System

Abstract

To provide a system.SOLUTION: A system includes: means for receiving keywords related to content to be searched from a user's terminal; means for collecting related information based on the received keywords; means for generating an introduction sentence excluding spoilers from the collected related information; means for formatting the introduction sentence into a format that is easy for the user to read; and means for transmitting the formatted introduction sentence to the terminal.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 a description and related instruction sentence regarding 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] JP 2022-180282 A Summary of the Invention [Problem to be solved by the invention]

[0004] In today's information society, when users search for an overview of the content they want to search for, unintended spoilers may appear in the search results, which can be a problem that ruins the user experience. [Means for solving the problem]

[0005] To solve this problem, the present invention provides a system that receives information about the content to be searched for, automatically generates an introduction that does not include spoilers based on that information, and displays the generated introduction in the search results. This allows users to avoid spoilers when viewing search results. [Brief description 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. [Diagram 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. FIG. [Diagram 3] FIG. 11 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Diagram 5] FIG. 13 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. 13 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 13 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 process flow of the data processing system in the first embodiment of the first form example. [Figure 12] FIG. 11 is a sequence diagram showing a process flow of the data processing system in the application example 1 of the first embodiment. [Figure 13] FIG. 11 is a sequence diagram showing a process flow of the data processing system in the second embodiment of the second embodiment. [Figure 14] FIG. 13 is a sequence diagram showing a process flow of the data processing system in application example 2 of embodiment 2. [Figure 15] FIG. 13 is a sequence diagram showing a process flow of a data processing system in a third embodiment of the present invention. [Figure 16]FIG. 13 is a sequence diagram showing a process flow of the data processing system in the third application example of the third embodiment. [Figure 17] FIG. 13 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. 13 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1 of Form Example 1 when combined with an emotion engine. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

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

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

[0009] In the following embodiments, a signed processor (hereinafter simply referred to as a "processor") may be one arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be one 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 signed RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by the 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 code is an interface including a communication processor and an antenna. The communication I / F controls communication between multiple computers. An example of a communication standard applied to the communication I / F is a wireless communication standard 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. In addition, in this specification, the same idea as "A and / or B" is also applied when three or more things are expressed by connecting them with "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 wide area network (WAN) and / or a local area network (LAN).

[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 and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (e.g., a pen or a finger) to receive user input by the touch of the pointer. 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 (e.g., voice and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs voice according to instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, an aperture, and a shutter, and an imaging element such as a Complementary Metal-Oxide-Semiconductor (CMOS) image sensor or a Charge Coupled Device (CCD) image sensor.

[0021] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54.

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

[0023] As shown in Fig. 2, 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. The specific process program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific process program 56 from the storage 32, and executes the read specific process 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 process 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 processing. The storage 50 stores a reception output program 60. The reception output program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads out the reception output program 60 from the storage 50, and executes the read reception output program 60 on the RAM 48. The reception output processing 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] In one embodiment of the present invention, an Internet search tool is provided. When a user inputs a keyword related to a content to be searched, the search tool collects information related to the keyword. The collected information is sent to a spoiler-free introduction generation module. The module removes spoilers from the collected information and extracts a summary of the content. The extracted summary is formatted as an introduction and displayed to the user along with the search results.

[0029] "Example 2"

[0030] As a concrete example, consider the case where a user searches for "game title." The search tool collects information related to "game title" and sends it to a description generation module to prevent spoilers. This module excludes the game's ending and important plot points from the collected information and extracts an overview of the game, such as its genre and play style. The extracted overview is formatted as a description and displayed to the user along with the search results. This allows the user to understand the content of the game, but does not reveal any spoilers about the game's ending or important plot points.

[0031] The process flow of each embodiment will be described below.

[0032] "Example 1"

[0033] Step 1: User enters keywords into the search tool.

[0034] Step 2: The search tool gathers information from the Internet related to the keywords you entered.

[0035] Step 3: The collected information is sent to a spoiler-free introduction generation module. Step 4: The introduction generation module removes spoilers from the collected information and extracts a summary of the content.

[0036] Step 5: The extracted summary is formatted as a description and displayed to the user along with the search results.

[0037] "Example 2"

[0038] Step 1: User types "game title" into the search tool.

[0039] Step 2: The search tool collects information related to the "game title" from the Internet.

[0040] Step 3: The collected information is sent to a description generation module to prevent spoilers. Step 4: The description generation module extracts an overview of the game, such as its genre and play style, from the collected information, excluding the game's ending and important plot details.

[0041] Step 5: The extracted synopsis is formatted as a description and displayed to the user alongside the search results, allowing the user to understand the game's contents without spoiling the game's ending or important plot details.

[0042] Example 1

[0043] Next, a description will be given of Example 1 of the embodiment 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".

[0044] Conventional Internet search tools often display information containing spoilers when collecting information about the content a user searches for, which can ruin the user's experience. In addition, there was a lack of a way to properly format the collected information and display it in a way that is easy for users to understand.

[0045] 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.

[0046] In this invention, the server includes a means for receiving keywords related to the content to be searched, a means for collecting related information based on the received keywords, a means for transmitting the collected information to an introductory text generation module for preventing spoilers, a means for generating an introductory text that excludes spoilers using a generative AI model, a means for formatting the generated introductory text, and a means for displaying the formatted introductory text together with the search results, thereby enabling the user to check the outline of the content without including spoilers.

[0047] "Searchable content" is data about a particular subject or topic about which a user wants information.

[0048] A "keyword" is a word or phrase that a user enters to identify the content they are searching for.

[0049] "Related information" refers to data and materials related to keywords collected from search engines and databases.

[0050] "Introduction Generation Module" is a software component for analyzing collected related information and generating a spoiler-free summary of the content.

[0051] A "generative AI model" is an algorithm or system that uses artificial intelligence technology to generate appropriate text from input data.

[0052] A "formatter" is a process or tool used to convert the generated testimonial into a user-friendly form.

[0053] "Search results" are a list of related information displayed based on the keywords entered by the user.

[0054] "Display Means" means the method or technology used to display the formatted description and search results on the user's device.

[0055] The present invention is a system in which a user inputs a keyword for a content they wish to search, collects information related to the keyword, and generates an introduction to prevent spoilers. A specific embodiment of this system will be described below.

[0056] The server receives the keyword entered by the user. The user enters the keyword of the content he or she wants to search for in the search bar of the terminal. For example, the user enters "review of the latest movie 'Avengers'."

[0057] The terminal sends the entered keyword to the server, using the HTTPS protocol for this communication.

[0058] The server collects related information based on the received keywords. To do this, it uses a search engine API such as Google Search API or Bing Search API. For example, it sends a query such as "Avengers movie review" to the search engine.

[0059] The server sends the collected information to an introductory text generation module, which analyzes the collected information and identifies parts that contain spoilers.

[0060] The introduction generation module uses a generative AI model to generate an introduction that excludes spoilers. Specifically, a generative AI model such as OpenAI's GPT-4 (registered trademark) is used. The generative AI model receives the prompt sentence as input and generates an appropriate introduction.

[0061] For example, the following sentence is input as a prompt into the generative AI model:

[0062] "Please give us your review of the latest movie, The Avengers, without any spoilers please."

[0063] The generated testimonial is then formatted by the server. Formatting is the process of converting the generated testimonial into a form that is easy for the user to read, i.e., converting it into a suitable format so that it is easy for the user to understand.

[0064] The server then sends the formatted introduction to the terminal, again using the HTTPS protocol.

[0065] The terminal displays the received introduction text to the user, allowing the user to check an outline of the content without including spoilers.

[0066] In this way, users can feel at ease knowing the outline of the content. This system provides an effective means of providing users with the necessary information while preventing spoilers.

[0067] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0068] Step 1:

[0069] The user enters search keywords.

[0070] The user inputs the keyword of the content they want to search for into the search bar of the device. For example, they input "Review of the latest movie 'Avengers'." The input keyword becomes the input data of the device.

[0071] Step 2:

[0072] The terminal transmits the entered keyword to the server.

[0073] The terminal sends the keyword entered by the user to the server. This communication uses the HTTPS protocol. The input is the keyword entered by the user, and the output is the keyword sent to the server.

[0074] Step 3:

[0075] The server collects information related to the keywords.

[0076] The server uses the Google Search API or Bing Search API to collect related information based on the received keywords. For example, a query such as "Avengers movie reviews" is sent to the search engine. The input is the keyword sent to the server, and the output is the collected related information.

[0077] Step 4:

[0078] The server sends the collected information to the testimonial generation module.

[0079] The server sends the collected information to the testimonial generation module, where the input is the collected relevant information and the output is the information sent to the testimonial generation module.

[0080] Step 5:

[0081] The introduction generation module generates an introduction that excludes spoilers.

[0082] The introduction generation module uses a generative AI model to generate an introduction that excludes spoilers from the collected information. Specifically, the prompt "Please give us a review of the latest movie, The Avengers, but without spoilers." is input to the generative AI model. The input is the information sent to the introduction generation module, and the output is the generated introduction.

[0083] Step 6:

[0084] The server formats the generated description.

[0085] The server formats the introduction received from the generative AI model. Formatting is the process of converting the generated introduction into a form that is easy for users to read, i.e., converting it into a proper format to make it easy for users to understand. The input is the generated introduction, and the output is the formatted introduction.

[0086] Step 7:

[0087] The server sends the formatted introduction to the terminal.

[0088] The server sends the formatted introduction to the terminal. This communication also uses the HTTPS protocol. The input is the formatted introduction, and the output is the introduction sent to the terminal.

[0089] Step 8:

[0090] The terminal displays the introductory text to the user.

[0091] The terminal displays the received introduction text to the user. The user can check the outline of the content without including spoilers. The input is the introduction text sent to the terminal, and the output is the introduction text displayed to the user.

[0092] (Application example 1)

[0093] 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 device 14 will be referred to as a "terminal."

[0094] Conventional Internet search tools often display information containing spoilers when collecting information about the content a user searches for, which can cause problems for the user's experience. In addition, it is difficult to efficiently collect information because it takes time to manually select information to avoid spoilers. Another issue is that the generated introduction text gets buried in the search results, making it difficult for users to quickly access the information they need.

[0095] 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.

[0096] In this invention, the server includes a means for receiving information about the content to be searched, a means for automatically generating an introduction that does not include spoilers based on the received information, a means for displaying the generated introduction in the search results, and a means for generating a prompt text using a generative AI model to generate an introduction that excludes spoilers. This allows the user to efficiently grasp the outline of the content while avoiding spoilers.

[0097] The "means for receiving information related to the content to be searched" refers to a device or program that has the function of collecting related information from the Internet based on keywords entered by the user.

[0098] The "means for automatically generating an introduction that does not include spoilers based on received information" refers to a device or program that has the function of excluding spoilers from collected information, extracting an outline of the content, and generating an introduction.

[0099] The "means for displaying the generated testimonial in the search results" refers to a device or program having a function of displaying the generated testimonial on the user's search result page.

[0100] "Means for generating a prompt sentence using a generative AI model and generating an introduction sentence that excludes spoilers" refers to a device or program that has the function of using a generative AI model to generate a prompt sentence for excluding spoilers from collected information, and generating an introduction sentence based on the prompt sentence.

[0101] A system for carrying out the present invention has the following configuration: A server includes means for receiving information related to the content to be searched, means for automatically generating an introductory text that does not include spoilers based on the received information, means for displaying the generated introductory text in the search results, and means for generating a prompt text using a generative AI model to generate an introductory text that excludes spoilers.

[0102] Hardware and Software Used

[0103] Hardware: Servers, user devices (smartphones, PCs, etc.)

[0104] Software: Python, BeautifulSoup, requests, OpenAI API

[0105] Data processing and calculation

[0106] 1. Data collection: Based on the keywords entered by the user's device, the server collects related information on the Internet. Specifically, it uses the requests library to obtain the search result page and parses it with BeautifulSoup.

[0107] 2. Spoiler removal and summary generation: The server inputs the collected information into OpenAI's generative AI model to generate a spoiler-free introduction. Specifically, it generates a prompt using the openai.Completion.create method and inputs it into the AI ​​model.

[0108] 3. Displaying the results: The server displays the generated synopsis on the user's search result page, allowing the user to efficiently get an overview of the content without spoiling it.

[0109] Examples

[0110] When a user searches for "popular movies," the server collects related information and generates and displays an introductory text that excludes spoilers. For example, by inputting the following prompt text into the generative AI model, an introductory text that does not include spoilers is generated.

[0111] Examples of prompt statements

[0112] Generate a content summary from the following information, excluding spoilers:

[0113] This movie is about the protagonist overcoming difficulties and growing as he goes on various adventures with his friends.

[0114] The story depicts the protagonist's growth as he comes to terms with his past.

[0115] The main characters include his best friend and mentor.

[0116] By inputting this prompt into a generative AI model, a spoiler-free introduction is generated and provided to the user.

[0117] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0118] Step 1:

[0119] The user inputs a search keyword from the terminal.

[0120] Input: The keyword for which the user wants to search for the content

[0121] Output: Search keywords sent to the server

[0122] Step 2:

[0123] The server collects relevant information on the Internet based on the search keywords.

[0124] Input: Search keyword

[0125] Output: A list of related information

[0126] What it does: The server uses the requests library to get the search results page, then parses it with BeautifulSoup to extract relevant information.

[0127] Step 3:

[0128] The server generates prompt sentences to input the collected information into the generative AI model.

[0129] Input: List of related information

[0130] Output: Prompt statement

[0131] Specific operation: The server generates a prompt text to filter out spoilers based on the collected information.

[0132] Step 4:

[0133] The server uses a generative AI model to generate a spoiler-free introduction based on the prompt text.

[0134] Input: Prompt statement

[0135] Output: Introduction without spoilers

[0136] Specific operation: The server uses the openai.Completion.create method to input the prompt text into the generation AI model and generate an introduction that excludes spoilers.

[0137] Step 5:

[0138] The server displays the generated testimonial on the user's search results page.

[0139] Input: Introduction without spoilers

[0140] Output: A description that will be displayed on the user's search results page.

[0141] Specific behavior: The server sets the generated testimonial to be displayed at the top of the search result page.

[0142] Example 2

[0143] Next, a second embodiment of the second embodiment will be described. 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."

[0144] In conventional search systems, when users searched for information related to specific content, information containing spoilers was often displayed, which had the problem of ruining the user's experience. In addition, there was a lack of means to efficiently collect related information and generate appropriate introductions, making it difficult to quickly and accurately provide the information users were looking for.

[0145] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0146] In this invention, the server includes a means for receiving information about the content to be searched, a means for collecting related information based on the received information, a means for automatically generating an introductory text that does not include spoilers from the collected information, a means for formatting the generated introductory text, and a means for displaying the formatted introductory text in the search results. This makes it possible to quickly and accurately provide related information to the content searched for by the user while avoiding spoilers.

[0147] The "means for receiving information regarding the content being searched" refers to a function that allows the server to receive keywords or phrases that a user enters into the search bar.

[0148] "Means of collecting related information based on received information" refers to a function that uses search tools to collect related data from the Internet based on received keywords or phrases.

[0149] "Means for automatically generating a spoiler-free introduction from collected information" refers to a function that analyzes collected data, excludes important plot details and endings, and automatically creates a summary of the content using a generative AI model.

[0150] The "means for formatting the generated introduction" is a function for grammar checking and formatting the generated introduction to make it easier for the user to read.

[0151] The "means for displaying the formatted introduction in the search results" is a function for transmitting the formatted introduction to the user's terminal and displaying it on the search result page.

[0152] The present invention provides a system for automatically generating an introduction that does not include spoilers and displaying it in the search results when a user searches for information related to a particular piece of content. A specific embodiment of this system will be described below.

[0153] The server has a means for receiving keywords or phrases entered by a user into the search bar. When a user enters a "game title" into the search bar using a browser or a dedicated application on the terminal and clicks a search button, this search request is sent to the server.

[0154] Based on the received keywords and phrases, the server uses search tools such as ElasticSearch to gather relevant data from the Internet, specifically from official game websites, review sites, forum posts, etc.

[0155] The collected information is then sent to a generative AI model, such as OpenAI’s GPT-4, using prompts to give the model specific instructions. For example, the following prompts can be used:

[0156] We have gathered information about the "Game Title". From this information, we would like you to generate a description that includes the game's genre, play style, and basic storyline, excluding the game's ending and important plot details.

[0157] The generative AI model analyzes the collected data, removes important plot details and endings, and automatically creates a summary of the content. The server checks the grammar and formats the summary to make it easier for users to read.

[0158] The formatted description is sent from the server to the user's device and displayed on the search results page, allowing the user to understand the general outline of the game, but without spoiling the ending or important plot details.

[0159] As a concrete example, consider the case where a user searches for "Final Fantasy VII." The server uses Elasticsearch to collect information related to "Final Fantasy VII" from the Internet. It then sends the collected information to GPT-4, which generates a description using the following prompt:

[0160] You have gathered information about "Final Fantasy VII." From this information, generate a description that includes the game's genre, play style, and basic storyline, excluding the game's ending and key plot details.

[0161] An example of a generated introduction might look like this:

[0162] "Final Fantasy VII" is a role-playing game. Players control characters and fight against giant corporations with rebel groups. The game employs a turn-based battle system and features a wide range of character development elements.

[0163] This description will be displayed on the user's device along with the search results.

[0164] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0165] Step 1:

[0166] A user enters keywords into the search bar and clicks the search button.

[0167] Input: The keyword entered by the user (e.g. "game title")

[0168] Output: A search request is sent to the server.

[0169] Specific operation: The user enters the "game title" in the search bar using the device's browser or a dedicated application, and clicks the search button. This action sends a search request to the server.

[0170] Step 2:

[0171] A server receives the search request and collects the relevant information.

[0172] Input: Search request (keywords entered by the user)

[0173] Output: Related information (e.g. official website, review sites, forum posts)

[0174] Specific operation: Based on the received search request, the server uses search tools such as Elasticsearch to collect information related to the "game title" from the Internet. Specifically, it obtains data from the game's official website, review sites, forum posts, etc.

[0175] Step 3:

[0176] The server sends the collected information to a generative AI model to generate a testimonial.

[0177] Input: Information collected (e.g. official sites, review sites, forum posts)

[0178] Output: Generated introduction (no spoilers)

[0179] Specific operation: The server sends the collected information to a generative AI model such as OpenAI's GPT-4. At this time, it uses a prompt to give specific instructions to the generative AI model. For example, the following prompt can be used:

[0180] We have gathered information about the "Game Title". From this information, we would like you to generate a description that includes the game's genre, play style, and basic storyline, excluding the game's ending and important plot details.

[0181] Step 4:

[0182] The server formats the generated description.

[0183] Input: Generated introductory text (no spoilers)

[0184] Output: A formatted introduction (grammar checked and formatted)

[0185] How it works: The server receives the introduction returned by the generative AI model and performs grammar checks and formatting adjustments to make it easier for users to read.

[0186] Step 5:

[0187] The server sends the formatted introduction to the user's terminal and displays it.

[0188] Input: Formatted introduction (grammar checked and formatted)

[0189] Output: The introductory text that is displayed to the user.

[0190] Specific operation: The server sends the formatted introductory text to the user's device. The user's device displays the received introductory text on the browser or application screen. This allows the user to understand the outline of the game, but does not reveal any spoilers about the ending or important plot points.

[0191] (Application example 2)

[0192] 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."

[0193] In conventional search systems, when users searched for information about content, information containing spoilers was often displayed, which led to problems that marred the user experience. In addition, the generated introduction text was sometimes not displayed properly in the search results, which meant that users could not quickly access the information they needed. Furthermore, there were problems with the quality of the introduction text and the speed of generation because the introduction text was not generated efficiently using a generative AI model.

[0194] 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.

[0195] In this invention, the server includes a means for receiving information about the content to be searched, a means for automatically generating an introduction that does not include spoilers based on the received information, a means for displaying the generated introduction in the search results, a means for generating the introduction using a generative AI model, and a means for receiving a prompt as an input. This allows the user to quickly obtain summary information about the required content while avoiding spoilers.

[0196] "Searchable content" refers to media works such as movies, dramas, anime, and games about which users want to obtain information.

[0197] The "means for receiving information" is a part of the system that has the function of collecting relevant data based on the search query entered by the user.

[0198] A "spoiler-free introduction" is a piece of text that provides basic information such as an overview, genre, and play style, excluding the ending or important plot details of the content.

[0199] An "automated generation means" is a part of a system that has the function of generating a testimonial based on the information received, using a specific algorithm or model.

[0200] "Means for displaying the generated testimonial in a search result" means a portion of the system that has functionality for appropriately placing and displaying the generated testimonial on a user's search result page.

[0201] A "generative AI model" is a trained model that uses artificial intelligence technology to generate appropriate introductions from input data.

[0202] A "prompt sentence" is text data input to a generative AI model, and is a sentence that contains instructions and conditions for the model to generate an appropriate output.

[0203] In order to implement this invention, the server, the terminal, and the user must each fulfill a specific role.

[0204] First, a user uses a terminal to input information about the content to be searched. The terminal can be a device such as a smartphone or a PC, and must be connected to the Internet. Once the user enters a search query, the terminal transmits the information to a server.

[0205] The server collects relevant information based on the received search query. Specifically, the server uses APIs to retrieve information about content from external databases and websites, including content overview, genre, play style, etc.

[0206] Next, the server uses a generative AI model to automatically generate a spoiler-free introductory text from the collected information. The generative AI model is a pre-trained natural language processing model that has the ability to generate an appropriate introductory text from the input information. The prompt text is text data input to the generative AI model, and includes instructions and conditions for the model to generate an appropriate output.

[0207] The generated introduction is sent from the server to the terminal and displayed on the terminal screen, allowing the user to quickly obtain an overview of the desired content while avoiding spoilers.

[0208] As a concrete example, consider the case where a user searches for the movie "Inception." When the user types "Inception" into the device, the device sends the information to the server. The server collects related information and uses a generative AI model to generate a description like this:

[0209] "Inception is a science fiction film with a complex plot involving dreams within dreams. The protagonist is a professional information stealer in dreams, and his latest mission is..."

[0210] This synopsis is displayed on the terminal screen, allowing the user to understand the outline of the movie.

[0211] Examples of prompts include:

[0212] "What kind of movie is Inception?"

[0213] In this way, the user can quickly obtain the necessary information while avoiding spoilers.

