System

Abstract

To provide a system.SOLUTION: A system includes the means for: loading acquisition success instances of a specific product contributed to an information sharing network service; analyzing the success instances loaded by the loading means; extracting contributions related to the success instances from analysis results of the analyzing means; saving the success instances extracted by the extracting means in a database; and providing the success instances saved in the saving means at a request from a user.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Although success stories of acquiring specific products are posted on information-sharing social networking sites, there is an issue in that this information is not being fully utilized. Also, there is no way to post this information regularly every day, so information sharing is insufficient. [Means for solving the problem]

[0005] To solve this problem, we developed a system that provides a means to read success stories of specific products posted on an information-sharing SNS, a means to generate a program that posts the read success stories every day, and a means to operate the generated program in a specific role. This will enable information on success stories to be shared efficiently and promote their use. [Brief explanation of the drawings]

[0006] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 2 is a sequence diagram showing a flow of processing in the data processing system according to the first embodiment of the first form example. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Embodiment 1. [Figure 13] FIG. 10 is a sequence diagram showing a processing flow of a data processing system in a second embodiment of the second form example. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Embodiment Example 2. [Figure 15] FIG. 10 is a sequence diagram showing the flow of processing in a data processing system according to a third embodiment of the third embodiment. [Figure 16]FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Embodiment 3. [Figure 17] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the first embodiment of the first form example when an emotion engine is combined. [Figure 18] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when an emotion engine is combined. [Figure 19] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the second embodiment of the second form example when an emotion engine is combined. [Figure 20] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 of Form Example 2 when an emotion engine is combined. [Figure 21] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in the third embodiment of the third form example when an emotion engine is combined. [Figure 22] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 3 of Form Example 3 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0007] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

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

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

[0010] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0011] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0012] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0013] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0014] [First embodiment]

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

[0016] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0017] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0018] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0019] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0020] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0021] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

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

[0023] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0024] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0025] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

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

[0027] "Example 1"

[0028] One embodiment of the present invention includes a means for reading success stories of specific products posted on an information-sharing social networking site. Specifically, a program is implemented to extract success stories of specific products from social networking sites used by experts on the product. This program analyzes keywords and hashtags in the posted content and automatically extracts posts related to the success stories.

[0029] "Example 2"

[0030] Furthermore, there is a means to generate a program that posts the read success stories every day. Specifically, a program is implemented that generates new posting content based on the extracted success stories. This program automatically generates new posting content based on the content of the success stories and posts it periodically.

[0031] "Example 3"

[0032] There is also a way to make the generated program act as a specific role. Specifically, a function has been implemented to make the generated program act as an experienced crew member. This function allows the program to post success stories as an experienced crew member. This allows for efficient information sharing on the information-sharing SNS.

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

[0034] "Example 1"

[0035] Step 1: Obtain posts from social media used by experts on a specific product. In this step, we use an API to obtain post data from social media.

[0036] Step 2: Extract success stories of product acquisition from the acquired posts. In this step, keywords and hashtags in the post content are analyzed and posts related to success stories are automatically extracted.

[0037] "Example 2"

[0038] Step 1: Generate new post content based on the extracted success stories. In this step, new post content is automatically generated based on the content of the success stories.

[0039] Step 2: Post the generated content on a regular basis. In this step, the generated content is posted to SNS on a regular basis.

[0040] "Example 3"

[0041] Step 1: Execute the generated program as a specific role. In this step, the generated program is executed as a skilled crew member.

[0042] Step 2: The program acting as a crew posts a success story. In this step, the program acts as an experienced crew and posts a success story.

[0043] Example 1

[0044] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0045] In conventional information sharing network services, it has been difficult to efficiently collect, analyze, and provide users with success stories of specific product acquisitions. In particular, advanced analytical techniques and efficient data management are required to extract useful information from network services used by experts. Therefore, there is a need to quickly and accurately provide users with the success stories they need.

[0046] 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.

[0047] In this invention, the server includes means for reading success stories of specific products posted on an information sharing network service, means for analyzing the read success stories, means for extracting posts related to the success stories from the analysis results, means for saving the extracted success stories in a database, and means for providing the saved success stories in response to user requests. This makes it possible to efficiently collect and analyze success stories related to specific products and provide them to users quickly and accurately.

[0048] An "information sharing network service" is an online platform that allows users to share information and interact via the Internet.

[0049] "Specific product" refers to a specific good or service sold in a specific market or application.

[0050] "Success stories" are information that shows specific cases or experiences where a particular product has been used successfully.

[0051] "Means of reading" refers to the methods and technologies for obtaining data from an information sharing network service and incorporating it into the system.

[0052] "Means of analysis" refers to methods and techniques for analyzing acquired data and extracting useful information.

[0053] "Means of extraction" refers to methods and techniques for selecting information that meets specific conditions from the analysis results.

[0054] "Means of storing in a database" refers to the methods and techniques used to systematically manage extracted information and store it for later use.

[0055] "Means for providing information in response to a user's request" refers to methods and technologies for retrieving and providing stored information in response to a user's request.

[0056] "Natural language processing technology" refers to technology that enables computers to understand and process human language.

[0057] The present invention provides a system for efficiently collecting, analyzing, and providing to users success stories of specific products posted on an information sharing network service. Specific embodiments of this system will be described below.

[0058] First, the server collects posts related to a specific product from an information-sharing network service (e.g., a social networking platform). To do this, it uses the Python libraries Tweepy and BeautifulSoup to retrieve posts containing specific hashtags (e.g., "product name" or "success stories").

[0059] Next, the server analyzes the collected post data using natural language processing (NLP) technology. NLP libraries such as NLTK and spaCy are used. This allows keywords and hashtags to be extracted from the post content, and posts related to success stories to be identified. For example, keywords such as "success," "acquisition," and "case study" can be extracted from the post content.

[0060] The server automatically extracts posts related to success stories based on the analysis results. Specifically, it uses the extracted keywords and hashtags to filter posts that correspond to success stories. For example, it selects posts that include "success story" or "product name."

[0061] The extracted posts of success stories are stored in a database by the server. The database uses MySQL (registered trademark) or PostgreSQL. The data stored includes information such as the post content, poster, and posting date and time. For example, the data is stored using the MySQL INSERT statement.

[0062] When a user wants to know about success stories of a specific product, they send a request from their device to the server. The request includes the product name and related keywords. For example, a user might request, "Please tell me about success stories of product A."

[0063] The server searches the database for relevant success stories and returns them to the device. The search is performed using the SQL SELECT statement. The user can view the success stories on the device. For example, the server sends a post saved as "Product A success story" to the device.

[0064] As a concrete example, the following is an example of a prompt sentence to be input to the generative AI model.

[0065] Example prompt sentence:

[0066] "Please tell us about success stories for a specific product. Please use data collected from social media to extract posts related to success stories."

[0067] When this prompt sentence is input into the generative AI model, the model analyzes data collected from social media, extracts posts related to success stories, and provides them to the user.

[0068] The above is a specific embodiment for carrying out the present invention.

[0069] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0070] Step 1:

[0071] The server collects posts related to a particular product from an information sharing network service.

[0072] Input: Post data obtained from the API of the social media platform.

[0073] Data processing: Use Python libraries (Tweepy and BeautifulSoup) to filter posts containing specific hashtags (e.g., "product name" or "success story").

[0074] Output: The filtered post data.

[0075] Specific operation: The server calls the API of the social networking site to retrieve posts containing a specific hashtag. The retrieved posts are then filtered to select only those related to a specific product.

[0076] Step 2:

[0077] The server analyzes the collected posting data using natural language processing (NLP) technology.

[0078] Input: Filtered post data.

[0079] Data processing: Use NLP libraries (NLTK and spaCy) to extract keywords and hashtags from the post content.

[0080] Output: Extracted keywords and hashtags.

[0081] Specific operation: The server analyzes the collected posting data and extracts keywords such as "success," "acquisition," and "case study" from the posting content.

[0082] Step 3:

[0083] The server automatically extracts posts related to success stories based on the analysis results.

[0084] Input: Extracted keywords and hashtags.

[0085] Data processing: Using the extracted keywords and hashtags, posts that correspond to success stories are filtered.

[0086] Output: Post data related to the success story.

[0087] Specific operation: Based on the analysis results, the server selects posts containing specific keywords or hashtags and extracts posts related to success stories.

[0088] Step 4:

[0089] The server stores the extracted success story posts in a database.

[0090] Input: Post data related to the success story.

[0091] Data processing: Save information such as post content, poster, and posting date and time in a database (MySQL or PostgreSQL).

[0092] Output: Success story submission data stored in the database.

[0093] Specific operation: The server saves the extracted success story posts in the database using the MySQL INSERT statement.

[0094] Step 5:

[0095] When a user wants to know about success stories of a particular product, the user sends a request from the terminal to the server.

[0096] Input: User request (product name and related keywords).

[0097] Data processing: Analyze the request content and search for relevant success stories.

[0098] Output: The request data to the server.

[0099] Specific operation: The user uses the terminal to send a request saying, "Please tell me some success stories about product A."

[0100] Step 6:

[0101] The server searches the database for the relevant success story and returns it to the terminal.

[0102] Input: User request data.

[0103] Data processing: Use the SQL SELECT statement to search the database for relevant success stories.

[0104] Output: Success story submission data as search results.

[0105] Specific operation: The server searches the database based on the user's request and sends the post saved as "Product A success story" to the terminal.

[0106] Step 7:

[0107] The user views the success stories on the terminal.

[0108] Input: Successful case submission data returned from the server.

[0109] Data processing: None.

[0110] Output: Success story submission data displayed on the device.

[0111] Specific operation: The user views the success story posts sent from the server on the terminal.

[0112] (Application example 1)

[0113] Next, a description will be given of Application Example 1 of Embodiment Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0114] Conventional information-sharing SNSs lack a means to efficiently collect and provide users with success stories about specific products. This means that users have to spend a lot of time and effort to find information that will help them when purchasing a product. Furthermore, since there is no function to automatically display success stories, users may miss out on the information they need. These issues need to be resolved.

[0115] 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.

[0116] In this invention, the server includes means for reading success stories of specific products posted on an information-sharing SNS, means for generating a program for posting the read success stories daily, means for running the generated program as a specific role, means for automatically displaying success stories related to the specific product, means for acquiring and analyzing HTML from the search result page of the SNS, and means for analyzing the posted content using regular expressions to extract posts related to the success stories. This allows users to efficiently collect success stories and easily obtain information that will be useful when purchasing a product.

[0117] An "information sharing SNS" is an online platform that allows users to share information with each other.

[0118] A "specific product" is a specific good or service sold in a particular market or for a particular purpose.

[0119] "Acquisition success stories" are cases or experiences of success when purchasing or using a particular product.

[0120] A "means for reading" is a method or device for obtaining information and converting it into a format that can be used within the system.

[0121] A "daily posting program" is software that automatically posts specific information to social media every day.

[0122] A "specific role" is a role assigned to perform a specific function or task within the system.

[0123] An "automatic display means" is a method or device for displaying information without requiring user interaction.

[0124] A "search results page" is a page that lists results generated by a search engine based on specific keywords or criteria.

[0125] "Means for acquiring and analyzing HTML" refers to a method or device for acquiring the HTML code of a web page and analyzing its content.

[0126] A "regular expression parser" is a method or device for analyzing text based on specific patterns.

[0127] The "means for extracting posts related to success stories" refers to a method or device for selecting and extracting posts that include information related to success stories.

[0128] A system for implementing this invention includes means for reading success stories of acquiring a specific product posted on an information-sharing SNS, means for generating a program that posts the read success stories daily, means for operating the generated program as a specific role, means for automatically displaying success stories related to a specific product, means for obtaining and analyzing HTML from the search results page of the SNS, and means for analyzing the posted content using regular expressions and extracting posts related to the success stories.

[0129] The server first accesses the information-sharing social networking site and searches for posts related to a specific product. Specifically, it retrieves HTML from the search results page of the social networking site and analyzes it using a library such as BeautifulSoup. Through this analysis, it extracts the content of the posts and uses regular expressions to select posts related to success stories.

[0130] The server then generates a program that automatically posts selected success stories daily, and the program acts as a specific role, automatically displaying related success stories when a user views a specific product page.

[0131] When a user searches for a specific product, the server displays success stories related to that product, allowing the user to easily obtain information that will be helpful when making a purchase.

[0132] As a concrete example, if a user searches for a "specific product name," by inputting the following prompt sentence into the generative AI model, success stories on social media can be automatically extracted and provided to the user.

[0133] Example prompt sentence:

[0134] Please extract successful examples of acquiring "specific product names" from social media.

[0135] This system allows users to efficiently collect success stories and easily obtain information that can be used as reference when purchasing products. The hardware used includes a server and the user's smartphone, and the software used includes Python, BeautifulSoup, and requests.

[0136] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0137] Step 1:

[0138] The server accesses the information sharing SNS and searches for posts related to a specific product.

[0139] Input: Specific product name

[0140] Output: HTML data of social media search results page

[0141] Specific operation: The server uses the social networking service's search API to search for posts related to a specific product name and retrieves the results in HTML format.

[0142] Step 2:

[0143] The server analyzes the acquired HTML data.

[0144] Input: HTML data of the search results page of the social networking site

[0145] Output: Text data of the post

[0146] Specific operation: The server parses the HTML data using the BeautifulSoup library and extracts the text data of the post content.

[0147] Step 3:

[0148] The server analyzes the content of the posts using regular expressions and extracts posts related to success stories.

[0149] Input: Text data of post content

[0150] Output: A list of posts related to the success story

[0151] Specific operation: The server analyzes the content of posts using regular expressions and extracts posts containing keywords such as "success," "achievement," and "acquisition."

[0152] Step 4:

[0153] The server generates a program that automatically posts extracted success stories every day.

[0154] Input: List of posts related to success stories

[0155] Output: Daily posting program

[0156] Specific operation: Based on the list of success stories, the server generates a program to automatically post to SNS every day.

[0157] Step 5:

[0158] The server runs the generated program as a specific role.

[0159] Input: Daily posting program

[0160] Output: A program that acts as a specific role

[0161] Specific operation: The server runs the generated program and automatically posts success stories to SNS every day.

[0162] Step 6:

[0163] When a user views a particular product page, the server automatically displays related success stories.

[0164] Input: User browsing information, list of posts related to success stories

[0165] Output: Display success stories

[0166] Specific operation: When a user views a specific product page, the server sends information to the user's device to automatically display related success stories.

[0167] Example 2

[0168] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0169] In conventional information sharing network services, it was difficult to efficiently collect success stories of specific products, automatically generate new posts based on them, and post them regularly. In addition, manual posting required time and effort, making it difficult to continuously disseminate information.

[0170] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for reading success stories of specific product acquisition posted on an information sharing network service, a means for generating a prompt sentence based on the read success story, a means for inputting the generated prompt sentence into a generative AI model to generate new posting content, a means for saving the generated posting content in a database, and a means for periodically posting the saved posting content. This enables automatic generation and periodic posting of new posting content based on success stories.

[0171] An "information sharing network service" is an online platform that allows users to share information and communicate.

[0172] "Specific product" refers to a specific good or service sold in a specific market or application.

[0173] "Acquisition success stories" refer to specific cases or episodes in which a particular product has achieved success in the market.

[0174] A "prompt sentence" is text to be input into a generative AI model, and is a sentence that contains the key points of a successful case.

[0175] A "generative AI model" is a model for generating text using artificial intelligence, such as one that uses natural language processing technology.

[0176] "New posts" refers to new text content generated by the generative AI model based on success stories.

[0177] A "database" is a system for systematically storing and managing information.

[0178] "Means for periodic posting" means a feature that automatically posts saved posts to an online platform at regular intervals.

[0179] The present invention relates to a system that efficiently collects successful cases of acquiring specific products posted on an information sharing network service, automatically generates new posting content based on the collected information, and posts the content periodically.

[0180] The server first reads the success case data provided by the user. This data is assumed to be stored in a text file or database. For example, the server reads the data from a file called success_cases.txt.

[0181] Next, the server generates a prompt sentence to be input to the generative AI model based on the content of the read success case. The prompt sentence is designed to include the key points of the success case. As a concrete example, the following prompt sentence can be generated:

[0182] Example prompt sentence:

[0183] "Below is an example of a company that successfully implemented a new marketing strategy. Please use this example to generate new content for your posts."

[0184] Success stories include:

[0185] "Company A implemented a new marketing strategy that leveraged social media. This strategy significantly improved customer engagement and increased sales by 20%."

[0186] The server inputs the generated prompt into a generative AI model (e.g., OpenAI's GPT-3™). The generative AI model generates new posts based on the prompt. Specific examples of generated posts include:

[0187] An example of the generated post:

[0188] "The key point to learn from Company A's success story is that by effectively using social media, you can increase engagement with customers. With this strategy, Company A was able to increase sales by 20%. Why not try implementing a marketing strategy that utilizes social media in your own business?"

[0189] The generated post content is saved in a database by the server, along with metadata such as the posting date and time and the ID of the related success story.

[0190] Finally, the server automatically posts the saved content to social media platforms or blogs periodically (e.g., daily) by connecting to each platform using an API. For example, posts can be made using the Twitter API.

[0191] In this way, the server automatically generates new posting content based on success stories and posts it periodically, reducing the user's workload and supporting continuous information dissemination.

[0192] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0193] Step 1: Load the success story data

[0194] The server reads the success case data provided by the user. This data is assumed to be stored in a text file or database. For example, data is read from a file called success_cases.txt. The input is the text data of the success case, and the output is the content of the success case stored in memory.

[0195] Step 2: Generate a prompt statement

[0196] The server generates a prompt sentence to be input to the generative AI model based on the content of the read success story. The prompt sentence is designed to include the key points of the success story. The input is the text data of the success story, and the output is the generated prompt sentence. Specifically, it extracts the key points of the success story and creates a prompt sentence that includes them.

[0197] Step 3: Enter a prompt into the generative AI model to generate new post content

[0198] The server inputs the generated prompt text into a generative AI model (for example, OpenAI's GPT-3). The generative AI model generates new post content based on the prompt text. The input is the prompt text, and the output is the generated new post content. Specifically, the server sends the prompt text to the generative AI model and receives the generated text.

[0199] Step 4: Save the generated post to the database

[0200] The server saves the new posts obtained from the generative AI model in a database. When saving, it also saves metadata such as the posting date and time and the ID of the related success story. The input is the generated post and metadata, and the output is the post saved in the database. Specifically, it connects to the database and inserts the post and metadata.

[0201] Step 5: Regularly post content to social media and your blog

[0202] The server automatically posts the saved posts to social media platforms and blogs periodically (for example, daily). To do this, it uses an API to connect to each platform and posts. The input is the post retrieved from the database, and the output is the post on the social media platform or blog. Specifically, it uses an API to connect to the platform and sends the post.

[0203] In this way, the server automatically performs a series of processes, saving the user time and effort while supporting continuous information dissemination.

[0204] (Application example 2)

[0205] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0206] Conventional information sharing networks lack a means to efficiently collect success stories of specific products and automatically generate and periodically distribute new posts based on them. This makes it difficult to continuously provide content that users are interested in, resulting in a decline in the freshness and usefulness of information. Furthermore, there is a need for a method to reduce the manual posting work while maintaining the quality of the generated content.

[0207] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0208] In this invention, the server includes a means for reading success stories of specific products posted on the information sharing network, a means for generating a program using a generative AI model that generates new posting content based on the read success stories, and a means for periodically posting the generated program. This makes it possible to automatically generate and periodically distribute fresh and useful content that interests users.

[0209] An "information sharing network" is an online platform where users can post information and share it with other users.

[0210] "Specific product" refers to a specific good or service used in a particular market or application.

[0211] A "success story" is a documented case that documents the success or results achieved by using a particular product.

[0212] A "reading means" is a device or program that has the function of obtaining specific data from an information sharing network and converting it into a format that can be used within the system.

[0213] A "generative AI model" is an algorithm or program that uses artificial intelligence techniques to generate new text or content.

[0214] A "program generating means" is a device or software that has the function of automatically creating a program with a specific function based on specific input data.

[0215] A "means for posting periodically" is a device or program that has the function of automatically posting content at regular time intervals.

[0216] An "expert" refers to an individual or organization with advanced knowledge or skills in a particular field.

[0217] A "prompt" is an instruction or question that is input into a generative AI model to determine the direction and content of the generated content.

[0218] The system for implementing this invention reads successful cases of acquiring specific products posted on an information sharing network, generates new posting content based on the cases, and periodically distributes the content. A specific embodiment of the system is described below.

[0219] The server first collects success stories for a specific product from the information sharing network. This collection can be done using APIs or web scraping technology. The collected success stories are stored in a database for later processing.

[0220] The server then uses a generative AI model to generate new posts based on the collected success stories. A suitable model for this purpose is the GPT-2 model using Hugging Face's Transformers library. The prompt text to be input to the generative AI model is in the following format:

[0221] Please generate new posts based on the following success stories:

[0222] Success Story 1: A company implemented a new marketing strategy and saw a 20% increase in sales.

[0223] Success Story 2: A startup developed an innovative product and quickly gained market share.

[0224] Success Story 3: A nonprofit organization ran an effective campaign and raised a lot of donations.

[0225] By inputting this prompt into the generative AI model, new posts are generated, which are then stored in the database and distributed periodically.

[0226] The server has a scheduling function to distribute generated posts periodically. For example, you can use the Python schedule library to automatically distribute new posts at a specific time each day.

[0227] This system ensures that users always receive fresh and useful content, and improves operational efficiency by reducing manual posting work.

[0228] As a specific example, a company can collect success stories of how they increased sales by 20% after implementing a new marketing strategy, and then use a generative AI model to generate new posts based on those stories. These new posts are automatically distributed at 10:00 every day, ensuring that users always have access to useful information based on the latest success stories.

[0229] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0230] Step 1:

[0231] The server collects success stories for specific products from the information sharing network. Specifically, it obtains success story data using APIs and web scraping technology. The input is the URL or API endpoint of the information sharing network, and the output is the success story data. The data is obtained in JSON or text format and stored in a database.

[0232] Step 2:

[0233] The server reads the collected success stories from the database. The input is a database query and the output is a list of success stories. The success stories retrieved from the database are loaded into memory for use in the next step.

[0234] Step 3:

[0235] The server generates a prompt based on the success stories it has read. The input is a list of success stories, and the output is a prompt to be input to the generative AI model. Specifically, it formats the success stories into text and creates a prompt like this:

[0236] Please generate new posts based on the following success stories:

[0237] Success Story 1: A company implemented a new marketing strategy and saw a 20% increase in sales.

[0238] Success Story 2: A startup developed an innovative product and quickly gained market share.

[0239] Success Story 3: A nonprofit organization ran an effective campaign and raised a lot of donations.

