes allows users to minimize the effort required for regular daily calls and maintain high quality of the content of their calls. In addition, manual corrections can be made as needed, so calls can be made in line with the user's intentions.

[0446] Example 1

[0447] 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."

[0448] In recent years, the number of users of social networking services (SNS) has increased, creating a need for continuous management of the content posted daily. However, it takes a lot of effort for users to come up with new content to post every day, resulting in a decline in the consistency and quality of posts. Furthermore, while there are systems that learn writing style and trends from past posts and automatically generate new posts in a natural way, it is often difficult to completely eliminate the user's effort. There is a need for a method to solve these issues and enable users to post high-quality content on a continuous basis.

[0449] 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.

[0450] In this invention, the server includes a means for collecting past posting data of users, a means for training a generative model that learns the user's writing style based on the past posting data, and a means for automatically generating daily posting content using the generative model, thereby making it possible to generate natural, consistent, and high-quality posting content while reducing the user's effort.

[0451] "User" means an individual or organization that posts using a social networking service.

[0452] "Past posting data" refers to all content (text, images, videos, metadata, etc.) that a user has previously posted on a social networking service.

[0453] "Means of collection" refers to the technology and devices used to obtain and store data using the APIs of social networking services.

[0454] A "generative model" refers to a mathematical model that uses machine learning algorithms to learn from specific data and generate new data based on that data.

[0455] "Training means" refers to the techniques and methods used to train a generative model using previously posted data.

[0456] "Means for automatic generation" refers to technologies and methods for automatically generating new user posts using a trained generative model.

[0457] "Means for presentation" refers to the technology and method for displaying the generated transmission content to the user and enabling confirmation and correction.

[0458] "Means enabling modification" refers to interfaces or technologies that allow users to change or modify automatically generated content.

[0459] "Specified social networking services" refers to online platforms such as Twitter, Facebook, and Instagram where users can post content.

[0460] "Means of posting" refers to the technology or method for posting the modified content online via the API of a social networking service.

[0461] "Means for managing schedule" refers to techniques and methods for managing time so that the generated transmission content is presented to the user at a specific time.

[0462] "Trending topics" refers to themes and topics that are currently attracting the interest of many people on the Internet and social networking services.

[0463] "Means of learning and incorporating it into generated communications" refers to the technology and methods for training a generative model to learn about popular topics in society and then generating communications that include those topics.

[0464] This invention relates to a system that automatically generates daily posts by collecting data on users' past posts on social networking services (SNS), training a generative AI model that learns writing styles and trends based on that data, and presenting the generated posts to the user, who can then make any necessary edits and finally post the posts to the SNS.

[0465] System configuration

[0466] The system consists of the following main components:

[0467] 1. Server: Responsible for collecting data, training generative models, and automatically generating dissemination content.

[0468] 2. Terminal: Presents the generated transmission content to the user and provides an interface for editing.

[0469] 3. User: A user of the SNS who makes final confirmations and corrections to the content posted.

[0470] Server Processing

[0471] The server first uses the SNS API to collect data on users' past posts. This data includes text data, image data, video data, and metadata such as posting time and location information. For example, past tweets can be obtained using the Twitter API.

[0472] The collected data is preprocessed and then used to train a generative AI model (e.g., GPT-3). Preprocessing includes text cleaning, tokenization, and conversion to multidimensional vectors. The result of training is a generative model that learns the user's writing style and the phrases they use.

[0473] Using a trained generative model, the server automatically generates daily posts. By inputting a prompt into the generative model, natural-sounding sentences are generated based on past posting patterns. For example, a prompt such as "Good morning! Let's do our best today!" can be used.

[0474] Terminal handling

[0475] The generated message is presented to the user via their device. A user interface similar to the posting field of an SNS is displayed on the device, allowing the user to review and edit the generated message. Once the user has finished editing, the edited message is sent back to the server.

[0476] User Action

[0477] The user can check the message displayed on the device and make corrections as necessary. For example, the generated message "Good morning. I feel like today is going to be a great day!" can be corrected to "Good morning. I feel like today is going to be a special day!"

[0478] Final call processing

[0479] The final revised content is posted via the server using the SNS API. For example, a tweet can be sent using the Twitter API.

[0480] This system allows users to generate natural, consistent, and high-quality posts based on past writing styles and patterns, saving them time and effort. It also allows users to schedule posts to be posted at specific times, and incorporates popular topics to attract more attention.

[0481] Specific examples

[0482] Example 1:

[0483] If a user frequently posts "Good morning! Let's do our best today!" every morning, the system will work as follows:

[0484] The server collects past posting data and creates a dataset that includes other morning greeting posts from this user.

[0485] The server trains a generative model to learn the user's writing style and frequently used phrases.

[0486] Every morning at a set time, the server automatically generates a new "good morning" message using this model.

[0487] This message is sent to the device and the user modifies it to say, "Good morning. I have a feeling today will be a special day!"

[0488] Finally, the server posts this modified message to the social networking site.

[0489] Example 2:

[0490] If a user frequently posts about the weather, such as "It looks like it's going to rain today. Be careful!":

[0491] The server collects past weather-related posts and uses them to train a generative model.

[0492] Weather forecast data is also used as a reference, and the automatically generated text includes content appropriate to the weather on that day.

[0493] The generated message is "It looks like it's going to rain today. Don't forget your umbrella!" and is presented to the user via the terminal.

[0494] The user corrects the situation by saying, "It's forecast to rain heavily today. Don't forget your umbrella when you go out!", and the server then posts the message to social media.

[0495] This allows users to generate natural content based on past posting data, saving them time and effort, and enabling them to continue to post high-quality content on a daily basis.

[0496] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0497] Step 1: Collect past posting data

[0498] Input: Social networking service API key and user ID

[0499] Operation:

[0500] The server uses the SNS API to collect data on users' past posts. This data includes metadata such as text, images, videos, posting times, and location information. It first authenticates the user using the API key and user ID, and then sends the appropriate request to the SNS API.

[0501] Output: A dataset of collected historical posting data

[0502] Step 2: Training the generative model

[0503] Input: A dataset of collected historical posting data

[0504] Operation:

[0505] The server preprocesses the collected data, which includes cleaning the text, tokenizing it, and converting it into multidimensional vectors. Once preprocessing is complete, a training dataset is created. A generative AI model (e.g., GPT-3) is then trained on this dataset. During this process, the model learns the user's writing style, the phrases they use, and their posting patterns.

[0506] Output: A trained generative AI model

[0507] Step 3: Automatically generate daily content

[0508] Input: A trained generative AI model, a prompt

[0509] Operation:

[0510] The server inputs the prompt sentences into a generative AI model to automatically generate daily posting content. The prompt sentences are generated based on the user's past posting patterns. The generative AI model then generates natural-sounding sentences based on these prompt sentences.

[0511] Output: Automatically generated call content

[0512] Step 4: Present the message

[0513] Input: Auto-generated call content

[0514] Operation:

[0515] The terminal receives the transmitted content sent from the server and presents it to the user. The user can check the content displayed on the terminal and make corrections as necessary. A user interface for this purpose is provided on the terminal.

[0516] Output: The message that the user confirmed and corrected

[0517] Step 5: Edit the message

[0518] Input: User feedback and corrections

[0519] Operation:

[0520] The user checks the message displayed on the terminal and makes corrections as necessary. For example, the generated message "Good morning. I feel like today is going to be a great day!" can be corrected to "Good morning. I feel like today is going to be a special day!". The corrected message is then sent back to the server.

[0521] Output: Modified outgoing message

[0522] Step 6: Final call processing

[0523] Input: Corrected call content

[0524] Operation:

[0525] The server receives the modified content and posts it to the designated social networking service using the SNS API. During this process, the server authenticates the user using the API key again and sends the appropriate request.

[0526] Output: Posted content on a specified social networking service

[0527] These processing steps allow users to automatically generate natural, high-quality content every day based on their own past posts, and easily post it to SNS after making any necessary edits.

[0528] (Application example 1)

[0529] 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."

[0530] Today's businesses need to efficiently and effectively run advertising campaigns using social networking services (SNS). However, consistently generating daily posting content is time-consuming, and it is difficult to reflect past posting patterns and trends. Managing posting at the right time is also a challenge. There is a need for a system that can solve these issues and enable businesses to effectively utilize SNS.

[0531] 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.

[0532] In this invention, the server includes means for collecting past posting data of users, means for training a generative model that learns the user's writing style based on the past posting data, means for automatically generating daily posting content using the generative model, means for automatically generating the automatically generated posting content as advertisements for products and services, and means for posting the corrected posting content to a predetermined communication network. This enables the automatic generation of high-quality advertising content based on past data and the implementation of efficient SNS campaigns.

[0533] "Past posting data" refers to a record of all information, such as text, images, and videos, that a user has previously made public on social networking services, etc.

[0534] A "generative model" is an artificial intelligence model that can learn from collected data and make predictions and generate results.

[0535] "Training" is the process of using data to adjust the parameters of a generative model to improve the model's performance.

[0536] "Auto-generation" refers to the use of pre-trained generative models to generate new content without human intervention.

[0537] "Communication network" is a general term for communication infrastructure for sending and receiving data, including the Internet.

[0538] "Advertising" is the act of disseminating information with the aim of promoting product sales or raising awareness of services.

[0539] System configuration

[0540] A system for implementing this invention comprises the following main components: a server, a terminal, and a user.

[0541] 1. Server

[0542] The server is responsible for collecting data, training generative models, and automatically generating content. Specifically, it uses the following hardware and software:

[0543] Hardware: High-performance processors, memory, and storage devices

[0544] Software: Social media API (Twitter API, Instagram Graph API), database (MySQL or MongoDB), generative model (OpenAI GPT-4)

[0545] The server first uses the SNS API to collect the user's past posting data (text, images, videos, etc.). The collected data is stored in a database. Next, a generative model (e.g., GPT-4) is trained using the past posting data. This allows the server to learn the user's writing style and frequently used phrases.

[0546] 2. Terminal

[0547] The terminal is used to present the generated transmission content to the user and to provide an interface for making corrections.

[0548] Hardware: Smartphones, tablets, PCs

[0549] Software: Front-end application (React Native)

[0550] The automatically generated message is presented to the user through the terminal and can be edited. The intuitive user interface allows the user to easily check, edit, and finally confirm the generated message.

[0551] 3. Users

[0552] The user plays a key role in making final confirmations and corrections.

[0553] System operation example

[0554] 1. Data collection: The server uses the SNS API to collect data on past company posts.

[0555] 2. Training the generative model: Train a generative model (OpenAI GPT-4) based on the collected data.

[0556] 3. Auto-generation: Use the trained model to generate new ad posts.

[0557] 4. Confirm and edit: The automatically generated post is presented to the user via their device, and the user can edit it as necessary.

[0558] 5. Posting: The server posts the final content to the SNS via the communication network.

[0559] Specific examples

[0560] For example, if a clothing brand is announcing a new product:

[0561] The server collects past posting data and uses it to train a generative model. Let's say a new product announcement is automatically generated, with the following content: "Look stylish this fall with our brand's new collection." The user then reviews it and modifies it to read, "Look stylish this fall with our new collection. Check the link for details!"

[0562] The server posts the finalized content to the social networking site.

[0563] Prompt Sentence Examples

[0564] "Generate social media posts to promote new products based on past posting data. Use keywords like 'autumn,' 'collection,' and 'brand.' The content should convey the charm of autumn."

[0565] In this way, the system of the present invention can efficiently generate high-quality and consistent SNS posts for advertising campaigns and support corporate marketing activities.

[0566] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0567] Step 1:

[0568] The server uses the SNS API to collect data on users' past posts. This data includes text, images, videos, etc. and is stored in a database. The input is data obtained from the SNS API, and the output is organized post data that is stored in the database.

[0569] Step 2:

[0570] The server trains a generative model (such as OpenAI GPT-4) based on the collected data. During this training process, it learns the writing style and phrases used in past posts. The input is the collected data, and the output is the trained generative model.

[0571] Step 3:

[0572] The server uses the trained generative model to automatically generate new posts, which are ad copy that reflect past posting patterns and trends. The input is the trained generative model, and the output is the automatically generated post.

[0573] Step 4:

[0574] The server sends the automatically generated message content to the terminal. The terminal presents this content to the user so that the user can confirm it. The input is the automatically generated message content, and the output is the content displayed on the terminal.

[0575] Step 5:

[0576] The user checks the presented message content and makes corrections as necessary. The corrected message content is sent back to the server via the terminal. The input is the content corrected by the user, and the corrected message content is sent to the server as output.

[0577] Step 6:

[0578] The server posts the revised content via the SNS API, which makes the final content available to the SNS. The input is the revised content, and the output is the content posted to the SNS.

[0579] 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.

[0580] This invention relates to a system that automatically generates daily posts by collecting data on users' past posts on social networking services (SNS), training a generative model that learns writing styles and tendencies based on that data, and combining it with an emotion engine that recognizes the user's emotions. This system includes a process in which the generated posts are presented to the user, who can then make any necessary edits and finally post the posts to the SNS.

[0581] System configuration

[0582] The system consists of the following main components:

[0583] 1. Server: Responsible for collecting data, training the generative model and emotion engine, and automatically generating dissemination content.

