system

Abstract

We provide the system. [Solution] A means for receiving user input data, A means of analyzing the received input data and extracting keywords, A method for searching past cases using extracted keywords, A method for suggesting related products using extracted keywords, A means of providing users with recommended past case studies and products, A means of identifying and introducing the necessary experts and systems based on the user's wishes, A system that includes this.

Description

Technical Field

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

Background Art

[0002] Patent Document 1 discloses a method for controlling a persona chatbot, which is performed by at least one processor, and includes steps of receiving a user utterance, adding the user utterance to a prompt including an instruction sentence related to an explanation of a character of the chatbot, 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

Summary of the Invention

Problems to be Solved by the Invention

[0004] In a modern business environment, when a user materializes a new idea, it is required to find appropriate past cases and business materials from a number of information sources, and further identify necessary experts and systems. However, performing this manually requires a great deal of time and effort, so an efficient support system is demanded. The present invention aims to make an optimal proposal based on a user's idea, and further automate a series of processes including the introduction of experts and systems, thereby reducing the burden on the user.

Means for Solving the Problems

[0005] The present invention solves the above problems by a system having the following means. That is,

[0006] A means of receiving user input data,

[0007] A means of analyzing the received input data and extracting keywords,

[0008] A method for searching past cases using extracted keywords,

[0009] A method for suggesting related products using extracted keywords,

[0010] A means of providing users with recommended past case studies and products,

[0011] A means of identifying and introducing the necessary experts and systems based on the user's wishes,

[0012] It is a system that includes this.

[0013] A "user" is an entity that uses this system to input ideas or obtain suggestions.

[0014] "Input data" refers to the ideas and requests that users provide to the system.

[0015] "Analysis" refers to natural language processing and other data processing techniques used to understand input data and extract necessary information.

[0016] A "keyword" is a word or phrase that represents important information or concepts, extracted from the input data through analysis.

[0017] "Past examples" refer to information about similar ideas and projects stored in the database, which can serve as a reference for new ideas.

[0018] "Commercial products" refer to the products and services necessary to bring a user's ideas to life.

[0019] "Expert" refers to an individual or organization with the knowledge and skills necessary to realize the user's idea.

[0020] "System" refers to an integrated computer program and database for executing a series of processes including analysis of user input data, extraction of keywords, proposal of past cases and commercial materials, and identification and introduction of experts and systems.

Brief Explanation of Drawings

[0021] [Figure 1] It is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] It is a conceptual diagram showing an example of the main functions of a data processing device and a smart device according to the first embodiment. [Figure 3] It is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] It is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] It is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] It is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7] It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which multiple emotions are mapped. [Figure 10] It shows an emotion map to which multiple emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] This is a sequence diagram showing the processing flow of the data processing system in Example 2, which incorporates an emotion engine. [Figure 14] This is a sequence diagram showing the processing flow of the data processing system in Application Example 2, which combines an emotion engine. [Modes for carrying out the invention]

[0022] Hereinafter, an example of an embodiment of the system relating to the technology of this disclosure will be described with reference to the attached drawings.

[0023] First, let's explain the terminology used in the following explanation.

[0024] In the following embodiments, the signed processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Furthermore, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include CPU (Central Processing Unit), GPU (Graphics Processing Unit), GPGPU (General-Purpose computing on Graphics Processing Units), and APU (Accelerated Processing Unit).

[0025] In the following embodiments, signed RAM (Random Access Memory) is a memory that temporarily stores information and is used as work memory by the processor.

[0026] In the following embodiments, the signed storage is one or more non-volatile storage devices that store various programs and various parameters. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes.

[0027] In the following embodiments, the signed communication interface (I / F) is an interface that includes a communication processor and an antenna, etc. The communication interface manages communication between multiple computers. Examples of communication standards applicable to the communication interface include wireless communication standards such as 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), or Bluetooth (registered trademark).

[0028] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0029] [First Embodiment]

[0030] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0031] As shown in Figure 1, the 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.

[0032] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0033] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0034] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and 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.

[0035] 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 perceptible to the user 20 (e.g., audio 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 audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0036] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0037] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0038] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this 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 according to the specific processing program 56 executed on the RAM 30.

[0039] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0040] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0041] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0042] Modes for carrying out the invention

[0043] This invention relates to a system that streamlines the process of users materializing their ideas, such as "I want to do XX." This system begins with the user submitting input data, provides past examples and products related to the idea, and further includes functions to identify and introduce the necessary experts and systems for implementation.

[0044] Program processing

[0045] User actions

[0046] The user uses their device to input a specific idea in text format. For example, they might type, "I want to start a new marketing campaign."

[0047] Sending data

[0048] The terminal sends this input data to the server. The input data is a concrete expression of the user's wishes and ideas.

[0049] Data Analysis

[0050] The server receives the input data and analyzes it using natural language processing (NLP) techniques. As a result of the analysis, several keywords are extracted from the data. For example, "marketing" and "campaign" might be extracted.

[0051] Searching past cases

[0052] Using the keywords obtained from the analysis, the server searches the database for relevant past cases. For example, "Campaign A" and "Campaign B" may be obtained as search results.

[0053] Product proposals

[0054] The server also searches its database for related products based on keywords and suggests them to the user. For example, "SNS advertising tools" or "email marketing tools" might be suggested.

[0055] Providing results

[0056] The server compiles past case studies and product suggestions and provides them to the user. This result is displayed to the user via their terminal.

[0057] Introduction of Experts and Systems

[0058] Furthermore, the server identifies and recommends the necessary experts and systems based on the user's preferences. For example, it might recommend "marketing personnel," "advertising specialists," "CRM systems," and "data analysis tools" needed for a marketing campaign.

[0059] Specific example

[0060] For example, consider a case where a user enters "I want to start an online shop."

[0061] 1. The user enters "I want to set up an online shop" into their device.

[0062] 2. The terminal sends the input data to the server.

[0063] 3. The server uses NLP to extract the keywords "online shop" and "launch".

[0064] 4. The server searches for past cases such as "Shop A launch case study" and "Shop B launch case study".

[0065] 5. The server proposes "EC site building tools" and "online payment systems" as products.

[0066] 6. The server compiles this information, sends it to the terminal, and displays it to the user.

[0067] 7. Furthermore, the server identifies and introduces specialists such as "web designers" and "SEO experts," as well as systems such as "hosting services" and "security solutions."

[0068] In this way, the present invention realizes a system that supports the effective realization of users' ideas. By using this system, users can acquire the information and resources necessary to advance their projects quickly and efficiently.

[0069] The following describes the processing flow.

[0070] Step 1:

[0071] The user enters specific ideas or wishes, such as "I want to do XX," into the device in text format. For example, they might enter, "I want to start a new marketing campaign."

[0072] Step 2:

[0073] The terminal sends the user's input data to the server. At this time, the input data is packaged in an appropriate format.

[0074] Step 3:

[0075] The server receives input data and transfers it to a natural language processing (NLP) module for text analysis.

[0076] Step 4:

[0077] The server uses an NLP module to analyze the input data and extract keywords. For example, "marketing" and "campaign" might be extracted.

[0078] Step 5:

[0079] The server searches the database for relevant past cases based on the extracted keywords. This retrieves, for example, "Campaign A" and "Campaign B".

[0080] Step 6:

[0081] The server uses the extracted keywords to search the database for related products and lists them. For example, "SNS advertising tools" and "email marketing tools" might be suggested.

[0082] Step 7:

[0083] The server compiles search results and product suggestions, creating response data to provide to the user. This data includes a list of relevant past cases and products.

[0084] Step 8:

[0085] The server sends response data to the terminal. The terminal receives this data and displays it appropriately to the user.

[0086] Step 9:

[0087] The server identifies the necessary experts and systems for implementation based on the user's requests. For example, it searches for "marketing specialists," "advertising specialists," "CRM systems," and "data analysis tools."

[0088] Step 10:

[0089] The server compiles expert and system information and sends it to the terminal as data indicating the next action for the user. The terminal receives this data and displays it to the user.

[0090] (Example 1)

[0091] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0092] The process of transforming users' abstract ideas into concrete ideas is often time-consuming, laborious, and difficult to carry out efficiently. In particular, quickly finding past success stories and relevant resources is a challenge. Furthermore, the process of identifying and introducing necessary experts and systems is cumbersome, resulting in insufficient support for users to effectively advance their projects. A system that addresses these challenges is needed.

[0093] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0094] In this invention, the server includes means for receiving user input data, means for analyzing the received input data and extracting key keywords, means for searching past cases using the extracted keywords, means for suggesting relevant resources using the extracted keywords, means for providing the user with the recommended past cases and resources, and means for identifying and introducing necessary experts and systems based on the user's preferences. This makes it possible for users to quickly and efficiently materialize their abstract ideas and rapidly acquire the necessary information and resources.

[0095] "Input data" refers to information entered by the user in text format, such as ideas and requests.

[0096] "Analysis" is the process of extracting key information and keywords from input data.