[0240] Step 4:

[0241] The server generates new posts using a generative AI model. The input is the prompt text, and the output is the generated post. Specifically, using Hugging Face's Transformers library, the server inputs the prompt text into a GPT-2 model to generate new text.

[0242] Step 5:

[0243] The server stores the generated posts in a database. The input is the generated posts, and the output is the posts stored in the database. The stored posts are distributed periodically in a later step.

[0244] Step 6:

[0245] The server periodically distributes the generated posts using a scheduling function. The input is the posts stored in the database, and the output is the posts to the information sharing network. Specifically, it uses the Python schedule library to automatically distribute new posts at a specific time every day.

[0246] Example 3

[0247] Next, a description will be given of a third embodiment of the third embodiment. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0248] In information-sharing social networking sites, there is a need for experts in specific fields to efficiently share success stories. However, manual posting takes time and effort, which can delay information sharing. It is also difficult to maintain a consistent quality of the content posted. To solve these issues, a system is needed that can efficiently and automatically post success stories.

[0249] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0250] In this invention, the server includes means for a user to input a prompt sentence, means for sending the prompt sentence to a generative AI model, means for the generative AI model to generate a post content, means for receiving the generated post content, means for sending the post content to an information-sharing SNS, and means for the information-sharing SNS to display the post. This makes it possible to automatically generate high-quality post content based on the prompt sentence entered by the user and efficiently post it to the information-sharing SNS.

[0251] A "user" is a person or organization that uses the system to input prompt text and gives instructions for generating content to be posted on the information-sharing SNS.

[0252] A "prompt sentence" is an instruction sentence that a user inputs to a generative AI model, and is a sentence that contains information that will form the basis of the generated post content.

[0253] A "generative AI model" is an artificial intelligence model that automatically generates appropriate post content based on a prompt entered by the user.

[0254] "Post content" refers to text and information generated by a generative AI model and posted to an information-sharing SNS.

[0255] An "information sharing SNS" is a social networking service used by experts in a particular field to share information and success stories.

[0256] The "server" is a computer system that receives prompt text from the user, sends it to the generative AI model, and posts the generated post content to an information-sharing SNS.

[0257] "Means" refers to a method or device for realizing a specific function or role.

[0258] This invention is a system for enabling experts in a specific field to efficiently share success stories on an information-sharing SNS. A specific embodiment of this system will be described below.

[0259] First, the user uses a device (such as a PC or smartphone) to access a dedicated input form. This input form is provided as an application that runs on a web browser. The user enters a prompt into the input form and clicks the submit button. For example, the user enters the following prompt:

[0260] "Submit a success story about Project X, where the entire team worked remotely and achieved their goal ahead of schedule. The use of a task management tool was particularly effective."

[0261] Next, the server receives the prompt text sent from the device. The server sends this prompt text to an API endpoint of a generative AI model (e.g., GPT-4 (registered trademark)). The generative AI model analyzes the prompt text and generates appropriate post content. The generated post content is sent back to the server.

[0262] The server receives the post content returned from the generative AI model and converts it into a data format suitable for posting to an information-sharing SNS. Examples of information-sharing SNS include Slack and MICROSOFT (registered trademark) TEAMS (registered trademark). The server uses the API of the information-sharing SNS to send the generated post content to a specific channel. The API request includes authentication information along with the post content.

[0263] Finally, the information-sharing SNS displays the posted content received from the server on the specified channel, allowing other users on the SNS to view the posted content in real time.

[0264] This system allows users to automatically generate high-quality posts by simply entering a prompt, enabling them to post efficiently to the information-sharing SNS. This allows information to be shared quickly and effectively. The flow of the specific processing in Example 3 will be described with reference to FIG. 15.

[0265] Step 1:

[0266] The user enters a prompt statement.

[0267] The user opens a browser on their device, accesses a dedicated input form, and writes, "Please post a success story about Project X. In Project X, the entire team worked remotely and achieved their goal earlier than expected. The use of a task management tool was particularly effective," and clicks the submit button.

[0268] Input: prompt statement

[0269] Output: Prompt sent from terminal to server

[0270] Step 2:

[0271] The server sends a prompt to the generative AI model.

[0272] The server receives the prompt sent from the device and sends it to the API endpoint of the generative AI model (e.g., GPT-4).

[0273] Input: The prompt received from the terminal

[0274] Output: Sending a prompt to the generative AI model

[0275] Step 3:

[0276] A generative AI model generates the post content.

[0277] The generative AI model generates post content based on the prompt it receives. For example, the generative AI model might generate a post like, "Sharing a success story about Project X! In this project, everyone worked remotely and achieved the goal earlier than expected. In particular, the use of a task management tool was very effective. We appreciate the efforts and cooperation of everyone on the team!"

[0278] Input: prompt statement

[0279] Output: Generated post

[0280] Step 4:

[0281] The server receives the generated post.

[0282] The server receives the post content generated by the generative AI model and converts it into a data format suitable for posting to an information-sharing SNS.

[0283] Input: Generated post content from a generative AI model

[0284] Output: Post content converted into a data format suitable for posting to information-sharing SNS

[0285] Step 5:

[0286] The server sends the post to the information-sharing SNS.

[0287] The server uses the API of an information sharing SNS (e.g., Slack) to send the generated post content to a specific channel. The API request includes authentication information along with the post content.

[0288] Input: Post content converted into data format

[0289] Output: Sending the content posted to an information sharing SNS

[0290] Step 6:

[0291] Information sharing social networking sites display posts.

[0292] The information-sharing SNS displays the posted content received from the server on the specified channel, allowing other users on the SNS to view the posted content in real time.

[0293] Input: Post content received from the server

[0294] Output: Display of posts on information-sharing SNS

[0295] (Application example 3)

[0296] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0297] In order to improve work efficiency in logistics centers, it is important to share the success stories and best practices of experienced workers. However, manually collecting and sharing this information takes time and effort, and is inefficient. It is also difficult to maintain the quality and consistency of the information. Therefore, there is a need for a system that can efficiently and automatically generate and share success stories.

[0298] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0299] In this invention, the server includes means for reading success stories of specific product acquisitions posted on an information sharing network, means for generating a program that posts the read success stories daily, means for running the generated program as a specific role, means for automatically generating success stories using a generative AI model, and means for posting the generated success stories so that other workers can view them. This enables efficient and automatic generation and sharing of success stories in a logistics center.

[0300] An "information sharing network" is an online platform for sharing information about specific products and services.

[0301] "Specific products" refers to the goods and items handled at the distribution center.

[0302] A "success story" is a specific example that demonstrates efficient work procedures or best practices for a particular product.

[0303] A "means of reading" is a function or process for obtaining specific information from an information sharing network.

[0304] A "daily posting program" is software for posting specific information on an online platform on a regular basis.

[0305] A "generating means" is a function or process that produces new programs or data for a specific purpose.

[0306] A "specific role" is a role for performing a specific function or task within the system.

[0307] A "generative AI model" is a model designed to accomplish a specific task using artificial intelligence.

[0308] "Means of automatic generation" refers to functions or processes that use artificial intelligence to automatically generate specific information or data.

[0309] "Means of posting" refers to the functions and processes for publishing generated information on an online platform.

[0310] "Skilled workers" refers to workers with high skills and experience at logistics centers.

[0311] A system for implementing this invention includes means for reading success stories of acquiring a specific product posted on an information sharing network, means for generating a program that posts the read success stories daily, means for operating the generated program as a specific role, means for automatically generating success stories using a generative AI model, and means for posting the generated success stories so that other workers can view them.

[0312] System configuration

[0313] Hardware

[0314] Server: A computer that retrieves data from an information-sharing network and runs generative AI models.

[0315] Smartphone: A device that allows workers to view and post success stories.

[0316] software

[0317] Python: A programming language for running generative AI models.

[0318] OpenAI API: A service that provides generative AI models.

[0319] Processing flow

[0320] 1. Information loading: The server loads the success stories of specific products posted on the information sharing network.

[0321] 2. Prompt sentence generation: The server generates prompt sentences related to specific tasks at the logistics center.

[0322] 3. Calling the generative AI model: The server uses the OpenAI API to input prompt statements into the generative AI model and generate success stories.

[0323] 4. Posting success stories: The server posts the generated success stories to the information sharing network so that other workers can view them.

[0324] Specific examples

[0325] For example, when sorting packages at a logistics center, a generative AI model can generate success stories like the following:

[0326] "When sorting packages, we can process larger packages first, followed by smaller packages, making efficient use of workspace. We can also use barcode scanners to manage inventory in real time, reducing errors."

[0327] Prompt Sentence Examples

[0328] "Please tell us some success stories about efficient package sorting methods in distribution centers."

[0329] "What are some best practices for speeding up picking operations?"

[0330] In this way, by sharing the generated success stories within the application, the work efficiency of the entire logistics center can be improved.

[0331] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0332] Step 1:

[0333] The server accesses the information sharing network and loads the acquisition success stories for the particular product.

[0334] Input: Information sharing network URL and authentication information.

[0335] Data processing: Obtaining success story data from the network and converting it into the required format.

[0336] Output: Success story data.

[0337] Step 2:

[0338] The server generates a program to post daily based on the success stories it has read.

[0339] Input: Success story data.

[0340] Data calculation: Analyze data from success stories and generate a posting schedule.

[0341] Output: A program that posts daily.

[0342] Step 3:

[0343] The server runs the generated program as a specific role.

[0344] Input: A program that posts daily.

[0345] Data calculation: Run the program and post success stories at the specified time.

[0346] Output: Posted success stories.

[0347] Step 4:

[0348] The server automatically generates success stories using a generative AI model.

[0349] Input: prompt statement.

[0350] Data calculation: Using the OpenAI API, prompt sentences are input to the generative AI model to generate success stories.

[0351] Output: Generated success stories.

[0352] Step 5:

[0353] The server posts the generated success stories to an information sharing network so that other workers can view them.

[0354] Input: Generated success stories.

[0355] Data processing: Convert success stories into a posting format for the information sharing network.

[0356] Output: Success stories posted to an information sharing network.

[0357] 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.

[0358] "Example 1"

[0359] We will explain an example of a system using an emotion engine. In this system, a program that posts success stories every day adjusts the content of the posts using an emotion engine that recognizes the user's emotions. Specifically, the emotion engine analyzes the emotions in the user's SNS posts and optimizes the content of the posts based on the analysis results. For example, if a user's post expresses joy or excitement, the emotion engine uses that information to select success stories that evoke similar emotions and generate post content. This enables posts to be made appropriately in accordance with the user's emotions, making it easier to attract the user's attention.

[0360] "Example 2"

[0361] An example of an embodiment in which an emotion engine analyzes emotions from a user's SNS posts will be described. In this embodiment, the emotion engine analyzes emotions from a user's SNS posts. Specifically, the emotion engine uses natural language processing technology to extract emotions from the text of a user's post. For example, the emotion of "joy" is extracted from a post such as "I'm so happy to have gotten this product!" The emotional information extracted in this way is used to generate the post content.

[0362] "Example 3"

[0363] An example of optimizing the posted content based on the emotions analyzed by the emotion engine will be described.

[0364] In this form, the emotion engine optimizes the content of posts based on the analyzed emotions. Specifically, the emotion engine generates post content that users can easily empathize with based on the analyzed emotional information. For example, if a user expresses the emotion of "joy," the emotion engine uses that information to select success stories that enhance the "joy" and generates post content. This makes it possible to post appropriate content based on the user's emotions, making it easier to attract the user's attention.

[0365] The processing flow of each embodiment will be described below.

[0366] "Example 1"

[0367] Step 1: Collect users' social media posts.

[0368] Step 2: Analyze user emotions from the collected posts using an emotion engine.

[0369] Step 3: Adjust your posts based on the analyzed sentiment.

[0370] Step 4: Post the adjusted content to social media.

[0371] "Example 2"

[0372] Step 1: Collect users' social media posts.

[0373] Step 2: Analyze user sentiment from the collected posts using an emotion engine.

[0374] Step 3: Generate post content based on the analyzed emotions.

[0375] Step 4: Post the generated post to social media.

[0376] "Example 3"

[0377] Step 1: Collect users' social media posts.

[0378] Step 2: Analyze user sentiment from the collected posts using an emotion engine.

[0379] Step 3: Optimize your posts based on the analyzed sentiment.

[0380] Step 4: Post your optimized post to social media.

[0381] Example 1

[0382] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0383] In conventional information-sharing network services, it was difficult to efficiently collect success stories of specific product acquisitions and generate optimal posting content that matched users' emotions. Furthermore, there was a lack of a way to automatically generate appropriate posting content to attract users' attention. This made it difficult to maintain users' interest, and information was not being used effectively.

[0384] 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.

[0385] In this invention, the server includes means for reading success stories of specific products posted on an information sharing network service, means for analyzing the read success stories, means for generating a program for posting the analyzed success stories daily, means for operating the generated program as a specific role, means for analyzing user emotions, and means for optimizing the posted content based on the analyzed emotions. This makes it possible to efficiently collect success stories related to specific products and automatically generate optimal posted content according to the user's emotions.

[0386] An "information sharing network service" is an online platform where users can post information and share it with other users.

[0387] "Specific products" refer to goods or services that are of interest in a particular market or application.

[0388] "Acquired Success Stories" refer to specific examples or experiences of success using a particular product.

[0389] "Means of reading" refers to the methods and technologies for obtaining data from an information sharing network service.

[0390] "Means of analysis" refers to methods and techniques for analyzing acquired data and extracting useful information.

[0391] A "daily posting program" refers to software or scripts that automatically post analyzed success stories every day.

[0392] "Means for operating as a specific role" refers to methods and techniques for executing a generated program according to a specific function or purpose.

[0393] "Means for analyzing user emotions" refers to methods and technologies for analyzing emotions from user posts and behavior and calculating an emotion score.

[0394] "Means for optimizing post content" refers to methods and techniques for adjusting post content to attract user interest based on analyzed emotions.

[0395] MODE FOR CARRYING OUT THE INVENTION

[0396] This invention provides a system that efficiently collects successful cases of acquiring a specific product posted on an information sharing network service and generates optimal posting content according to the user's emotions. Specific embodiments of this system are described below.

[0397] Program Generation

[0398] The server generates a program for reading success stories of specific products posted on an information sharing network service. This program has a function of extracting success stories from the network service used by experts on the specific product.

[0399] Program processing

[0400] The server performs the following processing using the generated program.

[0401] 1. Data Collection:

[0402] The server collects posted data from network services used by experts of specific products, using the APIs of SNSs (e.g., Twitter API or Facebook Graph API).

[0403] 2. Keyword analysis:

[0404] The server analyzes the collected posting data and extracts specific keywords and hashtags using natural language processing libraries (e.g., NLTK and spaCy).

[0405] 3. Extraction of success stories:

[0406] The server automatically extracts posts related to success stories based on the extracted keywords and hashtags, allowing for efficient collection of useful information about specific products.

[0407] 4. Emotion analysis:

[0408] The server uses an emotion engine (for example, IBM Watson (registered trademark) Natural Language Understanding or Microsoft Azure (registered trademark) Text Analytics) to analyze emotions from users' SNS posts.

[0409] 5. Optimize your posts:

[0410] The server optimizes the content of success stories based on the results of sentiment analysis. For example, if a user's post expresses joy or excitement, it selects success stories that evoke similar emotions and generates posts accordingly.

[0411] Specific examples

[0412] When a user posts on social media, "I tried a new product and I'm so happy!", the server passes this post to the emotion engine to obtain emotion scores such as "joy" or "satisfaction." Next, based on these emotion scores, the server selects success stories that similarly evoke joy or satisfaction, and generates a post with the content, "Other users are also having great success with this product!"

[0413] Prompt Sentence Examples

[0414] "Analyze the emotions of users' posts on social media, select success stories based on those emotions, and generate posts. For example, if a user's post expresses joy or excitement, select success stories that evoke similar emotions."

[0415] In this way, the server generates appropriate posts according to the user's emotions, making it easier to attract the user's attention.

[0416] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0417] Step 1:

[0418] The server collects posting data related to a specific product from an information sharing network service.

[0419] Input: Posted data obtained from the network service API.

[0420] Specific operation: The server periodically sends requests to the SNS API (for example, Twitter API or Facebook Graph API) to retrieve posts related to "Product Name" and "Product Name."

[0421] Output: A list of collected submission data.

[0422] Step 2:

[0423] The server analyzes the collected posting data and extracts specific keywords and hashtags.

[0424] Input: Post data collected in step 1.

[0425] Specific operation: The server uses a natural language processing library (e.g., NLTK or spaCy) to extract frequently occurring keywords and hashtags from the post data. For example, it extracts keywords such as "success," "acquisition," and "review."

[0426] Output: A list of extracted keywords and / or hashtags.

[0427] Step 3:

[0428] The server automatically extracts posts related to success stories based on the extracted keywords and hashtags.

[0429] Input: The list of keywords and hashtags extracted in step 2.

[0430] Specific operation: The server uses the results of keyword analysis as filtering conditions to select posts that correspond to success stories. For example, it extracts posts that contain the keyword "success."

[0431] Output: A list of posts related to the success story.

[0432] Step 4:

[0433] The server analyzes emotions from users' social media posts.

[0434] Input: The user's most recent social media posts.

[0435] Specific operation: The server uses an emotion engine (such as IBM Watson Natural Language Understanding or Microsoft Azure Text Analytics) to analyze the user's post and obtain an emotion score. For example, emotions such as "joy," "excitement," and "satisfaction" are quantified.

[0436] Output: Sentiment score.

[0437] Step 5:

[0438] The server optimizes the content of the success stories posted based on the results of the sentiment analysis.

[0439] Input: The list of success story posts extracted in step 3 and the sentiment scores obtained in step 4.

[0440] Specific operation: The server selects the most appropriate success story based on the emotion score and generates a post. For example, if the user's emotion indicates "joy," it selects a success story that evokes a similar emotion and generates a post with the content "Other users are also using this product with great success!"

[0441] Output: The optimized post content.

[0442] In this way, the server generates appropriate posts according to the user's emotions, making it easier to attract the user's attention.

[0443] (Application example 1)

[0444] Next, a description will be given of Application Example 1 of Embodiment Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0445] Conventional information-sharing SNSs lack a means to effectively share success stories of specific products. In addition, it is difficult to make optimal product recommendations based on users' emotions, which makes it difficult to attract users' attention.

[0446] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means for reading success stories of acquiring a specific product posted on an information-sharing SNS, means for generating a program for posting the read success stories daily, means for running the generated program as a specific role, means for adjusting the posted content using an emotion engine that recognizes the user's emotions, and means for analyzing the user's SNS posts and making optimal product recommendations based on the emotions. This enables appropriate posts and product recommendations to be made in accordance with the user's emotions, making it easier to attract the user's attention.

[0447] An "information sharing SNS" is a social networking service that allows users to share information with each other.

[0448] A "specific product" is a specific good or service sold in a particular market or for a particular purpose.

[0449] "Success stories" are cases that show successful experiences or results obtained when purchasing or using a particular product.

[0450] "Reading means" refers to a method or device for acquiring information and incorporating it into the system.

[0451] A "daily posting program" is software that automatically posts specific content to social media every day.

[0452] A "specific role" is a role for performing a specific function or task within the system.

[0453] An "emotion engine" is software or hardware that analyzes a user's emotions and adjusts the system's behavior based on the results.

[0454] A "means for adjusting posted content" is a method or device for optimizing the content posted to an SNS based on the user's emotions.

[0455] "Means for analyzing SNS posts" refers to a method or device for analyzing content posted on SNS and extracting specific information.

[0456] A "means for making product recommendations" is a method or device for recommending a particular product to a user.

[0457] The following describes the mode for carrying out the present invention: First, the system includes the following main components:

[0458] 1. A way to read success stories of specific products posted on information-sharing social networking sites

[0459] 2. A way to generate a program that posts the success stories it reads every day

[0460] 3. How to make the generated program act as a specific role

[0461] 4. A method for adjusting post content using an emotion engine that recognizes user emotions

[0462] 5. A method to analyze users' social media posts and make optimal product recommendations based on their emotions

[0463] System Program

[0464] The system is implemented using Python. Specifically, it uses the TextBlob library to analyze users' social media posts and recognize their emotions. It also uses the BeautifulSoup library to extract success stories about specific products from the web. Based on this data, it makes optimal product recommendations based on the user's emotions.

[0465] Processing Description

[0466] Hardware and Software

[0467] Hardware: Smartphone

[0468] Software: Python, TextBlob (sentiment analysis library), BeautifulSoup (web scraping library)

[0469] Data processing and calculation

[0470] 1. Social Media Post Analysis: The server analyzes users' social media posts using TextBlob and recognizes their emotions. For example, if a user posts "I'm really excited about this new gadget!", the emotion is recognized as "joy."

[0471] 2. Success story extraction: The server uses BeautifulSoup to extract success stories about a specific product from the Web. For example, it extracts success stories about the latest smartphones.

[0472] 3. Emotion-based recommendation: The server makes optimal product recommendations to users based on their recognized emotions. For example, if a user expresses the emotion "joy," it will recommend the most popular success stories.

[0473] Specific examples

[0474] User Submission: "I'm really excited about this new gadget!"

[0475] Product name: "Latest Smartphone"

[0476] Recommendation: "This phone has dramatically improved my photography!"

[0477] Prompt Sentence Examples

[0478] An example of a prompt for the generative AI model is as follows:

[0479] Create a program that analyzes users' social media posts, recognizes their emotions, and recommends success stories for specific products. If the user's post is "I'm really excited about this new gadget!" and the product name is "Latest Smartphone," recommend the most suitable success story.

[0480] In this way, it becomes possible to make posts and product recommendations that are appropriate to the user's emotions, making it easier to attract the user's attention.

[0481] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0482] Step 1:

[0483] The server retrieves the user's SNS posts. The input is the user's SNS post, and the output is the retrieved post data. Specifically, the server uses the SNS API to retrieve the user's latest posts.

[0484] Step 2:

[0485] The server analyzes the social media posts acquired using the TextBlob library and recognizes emotions. The input is the acquired post data, and the output is the analyzed emotion data. Specifically, the server passes the post content to TextBlob and determines whether the emotion is positive, negative, or neutral.

[0486] Step 3:

[0487] The server extracts success stories related to a specific product from the web. The input is the name of a specific product, and the output is the extracted success story data. Specifically, the server uses the BeautifulSoup library to scrape success stories related to the specified product from a website.

[0488] Step 4:

[0489] The server then recommends optimal products to users based on the recognized emotions. The input is the analyzed emotion data and success case data, and the output is the recommended success case. Specifically, the server selects the most appropriate case from the success case data based on the emotion data.

[0490] Step 5:

[0491] The server notifies the user of the selected success story. The input is the recommended success story, and the output is a notification message to the user. Specifically, the server uses the SNS API to send a message including the success story to the user.