[0214] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0215] Step 1:

[0216] A user uses a terminal to enter a search query.

[0217] Input: The user enters the content they are searching for (e.g., "Inception").

[0218] Output: The device sends the search query to the server.

[0219] Specific actions: The user types "Inception" into the search bar on their smartphone or computer and presses the search button.

[0220] Step 2:

[0221] A server receives the search query and collects related information.

[0222] Input: The search query sent from the device (e.g. "Inception").

[0223] Output: Content information collected by the server from external databases and websites.

[0224] What happens: The server uses an API to retrieve information about "Inception" (such as summary, genre, play style, etc.) from movie databases and review sites.

[0225] Step 3:

[0226] Based on the information collected by the server, a generative AI model is used to generate an introduction that does not contain spoilers.

[0227] Input: Collected content information (e.g., summary of "Inception", genre, play style).

[0228] Output: A spoiler-free introduction generated by the generative AI model.

[0229] Specific operation: The server inputs the collected information into a generative AI model and generates a spoiler-free introduction using a prompt sentence (e.g., "What kind of movie is Inception?").

[0230] Step 4:

[0231] The server transmits the generated introduction to the terminal.

[0232] Input: An introductory text generated by a generative AI model.

[0233] Output: The introductory text sent to the terminal.

[0234] Specific operation: The server sends the generated introduction to the terminal and displays it on the user's search result page.

[0235] Step 5:

[0236] The terminal displays the received introduction to the user.

[0237] Input: The introduction sent by the server.

[0238] Output: The introductory text displayed on the user's device screen.

[0239] Specific operation: The device displays the received introduction at the top of the search result page and the user views it.

[0240] Furthermore, an emotion engine that estimates the emotion of the user may be combined. That is, the identification processing unit 290 may estimate the emotion of the user using the emotion identification model 59, and perform identification processing using the emotion of the user.

[0241] "Example 1"

[0242] As one embodiment of the present invention, a system incorporating an emotion engine is provided. The system recognizes a user's emotion and automatically generates an introductory text based on the emotion. Specifically, behavioral data such as a user's search history and browsing history is analyzed, and the user's emotion is estimated from the data. The estimated emotion is used to generate an introductory text. For example, if a user expresses an emotion of joy, an introductory text is generated for content that is likely to make the user happy. Also, if a user expresses an emotion of anger, an introductory text is not generated for content that is likely to make the user angry.

[0243] "Example 2"

[0244] As another embodiment of the present invention, an adjustment of the display order of introductions using an emotion engine is provided. Specifically, the display order of introductions is adjusted according to the emotion of the user. For example, when a user expresses an emotion of joy, introductions related to content that may make the user happy are displayed at the top of the search results. Also, when a user expresses an emotion of anger, introductions related to content that may make the user angry are displayed at the bottom of the search results. This makes it possible to provide optimal search results according to the emotion of the user.

[0245] The process flow of each embodiment will be described below.

[0246] "Example 1"

[0247] Step 1: Collect user behavioral data (e.g. search history, browsing history).

[0248] Step 2: Input the collected behavioral data into the emotion engine to estimate the user's emotions. Step 3: Automatically generate an introduction based on the estimated emotions.

[0249] Step 4: Display the generated testimonial to the user.

[0250] "Example 2"

[0251] Step 1: Collect user behavioral data (e.g. search history, browsing history).

[0252] Step 2: Input the collected behavioral data into the emotion engine to estimate the user's emotion. Step 3: Adjust the display order of the testimonials based on the estimated emotion.

[0253] Step 4: Display the testimonials to the user according to the adjusted display order.

[0254] Example 1

[0255] Next, a description will be given of Example 1 of the embodiment 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".

[0256] In conventional Internet search tools, when collecting information about the content searched by the user, information containing spoilers may be displayed, which may spoil the user's experience. In addition, since it is not possible to provide an appropriate introduction according to the user's emotions, it is difficult to improve user satisfaction. Furthermore, since the search results are not customized based on the user's emotions, it is difficult for the user to quickly access the information he or she is looking for.

[0257] 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.

[0258] In this invention, the server includes a means for receiving information about the content to be searched, a means for automatically generating an introduction that does not include spoilers based on the received information, a means for displaying the generated introduction in the search results, a means for collecting user behavior data, a means for estimating the user's emotions based on the collected behavior data, and a means for generating an introduction based on the estimated emotions. This makes it possible for a user to be provided with an appropriate introduction that corresponds to the emotions while avoiding spoilers.

[0259] The "means for receiving information related to the search target content" refers to a device or program having a function of collecting related information from the Internet based on keywords entered by the user.

[0260] The "means for automatically generating an introduction that does not include spoilers" refers to a device or program having a function of excluding spoilers from collected information, extracting an outline of the content, and generating an introduction.

[0261] The "means for displaying the generated introduction text in the search results" refers to a device or program having a function for displaying the generated introduction text on the user's terminal.

[0262] The "means for collecting user behavioral data" refers to a device or program that has the function of collecting user behavioral data such as search history and browsing history.

[0263] The "means for inferring a user's emotions based on collected behavioral data" refers to a device or program having a function of analyzing collected behavioral data and inferring a user's emotions.

[0264] The "means for generating an introductory text based on an estimated emotion" refers to a device or a program having a function of automatically generating an introductory text appropriate to the emotion based on the estimated emotion of the user.

[0265] This invention is a system that, when a user inputs a keyword for the content they want to search for, collects information related to the keyword, generates and displays an introductory text that does not include spoilers, and also has the function of collecting user behavior data, estimating the user's emotions based on the data, and generating an introductory text according to the emotions.

[0266] Hardware and Software Used

[0267] 1. Server:

[0268] Search engine API: Used to collect information from the Internet. Specifically, Google Search API and Bing Search API are used.

[0269] Natural Language Processing library: Used to filter out spoilers and extract content summaries from collected information. Specifically, it uses the Hugging Face Transformers library and leverages a pre-trained BERT model.

[0270] Text summarization algorithms: used to extract an overview of the content. In particular, we use the Sumy library.

[0271] Sentiment Analysis API: Used to estimate emotions based on user behavior data. Specifically, it uses Google Cloud Natural Language API.

[0272] 2. Terminal:

[0273] Browser: Used by users to enter keywords and check search results. Specifically, common web browsers such as GOOGLE CHROME (registered trademark) and Mozilla Firefox are used.

[0274] 3. User:

[0275] Input device: Used to input keywords, specifically using a keyboard or touch screen.

[0276] Explanation of program processing

[0277] 1. User enters a keyword:

[0278] A user opens a browser on their device, accesses the search tool interface, enters a keyword such as "Inception" in the search bar, and clicks the search button.

[0279] 2. The server collects information:

[0280] The server receives the keywords entered by the user and uses the Google Search API or Bing Search API to collect related information from the Internet. For example, it calls the Google Search API to get a list of web pages related to "Inception."

[0281] 3. The server filters out spoilers:

[0282] The collected information is sent to the introductory text generation module in the server, which uses a pre-trained BERT model using Hugging Face's Transformers library to detect and remove spoilers from the collected text, for example removing sentences containing keywords such as "ending" or "culprit."

[0283] 4. Server extracts summary:

[0284] After filtering out spoilers, the server uses the Sumy library to summarize the text and extract an overview of the content, for example generating a short summary that includes key plot and character introductions for a movie.

[0285] 5. The server formats the description:

[0286] The extracted summary is formatted in Markdown or HTML, for example by displaying the movie title as a heading and a summary in paragraph format below it.

[0287] 6. The server displays the search results:

[0288] The formatted description is displayed in the user's browser as a search result page, and the user can view the results through their device's browser.

[0289] Examples and prompts

[0290] Examples

[0291] If a user searches for a movie title:

[0292] When a user enters the keyword "Inception", the server uses the Google Search API to collect information about "Inception". It excludes spoilers from the collected information, extracts a summary of the movie using the Sumy library, and generates a summary. If the user indicates the emotion of joy, a summary that highlights the positive aspects of the movie is displayed.

[0293] Examples of prompt statements

[0294] Prompt for generative AI model:

[0295] "A user has searched for the keyword "Inception". Extract a synopsis of the movie from the collected information, excluding spoilers. The user is currently expressing the emotion of joy. Generate a description that highlights the positive aspects."

[0296] In this way, the present invention is a system that provides appropriate information based on the user's input and emotions.

[0297] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0298] Step 1:

[0299] The user enters a keyword

[0300] A user opens a browser on their device, accesses the search tool interface, enters a keyword such as "Inception" in the search bar, and clicks the search button.

[0301] Input: The keyword entered by the user

[0302] Output: The keyword is sent to the server.

[0303] Step 2:

[0304] The server collects information

[0305] Based on the received keywords, the server calls a search engine API (e.g., Google Search API or Bing Search API) to collect related information.

[0306] Input: The keyword entered by the user

[0307] Output: Relevant information retrieved from the search engine API

[0308] Step 3:

[0309] Server filters out spoilers

[0310] The collected information is sent to a testimonial generation module in the server, which uses a natural language processing library (e.g., Hugging Face's Transformers library) to leverage a pre-trained model (e.g., the BERT model) to detect and filter out spoilers from the collected text.

[0311] Input: Related information obtained from search engine API

[0312] Output: Information without spoilers

[0313] Step 4:

[0314] The server extracts the summary

[0315] The spoiler-free information is then summarized using a text summarization algorithm (e.g., the Sumy library) to extract an overview of the content.

[0316] Input: Information without spoilers

[0317] Output: A summary of the extracted content

[0318] Step 5:

[0319] The server formats the introduction

[0320] The extracted summary is formatted in Markdown or HTML, for example by displaying the movie title as a heading and a summary in paragraph format below it.

[0321] Input: A summary of the extracted content

[0322] Output: A formatted introduction

[0323] Step 6:

[0324] The server displays the search results.

[0325] The formatted description is displayed in the user's browser as a search result page, and the user can view the results through their device's browser.

[0326] Input: Formatted description

[0327] Output: The search results displayed in the user's browser.

[0328] Step 7:

[0329] The server collects user behavior data

[0330] The server collects user behavioral data, such as search history and browsing history, using browser cookies and local storage.

[0331] Input: User search and browsing history

[0332] Output: Collected behavioral data

[0333] Step 8:

[0334] The server estimates the emotion

[0335] Analyze the collected behavioral data and infer user emotions using a sentiment analysis API (e.g., Google Cloud Natural Language API).

[0336] Input: Collected behavioral data

[0337] Output: Estimated user emotion

[0338] Step 9:

[0339] The server generates the introduction

[0340] Based on the estimated emotion, a generative AI model is used to input a prompt sentence and automatically generate an introduction that matches the emotion.

[0341] Input: Estimated user emotion

[0342] Output: An emotionally appropriate introduction

[0343] Step 10:

[0344] The server displays the introductory text.

[0345] The generated introduction is displayed on the user's browser, allowing the user to check the results through their device and enjoy content that matches their emotions.

[0346] Input: An emotionally appropriate introduction

[0347] Output: The introductory text displayed in the user's browser.

[0348] (Application example 1)

[0349] 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 device 14 will be referred to as a "terminal."

[0350] In conventional Internet search tools, when collecting information about the content a user searches for, information containing spoilers may be displayed, which may ruin the user's experience. In addition, since content is not introduced according to the user's emotions, it is difficult to increase user satisfaction.

[0351] 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.

[0352] In this invention, the server includes a means for receiving information about the content to be searched, a means for automatically generating an introduction that does not include spoilers based on the received information, a means for recognizing a user's emotions and customizing the introduction based on the emotions, and a means for displaying the generated introduction in the search results. This makes it possible to introduce content according to the user's emotions while preventing spoilers.

[0353] The "means for receiving information related to the search target content" is a function for collecting information on related content based on keywords entered by the user.

[0354] The "means for automatically generating an introduction that does not include spoilers based on the received information" is a function for excluding spoilers from the collected content information and generating an introduction that is suitable for the user.

[0355] "Means of recognizing user emotions and customizing the introductory text based on those emotions" refers to a function that analyzes a user's search history and behavioral data to infer emotions and adjust the introductory text according to those emotions.

[0356] "Means for displaying the generated testimonial in the search results" refers to a function for displaying the generated testimonial on the user's search result page.

[0357] A system for implementing the present invention includes a server, a user terminal, and a generative AI model. A specific embodiment of the system will be described below.

[0358] System Configuration

[0359] 1. Server:

[0360] The server receives search keywords from the user.

[0361] The server collects related content information based on the received keywords.

[0362] The server removes spoilers from the collected information and generates an introduction.

[0363] The server recognizes the user's emotions and customizes the testimonials based on the emotions.

[0364] The server transmits the generated introduction to the user terminal.

[0365] 2. User device:

[0366] The user terminal provides an interface for the user to input search keywords.

[0367] The user terminal displays the introduction sent from the server.

[0368] 3. Generative AI model:

[0369] The generative AI model analyzes users' search history and behavioral data to infer their emotions.

[0370] A generative AI model customizes testimonials based on sentiment.

[0371] Program Processing

[0372] When the server receives the search keyword entered by the user, it collects related content information. This information can be collected from external APIs or databases. The collected information is filtered to prevent spoilers and then sent to the introduction generation module.

[0373] The introduction generation module extracts an overview of the content from the collected information, excluding spoilers. Based on this overview, an introduction suitable for the user is generated. Next, the emotion engine analyzes the user's search history and behavioral data to estimate the user's emotions. Based on this emotion information, the introduction is customized.

[0374] For example, if the user feels like relaxing, an introductory text for relaxing content is generated. The generated introductory text is transmitted from the server to the user terminal and displayed on the user's search result page.

[0375] Examples

[0376] If a user searches for "relaxing movies", the following prompt might be generated:

[0377] Example prompt:

[0378] User's recent behavior data: "Recent searches: 'stress relief', 'relaxing music', 'yoga videos'"

[0379] When this prompt is fed into a sentiment analysis model, the user's sentiment is estimated to be "positive," and a description of a relaxing movie is generated based on this.

[0380] The above is a specific embodiment for carrying out the present invention. This system makes it possible to introduce content according to the user's emotions while preventing spoilers.

[0381] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0382] Step 1:

[0383] A user inputs a search keyword into a terminal. The terminal sends the keyword to a server. The input is the user's search keyword, and the output is a search request sent to the server.

[0384] Step 2:

[0385] The server collects relevant content information based on the received search keywords. This information collection is done using external APIs and databases. The input is the search keywords, and the output is the collected content information.

[0386] Step 3:

[0387] The server performs filtering to remove spoilers from the collected content information. Specifically, it removes specific keywords and phrases. The input is the collected content information, and the output is the content information with spoilers removed.

[0388] Step 4:

[0389] The server extracts a summary of the content from the spoiler-free content information. It generates an introduction based on the extracted summary. The input is the spoiler-free content information, and the output is the generated introduction.

[0390] Step 5:

[0391] The server analyzes the user's search history and behavioral data to estimate the user's emotions. A generative AI model is used for this analysis. The input is the user's search history and behavioral data, and the output is the estimated user's emotions.

[0392] Step 6:

[0393] The server customizes the introduction based on the estimated user's emotion. For example, if the user feels like relaxing, the server generates an introduction for relaxing content. The input is the estimated user's emotion and the generated introduction, and the output is the customized introduction.

[0394] Step 7:

[0395] The server sends the customized introduction to the user terminal, where the input is the customized introduction and the output is the introduction sent to the user terminal.

[0396] Step 8:

[0397] The user terminal displays the introduction text sent from the server on the search result page. The input is the introduction text sent from the server, and the output is the introduction text displayed to the user.

[0398] Example 2

[0399] Next, a second embodiment of the second embodiment will be described. 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."

[0400] In conventional search systems, when a user searches for information about a particular piece of content, information containing spoilers may be displayed, which may ruin the user's experience. There is also the problem that it is difficult to provide optimal search results according to the user's emotions. To solve these problems, a system is needed that generates introductions that do not include spoilers and adjusts the display order of search results based on the user's emotions.

[0401] 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 receiving information about the data to be searched, a means for automatically generating an introduction text that does not include spoilers based on the received information, a means for displaying the generated introduction text in the search results, a means for analyzing the user's emotions, and a means for adjusting the display order of the introduction text based on the analyzed emotions. This allows the user to obtain optimal search results according to their emotions while avoiding spoilers.

[0402] "Searchable data" refers to the specific information or content for which a user is searching.

[0403] "Means for receiving information" means a device or software that has the function of receiving a search query from a user and collecting related information based on the query.

[0404] A "spoiler-free introduction" is a piece of text that provides users with basic information such as an overview, genre, and play style, without including the ending or important plot details of the content.

[0405] An "automated generation means" is a device or software that has the capability to automatically generate a testimonial based on the information it receives using a particular algorithm or generative AI model.

[0406] "Means for displaying in the search results" refers to a device or software that has the function of displaying the generated introduction on the user's terminal.

[0407] "Means for analyzing user emotions" refers to devices or software that have the function of analyzing the user's emotional state based on data such as facial expressions and voice.

[0408] A "means for adjusting the display order" refers to a device or software that has the function of optimizing the display order of search results based on the analyzed user sentiment.

[0409] This invention is a system that generates an introduction that does not include spoilers when a user searches for information about a specific data item, and adjusts the display order of search results based on the user's feelings. This system works in cooperation with a server, a terminal, and a user.

[0410] First, a user uses a device to search for specific data. For example, a user opens a browser on a smartphone, enters "a specific game title" in the search bar, and presses the search button. This action sends a search query from the device to the server.

[0411] Based on the received search query, the server collects relevant information from the Internet using existing search engine APIs such as Google API or Bing API. The server sends an API request and analyzes the returned search results to extract the required information.

[0412] The collected information is sent to an introductory text generation module in the server. This module processes the information using a generative AI model (e.g., OpenAI's GPT-4). The server converts the collected information into an appropriate format and inputs it into the generative AI model. As an example of a specific prompt, we use the sentence, "Please generate an introductory text for a specific game title, but please do not include the game's ending or important plot."

[0413] The introduction generation module extracts an overview of the game, such as the game's genre and play style, from the collected information, excluding the game's ending and important plot details. Based on this prompt, the generative AI model generates an appropriate introduction.

[0414] The extracted summary is then formatted into an introduction by the server, which formats the resulting text in a way that is easy for the user to understand, and adds additional information and links as needed.

[0415] The formatted description is then displayed on the user's device alongside the search results. For example, when a user opens the search results page, they are presented with information about the game's overview, genre, and play style. This information is careful not to include the game's ending or important plot details.

[0416] In addition, the server uses an emotion engine to adjust the display order of the introductions. The user's emotions are analyzed based on data collected through the device's camera and microphone. For example, if the user expresses happiness during a search, the server uses the emotion engine to display introductions related to content that the user is likely to feel happy at the top of the search results. On the other hand, if the user expresses anger, the server displays introductions related to content that the user is likely to feel angry at the bottom of the search results.

[0417] In this way, users can avoid spoilers and get the best search results based on their emotions.

[0418] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0419] Step 1:

[0420] A user uses a device to search for specific data. The user opens a browser on his / her smartphone, enters "a specific game title" in the search bar, and presses the search button. This action causes a search query to be sent from the device to the server. The input is the user's search query, and the output is the query sent to the server.

[0421] Step 2:

[0422] Based on the search query received by the server, related information is collected from the Internet using existing search engine APIs such as Google API or Bing API. The server sends an API request and analyzes the returned search results to extract the required information. The input is the search query, and the output is the collected related information.

[0423] Step 3:

[0424] The server sends the collected information to the introduction generation module, which processes the information using a generative AI model (e.g., OpenAI's GPT-4). The server converts the collected information into an appropriate format and inputs it into the generative AI model. The input is the collected information, and the output is the input data to the generative AI model.

[0425] Step 4:

[0426] The introduction generation module excludes the game's ending and important plot from the collected information and extracts an overview of the game's genre, play style, etc. An example of a specific prompt is "Generate an introduction for a specific game title, but do not include the game's ending or important plot." The input is the prompt to the generative AI model and the collected information, and the output is an introduction that does not contain spoilers.

[0427] Step 5:

[0428] The server formats the extracted summary into a blurb. The server formats the generated text in a way that is easy for the user to understand, and adds additional information and links as needed. The input is the generated blurb, and the output is the formatted blurb.

[0429] Step 6:

[0430] The server displays the formatted description along with the search results on the user's device. When the user visits the search results page, they are presented with information about the game's synopsis, genre, and play style. This information is careful not to include the game's ending or important plot details. The input is the formatted description and the search results, and the output is the information displayed on the user's device.

[0431] Step 7:

[0432] The server adjusts the display order of the introductions using the emotion engine. The user's emotions are analyzed based on data collected through the device's camera and microphone. For example, if the user shows an emotion of happiness during a search, the server uses the emotion engine to display introductions about content that the user is likely to feel happy at the top of the search results. Also, if the user shows an emotion of anger, the server displays introductions about content that the user is likely to feel angry at the bottom of the search results. The input is the user's emotion data, and the output is the adjusted display order of the search results.

[0433] (Application example 2)

[0434] 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."

[0435] In conventional search systems, when providing information about the content searched by the user, information containing spoilers may be displayed, which may ruin the user's experience. In addition, since the information provided does not correspond to the user's emotions, it is difficult to increase user satisfaction. Furthermore, since the display order of search results is not adjusted based on the user's emotions, there is also the problem that the information provided is not optimal for the user.

[0436] 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.

[0437] In this invention, the server includes a means for receiving information about the content to be searched, a means for automatically generating an introduction that does not include spoilers based on the received information, a means for displaying the generated introduction in the search results, a means for analyzing the user's emotions, and a means for adjusting the display order of the introductions based on the analyzed emotions. This makes it possible to provide information about the content searched for by the user without spoilers, and further provide optimal information according to the user's emotions.

[0438] "Searchable content" is the specific digital content about which a user seeks to obtain information through a search engine or application.

[0439] "Means for receiving information" refers to functions or modules for obtaining data regarding the content searched by the user.

[0440] A "spoiler-free description" is a description that includes only basic information such as an overview, genre, and play style, excluding the ending of the content or important plot details.

[0441] "Automatic generation means" refers to a function that automatically creates an introduction based on received information using a specific algorithm or model.

[0442] "Means for displaying in search results" refers to a function or module that allows the generated testimonial to be displayed on a user's search results page.