[0584] 2. Terminal: Presents the generated transmission content to the user and provides an interface for editing.

[0585] 3. User: A user of the SNS who makes final confirmations and corrections to the content posted.

[0586] 4. Emotion engine: Analyzes emotions from users' past posting data and real-time input data, and reflects them in the output of the generative model.

[0587] System Operation

[0588] 1. Collection of past posting data

[0589] The server uses the SNS API to collect users' past posting data, including the content of posts, images, videos, and posting timing, and stores the data in a database.

[0590] 2. Training the generative model and emotion engine

[0591] The server uses the collected past posting data to train a generative model (e.g., GPT-3) and an emotion engine. The generative model learns writing style, and the emotion engine is used to analyze user emotions from past posting data.

[0592] 3. Automatic generation of daily posting content

[0593] The server uses the trained generative model and emotion engine to automatically generate the message for the day, and the tone and style of the message are generated based on the output of the emotion engine, depending on the user's emotional state.

[0594] 4. Modifications based on sentiment analysis

[0595] The automatically generated message is based on the user's emotional state and is presented to the user via the terminal. The user can review the presented text and modify it as necessary.

[0596] 5. Final call processing

[0597] Once the corrections are complete, the server posts the finalized message content via the SNS API. If the post is successful, the information is notified to the device and the user.

[0598] Specific examples

[0599] Example 1:

[0600] Suppose a user frequently posts "Good morning! Let's do our best today!". In this case, the system behaves as follows:

[0601] The server collects past posting data and uses this data to train the generative model and emotion engine.

[0602] Every morning, the server uses the generative model and emotion engine to automatically generate a new "good morning" message. For example, if the user was tired the night before, the emotion engine can suggest something like, "Take it easy today."

[0603] This message is sent to the device, and the user can modify it to say, "Maybe today is a good day to take it easy."

[0604] Finally, the server posts this modified message to the social networking site.

[0605] Example 2:

[0606] If a user frequently posts about the weather, such as "It looks like it's going to rain today. Be careful!":

[0607] The server collects past weather-related post data and uses it to train the generative model and emotion engine.

[0608] The emotion engine analyzes how users feel on rainy days, so if a user is typically inactive on rainy days, the generated messages will have a more subdued tone to match that emotion.

[0609] The generated message will be "It looks like it's going to rain today. Take it easy," and will be presented to the user via the device.

[0610] The user modifies the message to "Let's relax at home on a rainy day!", and the server then posts the message to social media.

[0611] This system generates natural-sounding messages based on the user's past posting data and emotions, saving the user time and effort while enabling high-quality daily messages. Furthermore, manual corrections can be made as needed, so messages can be sent in line with the user's intentions.

[0612] The processing flow will be explained below.

[0613] Step 1:

[0614] The server collects past posting data from users' SNS accounts. To do this, it uses the SNS's API and obtains the posting data with the user's permission. The data includes posted text, images, videos, and the timing of posting. This data is then stored in a database.

[0615] Step 2:

[0616] The server organizes the collected data into a dataset, extracts important information (post text, hashtags, tagged image and video information), and converts it into a format that can be used by the generative model and emotion engine. This dataset is used to train the generative model and emotion engine.

[0617] Step 3:

[0618] The server uses the organized dataset to train a text generation model (e.g., GPT-3). The generation model learns the user's writing style and the phrases they use, and prepares to generate future posts in a natural way.

[0619] Step 4:

[0620] The server also trains the emotion engine, which analyzes emotions from users' past posting data and reflects the results in the output of the generative model. This generates content that reflects the user's emotional state.

[0621] Step 5:

[0622] The server uses the trained generative model and emotion engine to automatically generate the message for the day, with the tone and style corresponding to the user's emotional state based on the output of the emotion engine.

[0623] Step 6:

[0624] The server sends the generated message to the terminal. The terminal displays the generated text to the user and provides an interface for confirmation and correction. The user can check the generated text and make corrections as necessary.

[0625] Step 7:

[0626] The user checks the automatically generated text and makes corrections as necessary. After completing the corrections, the user presses a button to confirm the corrected message content for final confirmation. If there are no corrections to be made, the user can confirm the message directly.

[0627] Step 8:

[0628] The server retrieves the finalized message content and posts it to the designated SNS platform using the SNS API. If the post is completed successfully, the information is notified to the device and the user. This completes the daily regular message.

[0629] The above processing steps allow users to minimize the effort required for regular daily calls and maintain high quality of the content of their calls. In addition, manual corrections can be made as needed, allowing calls to be made in line with the user's intentions.

[0630] Example 2

[0631] 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."

[0632] In modern social networking services (SNS), users spend a great deal of time and effort maintaining their daily posts. In particular, it is difficult for users to post high-quality content that reflects their personal style and emotions. This has led to problems such as a decline in user engagement and a decrease in the efficiency of SNS use.

[0633] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting past posting data, means for training a generative model and an emotion engine based on the past posting data, means for automatically generating daily posts using the generative model and emotion engine, means for presenting the generated posts to a user and allowing the user to modify them, and means for posting the modified posts to a predetermined social networking service. This enables the automatic generation and modification of high-quality posts based on the user's past posting style and emotions, thereby reducing user effort and improving engagement.

[0634] "Past posting data" refers to information such as all previous postings, images, videos, and posting timing made by a user on a social networking service.

[0635] A "generative model" refers to an AI model that learns writing style and idiom based on past posting data and automatically generates text.

[0636] An "emotion engine" refers to an algorithm that analyzes emotions from users' past posting data and reflects that information in a generative model.

[0637] "Means for automatic generation" refers to the function of automatically creating daily content using a trained generative model and emotion engine.

[0638] The "presentation means" refers to an interface that displays the generated transmission content to the user and allows the user to modify it.

[0639] "Modified Submission" means the final version that reflects any changes or edits made by the user to the presented auto-generated content.

[0640] "Social Networking Service" means an online platform that enables users to create profiles, share messages, photos, videos, etc., and communicate with other users.

[0641] The "schedule management means" refers to a function for making the generated transmission content be presented to the user at a specific time.

[0642] "Hot topics" refer to topics or themes that are currently attracting the interest of many people in society or communities and are being discussed.

[0643] This system collects data on users' past posts on social networking services (SNS), and uses that data to train a generative model and emotion engine to automatically generate daily posts, present them to users, and allow them to modify them. It also includes a process for posting the final modified posts to the SNS.

[0644] First, the server collects data on users' past posts through the social networking service's API. This data includes the post content, images, videos, and timing of posts. For example, the server calls the "GET / posts" endpoint to retrieve post data from the past year. This data is stored in a database using the SQL query "INSERT INTO posts (user_id, content, image_url, video_url, timestamp) VALUES ...".

[0645] Next, the server trains a generative AI model (e.g., GPT-3) and sentiment engine based on the post data stored in the database. For training, the "train.py" script is used, inputting the past 5,000 posts. The generative model learns writing style, and the sentiment engine extracts sentiment from the post data.

[0646] The server then uses the trained generative model and emotion engine to automatically generate the message content for that day. Based on the results output by the emotion engine, a prompt sentence is input into the generative model, and text is generated. Specifically, the "generate.py" script is executed to input a prompt sentence based on the output of the emotion engine into the generative AI model.

[0647] The generated message content is presented to the user via the device. The device calls the API endpoint " / getGeneratedContent" to obtain the generated text and displays it to the user. The user checks the displayed text and makes any necessary corrections. These corrections are sent from the device to the server. For example, if the user corrects it to "Maybe today is a good day to take it easy" and clicks the "submitChanges" button, the corrections are sent to the server.

[0648] Finally, the server checks the revised content and posts it to the specified SNS. The server calls "POST / finalPost" to post the revised text to the SNS. The "POST / notification" endpoint is then used to notify the user and device that the post has been completed.

[0649] Examples of concrete examples and prompts

[0650] Example 1:

[0651] If a user frequently posts "Good morning. Let's do our best today!", the server collects past posting data and trains a generative model and emotion engine. Every morning, the server uses the generative model and emotion engine to generate a new "Good morning" message. For example, if the user is tired the night before, the emotion engine will suggest "Let's take it easy today." In response, the user can modify the message by saying "Maybe today is a good day to take it easy," and the server will finally post the revised message to the SNS.

[0652] Example prompt sentence:

[0653] "Generate this morning's post based on past posting data. If the user was tired the night before, make the post reflect that emotion."

[0654] Example 2:

[0655] If a user frequently posts about the weather, such as "It looks like it's going to rain today. Be careful!", the server collects past weather-related posting data and uses it to train a generative model and emotion engine. The emotion engine analyzes the user's emotions on rainy days and generates messages with a more subdued tone. The generated message is "It looks like it's going to rain today. Take it easy," and is presented to the user via their device. The user then modifies it to "Take it easy at home on a rainy day!", after which the server posts it to the SNS.

[0656] Example prompt sentence:

[0657] "Generate a post about today's weather. Please keep the tone muted and based on rainy day emotions."

[0658] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0659] System program processing flow

[0660] Step 1: Collect past posting data

[0661] The server collects the user's past posting data through the SNS API. The input is the user's authentication information and the SNS API endpoint, and the output is the retrieved posting data. For example, calling the "GET / posts" endpoint retrieves the user's posting data from the past year. This data includes the post content, images, videos, and posting date and time.

[0662] Step 2: Saving to the database

[0663] The server saves the collected post data in a database. The input is the acquired post data, and the output is the completion of registration in the database. Specifically, it executes the SQL query "INSERT INTO posts (user_id, content, image_url, video_url, timestamp) VALUES ..." to save the data.

[0664] Step 3: Training the generative model and emotion engine

[0665] The server trains a generative AI model (e.g., GPT-3) and emotion engine based on the posted data stored in the database. The input is past posted data, and the output is the trained generative model and emotion engine. Specifically, the "train.py" script is run to train using the past 5,000 posted data.

[0666] Step 4: Automatic generation of daily postings

[0667] The server uses the trained generative model and emotion engine to automatically generate the message content for the day. The input is the output data of the emotion engine, and the output is the generated message content. Specifically, the "generate.py" script is executed, and a prompt sentence based on the output of the emotion engine is input to the generative AI model to generate text.

[0668] Step 5: Present the message

[0669] The terminal presents the generated call content to the user. The input is the generated call content, and the output is the text to be displayed to the user. Specifically, the terminal calls the API endpoint " / getGeneratedContent" to obtain the generated text and display it to the user.

[0670] Step 6: Edit the message

[0671] The user checks the presented message and makes corrections if necessary. The input is the generated message, and the output is the text corrected by the user. The user makes corrections on the screen and clicks the "submitChanges" button, and the corrections are sent to the server.

[0672] Step 7: Final call processing

[0673] The server performs a final check of the message content amended by the user and posts it to the SNS. The input is the text amended by the user, and the output is a notification that the post has been completed to the SNS. Specifically, it calls "POST / finalPost" to post the amended text to the SNS. It then uses the "POST / notification" endpoint to send a notification that the post has been completed to the user and their device.

[0674] (Application example 2)

[0675] 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."

[0676] Currently, it is difficult for users to think of what to post on social networking services (SNS) every day. It is also time-consuming to generate personalized content based on each user's interests and emotions and share it on other platforms. Furthermore, manual editing is required to improve the quality of the generated content, which often leaves users feeling overwhelmed. The present invention aims to solve these problems and provide users with an easy and natural sharing experience.

[0677] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting past posting data of users, means for training a generative model that learns the user's writing style based on the past posting data, and means for automatically generating daily posting content using the generative model. This enables means for generating personalized content based on the user's interests, means for sharing the generated content on other platforms, means for presenting the automatically generated posting content to the user and allowing the user to make corrections, and means for posting the corrected posting content to a predetermined social networking service.

[0678] "User's past posting data" refers to information such as text, images, videos, and the timing of posts made by the user in the past on social networking services.

[0679] A "generative model that learns writing style" is a model that can learn a user's unique writing style from their past posting data and generate new text based on this.

[0680] "Daily posts" refer to the text and content that users post on social networking services on a daily basis.

[0681] "Automatic generation means" refers to a method or device that uses a specific algorithm or program to generate text or content without human intervention.

[0682] "Means for user presentation and modification" refers to a method or interface that allows users to view system-generated content and change it as needed.

[0683] "Means for posting to designated social networking services" refers to a method or mechanism for automatically posting modified content to designated social networking platforms according to schedules or conditions.

[0684] "Means for generating personalized content" refers to algorithms or systems that generate individualized content based on the user's interests and concerns.

[0685] "Means of sharing to other platforms" refers to the methods and mechanisms for posting and distributing the generated content to websites, applications, etc. other than social networking services.

[0686] This invention is a system that automatically generates personalized posts for users by collecting data on past posts on social networking services (SNS), training a generative model based on that data, and combining it with a sentiment analysis engine. This system includes a process that presents the generated posts to the user, and then the user makes any edits before finally posting.

[0687] Components

[0688] The system consists of the following main components:

[0689] 1. Server: Responsible for collecting data, training generative models and emotion engines, automatically generating messages, and generating personalized content.

[0690] 2. Terminal: Presents the generated transmission content to the user and provides a user interface for editing.

[0691] 3. User: A user of the SNS who makes final confirmations and corrections to the content posted.