[0492] Step 6:

[0493] The server generates a program that posts success stories every day and runs it as a specific role. The input is the success story data, and the output is the generated program. Specifically, the server sets a schedule for automatically posting success stories and runs the program.

[0494] Example 2

[0495] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0496] In conventional information sharing networks, it was difficult to efficiently collect success stories of specific products, generate new posts based on them, and post them regularly. It was also difficult to analyze emotions from user posts and reflect that emotional information in the generation of posts. This resulted in issues such as not being able to keep users interested and reducing the effectiveness of information sharing.

[0497] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for reading success stories of specific product acquisitions posted on the information sharing network, means for analyzing the read success stories, means for generating new posting content based on the analyzed success stories, means for periodically posting the generated posting content, means for analyzing emotions from user posts, and means for using the analyzed emotional information to generate posting content. This makes it possible to efficiently collect success stories, generate new posting content that attracts users' attention based on the success stories, and post the new posting content periodically. Furthermore, by reflecting users' emotional information, more effective information sharing can be achieved.

[0498] An "information sharing network" is an online platform for users to share information about specific products or services.

[0499] A "success story" is an example that demonstrates specific results or positive outcomes achieved by using a particular product or service.

[0500] A "reading means" is a function or process for obtaining specific information from a database or file system.

[0501] "Means of analysis" refers to the functions and processes for analyzing acquired data using natural language processing technology, etc., and extracting important information.

[0502] "Means of generation" refers to the functions and processes for creating new content or posts based on analyzed information.

[0503] A "periodic posting mechanism" is a function or process for automatically posting generated content to an online platform at regular intervals.

[0504] "Means for analyzing emotions" refers to functions or processes that use natural language processing technology to extract emotions from user posts and classify those emotions.

[0505] "Means for utilizing emotional information" refers to functions and processes for generating new content and adjusting posted content based on analyzed emotional information.

[0506] This invention is a system that efficiently collects successful cases of acquiring specific products posted on an information sharing network, generates new posting content based on the collected information, and posts the content periodically. It also analyzes emotions from users' posts and reflects this emotional information in the generated posting content.

[0507] System configuration

[0508] The server implements the system using the following hardware and software.

[0509] Hardware: The server has a powerful processor, sufficient memory, and a large storage device.

[0510] Software: The server uses a database management system (e.g., MySQL), natural language processing libraries (e.g., NLTK, spaCy), generative AI models (e.g., GPT-3), and scheduling software (e.g., cron jobs).

[0511] Program processing

[0512] The server processes and calculates the data in the following procedure.

[0513] 1. Loading success stories:

[0514] The server loads success stories from a database or the file system. Specifically, the server connects to a MySQL database and retrieves data from the table where the success stories are stored. For example, it executes the SQL query "SELECT FROM success_stories WHERE date = CURDATE()".

[0515] 2. Natural Language Processing Analysis:

[0516] The server analyzes the text of success stories using natural language processing technology. Specifically, the server uses NLP libraries such as NLTK and spaCy to extract important information from the text. For example, it extracts keywords such as "sales" and "20% increase" from the phrase "sales increased by 20%."

[0517] 3. Generate a new post:

[0518] The server generates new post content based on the extracted information. At this time, the server uses a generative AI model (e.g., GPT-3) to generate natural-sounding sentences. For example, the server inputs a prompt such as, "Success story: Sales increased by 20%. Please generate new SNS post content based on this success story."

[0519] 4. Emotion analysis:

[0520] The emotion engine analyzes emotions from users' social media posts. Specifically, the emotion engine uses natural language processing technology to extract emotions from the text of users' posts. For example, it extracts the emotion of "joy" from a post such as "I'm so happy to have gotten this product!"

[0521] 5. Post regularly:

[0522] The server periodically posts the generated content to the social networking site using scheduling software (e.g., a cron job). For example, every day at 9:00 AM, the server could post something like, "We've received great news from a customer who introduced our new product that their sales have increased by 20%!"

[0523] Specific examples

[0524] Examples:

[0525] Loading success stories: The server executes the SQL query "SELECT FROM success_stories WHERE date = CURDATE()" to retrieve the success stories for today's date.

[0526] Analysis using natural language processing: The server tokenizes the text "Sales increased by 20%" and extracts keywords such as "sales" and "20% increase."

[0527] Generating new post content: The server inputs the prompt "Success story: Sales increased by 20%. Please generate new SNS post content based on this success story" into the generative AI model, and generates the sentence "We received the happy news that a customer who introduced our new product has increased their sales by 20%!"

[0528] Sentiment Analysis: The sentiment engine extracts the emotion "joy" from the post "I'm so happy I got this product!"

[0529] Periodic Posting: The server sets up a cron job that calls the SNS API at 9am every day and posts the generated post.

[0530] In this way, the server generates new posting content based on successful cases, analyzes user emotions using an emotion engine, and creates a system that posts to SNS periodically.

[0531] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0532] Step 1:

[0533] The server reads the success stories of a specific product posted on the information sharing network. Specifically, the server connects to the MySQL database and retrieves data from the table where the success stories are stored. As input, it executes the SQL query "SELECT FROM success_stories WHERE date = CURDATE()" and retrieves the success story data for today's date as output.

[0534] Step 2:

[0535] The server analyzes the text of the success stories it has loaded using natural language processing technology. Specifically, the server uses NLP libraries such as NLTK and spaCy to extract important information from the text. It receives the text data of the success stories as input and obtains extracted keywords and phrases as output. For example, it extracts keywords such as "sales" and "20% increase" from the phrase "sales increased by 20%."

[0536] Step 3:

[0537] The server generates new post content based on the extracted information. Specifically, the server uses a generative AI model (e.g., GPT-3) to generate natural-sounding sentences. As input, the extracted keywords and phrases are incorporated into a prompt sentence, which is then input into the generative AI model. The generated post content is obtained as output. For example, inputting the prompt sentence, "Success story: Sales increased by 20%. Please generate new SNS post content based on this success story," generates the sentence, "We received the happy news that a customer who introduced our new product has increased their sales by 20%!"

[0538] Step 4:

[0539] The emotion engine analyzes emotions from users' social media posts. Specifically, the emotion engine uses natural language processing technology to extract emotions from the text of users' posts. It receives the user's post text as input and obtains the extracted emotion label as output. For example, it extracts the emotion "joy" from a post such as "I'm so happy to have gotten this product!"

[0540] Step 5:

[0541] The server periodically posts the generated post content to SNS. Specifically, the server uses scheduling software (e.g., cron job). As input, it receives the generated post content and posting schedule, and as output, it calls the SNS API at the specified time to post. For example, every day at 9:00 AM, it posts, "We've received exciting news from a customer who introduced our new product that their sales have increased by 20%!"

[0542] In this way, the server generates new posting content based on successful cases, analyzes user emotions using an emotion engine, and creates a system that posts to SNS periodically.

[0543] (Application example 2)

[0544] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0545] In conventional information sharing networks, success stories are posted without considering the feelings of users, which makes it difficult to attract users' attention. In addition, regular posting is often done manually, which is inefficient.

[0546] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0547] In this invention, the server includes means for reading success stories of specific product acquisitions posted on the information sharing network, means for generating a program for posting the read success stories daily, means for operating the generated program in a specific role, means for analyzing emotions from user posts, means for generating new post content based on the analyzed emotional information, and means for periodically posting the generated post content. This enables effective posting based on user emotions and automates periodic posting, enabling efficient information sharing.

[0548] An "information sharing network" is an online platform where users can post information and share it with other users.

[0549] "Specific products" refers to specific goods or services offered by a particular company or brand.

[0550] "Success stories" are posts that show the success and satisfaction that users have gained from purchasing or using a particular product.

[0551] "Means of reading" refers to the methods and techniques for obtaining specific data from an information sharing network.

[0552] A "daily posting program" is software that automatically posts specific content every day.

[0553] "Means of generation" refers to methods and techniques for creating new data or programs for a specific purpose.

[0554] A "specific role" refers to a role that performs a specific function or task within the system.

[0555] "Means for operating" refers to the methods and techniques for actually running the generated program or system.

[0556] "Means for analyzing emotions" refers to methods and technologies for extracting and analyzing emotions from user posts.

[0557] "Emotion information" refers to emotion data extracted from users' posts.

[0558] "Means for generating new posts" refers to methods and technologies for creating new posts based on analyzed emotional information.

[0559] "Means for posting periodically" refers to methods or techniques for automatically posting at specific time intervals.

[0560] A system for implementing this invention includes means for reading success stories of acquiring a specific product posted on an information sharing network, means for generating a program that posts the read success stories every day, means for operating the generated program as a specific role, means for analyzing emotions from user posts, means for generating new post content based on the analyzed emotional information, and means for periodically posting the generated post content.

[0561] Program processing explanation

[0562] Hardware and software used

[0563] Hardware: Servers, smartphones, smart glasses

[0564] Software: Python, Transformers library, Schedule library

[0565] Data processing and calculation

[0566] 1. Data Acquisition from Information Sharing Networks:

[0567] The server acquires success stories about specific products from the information sharing network. This data is text data posted by users.

[0568] 2. Emotion analysis:

[0569] The server inputs the text data of the acquired success stories into a sentiment analysis engine (Transformers sentiment-analysis model) and analyzes the user's emotions. For example, the emotion of "joy" is extracted from a post such as "I'm so happy I got this product!"

[0570] 3. Generate a new post:

[0571] The server generates new post content based on the analyzed emotional information. For example, if the emotion of "joy" is extracted, it generates a post content such as "Use our product and become happy!"

[0572] 4. Post regularly:

[0573] The server sets up a schedule for periodically posting the generated posts, using the Schedule library to automatically post at a specific time each day.

[0574] Examples and prompts

[0575] Specific examples

[0576] Success Story: "I'm so happy I got this product!"

[0577] Emotion analysis result: "joy"

[0578] Post generated: "Use our product and make yourself happy!"

[0579] Prompt Sentence Examples

[0580] Analyze emotions from users' social media posts and generate ads based on those emotions. For example, extract the emotion of "joy" from a post such as "I'm so happy I got this product!" and generate an ad that says, "Use our product and become happy!"

[0581] In this way, effective posting based on the user's emotions becomes possible, and regular posting is also automated, resulting in efficient information sharing.

[0582] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0583] Step 1:

[0584] The server acquires success stories about specific products from the information sharing network. The input is the posted data on the information sharing network, and the output is the text data of the acquired success stories. Specifically, the server acquires the posted data from the network using an API and saves it in text format.

[0585] Step 2:

[0586] The server inputs the text data of the acquired success stories into a sentiment analysis engine to analyze the user's sentiment. The input is the text data of the success stories, and the output is the analyzed sentiment information. Specifically, sentiment is extracted from the text data using the sentiment-analysis model of the Transformers library.

[0587] Step 3:

[0588] The server generates new post content based on the analyzed emotional information. The input is the emotional information, and the output is the new post content. Specifically, the server automatically generates new post content using a template based on the emotional information.

[0589] Step 4:

[0590] The server schedules the generated posts for periodic posting. The input is the new post, and the output is the scheduled posting task. Specifically, it uses the Schedule library to set up a task to post at a specific time every day.

[0591] Step 5:

[0592] The server posts new posts to the information sharing network according to a set schedule. The input is the scheduled posting task, and the output is the actual posted content. Specifically, the server uses an API to post the generated posts to the network.

[0593] Example 3

[0594] Next, a description will be given of a third embodiment of the third embodiment. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0595] Conventional information sharing network services have had the problem that it is difficult to generate appropriate posting content that reflects users' emotions, making it difficult to attract users' attention. Furthermore, success stories posted tend to be formulaic, making it difficult to empathize with users' emotions. This has led to problems such as a decrease in the efficiency of information sharing and a decrease in user engagement.

[0596] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0597] In this invention, the server includes means for reading success stories of acquiring a specific product posted to an information sharing network service, means for generating a program for posting the read success stories daily, means for operating the generated program as a specific role, means for collecting user emotion data, emotion analysis means for analyzing the collected emotion data, means for using a generative AI model for generating post content based on the analysis results, and means for posting the generated post content to the information sharing network service. This enables the server to generate appropriate post content according to the user's emotion and efficiently share information on the information sharing network service.

[0598] An "information sharing network service" is an online platform where users can post information and share it with other users.

[0599] "Specific products" refers to specific goods or services available on the information sharing network service.

[0600] "Successful Acquisition Cases" refers to information that indicates successful cases and achievements regarding a particular product.

[0601] A "program" is a set of instructions designed to perform a particular function.

[0602] A "specific role" refers to a specific function or task that a program performs.

[0603] "User emotion data" is information about emotions expressed by users through their posts and comments.

[0604] "Emotion analysis means" refers to a technique or method for analyzing a user's emotion data and identifying that emotion.

[0605] A "generative AI model" is a model that uses artificial intelligence to generate text and data.

[0606] A "prompt" is an instruction or question that is input into a generative AI model.

[0607] "Posted content" refers to text or messages posted on the information sharing network service.

[0608] MODE FOR CARRYING OUT THE INVENTION

[0609] The present invention relates to a system for generating appropriate posting content in response to user emotions on an information sharing network service, thereby enabling efficient information sharing. Specific embodiments of this system will be described below.

[0610] 1. Program Generation

[0611] The server generates a program using the generative AI model. This program acts as a skilled crew and has the ability to post success stories on an information-sharing network service.

[0612] 2. Program Processing

[0613] The server analyzes the user's emotions using an emotion engine. The emotion engine uses a natural language processing library (e.g., NLTK or spaCy) to analyze text data and identify the user's emotions. For example, if a user posts, "I'm so happy that my new project was successful!", the text data is collected and the emotion engine extracts the emotion of "joy."

[0614] Next, the server inputs a prompt into the generative AI model (e.g., GPT-3) based on the emotion information obtained from the emotion engine. An example of a prompt is, "If the user expresses the emotion 'joy,' please generate a success story that highlights that joy." Based on this prompt, the generative AI model generates a post that is likely to empathize with the user's emotions. For example, a post might be generated that reads, "The new project was a success, and the whole team shared their joy!"

[0615] 3. Posting the content to social media

[0616] The server posts the generated content to the SNS. Specifically, it posts the generated text using the SNS's API. As a result, an appropriate post based on the user's emotions is displayed on the SNS.

[0617] Specific examples

[0618] For example, a user posts on a social networking site, "I'm so happy that our new project was a success!" The device collects this post and sends it to the server. The server uses an emotion engine to analyze the emotion of "joy." The server then inputs a prompt to the generative AI model: "If the user expresses the emotion 'joy,' please generate a success story that highlights their joy." The generative AI model then generates a post that reads, "Our new project was a success, and the whole team shared their joy!" Finally, the server posts this post to the social networking site, and an appropriate post based on the user's emotion is displayed on the social networking site.

[0619] In this way, the server utilizes the emotion engine and generative AI model to post appropriate information according to the user's emotion, thereby enabling efficient information sharing on the information sharing network service. The flow of the identification process in Example 3 will be described with reference to Fig. 21.

[0620] Program processing flow

[0621] Step 1: Collecting user emotion data

[0622] Users post and comment on the information sharing network service. The terminal collects these posts and comments in real time and sends them to the server.

[0623] Input: User posts and comments

[0624] Output: Collected text data

[0625] Specific operation: A user posts, "I'm so happy that my new project was a success!" The device collects this text data and sends it to the server.

[0626] Step 2: Emotion analysis using the emotion engine

[0627] The server passes the collected text data to the emotion engine, which uses a natural language processing library (e.g., NLTK or spaCy) to analyze the text data and identify the user's emotions.

[0628] Input: Collected text data

[0629] Output: Parsed emotion information

[0630] Specific operation: The server passes the text data "I'm so happy that the new project was a success!" to the emotion engine. The emotion engine extracts the emotion of "joy."

[0631] Step 3: Generate post content using a generative AI model

[0632] The server inputs a prompt sentence into the generative AI model based on the emotion information obtained from the emotion engine. Based on this prompt sentence, the generative AI model generates post content that is likely to resonate with the user's emotions.

[0633] Input: Analyzed emotion information, prompt sentence

[0634] Output: Generated post

[0635] Specific operation: The server inputs the prompt "If the user expresses the emotion 'joy,' please generate a success story that highlights the joy" into the generative AI model. The generative AI model then generates a post that reads, "The new project was a success, and the whole team shared their joy!"

[0636] Step 4: Post your post to social media

[0637] The server posts the generated post content to the information sharing network service. Specifically, the server posts the generated text using the API of the SNS.

[0638] Input: Generated post content

[0639] Output: Posts displayed on an information sharing network service

[0640] Specific operation: The server posts the generated message "The new project was a success, and the whole team shared their joy!" to social media.

[0641] In this way, the server utilizes the emotion engine and generative AI model to make appropriate posts based on the user's emotions, enabling efficient information sharing on the information-sharing network service.

[0642] (Application example 3)

[0643] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0644] In conventional information sharing networks, it is difficult to generate optimal posting content that reflects users' emotions, which makes it difficult to attract users' attention. Furthermore, success stories tend to be monotonous, making it difficult to sustain users' interest. Furthermore, since content recommendations are not based on emotions, the user experience is not improved.

[0645] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0646] In this invention, the server includes means for reading success stories of specific product acquisitions posted to an information sharing network, means for generating a program for posting the read success stories daily, means for operating the generated program in a specific role, means for analyzing user emotions using an emotion analysis engine, means for generating optimal posting content based on the analyzed emotions, and means for posting the generated posting content to the information sharing network. This allows optimal posting content to be generated based on the user's emotions, attracting the user's attention. Furthermore, the success story posts are diversified, thereby sustaining the user's interest. Furthermore, content recommendations based on emotions improve the user experience.

[0647] An "information sharing network" is an online platform where users can post information and share it with other users.

[0648] "Specific products" refers to specific goods or services that are of interest to users on an information sharing network.

[0649] "Acquisition Success" refers to experiences or instances of success in acquiring or using a particular product.

[0650] "Reading means" refers to a method or device for obtaining data from an information sharing network.

[0651] "Program generation means" refers to a method or apparatus for creating software code to perform a specific task.

[0652] "Means for operating as a specific role" refers to a method or device for executing a generated program so as to perform a specific function or role.

[0653] An "emotion analysis engine" refers to software or hardware that analyzes emotions from user input data and identifies those emotions.

[0654] "User emotion" refers to the type of psychological state or emotion exhibited by the user.

[0655] "Optimal posting content" refers to information or messages that are generated based on the user's emotions and are most suitable for attracting the user's attention.

[0656] "Generated posts" refers to information and messages created by a sentiment analysis engine based on the user's emotions.

[0657] An "expert" is an individual who has advanced knowledge or skills in a particular field.

[0658] "Skilled worker" refers to an individual who has a high level of experience and skill in a particular job or task.

[0659] A system for implementing this invention includes means for reading success stories of acquiring a specific product posted on an information sharing network, means for generating a program that posts the read success stories every day, means for operating the generated program as a specific role, means for analyzing a user's emotions using an emotion analysis engine, means for generating optimal posting content based on the analyzed emotions, and means for posting the generated posting content on the information sharing network.

[0660] System program generation

[0661] The server first reads the success stories of specific products from the information sharing network. Then, it generates a program for posting the read success stories every day. This program operates as a specific role and posts the success stories periodically.

[0662] Furthermore, the server analyzes the user's emotions using a sentiment analysis engine. The sentiment analysis engine identifies emotions from the user's input data (e.g., text or voice). Based on the analysis results, the server generates post content that best matches the user's emotions. The generated post content is posted to the information sharing network.

[0663] Hardware and software used

[0664] Hardware: Server, user device (smartphone, head-mounted display, etc.)

[0665] Software: Python, EmotionEngine library, ContentRecommender library, SNS API

[0666] Data processing and calculation

[0667] The server first obtains data from the information sharing network. Then, it analyzes the user's emotions using the EmotionEngine library. Based on the analyzed emotions, it generates optimal post content using the ContentRecommender library. The generated post content is posted to the information sharing network using the SNS API.

[0668] Specific examples

[0669] For example, if a user types "I am feeling very happy today!", the emotion analysis engine will analyze the emotion of "joy." Based on this analysis, the server will recommend positive content and post it to the information sharing network.

[0670] Prompt Sentence Examples

[0671] If a user types "I am feeling very happy today!", the emotion engine should parse the emotion "joy" and recommend positive content.

[0672] In this way, optimal posting content can be generated in response to the user's emotions and posted to the information sharing network, thereby attracting the user's attention.

[0673] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[0674] Step 1:

[0675] The server reads the success stories of acquiring a particular product from the information sharing network.

[0676] Input: Success story data from information sharing networks

[0677] Data processing: Analyze the success case data and extract the necessary information

[0678] Output: Extracted success story data

[0679] Step 2:

[0680] The server generates a program to post the success stories it has read every day.

[0681] Input: Extracted success story data

[0682] Data calculation: Generate a program that sets a regular posting schedule based on success case data

[0683] Output: Program for daily posting

[0684] Step 3:

[0685] The server runs the generated program as a specific role.

[0686] Input: Program for daily posting

[0687] Specific Actions: Implement the program and regularly post success stories

[0688] Output: Regularly posted success stories

[0689] Step 4:

[0690] The server analyzes the user's emotions using an emotion analysis engine.

[0691] Input: User input data (text or voice)

[0692] Data Calculation: Analyzing user emotions using the EmotionEngine library

[0693] Output: Parsed emotion data

[0694] Step 5:

[0695] The server generates optimal posting content based on the analyzed emotions.

[0696] Input: Parsed emotion data

[0697] Data crunching: Use the ContentRecommender library to generate optimal posts based on sentiment

[0698] Output: Optimal post content

[0699] Step 6:

[0700] The server posts the generated posting content to the information sharing network.

[0701] Input: Best post content

[0702] Specific behavior: Uses SNS API to post generated content to information sharing network.

[0703] Output: Posted content

[0704] In this way, the server generates optimal posting content according to the user's emotions and posts it to the information sharing network, thereby attracting the user's attention.

[0705] 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.

[0706] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0707] Another example of generative AI is Gemini (registered trademark) (Internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0708] 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.

[0709] [Second embodiment]

[0710] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0711] 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.

[0712] 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).

[0713] 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.

[0714] 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.

[0715] 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).

[0716] 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. 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.

[0717] 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.

[0718] 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.

[0719] 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.

[0720] 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.

[0721] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0722] "Example 1"

[0723] One embodiment of the present invention includes a means for reading success stories of specific products posted on an information-sharing social networking site. Specifically, a program is implemented to extract success stories of specific products from social networking sites used by experts on the product. This program analyzes keywords and hashtags in the posted content and automatically extracts posts related to the success stories.

[0724] "Example 2"

[0725] Furthermore, there is a means to generate a program that posts the read success stories every day. Specifically, a program is implemented that generates new posting content based on the extracted success stories. This program automatically generates new posting content based on the content of the success stories and posts it periodically.