[0097] A "keyword" is a word or phrase that represents important information extracted from the input data.

[0098] "Past examples" refer to information about previously successful projects and ideas stored in the database.

[0099] "Resources" is a general term for tools and services that help users realize their ideas.

[0100] An "expert" is a person who possesses advanced knowledge and experience in a particular field.

[0101] A "system" is the technical infrastructure and tools necessary to realize an idea, which are identified according to the user's needs.

[0102] "Suggesting" means that the server selects relevant resources and experts based on the user's needs and introduces them to the user.

[0103] Modes for carrying out the invention

[0104] This invention relates to a system that streamlines the process of materializing a user's idea of ​​"I want to do XX." This system begins with the user submitting input data, provides past examples and resources related to the idea, and further includes functions to identify and introduce the necessary experts and systems for implementation.

[0105] The server plays a central role in this system, working in conjunction with users and terminals to collect, analyze, and provide data. The specific operations at each step are described below.

[0106] 1. Receiving input data

[0107] The user uses a device to input specific ideas in text format. For example, they might type "I want to start a new marketing campaign." Typically, the user enters their idea into the text box displayed on the device and clicks the submit button. At this point, the input data expresses the idea concretely.

[0108] 2. Sending data

[0109] The terminal sends the input data to the server. This process uses the HTTP protocol and involves a POST request. Specifically, a request body containing the user's idea is sent to the URL "https: / / example.com / api / submit".

[0110] 3. Analysis using natural language processing

[0111] The server analyzes the received data using natural language processing (NLP) techniques. The server uses an NLP library (e.g., SpaCy or NLTK) deployed on a Python program to extract key keywords from the user's input text. This process includes text tokenization and part-of-speech tagging. For example, from the input "I want to start a new marketing campaign," the keywords "marketing" and "campaign" are extracted.

[0112] 4. Search past cases

[0113] Next, the server searches its internal database for relevant past cases based on the extracted keywords. This search process is performed using SQL queries. For example, a query such as "SELECT FROM cases WHERE keywords LIKE '%marketing%' AND keywords LIKE '%campaign%'" is executed, and relevant cases such as "Campaign A" and "Campaign B" are retrieved.

[0114] 5. Product Proposal

[0115] The server similarly searches the database for relevant resources based on keywords. SQL queries retrieve a list of relevant tools and services. For example, a query like "SELECT FROM products WHERE keywords LIKE '%marketing%' AND keywords LIKE '%campaign%'" is executed, and "SNS advertising tools" and "email marketing tools" are suggested.

[0116] 6. Providing results

[0117] The server compiles past cases and resource suggestions and provides them to the user. This result is created in HTML format and sent to the user's device. The results are displayed in the user's browser, allowing them to view detailed information about the suggested cases and tools. For example, the results screen might include a "Detailed Description of Campaign A" and a "List of Recommended Tools."

[0118] 7. Introduction to Experts and Systems

[0119] Furthermore, the server identifies and recommends the necessary experts and systems based on the user's preferences. Expert and system information is also retrieved from the database. For example, executing "SELECT FROM experts WHERE expertise LIKE '%marketing%'" will list "marketing specialists" and "advertising experts." Based on this, the user is introduced to contact information for experts such as "web designers" and "SEO specialists," as well as systems such as "hosting services" and "security solutions."

[0120] By using this system, users can acquire the information and resources necessary to advance their projects quickly and efficiently.

[0121] Specific example

[0122] For example, consider a case where a user enters "I want to start an online shop."

[0123] 1. The user enters "I want to set up an online shop" into their device.

[0124] 2. The terminal sends the input data to the server.

[0125] 3. The server uses NLP to extract the keywords "online shop" and "launch".

[0126] 4. The server searches for past cases such as "Shop A launch case study" and "Shop B launch case study".

[0127] 5. The server proposes "EC site building tools" and "online payment systems" as resources.

[0128] 6. The server compiles this information, sends it to the terminal, and displays it to the user.

[0129] 7. Furthermore, the server identifies and introduces specialists such as "web designers" and "SEO experts," as well as systems such as "hosting services" and "security solutions."

[0130] The following are some specific examples of prompt statements that can be input into a generative AI model.

[0131] "We need ideas to develop new products."

[0132] "Please tell me how to start an effective marketing campaign."

[0133] By using these prompts, users can effectively utilize the system.

[0134] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0135] Step 1:

[0136] The user uses their device to input specific ideas in text format. For example, they might input, "I want to start a new marketing campaign." The input data is entered into a text box, and the input is completed by pressing the submit button. Input is performed by the user entering their idea into the text box on their device and clicking the submit button. This generates the user's idea as text data.

[0137] Step 2:

[0138] The terminal sends text data entered by the user to the server. The HTTP protocol is used for data transmission, and a POST request is made. Specifically, the entered text data is included in the request body and sent to the URL "https: / / example.com / api / submit". The input for this step is the text data entered by the user, and the output is the completion of data transmission to the server.

[0139] Step 3:

[0140] The server analyzes the received text data using natural language processing (NLP) techniques. The server uses NLP libraries such as Python's SpaCy or NLTK to tokenize the text data and extract key keywords. For example, from the text "I want to start a new marketing campaign," it extracts the keywords "marketing" and "campaign." The input for this step is the text data sent to the server, and the output is the extracted keywords.

[0141] Step 4:

[0142] The server uses the extracted keywords to search its internal database for relevant past cases. This search uses SQL queries. For example, it might execute a query like "SELECT FROM cases WHERE keywords LIKE '%marketing%' AND keywords LIKE '%campaign%'" to retrieve the relevant cases. The input for this step is the extracted keywords, and the output is the relevant past case data.

[0143] Step 5:

[0144] The server then searches the database for relevant resources based on keywords. SQL queries are used for this search as well. For example, a query like "SELECT FROM resources WHERE keywords LIKE '%marketing%' AND keywords LIKE '%campaign%'" is executed to retrieve the relevant tools and services. The input for this step is the extracted keywords, and the output is the relevant resource data.

[0145] Step 6:

[0146] The server compiles past case studies and resource data based on keywords and generates results. These results are created in HTML format and sent to the user's terminal. For example, the results screen might include a "Detailed Description of Campaign A" and a "List of Recommended Tools." The input for this step is past case study data and resource data, and the output is the resulting HTML data.

[0147] Step 7:

[0148] Furthermore, the server identifies and recommends the necessary experts and systems based on the user's preferences. It retrieves expert and system information from the database using SQL queries. For example, it might execute "SELECT FROM experts WHERE expertise LIKE '%marketing%'" to list relevant experts. The input for this step is keywords based on the user's preferences, and the output is expert and system information.

[0149] Through the steps outlined above, this system can quickly and efficiently materialize users' ideas and provide the necessary resources.

[0150] (Application Example 1)

[0151] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0152] In today's world, even if users have concrete ideas, it is difficult to quickly and efficiently gather the information and resources necessary to realize those ideas. Furthermore, finding past success stories, relevant products, and appropriate experts and systems requires a tremendous amount of time and effort. In addition, it is difficult for users to generate prompts using AI models to find the appropriate approach. To solve these challenges, there is a need for a means for users to obtain the necessary information and resources quickly and efficiently.

[0153] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0154] In this invention, the server includes means for receiving user input data, means for analyzing the received input data and extracting keywords, means for searching past cases using the extracted keywords, means for suggesting relevant products using the extracted keywords, means for providing the user with the recommended past cases and products, means for identifying and introducing necessary experts and systems based on the user's wishes, means for generating appropriate prompt sentences using a generative AI model based on the input data, and means for suggesting relevant past cases and products based on the generated prompt sentences. This makes it possible for the user to acquire the necessary information and resources efficiently in a short amount of time, and the process of materializing their ideas is greatly simplified.

[0155] "Means for receiving user input data" refers to interfaces or devices that allow users to input their ideas and wishes in text or other formats.

[0156] "Methods for analyzing received input data and extracting keywords" refers to a system that uses natural language processing technology to identify important words and phrases from user input data and extract them.

[0157] "A means of searching for past cases using extracted keywords" refers to a system that searches for past achievements and cases related to the extracted keywords from information sources such as databases.

[0158] "A method for proposing related products using extracted keywords" refers to a system that selects and proposes products and services that are suitable for the user's needs based on keywords.

[0159] "Means of providing users with recommended past cases and products" refers to a system that provides users with information on past cases and suggested products obtained as search results, allowing them to review the information.

[0160] "A means of identifying and introducing necessary experts and systems based on user requests" refers to a system that selects the necessary experts and systems to address the user's specific requests and ideas, and provides information on them.

[0161] "A means of generating appropriate prompt sentences using a generative AI model based on input data" refers to a system that automatically creates appropriate instructional or question-based text using a generative AI model based on data input by the user.

[0162] "A means of suggesting relevant past cases and products based on generated prompt sentences" refers to a system that uses the generated prompt sentences to search for and suggest even more relevant past cases and products.