[0692] Hardware and Software

[0693] The server uses the following technology stack:

[0694] Data collection: Use Python (requests, BeautifulSoup, Tweepy, etc.) to retrieve data using SNS APIs.

[0695] Generative model: We use OpenAI GPT-3 via API to train the generative model.

[0696] Sentiment analysis: Sentiment analysis is performed using Microsoft Azure Cognitive Services.

[0697] Backend: Django is used, and the database is PostgreSQL.

[0698] Front-end: Use React Native to build the user interface.

[0699] Processing flow

[0700] 1. Collection of past posting data

[0701] The server collects users' past posting data through the SNS's API. This data includes the text, images, videos, and timing of posts. The collected data is stored in a database.

[0702] 2. Training the generative model and emotion engine

[0703] The server trains a generative model using OpenAI GPT-3 based on collected past posting data, and also uses Microsoft Azure Cognitive Services to train an emotion engine capable of analyzing users' emotional states.

[0704] 3. Daily posting and personalized content generation

[0705] The server uses a trained generative model and emotion engine to automatically generate personalized content based on the user's interests every day, resulting in natural, useful content tailored to the user.

[0706] 4. User Presentation and Modification

[0707] The generated message is presented to the user via the terminal, who can check the text and make corrections as necessary.

[0708] 5. Final Content Delivery

[0709] The revised content is automatically posted to the specified social networking service and other platforms via the server.

[0710] Specific examples

[0711] If a user frequently posts about the weather, such as "It looks like it's going to rain today. Be careful!", the system will act as follows:

[0712] The server collects past weather-related posting data and uses it to train the generative model and emotion engine.

[0713] The emotion engine analyzes how users feel on rainy days and reflects this in the messages they generate.

[0714] The generated message will be "It looks like it's going to rain today. Take it easy," and will be displayed to the user via their device.

[0715] The user modifies the message to "Let's stay home and relax on a rainy day!", after which the server posts it to social media and other platforms.

[0716] Example prompts for generative AI models

[0717] "Based on your posting history, today we will post the following:

[0718] Morning greeting: "Good morning. Today I have some special news for you."

[0719] About the weather: "The weather is sunny today. Let's enjoy a nice day."

[0720] Sentiment analysis correction:

[0721] "You seem to be tired lately. Let's not push ourselves too hard."

[0722] In this way, personalized, high-quality messages can be sent while reducing the burden on users.

[0723] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0724] Step 1:

[0725] The server uses the SNS API to collect data on users' past posts. The collected data includes the content of the post, images, videos, and the timing of the post. This collected data is stored in a database. The input is the post data obtained from the API, and the output is the formatted data stored in the database.

[0726] Step 2:

[0727] The server uses the previously posted data stored in the database to train a generative model (e.g., OpenAI GPT-3). Specifically, it trains the model to learn the user's writing style from this data. The input is the previously posted data, and the output is the trained generative model.

[0728] Step 3:

[0729] The server uses Microsoft Azure Cognitive Services to train the emotion engine. This emotion engine analyzes emotions in past posting data and learns what emotions appear in what situations. The input is the past posting data, and the output is the trained emotion engine.

[0730] Step 4:

[0731] The server automatically generates daily posts using a trained generative model and emotion engine, taking into account the user's past activities and current emotional state to generate content appropriate for the user. The input is the trained model and emotion engine, and the output is the automatically generated posts.

[0732] Step 5:

[0733] The automatically generated message content is presented to the user via the terminal. The user checks the presented content and makes corrections as necessary. The input is the generated message content, and the output is the message content corrected by the user.

[0734] Step 6:

[0735] The modified message is posted to a specified social networking service via the server. The server posts the generated message to the specified SNS platform. The input is the message modified by the user, and the output is the message posted to the SNS.

[0736] Step 7:

[0737] When personalized content generation is required, the server generates content based on the user's interests. This can be specialized for news articles or content related to a particular topic. The input is the user's past interest data, and the output is personalized content.

[0738] Step 8:

[0739] The generated personalized content is presented to the user through their device and shared to other platforms. The user can review it, modify it as necessary, and then share it across multiple platforms. The input is the personalized content, and the output is the content shared to other platforms.

[0740] 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.

[0741] 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.

[0742] 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.

[0743] [Third embodiment]

[0744] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0745] 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.

[0746] 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).

[0747] 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.

[0748] 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.

[0749] 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).

[0750] 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.

[0751] 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.

[0752] 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.

[0753] 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.

[0754] 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.

[0755] 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."

[0756] This invention relates to a system that automatically generates daily posts by collecting data on users' past posts on social networking services (SNS), training a generative model that learns writing styles and trends based on that data, and presenting the generated posts to the user, who can then make any necessary edits and finally post the posts to the SNS.

[0757] System configuration

[0758] The system consists of the following main components:

[0759] 1. Server: Responsible for collecting data, training generative models, and automatically generating dissemination content.

[0760] 2. Terminal: Presents the generated transmission content to the user and provides an interface for editing.

[0761] 3. User: A user of the SNS who makes final confirmations and corrections to the content posted.

[0762] System Operation

[0763] 1. Collection of past posting data

[0764] The server uses the SNS API to collect users' past posting data, including the content of posts, images, videos, and metadata.

[0765] 2. Training the generative model

[0766] The server uses the collected data to train a generative model (e.g., GPT-3), which learns the user's writing style and the phrases they use.

[0767] 3. Automatic generation of daily posting content

[0768] The server uses a trained generative model to automatically generate daily posts, which contain natural-sounding sentences based on past posting data.

[0769] 4. Check and correct the content of the message

[0770] The automatically generated message is presented to the user via the terminal, who can then check it and make any necessary corrections.

[0771] 5. Final call processing

[0772] Once the corrections are complete, the server posts the final message via the SNS API.

[0773] Specific examples

[0774] Example 1:

[0775] Let's say a user frequently posts "Good morning! Let's do our best today!" every morning. In this case, the system works as follows:

[0776] The server collects past posting data and creates a dataset that includes other morning greeting posts from this user.

[0777] The server trains a generative model to learn the user's writing style and frequently used phrases.

[0778] Every morning at a set time, the server automatically generates a new "good morning" message using this model.

[0779] This message is sent to the device and the user modifies it to say, "Good morning. I have a feeling today will be a special day!"

[0780] Finally, the server posts this modified message to the social networking site.

[0781] Example 2:

[0782] If a user frequently posts about the weather, such as "It looks like it's going to rain today. Be careful!":

[0783] The server collects past weather-related posts and uses them to train a generative model.

[0784] Weather forecast data is also used as a reference, so that the automatically generated text will include content appropriate for the weather on that day.

[0785] The generated message is "It looks like it's going to rain today. Don't forget your umbrella!" and is presented to the user via the terminal.

[0786] The user corrects the situation by saying, "It's forecast to rain heavily today. Don't forget your umbrella when you go out!", and the server then posts the message to social media.

[0787] This system generates natural content based on past posting data, saving users time and effort while enabling high-quality daily posting.

[0788] The processing flow will be explained below.

[0789] Step 1:

[0790] The server collects past posting data from the user's SNS account. To do this, it uses the SNS's API and obtains the posting data with the user's permission. The data includes posted text, images, videos, and the timing of posting. This allows the user's past posting history to be stored in a database.

[0791] Step 2:

[0792] The server organizes the collected data into a dataset, extracts important information (post text, hashtags, tagged images and videos) and converts it into a format that can be used by the generative model. This dataset is used to train the generative model.

[0793] Step 3:

[0794] The server uses the dataset organized in the previous step to train a text generation model (e.g., GPT-3). The generative model learns the user's writing style and prepares to generate future posts in a natural manner. This training process takes different amounts of time depending on the amount and complexity of the data collected.

[0795] Step 4:

[0796] The server uses the trained generative model to automatically generate the content to be posted that day. To prepare the automatically generated content for a specific time, the server issues commands to the generative model. The text generated at this stage is appropriate based on past posts and trend information.

[0797] Step 5:

[0798] The server sends the automatically generated message to a device (such as the user's smartphone or PC). The device displays the message to the user and provides an interface for prompting confirmation and correction. The user checks the presented text and corrects the text as necessary. This correction is made before the message is finalized.

[0799] Step 6:

[0800] The user checks the automatically generated text and makes any necessary corrections. Once the corrections are complete, the user presses a button to confirm the corrected message content and finalizes it. If there are no corrections to be made, the message can be confirmed as is.

[0801] Step 7:

[0802] The server retrieves the finalized message content and posts it to the designated SNS platform using the SNS API. If the post is successful, the information is notified to the device and the user. This completes the daily regular message.

[0803] This series of processes allows users to minimize the effort required for regular daily calls and maintain high quality of the content of their calls. In addition, manual corrections can be made as needed, so calls can be made in line with the user's intentions.

[0804] Example 1

[0805] 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."

[0806] In recent years, the number of users of social networking services (SNS) has increased, creating a need for continuous management of the content posted daily. However, it takes a lot of effort for users to come up with new content to post every day, resulting in a decline in the consistency and quality of posts. Furthermore, while there are systems that learn writing style and trends from past posts and automatically generate new posts in a natural way, it is often difficult to completely eliminate the user's effort. There is a need for a method to solve these issues and enable users to post high-quality content on a continuous basis.

[0807] 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.

[0808] In this invention, the server includes a means for collecting past posting data of users, a means for training a generative model that learns the user's writing style based on the past posting data, and a means for automatically generating daily posting content using the generative model, thereby making it possible to generate natural, consistent, and high-quality posting content while reducing the user's effort.

[0809] "User" means an individual or organization that posts using a social networking service.

[0810] "Past posting data" refers to all content (text, images, videos, metadata, etc.) that a user has previously posted on a social networking service.

[0811] "Means of collection" refers to the technology and devices used to obtain and store data using the APIs of social networking services.

[0812] A "generative model" refers to a mathematical model that uses machine learning algorithms to learn from specific data and generate new data based on that data.

[0813] "Training means" refers to the techniques and methods used to train a generative model using previously posted data.

[0814] "Means for automatic generation" refers to technologies and methods for automatically generating new user posts using a trained generative model.

[0815] "Means for presentation" refers to the technology and method for displaying the generated transmission content to the user and enabling confirmation and correction.

[0816] "Means enabling modification" refers to interfaces or technologies that allow users to change or modify automatically generated content.

[0817] "Specified social networking services" refers to online platforms such as Twitter, Facebook, and Instagram where users can post content.

[0818] "Means of posting" refers to the technology or method for posting the modified content online via the API of a social networking service.

[0819] "Means for managing schedule" refers to techniques and methods for managing time so that the generated transmission content is presented to the user at a specific time.

[0820] "Trending topics" refers to themes and topics that are currently attracting the interest of many people on the Internet and social networking services.

[0821] "Means of learning and incorporating it into generated communications" refers to the technology and methods for training a generative model to learn about popular topics in society and then generating communications that include those topics.

[0822] This invention relates to a system that automatically generates daily posts by collecting data on users' past posts on social networking services (SNS), training a generative AI model that learns writing styles and trends based on that data, and presenting the generated posts to the user, who can then make any necessary edits and finally post the posts to the SNS.

[0823] System configuration

[0824] The system consists of the following main components:

[0825] 1. Server: Responsible for collecting data, training generative models, and automatically generating dissemination content.

[0826] 2. Terminal: Presents the generated transmission content to the user and provides an interface for editing.

[0827] 3. User: A user of the SNS who makes final confirmations and corrections to the content posted.

[0828] Server Processing

[0829] The server first uses the SNS API to collect data on users' past posts. This data includes text data, image data, video data, and metadata such as posting time and location information. For example, past tweets can be obtained using the Twitter API.

[0830] The collected data is preprocessed and then used to train a generative AI model (e.g., GPT-3). Preprocessing includes text cleaning, tokenization, and conversion to multidimensional vectors. The result of training is a generative model that learns the user's writing style and the phrases they use.

[0831] Using a trained generative model, the server automatically generates daily posts. By inputting a prompt into the generative model, natural-sounding sentences are generated based on past posting patterns. For example, a prompt such as "Good morning! Let's do our best today!" can be used.

[0832] Terminal handling

[0833] The generated message is presented to the user via their device. A user interface similar to the posting field of an SNS is displayed on the device, allowing the user to review and edit the generated message. Once the user has finished editing, the edited message is sent back to the server.

[0834] User Action

[0835] The user can check the message displayed on the device and make corrections as necessary. For example, the generated message "Good morning. I feel like today is going to be a great day!" can be corrected to "Good morning. I feel like today is going to be a special day!"

[0836] Final call processing

[0837] The final revised content is posted via the server using the SNS API. For example, a tweet can be sent using the Twitter API.

[0838] This system allows users to generate natural, consistent, and high-quality posts based on past writing styles and patterns, saving them time and effort. It also allows users to schedule posts to be posted at specific times, and incorporates popular topics to attract more attention.

[0839] Specific examples

[0840] Example 1:

[0841] If a user frequently posts "Good morning! Let's do our best today!" every morning, the system will work as follows:

[0842] The server collects past posting data and creates a dataset that includes other morning greeting posts from this user.

[0843] The server trains a generative model to learn the user's writing style and frequently used phrases.

[0844] Every morning at a set time, the server automatically generates a new "good morning" message using this model.