[0726] "Example 3"

[0727] There is also a way to make the generated program act as a specific role. Specifically, a function has been implemented to make the generated program act as an experienced crew member. This function allows the program to post success stories as an experienced crew member. This allows for efficient information sharing on the information-sharing SNS.

[0728] The processing flow of each embodiment will be described below.

[0729] "Example 1"

[0730] Step 1: Obtain posts from social media used by experts on a specific product. In this step, we use an API to obtain post data from social media.

[0731] Step 2: Extract success stories of product acquisition from the acquired posts. In this step, keywords and hashtags in the post content are analyzed and posts related to success stories are automatically extracted.

[0732] "Example 2"

[0733] Step 1: Generate new post content based on the extracted success stories. In this step, new post content is automatically generated based on the content of the success stories.

[0734] Step 2: Post the generated content on a regular basis. In this step, the generated content is posted to SNS on a regular basis.

[0735] "Example 3"

[0736] Step 1: Execute the generated program as a specific role. In this step, the generated program is executed as a skilled crew member.

[0737] Step 2: The program acting as a crew posts a success story. In this step, the program acts as an experienced crew and posts a success story.

[0738] Example 1

[0739] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0740] In conventional information sharing network services, it has been difficult to efficiently collect, analyze, and provide users with success stories of specific product acquisitions. In particular, advanced analytical techniques and efficient data management are required to extract useful information from network services used by experts. Therefore, there is a need to quickly and accurately provide users with the success stories they need.

[0741] 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.

[0742] In this invention, the server includes means for reading success stories of specific products posted on an information sharing network service, means for analyzing the read success stories, means for extracting posts related to the success stories from the analysis results, means for saving the extracted success stories in a database, and means for providing the saved success stories in response to user requests. This makes it possible to efficiently collect and analyze success stories related to specific products and provide them to users quickly and accurately.

[0743] An "information sharing network service" is an online platform that allows users to share information and interact via the Internet.

[0744] "Specific product" refers to a specific good or service sold in a specific market or application.

[0745] "Success stories" are information that shows specific cases or experiences where a particular product has been used successfully.

[0746] "Means of reading" refers to the methods and technologies for obtaining data from an information sharing network service and incorporating it into the system.

[0747] "Means of analysis" refers to methods and techniques for analyzing acquired data and extracting useful information.

[0748] "Means of extraction" refers to methods and techniques for selecting information that meets specific conditions from the analysis results.

[0749] "Means of storing in a database" refers to the methods and techniques used to systematically manage extracted information and store it for later use.

[0750] "Means for providing information in response to a user's request" refers to methods and technologies for retrieving and providing stored information in response to a user's request.

[0751] "Natural language processing technology" refers to technology that enables computers to understand and process human language.

[0752] The present invention provides a system for efficiently collecting, analyzing, and providing to users success stories of specific products posted on an information sharing network service. Specific embodiments of this system will be described below.

[0753] First, the server collects posts related to a specific product from an information-sharing network service (e.g., a social networking platform). To do this, it uses the Python libraries Tweepy and BeautifulSoup to retrieve posts containing specific hashtags (e.g., "product name" or "success stories").

[0754] Next, the server analyzes the collected post data using natural language processing (NLP) technology. NLP libraries such as NLTK and spaCy are used. This allows keywords and hashtags to be extracted from the post content, and posts related to success stories to be identified. For example, keywords such as "success," "acquisition," and "case study" can be extracted from the post content.

[0755] The server automatically extracts posts related to success stories based on the analysis results. Specifically, it uses the extracted keywords and hashtags to filter posts that correspond to success stories. For example, it selects posts that include "success story" or "product name."

[0756] The extracted success story posts are stored in a database by the server. The database uses MySQL or PostgreSQL. The data stored includes information such as the post content, poster, and posting date and time. For example, the data is saved using the MySQL INSERT statement.

[0757] When a user wants to know about success stories of a specific product, they send a request from their device to the server. The request includes the product name and related keywords. For example, a user might request, "Please tell me about success stories of product A."

[0758] The server searches the database for relevant success stories and returns them to the device. The search is performed using the SQL SELECT statement. The user can view the success stories on the device. For example, the server sends a post saved as "Product A success story" to the device.

[0759] As a concrete example, the following is an example of a prompt sentence to be input to the generative AI model.

[0760] Example prompt sentence:

[0761] "Please tell us about success stories for a specific product. Please use data collected from social media to extract posts related to success stories."

[0762] When this prompt sentence is input into the generative AI model, the model analyzes data collected from social media, extracts posts related to success stories, and provides them to the user.

[0763] The above is a specific embodiment for carrying out the present invention.

[0764] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0765] Step 1:

[0766] The server collects posts related to a particular product from an information sharing network service.

[0767] Input: Post data obtained from the API of the social media platform.

[0768] Data processing: Use Python libraries (Tweepy and BeautifulSoup) to filter posts containing specific hashtags (e.g., "product name" or "success story").

[0769] Output: The filtered post data.

[0770] Specific operation: The server calls the API of the social networking site to retrieve posts containing a specific hashtag. The retrieved posts are then filtered to select only those related to a specific product.

[0771] Step 2:

[0772] The server analyzes the collected posting data using natural language processing (NLP) technology.

[0773] Input: Filtered post data.

[0774] Data processing: Use NLP libraries (NLTK and spaCy) to extract keywords and hashtags from the post content.

[0775] Output: Extracted keywords and hashtags.

[0776] Specific operation: The server analyzes the collected posting data and extracts keywords such as "success," "acquisition," and "case study" from the posting content.

[0777] Step 3:

[0778] The server automatically extracts posts related to success stories based on the analysis results.

[0779] Input: Extracted keywords and hashtags.

[0780] Data processing: Using the extracted keywords and hashtags, posts that correspond to success stories are filtered.

[0781] Output: Post data related to the success story.

[0782] Specific operation: Based on the analysis results, the server selects posts containing specific keywords or hashtags and extracts posts related to success stories.

[0783] Step 4:

[0784] The server stores the extracted success story posts in a database.

[0785] Input: Post data related to the success story.

[0786] Data processing: Save information such as post content, poster, and posting date and time in a database (MySQL or PostgreSQL).

[0787] Output: Success story submission data stored in the database.

[0788] Specific operation: The server saves the extracted success story posts in the database using the MySQL INSERT statement.

[0789] Step 5:

[0790] When a user wants to know about success stories of a particular product, the user sends a request from the terminal to the server.

[0791] Input: User request (product name and related keywords).

[0792] Data processing: Analyze the request content and search for relevant success stories.

[0793] Output: The request data to the server.

[0794] Specific operation: The user uses the terminal to send a request saying, "Please tell me some success stories about product A."

[0795] Step 6:

[0796] The server searches the database for the relevant success story and returns it to the terminal.

[0797] Input: User request data.

[0798] Data processing: Use the SQL SELECT statement to search the database for relevant success stories.

[0799] Output: Success story submission data as search results.

[0800] Specific operation: The server searches the database based on the user's request and sends the post saved as "Product A success story" to the terminal.

[0801] Step 7:

[0802] The user views the success stories on the terminal.

[0803] Input: Successful case submission data returned from the server.

[0804] Data processing: None.

[0805] Output: Success story submission data displayed on the device.

[0806] Specific operation: The user views the success story posts sent from the server on the terminal.

[0807] (Application example 1)

[0808] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0809] Conventional information-sharing SNSs lack a means to efficiently collect and provide users with success stories about specific products. This means that users have to spend a lot of time and effort to find information that will help them when purchasing a product. Furthermore, since there is no function to automatically display success stories, users may miss out on the information they need. These issues need to be resolved.

[0810] 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.

[0811] In this invention, the server includes means for reading success stories of specific products posted on an information-sharing SNS, means for generating a program for posting the read success stories daily, means for running the generated program as a specific role, means for automatically displaying success stories related to the specific product, means for acquiring and analyzing HTML from the search result page of the SNS, and means for analyzing the posted content using regular expressions to extract posts related to the success stories. This allows users to efficiently collect success stories and easily obtain information that will be useful when purchasing a product.

[0812] An "information sharing SNS" is an online platform that allows users to share information with each other.

[0813] A "specific product" is a specific good or service sold in a particular market or for a particular purpose.

[0814] "Acquisition success stories" are cases or experiences of success when purchasing or using a particular product.

[0815] A "means for reading" is a method or device for obtaining information and converting it into a format that can be used within the system.

[0816] A "daily posting program" is software that automatically posts specific information to social media every day.

[0817] A "specific role" is a role assigned to perform a specific function or task within the system.

[0818] An "automatic display means" is a method or device for displaying information without requiring user interaction.

[0819] A "search results page" is a page that lists results generated by a search engine based on specific keywords or criteria.

[0820] "Means for acquiring and analyzing HTML" refers to a method or device for acquiring the HTML code of a web page and analyzing its content.

[0821] A "regular expression parser" is a method or device for analyzing text based on specific patterns.

[0822] The "means for extracting posts related to success stories" refers to a method or device for selecting and extracting posts that include information related to success stories.

[0823] A system for implementing this invention includes means for reading success stories of acquiring a specific product posted on an information-sharing SNS, means for generating a program that posts the read success stories every day, means for operating the generated program as a specific role, means for automatically displaying success stories related to a specific product, means for obtaining and analyzing HTML from the search results page of the SNS, and means for analyzing the posted content using regular expressions and extracting posts related to the success stories.

[0824] The server first accesses the information-sharing social networking site and searches for posts related to a specific product. Specifically, it retrieves HTML from the search results page of the social networking site and analyzes it using a library such as BeautifulSoup. Through this analysis, it extracts the content of the posts and uses regular expressions to select posts related to success stories.

[0825] The server then generates a program that automatically posts selected success stories daily, and the program acts as a specific role, automatically displaying related success stories when a user views a specific product page.

[0826] When a user searches for a specific product, the server displays success stories related to that product, allowing the user to easily obtain information that will help them make a purchase.

[0827] As a concrete example, if a user searches for a "specific product name," by inputting the following prompt sentence into the generative AI model, success stories on social media can be automatically extracted and provided to the user.

[0828] Example prompt sentence:

[0829] Please extract successful examples of acquiring "specific product names" from social media.

[0830] This system allows users to efficiently collect success stories and easily obtain information that can be used as reference when purchasing products. The hardware used includes a server and the user's smartphone, and the software used includes Python, BeautifulSoup, and requests.

[0831] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0832] Step 1:

[0833] The server accesses the information sharing SNS and searches for posts related to a specific product.

[0834] Input: Specific product name

[0835] Output: HTML data of social media search results page

[0836] Specific operation: The server uses the social networking service's search API to search for posts related to a specific product name and retrieves the results in HTML format.

[0837] Step 2:

[0838] The server analyzes the acquired HTML data.

[0839] Input: HTML data of the search results page of the social networking site

[0840] Output: Text data of the post

[0841] Specific operation: The server parses the HTML data using the BeautifulSoup library and extracts the text data of the post content.

[0842] Step 3:

[0843] The server analyzes the content of the posts using regular expressions and extracts posts related to success stories.

[0844] Input: Text data of post content

[0845] Output: A list of posts related to the success story

[0846] Specific operation: The server analyzes the content of posts using regular expressions and extracts posts containing keywords such as "success," "achievement," and "acquisition."

[0847] Step 4:

[0848] The server generates a program that automatically posts extracted success stories every day.

[0849] Input: List of posts related to success stories

[0850] Output: Daily posting program

[0851] Specific operation: Based on the list of success stories, the server generates a program to automatically post to SNS every day.

[0852] Step 5:

[0853] The server runs the generated program as a specific role.

[0854] Input: Daily posting program

[0855] Output: A program that acts as a specific role

[0856] Specific operation: The server runs the generated program and automatically posts success stories to SNS every day.

[0857] Step 6:

[0858] When a user views a particular product page, the server automatically displays related success stories.

[0859] Input: User browsing information, list of posts related to success stories

[0860] Output: Display success stories

[0861] Specific operation: When a user views a specific product page, the server sends information to the user's device to automatically display related success stories.

[0862] Example 2

[0863] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0864] In conventional information sharing network services, it was difficult to efficiently collect success stories of specific products, automatically generate new posts based on them, and post them regularly. In addition, manual posting required time and effort, making it difficult to continuously disseminate information.

[0865] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for reading success stories of specific product acquisition posted on an information sharing network service, a means for generating a prompt sentence based on the read success story, a means for inputting the generated prompt sentence into a generative AI model to generate new posting content, a means for saving the generated posting content in a database, and a means for periodically posting the saved posting content. This enables automatic generation and periodic posting of new posting content based on success stories.

[0866] An "information sharing network service" is an online platform that allows users to share information and communicate.

[0867] "Specific product" refers to a specific good or service sold in a specific market or application.

[0868] "Acquisition success stories" refer to specific cases or episodes in which a particular product has achieved success in the market.

[0869] A "prompt sentence" is text to be input into a generative AI model, and is a sentence that contains the key points of a successful case.

[0870] A "generative AI model" is a model for generating text using artificial intelligence, such as one that uses natural language processing technology.

[0871] "New posts" refers to new text content generated by the generative AI model based on success stories.

[0872] A "database" is a system for systematically storing and managing information.

[0873] "Means for periodic posting" means a feature that automatically posts saved posts to an online platform at regular intervals.

[0874] The present invention relates to a system that efficiently collects successful cases of acquiring specific products posted on an information sharing network service, automatically generates new posting content based on the collected information, and posts the content periodically.

[0875] The server first reads the success case data provided by the user. This data is assumed to be stored in a text file or database. For example, the server reads the data from a file called success_cases.txt.

[0876] Next, the server generates a prompt sentence to be input to the generative AI model based on the content of the read success case. The prompt sentence is designed to include the key points of the success case. As a concrete example, the following prompt sentence can be generated:

[0877] Example prompt sentence:

[0878] "Below is an example of a company that successfully implemented a new marketing strategy. Please use this example to generate new content for your posts."

[0879] Success stories include:

[0880] "Company A implemented a new marketing strategy that leveraged social media. This strategy significantly improved customer engagement and increased sales by 20%."

[0881] The server inputs the generated prompt into a generative AI model (e.g., OpenAI's GPT-3). The generative AI model generates new posts based on the prompt. Examples of generated posts include:

[0882] An example of the generated post:

[0883] "The key point to learn from Company A's success story is that by effectively using social media, you can increase engagement with customers. With this strategy, Company A was able to increase sales by 20%. Why not try implementing a marketing strategy that utilizes social media in your own business?"

[0884] The generated post content is saved in a database by the server, along with metadata such as the posting date and time and the ID of the related success story.

[0885] Finally, the server automatically posts the saved content to social media platforms or blogs periodically (e.g., daily) by connecting to each platform using an API. For example, posts can be made using the Twitter API.

[0886] In this way, the server automatically generates new posting content based on success stories and posts it periodically, reducing the user's workload and supporting continuous information dissemination.

[0887] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0888] Step 1: Load the success story data

[0889] The server reads the success case data provided by the user. This data is assumed to be stored in a text file or database. For example, data is read from a file called success_cases.txt. The input is the text data of the success case, and the output is the content of the success case stored in memory.

[0890] Step 2: Generate a prompt statement

[0891] The server generates a prompt sentence to be input to the generative AI model based on the content of the read success story. The prompt sentence is designed to include the key points of the success story. The input is the text data of the success story, and the output is the generated prompt sentence. Specifically, it extracts the key points of the success story and creates a prompt sentence that includes them.

[0892] Step 3: Enter a prompt into the generative AI model to generate new post content

[0893] The server inputs the generated prompt text into a generative AI model (for example, OpenAI's GPT-3). The generative AI model generates new post content based on the prompt text. The input is the prompt text, and the output is the generated new post content. Specifically, the server sends the prompt text to the generative AI model and receives the generated text.

[0894] Step 4: Save the generated post to the database

[0895] The server saves the new posts obtained from the generative AI model in a database. When saving, it also saves metadata such as the posting date and time and the ID of the related success story. The input is the generated post and metadata, and the output is the post saved in the database. Specifically, it connects to the database and inserts the post and metadata.

[0896] Step 5: Regularly post content to social media and your blog

[0897] The server automatically posts the saved posts to social media platforms and blogs periodically (for example, daily). To do this, it uses an API to connect to each platform and posts. The input is the post retrieved from the database, and the output is the post on the social media platform or blog. Specifically, it uses an API to connect to the platform and sends the post.

[0898] In this way, the server automatically performs a series of processes, saving the user time and effort while supporting continuous information dissemination.

[0899] (Application example 2)

[0900] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0901] Conventional information sharing networks lack a means to efficiently collect success stories of specific products and automatically generate and periodically distribute new posts based on them. This makes it difficult to continuously provide content that users are interested in, resulting in a decline in the freshness and usefulness of information. Furthermore, there is a need for a method to reduce the manual posting work while maintaining the quality of the generated content.

[0902] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[0903] In this invention, the server includes a means for reading success stories of specific products posted on the information sharing network, a means for generating a program using a generative AI model that generates new posting content based on the read success stories, and a means for periodically posting the generated program. This makes it possible to automatically generate and periodically distribute fresh and useful content that interests users.

[0904] An "information sharing network" is an online platform where users can post information and share it with other users.

[0905] "Specific product" refers to a specific good or service used in a particular market or application.

[0906] A "success story" is a documented case that documents the success or results achieved by using a particular product.

[0907] A "reading means" is a device or program that has the function of obtaining specific data from an information sharing network and converting it into a format that can be used within the system.

[0908] A "generative AI model" is an algorithm or program that uses artificial intelligence techniques to generate new text or content.

[0909] A "program generating means" is a device or software that has the function of automatically creating a program with a specific function based on specific input data.

[0910] A "means for posting periodically" is a device or program that has the function of automatically posting content at regular time intervals.

[0911] An "expert" refers to an individual or organization with advanced knowledge or skills in a particular field.

[0912] A "prompt" is an instruction or question that is input into a generative AI model to determine the direction and content of the generated content.

[0913] The system for implementing this invention reads successful cases of acquiring specific products posted on an information sharing network, generates new posting content based on the cases, and periodically distributes the content. A specific embodiment of the system is described below.

[0914] The server first collects success stories for a specific product from the information sharing network. This collection can be done using APIs or web scraping technology. The collected success stories are stored in a database for later processing.

[0915] The server then uses a generative AI model to generate new posts based on the collected success stories. A suitable model for this purpose is the GPT-2 model using Hugging Face's Transformers library. The prompt text to be input to the generative AI model is in the following format:

[0916] Please generate new posts based on the following success stories:

[0917] Success Story 1: A company implemented a new marketing strategy and saw a 20% increase in sales.

[0918] Success Story 2: A startup developed an innovative product and quickly gained market share.

[0919] Success Story 3: A nonprofit organization ran an effective campaign and raised a lot of donations.

[0920] By inputting this prompt into the generative AI model, new posts are generated, which are then stored in the database and distributed periodically.

[0921] The server has a scheduling function to distribute generated posts periodically. For example, you can use the Python schedule library to automatically distribute new posts at a specific time each day.

[0922] This system ensures that users always receive fresh and useful content, and improves operational efficiency by reducing manual posting work.

[0923] As a specific example, a company can collect success stories of how they increased sales by 20% after implementing a new marketing strategy, and then use a generative AI model to generate new posts based on those stories. These new posts are automatically distributed at 10:00 every day, ensuring that users always have access to useful information based on the latest success stories.

[0924] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0925] Step 1:

[0926] The server collects success stories for specific products from the information sharing network. Specifically, it obtains success story data using APIs and web scraping technology. The input is the URL or API endpoint of the information sharing network, and the output is the success story data. The data is obtained in JSON or text format and stored in a database.

[0927] Step 2:

[0928] The server reads the collected success stories from the database. The input is a database query and the output is a list of success stories. The success stories retrieved from the database are loaded into memory for use in the next step.

[0929] Step 3:

[0930] The server generates a prompt based on the success stories it has read. The input is a list of success stories, and the output is a prompt to be input to the generative AI model. Specifically, it formats the success stories into text and creates a prompt like this:

[0931] Please generate new posts based on the following success stories:

[0932] Success Story 1: A company implemented a new marketing strategy and saw a 20% increase in sales.

[0933] Success Story 2: A startup developed an innovative product and quickly gained market share.

[0934] Success Story 3: A nonprofit organization ran an effective campaign and raised a lot of donations.

[0935] Step 4:

[0936] The server generates new posts using a generative AI model. The input is the prompt text, and the output is the generated post. Specifically, using Hugging Face's Transformers library, the server inputs the prompt text into a GPT-2 model to generate new text.

[0937] Step 5:

[0938] The server stores the generated posts in a database. The input is the generated posts, and the output is the posts stored in the database. The stored posts are distributed periodically in a later step.

[0939] Step 6:

[0940] The server periodically distributes the generated posts using a scheduling function. The input is the posts stored in the database, and the output is posts to the information sharing network. Specifically, it uses the Python schedule library to automatically distribute new posts at a specific time every day.

[0941] Example 3

[0942] Next, a description will be given of Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0943] In information-sharing social networking sites, there is a need for experts in specific fields to efficiently share success stories. However, manual posting takes time and effort, which can delay information sharing. It is also difficult to maintain a consistent quality of the content posted. To solve these issues, a system is needed that can efficiently and automatically post success stories.

[0944] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[0945] In this invention, the server includes means for a user to input a prompt sentence, means for sending the prompt sentence to a generative AI model, means for the generative AI model to generate a post content, means for receiving the generated post content, means for sending the post content to an information-sharing SNS, and means for the information-sharing SNS to display the post. This makes it possible to automatically generate high-quality post content based on the prompt sentence entered by the user and efficiently post it to the information-sharing SNS.

[0946] A "user" is a person or organization that uses the system to input prompt text and gives instructions for generating content to be posted on the information-sharing SNS.

[0947] A "prompt sentence" is an instruction sentence that a user inputs to a generative AI model, and is a sentence that contains information that will form the basis of the generated post content.

[0948] A "generative AI model" is an artificial intelligence model that automatically generates appropriate post content based on a prompt entered by the user.

[0949] "Post content" refers to text and information generated by a generative AI model and posted to an information-sharing SNS.

[0950] An "information sharing SNS" is a social networking service used by experts in a particular field to share information and success stories.

[0951] The "server" is a computer system that receives prompt text from the user, sends it to the generative AI model, and posts the generated post content to an information-sharing SNS.

[0952] "Means" refers to a method or device for realizing a specific function or role.

[0953] This invention is a system for enabling experts in a specific field to efficiently share success stories on an information-sharing SNS. A specific embodiment of this system will be described below.