[0443] A "means for analyzing user emotions" is a function for inferring emotions from a user's input or actions, and analyzing those emotions as numerical values ​​or categories.

[0444] The "means for adjusting the display order" is a function for changing the display order of the generated testimonials based on the analyzed user sentiment.

[0445] A system for carrying out the present invention has the following configuration: A server includes means for receiving information related to the content to be searched, means for automatically generating an introduction that does not include spoilers based on the received information, means for displaying the generated introduction in the search results, means for analyzing the user's emotions, and means for adjusting the display order of the introductions based on the analyzed emotions.

[0446] How to receive information

[0447] The server receives search queries entered by users through search engines or applications. For example, if a user searches for "game title," the server retrieves information about that game through the API. In this case, the server uses the requests library to gather data from external sources.

[0448] A method for automatically generating spoiler-free introductions

[0449] Based on the received information, the server uses a generative AI model to automatically generate an introductory text that does not contain spoilers. Specifically, the server uses the GPT-3 (registered trademark) model with the transformers library to generate an introductory text by inputting the following prompt text:

[0450] Example prompt:

[0451] Game Title: Example Game

[0452] Genre: Action

[0453] Play Style: Single Player

[0454] overview:

[0455] How to appear in search results

[0456] The generated description is displayed by the server on the user's search result page, allowing the user to obtain basic information about the game, such as its genre and play style, without giving away any spoilers.

[0457] A means of analyzing user sentiment

[0458] The server analyzes the sentiment of users based on their input text and behavioral data, and uses the TextBlob library to quantify the sentiment from the user's text and classify it into categories such as positive, negative, and neutral.

[0459] Ways to adjust display order

[0460] Based on the analyzed user sentiment, the server adjusts the display order of the generated testimonials. For example, if the user has positive sentiment, the server displays the testimonials with positive content at the top, and if the user has negative sentiment, the server displays the testimonials with negative content at the bottom.

[0461] Examples

[0462] If a user searches for the game title "Example Game" and enters the text "I am so excited to play this game!", the server will detect the positive emotion and display the positive review text at the top, so that the user can get the information that best matches their emotion.

[0463] In this way, the present invention provides information about the content searched for by the user without spoilers, and further provides optimal information according to the user's emotions.

[0464] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0465] Step 1:

[0466] The server receives the search query entered by the user. When a user searches for "game title", the query is sent to the server. The server takes this query as input and proceeds with the next step.

[0467] Step 2:

[0468] Based on the received search query, the server retrieves relevant content information from external sources. Specifically, it uses the requests library to send API requests to collect data about the game title, including the game genre, play style, basic information, etc. The retrieved data is used in the next step.

[0469] Step 3:

[0470] Based on the acquired content information, the server uses a generative AI model to automatically generate an introductory text that does not contain spoilers. Specifically, the server uses the transformers library to input a prompt text into the GPT-3 model to generate an introductory text. An example of a prompt text is in the following format:

[0471] Game Title: Example Game

[0472] Genre: Action

[0473] Play Style: Single Player

[0474] overview:

[0475] The generated testimonial is used in the next step.

[0476] Step 4:

[0477] The server analyzes the emotions based on the user's input text and behavioral data. It uses the TextBlob library to quantify the emotions from the user's text and classify them into categories such as positive, negative, neutral, etc. The analysis results are used in the next step.

[0478] Step 5:

[0479] The server adjusts the display order of the generated testimonials based on the analyzed user emotions. If positive emotions are detected, testimonials with positive content are displayed at the top, and if negative emotions are detected, testimonials with negative content are displayed at the bottom. This allows the server to provide optimal information according to the user's emotions.

[0480] Step 6:

[0481] The server displays the generated introductions based on the adjusted display order on the user's search result page, allowing the user to obtain the information that best suits their emotions while avoiding spoilers.

[0482] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice 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 voice data.

[0483] 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<URL: https: / / openai.com / blog / chatgpt> ) and other generation AIs. The data generation model 58 is obtained by making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[0484] Another example of generative AI is Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0485] In the above embodiment, an example was given in which the specific process was performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0486] [Second embodiment]

[0487] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0488] 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.

[0489] 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 wide area network (WAN) and / or a local area network (LAN).

[0490] 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.

[0491] 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 the voice according to instructions from the processor 46.

[0492] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0493] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0494] Fig. 4 shows an example of 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.

[0495] 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.

[0496] 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.

[0497] 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.

[0498] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0499] "Example 1"

[0500] In one embodiment of the present invention, an Internet search tool is provided. When a user inputs a keyword related to a content to be searched, the search tool collects information related to the keyword. The collected information is sent to a spoiler-free introduction generation module. The module removes spoilers from the collected information and extracts a summary of the content. The extracted summary is formatted as an introduction and displayed to the user along with the search results.

[0501] "Example 2"

[0502] As a concrete example, consider the case where a user searches for "game title." The search tool collects information related to "game title" and sends it to a description generation module to prevent spoilers. This module excludes the game's ending and important plot points from the collected information and extracts an overview of the game, such as its genre and play style. The extracted overview is formatted as a description and displayed to the user along with the search results. This allows the user to understand the content of the game, but does not reveal any spoilers about the game's ending or important plot points.

[0503] The process flow of each embodiment will be described below.

[0504] "Example 1"

[0505] Step 1: User enters keywords into the search tool.

[0506] Step 2: The search tool gathers information from the Internet related to the keywords you entered.

[0507] Step 3: The collected information is sent to a spoiler-free introduction generation module. Step 4: The introduction generation module removes spoilers from the collected information and extracts a summary of the content.

[0508] Step 5: The extracted summary is formatted as a description and displayed to the user along with the search results.

[0509] "Example 2"

[0510] Step 1: User types "game title" into the search tool.

[0511] Step 2: The search tool collects information related to the "game title" from the Internet.

[0512] Step 3: The collected information is sent to a description generation module to prevent spoilers. Step 4: The description generation module extracts an overview of the game, such as its genre and play style, from the collected information, excluding the game's ending and important plot details.

[0513] Step 5: The extracted synopsis is formatted as a description and displayed to the user alongside the search results, allowing the user to understand the game's contents without spoiling the game's ending or important plot details.

[0514] Example 1

[0515] 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".

[0516] Conventional Internet search tools often display information containing spoilers when collecting information about the content a user searches for, which can ruin the user's experience. In addition, there was a lack of a way to properly format the collected information and display it in a way that is easy for users to understand.

[0517] 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.

[0518] In this invention, the server includes a means for receiving keywords related to the content to be searched, a means for collecting related information based on the received keywords, a means for transmitting the collected information to an introductory text generation module for preventing spoilers, a means for generating an introductory text that excludes spoilers using a generative AI model, a means for formatting the generated introductory text, and a means for displaying the formatted introductory text together with the search results, thereby enabling the user to check the outline of the content without including spoilers.

[0519] "Searchable content" is data about a particular subject or topic about which a user wants information.

[0520] A "keyword" is a word or phrase that a user enters to identify the content they are searching for.

[0521] "Related information" refers to data and materials related to keywords collected from search engines and databases.

[0522] "Introduction Generation Module" is a software component for analyzing collected related information and generating a spoiler-free summary of the content.

[0523] A "generative AI model" is an algorithm or system that uses artificial intelligence technology to generate appropriate text from input data.

[0524] A "formatter" is a process or tool used to convert the generated testimonial into a user-friendly form.

[0525] "Search results" are a list of related information displayed based on the keywords entered by the user.

[0526] "Display Means" means the method or technology used to display the formatted description and search results on the user's device.

[0527] The present invention is a system in which a user inputs a keyword for a content they wish to search, collects information related to the keyword, and generates an introduction to prevent spoilers. A specific embodiment of this system will be described below.

[0528] The server receives the keyword entered by the user. The user enters the keyword of the content he or she wants to search for in the search bar of the terminal. For example, the user enters "review of the latest movie 'Avengers'."

[0529] The terminal sends the entered keyword to the server, using the HTTPS protocol for this communication.

[0530] The server collects relevant information based on the received keywords. To do this, it uses search engine APIs such as Google Search API and Bing Search API. For example, it sends a query such as "Avengers movie reviews" to the search engine.

[0531] The server sends the collected information to an introductory text generation module, which analyzes the collected information and identifies parts that contain spoilers.

[0532] The introduction generation module uses a generative AI model to generate an introduction that excludes spoilers. Specifically, it uses a generative AI model such as OpenAI's GPT-4. The generative AI model takes the prompt as input and generates an appropriate introduction.

[0533] For example, the following sentence is input as a prompt into the generative AI model:

[0534] "Please give us your review of the latest movie, The Avengers, without any spoilers please."

[0535] The generated testimonial is then formatted by the server. Formatting is the process of converting the generated testimonial into a form that is easy for the user to read, i.e., converting it into a suitable format so that it is easy for the user to understand.

[0536] The server then sends the formatted introduction to the terminal, again using the HTTPS protocol.

[0537] The terminal displays the received introduction text to the user, allowing the user to check an outline of the content without including spoilers.

[0538] In this way, users can feel at ease knowing the outline of the content. This system provides an effective means of providing users with the necessary information while preventing spoilers.

[0539] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0540] Step 1:

[0541] The user enters search keywords.

[0542] The user inputs the keyword of the content they want to search for into the search bar of the device. For example, they input "Review of the latest movie 'Avengers'." The input keyword becomes the input data of the device.

[0543] Step 2:

[0544] The terminal transmits the entered keyword to the server.

[0545] The terminal sends the keyword entered by the user to the server. This communication uses the HTTPS protocol. The input is the keyword entered by the user, and the output is the keyword sent to the server.

[0546] Step 3:

[0547] The server collects information related to the keywords.

[0548] The server uses the Google Search API or Bing Search API to collect related information based on the received keywords. For example, a query such as "Avengers movie reviews" is sent to the search engine. The input is the keyword sent to the server, and the output is the collected related information.

[0549] Step 4:

[0550] The server sends the collected information to the testimonial generation module.

[0551] The server sends the collected information to the testimonial generation module, where the input is the collected relevant information and the output is the information sent to the testimonial generation module.

[0552] Step 5:

[0553] The introduction generation module generates an introduction that excludes spoilers.

[0554] The introduction generation module uses a generative AI model to generate an introduction that excludes spoilers from the collected information. Specifically, the prompt "Please give us a review of the latest movie, The Avengers, but without spoilers." is input to the generative AI model. The input is the information sent to the introduction generation module, and the output is the generated introduction.

[0555] Step 6:

[0556] The server formats the generated description.

[0557] The server formats the introduction received from the generative AI model. Formatting is the process of converting the generated introduction into a form that is easy for users to read, i.e., converting it into a proper format to make it easy for users to understand. The input is the generated introduction, and the output is the formatted introduction.

[0558] Step 7:

[0559] The server sends the formatted introduction to the terminal.

[0560] The server sends the formatted introduction to the terminal. This communication also uses the HTTPS protocol. The input is the formatted introduction, and the output is the introduction sent to the terminal.

[0561] Step 8:

[0562] The terminal displays the introductory text to the user.

[0563] The terminal displays the received introduction text to the user. The user can check the outline of the content without including spoilers. The input is the introduction text sent to the terminal, and the output is the introduction text displayed to the user.

[0564] (Application example 1)

[0565] 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".

[0566] Conventional Internet search tools often display information containing spoilers when collecting information about the content a user searches for, which can cause problems for the user's experience. In addition, it is difficult to efficiently collect information because it takes time to manually select information to avoid spoilers. Another issue is that the generated introduction text gets buried in the search results, making it difficult for users to quickly access the information they need.

[0567] 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.

[0568] In this invention, the server includes a means for receiving information about the content to be searched, a means for automatically generating an introduction that does not include spoilers based on the received information, a means for displaying the generated introduction in the search results, and a means for generating a prompt text using a generative AI model to generate an introduction that excludes spoilers. This allows the user to efficiently grasp the outline of the content while avoiding spoilers.

[0569] The "means for receiving information related to the content to be searched" refers to a device or program that has the function of collecting related information from the Internet based on keywords entered by the user.

[0570] The "means for automatically generating an introduction that does not include spoilers based on received information" refers to a device or program that has the function of excluding spoilers from collected information, extracting an outline of the content, and generating an introduction.

[0571] The "means for displaying the generated testimonial in the search results" refers to a device or program having a function of displaying the generated testimonial on the user's search result page.

[0572] "Means for generating a prompt sentence using a generative AI model and generating an introduction sentence that excludes spoilers" refers to a device or program that has the function of using a generative AI model to generate a prompt sentence for excluding spoilers from collected information, and generating an introduction sentence based on the prompt sentence.

[0573] A system for carrying out the present invention has the following configuration: A server includes means for receiving information related to the content to be searched, means for automatically generating an introductory text that does not include spoilers based on the received information, means for displaying the generated introductory text in the search results, and means for generating a prompt text using a generative AI model to generate an introductory text that excludes spoilers.

[0574] Hardware and Software Used

[0575] Hardware: Servers, user devices (smartphones, PCs, etc.)

[0576] Software: Python, BeautifulSoup, requests, OpenAI API

[0577] Data processing and calculation

[0578] 1. Data collection: Based on the keywords entered by the user's device, the server collects related information on the Internet. Specifically, it uses the requests library to obtain the search result page and parses it with BeautifulSoup.

[0579] 2. Spoiler removal and summary generation: The server inputs the collected information into OpenAI's generative AI model to generate a spoiler-free introduction. Specifically, it generates a prompt using the openai.Completion.create method and inputs it into the AI ​​model.

[0580] 3. Displaying the results: The server displays the generated synopsis on the user's search result page, allowing the user to efficiently get an overview of the content without spoiling it.

[0581] Examples

[0582] When a user searches for "popular movies," the server collects related information and generates and displays an introductory text that excludes spoilers. For example, by inputting the following prompt text into the generative AI model, an introductory text that does not include spoilers is generated.

[0583] Examples of prompt statements

[0584] Generate a content summary from the following information, excluding spoilers:

[0585] This movie is about the protagonist overcoming difficulties and growing as he goes on various adventures with his friends.

[0586] The story depicts the protagonist's growth as he comes to terms with his past.

[0587] The main characters include his best friend and mentor.

[0588] By inputting this prompt into a generative AI model, a spoiler-free introduction is generated and provided to the user.

[0589] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0590] Step 1:

[0591] The user inputs a search keyword from the terminal.

[0592] Input: The keyword for which the user wants to search for the content

[0593] Output: Search keywords sent to the server

[0594] Step 2:

[0595] The server collects relevant information on the Internet based on the search keywords.

[0596] Input: Search keyword

[0597] Output: A list of related information

[0598] What it does: The server uses the requests library to get the search results page, then parses it with BeautifulSoup to extract relevant information.

[0599] Step 3:

[0600] The server generates prompt sentences to input the collected information into the generative AI model.

[0601] Input: List of related information

[0602] Output: Prompt statement

[0603] Specific operation: The server generates a prompt text to filter out spoilers based on the collected information.

[0604] Step 4:

[0605] The server uses a generative AI model to generate a spoiler-free introduction based on the prompt text.

[0606] Input: Prompt statement

[0607] Output: Introduction without spoilers

[0608] Specific operation: The server uses the openai.Completion.create method to input the prompt text into the generation AI model and generate an introduction that excludes spoilers.

[0609] Step 5:

[0610] The server displays the generated testimonial on the user's search results page.

[0611] Input: Introduction without spoilers

[0612] Output: A description that will be displayed on the user's search results page.

[0613] Specific behavior: The server sets the generated testimonial to be displayed at the top of the search result page.

[0614] Example 2

[0615] Next, a description will be given of Example 2 of the embodiment 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[0616] In conventional search systems, when users searched for information related to specific content, information containing spoilers was often displayed, which had the problem of ruining the user's experience. In addition, there was a lack of means to efficiently collect related information and generate appropriate introductions, making it difficult to quickly and accurately provide the information users were looking for.

[0617] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0618] In this invention, the server includes a means for receiving information about the content to be searched, a means for collecting related information based on the received information, a means for automatically generating an introductory text that does not include spoilers from the collected information, a means for formatting the generated introductory text, and a means for displaying the formatted introductory text in the search results. This makes it possible to quickly and accurately provide related information to the content searched for by the user while avoiding spoilers.

[0619] The "means for receiving information regarding the content being searched" refers to a function that allows the server to receive keywords or phrases that a user enters into the search bar.

[0620] "Means of collecting related information based on received information" refers to a function that uses search tools to collect related data from the Internet based on received keywords or phrases.

[0621] "Means for automatically generating a spoiler-free introduction from collected information" refers to a function that analyzes collected data, excludes important plot details and endings, and automatically creates a summary of the content using a generative AI model.

[0622] The "means for formatting the generated introduction" is a function for grammar checking and formatting the generated introduction to make it easier for the user to read.

[0623] The "means for displaying the formatted introduction in the search results" is a function for transmitting the formatted introduction to the user's terminal and displaying it on the search result page.

[0624] The present invention provides a system for automatically generating an introduction that does not include spoilers and displaying it in the search results when a user searches for information related to a particular piece of content. A specific embodiment of this system will be described below.

[0625] The server has a means for receiving keywords or phrases entered by a user into the search bar. When a user enters a "game title" into the search bar using a browser or a dedicated application on the terminal and clicks a search button, this search request is sent to the server.

[0626] Based on the received keywords or phrases, the server uses search tools such as Elasticsearch to gather relevant data from the Internet, including information from official game websites, review sites, forum posts, etc.

[0627] The collected information is then sent to a generative AI model, such as OpenAI’s GPT-4, using prompts to give the model specific instructions. For example, the following prompts can be used:

[0628] We have gathered information about the "Game Title". From this information, we would like you to generate a description that includes the game's genre, play style, and basic storyline, excluding the game's ending and important plot details.

[0629] The generative AI model analyzes the collected data, removes important plot details and endings, and automatically creates a summary of the content. The server checks the grammar and formats the summary to make it easier for users to read.

[0630] The formatted description is sent from the server to the user's device and displayed on the search results page, allowing the user to understand the general outline of the game, but without spoiling the ending or important plot details.

[0631] As a concrete example, consider the case where a user searches for "Final Fantasy VII." The server uses Elasticsearch to collect information related to "Final Fantasy VII" from the Internet. It then sends the collected information to GPT-4, which generates a description using the following prompt:

[0632] You have gathered information about "Final Fantasy VII." From this information, generate a description that includes the game's genre, play style, and basic storyline, excluding the game's ending and key plot details.

[0633] An example of a generated introduction might look like this:

[0634] "Final Fantasy VII" is a role-playing game. Players control characters and fight against giant corporations with rebel groups. The game employs a turn-based battle system and features a wide range of character development elements.

[0635] This description will be displayed on the user's device along with the search results.

[0636] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0637] Step 1:

[0638] A user enters keywords into the search bar and clicks the search button.

[0639] Input: The keyword entered by the user (e.g. "game title")

[0640] Output: A search request is sent to the server.

[0641] Specific operation: The user enters the "game title" in the search bar using the device's browser or a dedicated application, and clicks the search button. This action sends a search request to the server.

[0642] Step 2:

[0643] A server receives the search request and collects the relevant information.

[0644] Input: Search request (keywords entered by the user)

[0645] Output: Related information (e.g. official website, review sites, forum posts)

[0646] Specific operation: Based on the received search request, the server uses search tools such as Elasticsearch to collect information related to the "game title" from the Internet. Specifically, it obtains data from the game's official website, review sites, forum posts, etc.

[0647] Step 3:

[0648] The server sends the collected information to a generative AI model to generate a testimonial.

[0649] Input: Information collected (e.g. official sites, review sites, forum posts)

[0650] Output: Generated introduction (no spoilers)

[0651] Specific operation: The server sends the collected information to a generative AI model such as OpenAI's GPT-4. At this time, it uses a prompt to give specific instructions to the generative AI model. For example, the following prompt can be used:

[0652] We have gathered information about the "Game Title". From this information, we would like you to generate a description that includes the game's genre, play style, and basic storyline, excluding the game's ending and important plot details.

[0653] Step 4:

[0654] The server formats the generated description.

[0655] Input: Generated introductory text (no spoilers)

[0656] Output: A formatted introduction (grammar checked and formatted)

[0657] How it works: The server receives the introduction returned by the generative AI model and performs grammar checks and formatting adjustments to make it easier for users to read.

[0658] Step 5:

[0659] The server sends the formatted introduction to the user's terminal and displays it.

[0660] Input: Formatted introduction (grammar checked and formatted)

[0661] Output: The introductory text that is displayed to the user.

[0662] Specific operation: The server sends the formatted introductory text to the user's device. The user's device displays the received introductory text on the browser or application screen. This allows the user to understand the outline of the game, but does not reveal any spoilers about the ending or important plot points.

[0663] (Application example 2)

[0664] 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".

[0665] In conventional search systems, when users searched for information about content, information containing spoilers was often displayed, which led to problems that marred the user experience. In addition, the generated introduction text was sometimes not displayed properly in the search results, which meant that users could not quickly access the information they needed. Furthermore, there were problems with the quality of the introduction text and the speed of generation because the introduction text was not generated efficiently using a generative AI model.

[0666] 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.

[0667] In this invention, the server includes a means for receiving information about the content to be searched, a means for automatically generating an introduction that does not include spoilers based on the received information, a means for displaying the generated introduction in the search results, a means for generating the introduction using a generative AI model, and a means for receiving a prompt as an input. This allows the user to quickly obtain summary information about the required content while avoiding spoilers.

[0668] "Searchable content" refers to media works such as movies, dramas, anime, and games about which users want to obtain information.

[0669] The "means for receiving information" is a part of the system that has the function of collecting relevant data based on the search query entered by the user.

[0670] A "spoiler-free introduction" is a piece of text that provides basic information such as an overview, genre, and play style, excluding the ending or important plot details of the content.

[0671] An "automated generation means" is a part of a system that has the function of generating a testimonial based on the information received, using a specific algorithm or model.

[0672] "Means for displaying the generated testimonial in a search result" means a portion of the system that has functionality for appropriately placing and displaying the generated testimonial on a user's search result page.

[0673] A "generative AI model" is a trained model that uses artificial intelligence technology to generate appropriate introductions from input data.

[0674] A "prompt sentence" is text data input to a generative AI model, and is a sentence that contains instructions and conditions for the model to generate an appropriate output.

[0675] In order to implement this invention, the server, the terminal, and the user must each fulfill a specific role.