[0845] This message is sent to the device and the user modifies it to say, "Good morning. I have a feeling today will be a special day!"

[0846] Finally, the server posts this modified message to the social networking site.

[0847] Example 2:

[0848] If a user frequently posts about the weather, such as "It looks like it's going to rain today. Be careful!":

[0849] The server collects past weather-related posts and uses them to train a generative model.

[0850] Weather forecast data is also used as a reference, and the automatically generated text includes content appropriate to the weather on that day.

[0851] The generated message is "It looks like it's going to rain today. Don't forget your umbrella!" and is presented to the user via the terminal.

[0852] The user corrects the situation by saying, "It's forecast to rain heavily today. Don't forget your umbrella when you go out!", and the server then posts the message to social media.

[0853] This allows users to generate natural content based on past posting data, saving them time and effort, and enabling them to continue to post high-quality content on a daily basis.

[0854] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0855] Step 1: Collect past posting data

[0856] Input: Social networking service API key and user ID

[0857] Operation:

[0858] The server uses the SNS API to collect data on users' past posts. This data includes metadata such as text, images, videos, posting times, and location information. It first authenticates the user using the API key and user ID, and then sends the appropriate request to the SNS API.

[0859] Output: A dataset of collected historical posting data

[0860] Step 2: Training the generative model

[0861] Input: A dataset of collected historical posting data

[0862] Operation:

[0863] The server preprocesses the collected data, which includes cleaning the text, tokenizing it, and converting it into multidimensional vectors. Once preprocessing is complete, a training dataset is created. A generative AI model (e.g., GPT-3) is then trained on this dataset. During this process, the model learns the user's writing style, the phrases they use, and their posting patterns.

[0864] Output: A trained generative AI model

[0865] Step 3: Automatically generate daily content

[0866] Input: A trained generative AI model, a prompt

[0867] Operation:

[0868] The server inputs the prompt sentences into a generative AI model to automatically generate daily posting content. The prompt sentences are generated based on the user's past posting patterns. The generative AI model then generates natural-sounding sentences based on these prompt sentences.

[0869] Output: Automatically generated call content

[0870] Step 4: Present the message

[0871] Input: Auto-generated call content

[0872] Operation:

[0873] The terminal receives the transmitted content sent from the server and presents it to the user. The user can check the content displayed on the terminal and make corrections as necessary. A user interface for this purpose is provided on the terminal.

[0874] Output: The message that the user confirmed and corrected

[0875] Step 5: Edit the message

[0876] Input: User feedback and corrections

[0877] Operation:

[0878] The user checks the message displayed on the terminal and makes corrections as necessary. For example, the generated message "Good morning. I feel like today is going to be a great day!" can be corrected to "Good morning. I feel like today is going to be a special day!". The corrected message is then sent back to the server.

[0879] Output: Modified outgoing message

[0880] Step 6: Final call processing

[0881] Input: Corrected call content

[0882] Operation:

[0883] The server receives the modified content and posts it to the designated social networking service using the SNS API. During this process, the server authenticates the user using the API key again and sends the appropriate request.

[0884] Output: Posted content on a specified social networking service

[0885] These processing steps allow users to automatically generate natural, high-quality content every day based on their own past posts, and easily post it to SNS after making any necessary edits.

[0886] (Application example 1)

[0887] 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."

[0888] Today's businesses need to efficiently and effectively run advertising campaigns using social networking services (SNS). However, consistently generating daily posting content is time-consuming, and it is difficult to reflect past posting patterns and trends. Managing posting at the right time is also a challenge. There is a need for a system that can solve these issues and enable businesses to effectively utilize SNS.

[0889] 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.

[0890] In this invention, the server includes means for collecting past posting data of users, means for training a generative model that learns the user's writing style based on the past posting data, means for automatically generating daily posting content using the generative model, means for automatically generating the automatically generated posting content as advertisements for products and services, and means for posting the corrected posting content to a predetermined communication network. This enables the automatic generation of high-quality advertising content based on past data and the implementation of efficient SNS campaigns.

[0891] "Past posting data" refers to a record of all information, such as text, images, and videos, that a user has previously made public on social networking services, etc.

[0892] A "generative model" is an artificial intelligence model that can learn from collected data and make predictions and generate results.

[0893] "Training" is the process of using data to adjust the parameters of a generative model to improve the model's performance.

[0894] "Auto-generation" refers to the use of pre-trained generative models to generate new content without human intervention.

[0895] "Communication network" is a general term for communication infrastructure for sending and receiving data, including the Internet.

[0896] "Advertising" is the act of disseminating information with the aim of promoting product sales or raising awareness of services.

[0897] System configuration

[0898] A system for implementing this invention comprises the following main components: a server, a terminal, and a user.

[0899] 1. Server

[0900] The server is responsible for collecting data, training generative models, and automatically generating content. Specifically, it uses the following hardware and software:

[0901] Hardware: High-performance processors, memory, and storage devices

[0902] Software: Social media API (Twitter API, Instagram Graph API), database (MySQL or MongoDB), generative model (OpenAI GPT-4)

[0903] The server first uses the SNS API to collect the user's past posting data (text, images, videos, etc.). The collected data is stored in a database. Next, a generative model (e.g., GPT-4) is trained using the past posting data. This allows the server to learn the user's writing style and frequently used phrases.

[0904] 2. Terminal

[0905] The terminal is used to present the generated transmission content to the user and to provide an interface for making corrections.

[0906] Hardware: Smartphones, tablets, PCs

[0907] Software: Front-end application (React Native)

[0908] The automatically generated message is presented to the user through the terminal and can be edited. The intuitive user interface allows the user to easily check, edit, and finally confirm the generated message.

[0909] 3. Users

[0910] The user plays a key role in making final confirmations and corrections.

[0911] System operation example

[0912] 1. Data collection: The server uses the SNS API to collect data on past company posts.

[0913] 2. Training the generative model: Train a generative model (OpenAI GPT-4) based on the collected data.

[0914] 3. Auto-generation: Use the trained model to generate new ad posts.

[0915] 4. Confirm and edit: The automatically generated post is presented to the user via their device, and the user can edit it as necessary.

[0916] 5. Posting: The server posts the final content to the SNS via the communication network.

[0917] Specific examples

[0918] For example, if a clothing brand is announcing a new product:

[0919] The server collects past posting data and uses it to train a generative model. Let's say a new product announcement is automatically generated, with the following content: "Look stylish this fall with our brand's new collection." The user then reviews it and modifies it to read, "Look stylish this fall with our new collection. Check the link for details!"

[0920] The server posts the finalized content to the social networking site.

[0921] Prompt Sentence Examples

[0922] "Generate social media posts to promote new products based on past posting data. Use keywords like 'autumn,' 'collection,' and 'brand.' The content should convey the charm of autumn."

[0923] In this way, the system of the present invention can efficiently generate high-quality and consistent SNS posts for advertising campaigns and support corporate marketing activities.

[0924] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0925] Step 1:

[0926] The server uses the SNS API to collect data on users' past posts. This data includes text, images, videos, etc. and is stored in a database. The input is data obtained from the SNS API, and the output is organized post data that is stored in the database.

[0927] Step 2:

[0928] The server trains a generative model (such as OpenAI GPT-4) based on the collected data. During this training process, it learns the writing style and phrases used in past posts. The input is the collected data, and the output is the trained generative model.

[0929] Step 3:

[0930] The server uses the trained generative model to automatically generate new posts, which are ad copy that reflect past posting patterns and trends. The input is the trained generative model, and the output is the automatically generated post.

[0931] Step 4:

[0932] The server sends the automatically generated message content to the terminal. The terminal presents this content to the user so that the user can confirm it. The input is the automatically generated message content, and the output is the content displayed on the terminal.

[0933] Step 5:

[0934] The user checks the presented message content and makes corrections as necessary. The corrected message content is sent back to the server via the terminal. The input is the content corrected by the user, and the corrected message content is sent to the server as output.

[0935] Step 6:

[0936] The server posts the revised content via the SNS API, which makes the final content available to the SNS. The input is the revised content, and the output is the content posted to the SNS.

[0937] 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.

[0938] This invention relates to a system that automatically generates daily posts by collecting data on users' past posts on social networking services (SNS), training a generative model that learns writing styles and tendencies based on that data, and combining it with an emotion engine that recognizes the user's emotions. This system includes a process in which the generated posts are presented to the user, who can then make any necessary edits and finally post the posts to the SNS.

[0939] System configuration

[0940] The system consists of the following main components:

[0941] 1. Server: Responsible for collecting data, training the generative model and emotion engine, and automatically generating dissemination content.

[0942] 2. Terminal: Presents the generated transmission content to the user and provides an interface for editing.

[0943] 3. User: A user of the SNS who makes final confirmations and corrections to the content posted.

[0944] 4. Emotion engine: Analyzes emotions from users' past posting data and real-time input data, and reflects them in the output of the generative model.

[0945] System Operation

[0946] 1. Collection of past posting data

[0947] The server uses the SNS API to collect users' past posting data, including the content of posts, images, videos, and posting timing, and stores the data in a database.

[0948] 2. Training the generative model and emotion engine

[0949] The server uses the collected past posting data to train a generative model (e.g., GPT-3) and an emotion engine. The generative model learns writing style, and the emotion engine is used to analyze user emotions from past posting data.

[0950] 3. Automatic generation of daily posting content

[0951] The server uses the trained generative model and emotion engine to automatically generate the message for the day, and the tone and style of the message are generated based on the output of the emotion engine, depending on the user's emotional state.

[0952] 4. Modifications based on sentiment analysis

[0953] The automatically generated message is based on the user's emotional state and is presented to the user via the terminal. The user can review the presented text and modify it as necessary.

[0954] 5. Final call processing

[0955] Once the corrections are complete, the server posts the finalized message content via the SNS API. If the post is successful, the information is notified to the device and the user.

[0956] Specific examples

[0957] Example 1:

[0958] Suppose a user frequently posts "Good morning! Let's do our best today!". In this case, the system behaves as follows:

[0959] The server collects past posting data and uses this data to train the generative model and emotion engine.

[0960] Every morning, the server uses the generative model and emotion engine to automatically generate a new "good morning" message. For example, if the user was tired the night before, the emotion engine can suggest something like, "Take it easy today."

[0961] This message is sent to the device, and the user can modify it to say, "Maybe today is a good day to take it easy."

[0962] Finally, the server posts this modified message to the social networking site.

[0963] Example 2:

[0964] If a user frequently posts about the weather, such as "It looks like it's going to rain today. Be careful!":

[0965] The server collects past weather-related post data and uses it to train the generative model and emotion engine.

[0966] The emotion engine analyzes how users feel on rainy days, so if a user is typically inactive on rainy days, the generated messages will have a more subdued tone to match that emotion.

[0967] The generated message will be "It looks like it's going to rain today. Take it easy," and will be presented to the user via the device.

[0968] The user modifies the message to "Let's relax at home on a rainy day!", and the server then posts the message to social media.

[0969] This system generates natural-sounding messages based on the user's past posting data and emotions, saving the user time and effort while enabling high-quality daily messages. Furthermore, manual corrections can be made as needed, so messages can be sent in line with the user's intentions.

[0970] The processing flow will be explained below.

[0971] Step 1:

[0972] The server collects past posting data from users' SNS accounts. To do this, it uses the SNS's API and obtains the posting data with the user's permission. The data includes posted text, images, videos, and the timing of posting. This data is then stored in a database.

[0973] Step 2:

[0974] The server organizes the collected data into a dataset, extracts important information (post text, hashtags, tagged image and video information), and converts it into a format that can be used by the generative model and emotion engine. This dataset is used to train the generative model and emotion engine.

[0975] Step 3:

[0976] The server uses the organized dataset to train a text generation model (e.g., GPT-3). The generation model learns the user's writing style and the phrases they use, and prepares to generate future posts in a natural way.

[0977] Step 4:

[0978] The server also trains the emotion engine, which analyzes emotions from users' past posting data and reflects the results in the output of the generative model. This generates content that reflects the user's emotional state.

[0979] Step 5:

[0980] The server uses the trained generative model and emotion engine to automatically generate the message for the day, with the tone and style corresponding to the user's emotional state based on the output of the emotion engine.

[0981] Step 6:

[0982] The server sends the generated message to the terminal. The terminal displays the generated text to the user and provides an interface for confirmation and correction. The user can check the generated text and make corrections as necessary.

[0983] Step 7:

[0984] The user checks the automatically generated text and makes corrections as necessary. After completing the corrections, the user presses a button to confirm the corrected message content for final confirmation. If there are no corrections to be made, the user can confirm the message directly.

[0985] Step 8:

[0986] The server retrieves the finalized message content and posts it to the designated SNS platform using the SNS API. If the post is completed successfully, the information is notified to the device and the user. This completes the daily regular message.

[0987] The above processing steps allow users to minimize the effort required for regular daily calls and maintain high quality of the content of their calls. In addition, manual corrections can be made as needed, allowing calls to be made in line with the user's intentions.

[0988] Example 2

[0989] 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."

[0990] In modern social networking services (SNS), users spend a great deal of time and effort maintaining their daily posts. In particular, it is difficult for users to post high-quality content that reflects their personal style and emotions. This has led to problems such as a decline in user engagement and a decrease in the efficiency of SNS use.