[0954] First, the user uses a device (such as a PC or smartphone) to access a dedicated input form. This input form is provided as an application that runs on a web browser. The user enters a prompt into the input form and clicks the submit button. For example, the user enters the following prompt:

[0955] "Submit a success story about Project X, where the entire team worked remotely and achieved their goal ahead of schedule. The use of a task management tool was particularly effective."

[0956] Next, the server receives the prompt sent from the device. The server sends this prompt to the API endpoint of a generative AI model (e.g., GPT-4). The generative AI model analyzes the prompt and generates appropriate post content. The generated post content is sent back to the server.

[0957] The server receives the post content returned from the generative AI model and converts it into a data format suitable for posting to an information-sharing SNS. Examples of information-sharing SNS include Slack and Microsoft Teams. The server uses the information-sharing SNS's API to send the generated post content to a specific channel. The API request includes authentication information along with the post content.

[0958] Finally, the information-sharing SNS displays the posted content received from the server on the specified channel, allowing other users on the SNS to view the posted content in real time.

[0959] This system allows users to automatically generate high-quality posts by simply entering a prompt, enabling them to post efficiently to the information-sharing SNS. This allows information to be shared quickly and effectively. The flow of the specific processing in Example 3 will be described with reference to FIG. 15.

[0960] Step 1:

[0961] The user enters a prompt statement.

[0962] The user opens a browser on their device and accesses a dedicated input form, entering the following: "Please post a success story about Project X. In Project X, the entire team worked remotely and achieved their goal earlier than expected. The use of a task management tool was particularly effective.", and then clicks the submit button.

[0963] Input: prompt statement

[0964] Output: Prompt sent from terminal to server

[0965] Step 2:

[0966] The server sends a prompt to the generative AI model.

[0967] The server receives the prompt sent from the device and sends it to the API endpoint of the generative AI model (e.g., GPT-4).

[0968] Input: The prompt received from the terminal

[0969] Output: Sending a prompt to the generative AI model

[0970] Step 3:

[0971] A generative AI model generates the post content.

[0972] The generative AI model generates post content based on the prompt it receives. For example, the generative AI model might generate a post like, "Sharing a success story about Project X! In this project, everyone worked remotely and achieved the goal earlier than expected. In particular, the use of a task management tool was very effective. We appreciate the efforts and cooperation of everyone on the team!"

[0973] Input: prompt statement

[0974] Output: Generated post

[0975] Step 4:

[0976] The server receives the generated post.

[0977] The server receives the post content generated by the generative AI model and converts it into a data format suitable for posting to an information-sharing SNS.

[0978] Input: Generated post content from a generative AI model

[0979] Output: Post content converted into a data format suitable for posting to information-sharing SNS

[0980] Step 5:

[0981] The server sends the post to the information-sharing SNS.

[0982] The server uses the API of an information sharing SNS (e.g., Slack) to send the generated post content to a specific channel. The API request includes authentication information along with the post content.

[0983] Input: Post content converted into data format

[0984] Output: Sending the content posted to an information sharing SNS

[0985] Step 6:

[0986] Information sharing social networking sites display posts.

[0987] The information-sharing SNS displays the posted content received from the server on the specified channel, allowing other users on the SNS to view the posted content in real time.

[0988] Input: Post content received from the server

[0989] Output: Display of posts on information-sharing SNS

[0990] (Application example 3)

[0991] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0992] In order to improve work efficiency in logistics centers, it is important to share the success stories and best practices of experienced workers. However, manually collecting and sharing this information takes time and effort, and is inefficient. It is also difficult to maintain the quality and consistency of the information. Therefore, there is a need for a system that can efficiently and automatically generate and share success stories.

[0993] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[0994] In this invention, the server includes means for reading success stories of specific product acquisitions posted on an information sharing network, means for generating a program that posts the read success stories daily, means for running the generated program as a specific role, means for automatically generating success stories using a generative AI model, and means for posting the generated success stories so that other workers can view them. This enables efficient and automatic generation and sharing of success stories in a logistics center.

[0995] An "information sharing network" is an online platform for sharing information about specific products and services.

[0996] "Specific products" refers to the goods and items handled at the distribution center.

[0997] A "success story" is a specific example that demonstrates efficient work procedures or best practices for a particular product.

[0998] A "means of reading" is a function or process for obtaining specific information from an information sharing network.

[0999] A "daily posting program" is software for posting specific information on an online platform on a regular basis.

[1000] A "generating means" is a function or process that produces new programs or data for a specific purpose.

[1001] A "specific role" is a role for performing a specific function or task within the system.

[1002] A "generative AI model" is a model designed to accomplish a specific task using artificial intelligence.

[1003] "Means of automatic generation" refers to functions or processes that use artificial intelligence to automatically generate specific information or data.

[1004] "Means of posting" refers to the functions and processes for publishing generated information on an online platform.

[1005] "Skilled workers" refers to workers with high skills and experience at logistics centers.

[1006] A system for implementing this invention includes means for reading success stories of acquiring a specific product posted on an information sharing network, means for generating a program that posts the read success stories daily, means for operating the generated program as a specific role, means for automatically generating success stories using a generative AI model, and means for posting the generated success stories so that other workers can view them.

[1007] System configuration

[1008] Hardware

[1009] Server: A computer that retrieves data from an information-sharing network and runs generative AI models.

[1010] Smartphone: A device that allows workers to view and post success stories.

[1011] software

[1012] Python: A programming language for running generative AI models.

[1013] OpenAI API: A service that provides generative AI models.

[1014] Processing flow

[1015] 1. Information loading: The server loads the success stories of specific products posted on the information sharing network.

[1016] 2. Prompt sentence generation: The server generates prompt sentences related to specific tasks at the logistics center.

[1017] 3. Calling the generative AI model: The server uses the OpenAI API to input prompt statements into the generative AI model and generate success stories.

[1018] 4. Posting success stories: The server posts the generated success stories to the information sharing network so that other workers can view them.

[1019] Specific examples

[1020] For example, when sorting packages at a logistics center, a generative AI model can generate success stories like the following:

[1021] "When sorting packages, we can process larger packages first, followed by smaller packages, making efficient use of workspace. We can also use barcode scanners to manage inventory in real time, reducing errors."

[1022] Prompt Sentence Examples

[1023] "Please tell us some success stories about efficient package sorting methods in distribution centers."

[1024] "What are some best practices for speeding up picking operations?"

[1025] In this way, by sharing the generated success stories within the application, the work efficiency of the entire logistics center can be improved.

[1026] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1027] Step 1:

[1028] The server accesses the information sharing network and loads the acquisition success stories for the particular product.

[1029] Input: Information sharing network URL and authentication information.

[1030] Data processing: Obtaining success story data from the network and converting it into the required format.

[1031] Output: Success story data.

[1032] Step 2:

[1033] The server generates a program to post daily based on the success stories it has read.

[1034] Input: Success story data.

[1035] Data calculation: Analyze data from success stories and generate a posting schedule.

[1036] Output: A program that posts daily.

[1037] Step 3:

[1038] The server runs the generated program as a specific role.

[1039] Input: A program that posts daily.

[1040] Data calculation: Run the program and post success stories at the specified time.

[1041] Output: Posted success stories.

[1042] Step 4:

[1043] The server automatically generates success stories using a generative AI model.

[1044] Input: Prompt statement.

[1045] Data calculation: Using the OpenAI API, prompt sentences are input to the generative AI model to generate success stories.

[1046] Output: Generated success stories.

[1047] Step 5:

[1048] The server posts the generated success stories to an information sharing network so that other workers can view them.

[1049] Input: Generated success stories.

[1050] Data processing: Convert success stories into a posting format for the information sharing network.

[1051] Output: Success stories posted to an information sharing network.

[1052] 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.

[1053] "Example 1"

[1054] We will explain an example of a system using an emotion engine. In this system, a program that posts success stories every day adjusts the content of the posts using an emotion engine that recognizes the user's emotions. Specifically, the emotion engine analyzes the emotions in the user's SNS posts and optimizes the content of the posts based on the analysis results. For example, if a user's post expresses joy or excitement, the emotion engine uses that information to select success stories that evoke similar emotions and generate post content. This enables posts to be made appropriately in accordance with the user's emotions, making it easier to attract the user's attention.

[1055] "Example 2"

[1056] An example of an embodiment in which an emotion engine analyzes emotions from a user's SNS posts will be described. In this embodiment, the emotion engine analyzes emotions from a user's SNS posts. Specifically, the emotion engine uses natural language processing technology to extract emotions from the text of a user's post. For example, the emotion of "joy" is extracted from a post such as "I'm so happy to have gotten this product!" The emotional information extracted in this way is used to generate the post content.

[1057] "Example 3"

[1058] An example of a form in which post content is optimized based on emotions analyzed by an emotion engine will be described. In this form, the emotion engine optimizes post content based on the analyzed emotions. Specifically, the emotion engine generates post content that users can easily empathize with based on the analyzed emotion information. For example, if a user expresses the emotion of "joy," the emotion engine uses that information to select success stories that enhance the "joy" and generates post content. This enables posts that are appropriate to the user's emotions and more easily attracts the user's attention.

[1059] The processing flow of each embodiment will be described below.

[1060] "Example 1"

[1061] Step 1: Collect users' social media posts.

[1062] Step 2: Analyze user sentiment from the collected posts using an emotion engine.

[1063] Step 3: Adjust your posts based on the analyzed sentiment.

[1064] Step 4: Post the adjusted content to social media.

[1065] "Example 2"

[1066] Step 1: Collect users' social media posts.

[1067] Step 2: Analyze user sentiment from the collected posts using an emotion engine.

[1068] Step 3: Generate post content based on the analyzed emotions.

[1069] Step 4: Post the generated post to social media.

[1070] "Example 3"

[1071] Step 1: Collect users' social media posts.

[1072] Step 2: Analyze user sentiment from the collected posts using an emotion engine.

[1073] Step 3: Optimize your posts based on the analyzed sentiment.

[1074] Step 4: Post your optimized post to social media.

[1075] Example 1

[1076] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1077] In conventional information-sharing network services, it was difficult to efficiently collect success stories of specific product acquisitions and generate optimal posting content that matched users' emotions. Furthermore, there was a lack of a way to automatically generate appropriate posting content to attract users' attention. This made it difficult to maintain users' interest, and information was not being used effectively.

[1078] 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.

[1079] In this invention, the server includes means for reading success stories of specific products posted on an information sharing network service, means for analyzing the read success stories, means for generating a program for posting the analyzed success stories daily, means for operating the generated program as a specific role, means for analyzing user emotions, and means for optimizing the posted content based on the analyzed emotions. This makes it possible to efficiently collect success stories related to specific products and automatically generate optimal posted content according to the user's emotions.

[1080] An "information sharing network service" is an online platform where users can post information and share it with other users.

[1081] "Specific products" refer to goods or services that are of interest in a particular market or application.

[1082] "Acquired Success Stories" refer to specific examples or experiences of success using a particular product.

[1083] "Means of reading" refers to the methods and techniques for obtaining data from an information sharing network service.

[1084] "Means of analysis" refers to methods and techniques for analyzing acquired data and extracting useful information.

[1085] A "daily posting program" refers to software or scripts that automatically post analyzed success stories every day.

[1086] "Means for operating as a specific role" refers to methods and techniques for executing a generated program according to a specific function or purpose.

[1087] "Means for analyzing user emotions" refers to methods and technologies for analyzing emotions from user posts and behavior and calculating an emotion score.

[1088] "Means for optimizing post content" refers to methods and techniques for adjusting post content to attract user interest based on analyzed emotions.

[1089] MODE FOR CARRYING OUT THE INVENTION

[1090] This invention provides a system that efficiently collects successful cases of acquiring a specific product posted on an information sharing network service and generates optimal posting content according to the user's emotions. Specific embodiments of this system are described below.

[1091] Program Generation

[1092] The server generates a program for reading success stories of specific products posted on an information sharing network service. This program has a function of extracting success stories from the network service used by experts on the specific product.

[1093] Program processing

[1094] The server performs the following processing using the generated program.

[1095] 1. Data Collection:

[1096] The server collects posted data from network services used by experts of specific products, using the APIs of SNSs (e.g., Twitter API or Facebook Graph API).

[1097] 2. Keyword analysis:

[1098] The server analyzes the collected posting data and extracts specific keywords and hashtags using natural language processing libraries (e.g., NLTK and spaCy).

[1099] 3. Extraction of success stories:

[1100] The server automatically extracts posts related to success stories based on the extracted keywords and hashtags, allowing for efficient collection of useful information about specific products.

[1101] 4. Emotion analysis:

[1102] The server uses an emotion engine (e.g., IBM Watson Natural Language Understanding or Microsoft Azure Text Analytics) to analyze emotions from users' social media posts.

[1103] 5. Optimize your posts:

[1104] The server optimizes the content of success stories based on the results of sentiment analysis. For example, if a user's post expresses joy or excitement, it selects success stories that evoke similar emotions and generates posts accordingly.

[1105] Specific examples

[1106] When a user posts on social media, "I tried a new product and I'm so happy!", the server passes this post to the emotion engine to obtain emotion scores such as "joy" or "satisfaction." Next, based on these emotion scores, the server selects success stories that similarly evoke joy or satisfaction, and generates a post with the content, "Other users are also having great success with this product!"

[1107] Prompt Sentence Examples

[1108] "Analyze the emotions of users' posts on social media, select success stories based on those emotions, and generate posts. For example, if a user's post expresses joy or excitement, select success stories that evoke similar emotions."

[1109] In this way, the server generates appropriate posts according to the user's emotions, making it easier to attract the user's attention.

[1110] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1111] Step 1:

[1112] The server collects posting data related to a specific product from an information sharing network service.

[1113] Input: Posted data obtained from the network service API.

[1114] Specific operation: The server periodically sends requests to the SNS API (for example, Twitter API or Facebook Graph API) to retrieve posts related to "Product Name" and "Product Name."

[1115] Output: A list of collected submission data.

[1116] Step 2:

[1117] The server analyzes the collected posting data and extracts specific keywords and hashtags.

[1118] Input: Post data collected in step 1.

[1119] Specific operation: The server uses a natural language processing library (e.g., NLTK or spaCy) to extract frequently occurring keywords and hashtags from the post data. For example, it extracts keywords such as "success," "acquisition," and "review."

[1120] Output: A list of extracted keywords and / or hashtags.

[1121] Step 3:

[1122] The server automatically extracts posts related to success stories based on the extracted keywords and hashtags.

[1123] Input: The list of keywords and hashtags extracted in step 2.

[1124] Specific operation: The server uses the results of keyword analysis as filtering conditions to select posts that correspond to success stories. For example, it extracts posts that contain the keyword "success."

[1125] Output: A list of posts related to the success story.

[1126] Step 4:

[1127] The server analyzes emotions from users' social media posts.

[1128] Input: The user's most recent social media posts.

[1129] Specific operation: The server uses an emotion engine (such as IBM Watson Natural Language Understanding or Microsoft Azure Text Analytics) to analyze the user's post and obtain an emotion score. For example, emotions such as "joy," "excitement," and "satisfaction" are quantified.

[1130] Output: Sentiment score.

[1131] Step 5:

[1132] The server optimizes the content of the success stories posted based on the results of the sentiment analysis.

[1133] Input: The list of success story posts extracted in step 3 and the sentiment scores obtained in step 4.

[1134] Specific operation: The server selects the most appropriate success story based on the emotion score and generates a post. For example, if the user's emotion indicates "joy," it selects a success story that evokes a similar emotion and generates a post with the content "Other users are also using this product with great success!"

[1135] Output: The optimized post content.

[1136] In this way, the server generates appropriate posts according to the user's emotions, making it easier to attract the user's attention.

[1137] (Application example 1)

[1138] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1139] Conventional information-sharing SNSs lack effective ways to share success stories of specific products. Furthermore, it is difficult to make optimal product recommendations based on users' emotions, which makes it difficult to attract users' attention.

[1140] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means for reading success stories of acquiring a specific product posted on an information-sharing SNS, means for generating a program for posting the read success stories daily, means for running the generated program as a specific role, means for adjusting the posted content using an emotion engine that recognizes the user's emotions, and means for analyzing the user's SNS posts and making optimal product recommendations based on the emotions. This enables appropriate posts and product recommendations to be made in accordance with the user's emotions, making it easier to attract the user's attention.

[1141] An "information sharing SNS" is a social networking service that allows users to share information with each other.

[1142] A "specific product" is a specific good or service sold in a particular market or for a particular purpose.

[1143] "Success stories" are cases that show successful experiences or results obtained when purchasing or using a particular product.

[1144] "Reading means" refers to a method or device for acquiring information and incorporating it into the system.

[1145] A "daily posting program" is software that automatically posts specific content to social media every day.

[1146] A "specific role" is a role for performing a specific function or task within the system.

[1147] An "emotion engine" is software or hardware that analyzes a user's emotions and adjusts the system's behavior based on the results.

[1148] A "means for adjusting posted content" is a method or device for optimizing the content posted to an SNS based on the user's emotions.

[1149] "Means for analyzing SNS posts" refers to a method or device for analyzing content posted on SNS and extracting specific information.

[1150] A "means for making product recommendations" is a method or device for recommending a particular product to a user.

[1151] The following describes the mode for carrying out the present invention: First, the system includes the following main components:

[1152] 1. A way to read success stories of specific products posted on information-sharing social networking sites

[1153] 2. A way to generate a program that posts the success stories it reads every day

[1154] 3. How to make the generated program act as a specific role

[1155] 4. A method for adjusting post content using an emotion engine that recognizes user emotions

[1156] 5. A method to analyze users' social media posts and make optimal product recommendations based on their emotions

[1157] System Program

[1158] The system is implemented using Python. Specifically, it uses the TextBlob library to analyze users' social media posts and recognize their emotions. It also uses the BeautifulSoup library to extract success stories about specific products from the web. Based on this data, it makes optimal product recommendations based on the user's emotions.

[1159] Processing Description

[1160] Hardware and Software

[1161] Hardware: Smartphone

[1162] Software: Python, TextBlob (sentiment analysis library), BeautifulSoup (web scraping library)

[1163] Data processing and calculation

[1164] 1. SNS Post Analysis: The server analyzes the user's SNS posts using TextBlob and recognizes emotions. For example, if the user's post is "I'm really excited about this new gadget!", the emotion is recognized as "joy."

[1165] 2. Success story extraction: The server uses BeautifulSoup to extract success stories about a specific product from the Web. For example, it extracts success stories about the latest smartphones.

[1166] 3. Emotion-based recommendation: The server makes optimal product recommendations to users based on their recognized emotions. For example, if a user expresses the emotion "joy," it will recommend the most popular success stories.

[1167] Specific examples

[1168] User Submission: "I'm really excited about this new gadget!"

[1169] Product name: "Latest Smartphone"

[1170] Recommendation: "This phone has dramatically improved my photography!"

[1171] Prompt Sentence Examples

[1172] An example of a prompt for the generative AI model is as follows:

[1173] Create a program that analyzes users' social media posts, recognizes their emotions, and recommends success stories for specific products. If the user's post is "I'm really excited about this new gadget!" and the product name is "Latest Smartphone," recommend the most suitable success story.

[1174] In this way, it becomes possible to make posts and product recommendations that are appropriate to the user's emotions, making it easier to attract the user's attention.

[1175] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1176] Step 1:

[1177] The server retrieves the user's SNS posts. The input is the user's SNS post, and the output is the retrieved post data. Specifically, the server uses the SNS API to retrieve the user's latest posts.

[1178] Step 2:

[1179] The server analyzes the social media posts acquired using the TextBlob library and recognizes emotions. The input is the acquired post data, and the output is the analyzed emotion data. Specifically, the server passes the post content to TextBlob and determines whether the emotion is positive, negative, or neutral.

[1180] Step 3:

[1181] The server extracts success stories related to a specific product from the web. The input is the name of a specific product, and the output is the extracted success story data. Specifically, the server uses the BeautifulSoup library to scrape success stories related to the specified product from a website.

[1182] Step 4:

[1183] The server then recommends optimal products to users based on the recognized emotions. The input is the analyzed emotion data and success case data, and the output is the recommended success case. Specifically, the server selects the most appropriate case from the success case data based on the emotion data.

[1184] Step 5:

[1185] The server notifies the user of the selected success story. The input is the recommended success story, and the output is a notification message to the user. Specifically, the server uses the SNS API to send a message including the success story to the user.

[1186] Step 6:

[1187] The server generates a program that posts success stories every day and runs it as a specific role. The input is the success story data, and the output is the generated program. Specifically, the server sets a schedule for automatically posting success stories and runs the program.

[1188] Example 2

[1189] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1190] In conventional information sharing networks, it was difficult to efficiently collect success stories of specific products, generate new posts based on them, and post them regularly. It was also difficult to analyze emotions from user posts and reflect that emotional information in the generation of posts. This resulted in issues such as not being able to keep users interested and reducing the effectiveness of information sharing.

[1191] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for reading success stories of specific product acquisitions posted on the information sharing network, means for analyzing the read success stories, means for generating new posting content based on the analyzed success stories, means for periodically posting the generated posting content, means for analyzing emotions from user posts, and means for using the analyzed emotional information to generate posting content. This makes it possible to efficiently collect success stories, generate new posting content that attracts users' attention based on the success stories, and post the new posting content periodically. Furthermore, by reflecting users' emotional information, more effective information sharing can be achieved.

[1192] An "information sharing network" is an online platform for users to share information about specific products or services.

[1193] A "success story" is an example that demonstrates specific results or positive outcomes achieved by using a particular product or service.

[1194] A "reading means" is a function or process for obtaining specific information from a database or file system.

[1195] "Means of analysis" refers to the functions and processes for analyzing acquired data using natural language processing technology, etc., and extracting important information.

[1196] "Means of generation" refers to the functions and processes for creating new content or posts based on analyzed information.

[1197] A "periodic posting mechanism" is a function or process for automatically posting generated content to an online platform at regular intervals.

[1198] "Means for analyzing emotions" refers to functions or processes that use natural language processing technology to extract emotions from user posts and classify those emotions.

[1199] "Means for utilizing emotional information" refers to functions and processes for generating new content and adjusting posted content based on analyzed emotional information.

[1200] This invention is a system that efficiently collects successful cases of acquiring specific products posted on an information sharing network, generates new posting content based on the collected information, and posts the content periodically. It also analyzes emotions from users' posts and reflects this emotional information in the generated posting content.

[1201] System configuration

[1202] The server implements the system using the following hardware and software.

[1203] Hardware: The server has a powerful processor, sufficient memory, and a large storage device.

[1204] Software: The server uses a database management system (e.g., MySQL), natural language processing libraries (e.g., NLTK, spaCy), generative AI models (e.g., GPT-3), and scheduling software (e.g., cron jobs).

[1205] Program processing

[1206] The server processes and calculates the data in the following procedure.