[0163] This invention provides a system that efficiently supports the process of realizing a user's specific idea. The embodiments for carrying out this invention will be described in detail below.

[0164] Hardware and software to be used

[0165] Hardware: Cloud servers, smartphones

[0166] Software: React Native (frontend), Python, Flask (backend), NLTK (natural language processing), MongoDB (database management), generative AI model (prompt generation)

[0167] System Configuration

[0168] 1. User actions

[0169] Users use a smartphone application to input their ideas in text format. For example, they might enter specific requests such as, "I want to create a new content series."

[0170] 2. Sending data

[0171] User input data is sent from the smartphone to the cloud server. This communication is performed via API calls using the HTTPS protocol.

[0172] 3. Data Analysis

[0173] The cloud server uses Python and Flask to analyze the input data it receives. Here, natural language processing (NLP) techniques are used, and important keywords are extracted from the input data using the NLTK library.

[0174] 4. Prompt sentence generation using a generative AI model

[0175] Based on the extracted keywords, a generative AI model is used to generate appropriate prompt sentences. These prompt sentences are then used for subsequent search and recommendation processes.

[0176] 5. Search for past cases and products

[0177] The generated prompt is used to search the database stored in MongoDB for relevant past cases and product information.

[0178] 6. Providing results

[0179] Past case studies and suggested products obtained as search results are sent from the server to the smartphone and displayed for the user to review.

[0180] 7. Introduction of Experts and Systems

[0181] Based on the user's preferences, the necessary experts and systems for project implementation are identified and introduced. This information is also displayed on the smartphone.

[0182] Specific example

[0183] For example, if a user enters "I want to create a new podcast series," the process would be as follows:

[0184] 1. User actions

[0185] The user types "I want to create a new podcast series" into their smartphone.

[0186] 2. Sending data

[0187] The text data entered by the user is sent to the cloud server.

[0188] 3. Data Analysis

[0189] The server extracts keywords such as "podcast" and "series."

[0190] 4. Prompt sentence generation using a generative AI model

[0191] Based on the extracted keywords, the AI ​​model generates a prompt message that says, "Please recommend examples of successful podcast series and the necessary equipment."

[0192] 5. Search for past cases and products

[0193] The generated prompt is used to search MongoDB for relevant past cases (e.g., successful podcast series) and products (e.g., recording equipment).

[0194] 6. Providing results

[0195] The search results are displayed on the user's smartphone.

[0196] 7. Introduction of Experts and Systems

[0197] Furthermore, information from experts such as audio engineers and digital marketing specialists will also be provided.

[0198] Example of a prompt:

[0199] "I have an idea for a new podcast series. I'd like some examples of successful podcast series from the past and recommendations for necessary equipment."

[0200] This system allows users to quickly and efficiently acquire the necessary information and resources, and significantly simplifies the process of bringing their ideas to life.

[0201] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0202] Step 1:

[0203] The user uses a smartphone application to input a specific idea in text format. An example input is "I want to create a new podcast series." This input data is then sent to the server.

[0204] Step 2:

[0205] The server analyzes the received input data. Here, Python and Flask are used. Specifically, the NLTK natural language processing (NLP) library is used to extract important keywords from the input data. For example, keywords such as "podcast" and "series" are extracted.

[0206] Step 3:

[0207] The server uses a generative AI model to generate appropriate prompt sentences based on the extracted keywords. The generative AI model generates a prompt sentence such as, "I want to create a new podcast series. I would like recommendations for successful case studies and necessary equipment that would be helpful in this situation."

[0208] Step 4:

[0209] The server uses the generated prompt to search the database (MongoDB) for relevant past cases. The keywords included in the generated prompt are used as the search query. For example, successful podcast series cases might be retrieved as search results.

[0210] Step 5:

[0211] Similarly, the server uses the generated prompt to search the database for relevant products. The keywords included in the prompt are used as the search query. For example, recommended recording equipment or streaming platforms may be retrieved as search results.

[0212] Step 6:

[0213] The server aggregates search results and provides them to the user. Specifically, information on successful podcast series examples and recommended products is sent to the user's smartphone. This information is then displayed on the user's smartphone.

[0214] Step 7:

[0215] Based on the user's preferences, the server identifies and recommends further necessary experts and systems. For example, information on audio engineers, digital marketing specialists, and related systems is provided to the user. This information is also displayed on the smartphone.

[0216] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0217] Modes for carrying out the invention

[0218] This invention is a system that helps users materialize their "I want to do XX" ideas, and further incorporates an emotion engine that recognizes the user's emotions and makes optimal suggestions based on those emotions. The system of this invention consists of a number of different processing steps.

[0219] Program processing

[0220] User actions

[0221] The user uses their device to input specific ideas or wishes in text format, such as "I want to do XX." For example, they might input "I want to start a new marketing campaign."

[0222] Sending data

[0223] The terminal sends input data to the server. During this process, the input data is packaged in an appropriate format before being sent.

[0224] Data Analysis

[0225] The server receives user input data and forwards it to a natural language processing (NLP) module for text analysis. This analysis extracts multiple keywords. For example, "marketing" and "campaign" might be extracted.

[0226] Emotional analysis

[0227] Simultaneously, the server uses an emotion engine to analyze the user's emotions from the input data. This emotion analysis determines whether the user is expressing positive or negative emotions.

[0228] Searching past cases

[0229] The server uses keywords to search the database for relevant past cases. For example, it might search for "Campaign A" or "Campaign B".

[0230] Product proposals

[0231] The server then searches its database for related products based on the same keywords and lists them. For example, "SNS advertising tools" and "email marketing tools" might be suggested.

[0232] Adjusting the proposal

[0233] Based on the analysis results of the emotion engine, the server adjusts the suggestions for past examples and products that are best suited to the user's emotional state. For example, if the user is expressing negative emotions, the server prioritizes suggesting products and examples that provide a greater sense of security.

[0234] Providing results

[0235] The server compiles tailored search results and product recommendations, creating response data to provide to the user. This data includes relevant past cases, product lists, and sentiment-based recommendations.

[0236] Introduction of Experts and Systems

[0237] Furthermore, based on the user's preferences and sentiment analysis results, the server identifies the necessary experts and systems for implementation. For example, "marketing personnel," "advertising specialists," "CRM systems," and "data analysis tools" may be suggested.

[0238] Specific example

[0239] For example, consider a case where a user enters "I want to start an online shop."

[0240] 1. The user enters "I want to set up an online shop" into their device.

[0241] 2. The device sends data to the server.

[0242] 3. The server uses NLP to extract the keywords "online shop" and "launch".

[0243] 4. The server simultaneously analyzes the user's emotions using an emotion engine. This analysis can, for example, determine if the user is expressing positive emotions.

[0244] 5. The server searches for past examples such as "Shop A launch case study" and "Shop B launch case study".

[0245] 6. The server proposes "EC site building tools" and "online payment systems" as products.

[0246] 7. Based on the emotion analysis results, the server adjusts its settings to prioritize suggesting examples and products that are suitable for positive emotions.

[0247] 8. The server sends the adjusted results to the terminal and displays them to the user.

[0248] 9. Furthermore, the server identifies and recommends "web designers," "SEO specialists," and "hosting services" and "security solutions" based on the user's emotions and preferences.

[0249] In this way, the present invention realizes a system that supports the effective materialization of users' ideas. Furthermore, by providing suggestions tailored to the user's emotional state, it can offer more personalized support.

[0250] The following describes the processing flow.

[0251] Step 1:

[0252] The user enters specific ideas or wishes, such as "I want to do XX," into the device in text format. For example, they might enter, "I want to start a new marketing campaign."

[0253] Step 2:

[0254] The terminal sends input data to the server. At this time, the input data is packaged in an appropriate format, and a request is sent to the server.

[0255] Step 3:

[0256] The server receives input data and transfers it to the Natural Language Processing (NLP) module. The NLP module analyzes the text data and extracts multiple keywords.

[0257] Step 4:

[0258] The server uses an emotion engine to analyze the user's emotions from the input data. The emotion analysis module identifies the user's emotions and classifies them as positive, negative, or neutral.

[0259] Step 5:

[0260] The server searches the database for relevant past cases based on the extracted keywords. This search operation sends the keywords as a query to the database and retrieves matching cases.

[0261] Step 6:

[0262] The server also uses keywords to search the database for related products. This lists the products that match the keywords.

[0263] Step 7:

[0264] Based on the analysis results of the emotion engine, the server adjusts the suggestions for past examples and products that are best suited to the user's emotional state. For example, if the user is expressing negative emotions, the server prioritizes suggesting products and examples that provide a greater sense of security.

[0265] Step 8:

[0266] The server compiles tailored search results and product suggestions to create response data for the user. This response data includes relevant past cases, a list of products, and suggestions tailored based on sentiment.

[0267] Step 9:

[0268] The server sends response data to the terminal. The terminal receives this data and displays it appropriately to the user.