[0676] First, a user uses a terminal to input information about the content to be searched. The terminal can be a device such as a smartphone or a PC, and must be connected to the Internet. Once the user enters a search query, the terminal transmits the information to a server.

[0677] The server collects relevant information based on the received search query. Specifically, the server uses APIs to retrieve information about content from external databases and websites, including content overview, genre, play style, etc.

[0678] Next, the server uses a generative AI model to automatically generate a spoiler-free introductory text from the collected information. The generative AI model is a pre-trained natural language processing model that has the ability to generate an appropriate introductory text from the input information. The prompt text is text data input to the generative AI model, and includes instructions and conditions for the model to generate an appropriate output.

[0679] The generated introduction is sent from the server to the terminal and displayed on the terminal screen, allowing the user to quickly obtain an overview of the desired content while avoiding spoilers.

[0680] As a concrete example, consider the case where a user searches for the movie "Inception." When the user types "Inception" into the device, the device sends the information to the server. The server collects related information and uses a generative AI model to generate a description like this:

[0681] "Inception is a science fiction film with a complex plot involving dreams within dreams. The protagonist is a professional information stealer in dreams, and his latest mission is..."

[0682] This synopsis is displayed on the terminal screen, allowing the user to understand the outline of the movie.

[0683] Examples of prompts include:

[0684] "What kind of movie is Inception?"

[0685] In this way, the user can quickly obtain the necessary information while avoiding spoilers.

[0686] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0687] Step 1:

[0688] A user uses a terminal to enter a search query.

[0689] Input: The user enters the content they are searching for (e.g., "Inception").

[0690] Output: The device sends the search query to the server.

[0691] Specific actions: The user types "Inception" into the search bar on their smartphone or computer and presses the search button.

[0692] Step 2:

[0693] A server receives the search query and collects related information.

[0694] Input: The search query sent from the device (e.g. "Inception").

[0695] Output: Content information collected by the server from external databases and websites.

[0696] What happens: The server uses an API to retrieve information about "Inception" (such as summary, genre, play style, etc.) from movie databases and review sites.

[0697] Step 3:

[0698] Based on the information collected by the server, a generative AI model is used to generate an introduction that does not contain spoilers.

[0699] Input: Collected content information (e.g., summary of "Inception", genre, play style).

[0700] Output: A spoiler-free introduction generated by the generative AI model.

[0701] Specific operation: The server inputs the collected information into a generative AI model and generates a spoiler-free introduction using a prompt sentence (e.g., "What kind of movie is Inception?").

[0702] Step 4:

[0703] The server transmits the generated introduction to the terminal.

[0704] Input: An introductory text generated by a generative AI model.

[0705] Output: The introductory text sent to the terminal.

[0706] Specific operation: The server sends the generated introduction to the terminal and displays it on the user's search result page.

[0707] Step 5:

[0708] The terminal displays the received introduction to the user.

[0709] Input: The introduction sent by the server.

[0710] Output: The introductory text displayed on the user's device screen.

[0711] Specific operation: The device displays the received introduction at the top of the search result page and the user views it.

[0712] In addition, 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.

[0713] "Example 1"

[0714] As one embodiment of the present invention, a system incorporating an emotion engine is provided. The system recognizes a user's emotion and automatically generates an introductory text based on the emotion. Specifically, behavioral data such as a user's search history and browsing history is analyzed, and the user's emotion is estimated from the data. The estimated emotion is used to generate an introductory text. For example, if a user expresses an emotion of joy, an introductory text is generated for content that is likely to make the user happy. Also, if a user expresses an emotion of anger, an introductory text is not generated for content that is likely to make the user angry.

[0715] "Example 2"

[0716] As another embodiment of the present invention, an adjustment of the display order of introductions using an emotion engine is provided. Specifically, the display order of introductions is adjusted according to the emotion of the user. For example, when a user expresses an emotion of joy, introductions related to content that may make the user happy are displayed at the top of the search results. Also, when a user expresses an emotion of anger, introductions related to content that may make the user angry are displayed at the bottom of the search results. This makes it possible to provide optimal search results according to the emotion of the user.

[0717] The process flow of each embodiment will be described below.

[0718] "Example 1"

[0719] Step 1: Collect user behavioral data (e.g. search history, browsing history).

[0720] Step 2: Input the collected behavioral data into the emotion engine to estimate the user's emotions. Step 3: Automatically generate an introduction based on the estimated emotions.

[0721] Step 4: Display the generated testimonial to the user.

[0722] "Example 2"

[0723] Step 1: Collect user behavioral data (e.g. search history, browsing history).

[0724] Step 2: Input the collected behavioral data into the emotion engine to estimate the user's emotion. Step 3: Adjust the display order of the testimonials based on the estimated emotion.

[0725] Step 4: Display the testimonials to the user according to the adjusted display order.

[0726] Example 1

[0727] 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".

[0728] In conventional Internet search tools, when collecting information about the content searched by the user, information containing spoilers may be displayed, which may spoil the user's experience. In addition, since it is not possible to provide an appropriate introduction according to the user's emotions, it is difficult to improve user satisfaction. Furthermore, since the search results are not customized based on the user's emotions, it is difficult for the user to quickly access the information he or she is looking for.

[0729] 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.

[0730] In this invention, the server includes a means for receiving information about the content to be searched, a means for automatically generating an introduction that does not include spoilers based on the received information, a means for displaying the generated introduction in the search results, a means for collecting user behavior data, a means for estimating the user's emotions based on the collected behavior data, and a means for generating an introduction based on the estimated emotions. This makes it possible for a user to be provided with an appropriate introduction that corresponds to the emotions while avoiding spoilers.

[0731] The "means for receiving information related to the search target content" refers to a device or program having a function of collecting related information from the Internet based on keywords entered by the user.

[0732] The "means for automatically generating an introduction that does not include spoilers" refers to a device or program having a function of excluding spoilers from collected information, extracting an outline of the content, and generating an introduction.

[0733] The "means for displaying the generated introduction text in the search results" refers to a device or program having a function for displaying the generated introduction text on the user's terminal.

[0734] The "means for collecting user behavioral data" refers to a device or program that has the function of collecting user behavioral data such as search history and browsing history.

[0735] The "means for inferring a user's emotions based on collected behavioral data" refers to a device or program having a function of analyzing collected behavioral data and inferring a user's emotions.

[0736] The "means for generating an introductory text based on an estimated emotion" refers to a device or a program having a function of automatically generating an introductory text appropriate to the emotion based on the estimated emotion of the user.

[0737] This invention is a system that, when a user inputs a keyword for the content they want to search for, collects information related to the keyword, generates and displays an introductory text that does not include spoilers, and also has the function of collecting user behavior data, estimating the user's emotions based on the data, and generating an introductory text according to the emotions.

[0738] Hardware and Software Used

[0739] 1. Server:

[0740] Search engine API: Used to collect information from the Internet. Specifically, Google Search API and Bing Search API are used.

[0741] Natural Language Processing library: Used to filter out spoilers and extract content summaries from collected information. Specifically, it uses the Hugging Face Transformers library and leverages a pre-trained BERT model.

[0742] Text summarization algorithms: used to extract an overview of the content. In particular, we use the Sumy library.

[0743] Sentiment Analysis API: Used to estimate emotions based on user behavior data. Specifically, it uses Google Cloud Natural Language API.

[0744] 2. Terminal:

[0745] Browser: Used by users to enter keywords and check search results. Specifically, common web browsers such as Google Chrome and Mozilla Firefox are used.

[0746] 3. User:

[0747] Input device: Used to input keywords, specifically using a keyboard or touch screen.

[0748] Explanation of program processing

[0749] 1. User enters a keyword:

[0750] A user opens a browser on their device, accesses the search tool interface, enters a keyword such as "Inception" in the search bar, and clicks the search button.

[0751] 2. The server collects information:

[0752] The server receives the keywords entered by the user and uses the Google Search API or Bing Search API to collect related information from the Internet. For example, it calls the Google Search API to get a list of web pages related to "Inception."

[0753] 3. The server filters out spoilers:

[0754] The collected information is sent to the introductory text generation module in the server, which uses a pre-trained BERT model using Hugging Face's Transformers library to detect and remove spoilers from the collected text, for example removing sentences containing keywords such as "ending" or "culprit."

[0755] 4. Server extracts summary:

[0756] After filtering out spoilers, the server uses the Sumy library to summarize the text and extract an overview of the content, for example generating a short summary that includes key plot and character introductions for a movie.

[0757] 5. The server formats the description:

[0758] The extracted summary is formatted in Markdown or HTML, for example by displaying the movie title as a heading and a summary in paragraph format below it.

[0759] 6. The server displays the search results:

[0760] The formatted description is displayed in the user's browser as a search result page, and the user can view the results through their device's browser.

[0761] Examples and prompts

[0762] Examples

[0763] If a user searches for a movie title:

[0764] When a user enters the keyword "Inception", the server uses the Google Search API to collect information about "Inception". It excludes spoilers from the collected information, extracts a summary of the movie using the Sumy library, and generates a summary. If the user indicates the emotion of joy, a summary that highlights the positive aspects of the movie is displayed.

[0765] Examples of prompt statements

[0766] Prompt for generative AI model:

[0767] "A user has searched for the keyword "Inception". Extract a synopsis of the movie from the collected information, excluding spoilers. The user is currently expressing the emotion of joy. Generate a description that highlights the positive aspects."

[0768] In this way, the present invention is a system that provides appropriate information based on the user's input and emotions.

[0769] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0770] Step 1:

[0771] The user enters a keyword

[0772] A user opens a browser on their device, accesses the search tool interface, enters a keyword such as "Inception" in the search bar, and clicks the search button.

[0773] Input: The keyword entered by the user

[0774] Output: The keyword is sent to the server.

[0775] Step 2:

[0776] The server collects information

[0777] Based on the received keywords, the server calls a search engine API (e.g., Google Search API or Bing Search API) to collect related information.

[0778] Input: The keyword entered by the user

[0779] Output: Relevant information retrieved from the search engine API

[0780] Step 3:

[0781] Server filters out spoilers

[0782] The collected information is sent to a testimonial generation module in the server, which uses a natural language processing library (e.g., Hugging Face's Transformers library) to leverage a pre-trained model (e.g., the BERT model) to detect and filter out spoilers from the collected text.

[0783] Input: Related information obtained from search engine API

[0784] Output: Information without spoilers

[0785] Step 4:

[0786] The server extracts the summary

[0787] The spoiler-free information is then summarized using a text summarization algorithm (e.g., the Sumy library) to extract an overview of the content.

[0788] Input: Information without spoilers

[0789] Output: A summary of the extracted content

[0790] Step 5:

[0791] The server formats the introduction

[0792] The extracted summary is formatted in Markdown or HTML, for example by displaying the movie title as a heading and a summary in paragraph format below it.

[0793] Input: A summary of the extracted content

[0794] Output: A formatted introduction

[0795] Step 6:

[0796] The server displays the search results.

[0797] The formatted description is displayed in the user's browser as a search result page, and the user can view the results through their device's browser.

[0798] Input: Formatted description

[0799] Output: The search results displayed in the user's browser.

[0800] Step 7:

[0801] The server collects user behavior data

[0802] The server collects user behavioral data, such as search history and browsing history, using browser cookies and local storage.

[0803] Input: User search and browsing history

[0804] Output: Collected behavioral data

[0805] Step 8:

[0806] The server estimates the emotion

[0807] Analyze the collected behavioral data and infer user emotions using a sentiment analysis API (e.g., Google Cloud Natural Language API).

[0808] Input: Collected behavioral data

[0809] Output: Estimated user emotion

[0810] Step 9:

[0811] The server generates the introduction

[0812] Based on the estimated emotion, a generative AI model is used to input a prompt sentence and automatically generate an introduction that matches the emotion.

[0813] Input: Estimated user emotion

[0814] Output: An emotionally appropriate introduction

[0815] Step 10:

[0816] The server displays the introductory text.

[0817] The generated introduction is displayed on the user's browser, allowing the user to check the results through their device and enjoy content that matches their emotions.

[0818] Input: An emotionally appropriate introduction

[0819] Output: The introductory text displayed in the user's browser.

[0820] (Application example 1)

[0821] 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".

[0822] In conventional Internet search tools, when collecting information about the content a user searches for, information containing spoilers may be displayed, which may ruin the user's experience. In addition, since content is not introduced according to the user's emotions, it is difficult to increase user satisfaction.

[0823] 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.

[0824] In this invention, the server includes a means for receiving information about the content to be searched, a means for automatically generating an introduction that does not include spoilers based on the received information, a means for recognizing a user's emotions and customizing the introduction based on the emotions, and a means for displaying the generated introduction in the search results. This makes it possible to introduce content according to the user's emotions while preventing spoilers.

[0825] The "means for receiving information related to the search target content" is a function for collecting information on related content based on keywords entered by the user.

[0826] The "means for automatically generating an introduction that does not include spoilers based on the received information" is a function for excluding spoilers from the collected content information and generating an introduction that is suitable for the user.

[0827] "Means of recognizing user emotions and customizing the introductory text based on those emotions" refers to a function that analyzes a user's search history and behavioral data to infer emotions and adjust the introductory text according to those emotions.

[0828] "Means for displaying the generated testimonial in the search results" refers to a function for displaying the generated testimonial on the user's search result page.

[0829] A system for implementing the present invention includes a server, a user terminal, and a generative AI model. A specific embodiment of the system will be described below.

[0830] System Configuration

[0831] 1. Server:

[0832] The server receives search keywords from the user.

[0833] The server collects related content information based on the received keywords.

[0834] The server removes spoilers from the collected information and generates an introduction.

[0835] The server recognizes the user's emotions and customizes the testimonials based on the emotions.

[0836] The server transmits the generated introduction to the user terminal.

[0837] 2. User device:

[0838] The user terminal provides an interface for the user to input search keywords.

[0839] The user terminal displays the introduction sent from the server.

[0840] 3. Generative AI model:

[0841] The generative AI model analyzes users' search history and behavioral data to infer their emotions.

[0842] A generative AI model customizes testimonials based on sentiment.

[0843] Program Processing

[0844] When the server receives the search keyword entered by the user, it collects related content information. This information can be collected from external APIs or databases. The collected information is filtered to prevent spoilers and then sent to the introduction generation module.

[0845] The introduction generation module extracts an overview of the content from the collected information, excluding spoilers. Based on this overview, an introduction suitable for the user is generated. Next, the emotion engine analyzes the user's search history and behavioral data to estimate the user's emotions. Based on this emotion information, the introduction is customized.

[0846] For example, if the user feels like relaxing, an introductory text for relaxing content is generated. The generated introductory text is transmitted from the server to the user terminal and displayed on the user's search result page.

[0847] Examples

[0848] If a user searches for "relaxing movies", the following prompt might be generated:

[0849] Example prompt:

[0850] User's recent behavior data: "Recent searches: 'stress relief', 'relaxing music', 'yoga videos'"

[0851] When this prompt is fed into a sentiment analysis model, the user's sentiment is estimated to be "positive," and a description of a relaxing movie is generated based on this.

[0852] The above is a specific embodiment for carrying out the present invention. This system makes it possible to introduce content according to the user's emotions while preventing spoilers.

[0853] The flow of the specific process in the application example 1 will be described with reference to FIG.

[0854] Step 1:

[0855] A user inputs a search keyword into a terminal. The terminal sends the keyword to a server. The input is the user's search keyword, and the output is a search request sent to the server.

[0856] Step 2:

[0857] The server collects relevant content information based on the received search keywords. This information collection is done using external APIs and databases. The input is the search keywords, and the output is the collected content information.

[0858] Step 3:

[0859] The server performs filtering to remove spoilers from the collected content information. Specifically, it removes specific keywords and phrases. The input is the collected content information, and the output is the content information with spoilers removed.

[0860] Step 4:

[0861] The server extracts a summary of the content from the spoiler-free content information. It generates an introduction based on the extracted summary. The input is the spoiler-free content information, and the output is the generated introduction.

[0862] Step 5:

[0863] The server analyzes the user's search history and behavioral data to estimate the user's emotions. A generative AI model is used for this analysis. The input is the user's search history and behavioral data, and the output is the estimated user's emotions.

[0864] Step 6:

[0865] The server customizes the introduction based on the estimated user's emotion. For example, if the user feels like relaxing, the server generates an introduction for relaxing content. The input is the estimated user's emotion and the generated introduction, and the output is the customized introduction.

[0866] Step 7:

[0867] The server sends the customized introduction to the user terminal, where the input is the customized introduction and the output is the introduction sent to the user terminal.

[0868] Step 8:

[0869] The user terminal displays the introduction text sent from the server on the search result page. The input is the introduction text sent from the server, and the output is the introduction text displayed to the user.

[0870] Example 2

[0871] Next, a description will be given of Example 2 of the embodiment 2. In the following description, the data processing device 12 is referred to as a "server" and the smart glasses 214 are referred to as a "terminal".

[0872] In conventional search systems, when a user searches for information about a particular piece of content, information containing spoilers may be displayed, which may ruin the user's experience. There is also the problem that it is difficult to provide optimal search results according to the user's emotions. To solve these problems, a system is needed that generates introductions that do not include spoilers and adjusts the display order of search results based on the user's emotions.

[0873] 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 receiving information about the data to be searched, a means for automatically generating an introduction text that does not include spoilers based on the received information, a means for displaying the generated introduction text in the search results, a means for analyzing the user's emotions, and a means for adjusting the display order of the introduction text based on the analyzed emotions. This allows the user to obtain optimal search results according to their emotions while avoiding spoilers.

[0874] "Searchable data" refers to the specific information or content for which a user is searching.

[0875] "Means for receiving information" means a device or software that has the function of receiving a search query from a user and collecting related information based on the query.

[0876] A "spoiler-free introduction" is a piece of text that provides users with basic information such as an overview, genre, and play style, without including the ending or important plot details of the content.

[0877] An "automated generation means" is a device or software that has the capability to automatically generate a testimonial based on the information it receives using a particular algorithm or generative AI model.

[0878] "Means for displaying in the search results" refers to a device or software that has the function of displaying the generated introduction on the user's terminal.

[0879] "Means for analyzing user emotions" refers to devices or software that have the function of analyzing the user's emotional state based on data such as facial expressions and voice.

[0880] A "means for adjusting the display order" refers to a device or software that has the function of optimizing the display order of search results based on the analyzed user sentiment.

[0881] This invention is a system that generates an introduction that does not include spoilers when a user searches for information about a specific data item, and adjusts the display order of search results based on the user's feelings. This system works in cooperation with a server, a terminal, and a user.

[0882] First, a user uses a device to search for specific data. For example, a user opens a browser on a smartphone, enters "a specific game title" in the search bar, and presses the search button. This action sends a search query from the device to the server.

[0883] Based on the received search query, the server collects relevant information from the Internet using existing search engine APIs such as Google API or Bing API. The server sends an API request and analyzes the returned search results to extract the required information.

[0884] The collected information is sent to an introductory text generation module in the server. This module processes the information using a generative AI model (e.g., OpenAI's GPT-4). The server converts the collected information into an appropriate format and inputs it into the generative AI model. As an example of a specific prompt, we use the sentence, "Please generate an introductory text for a specific game title, but please do not include the game's ending or important plot."

[0885] The introduction generation module extracts an overview of the game, such as the game's genre and play style, from the collected information, excluding the game's ending and important plot details. Based on this prompt, the generative AI model generates an appropriate introduction.

[0886] The extracted summary is then formatted into an introduction by the server, which formats the resulting text in a way that is easy for the user to understand, and adds additional information and links as needed.

[0887] The formatted description is then displayed on the user's device alongside the search results. For example, when a user opens the search results page, they are presented with information about the game's overview, genre, and play style. This information is careful not to include the game's ending or important plot details.

[0888] In addition, the server uses an emotion engine to adjust the display order of the introductions. The user's emotions are analyzed based on data collected through the device's camera and microphone. For example, if the user expresses happiness during a search, the server uses the emotion engine to display introductions related to content that the user is likely to feel happy at the top of the search results. On the other hand, if the user expresses anger, the server displays introductions related to content that the user is likely to feel angry at the bottom of the search results.

[0889] In this way, users can avoid spoilers and get the best search results based on their emotions.

[0890] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0891] Step 1:

[0892] A user uses a device to search for specific data. The user opens a browser on his / her smartphone, enters "a specific game title" in the search bar, and presses the search button. This action causes a search query to be sent from the device to the server. The input is the user's search query, and the output is the query sent to the server.

[0893] Step 2:

[0894] Based on the search query received by the server, related information is collected from the Internet using existing search engine APIs such as Google API or Bing API. The server sends an API request and analyzes the returned search results to extract the required information. The input is the search query, and the output is the collected related information.

[0895] Step 3:

[0896] The server sends the collected information to the introduction generation module, which processes the information using a generative AI model (e.g., OpenAI's GPT-4). The server converts the collected information into an appropriate format and inputs it into the generative AI model. The input is the collected information, and the output is the input data to the generative AI model.

[0897] Step 4:

[0898] The introduction generation module excludes the game's ending and important plot from the collected information and extracts an overview of the game's genre, play style, etc. An example of a specific prompt is "Generate an introduction for a specific game title, but do not include the game's ending or important plot." The input is the prompt to the generative AI model and the collected information, and the output is an introduction that does not contain spoilers.

[0899] Step 5:

[0900] The server formats the extracted summary into a blurb. The server formats the generated text in a way that is easy for the user to understand, and adds additional information and links as needed. The input is the generated blurb, and the output is the formatted blurb.

[0901] Step 6:

[0902] The server displays the formatted description along with the search results on the user's device. When the user visits the search results page, they are presented with information about the game's synopsis, genre, and play style. This information is careful not to include the game's ending or important plot details. The input is the formatted description and the search results, and the output is the information displayed on the user's device.

[0903] Step 7:

[0904] The server adjusts the display order of the introductions using the emotion engine. The user's emotions are analyzed based on data collected through the device's camera and microphone. For example, if the user shows an emotion of happiness during a search, the server uses the emotion engine to display introductions about content that the user is likely to feel happy at the top of the search results. Also, if the user shows an emotion of anger, the server displays introductions about content that the user is likely to feel angry at the bottom of the search results. The input is the user's emotion data, and the output is the adjusted display order of the search results.

[0905] (Application example 2)

[0906] 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".