[1207] 1. Loading success stories:

[1208] The server loads success stories from a database or the file system. Specifically, the server connects to a MySQL database and retrieves data from the table where the success stories are stored. For example, it executes the SQL query "SELECT FROM success_stories WHERE date = CURDATE()".

[1209] 2. Natural Language Processing Analysis:

[1210] The server analyzes the text of success stories using natural language processing technology. Specifically, the server uses NLP libraries such as NLTK and spaCy to extract important information from the text. For example, it extracts keywords such as "sales" and "20% increase" from the phrase "sales increased by 20%."

[1211] 3. Generate a new post:

[1212] The server generates new post content based on the extracted information. At this time, the server uses a generative AI model (e.g., GPT-3) to generate natural-sounding sentences. For example, the server inputs a prompt such as, "Success story: Sales increased by 20%. Please generate new SNS post content based on this success story."

[1213] 4. Emotion analysis:

[1214] The emotion engine analyzes emotions from users' social media posts. Specifically, the emotion engine uses natural language processing technology to extract emotions from the text of users' posts. For example, it extracts the emotion of "joy" from a post such as "I'm so happy to have gotten this product!"

[1215] 5. Post regularly:

[1216] The server periodically posts the generated posts to the social networking site using scheduling software (e.g., a cron job). For example, every day at 9:00 AM, the server could post, "We've received exciting news from customers who have introduced our new product that their sales have increased by 20%!"

[1217] Specific examples

[1218] Examples:

[1219] Loading success stories: The server executes the SQL query "SELECT FROM success_stories WHERE date = CURDATE()" to retrieve the success stories for today's date.

[1220] Natural language processing analysis: The server tokenizes the text "Sales increased by 20%" and extracts keywords such as "sales" and "20% increase."

[1221] Generating new post content: The server inputs the prompt sentence "Success story: Sales increased by 20%. Please generate new SNS post content based on this success story" into the generative AI model, and generates the sentence "We received the happy news that a customer who introduced our new product has increased their sales by 20%!"

[1222] Sentiment Analysis: The sentiment engine extracts the emotion "joy" from the post "I'm so happy I got this product!"

[1223] Periodic Posting: The server sets up a cron job that calls the SNS API at 9am every day and posts the generated post.

[1224] In this way, the server generates new posting content based on successful cases, analyzes user emotions using an emotion engine, and creates a system that posts to SNS periodically.

[1225] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1226] Step 1:

[1227] The server reads the success stories of a specific product posted on the information sharing network. Specifically, the server connects to the MySQL database and retrieves data from the table where the success stories are stored. As input, it executes the SQL query "SELECT FROM success_stories WHERE date = CURDATE()" and retrieves the success story data for today's date as output.

[1228] Step 2:

[1229] The server analyzes the text of the success stories it has loaded using natural language processing technology. Specifically, the server uses NLP libraries such as NLTK and spaCy to extract important information from the text. It receives the text data of the success stories as input and obtains extracted keywords and phrases as output. For example, it extracts keywords such as "sales" and "20% increase" from the phrase "sales increased by 20%."

[1230] Step 3:

[1231] The server generates new post content based on the extracted information. Specifically, the server uses a generative AI model (e.g., GPT-3) to generate natural-sounding sentences. As input, the extracted keywords and phrases are incorporated into a prompt sentence, which is then input into the generative AI model. The generated post content is obtained as output. For example, inputting the prompt sentence, "Success story: Sales increased by 20%. Please generate new SNS post content based on this success story," generates the sentence, "We received the happy news that a customer who introduced our new product has increased their sales by 20%!"

[1232] Step 4:

[1233] The emotion engine analyzes emotions from users' social media posts. Specifically, the emotion engine uses natural language processing technology to extract emotions from the text of users' posts. It receives the user's post text as input and obtains the extracted emotion label as output. For example, it extracts the emotion "joy" from a post such as "I'm so happy to have gotten this product!"

[1234] Step 5:

[1235] The server periodically posts the generated post content to SNS. Specifically, the server uses scheduling software (e.g., cron job). As input, it receives the generated post content and posting schedule, and as output, it calls the SNS API at the specified time to post. For example, every day at 9:00 AM, it posts, "We've received exciting news from a customer who introduced our new product that their sales have increased by 20%!"

[1236] In this way, the server generates new posting content based on successful cases, analyzes user emotions using an emotion engine, and creates a system that posts to SNS periodically.

[1237] (Application example 2)

[1238] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1239] In conventional information sharing networks, success stories are posted without considering the feelings of users, which makes it difficult to attract users' attention. In addition, regular posting is often done manually, which is inefficient.

[1240] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1241] In this invention, the server includes means for reading success stories of specific product acquisitions posted on the information sharing network, means for generating a program for posting the read success stories daily, means for operating the generated program in a specific role, means for analyzing emotions from user posts, means for generating new post content based on the analyzed emotional information, and means for periodically posting the generated post content. This enables effective posting based on user emotions and automates periodic posting, enabling efficient information sharing.

[1242] An "information sharing network" is an online platform where users can post information and share it with other users.

[1243] "Specific products" refers to specific goods or services offered by a particular company or brand.

[1244] "Success stories" are posts that show the success and satisfaction that users have gained from purchasing or using a particular product.

[1245] "Means of reading" refers to the methods and techniques for obtaining specific data from an information sharing network.

[1246] A "daily posting program" is software that automatically posts specific content every day.

[1247] "Means of generation" refers to methods and techniques for creating new data or programs for a specific purpose.

[1248] A "specific role" refers to a role that performs a specific function or task within the system.

[1249] "Means for operating" refers to the methods and techniques for actually running the generated program or system.

[1250] "Means for analyzing emotions" refers to methods and technologies for extracting and analyzing emotions from user posts.

[1251] "Emotion information" refers to emotion data extracted from users' posts.

[1252] "Means for generating new posts" refers to methods and technologies for creating new posts based on analyzed emotional information.

[1253] "Means for posting periodically" refers to methods or techniques for automatically posting at specific time intervals.

[1254] A system for implementing this invention includes means for reading success stories of acquiring a specific product posted on an information sharing network, means for generating a program that posts the read success stories every day, means for operating the generated program as a specific role, means for analyzing emotions from user posts, means for generating new post content based on the analyzed emotional information, and means for periodically posting the generated post content.

[1255] Program processing explanation

[1256] Hardware and software used

[1257] Hardware: Servers, smartphones, smart glasses

[1258] Software: Python, Transformers library, Schedule library

[1259] Data processing and calculation

[1260] 1. Data Acquisition from Information Sharing Networks:

[1261] The server acquires success stories about specific products from the information sharing network. This data is text data posted by users.

[1262] 2. Emotion analysis:

[1263] The server inputs the text data of the acquired success stories into a sentiment analysis engine (Transformers sentiment-analysis model) and analyzes the user's emotions. For example, the emotion of "joy" is extracted from a post such as "I'm so happy I got this product!"

[1264] 3. Generate a new post:

[1265] The server generates new post content based on the analyzed emotional information. For example, if the emotion of "joy" is extracted, it generates a post content such as "Use our product and become happy!"

[1266] 4. Post regularly:

[1267] The server sets up a schedule for periodically posting the generated posts, using the Schedule library to automatically post at a specific time each day.

[1268] Examples and prompts

[1269] Specific examples

[1270] Success Story: "I'm so happy I got this product!"

[1271] Emotion analysis result: "joy"

[1272] Post generated: "Use our product and make yourself happy!"

[1273] Prompt Sentence Examples

[1274] Analyze emotions from users' social media posts and generate ads based on those emotions. For example, extract the emotion of "joy" from a post such as "I'm so happy I got this product!" and generate an ad that says, "Use our product and become happy!"

[1275] In this way, effective posting based on the user's emotions becomes possible, and regular posting is also automated, resulting in efficient information sharing.

[1276] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1277] Step 1:

[1278] The server acquires success stories about specific products from the information sharing network. The input is the posted data on the information sharing network, and the output is the text data of the acquired success stories. Specifically, the server acquires the posted data from the network using an API and saves it in text format.

[1279] Step 2:

[1280] The server inputs the text data of the acquired success stories into a sentiment analysis engine to analyze the user's sentiment. The input is the text data of the success stories, and the output is the analyzed sentiment information. Specifically, sentiment is extracted from the text data using the sentiment-analysis model of the Transformers library.

[1281] Step 3:

[1282] The server generates new post content based on the analyzed emotional information. The input is the emotional information, and the output is the new post content. Specifically, the server automatically generates new post content using a template based on the emotional information.

[1283] Step 4:

[1284] The server schedules the generated posts for periodic posting. The input is the new post, and the output is the scheduled posting task. Specifically, it uses the Schedule library to set up a task to post at a specific time every day.

[1285] Step 5:

[1286] The server posts new posts to the information sharing network according to a set schedule. The input is the scheduled posting task, and the output is the actual posted content. Specifically, the server uses an API to post the generated posts to the network.

[1287] Example 3

[1288] Next, a description will be given of Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1289] Conventional information sharing network services have had the problem that it is difficult to generate appropriate posting content that reflects users' emotions, making it difficult to attract users' attention. Furthermore, success stories posted tend to be formulaic, making it difficult to empathize with users' emotions. This has led to problems such as a decrease in the efficiency of information sharing and a decrease in user engagement.

[1290] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1291] In this invention, the server includes means for reading success stories of acquiring a specific product posted to an information sharing network service, means for generating a program for posting the read success stories daily, means for operating the generated program as a specific role, means for collecting user emotion data, emotion analysis means for analyzing the collected emotion data, means for using a generative AI model for generating post content based on the analysis results, and means for posting the generated post content to the information sharing network service. This enables appropriate post content to be generated in accordance with the user's emotion, and enables efficient information sharing on the information sharing network service.

[1292] An "information sharing network service" is an online platform where users can post information and share it with other users.

[1293] "Specific products" refers to specific goods or services available on the information sharing network service.

[1294] "Successful Acquisition Cases" refers to information that indicates successful cases and achievements regarding a particular product.

[1295] A "program" is a set of instructions designed to perform a particular function.

[1296] A "specific role" refers to a specific function or task that a program performs.

[1297] "User emotion data" is information about emotions expressed by users through their posts and comments.

[1298] "Emotion analysis means" refers to a technique or method for analyzing a user's emotion data and identifying that emotion.

[1299] A "generative AI model" is a model that uses artificial intelligence to generate text and data.

[1300] A "prompt" is an instruction or question that is input into a generative AI model.

[1301] "Posted content" refers to text or messages posted on the information sharing network service.

[1302] MODE FOR CARRYING OUT THE INVENTION

[1303] The present invention relates to a system for generating appropriate posting content in response to user emotions on an information sharing network service, thereby enabling efficient information sharing. Specific embodiments of this system will be described below.

[1304] 1. Program Generation

[1305] The server generates a program using the generative AI model. This program acts as a skilled crew and has the ability to post success stories on an information-sharing network service.

[1306] 2. Program Processing

[1307] The server analyzes the user's emotions using an emotion engine. The emotion engine uses a natural language processing library (e.g., NLTK or spaCy) to analyze text data and identify the user's emotions. For example, if a user posts, "I'm so happy that my new project was successful!", the text data is collected and the emotion engine extracts the emotion of "joy."

[1308] Next, the server inputs a prompt into the generative AI model (e.g., GPT-3) based on the emotion information obtained from the emotion engine. An example of a prompt is, "If the user expresses the emotion 'joy,' please generate a success story that highlights that joy." Based on this prompt, the generative AI model generates a post that is likely to empathize with the user's emotions. For example, a post might be generated that reads, "The new project was a success, and the whole team shared their joy!"

[1309] 3. Posting the content to social media

[1310] The server posts the generated content to the SNS. Specifically, it posts the generated text using the SNS's API. As a result, an appropriate post based on the user's emotions is displayed on the SNS.

[1311] Specific examples

[1312] For example, a user posts on a social networking site, "I'm so happy that our new project was a success!" The device collects this post and sends it to the server. The server uses an emotion engine to analyze the emotion of "joy." The server then inputs a prompt to the generative AI model: "If the user expresses the emotion 'joy,' please generate a success story that highlights their joy." The generative AI model generates a post that reads, "Our new project was a success, and the whole team shared their joy!" Finally, the server posts this post to the social networking site, and an appropriate post based on the user's emotion is displayed on the social networking site.

[1313] In this way, the server utilizes the emotion engine and generative AI model to post appropriate information according to the user's emotion, thereby enabling efficient information sharing on the information sharing network service. The flow of the identification process in Example 3 will be described with reference to Fig. 21.

[1314] Program processing flow

[1315] Step 1: Collecting user emotion data

[1316] Users post and comment on the information sharing network service. The terminal collects these posts and comments in real time and sends them to the server.

[1317] Input: User posts and comments

[1318] Output: Collected text data

[1319] Specific operation: A user posts, "I'm so happy that my new project was a success!" The device collects this text data and sends it to the server.

[1320] Step 2: Emotion analysis using the emotion engine

[1321] The server passes the collected text data to the emotion engine, which uses a natural language processing library (e.g., NLTK or spaCy) to analyze the text data and identify the user's emotions.

[1322] Input: Collected text data

[1323] Output: Parsed emotion information

[1324] Specific operation: The server passes the text data "I'm so happy that the new project was a success!" to the emotion engine. The emotion engine extracts the emotion of "joy."

[1325] Step 3: Generate post content using a generative AI model

[1326] The server inputs a prompt sentence into the generative AI model based on the emotion information obtained from the emotion engine. Based on this prompt sentence, the generative AI model generates post content that is likely to resonate with the user's emotions.

[1327] Input: Analyzed emotion information, prompt sentence

[1328] Output: Generated post

[1329] Specific operation: The server inputs the prompt "If the user expresses the emotion 'joy,' please generate a success story that highlights the joy" into the generative AI model. The generative AI model then generates a post that reads, "The new project was a success, and the whole team shared their joy!"

[1330] Step 4: Post your post to social media

[1331] The server posts the generated post content to the information sharing network service. Specifically, the server posts the generated text using the API of the SNS.

[1332] Input: Generated post content

[1333] Output: Posts displayed on an information sharing network service

[1334] Specific operation: The server posts the generated message "The new project was a success, and the whole team shared their joy!" to social media.

[1335] In this way, the server utilizes the emotion engine and generative AI model to make appropriate posts based on the user's emotions, enabling efficient information sharing on the information-sharing network service.

[1336] (Application example 3)

[1337] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[1338] In conventional information sharing networks, it is difficult to generate optimal posting content that reflects users' emotions, which makes it difficult to attract users' attention. Furthermore, success stories tend to be monotonous, making it difficult to sustain users' interest. Furthermore, since content recommendations are not based on emotions, the user experience is not improved.

[1339] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1340] In this invention, the server includes means for reading success stories of specific product acquisitions posted to an information sharing network, means for generating a program for posting the read success stories daily, means for operating the generated program in a specific role, means for analyzing user emotions using an emotion analysis engine, means for generating optimal posting content based on the analyzed emotions, and means for posting the generated posting content to the information sharing network. This allows optimal posting content to be generated based on the user's emotions, attracting the user's attention. Furthermore, the success story posts are diversified, thereby sustaining the user's interest. Furthermore, content recommendations based on emotions improve the user experience.

[1341] An "information sharing network" is an online platform where users can post information and share it with other users.

[1342] "Specific products" refers to specific goods or services that are of interest to users on an information sharing network.

[1343] "Acquisition Success" refers to experiences or instances of success in acquiring or using a particular product.

[1344] "Reading means" refers to a method or device for obtaining data from an information sharing network.

[1345] "Program generation means" refers to a method or apparatus for creating software code to perform a specific task.

[1346] "Means for operating as a specific role" refers to a method or device for executing a generated program so as to perform a specific function or role.

[1347] An "emotion analysis engine" refers to software or hardware that analyzes emotions from user input data and identifies those emotions.

[1348] "User emotion" refers to the type of psychological state or emotion exhibited by the user.

[1349] "Optimal posting content" refers to information or messages that are generated based on the user's emotions and are most suitable for attracting the user's attention.

[1350] "Generated posts" refers to information and messages created by a sentiment analysis engine based on the user's emotions.

[1351] An "expert" is an individual who has advanced knowledge or skills in a particular field.

[1352] "Skilled worker" refers to an individual who has a high level of experience and skill in a particular job or task.

[1353] A system for implementing this invention includes means for reading success stories of acquiring a specific product posted on an information sharing network, means for generating a program that posts the read success stories every day, means for operating the generated program as a specific role, means for analyzing a user's emotions using an emotion analysis engine, means for generating optimal posting content based on the analyzed emotions, and means for posting the generated posting content on the information sharing network.

[1354] System program generation

[1355] The server first reads the success stories of specific products from the information sharing network. Then, it generates a program for posting the read success stories every day. This program operates as a specific role and posts the success stories periodically.

[1356] Furthermore, the server analyzes the user's emotions using a sentiment analysis engine. The sentiment analysis engine identifies emotions from the user's input data (e.g., text or voice). Based on the analysis results, the server generates post content that best matches the user's emotions. The generated post content is posted to the information sharing network.

[1357] Hardware and software used

[1358] Hardware: Server, user device (smartphone, head-mounted display, etc.)

[1359] Software: Python, EmotionEngine library, ContentRecommender library, SNS API

[1360] Data processing and calculation

[1361] The server first obtains data from the information sharing network. Then, it analyzes the user's emotions using the EmotionEngine library. Based on the analyzed emotions, it generates optimal post content using the ContentRecommender library. The generated post content is posted to the information sharing network using the SNS API.

[1362] Specific examples

[1363] For example, if a user types "I am feeling very happy today!", the emotion analysis engine will analyze the emotion of "joy." Based on this analysis, the server will recommend positive content and post it to the information sharing network.

[1364] Prompt Sentence Examples

[1365] If a user types "I am feeling very happy today!", the emotion engine should parse the emotion "joy" and recommend positive content.

[1366] In this way, optimal posting content that matches the user's emotions can be generated and posted to the information sharing network, thereby attracting the user's attention.

[1367] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1368] Step 1:

[1369] The server reads the success stories of the acquisition of a particular product from the information sharing network.

[1370] Input: Success story data from information sharing networks

[1371] Data processing: Analyze the success case data and extract the necessary information

[1372] Output: Extracted success story data

[1373] Step 2:

[1374] The server generates a program to post the success stories it has read every day.

[1375] Input: Extracted success story data

[1376] Data calculation: Generate a program that sets a regular posting schedule based on success case data

[1377] Output: Program for daily posting

[1378] Step 3:

[1379] The server runs the generated program as a specific role.

[1380] Input: Program for daily posting

[1381] Specific Actions: Implement the program and regularly post success stories

[1382] Output: Regularly posted success stories

[1383] Step 4:

[1384] The server analyzes the user's emotions using an emotion analysis engine.

[1385] Input: User input data (text or voice)

[1386] Data Calculation: Analyzing user emotions using the EmotionEngine library

[1387] Output: Parsed emotion data

[1388] Step 5:

[1389] The server generates optimal posting content based on the analyzed emotions.

[1390] Input: Parsed emotion data

[1391] Data crunching: Use the ContentRecommender library to generate optimal posts based on sentiment

[1392] Output: Optimal post content

[1393] Step 6:

[1394] The server posts the generated posting content to the information sharing network.

[1395] Input: Best post content

[1396] Specific behavior: Uses SNS API to post generated content to information sharing network.

[1397] Output: Posted content

[1398] In this way, the server generates optimal posting content according to the user's emotions and posts it to the information sharing network, thereby attracting the user's attention.

[1399] 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.

[1400] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1401] Another example of generative AI is Gemini (internet search engine). <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1402] 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.

[1403] [Third embodiment]

[1404] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[1405] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[1406] 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).

[1407] 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.

[1408] 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.

[1409] 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).

[1410] 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.

[1411] 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.

[1412] 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.

[1413] 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.

[1414] 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.

[1415] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1416] "Example 1"

[1417] One embodiment of the present invention includes a means for reading success stories of specific products posted on an information-sharing social networking site. Specifically, a program is implemented to extract success stories of specific products from social networking sites used by experts on the product. This program analyzes keywords and hashtags in the posted content and automatically extracts posts related to the success stories.

[1418] "Example 2"

[1419] Furthermore, there is a means to generate a program that posts the read success stories every day. Specifically, a program is implemented that generates new posting content based on the extracted success stories. This program automatically generates new posting content based on the content of the success stories and posts it periodically.

[1420] "Example 3"

[1421] There is also a way to make the generated program act as a specific role. Specifically, a function has been implemented to make the generated program act as an experienced crew member. This function allows the program to post success stories as an experienced crew member. This allows for efficient information sharing on the information-sharing SNS.

[1422] The processing flow of each embodiment will be described below.

[1423] "Example 1"

[1424] Step 1: Obtain posts from social media used by experts on a specific product. In this step, we use an API to obtain post data from social media.

[1425] Step 2: Extract success stories of product acquisition from the acquired posts. In this step, keywords and hashtags in the post content are analyzed and posts related to success stories are automatically extracted.

[1426] "Example 2"

[1427] Step 1: Generate new post content based on the extracted success stories. In this step, new post content is automatically generated based on the content of the success stories.

[1428] Step 2: Post the generated content on a regular basis. In this step, the generated content is posted to SNS on a regular basis.

[1429] "Example 3"

[1430] Step 1: Execute the generated program as a specific role. In this step, the generated program is executed as a skilled crew member.

[1431] Step 2: The program acting as a crew posts a success story. In this step, the program acts as an experienced crew and posts a success story.

[1432] Example 1

[1433] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1434] In conventional information sharing network services, it has been difficult to efficiently collect, analyze, and provide users with success stories of specific product acquisitions. In particular, advanced analytical techniques and efficient data management are required to extract useful information from network services used by experts. Therefore, there is a need to quickly and accurately provide users with the success stories they need.

[1435] 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.

[1436] In this invention, the server includes means for reading success stories of specific products posted on an information sharing network service, means for analyzing the read success stories, means for extracting posts related to the success stories from the analysis results, means for saving the extracted success stories in a database, and means for providing the saved success stories in response to user requests. This makes it possible to efficiently collect and analyze success stories related to specific products and provide them to users quickly and accurately.

[1437] An "information sharing network service" is an online platform that allows users to share information and interact via the Internet.

[1438] "Specific product" refers to a specific good or service sold in a specific market or application.

[1439] "Success stories" are information that shows specific cases or experiences where a particular product has been used successfully.

[1440] "Means of reading" refers to the methods and technologies for obtaining data from an information sharing network service and incorporating it into the system.

[1441] "Means of analysis" refers to methods and techniques for analyzing acquired data and extracting useful information.

[1442] "Means of extraction" refers to methods and techniques for selecting information that meets specific conditions from the analysis results.

[1443] "Means of storing in a database" refers to the methods and techniques used to systematically manage extracted information and store it for later use.