[0269] Step 10:

[0270] The server identifies the necessary experts and systems for implementation based on the user's preferences and sentiment analysis results. To this end, it sends queries to expert and system databases to retrieve relevant information.

[0271] Step 11:

[0272] The server compiles expert and system information and sends it to the terminal as an action plan for the user. The terminal receives this data and displays it to the user, indicating the next steps to take.

[0273] As a specific example, the processing when a user inputs "want to launch an online store" is shown below.

[0274] 1. The user inputs "want to launch an online store" into the terminal.

[0275] 2. The terminal sends the input data to the server.

[0276] 3. The server extracts keywords "online store" and "launch" using the NLP module.

[0277] 4. The server analyzes the user's sentiment with the sentiment engine and determines, for example, that the user is expressing a positive sentiment.

[0278] 5. The server searches for "launch cases of Shop A" and "launch cases of Shop B" as past cases.

[0279] 6. The server proposes "EC site construction tools" and "online payment systems" as commercial materials.

[0280] 7. Based on the sentiment analysis result, the server adjusts to preferentially propose cases and commercial materials suitable for positive sentiment.

[0281] 8. The server sends the adjusted result to the terminal and displays it to the user.

[0282] 9. Further, the server identifies and introduces "web designers", "SEO experts", as well as "hosting services" and "security solutions".

[0283] (Example 2)

[0284] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart device 14 is referred to as the "terminal".

[0285] When providing support to realize specific ideas and wishes of users, simply conducting keyword analysis and proposing related commercial materials is insufficient. The issue is that individualized proposals considering users' emotions are required. In ordinary systems, since uniform information is provided regardless of whether users have positive or negative emotions, user satisfaction is likely to decline. To solve this problem, a function for analyzing users' emotions and making optimal proposals based on that is necessary.

[0286] The specific processing by the specific processing unit 290 of the data processing device 12 in Embodiment 2 is realized by the following means. In this invention, the server includes means for receiving users' input data, means for analyzing the received input data and extracting keywords, means for analyzing users' emotions from the input data, means for searching for past cases using the extracted keywords, means for proposing related commercial materials using the extracted keywords, means for adjusting the proposals based on the emotion analysis results, means for providing the recommended past cases and commercial materials to the users, and means for identifying and introducing necessary experts and systems based on users' wishes. Thereby, it becomes possible to more individualize specific ideas and wishes of users and make optimal proposals according to emotions.

[0287] The "users' input data" is text-form information including specific ideas, wishes, requirements, etc. that users provide to the system.

[0288] The "means for extracting keywords" is a technology for identifying and extracting important words and phrases from the received users' input data.

[0289] The "means for searching for past cases" is a technology for identifying and obtaining related past cases from the database using the extracted keywords.

[0290] The "means for proposing commercial materials" is a technology for identifying and proposing related products and services from the database based on the extracted keywords.

[0291] "Means of providing users with recommended past cases and products" refers to technologies that present search and suggestion results to users.

[0292] "Means for identifying and introducing necessary experts and systems" refers to the technology of identifying relevant experts and systems based on the user's preferences and introducing them to the user.

[0293] "Methods for analyzing emotions" refer to technologies that identify and analyze a user's emotional state (positive, negative, etc.) from user input data.

[0294] "Methods for adjusting suggestions" refers to technologies that modify and adjust suggestions to the optimal content based on the user's emotions, using the results of sentiment analysis.

[0295] This invention is a system that helps users materialize their "I want to do XX" ideas, and further incorporates an emotion engine that recognizes the user's emotions and makes optimal suggestions based on those emotions. The system of this invention consists of a terminal, a server, a natural language processing module, an emotion engine, a database, and several related software modules.

[0296] The terminal is a device for users to input specific ideas and wishes. Through the terminal, users input their wishes in text format, such as "I want to do XX." For example, they might input "I want to start an online shop." The terminal then formats the user's input data into the appropriate format and sends it to the server.

[0297] When the server receives user input data, it forwards it to a natural language processing (NLP) module. Specific technologies that can be used include Python's NLTK library and Google's Cloud Natural Language API. The NLP module analyzes the text data and extracts important keywords. For example, it might extract keywords like "online shop" or "launch."

[0298] Simultaneously, the server uses an emotion engine to analyze the user's emotions from the input data. The emotion engine uses IBM Watson's Tone Analyzer API, among others, to determine whether the user is experiencing positive or negative emotions.

[0299] Next, the server searches the database for past relevant cases based on the extracted keywords. For example, it searches for "Shop A launch case study" or "Shop B launch case study." SQL queries or Elasticsearch (registered trademark) can be used here. At the same time, it also searches the database for related products based on the keywords. For example, "EC site construction tools" or "online payment systems" may be retrieved.

[0300] Furthermore, the server adjusts its recommendations based on the results of sentiment analysis. For example, if a user has positive emotions, it prioritizes suggesting success stories and innovative products, while if they have negative emotions, it adjusts its recommendations to prioritize safe and reliable examples and products.

[0301] Finally, the server compiles the refined search results and product recommendations and generates response data. This data includes relevant past cases, a list of products, and sentiment-based recommendations that should be provided to the user. The user then receives the final recommendations through their device.

[0302] Furthermore, based on the user's preferences and sentiment analysis results, the server identifies and recommends the necessary experts and systems to carry out the task. For example, it may recommend "web designers," "SEO specialists," "hosting services," and "security solutions." This allows users to receive comprehensive support, including specific implementation steps.

[0303] As a specific example, consider the case where a user inputs "want to launch an online store". This information input by the user from the terminal is sent to the server. The server extracts keywords such as "online store" and "launch" using the NLP module, and determines that the user's sentiment is positive using the sentiment engine. Then, it searches for past "launch cases of Store A" and "launch cases of Store B", and proposes an "EC site construction tool" and an "online payment system". Finally, based on the sentiment analysis result, the proposal is adjusted, and the adjusted result is sent to the terminal and displayed to the user. Also, "web designers" and "SEO experts" are introduced.

[0304] By using this system, the user's ideas can be specifically supported, and an optimal proposal according to the sentiment can be made. Examples of prompt sentences input to the generative AI model include "I want to launch an online store. What tools and support are needed? Also, if there are past successful cases based on my idea, please let me know."

[0305] The flow of the specific process in Example 2 will be described using FIG. 13.

[0306] Step 1:

[0307] The user inputs an idea into the terminal.

[0308] Input: The user inputs text data such as "want to do ○○" into the terminal.

[0309] Specific operation: The user inputs "want to launch an online store" into the input field of the terminal.

[0310] Output: The user's idea is saved as text data in the terminal.

[0311] Step 2:

[0312] The terminal sends the entered text data to the server.

[0313] Input: User text data saved on the device.

[0314] Specific operation: The terminal formats the input data into an appropriate format (e.g., JSON format), encrypts it, and sends it to the server over the network.

[0315] Output: User text data sent to the server.

[0316] Step 3:

[0317] The server receives the text data and transfers it to the natural language processing module.

[0318] Input: User text data sent to the server.

[0319] Specific operation: The server parses the received text data using Python's NLTK library or the Google Cloud Natural Language API.

[0320] Output: Extracted keywords (e.g., "online shop", "launch").

[0321] Step 4:

[0322] The server uses an emotion engine to analyze the user's emotions.

[0323] Input: User's text data.

[0324] Specific operation: The server uses IBM Watson's Tone Analyzer API to analyze the input data and determine whether the sentiment is positive or negative.

[0325] Output: User's emotional state (e.g., positive).

[0326] Step 5:

[0327] The server uses the extracted keywords to search the database for past cases.

[0328] Input: Extracted keywords.

[0329] Specific operation: The server uses SQL queries and Elasticsearch to identify and retrieve relevant historical cases from the database.

[0330] Output: A list of past case studies as search results (e.g., "Shop A launch case study", "Shop B launch case study").

[0331] Step 6:

[0332] The server uses keywords to search the database for related products.

[0333] Input: Extracted keywords.

[0334] Specific operation: The server uses SQL queries and Elasticsearch to retrieve relevant product information.

[0335] Output: A list of related products (e.g., "EC site building tools", "online payment systems").

[0336] Step 7:

[0337] The server adjusts the suggestions based on the sentiment analysis results.

[0338] Input: Sentiment analysis results, list of past cases, list of products.

[0339] Specific operation: The server adjusts the priority of suggested products based on whether the user has positive or negative emotions. For example, if the user has positive emotions, innovative products will be prioritized.

[0340] Output: Revised proposal.

[0341] Step 8:

[0342] The server aggregates the adjusted search results and product suggestions to generate response data.

[0343] Input: Adjusted proposal content.

[0344] Specific operation: The server compiles relevant past cases and product lists, and creates response data that includes sentiment-based, tailored suggestions.

[0345] Output: Response data to be provided to the user.

[0346] Step 9:

[0347] The terminal receives response data from the server and displays it to the user.

[0348] Input: Response data from the server.