[0991] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting past posting data, means for training a generative model and an emotion engine based on the past posting data, means for automatically generating daily posts using the generative model and emotion engine, means for presenting the generated posts to a user and allowing the user to modify them, and means for posting the modified posts to a predetermined social networking service. This enables the automatic generation and modification of high-quality posts based on the user's past posting style and emotions, thereby reducing user effort and improving engagement.

[0992] "Past posting data" refers to information such as all previous postings, images, videos, and posting timing made by a user on a social networking service.

[0993] A "generative model" refers to an AI model that learns writing style and idiom based on past posting data and automatically generates text.

[0994] An "emotion engine" refers to an algorithm that analyzes emotions from users' past posting data and reflects that information in a generative model.

[0995] "Means for automatic generation" refers to the function of automatically creating daily content using a trained generative model and emotion engine.

[0996] The "presentation means" refers to an interface that displays the generated transmission content to the user and allows the user to modify it.

[0997] "Modified Submission" means the final version that reflects any changes or edits made by the user to the presented auto-generated content.

[0998] "Social Networking Service" means an online platform that enables users to create profiles, share messages, photos, videos, etc., and communicate with other users.

[0999] The "schedule management means" refers to a function for making the generated transmission content be presented to the user at a specific time.

[1000] "Hot topics" refer to topics or themes that are currently attracting the interest of many people in society or communities and are being discussed.

[1001] This system collects data on users' past posts on social networking services (SNS), and uses that data to train a generative model and emotion engine to automatically generate daily posts, present them to users, and allow them to modify them. It also includes a process for posting the final modified posts to the SNS.

[1002] First, the server collects data on users' past posts through the social networking service's API. This data includes the post content, images, videos, and timing of posts. For example, the server calls the "GET / posts" endpoint to retrieve post data from the past year. This data is stored in a database using the SQL query "INSERT INTO posts (user_id, content, image_url, video_url, timestamp) VALUES ...".

[1003] Next, the server trains a generative AI model (e.g., GPT-3) and sentiment engine based on the post data stored in the database. For training, the "train.py" script is used, inputting the past 5,000 posts. The generative model learns writing style, and the sentiment engine extracts sentiment from the post data.

[1004] The server then uses the trained generative model and emotion engine to automatically generate the message content for that day. Based on the results output by the emotion engine, a prompt sentence is input into the generative model, and text is generated. Specifically, the "generate.py" script is executed to input a prompt sentence based on the output of the emotion engine into the generative AI model.

[1005] The generated message content is presented to the user via the device. The device calls the API endpoint " / getGeneratedContent" to obtain the generated text and displays it to the user. The user checks the displayed text and makes any necessary corrections. These corrections are sent from the device to the server. For example, if the user corrects it to "Maybe today is a good day to take it easy" and clicks the "submitChanges" button, the corrections are sent to the server.

[1006] Finally, the server checks the revised content and posts it to the specified SNS. The server calls "POST / finalPost" to post the revised text to the SNS. The "POST / notification" endpoint is then used to notify the user and device that the post has been completed.

[1007] Examples of concrete examples and prompts

[1008] Example 1:

[1009] If a user frequently posts "Good morning. Let's do our best today!", the server collects past posting data and trains a generative model and emotion engine. Every morning, the server uses the generative model and emotion engine to generate a new "Good morning" message. For example, if the user is tired the night before, the emotion engine will suggest "Let's take it easy today." In response, the user can modify the message by saying "Maybe today is a good day to take it easy," and the server will finally post the revised message to the SNS.

[1010] Example prompt sentence:

[1011] "Generate this morning's post based on past posting data. If the user was tired the night before, make the post reflect that emotion."

[1012] Example 2:

[1013] If a user frequently posts about the weather, such as "It looks like it's going to rain today. Be careful!", the server collects past weather-related posting data and uses it to train a generative model and emotion engine. The emotion engine analyzes the user's emotions on rainy days and generates messages with a more subdued tone. The generated message is "It looks like it's going to rain today. Take it easy," and is presented to the user via their device. The user then modifies it to "Take it easy at home on a rainy day!", after which the server posts it to the SNS.

[1014] Example prompt sentence:

[1015] "Generate a post about today's weather. Please keep the tone muted and based on rainy day emotions."

[1016] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1017] System program processing flow

[1018] Step 1: Collect past posting data

[1019] The server collects the user's past posting data through the SNS API. The input is the user's authentication information and the SNS API endpoint, and the output is the retrieved posting data. For example, calling the "GET / posts" endpoint retrieves the user's posting data from the past year. This data includes the post content, images, videos, and posting date and time.

[1020] Step 2: Saving to the database

[1021] The server saves the collected post data in a database. The input is the acquired post data, and the output is the completion of registration in the database. Specifically, it executes the SQL query "INSERT INTO posts (user_id, content, image_url, video_url, timestamp) VALUES ..." to save the data.

[1022] Step 3: Training the generative model and emotion engine

[1023] The server trains a generative AI model (e.g., GPT-3) and emotion engine based on the posted data stored in the database. The input is past posted data, and the output is the trained generative model and emotion engine. Specifically, the "train.py" script is run to train using the past 5,000 posted data.

[1024] Step 4: Automatic generation of daily postings

[1025] The server uses the trained generative model and emotion engine to automatically generate the message content for the day. The input is the output data of the emotion engine, and the output is the generated message content. Specifically, the "generate.py" script is executed, and a prompt sentence based on the output of the emotion engine is input to the generative AI model to generate text.

[1026] Step 5: Present the message

[1027] The terminal presents the generated call content to the user. The input is the generated call content, and the output is the text to be displayed to the user. Specifically, the terminal calls the API endpoint " / getGeneratedContent" to obtain the generated text and display it to the user.

[1028] Step 6: Edit the message

[1029] The user checks the presented message and makes corrections if necessary. The input is the generated message, and the output is the text corrected by the user. The user makes corrections on the screen and clicks the "submitChanges" button, and the corrections are sent to the server.

[1030] Step 7: Final call processing

[1031] The server performs a final check of the message content amended by the user and posts it to the SNS. The input is the text amended by the user, and the output is a notification that the post has been completed to the SNS. Specifically, it calls "POST / finalPost" to post the amended text to the SNS. It then uses the "POST / notification" endpoint to send a notification that the post has been completed to the user and their device.

[1032] (Application example 2)

[1033] 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."

[1034] Currently, it is difficult for users to think of what to post on social networking services (SNS) every day. It is also time-consuming to generate personalized content based on each user's interests and emotions and share it on other platforms. Furthermore, manual editing is required to improve the quality of the generated content, which often leaves users feeling overwhelmed. The present invention aims to solve these problems and provide users with an easy and natural sharing experience.

[1035] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting past posting data of users, means for training a generative model that learns the user's writing style based on the past posting data, and means for automatically generating daily posting content using the generative model. This enables means for generating personalized content based on the user's interests, means for sharing the generated content on other platforms, means for presenting the automatically generated posting content to the user and allowing the user to make corrections, and means for posting the corrected posting content to a predetermined social networking service.

[1036] "User's past posting data" refers to information such as text, images, videos, and the timing of posts made by the user in the past on social networking services.

[1037] A "generative model that learns writing style" is a model that can learn a user's unique writing style from their past posting data and generate new text based on this.

[1038] "Daily posts" refer to the text and content that users post on social networking services on a daily basis.

[1039] "Automatic generation means" refers to a method or device that uses a specific algorithm or program to generate text or content without human intervention.

[1040] "Means for user presentation and modification" refers to a method or interface that allows users to view system-generated content and change it as needed.

[1041] "Means for posting to designated social networking services" refers to a method or mechanism for automatically posting modified content to designated social networking platforms according to schedules or conditions.

[1042] "Means for generating personalized content" refers to algorithms or systems that generate individualized content based on the user's interests and concerns.

[1043] "Means of sharing to other platforms" refers to the methods and mechanisms for posting and distributing the generated content to websites, applications, etc. other than social networking services.

[1044] This invention is a system that automatically generates personalized posts for users by collecting data on past posts on social networking services (SNS), training a generative model based on that data, and combining it with a sentiment analysis engine. This system includes a process that presents the generated posts to the user, and then the user makes any edits before finally posting.

[1045] Components

[1046] The system consists of the following main components:

[1047] 1. Server: Responsible for collecting data, training generative models and emotion engines, automatically generating messages, and generating personalized content.

[1048] 2. Terminal: Presents the generated transmission content to the user and provides a user interface for editing.

[1049] 3. User: A user of the SNS who makes final confirmations and corrections to the content posted.

[1050] Hardware and Software

[1051] The server uses the following technology stack:

[1052] Data collection: Use Python (requests, BeautifulSoup, Tweepy, etc.) to retrieve data using SNS APIs.

[1053] Generative model: We use OpenAI GPT-3 via API to train the generative model.

[1054] Sentiment analysis: Sentiment analysis is performed using Microsoft Azure Cognitive Services.

[1055] Backend: Django is used, and the database is PostgreSQL.

[1056] Front-end: Use React Native to build the user interface.

[1057] Processing flow

[1058] 1. Collection of past posting data

[1059] The server collects users' past posting data through the SNS's API. This data includes the text, images, videos, and timing of posts. The collected data is stored in a database.

[1060] 2. Training the generative model and emotion engine

[1061] The server trains a generative model using OpenAI GPT-3 based on collected past posting data, and also uses Microsoft Azure Cognitive Services to train an emotion engine capable of analyzing users' emotional states.

[1062] 3. Daily posting and personalized content generation

[1063] The server uses a trained generative model and emotion engine to automatically generate personalized content based on the user's interests every day, resulting in natural, useful content tailored to the user.

[1064] 4. User Presentation and Modification

[1065] The generated message is presented to the user via the terminal, who can check the text and make corrections as necessary.

[1066] 5. Final Content Delivery

[1067] The revised content is automatically posted to the specified social networking service and other platforms via the server.

[1068] Specific examples

[1069] If a user frequently posts about the weather, such as "It looks like it's going to rain today. Be careful!", the system will act as follows:

[1070] The server collects past weather-related posting data and uses it to train the generative model and emotion engine.

[1071] The emotion engine analyzes how users feel on rainy days and reflects this in the messages they generate.

[1072] The generated message will be "It looks like it's going to rain today. Take it easy," and will be displayed to the user via their device.

[1073] The user modifies the message to "Let's stay home and relax on a rainy day!", after which the server posts it to social media and other platforms.

[1074] Example prompts for generative AI models

[1075] "Based on your posting history, today we will post the following:

[1076] Morning greeting: "Good morning. Today I have some special news for you."

[1077] About the weather: "The weather is sunny today. Let's enjoy a nice day."

[1078] Sentiment analysis correction:

[1079] "You seem to be tired lately. Let's not push ourselves too hard."

[1080] In this way, personalized, high-quality messages can be sent while reducing the burden on users.

[1081] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1082] Step 1:

[1083] The server uses the SNS API to collect data on users' past posts. The collected data includes the content of the post, images, videos, and the timing of the post. This collected data is stored in a database. The input is the post data obtained from the API, and the output is the formatted data stored in the database.

[1084] Step 2:

[1085] The server uses the previously posted data stored in the database to train a generative model (e.g., OpenAI GPT-3). Specifically, it trains the model to learn the user's writing style from this data. The input is the previously posted data, and the output is the trained generative model.

[1086] Step 3:

[1087] The server uses Microsoft Azure Cognitive Services to train the emotion engine. This emotion engine analyzes emotions in past posting data and learns what emotions appear in what situations. The input is the past posting data, and the output is the trained emotion engine.

[1088] Step 4:

[1089] The server automatically generates daily posts using a trained generative model and emotion engine, taking into account the user's past activities and current emotional state to generate content appropriate for the user. The input is the trained model and emotion engine, and the output is the automatically generated posts.

[1090] Step 5:

[1091] The automatically generated message content is presented to the user via the terminal. The user checks the presented content and makes corrections as necessary. The input is the generated message content, and the output is the message content corrected by the user.

[1092] Step 6:

[1093] The modified message is posted to a specified social networking service via the server. The server posts the generated message to the specified SNS platform. The input is the message modified by the user, and the output is the message posted to the SNS.

[1094] Step 7:

[1095] When personalized content generation is required, the server generates content based on the user's interests. This can be specialized for news articles or content related to a particular topic. The input is the user's past interest data, and the output is personalized content.

[1096] Step 8:

[1097] The generated personalized content is presented to the user through their device and shared to other platforms. The user can review it, modify it as necessary, and then share it across multiple platforms. The input is the personalized content, and the output is the content shared to other platforms.

[1098] 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.

[1099] 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.

[1100] 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.

[1101] [Fourth embodiment]

[1102] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1103] 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.

[1104] 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).

[1105] 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.

[1106] 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.

[1107] 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).

[1108] 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.

[1109] 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.

[1110] 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.

[1111] 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.

[1112] 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.

[1113] 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.

[1114] 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."

[1115] This invention relates to a system that automatically generates daily posts by collecting data on users' past posts on social networking services (SNS), training a generative model that learns writing styles and trends based on that data, and presenting the generated posts to the user, who can then make any necessary edits and finally post the posts to the SNS.