[0907] In conventional search systems, when providing information about the content searched by the user, information containing spoilers may be displayed, which may ruin the user's experience. In addition, since the information provided does not correspond to the user's emotions, it is difficult to increase user satisfaction. Furthermore, since the display order of search results is not adjusted based on the user's emotions, there is also the problem that the information provided is not optimal for the user.

[0908] 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.

[0909] In this invention, the server includes a means for receiving information about the content to be searched, a means for automatically generating an introduction that does not include spoilers based on the received information, a means for displaying the generated introduction in the search results, a means for analyzing the user's emotions, and a means for adjusting the display order of the introductions based on the analyzed emotions. This makes it possible to provide information about the content searched for by the user without spoilers, and further provide optimal information according to the user's emotions.

[0910] "Searchable content" is the specific digital content about which a user seeks to obtain information through a search engine or application.

[0911] "Means for receiving information" refers to functions or modules for obtaining data regarding the content searched by the user.

[0912] A "spoiler-free description" is a description that includes only basic information such as an overview, genre, and play style, excluding the ending of the content or important plot details.

[0913] "Automatic generation means" refers to a function that automatically creates an introduction based on received information using a specific algorithm or model.

[0914] "Means for displaying in search results" refers to a function or module that allows the generated testimonial to be displayed on a user's search results page.

[0915] A "means for analyzing user emotions" is a function for inferring emotions from a user's input or actions, and analyzing those emotions as numerical values ​​or categories.

[0916] The "means for adjusting the display order" is a function for changing the display order of the generated testimonials based on the analyzed user sentiment.

[0917] A system for carrying out the present invention has the following configuration: A server includes means for receiving information related to the content to be searched, means for automatically generating an introduction that does not include spoilers based on the received information, means for displaying the generated introduction in the search results, means for analyzing the user's emotions, and means for adjusting the display order of the introductions based on the analyzed emotions.

[0918] How to receive information

[0919] The server receives search queries entered by users through search engines or applications. For example, if a user searches for "game title," the server retrieves information about that game through the API. In this case, the server uses the requests library to gather data from external sources.

[0920] A method for automatically generating spoiler-free introductions

[0921] Based on the received information, the server uses a generative AI model to automatically generate an introductory text that does not contain spoilers. Specifically, the server uses the GPT-3 model with the transformers library to generate an introductory text by inputting the following prompt text:

[0922] Example prompt:

[0923] Game Title: Example Game

[0924] Genre: Action

[0925] Play Style: Single Player

[0926] overview:

[0927] How to appear in search results

[0928] The generated description is displayed by the server on the user's search result page, allowing the user to obtain basic information about the game, such as its genre and play style, without giving away any spoilers.

[0929] A means of analyzing user sentiment

[0930] The server analyzes the sentiment of users based on their input text and behavioral data, and uses the TextBlob library to quantify the sentiment from the user's text and classify it into categories such as positive, negative, and neutral.

[0931] Ways to adjust display order

[0932] Based on the analyzed user sentiment, the server adjusts the display order of the generated testimonials. For example, if the user has positive sentiment, the server displays the testimonials with positive content at the top, and if the user has negative sentiment, the server displays the testimonials with negative content at the bottom.

[0933] Examples

[0934] If a user searches for the game title "Example Game" and enters the text "I am so excited to play this game!", the server will detect the positive emotion and display the positive review text at the top, so that the user can get the information that best matches their emotion.

[0935] In this way, the present invention provides information about the content searched for by the user without spoilers, and further provides optimal information according to the user's emotions.

[0936] The flow of the specific process in the application example 2 will be described with reference to FIG.

[0937] Step 1:

[0938] The server receives the search query entered by the user. When a user searches for "game title", the query is sent to the server. The server takes this query as input and proceeds with the next step.

[0939] Step 2:

[0940] Based on the received search query, the server retrieves relevant content information from external sources. Specifically, it uses the requests library to send API requests to collect data about the game title, including the game genre, play style, basic information, etc. The retrieved data is used in the next step.

[0941] Step 3:

[0942] Based on the acquired content information, the server uses a generative AI model to automatically generate an introductory text that does not contain spoilers. Specifically, the server uses the transformers library to input a prompt text into the GPT-3 model to generate an introductory text. An example of a prompt text is in the following format:

[0943] Game Title: Example Game

[0944] Genre: Action

[0945] Play Style: Single Player

[0946] overview:

[0947] The generated testimonial is used in the next step.

[0948] Step 4:

[0949] The server analyzes the emotions based on the user's input text and behavioral data. It uses the TextBlob library to quantify the emotions from the user's text and classify them into categories such as positive, negative, neutral, etc. The analysis results are used in the next step.

[0950] Step 5:

[0951] The server adjusts the display order of the generated testimonials based on the analyzed user emotions. If positive emotions are detected, testimonials with positive content are displayed at the top, and if negative emotions are detected, testimonials with negative content are displayed at the bottom. This allows the server to provide optimal information according to the user's emotions.

[0952] Step 6:

[0953] The server displays the generated introductions based on the adjusted display order on the user's search result page, allowing the user to obtain the information that best suits their emotions while avoiding spoilers.

[0954] 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 a voice indicating a user input for the result of the specific processing. The control unit 46A transmits the voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0955] 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 making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[0956] Another example of generative AI is Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[0957] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0958] [Third embodiment]

[0959] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0960] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0961] 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 wide area network (WAN) and / or a local area network (LAN).

[0962] 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.

[0963] 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 the voice according to instructions from the processor 46.

[0964] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[0965] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[0966] Fig. 6 shows an example of 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.

[0967] 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.

[0968] 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.

[0969] In the headset type terminal 314, 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.

[0970] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[0971] "Example 1"

[0972] In one embodiment of the present invention, an Internet search tool is provided. When a user inputs a keyword related to a content to be searched, the search tool collects information related to the keyword. The collected information is sent to a spoiler-free introduction generation module. The module removes spoilers from the collected information and extracts a summary of the content. The extracted summary is formatted as an introduction and displayed to the user along with the search results.

[0973] "Example 2"

[0974] As a concrete example, consider the case where a user searches for "game title." The search tool collects information related to "game title" and sends it to a description generation module to prevent spoilers. This module excludes the game's ending and important plot points from the collected information and extracts an overview of the game, such as its genre and play style. The extracted overview is formatted as a description and displayed to the user along with the search results. This allows the user to understand the content of the game, but does not reveal any spoilers about the game's ending or important plot points.

[0975] The process flow of each embodiment will be described below.

[0976] "Example 1"

[0977] Step 1: User enters keywords into the search tool.

[0978] Step 2: The search tool gathers information from the Internet related to the keywords you entered.

[0979] Step 3: The collected information is sent to a spoiler-free introduction generation module. Step 4: The introduction generation module removes spoilers from the collected information and extracts a summary of the content.

[0980] Step 5: The extracted summary is formatted as a description and displayed to the user along with the search results.

[0981] "Example 2"

[0982] Step 1: User types "game title" into the search tool.

[0983] Step 2: The search tool collects information related to the "game title" from the Internet.

[0984] Step 3: The collected information is sent to a description generation module to prevent spoilers. Step 4: The description generation module extracts an overview of the game, such as its genre and play style, from the collected information, excluding the game's ending and important plot details.

[0985] Step 5: The extracted synopsis is formatted as a description and displayed to the user alongside the search results, allowing the user to understand the game's contents without spoiling the game's ending or important plot details.

[0986] Example 1

[0987] Next, a description will be given of Example 1 of the embodiment 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".

[0988] Conventional Internet search tools often display information containing spoilers when collecting information about the content a user searches for, which can ruin the user's experience. In addition, there was a lack of a way to properly format the collected information and display it in a way that is easy for users to understand.

[0989] 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.

[0990] In this invention, the server includes a means for receiving keywords related to the content to be searched, a means for collecting related information based on the received keywords, a means for transmitting the collected information to an introductory text generation module for preventing spoilers, a means for generating an introductory text that excludes spoilers using a generative AI model, a means for formatting the generated introductory text, and a means for displaying the formatted introductory text together with the search results, thereby enabling the user to check the outline of the content without including spoilers.

[0991] "Searchable content" is data about a particular subject or topic about which a user wants information.

[0992] A "keyword" is a word or phrase that a user enters to identify the content they are searching for.

[0993] "Related information" refers to data and materials related to keywords collected from search engines and databases.

[0994] "Introduction Generation Module" is a software component for analyzing collected related information and generating a spoiler-free summary of the content.

[0995] A "generative AI model" is an algorithm or system that uses artificial intelligence technology to generate appropriate text from input data.

[0996] A "formatter" is a process or tool used to convert the generated testimonial into a user-friendly form.

[0997] "Search results" are a list of related information displayed based on the keywords entered by the user.

[0998] "Display Means" means the method or technology used to display the formatted description and search results on the user's device.

[0999] The present invention is a system in which a user inputs a keyword for a content they wish to search, collects information related to the keyword, and generates an introduction to prevent spoilers. A specific embodiment of this system will be described below.

[1000] The server receives the keyword entered by the user. The user enters the keyword of the content he or she wants to search for in the search bar of the terminal. For example, the user enters "review of the latest movie 'Avengers'."

[1001] The terminal sends the entered keyword to the server, using the HTTPS protocol for this communication.

[1002] The server collects relevant information based on the received keywords. To do this, it uses search engine APIs such as Google Search API and Bing Search API. For example, it sends a query such as "Avengers movie reviews" to the search engine.

[1003] The server sends the collected information to an introductory text generation module, which analyzes the collected information and identifies parts that contain spoilers.

[1004] The introduction generation module uses a generative AI model to generate an introduction that excludes spoilers. Specifically, it uses a generative AI model such as OpenAI's GPT-4. The generative AI model takes the prompt as input and generates an appropriate introduction.

[1005] For example, the following sentence is input as a prompt into the generative AI model:

[1006] "Please give us your review of the latest movie, The Avengers, without any spoilers please."

[1007] The generated testimonial is then formatted by the server. Formatting is the process of converting the generated testimonial into a form that is easy for the user to read, i.e., converting it into a suitable format so that it is easy for the user to understand.

[1008] The server then sends the formatted introduction to the terminal, again using the HTTPS protocol.

[1009] The terminal displays the received introduction text to the user, allowing the user to check an outline of the content without including spoilers.

[1010] In this way, users can feel at ease knowing the outline of the content. This system provides an effective means of providing users with the necessary information while preventing spoilers.

[1011] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1012] Step 1:

[1013] The user enters search keywords.

[1014] The user inputs the keyword of the content they want to search for into the search bar of the device. For example, they input "Review of the latest movie 'Avengers'." The input keyword becomes the input data of the device.

[1015] Step 2:

[1016] The terminal transmits the entered keyword to the server.

[1017] The terminal sends the keyword entered by the user to the server. This communication uses the HTTPS protocol. The input is the keyword entered by the user, and the output is the keyword sent to the server.

[1018] Step 3:

[1019] The server collects information related to the keywords.

[1020] The server uses the Google Search API or Bing Search API to collect related information based on the received keywords. For example, a query such as "Avengers movie reviews" is sent to the search engine. The input is the keyword sent to the server, and the output is the collected related information.

[1021] Step 4:

[1022] The server sends the collected information to the testimonial generation module.

[1023] The server sends the collected information to the testimonial generation module, where the input is the collected relevant information and the output is the information sent to the testimonial generation module.

[1024] Step 5:

[1025] The introduction generation module generates an introduction that excludes spoilers.

[1026] The introduction generation module uses a generative AI model to generate an introduction that excludes spoilers from the collected information. Specifically, the prompt "Please give us a review of the latest movie, The Avengers, but without spoilers." is input to the generative AI model. The input is the information sent to the introduction generation module, and the output is the generated introduction.

[1027] Step 6:

[1028] The server formats the generated description.

[1029] The server formats the introduction received from the generative AI model. Formatting is the process of converting the generated introduction into a form that is easy for users to read, i.e., converting it into a proper format to make it easy for users to understand. The input is the generated introduction, and the output is the formatted introduction.

[1030] Step 7:

[1031] The server sends the formatted introduction to the terminal.

[1032] The server sends the formatted introduction to the terminal. This communication also uses the HTTPS protocol. The input is the formatted introduction, and the output is the introduction sent to the terminal.

[1033] Step 8:

[1034] The terminal displays the introductory text to the user.

[1035] The terminal displays the received introduction text to the user. The user can check the outline of the content without including spoilers. The input is the introduction text sent to the terminal, and the output is the introduction text displayed to the user.

[1036] (Application example 1)

[1037] 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".

[1038] Conventional Internet search tools often display information containing spoilers when collecting information about the content a user searches for, which can cause problems for the user's experience. In addition, it is difficult to efficiently collect information because it takes time to manually select information to avoid spoilers. Another issue is that the generated introduction text gets buried in the search results, making it difficult for users to quickly access the information they need.

[1039] 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.

[1040] In this invention, the server includes a means for receiving information about the content to be searched, a means for automatically generating an introduction that does not include spoilers based on the received information, a means for displaying the generated introduction in the search results, and a means for generating a prompt text using a generative AI model to generate an introduction that excludes spoilers. This allows the user to efficiently grasp the outline of the content while avoiding spoilers.

[1041] The "means for receiving information related to the content to be searched" refers to a device or program that has the function of collecting related information from the Internet based on keywords entered by the user.

[1042] The "means for automatically generating an introduction that does not include spoilers based on received information" refers to a device or program that has the function of excluding spoilers from collected information, extracting an outline of the content, and generating an introduction.

[1043] The "means for displaying the generated testimonial in the search results" refers to a device or program having a function of displaying the generated testimonial on the user's search result page.

[1044] "Means for generating a prompt sentence using a generative AI model and generating an introduction sentence that excludes spoilers" refers to a device or program that has the function of using a generative AI model to generate a prompt sentence for excluding spoilers from collected information, and generating an introduction sentence based on the prompt sentence.

[1045] A system for carrying out the present invention has the following configuration: A server includes means for receiving information related to the content to be searched, means for automatically generating an introductory text that does not include spoilers based on the received information, means for displaying the generated introductory text in the search results, and means for generating a prompt text using a generative AI model to generate an introductory text that excludes spoilers.

[1046] Hardware and Software Used

[1047] Hardware: Servers, user devices (smartphones, PCs, etc.)

[1048] Software: Python, BeautifulSoup, requests, OpenAI API

[1049] Data processing and calculation

[1050] 1. Data collection: Based on the keywords entered by the user's device, the server collects related information on the Internet. Specifically, it uses the requests library to obtain the search result page and parses it with BeautifulSoup.

[1051] 2. Spoiler removal and summary generation: The server inputs the collected information into OpenAI's generative AI model to generate a spoiler-free introduction. Specifically, it generates a prompt using the openai.Completion.create method and inputs it into the AI ​​model.

[1052] 3. Displaying the results: The server displays the generated synopsis on the user's search result page, allowing the user to efficiently get an overview of the content without spoiling it.

[1053] Examples

[1054] When a user searches for "popular movies," the server collects related information and generates and displays an introductory text that excludes spoilers. For example, by inputting the following prompt text into the generative AI model, an introductory text that does not include spoilers is generated.

[1055] Examples of prompt statements

[1056] Generate a content summary from the following information, excluding spoilers:

[1057] This movie is about the protagonist overcoming difficulties and growing as he goes on various adventures with his friends.

[1058] The story depicts the protagonist's growth as he comes to terms with his past.

[1059] The main characters include his best friend and mentor.

[1060] By inputting this prompt into a generative AI model, a spoiler-free introduction is generated and provided to the user.

[1061] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1062] Step 1:

[1063] The user inputs a search keyword from the terminal.

[1064] Input: The keyword for which the user wants to search for the content

[1065] Output: Search keywords sent to the server

[1066] Step 2:

[1067] The server collects relevant information on the Internet based on the search keywords.

[1068] Input: Search keyword

[1069] Output: A list of related information

[1070] What it does: The server uses the requests library to get the search results page, then parses it with BeautifulSoup to extract relevant information.

[1071] Step 3:

[1072] The server generates prompt sentences to input the collected information into the generative AI model.

[1073] Input: List of related information

[1074] Output: Prompt statement

[1075] Specific operation: The server generates a prompt text to filter out spoilers based on the collected information.

[1076] Step 4:

[1077] The server uses a generative AI model to generate a spoiler-free introduction based on the prompt text.

[1078] Input: Prompt statement

[1079] Output: Introduction without spoilers

[1080] Specific operation: The server uses the openai.Completion.create method to input the prompt text into the generation AI model and generate an introduction that excludes spoilers.

[1081] Step 5:

[1082] The server displays the generated testimonial on the user's search results page.

[1083] Input: Introduction without spoilers

[1084] Output: A description that will be displayed on the user's search results page.

[1085] Specific behavior: The server sets the generated testimonial to be displayed at the top of the search result page.

[1086] Example 2

[1087] Next, a second embodiment of the second form 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".

[1088] In conventional search systems, when users searched for information related to specific content, information containing spoilers was often displayed, which had the problem of ruining the user's experience. In addition, there was a lack of means to efficiently collect related information and generate appropriate introductions, making it difficult to quickly and accurately provide the information users were looking for.

[1089] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1090] In this invention, the server includes a means for receiving information about the content to be searched, a means for collecting related information based on the received information, a means for automatically generating an introductory text that does not include spoilers from the collected information, a means for formatting the generated introductory text, and a means for displaying the formatted introductory text in the search results. This makes it possible to quickly and accurately provide related information to the content searched for by the user while avoiding spoilers.

[1091] The "means for receiving information regarding the content being searched" refers to a function that allows the server to receive keywords or phrases that a user enters into the search bar.

[1092] "Means of collecting related information based on received information" refers to a function that uses search tools to collect related data from the Internet based on received keywords or phrases.

[1093] "Means for automatically generating a spoiler-free introduction from collected information" refers to a function that analyzes collected data, excludes important plot details and endings, and automatically creates a summary of the content using a generative AI model.

[1094] The "means for formatting the generated introduction" is a function for grammar checking and formatting the generated introduction to make it easier for the user to read.

[1095] The "means for displaying the formatted introduction in the search results" is a function for transmitting the formatted introduction to the user's terminal and displaying it on the search result page.

[1096] The present invention provides a system for automatically generating an introduction that does not include spoilers and displaying it in the search results when a user searches for information related to a particular piece of content. A specific embodiment of this system will be described below.

[1097] The server has a means for receiving keywords or phrases entered by a user into the search bar. When a user enters a "game title" into the search bar using a browser or a dedicated application on the terminal and clicks a search button, this search request is sent to the server.

[1098] Based on the received keywords or phrases, the server uses search tools such as Elasticsearch to gather relevant data from the Internet, including information from official game websites, review sites, forum posts, etc.

[1099] The collected information is then sent to a generative AI model, such as OpenAI’s GPT-4, using prompts to give the model specific instructions. For example, the following prompts can be used:

[1100] We have gathered information about the "Game Title". From this information, we would like you to generate a description that includes the game's genre, play style, and basic storyline, excluding the game's ending and important plot details.

[1101] The generative AI model analyzes the collected data, removes important plot details and endings, and automatically creates a summary of the content. The server checks the grammar and formats the summary to make it easier for users to read.

[1102] The formatted description is sent from the server to the user's device and displayed on the search results page, allowing the user to understand the general outline of the game, but without spoiling the ending or important plot details.

[1103] As a concrete example, consider the case where a user searches for "Final Fantasy VII." The server uses Elasticsearch to collect information related to "Final Fantasy VII" from the Internet. It then sends the collected information to GPT-4, which generates a description using the following prompt:

[1104] You have gathered information about "Final Fantasy VII." From this information, generate a description that includes the game's genre, play style, and basic storyline, excluding the game's ending and key plot details.

[1105] An example of a generated introduction might look like this:

[1106] "Final Fantasy VII" is a role-playing game. Players control characters and fight against giant corporations with rebel groups. The game employs a turn-based battle system and features a wide range of character development elements.

[1107] This description will be displayed on the user's device along with the search results.

[1108] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1109] Step 1:

[1110] A user enters keywords into the search bar and clicks the search button.

[1111] Input: The keyword entered by the user (e.g. "game title")

[1112] Output: A search request is sent to the server.

[1113] Specific operation: The user enters the "game title" in the search bar using the device's browser or a dedicated application, and clicks the search button. This action sends a search request to the server.

[1114] Step 2:

[1115] A server receives the search request and collects the relevant information.

[1116] Input: Search request (keywords entered by the user)

[1117] Output: Related information (e.g. official website, review sites, forum posts)

[1118] Specific operation: Based on the received search request, the server uses search tools such as Elasticsearch to collect information related to the "game title" from the Internet. Specifically, it obtains data from the game's official website, review sites, forum posts, etc.

[1119] Step 3:

[1120] The server sends the collected information to a generative AI model to generate a testimonial.

[1121] Input: Information collected (e.g. official sites, review sites, forum posts)

[1122] Output: Generated introduction (no spoilers)

[1123] Specific operation: The server sends the collected information to a generative AI model such as OpenAI's GPT-4. At this time, it uses a prompt to give specific instructions to the generative AI model. For example, the following prompt can be used:

[1124] We have gathered information about the "Game Title". From this information, we would like you to generate a description that includes the game's genre, play style, and basic storyline, excluding the game's ending and important plot details.

[1125] Step 4:

[1126] The server formats the generated description.

[1127] Input: Generated introductory text (no spoilers)

[1128] Output: A formatted introduction (grammar checked and formatted)

[1129] How it works: The server receives the introduction returned by the generative AI model and performs grammar checks and formatting adjustments to make it easier for users to read.

[1130] Step 5:

[1131] The server sends the formatted introduction to the user's terminal and displays it.

[1132] Input: Formatted introduction (grammar checked and formatted)

[1133] Output: The introductory text that is displayed to the user.

[1134] Specific operation: The server sends the formatted introductory text to the user's device. The user's device displays the received introductory text on the browser or application screen. This allows the user to understand the outline of the game, but does not reveal any spoilers about the ending or important plot points.

[1135] (Application example 2)

[1136] 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".

[1137] In conventional search systems, when users searched for information about content, information containing spoilers was often displayed, which led to problems that marred the user experience. In addition, the generated introduction text was sometimes not displayed properly in the search results, which meant that users could not quickly access the information they needed. Furthermore, there were problems with the quality of the introduction text and the speed of generation because the introduction text was not generated efficiently using a generative AI model.

[1138] 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.