[0349] Specific operation: The device analyzes the response data it receives and displays it in a user-friendly format. For example, it may display the data through a dedicated app or web interface.

[0350] Output: The suggested content that the user will view.

[0351] (Application Example 2)

[0352] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0353] Currently, there is a lack of systems that provide optimal routes and entertainment content based on the user's emotions and specific preferences when using autonomous vehicles. As a result, user dissatisfaction and anxiety during rides increase, leading to a decline in the overall ride experience. Furthermore, conventional systems are limited to simple suggestions based on user input data, making it difficult to provide advanced customization that addresses individual emotions and needs.

[0354] In Application Example 2, the identification processing by the identification processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving user input data, means for analyzing the received input data and extracting keywords, means for analyzing the user's emotions from the received input data, means for searching past cases using the extracted keywords, means for suggesting related products using the extracted keywords, means for providing the user with the recommended past cases and products, means for adjusting the suggested content based on the emotion analysis results, means for providing suggestions regarding the use of autonomous vehicles, and means for identifying and introducing necessary experts and systems based on the user's wishes. This makes it possible to suggest optimal routes and entertainment content that correspond to the user's emotions and specific wishes, thereby improving the overall riding experience.

[0355] "User input data" refers to information such as text, audio, and images that users input via their devices.

[0356] "Means for extracting keywords" refers to functions or technologies that analyze user input data to identify important words and phrases.

[0357] "Means of searching past cases" refers to functions or technologies for searching previously successful cases and related information from a stored database.

[0358] "Means of proposing products" refers to functions or technologies that propose relevant products or services to users based on extracted keywords.

[0359] "Means of providing to the user" refers to the functions or technologies that allow the server to display analysis results and suggestions on the user's terminal.

[0360] "Means of analyzing emotions" refers to functions or technologies for identifying a user's emotional state from user input data.

[0361] "Means for adjusting the content of suggestions" refers to a function or technology for selecting and adjusting the most suitable suggestions for the user based on the results of sentiment analysis.

[0362] "Means of providing suggestions regarding the use of autonomous vehicles" refers to functions or technologies that suggest optimal ways to use autonomous vehicles, routes, and entertainment content based on the user's wishes and emotions.

[0363] "Means for identifying and introducing experts and systems" refers to functions or technologies for selecting and introducing appropriate experts and systems to users based on their preferences.

[0364] This invention relates to a system for providing optimal suggestions based on the user's emotions and wishes when using an autonomous vehicle. The specific methods and means for realizing this system are described below.

[0365] System Overview

[0366] The system primarily consists of smartphones, servers, and terminals. Users input their travel preferences and feelings using their smartphones, and this data is sent to the server. The server analyzes the data and makes optimal suggestions based on the user's feelings and preferences.

[0367] Hardware used

[0368] Smartphone: A device used to receive user input.

[0369] Server: A central processing unit used for data analysis, sentiment analysis, keyword extraction, past case studies, and product / service recommendations.

[0370] Software used

[0371] Natural Language Processing (NLP) Module: A library for extracting and analyzing keywords from user input data. Specifically, Python's TextBlob library is used.

[0372] Sentiment Analysis Engine: A module for analyzing emotions from user text data. It can obtain emotional polarity.

[0373] Explanation of the process

[0374] 1. User Input: The user uses their smartphone to input their preferences, such as "where they want to go" and "what they want to do," in text format.

[0375] 2. Data Transmission: The smartphone sends the user's input data to the server. The data is packaged in the appropriate format before being transmitted.

[0376] 3. Data Analysis: The server analyzes the received data using a natural language processing (NLP) module and extracts keywords. For example, "tourist spots" and "relaxation" might be extracted.

[0377] 4. Emotion Analysis: The server uses an emotion engine to analyze the user's input data to determine their emotions. Positive, negative, and neutral emotions are identified.

[0378] 5. Searching past cases: The server searches the database for relevant past cases based on the extracted keywords.

[0379] 6. Product Proposal: Based on the extracted keywords, search the database for relevant products (e.g., tourist spot guides, relaxation music, etc.) and propose them.

[0380] 7. Adjusting Suggestions: Based on the emotion analysis results, select and adjust suggestions that are best suited to the user's emotions. Prioritize active suggestions for positive emotions, and suggestions that provide comfort and reassurance for negative emotions.

[0381] 8. Delivery of results: The server sends the adjusted results to the smartphone and displays them to the user.

[0382] Examples of specific cases and prompt statements

[0383] Specific example

[0384] If a user enters "I want to do some leisurely sightseeing today," and the sentiment analysis results are positive, then suggestions such as "popular nearby tourist spots" and "hit music" will be displayed.

[0385] If a user enters "I'm tired today and want to relax," and the sentiment analysis results in a negative tone, suggestions such as "a scenic drive through a forest" or "relaxing music" will be provided.

[0386] Example of a prompt

[0387] text

[0388] User: "Today I want to take it easy and do some sightseeing."

[0389] Server: "Based on the user's emotional state, we will make the following suggestions: popular nearby tourist attractions, hit music."

[0390] In this way, the system proposes the optimal way to use the autonomous vehicle based on user input and emotion analysis results, providing a better riding experience.

[0391] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0392] Step 1:

[0393] User input: The user uses their smartphone to input their wishes, such as "where they want to go" and "what they want to do," in text format.

[0394] Specific action: The user types "I want to take it easy and sightsee today" into the input field and presses the submit button.

[0395] Input: User-generated text (e.g., "I want to take it easy and sightsee today")

[0396] Output: Text data sent from a smartphone

[0397] Step 2:

[0398] Data transmission: The device (smartphone) sends user input data to the server. The data is packaged in an appropriate format, such as JSON, before being transmitted.

[0399] Specific operation: The smartphone packages the input data in JSON format and sends it to the server via an HTTPS request.

[0400] Input: User input data (text format)

[0401] Output: Packaged data received by the server

[0402] Step 3:

[0403] Data Analysis: The server analyzes the received data using a natural language processing (NLP) module and extracts keywords.

[0404] Specific operation: The server's Python script uses the TextBlob library to extract keywords such as "tourism" and "relaxing".

[0405] Input: Packaged user input data

[0406] Output: Extracted keywords (e.g., "tourism", "relaxing")

[0407] Step 4:

[0408] Emotion Analysis: The server uses an emotion engine to analyze the user's input data to determine their emotions. Positive, negative, neutral, and other emotions are identified.

[0409] Specific operation: The server script uses TextBlob's sentiment analysis function to determine a positive sentiment from the text "I want to take it easy and sightsee today."

[0410] Input: User input data (text format)

[0411] Output: Sentiment score (e.g., positive)

[0412] Step 5:

[0413] Searching past cases: The server searches the database for relevant past cases based on the extracted keywords.

[0414] Specific operation: The server executes an SQL statement to retrieve past success stories related to "tourism" and "relaxation" from the database.

[0415] Input: Extracted keywords (e.g., "tourism", "relaxing")

[0416] Output: Relevant past examples (e.g., "Success story of tourist spot A")

[0417] Step 6:

[0418] Product Suggestion: Based on the extracted keywords, the server searches the database for relevant products (e.g., tourist spot guides, relaxation music, etc.) and suggests them.

[0419] Specific operation: The server executes the SQL statement again, searching for and listing relevant products (e.g., "tourist attraction guides").

[0420] Input: Extracted keywords (e.g., "tourism", "relaxing")

[0421] Output: A list of related products (e.g., "Tourist Spot Guide")

[0422] Step 7:

[0423] Suggestion Adjustment: Based on sentiment analysis results, the server selects and adjusts suggestions to best suit the user's emotions.

[0424] Specific operation: The server performs a step of generating a list suitable for positive emotions based on the emotion score. The contents of the list are automatically adjusted.

[0425] Input: Sentiment score (e.g., positive), list of related products.

[0426] Output: A list of products suitable for specific emotions.

[0427] Step 8:

[0428] Result delivery: The server packages the adjusted results, sends them to the smartphone, and displays them to the user.

[0429] Specific operation: The server packages the results list in JSON format and sends it to the smartphone via an HTTPS request. The smartphone receives the data and displays it in the user interface.

[0430] Input: Adjusted results (list of products, past examples)

[0431] Output: Displayed to the user (e.g., "Success Story of Tourist Spot A," "Tourist Spot Guide")

[0432] In this way, the system can suggest the optimal way to use the autonomous vehicle based on user input data and emotion analysis results, thereby improving the user's riding experience.

[0433] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0434] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0435] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0436] [Second Embodiment]

[0437] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0438] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0439] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0440] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0441] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0442] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0443] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0444] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0445] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0446] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0447] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0448] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0449] Modes for carrying out the invention

[0450] This invention relates to a system that streamlines the process of users materializing their ideas, such as "I want to do XX." This system begins with the user submitting input data, provides past examples and products related to the idea, and further includes functions to identify and introduce the necessary experts and systems for implementation.