[1116] System configuration

[1117] The system consists of the following main components:

[1118] 1. Server: Responsible for collecting data, training generative models, and automatically generating dissemination content.

[1119] 2. Terminal: Presents the generated transmission content to the user and provides an interface for editing.

[1120] 3. User: A user of the SNS who makes final confirmations and corrections to the content posted.

[1121] System Operation

[1122] 1. Collection of past posting data

[1123] The server uses the SNS API to collect users' past posting data, including the content of posts, images, videos, and metadata.

[1124] 2. Training the generative model

[1125] The server uses the collected data to train a generative model (e.g., GPT-3), which learns the user's writing style and the phrases they use.

[1126] 3. Automatic generation of daily posting content

[1127] The server uses a trained generative model to automatically generate daily posts, which contain natural-sounding sentences based on past posting data.

[1128] 4. Check and correct the content of the message

[1129] The automatically generated message is presented to the user via the terminal, who can then check it and make any necessary corrections.

[1130] 5. Final call processing

[1131] Once the corrections are complete, the server posts the final message via the SNS API.

[1132] Specific examples

[1133] Example 1:

[1134] Let's say a user frequently posts "Good morning! Let's do our best today!" every morning. In this case, the system works as follows:

[1135] The server collects past posting data and creates a dataset that includes other morning greeting posts from this user.

[1136] The server trains a generative model to learn the user's writing style and frequently used phrases.

[1137] Every morning at a set time, the server automatically generates a new "good morning" message using this model.

[1138] This message is sent to the device and the user modifies it to say, "Good morning. I have a feeling today will be a special day!"

[1139] Finally, the server posts this modified message to the social networking site.

[1140] Example 2:

[1141] If a user frequently posts about the weather, such as "It looks like it's going to rain today. Be careful!":

[1142] The server collects past weather-related posts and uses them to train a generative model.

[1143] Weather forecast data is also used as a reference, so that the automatically generated text will include content appropriate for the weather on that day.

[1144] The generated message is "It looks like it's going to rain today. Don't forget your umbrella!" and is presented to the user via the terminal.

[1145] The user corrects the situation by saying, "It's forecast to rain heavily today. Don't forget your umbrella when you go out!", and the server then posts the message to social media.

[1146] This system generates natural content based on past posting data, saving users time and effort while enabling high-quality daily posting.

[1147] The processing flow will be explained below.

[1148] Step 1:

[1149] The server collects past posting data from the user's SNS account. To do this, it uses the SNS's API and obtains the posting data with the user's permission. The data includes posted text, images, videos, and the timing of posting. This allows the user's past posting history to be stored in a database.

[1150] Step 2:

[1151] The server organizes the collected data into a dataset, extracts important information (post text, hashtags, tagged images and videos) and converts it into a format that can be used by the generative model. This dataset is used to train the generative model.

[1152] Step 3:

[1153] The server uses the dataset organized in the previous step to train a text generation model (e.g., GPT-3). The generative model learns the user's writing style and prepares to generate future posts in a natural manner. This training process takes different amounts of time depending on the amount and complexity of the data collected.

[1154] Step 4:

[1155] The server uses the trained generative model to automatically generate the content to be posted that day. To prepare the automatically generated content for a specific time, the server issues commands to the generative model. The text generated at this stage is appropriate based on past posts and trend information.

[1156] Step 5:

[1157] The server sends the automatically generated message to a device (such as the user's smartphone or PC). The device displays the message to the user and provides an interface for prompting confirmation and correction. The user checks the presented text and corrects the text as necessary. This correction is made before the message is finalized.

[1158] Step 6:

[1159] The user checks the automatically generated text and makes any necessary corrections. Once the corrections are complete, the user presses a button to confirm the corrected message content and finalizes it. If there are no corrections to be made, the message can be confirmed as is.

[1160] Step 7:

[1161] The server retrieves the finalized message content and posts it to the designated SNS platform using the SNS API. If the post is successful, the information is notified to the device and the user. This completes the daily regular message.

[1162] This series of processes allows users to minimize the effort required for regular daily calls and maintain high quality of the content of their calls. In addition, manual corrections can be made as needed, so calls can be made in line with the user's intentions.

[1163] Example 1

[1164] 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."

[1165] In recent years, the number of users of social networking services (SNS) has increased, creating a need for continuous management of the content posted daily. However, it takes a lot of effort for users to come up with new content to post every day, resulting in a decline in the consistency and quality of posts. Furthermore, while there are systems that learn writing style and trends from past posts and automatically generate new posts in a natural way, it is often difficult to completely eliminate the user's effort. There is a need for a method to solve these issues and enable users to post high-quality content on a continuous basis.

[1166] 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.

[1167] In this invention, the server includes a means for collecting past posting data of users, a means for training a generative model that learns the user's writing style based on the past posting data, and a means for automatically generating daily posting content using the generative model, thereby making it possible to generate natural, consistent, and high-quality posting content while reducing the user's effort.

[1168] "User" means an individual or organization that posts using a social networking service.

[1169] "Past posting data" refers to all content (text, images, videos, metadata, etc.) that a user has previously posted on a social networking service.

[1170] "Means of collection" refers to the technology and devices used to obtain and store data using the APIs of social networking services.

[1171] A "generative model" refers to a mathematical model that uses machine learning algorithms to learn from specific data and generate new data based on that data.

[1172] "Training means" refers to the techniques and methods used to train a generative model using previously posted data.

[1173] "Means for automatic generation" refers to technologies and methods for automatically generating new user posts using a trained generative model.

[1174] "Means for presentation" refers to the technology and method for displaying the generated transmission content to the user and enabling confirmation and correction.

[1175] "Means enabling modification" refers to interfaces or technologies that allow users to change or modify automatically generated content.

[1176] "Specified social networking services" refers to online platforms such as Twitter, Facebook, and Instagram where users can post content.

[1177] "Means of posting" refers to the technology or method for posting the modified content online via the API of a social networking service.

[1178] "Means for managing schedule" refers to techniques and methods for managing time so that the generated transmission content is presented to the user at a specific time.

[1179] "Trending topics" refers to themes and topics that are currently attracting the interest of many people on the Internet and social networking services.

[1180] "Means of learning and incorporating it into generated communications" refers to the technology and methods for training a generative model to learn about popular topics in society and then generating communications that include those topics.

[1181] This invention relates to a system that automatically generates daily posts by collecting data on users' past posts on social networking services (SNS), training a generative AI model that learns writing styles and trends based on that data, and presenting the generated posts to the user, who can then make any necessary edits and finally post the posts to the SNS.

[1182] System configuration

[1183] The system consists of the following main components:

[1184] 1. Server: Responsible for collecting data, training generative models, and automatically generating dissemination content.

[1185] 2. Terminal: Presents the generated transmission content to the user and provides an interface for editing.

[1186] 3. User: A user of the SNS who makes final confirmations and corrections to the content posted.

[1187] Server Processing

[1188] The server first uses the SNS API to collect data on users' past posts. This data includes text data, image data, video data, and metadata such as posting time and location information. For example, past tweets can be obtained using the Twitter API.

[1189] The collected data is preprocessed and then used to train a generative AI model (e.g., GPT-3). Preprocessing includes text cleaning, tokenization, and conversion to multidimensional vectors. The result of training is a generative model that learns the user's writing style and the phrases they use.

[1190] Using a trained generative model, the server automatically generates daily posts. By inputting a prompt into the generative model, natural-sounding sentences are generated based on past posting patterns. For example, a prompt such as "Good morning! Let's do our best today!" can be used.

[1191] Terminal handling

[1192] The generated message is presented to the user via their device. A user interface similar to the posting field of an SNS is displayed on the device, allowing the user to review and edit the generated message. Once the user has finished editing, the edited message is sent back to the server.

[1193] User Action

[1194] The user can check the message displayed on the device and make corrections as necessary. For example, the generated message "Good morning. I feel like today is going to be a great day!" can be corrected to "Good morning. I feel like today is going to be a special day!"

[1195] Final call processing

[1196] The final revised content is posted via the server using the SNS API. For example, a tweet can be sent using the Twitter API.

[1197] This system allows users to generate natural, consistent, and high-quality posts based on past writing styles and patterns, saving them time and effort. It also allows users to schedule posts to be posted at specific times, and incorporates popular topics to attract more attention.

[1198] Specific examples

[1199] Example 1:

[1200] If a user frequently posts "Good morning! Let's do our best today!" every morning, the system will work as follows:

[1201] The server collects past posting data and creates a dataset that includes other morning greeting posts from this user.

[1202] The server trains a generative model to learn the user's writing style and frequently used phrases.

[1203] Every morning at a set time, the server automatically generates a new "good morning" message using this model.

[1204] This message is sent to the device and the user modifies it to say, "Good morning. I have a feeling today will be a special day!"

[1205] Finally, the server posts this modified message to the social networking site.

[1206] Example 2:

[1207] If a user frequently posts about the weather, such as "It looks like it's going to rain today. Be careful!":

[1208] The server collects past weather-related posts and uses them to train a generative model.

[1209] Weather forecast data is also used as a reference, and the automatically generated text includes content appropriate to the weather on that day.

[1210] The generated message is "It looks like it's going to rain today. Don't forget your umbrella!" and is presented to the user via the terminal.

[1211] The user corrects the situation by saying, "It's forecast to rain heavily today. Don't forget your umbrella when you go out!", and the server then posts the message to social media.

[1212] This allows users to generate natural content based on past posting data, saving them time and effort, and enabling them to continue to post high-quality content on a daily basis.

[1213] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1214] Step 1: Collect past posting data

[1215] Input: Social networking service API key and user ID

[1216] Operation:

[1217] The server uses the SNS API to collect data on users' past posts. This data includes metadata such as text, images, videos, posting times, and location information. It first authenticates the user using the API key and user ID, and then sends the appropriate request to the SNS API.

[1218] Output: A dataset of collected historical posting data

[1219] Step 2: Training the generative model

[1220] Input: A dataset of collected historical posting data

[1221] Operation:

[1222] The server preprocesses the collected data, which includes cleaning the text, tokenizing it, and converting it into multidimensional vectors. Once preprocessing is complete, a training dataset is created. A generative AI model (e.g., GPT-3) is then trained on this dataset. During this process, the model learns the user's writing style, the phrases they use, and their posting patterns.

[1223] Output: A trained generative AI model

[1224] Step 3: Automatically generate daily content

[1225] Input: A trained generative AI model, a prompt

[1226] Operation:

[1227] The server inputs the prompt sentences into a generative AI model to automatically generate daily posting content. The prompt sentences are generated based on the user's past posting patterns. The generative AI model then generates natural-sounding sentences based on these prompt sentences.

[1228] Output: Automatically generated call content

[1229] Step 4: Present the message

[1230] Input: Auto-generated call content

[1231] Operation:

[1232] The terminal receives the transmitted content sent from the server and presents it to the user. The user can check the content displayed on the terminal and make corrections as necessary. A user interface for this purpose is provided on the terminal.

[1233] Output: The message that the user confirmed and corrected

[1234] Step 5: Edit the message

[1235] Input: User feedback and corrections

[1236] Operation:

[1237] The user checks the message displayed on the terminal and makes corrections as necessary. For example, the generated message "Good morning. I feel like today is going to be a great day!" can be corrected to "Good morning. I feel like today is going to be a special day!". The corrected message is then sent back to the server.

[1238] Output: Modified outgoing message

[1239] Step 6: Final call processing

[1240] Input: Corrected call content

[1241] Operation:

[1242] The server receives the modified content and posts it to the designated social networking service using the SNS API. During this process, the server authenticates the user using the API key again and sends the appropriate request.

[1243] Output: Posted content on a specified social networking service

[1244] These processing steps allow users to automatically generate natural, high-quality content every day based on their own past posts, and easily post it to SNS after making any necessary edits.

[1245] (Application example 1)

[1246] 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."

[1247] Today's businesses need to efficiently and effectively run advertising campaigns using social networking services (SNS). However, consistently generating daily posting content is time-consuming, and it is difficult to reflect past posting patterns and trends. Managing posting at the right time is also a challenge. There is a need for a system that can solve these issues and enable businesses to effectively utilize SNS.

[1248] 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.

[1249] In this invention, the server includes means for collecting past posting data of users, means for training a generative model that learns the user's writing style based on the past posting data, means for automatically generating daily posting content using the generative model, means for automatically generating the automatically generated posting content as advertisements for products and services, and means for posting the corrected posting content to a predetermined communication network. This enables the automatic generation of high-quality advertising content based on past data and the implementation of efficient SNS campaigns.

[1250] "Past posting data" refers to a record of all information, such as text, images, and videos, that a user has previously made public on social networking services, etc.

[1251] A "generative model" is an artificial intelligence model that can learn from collected data and make predictions and generate results.

[1252] "Training" is the process of using data to adjust the parameters of a generative model to improve the model's performance.

[1253] "Auto-generation" refers to the use of pre-trained generative models to generate new content without human intervention.

[1254] "Communication network" is a general term for communication infrastructure for sending and receiving data, including the Internet.

[1255] "Advertising" is the act of disseminating information with the aim of promoting product sales or raising awareness of services.

[1256] System configuration

[1257] A system for implementing this invention comprises the following main components: a server, a terminal, and a user.