[1139] In this invention, the server includes a means for receiving information about the content to be searched, a means for automatically generating an introduction that does not include spoilers based on the received information, a means for displaying the generated introduction in the search results, a means for generating the introduction using a generative AI model, and a means for receiving a prompt as an input. This allows the user to quickly obtain summary information about the required content while avoiding spoilers.

[1140] "Searchable content" refers to media works such as movies, dramas, anime, and games about which users want to obtain information.

[1141] The "means for receiving information" is a part of the system that has the function of collecting relevant data based on the search query entered by the user.

[1142] A "spoiler-free introduction" is a piece of text that provides basic information such as an overview, genre, and play style, excluding the ending or important plot details of the content.

[1143] An "automated generation means" is a part of a system that has the function of generating a testimonial based on the information received, using a specific algorithm or model.

[1144] "Means for displaying the generated testimonial in a search result" means a portion of the system that has functionality for appropriately placing and displaying the generated testimonial on a user's search result page.

[1145] A "generative AI model" is a trained model that uses artificial intelligence technology to generate appropriate introductions from input data.

[1146] A "prompt sentence" is text data input to a generative AI model, and is a sentence that contains instructions and conditions for the model to generate an appropriate output.

[1147] In order to implement this invention, the server, the terminal, and the user must each fulfill a specific role.

[1148] First, a user uses a terminal to input information about the content to be searched. The terminal can be a device such as a smartphone or a PC, and must be connected to the Internet. Once the user enters a search query, the terminal transmits the information to a server.

[1149] The server collects relevant information based on the received search query. Specifically, the server uses APIs to retrieve information about content from external databases and websites, including content overview, genre, play style, etc.

[1150] Next, the server uses a generative AI model to automatically generate a spoiler-free introductory text from the collected information. The generative AI model is a pre-trained natural language processing model that has the ability to generate an appropriate introductory text from the input information. The prompt text is text data input to the generative AI model, and includes instructions and conditions for the model to generate an appropriate output.

[1151] The generated introduction is sent from the server to the terminal and displayed on the terminal screen, allowing the user to quickly obtain an overview of the desired content while avoiding spoilers.

[1152] As a concrete example, consider the case where a user searches for the movie "Inception." When the user types "Inception" into the device, the device sends the information to the server. The server collects related information and uses a generative AI model to generate a description like this:

[1153] "Inception is a science fiction film with a complex plot involving dreams within dreams. The protagonist is a professional information stealer in dreams, and his latest mission is..."

[1154] This synopsis is displayed on the terminal screen, allowing the user to understand the outline of the movie.

[1155] Examples of prompts include:

[1156] "What kind of movie is Inception?"

[1157] In this way, the user can quickly obtain the necessary information while avoiding spoilers.

[1158] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1159] Step 1:

[1160] A user uses a terminal to enter a search query.

[1161] Input: The user enters the content they are searching for (e.g., "Inception").

[1162] Output: The device sends the search query to the server.

[1163] Specific actions: The user types "Inception" into the search bar on their smartphone or computer and presses the search button.

[1164] Step 2:

[1165] A server receives the search query and collects related information.

[1166] Input: The search query sent from the device (e.g. "Inception").

[1167] Output: Content information collected by the server from external databases and websites.

[1168] What happens: The server uses an API to retrieve information about "Inception" (such as summary, genre, play style, etc.) from movie databases and review sites.

[1169] Step 3:

[1170] Based on the information collected by the server, a generative AI model is used to generate an introduction that does not contain spoilers.

[1171] Input: Collected content information (e.g., summary of "Inception", genre, play style).

[1172] Output: A spoiler-free introduction generated by the generative AI model.

[1173] Specific operation: The server inputs the collected information into a generative AI model and generates a spoiler-free introduction using a prompt sentence (e.g., "What kind of movie is Inception?").

[1174] Step 4:

[1175] The server transmits the generated introduction to the terminal.

[1176] Input: An introductory text generated by a generative AI model.

[1177] Output: The introductory text sent to the terminal.

[1178] Specific operation: The server sends the generated introduction to the terminal and displays it on the user's search result page.

[1179] Step 5:

[1180] The terminal displays the received introduction to the user.

[1181] Input: The introduction sent by the server.

[1182] Output: The introductory text displayed on the user's device screen.

[1183] Specific operation: The device displays the received introduction at the top of the search result page and the user views it.

[1184] In addition, 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.

[1185] "Example 1"

[1186] As one embodiment of the present invention, a system incorporating an emotion engine is provided. The system recognizes a user's emotion and automatically generates an introductory text based on the emotion. Specifically, behavioral data such as a user's search history and browsing history is analyzed, and the user's emotion is estimated from the data. The estimated emotion is used to generate an introductory text. For example, if a user expresses an emotion of joy, an introductory text is generated for content that is likely to make the user happy. Also, if a user expresses an emotion of anger, an introductory text is not generated for content that is likely to make the user angry.

[1187] "Example 2"

[1188] As another embodiment of the present invention, an adjustment of the display order of introductions using an emotion engine is provided. Specifically, the display order of introductions is adjusted according to the emotion of the user. For example, when a user expresses an emotion of joy, introductions related to content that may make the user happy are displayed at the top of the search results. Also, when a user expresses an emotion of anger, introductions related to content that may make the user angry are displayed at the bottom of the search results. This makes it possible to provide optimal search results according to the emotion of the user.

[1189] The process flow of each embodiment will be described below.

[1190] "Example 1"

[1191] Step 1: Collect user behavioral data (e.g. search history, browsing history).

[1192] Step 2: Input the collected behavioral data into the emotion engine to estimate the user's emotions. Step 3: Automatically generate an introduction based on the estimated emotions.

[1193] Step 4: Display the generated testimonial to the user.

[1194] "Example 2"

[1195] Step 1: Collect user behavioral data (e.g. search history, browsing history).

[1196] Step 2: Input the collected behavioral data into the emotion engine to estimate the user's emotion. Step 3: Adjust the display order of the testimonials based on the estimated emotion.

[1197] Step 4: Display the testimonials to the user according to the adjusted display order.

[1198] Example 1

[1199] Next, a description will be given of Example 1 of the embodiment 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".

[1200] In conventional Internet search tools, when collecting information about the content searched by the user, information containing spoilers may be displayed, which may spoil the user's experience. In addition, since it is not possible to provide an appropriate introduction according to the user's emotions, it is difficult to improve user satisfaction. Furthermore, since the search results are not customized based on the user's emotions, it is difficult for the user to quickly access the information he or she is looking for.

[1201] 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.

[1202] In this invention, the server includes a means for receiving information about the content to be searched, a means for automatically generating an introduction that does not include spoilers based on the received information, a means for displaying the generated introduction in the search results, a means for collecting user behavior data, a means for estimating the user's emotions based on the collected behavior data, and a means for generating an introduction based on the estimated emotions. This makes it possible for a user to be provided with an appropriate introduction that corresponds to the emotions while avoiding spoilers.

[1203] The "means for receiving information related to the search target content" refers to a device or program having a function of collecting related information from the Internet based on keywords entered by the user.

[1204] The "means for automatically generating an introduction that does not include spoilers" refers to a device or program having a function of excluding spoilers from collected information, extracting an outline of the content, and generating an introduction.

[1205] The "means for displaying the generated introduction text in the search results" refers to a device or program having a function for displaying the generated introduction text on the user's terminal.

[1206] The "means for collecting user behavioral data" refers to a device or program that has the function of collecting user behavioral data such as search history and browsing history.

[1207] The "means for inferring a user's emotions based on collected behavioral data" refers to a device or program having a function of analyzing collected behavioral data and inferring a user's emotions.

[1208] The "means for generating an introductory text based on an estimated emotion" refers to a device or a program having a function of automatically generating an introductory text appropriate to the emotion based on the estimated emotion of the user.

[1209] This invention is a system that, when a user inputs a keyword for the content they want to search for, collects information related to the keyword, generates and displays an introductory text that does not include spoilers, and also has the function of collecting user behavior data, estimating the user's emotions based on the data, and generating an introductory text according to the emotions.

[1210] Hardware and Software Used

[1211] 1. Server:

[1212] Search engine API: Used to collect information from the Internet. Specifically, Google Search API and Bing Search API are used.

[1213] Natural Language Processing library: Used to filter out spoilers and extract content summaries from collected information. Specifically, it uses the Hugging Face Transformers library and leverages a pre-trained BERT model.

[1214] Text summarization algorithms: used to extract an overview of the content. In particular, we use the Sumy library.

[1215] Sentiment Analysis API: Used to estimate emotions based on user behavior data. Specifically, it uses Google Cloud Natural Language API.

[1216] 2. Terminal:

[1217] Browser: Used by users to enter keywords and check search results. Specifically, common web browsers such as Google Chrome and Mozilla Firefox are used.

[1218] 3. User:

[1219] Input device: Used to input keywords, specifically using a keyboard or touch screen.

[1220] Explanation of program processing

[1221] 1. User enters a keyword:

[1222] A user opens a browser on their device, accesses the search tool interface, enters a keyword such as "Inception" in the search bar, and clicks the search button.

[1223] 2. The server collects information:

[1224] The server receives the keywords entered by the user and uses the Google Search API or Bing Search API to collect related information from the Internet. For example, it calls the Google Search API to get a list of web pages related to "Inception."

[1225] 3. The server filters out spoilers:

[1226] The collected information is sent to the introductory text generation module in the server, which uses a pre-trained BERT model using Hugging Face's Transformers library to detect and remove spoilers from the collected text, for example removing sentences containing keywords such as "ending" or "culprit."

[1227] 4. Server extracts summary:

[1228] After filtering out spoilers, the server uses the Sumy library to summarize the text and extract an overview of the content, for example generating a short summary that includes key plot and character introductions for a movie.

[1229] 5. The server formats the description:

[1230] The extracted summary is formatted in Markdown or HTML, for example by displaying the movie title as a heading and a summary in paragraph format below it.

[1231] 6. The server displays the search results:

[1232] The formatted description is displayed in the user's browser as a search result page, and the user can view the results through their device's browser.

[1233] Examples and prompts

[1234] Examples

[1235] If a user searches for a movie title:

[1236] When a user enters the keyword "Inception", the server uses the Google Search API to collect information about "Inception". It excludes spoilers from the collected information, extracts a summary of the movie using the Sumy library, and generates a summary. If the user indicates the emotion of joy, a summary that highlights the positive aspects of the movie is displayed.

[1237] Examples of prompt statements

[1238] Prompt for generative AI model:

[1239] "A user has searched for the keyword "Inception". Extract a synopsis of the movie from the collected information, excluding spoilers. The user is currently expressing the emotion of joy. Generate a description that highlights the positive aspects."

[1240] In this way, the present invention is a system that provides appropriate information based on the user's input and emotions.

[1241] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1242] Step 1:

[1243] The user enters a keyword

[1244] A user opens a browser on their device, accesses the search tool interface, enters a keyword such as "Inception" in the search bar, and clicks the search button.

[1245] Input: The keyword entered by the user

[1246] Output: The keyword is sent to the server.

[1247] Step 2:

[1248] The server collects information

[1249] Based on the received keywords, the server calls a search engine API (e.g., Google Search API or Bing Search API) to collect related information.

[1250] Input: The keyword entered by the user

[1251] Output: Relevant information retrieved from the search engine API

[1252] Step 3:

[1253] Server filters out spoilers

[1254] The collected information is sent to a testimonial generation module in the server, which uses a natural language processing library (e.g., Hugging Face's Transformers library) to leverage a pre-trained model (e.g., the BERT model) to detect and filter out spoilers from the collected text.

[1255] Input: Related information obtained from search engine API

[1256] Output: Information without spoilers

[1257] Step 4:

[1258] The server extracts the summary

[1259] The spoiler-free information is then summarized using a text summarization algorithm (e.g., the Sumy library) to extract an overview of the content.

[1260] Input: Information without spoilers

[1261] Output: A summary of the extracted content

[1262] Step 5:

[1263] The server formats the introduction

[1264] The extracted summary is formatted in Markdown or HTML, for example by displaying the movie title as a heading and a summary in paragraph format below it.

[1265] Input: A summary of the extracted content

[1266] Output: A formatted introduction

[1267] Step 6:

[1268] The server displays the search results.

[1269] The formatted description is displayed in the user's browser as a search result page, and the user can view the results through their device's browser.

[1270] Input: Formatted description

[1271] Output: The search results displayed in the user's browser.

[1272] Step 7:

[1273] The server collects user behavior data

[1274] The server collects user behavioral data, such as search history and browsing history, using browser cookies and local storage.

[1275] Input: User search and browsing history

[1276] Output: Collected behavioral data

[1277] Step 8:

[1278] The server estimates the emotion

[1279] Analyze the collected behavioral data and infer user emotions using a sentiment analysis API (e.g., Google Cloud Natural Language API).

[1280] Input: Collected behavioral data

[1281] Output: Estimated user emotion

[1282] Step 9:

[1283] The server generates the introduction

[1284] Based on the estimated emotion, a generative AI model is used to input a prompt sentence and automatically generate an introduction that matches the emotion.

[1285] Input: Estimated user emotion

[1286] Output: An emotionally appropriate introduction

[1287] Step 10:

[1288] The server displays the introductory text.

[1289] The generated introduction is displayed on the user's browser, allowing the user to check the results through their device and enjoy content that matches their emotions.

[1290] Input: An emotionally appropriate introduction

[1291] Output: The introductory text displayed in the user's browser.

[1292] (Application example 1)

[1293] 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".

[1294] In conventional Internet search tools, when collecting information about the content a user searches for, information containing spoilers may be displayed, which may ruin the user's experience. In addition, since content is not introduced according to the user's emotions, it is difficult to increase user satisfaction.

[1295] 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.

[1296] In this invention, the server includes a means for receiving information about the content to be searched, a means for automatically generating an introduction that does not include spoilers based on the received information, a means for recognizing a user's emotions and customizing the introduction based on the emotions, and a means for displaying the generated introduction in the search results. This makes it possible to introduce content according to the user's emotions while preventing spoilers.

[1297] The "means for receiving information related to the search target content" is a function for collecting information on related content based on keywords entered by the user.

[1298] The "means for automatically generating an introduction that does not include spoilers based on the received information" is a function for excluding spoilers from the collected content information and generating an introduction that is suitable for the user.

[1299] "Means of recognizing user emotions and customizing the introductory text based on those emotions" refers to a function that analyzes a user's search history and behavioral data to infer emotions and adjust the introductory text according to those emotions.

[1300] "Means for displaying the generated testimonial in the search results" refers to a function for displaying the generated testimonial on the user's search result page.

[1301] A system for implementing the present invention includes a server, a user terminal, and a generative AI model. A specific embodiment of the system will be described below.

[1302] System Configuration

[1303] 1. Server:

[1304] The server receives search keywords from the user.

[1305] The server collects related content information based on the received keywords.

[1306] The server removes spoilers from the collected information and generates an introduction.

[1307] The server recognizes the user's emotions and customizes the testimonials based on the emotions.

[1308] The server transmits the generated introduction to the user terminal.

[1309] 2. User device:

[1310] The user terminal provides an interface for the user to input search keywords.

[1311] The user terminal displays the introduction sent from the server.

[1312] 3. Generative AI model:

[1313] The generative AI model analyzes users' search history and behavioral data to infer their emotions.

[1314] A generative AI model customizes testimonials based on sentiment.

[1315] Program Processing

[1316] When the server receives the search keyword entered by the user, it collects related content information. This information can be collected from external APIs or databases. The collected information is filtered to prevent spoilers and then sent to the introduction generation module.

[1317] The introduction generation module extracts an overview of the content from the collected information, excluding spoilers. Based on this overview, an introduction suitable for the user is generated. Next, the emotion engine analyzes the user's search history and behavioral data to estimate the user's emotions. Based on this emotion information, the introduction is customized.

[1318] For example, if the user feels like relaxing, an introductory text for relaxing content is generated. The generated introductory text is transmitted from the server to the user terminal and displayed on the user's search result page.

[1319] Examples

[1320] If a user searches for "relaxing movies", the following prompt might be generated:

[1321] Example prompt:

[1322] User's recent behavior data: "Recent searches: 'stress relief', 'relaxing music', 'yoga videos'"

[1323] When this prompt is fed into a sentiment analysis model, the user's sentiment is estimated to be "positive," and a description of a relaxing movie is generated based on this.

[1324] The above is a specific embodiment for carrying out the present invention. This system makes it possible to introduce content according to the user's emotions while preventing spoilers.

[1325] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1326] Step 1:

[1327] A user inputs a search keyword into a terminal. The terminal sends the keyword to a server. The input is the user's search keyword, and the output is a search request sent to the server.

[1328] Step 2:

[1329] The server collects relevant content information based on the received search keywords. This information collection is done using external APIs and databases. The input is the search keywords, and the output is the collected content information.

[1330] Step 3:

[1331] The server performs filtering to remove spoilers from the collected content information. Specifically, it removes specific keywords and phrases. The input is the collected content information, and the output is the content information with spoilers removed.

[1332] Step 4:

[1333] The server extracts a summary of the content from the spoiler-free content information. It generates an introduction based on the extracted summary. The input is the spoiler-free content information, and the output is the generated introduction.

[1334] Step 5:

[1335] The server analyzes the user's search history and behavioral data to estimate the user's emotions. A generative AI model is used for this analysis. The input is the user's search history and behavioral data, and the output is the estimated user's emotions.

[1336] Step 6:

[1337] The server customizes the introduction based on the estimated user's emotion. For example, if the user feels like relaxing, the server generates an introduction for relaxing content. The input is the estimated user's emotion and the generated introduction, and the output is the customized introduction.

[1338] Step 7:

[1339] The server sends the customized introduction to the user terminal, where the input is the customized introduction and the output is the introduction sent to the user terminal.

[1340] Step 8:

[1341] The user terminal displays the introduction text sent from the server on the search result page. The input is the introduction text sent from the server, and the output is the introduction text displayed to the user.

[1342] Example 2

[1343] Next, a second embodiment of the second form 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".

[1344] In conventional search systems, when a user searches for information about a particular piece of content, information containing spoilers may be displayed, which may ruin the user's experience. There is also the problem that it is difficult to provide optimal search results according to the user's emotions. To solve these problems, a system is needed that generates introductions that do not include spoilers and adjusts the display order of search results based on the user's emotions.

[1345] 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 receiving information about the data to be searched, a means for automatically generating an introduction text that does not include spoilers based on the received information, a means for displaying the generated introduction text in the search results, a means for analyzing the user's emotions, and a means for adjusting the display order of the introduction text based on the analyzed emotions. This allows the user to obtain optimal search results according to their emotions while avoiding spoilers.

[1346] "Searchable data" refers to the specific information or content for which a user is searching.

[1347] "Means for receiving information" means a device or software that has the function of receiving a search query from a user and collecting related information based on the query.

[1348] A "spoiler-free introduction" is a piece of text that provides users with basic information such as an overview, genre, and play style, without including the ending or important plot details of the content.

[1349] An "automated generation means" is a device or software that has the capability to automatically generate a testimonial based on the information it receives using a particular algorithm or generative AI model.

[1350] "Means for displaying in the search results" refers to a device or software that has the function of displaying the generated introduction on the user's terminal.

[1351] "Means for analyzing user emotions" refers to devices or software that have the function of analyzing the user's emotional state based on data such as facial expressions and voice.

[1352] A "means for adjusting the display order" refers to a device or software that has the function of optimizing the display order of search results based on the analyzed user sentiment.

[1353] This invention is a system that generates an introduction that does not include spoilers when a user searches for information about a specific data item, and adjusts the display order of search results based on the user's feelings. This system works in cooperation with a server, a terminal, and a user.

[1354] First, a user uses a device to search for specific data. For example, a user opens a browser on a smartphone, enters "a specific game title" in the search bar, and presses the search button. This action sends a search query from the device to the server.

[1355] Based on the received search query, the server collects relevant information from the Internet using existing search engine APIs such as Google API or Bing API. The server sends an API request and analyzes the returned search results to extract the required information.

[1356] The collected information is sent to an introductory text generation module in the server. This module processes the information using a generative AI model (e.g., OpenAI's GPT-4). The server converts the collected information into an appropriate format and inputs it into the generative AI model. As an example of a specific prompt, we use the sentence, "Please generate an introductory text for a specific game title, but please do not include the game's ending or important plot."

[1357] The introduction generation module extracts an overview of the game, such as the game's genre and play style, from the collected information, excluding the game's ending and important plot details. Based on this prompt, the generative AI model generates an appropriate introduction.

[1358] The extracted summary is then formatted into an introduction by the server, which formats the resulting text in a way that is easy for the user to understand, and adds additional information and links as needed.

[1359] The formatted description is then displayed on the user's device alongside the search results. For example, when a user opens the search results page, they are presented with information about the game's overview, genre, and play style. This information is careful not to include the game's ending or important plot details.

[1360] In addition, the server uses an emotion engine to adjust the display order of the introductions. The user's emotions are analyzed based on data collected through the device's camera and microphone. For example, if the user expresses happiness during a search, the server uses the emotion engine to display introductions related to content that the user is likely to feel happy at the top of the search results. On the other hand, if the user expresses anger, the server displays introductions related to content that the user is likely to feel angry at the bottom of the search results.

[1361] In this way, users can avoid spoilers and get the best search results based on their emotions.

[1362] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1363] Step 1:

[1364] A user uses a device to search for specific data. The user opens a browser on his / her smartphone, enters "a specific game title" in the search bar, and presses the search button. This action causes a search query to be sent from the device to the server. The input is the user's search query, and the output is the query sent to the server.

[1365] Step 2:

[1366] Based on the search query received by the server, related information is collected from the Internet using existing search engine APIs such as Google API or Bing API. The server sends an API request and analyzes the returned search results to extract the required information. The input is the search query, and the output is the collected related information.

[1367] Step 3:

[1368] The server sends the collected information to the introduction generation module, which processes the information using a generative AI model (e.g., OpenAI's GPT-4). The server converts the collected information into an appropriate format and inputs it into the generative AI model. The input is the collected information, and the output is the input data to the generative AI model.

[1369] Step 4:

[1370] The introduction generation module excludes the game's ending and important plot from the collected information and extracts an overview of the game's genre, play style, etc. An example of a specific prompt is "Generate an introduction for a specific game title, but do not include the game's ending or important plot." The input is the prompt to the generative AI model and the collected information, and the output is an introduction that does not contain spoilers.