[0451] Program processing

[0452] User actions

[0453] The user uses their device to input a specific idea in text format. For example, they might type, "I want to start a new marketing campaign."

[0454] Sending data

[0455] The terminal sends this input data to the server. The input data is a concrete expression of the user's wishes and ideas.

[0456] Data analysis

[0457] The server receives the input data and analyzes it using natural language processing (NLP) techniques. As a result of the analysis, several keywords are extracted from the data. For example, "marketing" and "campaign" might be extracted.

[0458] Searching past cases

[0459] Using the keywords obtained from the analysis, the server searches the database for relevant past cases. For example, "Campaign A" and "Campaign B" may be obtained as search results.

[0460] Product proposals

[0461] The server also searches its database for related products based on keywords and suggests them to the user. For example, "SNS advertising tools" or "email marketing tools" might be suggested.

[0462] Providing results

[0463] The server compiles past case studies and product suggestions and provides them to the user. This result is displayed to the user via their terminal.

[0464] Introduction of Experts and Systems

[0465] Furthermore, the server identifies and recommends the necessary experts and systems based on the user's preferences. For example, it might recommend "marketing personnel," "advertising specialists," "CRM systems," and "data analysis tools" needed for a marketing campaign.

[0466] Specific example

[0467] For example, consider a case where a user enters "I want to start an online shop."

[0468] 1. The user enters "I want to set up an online shop" into their device.

[0469] 2. The terminal sends the input data to the server.

[0470] 3. The server uses NLP to extract the keywords "online shop" and "launch".

[0471] 4. The server searches for past cases such as "Shop A launch case study" and "Shop B launch case study".

[0472] 5. The server proposes "EC site building tools" and "online payment systems" as products.

[0473] 6. The server compiles this information, sends it to the terminal, and displays it to the user.

[0474] 7. Furthermore, the server identifies and introduces specialists such as "web designers" and "SEO experts," as well as systems such as "hosting services" and "security solutions."

[0475] In this way, the present invention realizes a system that supports the effective realization of users' ideas. By using this system, users can acquire the information and resources necessary to advance their projects quickly and efficiently.

[0476] The following describes the processing flow.

[0477] Step 1:

[0478] The user enters specific ideas or wishes, such as "I want to do XX," into the device in text format. For example, they might enter, "I want to start a new marketing campaign."

[0479] Step 2:

[0480] The terminal sends user input data to the server. At this time, the input data is packaged in an appropriate format.

[0481] Step 3:

[0482] The server receives input data and transfers it to a natural language processing (NLP) module for text analysis.

[0483] Step 4:

[0484] The server uses an NLP module to analyze the input data and extract keywords. For example, "marketing" and "campaign" might be extracted.

[0485] Step 5:

[0486] The server searches the database for relevant past cases based on the extracted keywords. This retrieves, for example, "Campaign A" and "Campaign B".

[0487] Step 6:

[0488] The server uses the extracted keywords to search the database for related products and list them. For example, "SNS advertising tools" and "email marketing tools" might be suggested.

[0489] Step 7:

[0490] The server compiles search results and product suggestions, creating response data to provide to the user. This data includes a list of relevant past cases and products.

[0491] Step 8:

[0492] The server sends response data to the terminal. The terminal receives this data and displays it appropriately to the user.

[0493] Step 9:

[0494] The server identifies the necessary experts and systems for implementation based on the user's requests. For example, it searches for "marketing specialists," "advertising specialists," "CRM systems," and "data analysis tools."

[0495] Step 10:

[0496] The server compiles expert and system information and sends it to the terminal as data indicating the next action for the user. The terminal receives this data and displays it to the user.

[0497] (Example 1)

[0498] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0499] The process of transforming users' abstract ideas into concrete ideas is often time-consuming, laborious, and difficult to carry out efficiently. In particular, quickly finding past success stories and relevant resources is a challenge. Furthermore, the process of identifying and introducing necessary experts and systems is cumbersome, resulting in insufficient support for users to effectively advance their projects. A system that addresses these challenges is needed.

[0500] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0501] In this invention, the server includes means for receiving user input data, means for analyzing the received input data and extracting key keywords, means for searching past cases using the extracted keywords, means for suggesting relevant resources using the extracted keywords, means for providing the user with the recommended past cases and resources, and means for identifying and introducing necessary experts and systems based on the user's preferences. This makes it possible for users to quickly and efficiently materialize their abstract ideas and rapidly acquire the necessary information and resources.

[0502] "Input data" refers to information entered by the user in text format, such as ideas and requests.

[0503] "Analysis" is the process of extracting key information and keywords from input data.

[0504] A "keyword" is a word or phrase that represents important information extracted from the input data.

[0505] "Past examples" refer to information about previously successful projects and ideas stored in the database.

[0506] "Resources" is a general term for tools and services that help users realize their ideas.

[0507] An "expert" is a person who possesses advanced knowledge and experience in a particular field.

[0508] A "system" is the technical infrastructure and tools necessary to realize an idea, which are identified according to the user's needs.

[0509] "Suggesting" means that the server selects relevant resources and experts based on the user's needs and introduces them to the user.

[0510] Modes for carrying out the invention

[0511] This invention relates to a system that streamlines the process of materializing a user's idea of ​​"I want to do XX." This system begins with the user submitting input data, provides past examples and resources related to the idea, and further includes functions to identify and introduce the necessary experts and systems for implementation.

[0512] The server plays a central role in this system, working in conjunction with users and terminals to collect, analyze, and provide data. The specific operations at each step are described below.

[0513] 1. Receiving input data

[0514] The user uses a device to input specific ideas in text format. For example, they might type "I want to start a new marketing campaign." Typically, the user enters their idea into the text box displayed on the device and clicks the submit button. At this point, the input data expresses the idea concretely.

[0515] 2. Sending data

[0516] The terminal sends the input data to the server. This process uses the HTTP protocol and involves a POST request. Specifically, a request body containing the user's idea is sent to the URL "https: / / example.com / api / submit".

[0517] 3. Analysis using natural language processing

[0518] The server analyzes the received data using natural language processing (NLP) techniques. The server uses an NLP library (e.g., SpaCy or NLTK) deployed on a Python program to extract key keywords from the user's input text. This process includes text tokenization and part-of-speech tagging. For example, from the input "I want to start a new marketing campaign," the keywords "marketing" and "campaign" are extracted.

[0519] 4. Search past cases

[0520] Next, the server searches its internal database for relevant past cases based on the extracted keywords. This search process is performed using SQL queries. For example, a query such as "SELECT FROM cases WHERE keywords LIKE '%marketing%' AND keywords LIKE '%campaign%'" is executed, and relevant cases such as "Campaign A" and "Campaign B" are retrieved.

[0521] 5. Product Proposal

[0522] The server similarly searches the database for relevant resources based on keywords. SQL queries retrieve a list of relevant tools and services. For example, a query like "SELECT FROM products WHERE keywords LIKE '%marketing%' AND keywords LIKE '%campaign%'" is executed, and "SNS advertising tools" and "email marketing tools" are suggested.

[0523] 6. Providing results

[0524] The server compiles past cases and resource suggestions and provides them to the user. This result is created in HTML format and sent to the user's device. The results are displayed in the user's browser, allowing them to view detailed information about the suggested cases and tools. For example, the results screen might include a "Detailed Description of Campaign A" and a "List of Recommended Tools."

[0525] 7. Introduction to Experts and Systems

[0526] Furthermore, the server identifies and recommends the necessary experts and systems based on the user's preferences. Expert and system information is also retrieved from the database. For example, executing "SELECT FROM experts WHERE expertise LIKE '%marketing%'" will list "marketing specialists" and "advertising experts." Based on this, the user is introduced to contact information for experts such as "web designers" and "SEO specialists," as well as systems such as "hosting services" and "security solutions."

[0527] By using this system, users can acquire the information and resources necessary to advance their projects quickly and efficiently.

[0528] Specific example

[0529] For example, consider a case where a user enters "I want to start an online shop."

[0530] 1. The user enters "I want to set up an online shop" into their device.

[0531] 2. The terminal sends the input data to the server.

[0532] 3. The server uses NLP to extract the keywords "online shop" and "launch".

[0533] 4. The server searches for past cases such as "Shop A launch case study" and "Shop B launch case study".

[0534] 5. The server proposes "EC site building tools" and "online payment systems" as resources.

[0535] 6. The server compiles this information, sends it to the terminal, and displays it to the user.

[0536] 7. Furthermore, the server identifies and introduces specialists such as "web designers" and "SEO experts," as well as systems such as "hosting services" and "security solutions."

[0537] The following are some specific examples of prompt statements that can be input into a generative AI model.

[0538] "We need ideas to develop new products."

[0539] "Please tell me how to start an effective marketing campaign."

[0540] By using these prompts, users can effectively utilize the system.

[0541] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0542] Step 1:

[0543] The user uses their device to input specific ideas in text format. For example, they might input, "I want to start a new marketing campaign." The input data is entered into a text box, and the input is completed by pressing the submit button. Input is performed by the user entering their idea into the text box on their device and clicking the submit button. This generates the user's idea as text data.