[1258] 1. Server

[1259] The server is responsible for collecting data, training generative models, and automatically generating content. Specifically, it uses the following hardware and software:

[1260] Hardware: High-performance processors, memory, and storage devices

[1261] Software: Social media API (Twitter API, Instagram Graph API), database (MySQL or MongoDB), generative model (OpenAI GPT-4)

[1262] The server first uses the SNS API to collect the user's past posting data (text, images, videos, etc.). The collected data is stored in a database. Next, a generative model (e.g., GPT-4) is trained using the past posting data. This allows the server to learn the user's writing style and frequently used phrases.

[1263] 2. Terminal

[1264] The terminal is used to present the generated transmission content to the user and to provide an interface for making corrections.

[1265] Hardware: Smartphones, tablets, PCs

[1266] Software: Front-end application (React Native)

[1267] The automatically generated message is presented to the user through the terminal and can be edited. The intuitive user interface allows the user to easily check, edit, and finally confirm the generated message.

[1268] 3. Users

[1269] The user plays a key role in making final confirmations and corrections.

[1270] System operation example

[1271] 1. Data collection: The server uses the SNS API to collect data on past company posts.

[1272] 2. Training the generative model: Train a generative model (OpenAI GPT-4) based on the collected data.

[1273] 3. Auto-generation: Use the trained model to generate new ad posts.

[1274] 4. Confirm and edit: The automatically generated post is presented to the user via their device, and the user can edit it as necessary.

[1275] 5. Posting: The server posts the final content to the SNS via the communication network.

[1276] Specific examples

[1277] For example, if a clothing brand is announcing a new product:

[1278] The server collects past posting data and uses it to train a generative model. Let's say a new product announcement is automatically generated, with the following content: "Look stylish this fall with our brand's new collection." The user then reviews it and modifies it to read, "Look stylish this fall with our new collection. Check the link for details!"

[1279] The server posts the finalized content to the social networking site.

[1280] Prompt Sentence Examples

[1281] "Generate social media posts to promote new products based on past posting data. Use keywords like 'autumn,' 'collection,' and 'brand.' The content should convey the charm of autumn."

[1282] In this way, the system of the present invention can efficiently generate high-quality and consistent SNS posts for advertising campaigns and support corporate marketing activities.

[1283] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1284] Step 1:

[1285] The server uses the SNS API to collect data on users' past posts. This data includes text, images, videos, etc. and is stored in a database. The input is data obtained from the SNS API, and the output is organized post data that is stored in the database.

[1286] Step 2:

[1287] The server trains a generative model (such as OpenAI GPT-4) based on the collected data. During this training process, it learns the writing style and phrases used in past posts. The input is the collected data, and the output is the trained generative model.

[1288] Step 3:

[1289] The server uses the trained generative model to automatically generate new posts, which are ad copy that reflect past posting patterns and trends. The input is the trained generative model, and the output is the automatically generated post.

[1290] Step 4:

[1291] The server sends the automatically generated message content to the terminal. The terminal presents this content to the user so that the user can confirm it. The input is the automatically generated message content, and the output is the content displayed on the terminal.

[1292] Step 5:

[1293] The user checks the presented message content and makes corrections as necessary. The corrected message content is sent back to the server via the terminal. The input is the content corrected by the user, and the corrected message content is sent to the server as output.

[1294] Step 6:

[1295] The server posts the revised content via the SNS API, which makes the final content available to the SNS. The input is the revised content, and the output is the content posted to the SNS.

[1296] 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.

[1297] This invention relates to a system that automatically generates daily posts by collecting data on users' past posts on social networking services (SNS), training a generative model that learns writing styles and tendencies based on that data, and combining it with an emotion engine that recognizes the user's emotions. This system includes a process in which the generated posts are presented to the user, who can then make any necessary edits and finally post the posts to the SNS.

[1298] System configuration

[1299] The system consists of the following main components:

[1300] 1. Server: Responsible for collecting data, training the generative model and emotion engine, and automatically generating dissemination content.

[1301] 2. Terminal: Presents the generated transmission content to the user and provides an interface for editing.

[1302] 3. User: A user of the SNS who makes final confirmations and corrections to the content posted.

[1303] 4. Emotion engine: Analyzes emotions from users' past posting data and real-time input data, and reflects them in the output of the generative model.

[1304] System Operation

[1305] 1. Collection of past posting data

[1306] The server uses the SNS API to collect users' past posting data, including the content of posts, images, videos, and posting timing, and stores the data in a database.

[1307] 2. Training the generative model and emotion engine

[1308] The server uses the collected past posting data to train a generative model (e.g., GPT-3) and an emotion engine. The generative model learns writing style, and the emotion engine is used to analyze user emotions from past posting data.

[1309] 3. Automatic generation of daily posting content

[1310] The server uses the trained generative model and emotion engine to automatically generate the message for the day, and the tone and style of the message are generated based on the output of the emotion engine, depending on the user's emotional state.

[1311] 4. Modifications based on sentiment analysis

[1312] The automatically generated message is based on the user's emotional state and is presented to the user via the terminal. The user can review the presented text and modify it as necessary.

[1313] 5. Final call processing

[1314] Once the corrections are complete, the server posts the finalized message content via the SNS API. If the post is successful, the information is notified to the device and the user.

[1315] Specific examples

[1316] Example 1:

[1317] Suppose a user frequently posts "Good morning! Let's do our best today!". In this case, the system behaves as follows:

[1318] The server collects past posting data and uses this data to train the generative model and emotion engine.

[1319] Every morning, the server uses the generative model and emotion engine to automatically generate a new "good morning" message. For example, if the user was tired the night before, the emotion engine can suggest something like, "Take it easy today."

[1320] This message is sent to the device, and the user can modify it to say, "Maybe today is a good day to take it easy."

[1321] Finally, the server posts this modified message to the social networking site.

[1322] Example 2:

[1323] If a user frequently posts about the weather, such as "It looks like it's going to rain today. Be careful!":

[1324] The server collects past weather-related post data and uses it to train the generative model and emotion engine.

[1325] The emotion engine analyzes how users feel on rainy days, so if a user is typically inactive on rainy days, the generated messages will have a more subdued tone to match that emotion.

[1326] The generated message will be "It looks like it's going to rain today. Take it easy," and will be presented to the user via the device.

[1327] The user modifies the message to "Let's relax at home on a rainy day!", and the server then posts the message to social media.

[1328] This system generates natural-sounding messages based on the user's past posting data and emotions, saving the user time and effort while enabling high-quality daily messages. Furthermore, manual corrections can be made as needed, so messages can be sent in line with the user's intentions.

[1329] The processing flow will be explained below.

[1330] Step 1:

[1331] The server collects past posting data from users' SNS accounts. To do this, it uses the SNS's API and obtains the posting data with the user's permission. The data includes posted text, images, videos, and the timing of posting. This data is then stored in a database.

[1332] Step 2:

[1333] The server organizes the collected data into a dataset, extracts important information (post text, hashtags, tagged image and video information), and converts it into a format that can be used by the generative model and emotion engine. This dataset is used to train the generative model and emotion engine.

[1334] Step 3:

[1335] The server uses the organized dataset to train a text generation model (e.g., GPT-3). The generation model learns the user's writing style and the phrases they use, and prepares to generate future posts in a natural way.

[1336] Step 4:

[1337] The server also trains the emotion engine, which analyzes emotions from users' past posting data and reflects the results in the output of the generative model. This generates content that reflects the user's emotional state.

[1338] Step 5:

[1339] The server uses the trained generative model and emotion engine to automatically generate the message for the day, with the tone and style corresponding to the user's emotional state based on the output of the emotion engine.

[1340] Step 6:

[1341] The server sends the generated message to the terminal. The terminal displays the generated text to the user and provides an interface for confirmation and correction. The user can check the generated text and make corrections as necessary.

[1342] Step 7:

[1343] The user checks the automatically generated text and makes corrections as necessary. After completing the corrections, the user presses a button to confirm the corrected message content for final confirmation. If there are no corrections to be made, the user can confirm the message directly.

[1344] Step 8:

[1345] The server retrieves the finalized message content and posts it to the designated SNS platform using the SNS API. If the post is completed successfully, the information is notified to the device and the user. This completes the daily regular message.

[1346] The above processing steps allow users to minimize the effort required for regular daily calls and maintain high quality of the content of their calls. In addition, manual corrections can be made as needed, allowing calls to be made in line with the user's intentions.

[1347] Example 2

[1348] 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."

[1349] In modern social networking services (SNS), users spend a great deal of time and effort maintaining their daily posts. In particular, it is difficult for users to post high-quality content that reflects their personal style and emotions. This has led to problems such as a decline in user engagement and a decrease in the efficiency of SNS use.

[1350] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for collecting past posting data, means for training a generative model and an emotion engine based on the past posting data, means for automatically generating daily posts using the generative model and emotion engine, means for presenting the generated posts to a user and allowing the user to modify them, and means for posting the modified posts to a predetermined social networking service. This enables the automatic generation and modification of high-quality posts based on the user's past posting style and emotions, thereby reducing user effort and improving engagement.

[1351] "Past posting data" refers to information such as all previous postings, images, videos, and posting timing made by a user on a social networking service.

[1352] A "generative model" refers to an AI model that learns writing style and idiom based on past posting data and automatically generates text.

[1353] An "emotion engine" refers to an algorithm that analyzes emotions from users' past posting data and reflects that information in a generative model.

[1354] "Means for automatic generation" refers to the function of automatically creating daily content using a trained generative model and emotion engine.

[1355] The "presentation means" refers to an interface that displays the generated transmission content to the user and allows the user to modify it.

[1356] "Modified Submission" means the final version that reflects any changes or edits made by the user to the presented auto-generated content.

[1357] "Social Networking Service" means an online platform that enables users to create profiles, share messages, photos, videos, etc., and communicate with other users.

[1358] The "schedule management means" refers to a function for making the generated transmission content be presented to the user at a specific time.

[1359] "Hot topics" refer to topics or themes that are currently attracting the interest of many people in society or communities and are being discussed.

[1360] This system collects data on users' past posts on social networking services (SNS), and uses that data to train a generative model and emotion engine to automatically generate daily posts, present them to users, and allow them to modify them. It also includes a process for posting the final modified posts to the SNS.

[1361] First, the server collects data on users' past posts through the social networking service's API. This data includes the post content, images, videos, and timing of posts. For example, the server calls the "GET / posts" endpoint to retrieve post data from the past year. This data is stored in a database using the SQL query "INSERT INTO posts (user_id, content, image_url, video_url, timestamp) VALUES ...".

[1362] Next, the server trains a generative AI model (e.g., GPT-3) and sentiment engine based on the post data stored in the database. For training, the "train.py" script is used, inputting the past 5,000 posts. The generative model learns writing style, and the sentiment engine extracts sentiment from the post data.

[1363] The server then uses the trained generative model and emotion engine to automatically generate the message content for that day. Based on the results output by the emotion engine, a prompt sentence is input into the generative model, and text is generated. Specifically, the "generate.py" script is executed to input a prompt sentence based on the output of the emotion engine into the generative AI model.

[1364] The generated message content is presented to the user via the device. The device calls the API endpoint " / getGeneratedContent" to obtain the generated text and displays it to the user. The user checks the displayed text and makes any necessary corrections. These corrections are sent from the device to the server. For example, if the user corrects it to "Maybe today is a good day to take it easy" and clicks the "submitChanges" button, the corrections are sent to the server.

[1365] Finally, the server checks the revised content and posts it to the specified SNS. The server calls "POST / finalPost" to post the revised text to the SNS. The "POST / notification" endpoint is then used to notify the user and device that the post has been completed.

[1366] Examples of concrete examples and prompts

[1367] Example 1:

[1368] If a user frequently posts "Good morning. Let's do our best today!", the server collects past posting data and trains a generative model and emotion engine. Every morning, the server uses the generative model and emotion engine to generate a new "Good morning" message. For example, if the user is tired the night before, the emotion engine will suggest "Let's take it easy today." In response, the user can modify the message by saying "Maybe today is a good day to take it easy," and the server will finally post the revised message to the SNS.

[1369] Example prompt sentence:

[1370] "Generate this morning's post based on past posting data. If the user was tired the night before, make the post reflect that emotion."

[1371] Example 2:

[1372] If a user frequently posts about the weather, such as "It looks like it's going to rain today. Be careful!", the server collects past weather-related posting data and uses it to train a generative model and emotion engine. The emotion engine analyzes the user's emotions on rainy days and generates messages with a more subdued tone. The generated message is "It looks like it's going to rain today. Take it easy," and is presented to the user via their device. The user then modifies it to "Take it easy at home on a rainy day!", after which the server posts it to the SNS.

[1373] Example prompt sentence:

[1374] "Generate a post about today's weather. Please keep the tone muted and based on rainy day emotions."

[1375] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1376] System program processing flow

[1377] Step 1: Collect past posting data

[1378] The server collects the user's past posting data through the SNS API. The input is the user's authentication information and the SNS API endpoint, and the output is the retrieved posting data. For example, calling the "GET / posts" endpoint retrieves the user's posting data from the past year. This data includes the post content, images, videos, and posting date and time.