[1371] Step 5:

[1372] The server formats the extracted summary into a blurb. The server formats the generated text in a way that is easy for the user to understand, and adds additional information and links as needed. The input is the generated blurb, and the output is the formatted blurb.

[1373] Step 6:

[1374] The server displays the formatted description along with the search results on the user's device. When the user visits the search results page, they are presented with information about the game's synopsis, genre, and play style. This information is careful not to include the game's ending or important plot details. The input is the formatted description and the search results, and the output is the information displayed on the user's device.

[1375] Step 7:

[1376] The server adjusts the display order of the introductions using the emotion engine. The user's emotions are analyzed based on data collected through the device's camera and microphone. For example, if the user shows an emotion of happiness during a search, the server uses the emotion engine to display introductions about content that the user is likely to feel happy at the top of the search results. Also, if the user shows an emotion of anger, the server displays introductions about content that the user is likely to feel angry at the bottom of the search results. The input is the user's emotion data, and the output is the adjusted display order of the search results.

[1377] (Application example 2)

[1378] 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".

[1379] In conventional search systems, when providing information about the content searched by the user, information containing spoilers may be displayed, which may ruin the user's experience. In addition, since the information provided does not correspond to the user's emotions, it is difficult to increase user satisfaction. Furthermore, since the display order of search results is not adjusted based on the user's emotions, there is also the problem that the information provided is not optimal for the user.

[1380] 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.

[1381] In this invention, the server includes a means for receiving information about the content to be searched, a means for automatically generating an introduction that does not include spoilers based on the received information, a means for displaying the generated introduction in the search results, a means for analyzing the user's emotions, and a means for adjusting the display order of the introductions based on the analyzed emotions. This makes it possible to provide information about the content searched for by the user without spoilers, and further provide optimal information according to the user's emotions.

[1382] "Searchable content" is the specific digital content about which a user seeks to obtain information through a search engine or application.

[1383] "Means for receiving information" refers to functions or modules for obtaining data regarding the content searched by the user.

[1384] A "spoiler-free description" is a description that includes only basic information such as an overview, genre, and play style, excluding the ending of the content or important plot details.

[1385] "Automatic generation means" refers to a function that automatically creates an introduction based on received information using a specific algorithm or model.

[1386] "Means for displaying in search results" refers to a function or module that allows the generated testimonial to be displayed on a user's search results page.

[1387] A "means for analyzing user emotions" is a function for inferring emotions from a user's input or actions, and analyzing those emotions as numerical values ​​or categories.

[1388] The "means for adjusting the display order" is a function for changing the display order of the generated testimonials based on the analyzed user sentiment.

[1389] A system for carrying out the present invention has the following configuration: A server includes means for receiving information related to the content to be searched, means for automatically generating an introduction that does not include spoilers based on the received information, means for displaying the generated introduction in the search results, means for analyzing the user's emotions, and means for adjusting the display order of the introductions based on the analyzed emotions.

[1390] How to receive information

[1391] The server receives search queries entered by users through search engines or applications. For example, if a user searches for "game title," the server retrieves information about that game through the API. In this case, the server uses the requests library to gather data from external sources.

[1392] A method for automatically generating spoiler-free introductions

[1393] Based on the received information, the server uses a generative AI model to automatically generate an introductory text that does not contain spoilers. Specifically, the server uses the GPT-3 model with the transformers library to generate an introductory text by inputting the following prompt text:

[1394] Example prompt:

[1395] Game Title: Example Game

[1396] Genre: Action

[1397] Play Style: Single Player

[1398] overview:

[1399] How to appear in search results

[1400] The generated description is displayed by the server on the user's search result page, allowing the user to obtain basic information about the game, such as its genre and play style, without giving away any spoilers.

[1401] A means of analyzing user sentiment

[1402] The server analyzes the sentiment of users based on their input text and behavioral data, and uses the TextBlob library to quantify the sentiment from the user's text and classify it into categories such as positive, negative, and neutral.

[1403] Ways to adjust display order

[1404] Based on the analyzed user sentiment, the server adjusts the display order of the generated testimonials. For example, if the user has positive sentiment, the server displays the testimonials with positive content at the top, and if the user has negative sentiment, the server displays the testimonials with negative content at the bottom.

[1405] Examples

[1406] If a user searches for the game title "Example Game" and enters the text "I am so excited to play this game!", the server will detect the positive emotion and display the positive review text at the top, so that the user can get the information that best matches their emotion.

[1407] In this way, the present invention provides information about the content searched for by the user without spoilers, and further provides optimal information according to the user's emotions.

[1408] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1409] Step 1:

[1410] The server receives the search query entered by the user. When a user searches for "game title", the query is sent to the server. The server takes this query as input and proceeds with the next step.

[1411] Step 2:

[1412] Based on the received search query, the server retrieves relevant content information from external sources. Specifically, it uses the requests library to send API requests to collect data about the game title, including the game genre, play style, basic information, etc. The retrieved data is used in the next step.

[1413] Step 3:

[1414] Based on the acquired content information, the server uses a generative AI model to automatically generate an introductory text that does not contain spoilers. Specifically, the server uses the transformers library to input a prompt text into the GPT-3 model to generate an introductory text. An example of a prompt text is in the following format:

[1415] Game Title: Example Game

[1416] Genre: Action

[1417] Play Style: Single Player

[1418] overview:

[1419] The generated testimonial is used in the next step.

[1420] Step 4:

[1421] The server analyzes the emotions based on the user's input text and behavioral data. It uses the TextBlob library to quantify the emotions from the user's text and classify them into categories such as positive, negative, neutral, etc. The analysis results are used in the next step.

[1422] Step 5:

[1423] The server adjusts the display order of the generated testimonials based on the analyzed user emotions. If positive emotions are detected, testimonials with positive content are displayed at the top, and if negative emotions are detected, testimonials with negative content are displayed at the bottom. This allows the server to provide optimal information according to the user's emotions.

[1424] Step 6:

[1425] The server displays the generated introductions based on the adjusted display order on the user's search result page, allowing the user to obtain the information that best suits their emotions while avoiding spoilers.

[1426] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input for the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1427] 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 making a neural network perform deep learning. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating a voice, text data indicating a text, and image data indicating an image is input. The data generation model 58 performs inference on the input inference data according to 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.

[1428] Another example of generative AI is Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) are mentioned.

[1429] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1430] [Fourth embodiment]

[1431] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1432] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1433] 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 wide area network (WAN) and / or a local area network (LAN).

[1434] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. In addition, the microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1435] 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 the voice according to instructions from the processor 46.

[1436] Camera 42 is a small digital camera equipped with an optical system including a lens, an aperture, and a 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 (e.g., an imaging range defined by an angle of view equivalent to the width of the field of vision of an average healthy person).

[1437] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for transmitting and receiving various types of information between the processor 46 and the processor 28 via the network 54. The transmission and reception of various types of information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is performed in a secure state.

[1438] The control target 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, legs, etc. The posture and behavior of the robot 414 are controlled by controlling the motors of the arms, hands, legs, etc. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1439] Fig. 8 shows an example of main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1440] 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.

[1441] 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.

[1442] In the robot 414, 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.

[1443] Next, the specific processing by the specific processing unit 290 of the data processing device 12 will be described.

[1444] "Example 1"

[1445] In one embodiment of the present invention, an Internet search tool is provided. When a user inputs a keyword related to a content to be searched, the search tool collects information related to the keyword. The collected information is sent to a spoiler-free introduction generation module. The module removes spoilers from the collected information and extracts a summary of the content. The extracted summary is formatted as an introduction and displayed to the user along with the search results.

[1446] "Example 2"

[1447] As a concrete example, consider the case where a user searches for "game title." The search tool collects information related to "game title" and sends it to a description generation module to prevent spoilers. This module excludes the game's ending and important plot points from the collected information and extracts an overview of the game, such as its genre and play style. The extracted overview is formatted as a description and displayed to the user along with the search results. This allows the user to understand the content of the game, but does not reveal any spoilers about the game's ending or important plot points.

[1448] The process flow of each embodiment will be described below.

[1449] "Example 1"

[1450] Step 1: User enters keywords into the search tool.

[1451] Step 2: The search tool gathers information from the Internet related to the keywords you entered.

[1452] Step 3: The collected information is sent to a spoiler-free introduction generation module. Step 4: The introduction generation module removes spoilers from the collected information and extracts a summary of the content.

[1453] Step 5: The extracted summary is formatted as a description and displayed to the user along with the search results.

[1454] "Example 2"

[1455] Step 1: User types "game title" into the search tool.

[1456] Step 2: The search tool collects information related to the "game title" from the Internet.

[1457] Step 3: The collected information is sent to a description generation module to prevent spoilers. Step 4: The description generation module extracts an overview of the game, such as its genre and play style, from the collected information, excluding the game's ending and important plot details.

[1458] Step 5: The extracted synopsis is formatted as a description and displayed to the user alongside the search results, allowing the user to understand the game's contents without spoiling the game's ending or important plot details.

[1459] Example 1

[1460] Next, a description will be given of Example 1 of the embodiment 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal".

[1461] Conventional Internet search tools often display information containing spoilers when collecting information about the content a user searches for, which can ruin the user's experience. In addition, there was a lack of a way to properly format the collected information and display it in a way that is easy for users to understand.

[1462] 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.

[1463] In this invention, the server includes a means for receiving keywords related to the content to be searched, a means for collecting related information based on the received keywords, a means for transmitting the collected information to an introductory text generation module for preventing spoilers, a means for generating an introductory text that excludes spoilers using a generative AI model, a means for formatting the generated introductory text, and a means for displaying the formatted introductory text together with the search results, thereby enabling the user to check the outline of the content without including spoilers.

[1464] "Searchable content" is data about a particular subject or topic about which a user wants information.

[1465] A "keyword" is a word or phrase that a user enters to identify the content they are searching for.

[1466] "Related information" refers to data and materials related to keywords collected from search engines and databases.

[1467] "Introduction Generation Module" is a software component for analyzing collected related information and generating a spoiler-free summary of the content.

[1468] A "generative AI model" is an algorithm or system that uses artificial intelligence technology to generate appropriate text from input data.

[1469] A "formatter" is a process or tool used to convert the generated testimonial into a user-friendly form.

[1470] "Search results" are a list of related information displayed based on the keywords entered by the user.

[1471] "Display Means" means the method or technology used to display the formatted description and search results on the user's device.

[1472] The present invention is a system in which a user inputs a keyword for a content they wish to search, collects information related to the keyword, and generates an introduction to prevent spoilers. A specific embodiment of this system will be described below.

[1473] The server receives the keyword entered by the user. The user enters the keyword of the content he or she wants to search for in the search bar of the terminal. For example, the user enters "review of the latest movie 'Avengers'."

[1474] The terminal sends the entered keyword to the server, using the HTTPS protocol for this communication.

[1475] The server collects relevant information based on the received keywords. To do this, it uses search engine APIs such as Google Search API and Bing Search API. For example, it sends a query such as "Avengers movie reviews" to the search engine.

[1476] The server sends the collected information to an introductory text generation module, which analyzes the collected information and identifies parts that contain spoilers.

[1477] The introduction generation module uses a generative AI model to generate an introduction that excludes spoilers. Specifically, it uses a generative AI model such as OpenAI's GPT-4. The generative AI model takes the prompt as input and generates an appropriate introduction.

[1478] For example, the following sentence is input as a prompt into the generative AI model:

[1479] "Please give us your review of the latest movie, The Avengers, without any spoilers please."

[1480] The generated testimonial is then formatted by the server. Formatting is the process of converting the generated testimonial into a form that is easy for the user to read, i.e., converting it into a suitable format so that it is easy for the user to understand.

[1481] The server then sends the formatted introduction to the terminal, again using the HTTPS protocol.

[1482] The terminal displays the received introduction text to the user, allowing the user to check an outline of the content without including spoilers.

[1483] In this way, users can feel at ease knowing the outline of the content. This system provides an effective means of providing users with the necessary information while preventing spoilers.

[1484] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1485] Step 1:

[1486] The user enters search keywords.

[1487] The user inputs the keyword of the content they want to search for into the search bar of the device. For example, they input "Review of the latest movie 'Avengers'." The input keyword becomes the input data of the device.

[1488] Step 2:

[1489] The terminal transmits the entered keyword to the server.

[1490] The terminal sends the keyword entered by the user to the server. This communication uses the HTTPS protocol. The input is the keyword entered by the user, and the output is the keyword sent to the server.

[1491] Step 3:

[1492] The server collects information related to the keywords.

[1493] The server uses the Google Search API or Bing Search API to collect related information based on the received keywords. For example, a query such as "Avengers movie reviews" is sent to the search engine. The input is the keyword sent to the server, and the output is the collected related information.

[1494] Step 4:

[1495] The server sends the collected information to the testimonial generation module.

[1496] The server sends the collected information to the testimonial generation module, where the input is the collected relevant information and the output is the information sent to the testimonial generation module.

[1497] Step 5:

[1498] The introduction generation module generates an introduction that excludes spoilers.

[1499] The introduction generation module uses a generative AI model to generate an introduction that excludes spoilers from the collected information. Specifically, the prompt "Please give us a review of the latest movie, The Avengers, but without spoilers." is input to the generative AI model. The input is the information sent to the introduction generation module, and the output is the generated introduction.

[1500] Step 6:

[1501] The server formats the generated description.

[1502] The server formats the introduction received from the generative AI model. Formatting is the process of converting the generated introduction into a form that is easy for users to read, i.e., converting it into a proper format to make it easy for users to understand. The input is the generated introduction, and the output is the formatted introduction.

[1503] Step 7:

[1504] The server sends the formatted introduction to the terminal.

[1505] The server sends the formatted introduction to the terminal. This communication also uses the HTTPS protocol. The input is the formatted introduction, and the output is the introduction sent to the terminal.

[1506] Step 8:

[1507] The terminal displays the introductory text to the user.

[1508] The terminal displays the received introduction text to the user. The user can check the outline of the content without including spoilers. The input is the introduction text sent to the terminal, and the output is the introduction text displayed to the user.

[1509] (Application example 1)

[1510] 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 robot 414 will be referred to as a "terminal".

[1511] Conventional Internet search tools often display information containing spoilers when collecting information about the content a user searches for, which can cause problems for the user's experience. In addition, it is difficult to efficiently collect information because it takes time to manually select information to avoid spoilers. Another issue is that the generated introduction text gets buried in the search results, making it difficult for users to quickly access the information they need.

[1512] 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.

[1513] In this invention, the server includes a means for receiving information about the content to be searched, a means for automatically generating an introduction that does not include spoilers based on the received information, a means for displaying the generated introduction in the search results, and a means for generating a prompt text using a generative AI model to generate an introduction that excludes spoilers. This allows the user to efficiently grasp the outline of the content while avoiding spoilers.

[1514] The "means for receiving information related to the content to be searched" refers to a device or program that has the function of collecting related information from the Internet based on keywords entered by the user.

[1515] The "means for automatically generating an introduction that does not include spoilers based on received information" refers to a device or program that has the function of excluding spoilers from collected information, extracting an outline of the content, and generating an introduction.

[1516] The "means for displaying the generated testimonial in the search results" refers to a device or program having a function of displaying the generated testimonial on the user's search result page.

[1517] "Means for generating a prompt sentence using a generative AI model and generating an introduction sentence that excludes spoilers" refers to a device or program that has the function of using a generative AI model to generate a prompt sentence for excluding spoilers from collected information, and generating an introduction sentence based on the prompt sentence.

[1518] A system for carrying out the present invention has the following configuration: A server includes means for receiving information related to the content to be searched, means for automatically generating an introductory text that does not include spoilers based on the received information, means for displaying the generated introductory text in the search results, and means for generating a prompt text using a generative AI model to generate an introductory text that excludes spoilers.

[1519] Hardware and Software Used

[1520] Hardware: Servers, user devices (smartphones, PCs, etc.)

[1521] Software: Python, BeautifulSoup, requests, OpenAI API

[1522] Data processing and calculation

[1523] 1. Data collection: Based on the keywords entered by the user's device, the server collects related information on the Internet. Specifically, it uses the requests library to obtain the search result page and parses it with BeautifulSoup.

[1524] 2. Spoiler removal and summary generation: The server inputs the collected information into OpenAI's generative AI model to generate a spoiler-free introduction. Specifically, it generates a prompt using the openai.Completion.create method and inputs it into the AI ​​model.

[1525] 3. Displaying the results: The server displays the generated synopsis on the user's search result page, allowing the user to efficiently get an overview of the content without spoiling it.

[1526] Examples

[1527] When a user searches for "popular movies," the server collects related information and generates and displays an introductory text that excludes spoilers. For example, by inputting the following prompt text into the generative AI model, an introductory text that does not include spoilers is generated.

[1528] Examples of prompt statements

[1529] Generate a content summary from the following information, excluding spoilers:

[1530] This movie is about the protagonist overcoming difficulties and growing as he goes on various adventures with his friends.

[1531] The story depicts the protagonist's growth as he comes to terms with his past.

[1532] The main characters include his best friend and mentor.

[1533] By inputting this prompt into a generative AI model, a spoiler-free introduction is generated and provided to the user.

[1534] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1535] Step 1:

[1536] The user inputs a search keyword from the terminal.

[1537] Input: The keyword for which the user wants to search for the content

[1538] Output: Search keywords sent to the server

[1539] Step 2:

[1540] The server collects relevant information on the Internet based on the search keywords.

[1541] Input: Search keyword

[1542] Output: A list of related information

[1543] What it does: The server uses the requests library to get the search results page, then parses it with BeautifulSoup to extract relevant information.

[1544] Step 3:

[1545] The server generates prompt sentences to input the collected information into the generative AI model.

[1546] Input: List of related information

[1547] Output: Prompt statement

[1548] Specific operation: The server generates a prompt text to filter out spoilers based on the collected information.

[1549] Step 4:

[1550] The server uses a generative AI model to generate a spoiler-free introduction based on the prompt text.

[1551] Input: Prompt statement

[1552] Output: Introduction without spoilers

[1553] Specific operation: The server uses the openai.Completion.create method to input the prompt text into the generation AI model and generate an introduction that excludes spoilers.

[1554] Step 5:

[1555] The server displays the generated testimonial on the user's search results page.

[1556] Input: Introduction without spoilers

[1557] Output: A description that will be displayed on the user's search results page.

[1558] Specific behavior: The server sets the generated testimonial to be displayed at the top of the search result page.

[1559] Example 2

[1560] Next, a second embodiment of the second embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal".

[1561] In conventional search systems, when users searched for information related to specific content, information containing spoilers was often displayed, which had the problem of ruining the user's experience. In addition, there was a lack of means to efficiently collect related information and generate appropriate introductions, making it difficult to quickly and accurately provide the information users were looking for.

[1562] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1563] In this invention, the server includes a means for receiving information about the content to be searched, a means for collecting related information based on the received information, a means for automatically generating an introductory text that does not include spoilers from the collected information, a means for formatting the generated introductory text, and a means for displaying the formatted introductory text in the search results. This makes it possible to quickly and accurately provide related information to the content searched for by the user while avoiding spoilers.

[1564] The "means for receiving information regarding the content being searched" refers to a function that allows the server to receive keywords or phrases that a user enters into the search bar.

[1565] "Means of collecting related information based on received information" refers to a function that uses search tools to collect related data from the Internet based on received keywords or phrases.

[1566] "Means for automatically generating a spoiler-free introduction from collected information" refers to a function that analyzes collected data, excludes important plot details and endings, and automatically creates a summary of the content using a generative AI model.

[1567] The "means for formatting the generated introduction" is a function for grammar checking and formatting the generated introduction to make it easier for the user to read.

[1568] The "means for displaying the formatted introduction in the search results" is a function for transmitting the formatted introduction to the user's terminal and displaying it on the search result page.

[1569] The present invention provides a system for automatically generating an introduction that does not include spoilers and displaying it in the search results when a user searches for information related to a particular piece of content. A specific embodiment of this system will be described below.

[1570] The server has a means for receiving keywords or phrases entered by a user into the search bar. When a user enters a "game title" into the search bar using a browser or a dedicated application on the terminal and clicks a search button, this search request is sent to the server.

[1571] Based on the received keywords or phrases, the server uses search tools such as Elasticsearch to gather relevant data from the Internet, including information from official game websites, review sites, forum posts, etc.

[1572] The collected information is then sent to a generative AI model, such as OpenAI’s GPT-4, using prompts to give the model specific instructions. For example, the following prompts can be used:

[1573] We have gathered information about the "Game Title". From this information, we would like you to generate a description that includes the game's genre, play style, and basic storyline, excluding the game's ending and important plot details.

[1574] The generative AI model analyzes the collected data, removes important plot details and endings, and automatically creates a summary of the content. The server checks the grammar and formats the summary to make it easier for users to read.

[1575] The formatted description is sent from the server to the user's device and displayed on the search results page, allowing the user to understand the general outline of the game, but without spoiling the ending or important plot details.

[1576] As a concrete example, consider the case where a user searches for "Final Fantasy VII." The server uses Elasticsearch to collect information related to "Final Fantasy VII" from the Internet. It then sends the collected information to GPT-4, which generates a description using the following prompt:

[1577] You have gathered information about "Final Fantasy VII." From this information, generate a description that includes the game's genre, play style, and basic storyline, excluding the game's ending and key plot details.

[1578] An example of a generated introduction might look like this:

[1579] "Final Fantasy VII" is a role-playing game. Players control characters and fight against giant corporations with rebel groups. The game employs a turn-based battle system and features a wide range of character development elements.

[1580] This description will be displayed on the user's device along with the search results.

[1581] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1582] Step 1:

[1583] A user enters keywords into the search bar and clicks the search button.

[1584] Input: The keyword entered by the user (e.g. "game title")

[1585] Output: A search request is sent to the server.

[1586] Specific operation: The user enters the "game title" in the search bar using the device's browser or a dedicated application, and clicks the search button. This action sends a search request to the server.

[1587] Step 2:

[1588] A server receives the search request and collects the relevant information.

[1589] Input: Search request (keywords entered by the user)

[1590] Output: Related information (e.g. official website, review sites, forum posts)

[1591] Specific operation: Based on the received search request, the server uses search tools such as Elasticsearch to collect information related to the "game title" from the Internet. Specifically, it obtains data from the game's official website, review sites, forum posts, etc.