[0544] Step 2:

[0545] The terminal sends text data entered by the user to the server. The HTTP protocol is used for data transmission, and a POST request is made. Specifically, the entered text data is included in the request body and sent to the URL "https: / / example.com / api / submit". The input for this step is the text data entered by the user, and the output is the completion of data transmission to the server.

[0546] Step 3:

[0547] The server analyzes the received text data using natural language processing (NLP) techniques. The server uses NLP libraries such as Python's SpaCy or NLTK to tokenize the text data and extract key keywords. For example, from the text "I want to start a new marketing campaign," it extracts the keywords "marketing" and "campaign." The input for this step is the text data sent to the server, and the output is the extracted keywords.

[0548] Step 4:

[0549] The server uses the extracted keywords to search its internal database for relevant past cases. This search uses SQL queries. For example, it might execute a query like "SELECT FROM cases WHERE keywords LIKE '%marketing%' AND keywords LIKE '%campaign%'" to retrieve the relevant cases. The input for this step is the extracted keywords, and the output is the relevant past case data.

[0550] Step 5:

[0551] The server then searches the database for relevant resources based on keywords. SQL queries are used for this search as well. For example, a query like "SELECT FROM resources WHERE keywords LIKE '%marketing%' AND keywords LIKE '%campaign%'" is executed to retrieve the relevant tools and services. The input for this step is the extracted keywords, and the output is the relevant resource data.

[0552] Step 6:

[0553] The server compiles past case studies and resource data based on keywords and generates results. These results are created in HTML format and sent to the user's terminal. For example, the results screen might include a "Detailed Description of Campaign A" and a "List of Recommended Tools." The input for this step is past case study data and resource data, and the output is the resulting HTML data.

[0554] Step 7:

[0555] Furthermore, the server identifies and recommends the necessary experts and systems based on the user's preferences. It retrieves expert and system information from the database using SQL queries. For example, it might execute "SELECT FROM experts WHERE expertise LIKE '%marketing%'" to list relevant experts. The input for this step is keywords based on the user's preferences, and the output is expert and system information.

[0556] Through the steps outlined above, this system can quickly and efficiently materialize users' ideas and provide the necessary resources.

[0557] (Application Example 1)

[0558] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0559] In today's world, even if users have concrete ideas, it is difficult to quickly and efficiently gather the information and resources necessary to realize those ideas. Furthermore, finding past success stories, relevant products, and appropriate experts and systems requires a tremendous amount of time and effort. In addition, it is difficult for users to generate prompts using AI models to find the appropriate approach. To solve these challenges, there is a need for a means for users to obtain the necessary information and resources quickly and efficiently.

[0560] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0561] In this invention, the server includes means for receiving user input data, means for analyzing the received input data and extracting keywords, means for searching past cases using the extracted keywords, means for suggesting relevant products using the extracted keywords, means for providing the user with the recommended past cases and products, means for identifying and introducing necessary experts and systems based on the user's wishes, means for generating appropriate prompt sentences using a generative AI model based on the input data, and means for suggesting relevant past cases and products based on the generated prompt sentences. This makes it possible for the user to acquire the necessary information and resources efficiently in a short amount of time, and the process of materializing their ideas is greatly simplified.

[0562] "Means for receiving user input data" refers to interfaces or devices that allow users to input their ideas and wishes in text or other formats.

[0563] "Methods for analyzing received input data and extracting keywords" refers to a system that uses natural language processing technology to identify important words and phrases from user input data and extract them.

[0564] "A means of searching for past cases using extracted keywords" refers to a system that searches for past achievements and cases related to the extracted keywords from information sources such as databases.

[0565] "A method for proposing related products using extracted keywords" refers to a system that selects and proposes products and services that are suitable for the user's needs based on keywords.

[0566] "Means of providing users with recommended past cases and products" refers to a system that provides users with information on past cases and suggested products obtained as search results, allowing them to review the information.

[0567] "A means of identifying and introducing necessary experts and systems based on user requests" refers to a system that selects the necessary experts and systems to address the user's specific requests and ideas, and provides information on them.

[0568] "A means of generating appropriate prompt sentences using a generative AI model based on input data" refers to a system that automatically creates appropriate instructional or question-based text using a generative AI model based on data input by the user.

[0569] "A means of suggesting relevant past cases and products based on generated prompt sentences" refers to a system that uses the generated prompt sentences to search for and suggest even more relevant past cases and products.

[0570] This invention provides a system that efficiently supports the process of realizing a user's specific idea. The embodiments for carrying out this invention will be described in detail below.

[0571] Hardware and software to be used

[0572] Hardware: Cloud servers, smartphones

[0573] Software: React Native (frontend), Python, Flask (backend), NLTK (natural language processing), MongoDB (database management), generative AI model (prompt generation)

[0574] System Configuration

[0575] 1. User actions

[0576] Users use a smartphone application to input their ideas in text format. For example, they might enter specific requests such as, "I want to create a new content series."

[0577] 2. Sending data

[0578] User input data is sent from the smartphone to the cloud server. This communication is performed via API calls using the HTTPS protocol.

[0579] 3. Data Analysis

[0580] The cloud server uses Python and Flask to analyze the input data it receives. Here, natural language processing (NLP) techniques are used, and important keywords are extracted from the input data using the NLTK library.

[0581] 4. Prompt sentence generation using a generative AI model

[0582] Based on the extracted keywords, a generative AI model is used to generate appropriate prompt sentences. These prompt sentences are then used for subsequent search and recommendation processes.

[0583] 5. Search for past cases and products

[0584] The generated prompt is used to search the database stored in MongoDB for relevant past cases and product information.

[0585] 6. Providing results

[0586] Past case studies and suggested products obtained as search results are sent from the server to the smartphone and displayed for the user to review.

[0587] 7. Introduction of Experts and Systems

[0588] Based on the user's preferences, the necessary experts and systems for project implementation are identified and introduced. This information is also displayed on the smartphone.

[0589] Specific example

[0590] For example, if a user enters "I want to create a new podcast series," the process would be as follows:

[0591] 1. User actions

[0592] The user types "I want to create a new podcast series" into their smartphone.

[0593] 2. Sending data

[0594] The text data entered by the user is sent to the cloud server.

[0595] 3. Data Analysis

[0596] The server extracts keywords such as "podcast" and "series."

[0597] 4. Prompt sentence generation using a generative AI model

[0598] Based on the extracted keywords, the AI ​​model generates a prompt message that says, "Please recommend examples of successful podcast series and the necessary equipment."

[0599] 5. Search for past cases and products

[0600] The generated prompt is used to search MongoDB for relevant past cases (e.g., successful podcast series) and products (e.g., recording equipment).

[0601] 6. Providing results

[0602] The search results are displayed on the user's smartphone.

[0603] 7. Introduction of Experts and Systems

[0604] Furthermore, information from experts such as audio engineers and digital marketing specialists will also be provided.

[0605] Example of a prompt:

[0606] "I have an idea for a new podcast series. I'd like some examples of successful podcast series from the past and recommendations for necessary equipment."

[0607] This system allows users to quickly and efficiently acquire the necessary information and resources, and significantly simplifies the process of bringing their ideas to life.

[0608] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0609] Step 1:

[0610] The user uses a smartphone application to input a specific idea in text format. An example input is "I want to create a new podcast series." This input data is then sent to the server.

[0611] Step 2:

[0612] The server analyzes the received input data. Python and Flask are used here. Specifically, the NLTK natural language processing (NLP) library is used to extract important keywords from the input data. For example, keywords such as "podcast" and "series" are extracted.

[0613] Step 3:

[0614] The server uses a generative AI model to generate appropriate prompt sentences based on the extracted keywords. The generative AI model generates a prompt sentence such as, "I want to create a new podcast series. I would like recommendations for successful case studies and necessary equipment that would be helpful in this situation."

[0615] Step 4:

[0616] The server uses the generated prompt to search the database (MongoDB) for relevant past cases. The keywords included in the generated prompt are used as the search query. For example, successful podcast series cases might be retrieved as search results.

[0617] Step 5:

[0618] Similarly, the server uses the generated prompt to search the database for relevant products. The keywords included in the prompt are used as the search query. For example, recommended recording equipment or streaming platforms may be retrieved as search results.

[0619] Step 6:

[0620] The server aggregates search results and provides them to the user. Specifically, information on successful podcast series examples and recommended products is sent to the user's smartphone. This information is then displayed on the user's smartphone.

[0621] Step 7:

[0622] Based on the user's preferences, the server identifies and recommends further necessary experts and systems. For example, information on audio engineers, digital marketing specialists, and related systems is provided to the user. This information is also displayed on the smartphone.

[0623] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0624] Modes for carrying out the invention

[0625] This invention is a system that helps users materialize their "I want to do XX" ideas, and further incorporates an emotion engine that recognizes the user's emotions and makes optimal suggestions based on those emotions. The system of this invention consists of a number of different processing steps.