[1379] Step 2: Saving to the database

[1380] The server saves the collected post data in a database. The input is the acquired post data, and the output is the completion of registration in the database. Specifically, it executes the SQL query "INSERT INTO posts (user_id, content, image_url, video_url, timestamp) VALUES ..." to save the data.

[1381] Step 3: Training the generative model and emotion engine

[1382] The server trains a generative AI model (e.g., GPT-3) and emotion engine based on the posted data stored in the database. The input is past posted data, and the output is the trained generative model and emotion engine. Specifically, the "train.py" script is run to train using the past 5,000 posted data.

[1383] Step 4: Automatic generation of daily postings

[1384] The server uses the trained generative model and emotion engine to automatically generate the message content for the day. The input is the output data of the emotion engine, and the output is the generated message content. Specifically, the "generate.py" script is executed, and a prompt sentence based on the output of the emotion engine is input to the generative AI model to generate text.

[1385] Step 5: Present the message

[1386] The terminal presents the generated call content to the user. The input is the generated call content, and the output is the text to be displayed to the user. Specifically, the terminal calls the API endpoint " / getGeneratedContent" to obtain the generated text and display it to the user.

[1387] Step 6: Edit the message

[1388] The user checks the presented message and makes corrections if necessary. The input is the generated message, and the output is the text corrected by the user. The user makes corrections on the screen and clicks the "submitChanges" button, and the corrections are sent to the server.

[1389] Step 7: Final call processing

[1390] The server performs a final check of the message content amended by the user and posts it to the SNS. The input is the text amended by the user, and the output is a notification that the post has been completed to the SNS. Specifically, it calls "POST / finalPost" to post the amended text to the SNS. It then uses the "POST / notification" endpoint to send a notification that the post has been completed to the user and their device.

[1391] (Application example 2)

[1392] 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."

[1393] Currently, it is difficult for users to think of what to post on social networking services (SNS) every day. It is also time-consuming to generate personalized content based on each user's interests and emotions and share it on other platforms. Furthermore, manual editing is required to improve the quality of the generated content, which often leaves users feeling overwhelmed. The present invention aims to solve these problems and provide users with an easy and natural sharing experience.

[1394] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes means for collecting past posting data of users, means for training a generative model that learns the user's writing style based on the past posting data, and means for automatically generating daily posting content using the generative model. This enables means for generating personalized content based on the user's interests, means for sharing the generated content on other platforms, means for presenting the automatically generated posting content to the user and allowing the user to make corrections, and means for posting the corrected posting content to a predetermined social networking service.

[1395] "User's past posting data" refers to information such as text, images, videos, and the timing of posts made by the user in the past on social networking services.

[1396] A "generative model that learns writing style" is a model that can learn a user's unique writing style from their past posting data and generate new text based on this.

[1397] "Daily posts" refer to the text and content that users post on social networking services on a daily basis.

[1398] "Automatic generation means" refers to a method or device that uses a specific algorithm or program to generate text or content without human intervention.

[1399] "Means for user presentation and modification" refers to a method or interface that allows users to view system-generated content and change it as needed.

[1400] "Means for posting to designated social networking services" refers to a method or mechanism for automatically posting modified content to designated social networking platforms according to schedules or conditions.

[1401] "Means for generating personalized content" refers to algorithms or systems that generate individualized content based on the user's interests and concerns.

[1402] "Means of sharing to other platforms" refers to the methods and mechanisms for posting and distributing the generated content to websites, applications, etc. other than social networking services.

[1403] This invention is a system that automatically generates personalized posts for users by collecting data on past posts on social networking services (SNS), training a generative model based on that data, and combining it with a sentiment analysis engine. This system includes a process that presents the generated posts to the user, and then the user makes any edits before finally posting.

[1404] Components

[1405] The system consists of the following main components:

[1406] 1. Server: Responsible for collecting data, training generative models and emotion engines, automatically generating messages, and generating personalized content.

[1407] 2. Terminal: Presents the generated transmission content to the user and provides a user interface for editing.

[1408] 3. User: A user of the SNS who makes final confirmations and corrections to the content posted.

[1409] Hardware and Software

[1410] The server uses the following technology stack:

[1411] Data collection: Use Python (requests, BeautifulSoup, Tweepy, etc.) to retrieve data using SNS APIs.

[1412] Generative model: We use OpenAI GPT-3 via API to train the generative model.

[1413] Sentiment analysis: Sentiment analysis is performed using Microsoft Azure Cognitive Services.

[1414] Backend: Django is used, and the database is PostgreSQL.

[1415] Front-end: Use React Native to build the user interface.

[1416] Processing flow

[1417] 1. Collection of past posting data

[1418] The server collects users' past posting data through the SNS's API. This data includes the text, images, videos, and timing of posts. The collected data is stored in a database.

[1419] 2. Training the generative model and emotion engine

[1420] The server trains a generative model using OpenAI GPT-3 based on collected past posting data, and also uses Microsoft Azure Cognitive Services to train an emotion engine capable of analyzing users' emotional states.

[1421] 3. Daily posting and personalized content generation

[1422] The server uses a trained generative model and emotion engine to automatically generate personalized content based on the user's interests every day, resulting in natural, useful content tailored to the user.

[1423] 4. User Presentation and Modification

[1424] The generated message is presented to the user via the terminal, who can check the text and make corrections as necessary.

[1425] 5. Final Content Delivery

[1426] The revised content is automatically posted to the specified social networking service and other platforms via the server.

[1427] Specific examples

[1428] If a user frequently posts about the weather, such as "It looks like it's going to rain today. Be careful!", the system will act as follows:

[1429] The server collects past weather-related posting data and uses it to train the generative model and emotion engine.

[1430] The emotion engine analyzes how users feel on rainy days and reflects this in the messages they generate.

[1431] The generated message will be "It looks like it's going to rain today. Take it easy," and will be displayed to the user via their device.

[1432] The user modifies the message to "Let's stay home and relax on a rainy day!", after which the server posts it to social media and other platforms.

[1433] Example prompts for generative AI models

[1434] "Based on your posting history, today we will post the following:

[1435] Morning greeting: "Good morning. Today I have some special news for you."

[1436] About the weather: "The weather is sunny today. Let's enjoy a nice day."

[1437] Sentiment analysis correction:

[1438] "You seem to be tired lately. Let's not push ourselves too hard."

[1439] In this way, personalized, high-quality messages can be sent while reducing the burden on users.

[1440] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1441] Step 1:

[1442] The server uses the SNS API to collect data on users' past posts. The collected data includes the content of the post, images, videos, and the timing of the post. This collected data is stored in a database. The input is the post data obtained from the API, and the output is the formatted data stored in the database.

[1443] Step 2:

[1444] The server uses the previously posted data stored in the database to train a generative model (e.g., OpenAI GPT-3). Specifically, it trains the model to learn the user's writing style from this data. The input is the previously posted data, and the output is the trained generative model.

[1445] Step 3:

[1446] The server uses Microsoft Azure Cognitive Services to train the emotion engine. This emotion engine analyzes emotions in past posting data and learns what emotions appear in what situations. The input is the past posting data, and the output is the trained emotion engine.

[1447] Step 4:

[1448] The server automatically generates daily posts using a trained generative model and emotion engine, taking into account the user's past activities and current emotional state to generate content appropriate for the user. The input is the trained model and emotion engine, and the output is the automatically generated posts.

[1449] Step 5:

[1450] The automatically generated message content is presented to the user via the terminal. The user checks the presented content and makes corrections as necessary. The input is the generated message content, and the output is the message content corrected by the user.

[1451] Step 6:

[1452] The modified message is posted to a specified social networking service via the server. The server posts the generated message to the specified SNS platform. The input is the message modified by the user, and the output is the message posted to the SNS.

[1453] Step 7:

[1454] When personalized content generation is required, the server generates content based on the user's interests. This can be specialized for news articles or content related to a particular topic. The input is the user's past interest data, and the output is personalized content.

[1455] Step 8:

[1456] The generated personalized content is presented to the user through their device and shared to other platforms. The user can review it, modify it as necessary, and then share it across multiple platforms. The input is the personalized content, and the output is the content shared to other platforms.

[1457] 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.

[1458] 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.

[1459] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1460] 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.

[1461] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1462] 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.

[1463] 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).

[1464] 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.

[1465] 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."

[1466] 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.

[1467] 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).

[1468] 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.

[1469] 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.

[1470] 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.

[1471] 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.

[1472] 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.

[1473] 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.

[1474] 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.

[1475] 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.

[1476] 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.

[1477] 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.

[1478] The following is further disclosed regarding the above embodiment.

[1479] (Claim 1)

[1480] A means for collecting past posting data of users;

[1481] a means for training a generative model that learns a user's writing style based on the past posting data;

[1482] means for automatically generating daily message content using the generative model;

[1483] means for presenting the automatically generated message content to a user and allowing the user to make corrections;

[1484] means for posting the corrected message content to a predetermined social networking service;

[1485] A system including:

[1486] (Claim 2)

[1487] 2. The system according to claim 1, further comprising means for scheduling the generated message content so that it is presented to the user at a specific time.

[1488] (Claim 3)

[1489] The system according to claim 1, further comprising means for the generative model to learn about popular topics in society and incorporate the learned topics into the generated communication content.

[1490] (Claim 4)

[1491] 2. The system according to claim 1, further comprising means for including an image in the automatically generated message content and automatically generating a copy of the message content that matches the image content.

[1492] (Claim 5)

[1493] 10. The system of claim 1, further comprising means for simultaneously posting the modified submission to multiple social networking accounts of the user.

[1494] "Example 1"

[1495] (Claim 1)

[1496] A means for collecting past posting data of users;

[1497] a means for training a generative model that learns a user's writing style based on the past posting data;

[1498] means for automatically generating daily message content using the generative model;

[1499] means for presenting the automatically generated message content to a user and allowing the user to make corrections;

[1500] means for posting the corrected message content to a predetermined social networking service;

[1501] A system including:

[1502] (Claim 2)

[1503] 2. The system according to claim 1, further comprising means for scheduling the generated message content so that it is presented to the user at a specific time.

[1504] (Claim 3)

[1505] The system according to claim 1, further comprising means for the generative model to learn about popular topics in society and incorporate the learned topics into the generated communication content.

[1506] "Application Example 1"

[1507] (Claim 1)

[1508] A means for collecting past posting data of users;

[1509] a means for training a generative model that learns a user's writing style based on the past posting data;

[1510] means for automatically generating daily message content using the generative model;

[1511] means for presenting the automatically generated message content to a user and allowing the user to make corrections;

[1512] means for posting the corrected transmission content to a predetermined communication network;

[1513] means for automatically generating the transmitted content as an advertisement for a product or service;

[1514] A system including:

[1515] (Claim 2)

[1516] 2. The system according to claim 1, further comprising means for scheduling the generated message content so that it is presented to the user at a specific time.

[1517] (Claim 3)

[1518] The system according to claim 1, further comprising means for the generative model to learn about popular topics in society and incorporate the learned topics into the generated communication content.

[1519] "Example 2: Combining Emotion Engines"

[1520] (Claim 1)

[1521] A means of collecting past posting data;

[1522] means for training a generative model and an emotion engine based on the past posting data;

[1523] means for automatically generating daily messages using the generative model and an emotion engine;

[1524] means for presenting the generated transmission to a user and allowing the user to modify it;

[1525] means for posting the corrected message content to a predetermined social networking service;

[1526] A system including:

[1527] (Claim 2)

[1528] 10. The system of claim 1, further comprising means for scheduling the generated message content to be presented to the user at a specific time.

[1529] (Claim 3)

[1530] The system according to claim 1, further comprising means for the generative model to learn about popular topics in society and incorporate the learned topics into the generated communication content.

[1531] "Application example 2 when combining emotion engines"

[1532] (Claim 1)

[1533] A means for collecting past posting data of users;

[1534] a means for training a generative model that learns a user's writing style based on the past posting data;

[1535] means for automatically generating daily message content using the generative model;

[1536] means for presenting the automatically generated message content to a user and allowing the user to make corrections;

[1537] means for posting the corrected message content to a predetermined social networking service;

[1538] A means for generating personalized content based on the user's interests;

[1539] A way to share the generated content to other platforms,

[1540] A system including:

[1541] (Claim 2)

[1542] 2. The system according to claim 1, further comprising means for scheduling the generated message content so that it is presented to the user at a specific time.

[1543] (Claim 3)

[1544] The system according to claim 1, further comprising means for the generative model to learn about popular topics in society and incorporate the learned topics into the generated communication content. [Explanation of symbols]

[1545] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for collecting past posting data of users; a means for training a generative model that learns a user's writing style based on the past posting data; means for automatically generating daily message content using the generative model; means for presenting the automatically generated message content to a user and allowing the user to make corrections; means for posting the corrected message content to a predetermined social networking service; A system including:

2. 2. The system of claim 1, further comprising means for scheduling the generated message content to be presented to the user at a specific time.

3. The system according to claim 1 , further comprising means for the generative model to learn popular topics in society and incorporate the learned topics into the generated communication content.

4. The system according to claim 1, further comprising means for including an image in the automatically generated message content and automatically generating a copy of the message content that matches the image content.

5. The system of claim 1 , further comprising means for simultaneously posting the modified submission to multiple social networking accounts of the user.

Images