[1592] Step 3:

[1593] The server sends the collected information to a generative AI model to generate a testimonial.

[1594] Input: Information collected (e.g. official sites, review sites, forum posts)

[1595] Output: Generated introduction (no spoilers)

[1596] Specific operation: The server sends the collected information to a generative AI model such as OpenAI's GPT-4. At this time, it uses a prompt to give specific instructions to the generative AI model. For example, the following prompt can be used:

[1597] We have gathered information about the "Game Title". From this information, we would like you to generate a description that includes the game's genre, play style, and basic storyline, excluding the game's ending and important plot details.

[1598] Step 4:

[1599] The server formats the generated description.

[1600] Input: Generated introductory text (no spoilers)

[1601] Output: A formatted introduction (grammar checked and formatted)

[1602] How it works: The server receives the introduction returned by the generative AI model and performs grammar checks and formatting adjustments to make it easier for users to read.

[1603] Step 5:

[1604] The server sends the formatted introduction to the user's terminal and displays it.

[1605] Input: Formatted introduction (grammar checked and formatted)

[1606] Output: The introductory text that is displayed to the user.

[1607] Specific operation: The server sends the formatted introductory text to the user's device. The user's device displays the received introductory text on the browser or application screen. This allows the user to understand the outline of the game, but does not reveal any spoilers about the ending or important plot points.

[1608] (Application example 2)

[1609] 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 robot 414 will be referred to as a "terminal".

[1610] In conventional search systems, when users searched for information about content, information containing spoilers was often displayed, which led to problems that marred the user experience. In addition, the generated introduction text was sometimes not displayed properly in the search results, which meant that users could not quickly access the information they needed. Furthermore, there were problems with the quality of the introduction text and the speed of generation because the introduction text was not generated efficiently using a generative AI model.

[1611] 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.

[1612] In this invention, the server includes a means for receiving information about the content to be searched, a means for automatically generating an introduction that does not include spoilers based on the received information, a means for displaying the generated introduction in the search results, a means for generating the introduction using a generative AI model, and a means for receiving a prompt as an input. This allows the user to quickly obtain summary information about the required content while avoiding spoilers.

[1613] "Searchable content" refers to media works such as movies, dramas, anime, and games about which users want to obtain information.

[1614] The "means for receiving information" is a part of the system that has the function of collecting relevant data based on the search query entered by the user.

[1615] A "spoiler-free introduction" is a piece of text that provides basic information such as an overview, genre, and play style, excluding the ending or important plot details of the content.

[1616] An "automated generation means" is a part of a system that has the function of generating a testimonial based on the information received, using a specific algorithm or model.

[1617] "Means for displaying the generated testimonial in a search result" means a portion of the system that has functionality for appropriately placing and displaying the generated testimonial on a user's search result page.

[1618] A "generative AI model" is a trained model that uses artificial intelligence technology to generate appropriate introductions from input data.

[1619] A "prompt sentence" is text data input to a generative AI model, and is a sentence that contains instructions and conditions for the model to generate an appropriate output.

[1620] In order to implement this invention, the server, the terminal, and the user must each fulfill a specific role.

[1621] First, a user uses a terminal to input information about the content to be searched. The terminal can be a device such as a smartphone or a PC, and must be connected to the Internet. Once the user enters a search query, the terminal transmits the information to a server.

[1622] The server collects relevant information based on the received search query. Specifically, the server uses APIs to retrieve information about content from external databases and websites, including content overview, genre, play style, etc.

[1623] Next, the server uses a generative AI model to automatically generate a spoiler-free introductory text from the collected information. The generative AI model is a pre-trained natural language processing model that has the ability to generate an appropriate introductory text from the input information. The prompt text is text data input to the generative AI model, and includes instructions and conditions for the model to generate an appropriate output.

[1624] The generated introduction is sent from the server to the terminal and displayed on the terminal screen, allowing the user to quickly obtain an overview of the desired content while avoiding spoilers.

[1625] As a concrete example, consider the case where a user searches for the movie "Inception." When the user types "Inception" into the device, the device sends the information to the server. The server collects related information and uses a generative AI model to generate a description like this:

[1626] "Inception is a science fiction film with a complex plot involving dreams within dreams. The protagonist is a professional information stealer in dreams, and his latest mission is..."

[1627] This synopsis is displayed on the terminal screen, allowing the user to understand the outline of the movie.

[1628] Examples of prompts include:

[1629] "What kind of movie is Inception?"

[1630] In this way, the user can quickly obtain the necessary information while avoiding spoilers.

[1631] The flow of the specific process in the application example 2 will be described with reference to FIG.

[1632] Step 1:

[1633] A user uses a terminal to enter a search query.

[1634] Input: The user enters the content they are searching for (e.g., "Inception").

[1635] Output: The device sends the search query to the server.

[1636] Specific actions: The user types "Inception" into the search bar on their smartphone or computer and presses the search button.

[1637] Step 2:

[1638] A server receives the search query and collects related information.

[1639] Input: The search query sent from the device (e.g. "Inception").

[1640] Output: Content information collected by the server from external databases and websites.

[1641] What happens: The server uses an API to retrieve information about "Inception" (such as summary, genre, play style, etc.) from movie databases and review sites.

[1642] Step 3:

[1643] Based on the information collected by the server, a generative AI model is used to generate an introduction that does not contain spoilers.

[1644] Input: Collected content information (e.g., summary of "Inception", genre, play style).

[1645] Output: A spoiler-free introduction generated by the generative AI model.

[1646] Specific operation: The server inputs the collected information into a generative AI model and generates a spoiler-free introduction using a prompt sentence (e.g., "What kind of movie is Inception?").

[1647] Step 4:

[1648] The server transmits the generated introduction to the terminal.

[1649] Input: An introductory text generated by a generative AI model.

[1650] Output: The introductory text sent to the terminal.

[1651] Specific operation: The server sends the generated introduction to the terminal and displays it on the user's search result page.

[1652] Step 5:

[1653] The terminal displays the received introduction to the user.

[1654] Input: The introduction sent by the server.

[1655] Output: The introductory text displayed on the user's device screen.

[1656] Specific operation: The device displays the received introduction at the top of the search result page and the user views it.

[1657] In addition, 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.

[1658] "Example 1"

[1659] As one embodiment of the present invention, a system incorporating an emotion engine is provided. The system recognizes a user's emotion and automatically generates an introductory text based on the emotion. Specifically, behavioral data such as a user's search history and browsing history is analyzed, and the user's emotion is estimated from the data. The estimated emotion is used to generate an introductory text. For example, if a user expresses an emotion of joy, an introductory text is generated for content that is likely to make the user happy. Also, if a user expresses an emotion of anger, an introductory text is not generated for content that is likely to make the user angry.

[1660] "Example 2"

[1661] As another embodiment of the present invention, an adjustment of the display order of introductions using an emotion engine is provided. Specifically, the display order of introductions is adjusted according to the emotion of the user. For example, when a user expresses an emotion of joy, introductions related to content that may make the user happy are displayed at the top of the search results. Also, when a user expresses an emotion of anger, introductions related to content that may make the user angry are displayed at the bottom of the search results. This makes it possible to provide optimal search results according to the emotion of the user.

[1662] The process flow of each embodiment will be described below.

[1663] "Example 1"

[1664] Step 1: Collect user behavioral data (e.g. search history, browsing history).

[1665] Step 2: Input the collected behavioral data into the emotion engine to estimate the user's emotions. Step 3: Automatically generate an introduction based on the estimated emotions.

[1666] Step 4: Display the generated testimonial to the user.

[1667] "Example 2"

[1668] Step 1: Collect user behavioral data (e.g. search history, browsing history).

[1669] Step 2: Input the collected behavioral data into the emotion engine to estimate the user's emotion. Step 3: Adjust the display order of the testimonials based on the estimated emotion.

[1670] Step 4: Display the testimonials to the user according to the adjusted display order.

[1671] Example 1

[1672] Next, a description will be given of Example 1 of the embodiment 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal".

[1673] In conventional Internet search tools, when collecting information about the content searched by the user, information containing spoilers may be displayed, which may spoil the user's experience. In addition, since it is not possible to provide an appropriate introduction according to the user's emotions, it is difficult to improve user satisfaction. Furthermore, since the search results are not customized based on the user's emotions, it is difficult for the user to quickly access the information he or she is looking for.

[1674] 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.

[1675] In this invention, the server includes a means for receiving information about the content to be searched, a means for automatically generating an introduction that does not include spoilers based on the received information, a means for displaying the generated introduction in the search results, a means for collecting user behavior data, a means for estimating the user's emotions based on the collected behavior data, and a means for generating an introduction based on the estimated emotions. This makes it possible for a user to be provided with an appropriate introduction that corresponds to the emotions while avoiding spoilers.

[1676] The "means for receiving information related to the search target content" refers to a device or program having a function of collecting related information from the Internet based on keywords entered by the user.

[1677] The "means for automatically generating an introduction that does not include spoilers" refers to a device or program having a function of excluding spoilers from collected information, extracting an outline of the content, and generating an introduction.

[1678] The "means for displaying the generated introduction text in the search results" refers to a device or program having a function for displaying the generated introduction text on the user's terminal.

[1679] The "means for collecting user behavioral data" refers to a device or program that has the function of collecting user behavioral data such as search history and browsing history.

[1680] The "means for inferring a user's emotions based on collected behavioral data" refers to a device or program having a function of analyzing collected behavioral data and inferring a user's emotions.

[1681] The "means for generating an introductory text based on an estimated emotion" refers to a device or a program having a function of automatically generating an introductory text appropriate to the emotion based on the estimated emotion of the user.

[1682] This invention is a system that, when a user inputs a keyword for the content they want to search for, collects information related to the keyword, generates and displays an introductory text that does not include spoilers, and also has the function of collecting user behavior data, estimating the user's emotions based on the data, and generating an introductory text according to the emotions.

[1683] Hardware and Software Used

[1684] 1. Server:

[1685] Search engine API: Used to collect information from the Internet. Specifically, Google Search API and Bing Search API are used.

[1686] Natural Language Processing library: Used to filter out spoilers and extract content summaries from collected information. Specifically, it uses the Hugging Face Transformers library and leverages a pre-trained BERT model.

[1687] Text summarization algorithms: used to extract an overview of the content. In particular, we use the Sumy library.

[1688] Sentiment Analysis API: Used to estimate emotions based on user behavior data. Specifically, it uses Google Cloud Natural Language API.

[1689] 2. Terminal:

[1690] Browser: Used by users to enter keywords and check search results. Specifically, common web browsers such as Google Chrome and Mozilla Firefox are used.

[1691] 3. User:

[1692] Input device: Used to input keywords, specifically using a keyboard or touch screen.

[1693] Explanation of program processing

[1694] 1. User enters a keyword:

[1695] A user opens a browser on their device, accesses the search tool interface, enters a keyword such as "Inception" in the search bar, and clicks the search button.

[1696] 2. The server collects information:

[1697] The server receives the keywords entered by the user and uses the Google Search API or Bing Search API to collect related information from the Internet. For example, it calls the Google Search API to get a list of web pages related to "Inception."

[1698] 3. The server filters out spoilers:

[1699] The collected information is sent to the introductory text generation module in the server, which uses a pre-trained BERT model using Hugging Face's Transformers library to detect and remove spoilers from the collected text, for example removing sentences containing keywords such as "ending" or "culprit."

[1700] 4. Server extracts summary:

[1701] After filtering out spoilers, the server uses the Sumy library to summarize the text and extract an overview of the content, for example generating a short summary that includes key plot and character introductions for a movie.

[1702] 5. The server formats the description:

[1703] The extracted summary is formatted in Markdown or HTML, for example by displaying the movie title as a heading and a summary in paragraph format below it.

[1704] 6. The server displays the search results:

[1705] The formatted description is displayed in the user's browser as a search result page, and the user can view the results through their device's browser.

[1706] Examples and prompts

[1707] Examples

[1708] If a user searches for a movie title:

[1709] When a user enters the keyword "Inception", the server uses the Google Search API to collect information about "Inception". It excludes spoilers from the collected information, extracts a summary of the movie using the Sumy library, and generates a summary. If the user indicates the emotion of joy, a summary that highlights the positive aspects of the movie is displayed.

[1710] Examples of prompt statements

[1711] Prompt for generative AI model:

[1712] "A user has searched for the keyword "Inception". Extract a synopsis of the movie from the collected information, excluding spoilers. The user is currently expressing the emotion of joy. Generate a description that highlights the positive aspects."

[1713] In this way, the present invention is a system that provides appropriate information based on the user's input and emotions.

[1714] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1715] Step 1:

[1716] The user enters a keyword

[1717] A user opens a browser on their device, accesses the search tool interface, enters a keyword such as "Inception" in the search bar, and clicks the search button.

[1718] Input: The keyword entered by the user

[1719] Output: The keyword is sent to the server.

[1720] Step 2:

[1721] The server collects information

[1722] Based on the received keywords, the server calls a search engine API (e.g., Google Search API or Bing Search API) to collect related information.

[1723] Input: The keyword entered by the user

[1724] Output: Relevant information retrieved from the search engine API

[1725] Step 3:

[1726] Server filters out spoilers

[1727] The collected information is sent to a testimonial generation module in the server, which uses a natural language processing library (e.g., Hugging Face's Transformers library) to leverage a pre-trained model (e.g., the BERT model) to detect and filter out spoilers from the collected text.

[1728] Input: Related information obtained from search engine API

[1729] Output: Information without spoilers

[1730] Step 4:

[1731] The server extracts the summary

[1732] The spoiler-free information is then summarized using a text summarization algorithm (e.g., the Sumy library) to extract an overview of the content.

[1733] Input: Information without spoilers

[1734] Output: A summary of the extracted content

[1735] Step 5:

[1736] The server formats the introduction

[1737] The extracted summary is formatted in Markdown or HTML, for example by displaying the movie title as a heading and a summary in paragraph format below it.

[1738] Input: A summary of the extracted content

[1739] Output: A formatted introduction

[1740] Step 6:

[1741] The server displays the search results.

[1742] The formatted description is displayed in the user's browser as a search result page, and the user can view the results through their device's browser.

[1743] Input: Formatted description

[1744] Output: The search results displayed in the user's browser.

[1745] Step 7:

[1746] The server collects user behavior data

[1747] The server collects user behavioral data, such as search history and browsing history, using browser cookies and local storage.

[1748] Input: User search and browsing history

[1749] Output: Collected behavioral data

[1750] Step 8:

[1751] The server estimates the emotion

[1752] Analyze the collected behavioral data and infer user emotions using a sentiment analysis API (e.g., Google Cloud Natural Language API).

[1753] Input: Collected behavioral data

[1754] Output: Estimated user emotion

[1755] Step 9:

[1756] The server generates the introduction

[1757] Based on the estimated emotion, a generative AI model is used to input a prompt sentence and automatically generate an introduction that matches the emotion.

[1758] Input: Estimated user emotion

[1759] Output: An emotionally appropriate introduction

[1760] Step 10:

[1761] The server displays the introductory text.

[1762] The generated introduction is displayed on the user's browser, allowing the user to check the results through their device and enjoy content that matches their emotions.

[1763] Input: An emotionally appropriate introduction

[1764] Output: The introductory text displayed in the user's browser.

[1765] (Application example 1)

[1766] 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 robot 414 will be referred to as a "terminal".

[1767] In conventional Internet search tools, when collecting information about the content a user searches for, information containing spoilers may be displayed, which may ruin the user's experience. In addition, since content is not introduced according to the user's emotions, it is difficult to increase user satisfaction.

[1768] 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.

[1769] In this invention, the server includes a means for receiving information about the content to be searched, a means for automatically generating an introduction that does not include spoilers based on the received information, a means for recognizing a user's emotions and customizing the introduction based on the emotions, and a means for displaying the generated introduction in the search results. This makes it possible to introduce content according to the user's emotions while preventing spoilers.

[1770] The "means for receiving information related to the search target content" is a function for collecting information on related content based on keywords entered by the user.

[1771] The "means for automatically generating an introduction that does not include spoilers based on the received information" is a function for excluding spoilers from the collected content information and generating an introduction that is suitable for the user.

[1772] "Means of recognizing user emotions and customizing the introductory text based on those emotions" refers to a function that analyzes a user's search history and behavioral data to infer emotions and adjust the introductory text according to those emotions.

[1773] "Means for displaying the generated testimonial in the search results" refers to a function for displaying the generated testimonial on the user's search result page.

[1774] A system for implementing the present invention includes a server, a user terminal, and a generative AI model. A specific embodiment of the system will be described below.

[1775] System Configuration

[1776] 1. Server:

[1777] The server receives search keywords from the user.

[1778] The server collects related content information based on the received keywords.

[1779] The server removes spoilers from the collected information and generates an introduction.

[1780] The server recognizes the user's emotions and customizes the testimonials based on the emotions.

[1781] The server transmits the generated introduction to the user terminal.

[1782] 2. User device:

[1783] The user terminal provides an interface for the user to input search keywords.

[1784] The user terminal displays the introduction sent from the server.

[1785] 3. Generative AI model:

[1786] The generative AI model analyzes users' search history and behavioral data to infer their emotions.

[1787] A generative AI model customizes testimonials based on sentiment.

[1788] Program Processing

[1789] When the server receives the search keyword entered by the user, it collects related content information. This information can be collected from external APIs or databases. The collected information is filtered to prevent spoilers and then sent to the introduction generation module.

[1790] The introduction generation module extracts an overview of the content from the collected information, excluding spoilers. Based on this overview, an introduction suitable for the user is generated. Next, the emotion engine analyzes the user's search history and behavioral data to estimate the user's emotions. Based on this emotion information, the introduction is customized.

[1791] For example, if the user feels like relaxing, an introductory text for relaxing content is generated. The generated introductory text is transmitted from the server to the user terminal and displayed on the user's search result page.

[1792] Examples

[1793] If a user searches for "relaxing movies", the following prompt might be generated:

[1794] Example prompt:

[1795] User's recent behavior data: "Recent searches: 'stress relief', 'relaxing music', 'yoga videos'"

[1796] When this prompt is fed into a sentiment analysis model, the user's sentiment is estimated to be "positive," and a description of a relaxing movie is generated based on this.

[1797] The above is a specific embodiment for carrying out the present invention. This system makes it possible to introduce content according to the user's emotions while preventing spoilers.

[1798] The flow of the specific process in the application example 1 will be described with reference to FIG.

[1799] Step 1:

[1800] A user inputs a search keyword into a terminal. The terminal sends the keyword to a server. The input is the user's search keyword, and the output is a search request sent to the server.

[1801] Step 2:

[1802] The server collects relevant content information based on the received search keywords. This information collection is done using external APIs and databases. The input is the search keywords, and the output is the collected content information.

[1803] Step 3:

[1804] The server performs filtering to remove spoilers from the collected content information. Specifically, it removes specific keywords and phrases. The input is the collected content information, and the output is the content information with spoilers removed.

[1805] Step 4:

[1806] The server extracts a summary of the content from the spoiler-free content information. It generates an introduction based on the extracted summary. The input is the spoiler-free content information, and the output is the generated introduction.

[1807] Step 5:

[1808] The server analyzes the user's search history and behavioral data to estimate the user's emotions. A generative AI model is used for this analysis. The input is the user's search history and behavioral data, and the output is the estimated user's emotions.

[1809] Step 6:

[1810] The server customizes the introduction based on the estimated user's emotion. For example, if the user feels like relaxing, the server generates an introduction for relaxing content. The input is the estimated user's emotion and the generated introduction, and the output is the customized introduction.

[1811] Step 7:

[1812] The server sends the customized introduction to the user terminal, where the input is the customized introduction and the output is the introduction sent to the user terminal.

[1813] Step 8:

[1814] The user terminal displays the introduction text sent from the server on the search result page. The input is the introduction text sent from the server, and the output is the introduction text displayed to the user.

[1815] Example 2

[1816] Next, a second embodiment of the second embodiment will be described. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal".

[1817] In conventional search systems, when a user searches for information about a particular piece of content, information containing spoilers may be displayed, which may ruin the user's experience. There is also the problem that it is difficult to provide optimal search results according to the user's emotions. To solve these problems, a system is needed that generates introductions that do not include spoilers and adjusts the display order of search results based on the user's emotions.

[1818] 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 receiving information about the data to be searched, a means for automatically generating an introduction text that does not include spoilers based on the received information, a means for displaying the generated introduction text in the search results, a means for analyzing the user's emotions, and a means for adjusting the display order of the introduction text based on the analyzed emotions. This allows the user to obtain optimal search results according to their emotions while avoiding spoilers.

[1819] "Searchable data" refers to the specific information or content for which a user is searching.

[1820] "Means for receiving information" means a device or software that has the function of receiving a search query from a user and collecting related information based on the query.

[1821] A "spoiler-free introduction" is a piece of text that provides users with basic information such as an overview, genre, and play style, without including the ending or important plot details of the content.

[1822] An "automated generation means" is a device or software that has the capability to automatically generate a testimonial based on the information it receives using a particular algorithm or generative AI model.

[1823] "Means for displaying in the search results" refers to a device or software that has the function of displaying the generated introduction on the user's terminal.

[1824] "Means for analyzing user emotions" refers to devices or software that have the function of analyzing the user's emotional state based on data such as facial expressions and voice.

[1825] A "means for adjusting the display order" refers to a device or software that has the function of optimizing the display order of search results based on the analyzed user sentiment.

[1826] This invention is a system that generates an introduction that does not include spoilers when a user searches for information about a specific data item, and adjusts the display order of search results based on the user's feelings. This system works in cooperation with a server, a terminal, and a user.

[1827] First, a user uses a device to search for specific data. For example, a user opens a browser on a smartphone, enters "a specific game title" in the search bar, and presses the search button. This action sends a search query from the device to the server.

[1828] Based on the received search query, the server collects relevant information from the Internet using existing search engine APIs such as...

Claims

1. A means for receiving keywords relating to the content to be searched from a user's terminal; means for collecting related information based on the received keywords; A means for generating an introduction text excluding spoilers from the collected related information; means for formatting the introduction into a format that is easy for a user to read; means for transmitting the formatted introduction text to the terminal; A system including:

2. The system of claim 1 , wherein the means for generating the testimonial uses a generation AI to generate the testimonial.

3. The system of claim 1 , further comprising means for configuring the testimonial to be displayed higher on a search result page for the user.

Images