[1444] "Means for providing information in response to a user's request" refers to methods and technologies for retrieving and providing stored information in response to a user's request.

[1445] "Natural language processing technology" refers to technology that enables computers to understand and process human language.

[1446] The present invention provides a system for efficiently collecting, analyzing, and providing to users success stories of specific products posted on an information sharing network service. Specific embodiments of this system will be described below.

[1447] First, the server collects posts related to a specific product from an information-sharing network service (e.g., a social networking platform). To do this, it uses the Python libraries Tweepy and BeautifulSoup to retrieve posts containing specific hashtags (e.g., "product name" or "success stories").

[1448] Next, the server analyzes the collected post data using natural language processing (NLP) technology. NLP libraries such as NLTK and spaCy are used. This allows keywords and hashtags to be extracted from the post content, and posts related to success stories to be identified. For example, keywords such as "success," "acquisition," and "case study" can be extracted from the post content.

[1449] The server automatically extracts posts related to success stories based on the analysis results. Specifically, it uses the extracted keywords and hashtags to filter posts that correspond to success stories. For example, it selects posts that include "success story" or "product name."

[1450] The extracted success story posts are stored in a database by the server. The database uses MySQL or PostgreSQL. The data stored includes information such as the post content, poster, and posting date and time. For example, the data is saved using the MySQL INSERT statement.

[1451] When a user wants to know about success stories of a specific product, they send a request from their device to the server. The request includes the product name and related keywords. For example, a user might request, "Please tell me about success stories of product A."

[1452] The server searches the database for relevant success stories and returns them to the device. The search is performed using the SQL SELECT statement. The user can view the success stories on the device. For example, the server sends a post saved as "Product A success story" to the device.

[1453] As a concrete example, the following is an example of a prompt sentence to be input to the generative AI model.

[1454] Example prompt sentence:

[1455] "Please tell us about success stories for a specific product. Please use data collected from social media to extract posts related to success stories."

[1456] When this prompt sentence is input into the generative AI model, the model analyzes data collected from social media, extracts posts related to success stories, and provides them to the user.

[1457] The above is a specific embodiment for carrying out the present invention.

[1458] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1459] Step 1:

[1460] The server collects posts related to a particular product from an information sharing network service.

[1461] Input: Post data obtained from the API of the social media platform.

[1462] Data processing: Use Python libraries (Tweepy and BeautifulSoup) to filter posts containing specific hashtags (e.g., "product name" or "success story").

[1463] Output: The filtered post data.

[1464] Specific operation: The server calls the API of the social networking site to retrieve posts containing a specific hashtag. The retrieved posts are then filtered to select only those related to a specific product.

[1465] Step 2:

[1466] The server analyzes the collected posting data using natural language processing (NLP) technology.

[1467] Input: Filtered post data.

[1468] Data processing: Use NLP libraries (NLTK and spaCy) to extract keywords and hashtags from the post content.

[1469] Output: Extracted keywords and hashtags.

[1470] Specific operation: The server analyzes the collected posting data and extracts keywords such as "success," "acquisition," and "case study" from the posting content.

[1471] Step 3:

[1472] The server automatically extracts posts related to success stories based on the analysis results.

[1473] Input: Extracted keywords and hashtags.

[1474] Data processing: Using the extracted keywords and hashtags, posts that correspond to success stories are filtered.

[1475] Output: Post data related to the success story.

[1476] Specific operation: Based on the analysis results, the server selects posts containing specific keywords or hashtags and extracts posts related to success stories.

[1477] Step 4:

[1478] The server stores the extracted success story posts in a database.

[1479] Input: Post data related to the success story.

[1480] Data processing: Save information such as post content, poster, and posting date and time in a database (MySQL or PostgreSQL).

[1481] Output: Success story submission data stored in the database.

[1482] Specific operation: The server saves the extracted success story posts in the database using the MySQL INSERT statement.

[1483] Step 5:

[1484] When a user wants to know about success stories of a particular product, the user sends a request from the terminal to the server.

[1485] Input: User request (product name and related keywords).

[1486] Data processing: Analyze the request content and search for relevant success stories.

[1487] Output: The request data to the server.

[1488] Specific operation: The user uses the terminal to send a request saying, "Please tell me some success stories about product A."

[1489] Step 6:

[1490] The server searches the database for the relevant success story and returns it to the terminal.

[1491] Input: User request data.

[1492] Data processing: Use the SQL SELECT statement to search the database for relevant success stories.

[1493] Output: Success story submission data as search results.

[1494] Specific operation: The server searches the database based on the user's request and sends the post saved as "Product A success story" to the terminal.

[1495] Step 7:

[1496] The user views the success stories on the terminal.

[1497] Input: Successful case submission data returned from the server.

[1498] Data processing: None.

[1499] Output: Success story submission data displayed on the device.

[1500] Specific operation: The user views the success story posts sent from the server on the terminal.

[1501] (Application example 1)

[1502] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1503] Conventional information-sharing SNSs lack a means to efficiently collect and provide users with success stories about specific products. This means that users have to spend a lot of time and effort to find information that will help them when purchasing a product. Furthermore, since there is no function to automatically display success stories, users may miss out on the information they need. These issues need to be resolved.

[1504] 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.

[1505] In this invention, the server includes means for reading success stories of specific products posted on an information-sharing SNS, means for generating a program for posting the read success stories daily, means for running the generated program as a specific role, means for automatically displaying success stories related to the specific product, means for acquiring and analyzing HTML from the search result page of the SNS, and means for analyzing the posted content using regular expressions to extract posts related to the success stories. This allows users to efficiently collect success stories and easily obtain information that will be useful when purchasing a product.

[1506] An "information sharing SNS" is an online platform that allows users to share information with each other.

[1507] A "specific product" is a specific good or service sold in a particular market or for a particular purpose.

[1508] "Acquisition success stories" are cases or experiences of success when purchasing or using a particular product.

[1509] A "means for reading" is a method or device for obtaining information and converting it into a format that can be used within the system.

[1510] A "daily posting program" is software that automatically posts specific information to social media every day.

[1511] A "specific role" is a role assigned to perform a specific function or task within the system.

[1512] An "automatic display means" is a method or device for displaying information without requiring user interaction.

[1513] A "search results page" is a page that lists results generated by a search engine based on specific keywords or criteria.

[1514] "Means for acquiring and analyzing HTML" refers to a method or device for acquiring the HTML code of a web page and analyzing its content.

[1515] A "regular expression parser" is a method or device for analyzing text based on specific patterns.

[1516] The "means for extracting posts related to success stories" refers to a method or device for selecting and extracting posts that include information related to success stories.

[1517] A system for implementing this invention includes means for reading success stories of acquiring a specific product posted on an information-sharing SNS, means for generating a program that posts the read success stories every day, means for operating the generated program as a specific role, means for automatically displaying success stories related to a specific product, means for obtaining and analyzing HTML from the search results page of the SNS, and means for analyzing the posted content using regular expressions and extracting posts related to the success stories.

[1518] The server first accesses the information-sharing social networking site and searches for posts related to a specific product. Specifically, it retrieves HTML from the search results page of the social networking site and analyzes it using a library such as BeautifulSoup. Through this analysis, it extracts the content of the posts and uses regular expressions to select posts related to success stories.

[1519] The server then generates a program that automatically posts selected success stories daily, and the program acts as a specific role, automatically displaying related success stories when a user views a specific product page.

[1520] When a user searches for a specific product, the server displays success stories related to that product, allowing the user to easily obtain information that will help them make a purchase.

[1521] As a concrete example, if a user searches for a "specific product name," by inputting the following prompt sentence into the generative AI model, success stories on social media can be automatically extracted and provided to the user.

[1522] Example prompt sentence:

[1523] Please extract successful examples of acquiring "specific product names" from social media.

[1524] This system allows users to efficiently collect success stories and easily obtain information that can be used as reference when purchasing products. The hardware used includes a server and the user's smartphone, and the software used includes Python, BeautifulSoup, and requests.

[1525] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1526] Step 1:

[1527] The server accesses the information sharing SNS and searches for posts related to a specific product.

[1528] Input: Specific product name

[1529] Output: HTML data of social media search results page

[1530] Specific operation: The server uses the social networking service's search API to search for posts related to a specific product name and retrieves the results in HTML format.

[1531] Step 2:

[1532] The server analyzes the acquired HTML data.

[1533] Input: HTML data of the search results page of the social networking site

[1534] Output: Text data of the post

[1535] Specific operation: The server parses the HTML data using the BeautifulSoup library and extracts the text data of the post content.

[1536] Step 3:

[1537] The server analyzes the content of the posts using regular expressions and extracts posts related to success stories.

[1538] Input: Text data of post content

[1539] Output: A list of posts related to the success story

[1540] Specific operation: The server analyzes the content of posts using regular expressions and extracts posts containing keywords such as "success," "achievement," and "acquisition."

[1541] Step 4:

[1542] The server generates a program that automatically posts extracted success stories every day.

[1543] Input: List of posts related to success stories

[1544] Output: Daily posting program

[1545] Specific operation: Based on the list of success stories, the server generates a program to automatically post to SNS every day.

[1546] Step 5:

[1547] The server runs the generated program as a specific role.

[1548] Input: Daily posting program

[1549] Output: A program that acts as a specific role

[1550] Specific operation: The server runs the generated program and automatically posts success stories to SNS every day.

[1551] Step 6:

[1552] When a user views a particular product page, the server automatically displays related success stories.

[1553] Input: User browsing information, list of posts related to success stories

[1554] Output: Display success stories

[1555] Specific operation: When a user views a specific product page, the server sends information to the user's device to automatically display related success stories.

[1556] Example 2

[1557] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1558] In conventional information sharing network services, it was difficult to efficiently collect success stories of specific products, automatically generate new posts based on them, and post them regularly. In addition, manual posting required time and effort, making it difficult to continuously disseminate information.

[1559] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes a means for reading success stories of specific product acquisition posted on an information sharing network service, a means for generating a prompt sentence based on the read success story, a means for inputting the generated prompt sentence into a generative AI model to generate new posting content, a means for saving the generated posting content in a database, and a means for periodically posting the saved posting content. This enables automatic generation and periodic posting of new posting content based on success stories.

[1560] An "information sharing network service" is an online platform that allows users to share information and communicate.

[1561] "Specific product" refers to a specific good or service sold in a specific market or application.

[1562] "Acquisition success stories" refer to specific cases or episodes in which a particular product has achieved success in the market.

[1563] A "prompt sentence" is text to be input into a generative AI model, and is a sentence that contains the key points of a successful case.

[1564] A "generative AI model" is a model for generating text using artificial intelligence, such as one that uses natural language processing technology.

[1565] "New posts" refers to new text content generated by the generative AI model based on success stories.

[1566] A "database" is a system for systematically storing and managing information.

[1567] "Means for periodic posting" means a feature that automatically posts saved posts to an online platform at regular intervals.

[1568] The present invention relates to a system that efficiently collects successful cases of acquiring specific products posted on an information sharing network service, automatically generates new posting content based on the collected information, and posts the content periodically.

[1569] The server first reads the success case data provided by the user. This data is assumed to be stored in a text file or database. For example, the server reads the data from a file called success_cases.txt.

[1570] Next, the server generates a prompt sentence to be input to the generative AI model based on the content of the read success case. The prompt sentence is designed to include the key points of the success case. As a concrete example, the following prompt sentence can be generated:

[1571] Example prompt sentence:

[1572] "Below is an example of a company that successfully implemented a new marketing strategy. Please use this example to generate new content for your posts."

[1573] Success stories include:

[1574] "Company A implemented a new marketing strategy that leveraged social media. This strategy significantly improved customer engagement and increased sales by 20%."

[1575] The server inputs the generated prompt into a generative AI model (e.g., OpenAI's GPT-3). The generative AI model generates new posts based on the prompt. Examples of generated posts include:

[1576] An example of the generated post:

[1577] "The key point to learn from Company A's success story is that by effectively using social media, you can increase engagement with customers. With this strategy, Company A was able to increase sales by 20%. Why not try implementing a marketing strategy that utilizes social media in your own business?"

[1578] The generated post content is saved in a database by the server, along with metadata such as the posting date and time and the ID of the related success story.

[1579] Finally, the server automatically posts the saved content to social media platforms or blogs periodically (e.g., daily) by connecting to each platform using an API. For example, posts can be made using the Twitter API.

[1580] In this way, the server automatically generates new posting content based on success stories and posts it periodically, reducing the user's workload and supporting continuous information dissemination.

[1581] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1582] Step 1: Load the success story data

[1583] The server reads the success case data provided by the user. This data is assumed to be stored in a text file or database. For example, data is read from a file called success_cases.txt. The input is the text data of the success case, and the output is the content of the success case stored in memory.

[1584] Step 2: Generate a prompt statement

[1585] The server generates a prompt sentence to be input to the generative AI model based on the content of the read success story. The prompt sentence is designed to include the key points of the success story. The input is the text data of the success story, and the output is the generated prompt sentence. Specifically, it extracts the key points of the success story and creates a prompt sentence that includes them.

[1586] Step 3: Enter a prompt into the generative AI model to generate new post content

[1587] The server inputs the generated prompt text into a generative AI model (for example, OpenAI's GPT-3). The generative AI model generates new post content based on the prompt text. The input is the prompt text, and the output is the generated new post content. Specifically, the server sends the prompt text to the generative AI model and receives the generated text.

[1588] Step 4: Save the generated post to the database

[1589] The server saves the new posts obtained from the generative AI model in a database. When saving, it also saves metadata such as the posting date and time and the ID of the related success story. The input is the generated post and metadata, and the output is the post saved in the database. Specifically, it connects to the database and inserts the post and metadata.

[1590] Step 5: Regularly post content to social media and your blog

[1591] The server automatically posts the saved posts to social media platforms and blogs periodically (for example, daily). To do this, it uses an API to connect to each platform and posts. The input is the post retrieved from the database, and the output is the post on the social media platform or blog. Specifically, it uses an API to connect to the platform and sends the post.

[1592] In this way, the server automatically performs a series of processes, saving the user time and effort while supporting continuous information dissemination.

[1593] (Application example 2)

[1594] Next, a description will be given of Application Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1595] Conventional information sharing networks lack a means to efficiently collect success stories of specific products and automatically generate and periodically distribute new posts based on them. This makes it difficult to continuously provide content that users are interested in, resulting in a decline in the freshness and usefulness of information. Furthermore, there is a need for a method to reduce the manual posting work while maintaining the quality of the generated content.

[1596] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 2 is realized by the following means.

[1597] In this invention, the server includes a means for reading success stories of specific products posted on the information sharing network, a means for generating a program using a generative AI model that generates new posting content based on the read success stories, and a means for periodically posting the generated program. This makes it possible to automatically generate and periodically distribute fresh and useful content that interests users.

[1598] An "information sharing network" is an online platform where users can post information and share it with other users.

[1599] "Specific product" refers to a specific good or service used in a particular market or application.

[1600] A "success story" is a documented case that documents the success or results achieved by using a particular product.

[1601] A "reading means" is a device or program that has the function of obtaining specific data from an information sharing network and converting it into a format that can be used within the system.

[1602] A "generative AI model" is an algorithm or program that uses artificial intelligence techniques to generate new text or content.

[1603] A "program generating means" is a device or software that has the function of automatically creating a program with a specific function based on specific input data.

[1604] A "means for posting periodically" is a device or program that has the function of automatically posting content at regular time intervals.

[1605] An "expert" refers to an individual or organization with advanced knowledge or skills in a particular field.

[1606] A "prompt" is an instruction or question that is input into a generative AI model to determine the direction and content of the generated content.

[1607] The system for implementing this invention reads successful cases of acquiring specific products posted on an information sharing network, generates new posting content based on the cases, and periodically distributes the content. A specific embodiment of the system is described below.

[1608] The server first collects success stories for a specific product from the information sharing network. This collection can be done using APIs or web scraping technology. The collected success stories are stored in a database for later processing.

[1609] The server then uses a generative AI model to generate new posts based on the collected success stories. A suitable model for this purpose is the GPT-2 model using Hugging Face's Transformers library. The prompt text to be input to the generative AI model is in the following format:

[1610] Please generate new posts based on the following success stories:

[1611] Success Story 1: A company implemented a new marketing strategy and saw a 20% increase in sales.

[1612] Success Story 2: A startup developed an innovative product and quickly gained market share.

[1613] Success Story 3: A nonprofit organization ran an effective campaign and raised a lot of donations.

[1614] By inputting this prompt into the generative AI model, new posts are generated, which are then stored in the database and distributed periodically.

[1615] The server has a scheduling function to distribute generated posts periodically. For example, you can use the Python schedule library to automatically distribute new posts at a specific time each day.

[1616] This system ensures that users always receive fresh and useful content, and improves operational efficiency by reducing manual posting work.

[1617] As a specific example, a company can collect success stories of how they increased sales by 20% after implementing a new marketing strategy, and then use a generative AI model to generate new posts based on those stories. These new posts are automatically distributed at 10:00 every day, ensuring that users always have access to useful information based on the latest success stories.

[1618] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1619] Step 1:

[1620] The server collects success stories for specific products from the information sharing network. Specifically, it obtains success story data using APIs and web scraping technology. The input is the URL or API endpoint of the information sharing network, and the output is the success story data. The data is obtained in JSON or text format and stored in a database.

[1621] Step 2:

[1622] The server reads the collected success stories from the database. The input is a database query and the output is a list of success stories. The success stories retrieved from the database are loaded into memory for use in the next step.

[1623] Step 3:

[1624] The server generates a prompt based on the success stories it has read. The input is a list of success stories, and the output is a prompt to be input to the generative AI model. Specifically, it formats the success stories into text and creates a prompt like this:

[1625] Please generate new posts based on the following success stories:

[1626] Success Story 1: A company implemented a new marketing strategy and saw a 20% increase in sales.

[1627] Success Story 2: A startup developed an innovative product and quickly gained market share.

[1628] Success Story 3: A nonprofit organization ran an effective campaign and raised a lot of donations.

[1629] Step 4:

[1630] The server generates new posts using a generative AI model. The input is the prompt text, and the output is the generated post. Specifically, using Hugging Face's Transformers library, the server inputs the prompt text into a GPT-2 model to generate new text.

[1631] Step 5:

[1632] The server stores the generated posts in a database. The input is the generated posts, and the output is the posts stored in the database. The stored posts are distributed periodically in a later step.

[1633] Step 6:

[1634] The server periodically distributes the generated posts using a scheduling function. The input is the posts stored in the database, and the output is posts to the information sharing network. Specifically, it uses the Python schedule library to automatically distribute new posts at a specific time every day.

[1635] Example 3

[1636] Next, a third embodiment of the third embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1637] In information-sharing social networking sites, there is a need for experts in specific fields to efficiently share success stories. However, manual posting takes time and effort, which can delay information sharing. It is also difficult to maintain a consistent quality of the content posted. To solve these issues, a system is needed that can efficiently and automatically post success stories.

[1638] The specific processing by the specific processing unit 290 of the data processing device 12 in the third embodiment is realized by the following means.

[1639] In this invention, the server includes means for a user to input a prompt sentence, means for sending the prompt sentence to a generative AI model, means for the generative AI model to generate a post content, means for receiving the generated post content, means for sending the post content to an information-sharing SNS, and means for the information-sharing SNS to display the post. This makes it possible to automatically generate high-quality post content based on the prompt sentence entered by the user and efficiently post it to the information-sharing SNS.

[1640] A "user" is a person or organization that uses the system to input prompt text and gives instructions for generating content to be posted on the information-sharing SNS.

[1641] A "prompt sentence" is an instruction sentence that a user inputs to a generative AI model, and is a sentence that contains information that will form the basis of the generated post content.

[1642] A "generative AI model" is an artificial intelligence model that automatically generates appropriate post content based on a prompt entered by the user.

[1643] "Post content" refers to text and information generated by a generative AI model and posted to an information-sharing SNS.

[1644] An "information sharing SNS" is a social networking service used by experts in a particular field to share information and success stories.

[1645] The "server" is a computer system that receives prompt text from the user, sends it to the generative AI model, and posts the generated post content to an information-sharing SNS.

[1646] "Means" refers to a method or device for realizing a specific function or role.

[1647] This invention is a system for enabling experts in a specific field to efficiently share success stories on an information-sharing SNS. A specific embodiment of this system will be described below.

[1648] First, the user uses a device (such as a PC or smartphone) to access a dedicated input form. This input form is provided as an application that runs on a web browser. The user enters a prompt into the input form and clicks the submit button. For example, the user enters the following prompt:

[1649] "Submit a success story about Project X, where the entire team worked remotely and achieved their goal ahead of schedule. The use of a task management tool was particularly effective."

[1650] Next, the server receives the prompt sent from the device. The server sends this prompt to the API endpoint of a generative AI model (e.g., GPT-4). The generative AI model analyzes the prompt and generates appropriate post content. The generated post content is sent back to the server.

[1651] The server receives the post content returned from the generative AI model and converts it into a data format suitable for posting to an information-sharing SNS. Examples of information-sharing SNS include Slack and Microsoft Teams. The server uses the information-sharing SNS's API to send the generated post content to a specific channel. The API request includes authentication information along with the post content.

[1652] Finally, the information-sharing SNS displays the posted content received from the server on the specified channel, allowing other users on the SNS to view the posted content in real time.

[1653] This system allows users to automatically generate high-quality posts by simply entering a prompt, enabling them to post efficiently to the information-sharing SNS. This allows information to be shared quickly and effectively. The flow of the specific processing in Example 3 will be described with reference to FIG. 15.

[1654] Step 1:

[1655] The user enters a prompt statement.

[1656] The user opens a browser on their device and accesses a dedicated input form, entering the following: "Please post a success story about Project X. In Project X, the entire team worked remotely and achieved their goal earlier than expected. The use of a task management tool was particularly effective.", and then clicks the submit button.

[1657] Input: prompt statement

[1658] Output: Prompt sent from terminal to server

[1659] Step 2:

[1660] The server sends a prompt to the generative AI model.

[1661] The server receives the prompt sent from the device and sends it to the API endpoint of the generative AI model (e.g., GPT-4).

[1662] Input: The prompt received from the terminal

[1663] Output: Sending a prompt to the generative AI model

[1664] Step 3:

[1665] A generative AI model generates the post content.

[1666] The generative AI model generates post content based on the prompt it receives. For example, the generative AI model might generate a post like, "Sharing a success story about Project X! In this project, everyone worked remotely and achieved the goal earlier than expected. In particular, the use of a task management tool was very effective. We appreciate the efforts and cooperation of everyone on the team!"

[1667] Input: prompt statement

[1668] Output: Generated post

[1669] Step 4:

[1670] The server receives the generated post.

[1671] The server receives the post content generated by the generative AI model and converts it into a data format suitable for posting to an information-sharing SNS.

[1672] Input: Generated post content from a generative AI model

[1673] Output: Post content converted into a data format suitable for posting to information-sharing SNS

[1674] Step 5:

[1675] The server sends the post to the information-sharing SNS.

[1676] The server uses the API of an information sharing SNS (e.g., Slack) to send the generated post content to a specific channel. The API request includes authentication information along with the post content.

[1677] Input: Post content converted into data format

[1678] Output: Sending the content posted to an information sharing SNS

[1679] Step 6:

[1680] Information sharing social networking sites display posts.

[1681] The information-sharing SNS displays the posted content received from the server on the specified channel, allowing other users on the SNS to view the posted content in real time.

[1682] Input: Post content received from the server

[1683] Output: Display of posts on information-sharing SNS

[1684] (Application example 3)

[1685] Next, a description will be given of Application Example 3 of Form Example 3. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1686] In order to improve work efficiency in logistics centers, it is important to share the success stories and best practices of experienced workers. However, manually collecting and sharing this information takes time and effort, and is inefficient. It is also difficult to maintain the quality and consistency of the information. Therefore, there is a need for a system that can efficiently and automatically generate and share success stories.

[1687] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 3 is realized by the following means.

[1688] In this invention, the server includes means for reading success stories of specific product acquisitions posted on an information sharing network, means for generating a program that posts the read success stories daily, means for running the generated program as a specific role, means for automatically generating success stories using a generative AI model, and means for posting the generated success stories so that other workers can view them. This enables efficient and automatic generation and sharing of success stories in a logistics center.

[1689] An "information sharing network" is an online platform for sharing information about specific products and services.

[1690] "Specific products" refers to the goods and items handled at the distribution center.

[1691] A "success story" is a specific example that demonstrates efficient work procedures or best practices for a particular product.

[1692] A "means of reading" is a function or process for obtaining specific information from an information sharing network.

[1693] A "daily posting program" is software for posting specific information on an online platform on a regular basis.

[1694] A "generating means" is a function or process that produces new programs or data for a specific purpose.

[1695] A "specific role" is a role for performing a specific function or task within the system.

[1696] A "generative AI model" is a model designed to accomplish a specific task using artificial intelligence.

[1697] "Means of automatic generation" refers to functions or processes that use artificial intelligence to automatically generate specific information or data.

[1698] "Means of posting" refers to the functions and processes for publishing generated information on an online platform.

[1699] "Skilled workers" refers to workers with high skills and experience at logistics centers.

[1700] A system for implementing this invention includes means for reading success stories of acquiring a specific product posted on an information sharing network, means for generating a program that posts the read success stories daily, means for operating the generated program as a specific role, means for automatically generating success stories using a generative AI model, and means for posting the generated success stories so that other workers can view them.

[1701] System configuration

[1702] Hardware

[1703] Server: A computer that retrieves data from an information-sharing network and runs generative AI models.

[1704] Smartphone: A device that allows workers to view and post success stories.

[1705] software

[1706] Python: A programming language for running generative AI models.

[1707] OpenAI API: A service that provides generative AI models.

[1708] Processing flow

[1709] 1. Information loading: The server loads the success stories of specific products posted on the information sharing network.

[1710] 2. Prompt sentence generation: The server generates prompt sentences related to specific tasks at the logistics center.

[1711] 3. Calling the generative AI model: The server uses the OpenAI API to input prompt statements into the generative AI model and generate success stories.

[1712] 4. Posting success stories: The server posts the generated success stories to the information sharing network so that other workers can view them.

[1713] Specific examples

[1714] For example, when sorting packages at a logistics center, a generative AI model can generate success stories like the following:

[1715] "When sorting packages, we can process larger packages first, followed by smaller packages, making efficient use of workspace. We can also use barcode scanners to manage inventory in real time, reducing errors."

[1716] Prompt Sentence Examples

[1717] "Please tell us some success stories about efficient package sorting methods in distribution centers."

[1718] "What are some best practices for speeding up picking operations?"

[1719] In this way, by sharing the generated success stories within the application, the work efficiency of the entire logistics center can be improved.

[1720] The flow of the specific processing in Application Example 3 will be described with reference to FIG.

[1721] Step 1:

[1722] The server accesses the information sharing network and loads the acquisition success stories for the particular product.

[1723] Input: Information sharing network URL and authentication information.

[1724] Data processing: Obtaining success story data from the network and converting it into the required format.

[1725] Output: Success story data.

[1726] Step 2:

[1727] The server generates a program to post daily based on the success stories it has read.

[1728] Input: Success story data.

[1729] Data calculation: Analyze data from success stories and generate a posting schedule.

[1730] Output: A program that posts daily.

[1731] Step 3:

[1732] The server runs the generated program as a specific role.

[1733] Input: A program that posts daily.

[1734] Data calculation: Run the program and post success stories at the specified time.

[1735] Output: Posted success stories.

[1736] Step 4:

[1737] The server automatically generates success stories using a generative AI model.

[1738] Input: Prompt statement.

[1739] Data calculation: Using the OpenAI API, prompt sentences are input to the generative AI model to generate success stories.

[1740] Output: Generated success stories.

[1741] Step 5:

[1742] The server posts the generated success stories to an information sharing network so that other workers can view them.

[1743] Input: Generated success stories.

[1744] Data processing: Convert success stories into a posting format for the information sharing network.

[1745] Output: Success stories posted to an information sharing network.

[1746] 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.

[1747] "Example 1"

[1748] We will explain an example of a system using an emotion engine. In this system, a program that posts success stories every day adjusts the content of the posts using an emotion engine that recognizes the user's emotions. Specifically, the emotion engine analyzes the emotions in the user's SNS posts and optimizes the content of the posts based on the analysis results. For example, if a user's post expresses joy or excitement, the emotion engine uses that information to select success stories that evoke similar emotions and generate post content. This enables posts to be made appropriately in accordance with the user's emotions, making it easier to attract the user's attention.

[1749] "Example 2"

[1750] An example of an embodiment in which an emotion engine analyzes emotions from a user's SNS posts will be described. In this embodiment, the emotion engine analyzes emotions from a user's SNS posts. Specifically, the emotion engine uses natural language processing technology to extract emotions from the text of a user's post. For example, the emotion of "joy" is extracted from a post such as "I'm so happy to have gotten this product!" The emotional information extracted in this way is used to generate the post content.

[1751] "Example 3"

[1752] An example of a form in which post content is optimized based on emotions analyzed by an emotion engine will be described. In this form, the emotion engine optimizes post content based on the analyzed emotions. Specifically, the emotion engine generates post content that users can easily empathize with based on the analyzed emotion information. For example, if a user expresses the emotion of "joy," the emotion engine uses that information to select success stories that enhance the "joy" and generates post content. This enables posts that are appropriate to the user's emotions and more easily attracts the user's attention.

[1753] The processing flow of each embodiment will be described below.

[1754] "Example 1"

[1755] Step 1: Collect users' social media posts.

[1756] Step 2: Analyze user sentiment from the collected posts using an emotion engine.

[1757] Step 3: Adjust your posts based on the analyzed sentiment.

[1758] Step 4: Post the adjusted content to social media.

[1759] "Example 2"

[1760] Step 1: Collect users' social media posts.

[1761] Step 2: Analyze user sentiment from the collected posts using an emotion engine.

[1762] Step 3: Generate post content based on the analyzed emotions.

[1763] Step 4: Post the generated post to social media.

[1764] "Example 3"

[1765] Step 1: Collect users' social media posts.

[1766] Step 2: Analyze user sentiment from the collected posts using an emotion engine.

[1767] Step 3: Optimize your posts based on the analyzed sentiment.

[1768] Step 4: Post your optimized post to social media.

[1769] Example 1

[1770] Next, a description will be given of Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1771] In conventional information-sharing network services, it was difficult to efficiently collect success stories of specific product acquisitions and generate optimal posting content that matched users' emotions. Furthermore, there was a lack of a way to automatically generate appropriate posting content to attract users' attention. This made it difficult to maintain users' interest, and information was not being used effectively.

[1772] 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.

[1773] In this invention, the server includes means for reading success stories of specific products posted on an information sharing network service, means for analyzing the read success stories, means for generating a program for posting the analyzed success stories daily, means for operating the generated program as a specific role, means for analyzing user emotions, and means for optimizing the posted content based on the analyzed emotions. This makes it possible to efficiently collect success stories related to specific products and automatically generate optimal posted content according to the user's emotions.

[1774] An "information sharing network service" is an online platform where users can post information and share it with other users.

[1775] "Specific products" refer to goods or services that are of interest in a particular market or application.

[1776] "Acquired Success Stories" refer to specific examples or experiences of success using a particular product.

[1777] "Means of reading" refers to the methods and techniques for obtaining data from an information sharing network service.

[1778] "Means of analysis" refers to methods and techniques for analyzing acquired data and extracting useful information.

[1779] A "daily posting program" refers to software or scripts that automatically post analyzed success stories every day.

[1780] "Means for operating as a specific role" refers to methods and techniques for executing a generated program according to a specific function or purpose.

[1781] "Means for analyzing user emotions" refers to methods and technologies for analyzing emotions from user posts and behavior and calculating an emotion score.

[1782] "Means for optimizing post content" refers to methods and techniques for adjusting post content to attract user interest based on analyzed emotions.

[1783] MODE FOR CARRYING OUT THE INVENTION

[1784] This invention provides a system that efficiently collects successful cases of acquiring a specific product posted on an information sharing network service and generates optimal posting content according to the user's emotions. Specific embodiments of this system are described below.

[1785] Program Generation

[1786] The server generates a program for reading success stories of specific products posted on an information sharing network service. This program has a function of extracting success stories from the network service used by experts on the specific product.

[1787] Program processing

[1788] The server performs the following processing using the generated program.

[1789] 1. Data Collection:

[1790] The server collects posted data from network services used by experts of specific products, using the APIs of SNSs (e.g., Twitter API or Facebook Graph API).

[1791] 2. Keyword analysis:

[1792] The server analyzes the collected posting data and extracts specific keywords and hashtags using natural language processing libraries (e.g., NLTK and spaCy).

[1793] 3. Extraction of success stories:

[1794] The server automatically extracts posts related to success stories based on the extracted keywords and hashtags, allowing for efficient collection of useful information about specific products.

[1795] 4. Emotion analysis:

[1796] The server uses an emotion engine (e.g., IBM Watson Natural Language Understanding or Microsoft Azure Text Analytics) to analyze emotions from users' social media posts.

[1797] 5. Optimize your posts:

[1798] The server optimizes the content of success stories based on the results of sentiment analysis. For example, if a user's post expresses joy or excitement, it selects success stories that evoke similar emotions and generates posts accordingly.

[1799] Specific examples

[1800] When a user posts on social media, "I tried a new product and I'm so happy!", the server passes this post to the emotion engine to obtain emotion scores such as "joy" or "satisfaction." Next, based on these emotion scores, the server selects success stories that similarly evoke joy or satisfaction, and generates a post with the content, "Other users are also having great success with this product!"

[1801] Prompt Sentence Examples

[1802] "Analyze the emotions of users' posts on social media, select success stories based on those emotions, and generate posts. For example, if a user's post expresses joy or excitement, select success stories that evoke similar emotions."

[1803] In this way, the server generates appropriate posts according to the user's emotions, making it easier to attract the user's attention.

[1804] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1805] Step 1:

[1806] The server collects posting data related to a specific product from an information sharing network service.

[1807] Input: Posted data obtained from the network service API.

[1808] Specific operation: The server periodically sends requests to the SNS API (for example, Twitter API or Facebook Graph API) to retrieve posts related to "Product Name" and "Product Name."

[1809] Output: A list of collected submission data.

[1810] Step 2:

[1811] The server analyzes the collected posting data and extracts specific keywords and hashtags.

[1812] Input: Post data collected in step 1.

[1813] Specific operation: The server uses a natural language processing library (e.g., NLTK or spaCy) to extract frequently occurring keywords and hashtags from the post data. For example, it extracts keywords such as "success," "acquisition," and "review."

[1814] Output: A list of extracted keywords and / or hashtags.

[1815] Step 3:

[1816] The server automatically extracts posts related to success stories based on the extracted keywords and hashtags.

[1817] Input: The list of keywords and hashtags extracted in step 2.

[1818] Specific operation: The server uses the results of keyword analysis as filtering conditions to select posts that correspond to success stories. For example, it extracts posts that contain the keyword "success."

[1819] Output: A list of posts related to the success story.

[1820] Step 4:

[1821] The server analyzes emotions from users' social media posts.

[1822] Input: The user's most recent social media posts.

[1823] Specific operation: The server uses an emotion engine (such as IBM Watson Natural Language Understanding or Microsoft Azure Text Analytics) to analyze the user's post and obtain an emotion score. For example, emotions such as "joy," "excitement," and "satisfaction" are quantified.

[1824] Output: Sentiment score.

[1825] Step 5:

[1826] The server optimizes the content of the success stories posted based on the results of the sentiment analysis.

[1827] Input: The list of success story posts extracted in step 3 and the sentiment scores obtained in step 4.

[1828] Specific operation: The server selects the most appropriate success story based on the emotion score and generates a post. For example, if the user's emotion indicates "joy," it selects a success story that evokes a similar emotion and generates a post with the content "Other users are also using this product with great success!"

[1829] Output: The optimized post content.

[1830] In this way, the server generates appropriate posts according to the user's emotions, making it easier to attract the user's attention.

[1831] (Application example 1)

[1832] Next, a description will be given of Application Example 1 of Form Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1833] Conventional information-sharing SNSs lack effective ways to share success stories of specific products. Furthermore, it is difficult to make optimal product recommendations based on users' emotions, which makes it difficult to attract users' attention.

[1834] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means. In this invention, the server includes means for reading success stories of acquiring a specific product posted on an information-sharing SNS, means for generating a program for posting the read success stories daily, means for running the generated program as a specific role, means for adjusting the posted content using an emotion engine that recognizes the user's emotions, and means for analyzing the user's SNS posts and making optimal product recommendations based on the emotions. This enables appropriate posts and product recommendations to be made in accordance with the user's emotions, making it easier to attract the user's attention.

[1835] An "information sharing SNS" is a social networking service that allows users to share information with each other.

[1836] A "specific product" is a specific good or service sold in a particular market or for a particular purpose.

[1837] "Success stories" are cases that show successful experiences or results obtained when purchasing or using a particular product.

[1838] "Reading means" refers to a method or device for acquiring information and incorporating it into the system.

[1839] A "daily posting program" is software that automatically posts specific content to social media every day.

[1840] A "specific role" is a role for performing a specific function or task within the system.

[1841] An "emotion engine" is software or hardware that analyzes a user's emotions and adjusts the system's behavior based on the results.

[1842] A "means for adjusting posted content" is a method or device for optimizing the content posted to an SNS based on the user's emotions.

[1843] "Means for analyzing SNS posts" refers to a method or device for analyzing content posted on SNS and extracting specific information.

[1844] A "means for making product recommendations" is a method or device for recommending a particular product to a user.

[1845] The following describes the mode for carrying out the present invention: First, the system includes the following main components:

[1846] 1. A way to read success stories of specific products posted on information-sharing social networking sites

[1847] 2. A way to generate a program that posts the success stories it reads every day

[1848] 3. How to make the generated program act as a specific role

[1849] 4. A method for adjusting post content using an emotion engine that recognizes user emotions

[1850] 5. A method to analyze users' social media posts and make optimal product recommendations based on their emotions

[1851] System Program

[1852] The system is implemented using Python. Specifically, it uses the TextBlob library to analyze users' social media posts and recognize their emotions. It also uses the BeautifulSoup library to extract success stories about specific products from the web. Based on this data, it makes optimal product recommendations based on the user's emotions.

[1853] Processing Description

[1854] Hardware and Software

[1855] Hardware: Smartphone

[1856] Software: Python, TextBlob (sentiment analysis library), BeautifulSoup (web scraping library)

[1857] Data processing and calculation

[1858] 1. SNS Post Analysis: The server analyzes the user's SNS posts using TextBlob and recognizes emotions. For example, if the user's post is "I'm really excited about this new gadget!", the emotion is recognized as "joy."

[1859] 2. Success story extraction: The server uses BeautifulSoup to extract success stories about a specific product from the Web. For example, it extracts success stories about the latest smartphones.

[1860] 3. Emotion-based recommendation: The server makes optimal product recommendations to users based on their recognized emotions. For example, if a user expresses the emotion "joy," it will recommend the most popular success stories.

[1861] Specific examples

[1862] User Submission: "I'm really excited about this new gadget!"

[1863] Product name: "Latest Smartphone"

[1864] Recommendation: "This phone has dramatically improved my photography!"

[1865] Prompt Sentence Examples

[1866] An example of a prompt for the generative AI model is as follows:

[1867] Create a program that analyzes users' social media posts, recognizes their emotions, and recommends success stories for specific products. If the user's post is "I'm really excited about this new gadget!" and the product name is "Latest Smartphone," recommend the most suitable success story.

[1868] In this way, it becomes possible to make posts and product recommendations that are appropriate to the user's emotions, making it easier to attract the user's attention.

[1869] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1870] Step 1:

[1871] The server retrieves the user's SNS posts. The input is the user's SNS post, and the output is the retrieved post data. Specifically, the server uses the SNS API to retrieve the user's latest posts.

[1872] Step 2:

[1873] The server analyzes the social media posts acquired using the TextBlob library and recognizes emotions. The input is the acquired post data, and the output is the analyzed emotion data. Specifically, the server passes the post content to TextBlob and determines whether the emotion is positive, negative, or neutral.

[1874] Step 3:

[1875] The server extracts success stories related to a specific product from the web. The input is the name of a specific product, and the output is the extracted success story data. Specifically, the server uses the BeautifulSoup library to scrape success stories related to the specified product from a website.

[1876] Step 4:

[1877] The server then recommends optimal products to users based on the recognized emotions. The input is the analyzed emotion data and success case data, and the output is the recommended success case. Specifically, the server selects the most appropriate case from the success case data based on the emotion data.

[1878] Step 5:

[1879] The server notifies the user of the selected success story. The input is the recommended success story, and the output is a notification message to the user. Specifically, the server uses the SNS API to send a message including the success story to the user.

[1880] Step 6:

[1881] The server generates a program that posts success stories every day and runs it as a specific role. The input is the success story data, and the output is the generated program. Specifically, the server sets a schedule for automatically posting success stories and runs the program.

[1882] Example 2

[1883] Next, a description will be given of Example 2 of Form Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1884] In conventional information sharing networks, it was difficult to efficiently collect success stories of specific products, generate new posts based on them, and post them regularly. It was also difficult to analyze emotions from user posts and reflect that emotional information in the generation of posts. This resulted in issues such as not being able to keep users interested and reducing the effectiveness of information sharing.

[1885] The identification process by the identification processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means. In this invention, the server includes means for reading success stories of specific product acquisitions posted on the information sharing network, means for analyzing the read success stories, means for generating new posting content based on the analyzed success stories, means for periodically posting the generated posting content, means for analyzing emotions from user posts, and means for using the analyzed emotional information to generate posting content. This makes it possible to efficiently collect success stories, generate new posting content that attracts users' attention based on the success stories, and post the new posting content periodically. Furthermore, by reflecting users' emotional information, more effective information sharing can be achieved.

[1886] An "information sharing network" is an online platform for users to share information about specific products or services.

[1887] A "success story" is an example that demonstrates specific results or positive outcomes achieved by using a particular product or service.

[1888] A "reading means" is a function or process for obtaining specific information from a database or file system.

[1889] "Means of analysis" refers to the functions and processes for analyzing acquired data using natural language processing technology, etc., and extracting important information.

[1890] "Means of generation" refers to the functions and processes for creating new content or posts based on analyzed information.

[1891] A "periodic posting mechanism" is a function or process for automatically posting generated content to an online platform at regular intervals.

[1892] "Means for analyzing emotions" refers to functions or processes that use natural language processing technology to extract emotions from user posts and classify those emotions.

[1893] "Means for utilizing emotional information" refers to functions and processes for generating new content and adjusting posted content based on analyzed emotional information.

[1894] This invention is a system that efficiently collects successful cases of acquiring specific products posted on an information sharing network, generates new posting content based on the collected information, and posts the content periodically. It also analyzes emotions from users' posts and reflects this emotional information in the generated posting content.

[1895] System configuration

[1896] The server implements the system using the following hardware and software.

[1897] Hardware: The server has a powerful processor, sufficient memory, and a large storage device.

[1898] Software: The server uses a database management system (e.g., MySQL), natural language processing libraries (e.g., NLTK, spaCy), generative AI models (e.g., GPT-3), and scheduling software (e.g., cron jobs).

[1899] Program processing

[1900] The server processes and calculates the data in the following procedure.

[1901] 1. Loading success stories:

[1902] The server loads success stories from a database or the file system. Specifically, the server connects to a MySQL database and retrieves data from the table where the success stories are stored. For example, it executes the SQL query "SELECT FROM success_stories WHERE date = CURDATE()".

[1903] 2. Natural Language Processing Analysis:

[1904] The server analyzes the text of success stories using natural language processing technology. Specifically, the server uses NLP libraries such as NLTK and spaCy to extract important information from the text. For example, it extracts keywords such as "sales" and "20% increase" from the phrase "sales increased by 20%."

[1905] 3. Generate a new post:

[1906] The server generates new post content based on the extracted information. At this time, the server uses a generative AI model (e.g., GPT-3) to generate natural-sounding sentences. For example, the server inputs a prompt such as, "Success story: Sales increased by 20%. Please generate new SNS post content based on this success story."

[1907] 4. Emotion analysis:

[1908] The emotion engine analyzes emotions from users' social media posts. Specifically, the emotion engine uses natural language processing technology to extract emotions from the text of users' posts. For example, it extracts the emotion of "joy" from a post such as "I'm so happy to have gotten this product!"

[1909] 5. Post regularly:

[1910] The server periodically posts the generated posts to the social networking site using scheduling software (e.g., a cron job). For example, every day at 9:00 AM, the server could post, "We've received exciting news from customers who have introduced our new product that their sales have increased by 20%!"

[1911] Specific examples

[1912] Examples:

[1913] Loading success stories: The server executes the SQL query "SELECT FROM success_stories WHE...

Claims

1. A means for reading a success story of acquiring a specific product posted on an information sharing network service; A means for analyzing the success cases read by the reading means; A means for extracting posts related to success stories from the analysis results of the analyzing means; A means for storing the success cases extracted by the extracting means in a database; A means for providing the success cases stored in the storing means in response to a request from a user; A system including:

2. 2. The system according to claim 1, wherein the information sharing network service is a network service used by experts of a particular product.

3. 2. The system of claim 1, wherein the means for providing the stored success stories in response to a request from the user operates based on data analyzed using natural language processing techniques.

Images