[0626] Program processing

[0627] User actions

[0628] The user uses their device to input specific ideas or wishes in text format, such as "I want to do XX." For example, they might input, "I want to start a new marketing campaign."

[0629] Sending data

[0630] The terminal sends input data to the server. During this process, the input data is packaged in an appropriate format before being sent.

[0631] Data analysis

[0632] The server receives user input data and forwards it to a natural language processing (NLP) module for text analysis. This analysis extracts multiple keywords. For example, "marketing" and "campaign" might be extracted.

[0633] Emotional analysis

[0634] Simultaneously, the server uses an emotion engine to analyze the user's emotions from the input data. This emotion analysis determines whether the user is expressing positive or negative emotions.

[0635] Searching past cases

[0636] The server uses keywords to search the database for relevant past cases. For example, it might search for "Campaign A" or "Campaign B".

[0637] Product proposals

[0638] The server then searches its database for related products based on the same keywords and lists them. For example, "SNS advertising tools" and "email marketing tools" might be suggested.

[0639] Adjusting the proposal

[0640] Based on the analysis results of the emotion engine, the server adjusts the suggestions for past examples and products that are best suited to the user's emotional state. For example, if the user is expressing negative emotions, the server prioritizes suggesting products and examples that provide a greater sense of security.

[0641] Providing results

[0642] The server compiles tailored search results and product recommendations, creating response data to provide to the user. This data includes relevant past cases, product lists, and sentiment-based recommendations.

[0643] Introduction of Experts and Systems

[0644] Furthermore, based on the user's preferences and sentiment analysis results, the server identifies the necessary experts and systems for implementation. For example, "marketing personnel," "advertising specialists," "CRM systems," and "data analysis tools" may be suggested.

[0645] Specific example

[0646] For example, consider a case where a user enters "I want to start an online shop."

[0647] 1. The user enters "I want to set up an online shop" into their device.

[0648] 2. The device sends data to the server.

[0649] 3. The server uses NLP to extract the keywords "online shop" and "launch".

[0650] 4. The server simultaneously analyzes the user's emotions using an emotion engine. This analysis can, for example, determine if the user is expressing positive emotions.

[0651] 5. The server searches for past examples such as "Shop A launch case study" and "Shop B launch case study".

[0652] 6. The server proposes "EC site building tools" and "online payment systems" as products.

[0653] 7. Based on the emotion analysis results, the server adjusts its settings to prioritize suggesting examples and products that are suitable for positive emotions.

[0654] 8. The server sends the adjusted results to the terminal and displays them to the user.

[0655] 9. Furthermore, the server identifies and recommends "web designers," "SEO specialists," and "hosting services" and "security solutions" based on the user's emotions and preferences.

[0656] In this way, the present invention realizes a system that supports the effective materialization of users' ideas. Furthermore, by providing suggestions tailored to the user's emotional state, it can offer more personalized support.

[0657] The following describes the processing flow.

[0658] Step 1:

[0659] The user enters specific ideas or wishes, such as "I want to do XX," into the device in text format. For example, they might enter, "I want to start a new marketing campaign."

[0660] Step 2:

[0661] The terminal sends input data to the server. At this time, the input data is packaged in an appropriate format, and a request is sent to the server.

[0662] Step 3:

[0663] The server receives input data and transfers it to the natural language processing (NLP) module. The NLP module analyzes the text data and extracts multiple keywords.

[0664] Step 4:

[0665] The server uses an emotion engine to analyze the user's emotions from the input data. The emotion analysis module identifies the user's emotions and classifies them as positive, negative, or neutral.

[0666] Step 5:

[0667] The server searches the database for relevant past cases based on the extracted keywords. This search operation sends the keywords as a query to the database and retrieves matching cases.

[0668] Step 6:

[0669] The server also uses keywords to search the database for related products. This lists the products that match the keywords.

[0670] Step 7:

[0671] Based on the analysis results of the emotion engine, the server adjusts the suggestions for past examples and products that are best suited to the user's emotional state. For example, if the user is expressing negative emotions, the server prioritizes suggesting products and examples that provide a greater sense of security.

[0672] Step 8:

[0673] The server compiles tailored search results and product suggestions to create response data for the user. This response data includes relevant past cases, a list of products, and suggestions tailored based on sentiment.

[0674] Step 9:

[0675] The server sends response data to the terminal. The terminal receives this data and displays it appropriately to the user.

[0676] Step 10:

[0677] The server identifies the necessary experts and systems for implementation based on the user's preferences and sentiment analysis results. To this end, it sends queries to expert and system databases to retrieve relevant information.

[0678] Step 11:

[0679] The server compiles expert and system information and sends it to the terminal as an action plan for the user. The terminal receives this data and displays it to the user, indicating the next steps to take.

[0680] As a concrete example, the following shows how to process a user who enters "I want to start an online shop."

[0681] 1. The user enters "I want to set up an online shop" into their device.

[0682] 2. The terminal sends the input data to the server.

[0683] 3. The server uses an NLP module to extract the keywords "online shop" and "launch".

[0684] 4. The server uses an emotion engine to analyze the user's emotions and determine, for example, whether they are expressing positive emotions.

[0685] 5. The server searches for past case studies such as "Shop A launch case study" and "Shop B launch case study".

[0686] 6. The server proposes "EC site building tools" and "online payment systems" as products.

[0687] 7. Based on the emotion analysis results, the server adjusts its settings to prioritize suggesting examples and products that are suitable for positive emotions.

[0688] 8. The server sends the adjusted results to the terminal and displays them to the user.

[0689] 9. Furthermore, the server identifies and recommends "web designers," "SEO specialists," and "hosting services" and "security solutions."

[0690] (Example 2)

[0691] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0692] When supporting users in realizing their specific ideas and desires, simply performing keyword analysis and suggesting related products is insufficient; a challenge lies in the need for personalized suggestions that take into account the user's emotions. Conventional systems provide uniform information regardless of whether the user has positive or negative emotions, which tends to lower user satisfaction. To solve this problem, a function is needed that analyzes the user's emotions and provides optimal suggestions based on that analysis.

[0693] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving user input data, means for analyzing the received input data and extracting keywords, means for analyzing the user's emotions from the input data, means for searching past cases using the extracted keywords, means for suggesting related products using the extracted keywords, means for adjusting the suggestions based on the emotion analysis results, means for providing the user with the recommended past cases and products, and means for identifying and introducing necessary experts and systems based on the user's wishes. This makes it possible to further individualize the user's specific ideas and wishes and make optimal suggestions that respond to their emotions.

[0694] "User input data" refers to text-based information that includes specific ideas, wishes, and requests that users provide to the system.

[0695] "Keyword extraction methods" refer to technologies that identify and extract important words and phrases from user input data.

[0696] "Methods for searching past cases" refers to techniques that use extracted keywords to identify and retrieve relevant past cases from a database.

[0697] "Methods for proposing products and services" refers to techniques that identify and propose relevant products and services from a database based on extracted keywords.

[0698] "Means of providing users with recommended past cases and products" refers to technologies that present search and suggestion results to users.

[0699] "Means for identifying and introducing necessary experts and systems" refers to the technology of identifying relevant experts and systems based on the user's preferences and introducing them to the user.

[0700] "Methods for analyzing emotions" refer to technologies that identify and analyze a user's emotional state (positive, negative, etc.) from user input data.

[0701] "Methods for adjusting suggestions" refers to technologies that modify and adjust suggestions to the optimal content based on the user's emotions, using the results of sentiment analysis.

[0702] This invention is a system that helps users materialize their "I want to do XX" ideas, and further incorporates an emotion engine that recognizes the user's emotions and makes optimal suggestions based on those emotions. The system of this invention consists of a terminal, a server, a natural language processing module, an emotion engine, a database, and several related software modules.

[0703] The terminal is a device for users to input specific ideas and wishes. Through the terminal, users input their wishes in text format, such as "I want to do XX." For example, they might input "I want to start an online shop." The terminal then formats the user's input data into the appropriate format and sends it to the server.

[0704] When the server receives user input data, it forwards it to a natural language processing (NLP) module. Specific technologies that can be used include Python's NLTK library and the Google Cloud Natural Language API. The NLP module analyzes the text data and extracts important keywords. For example, it might extract keywords like "online shop" or "launch."

[0705] Simultaneously, the server uses an emotion engine to analyze the user's emotions from the input data. The emotion engine uses tools such as IBM Watson's Tone Analyzer API to determine whether the user is experiencing positive or negative emotions.

[0706] Next, the server searches the database for past relevant cases based on the extracted keywords. For example, it searches for "Shop A launch case study" or "Shop B launch case study." SQL queries or Elasticsearch can be used here. At the same time, it also searches the database for related products based on the keywords. For example, "EC site building tools" or "online payment systems" might be retrieved.

[0707] Furthermore, the server adjusts its recommendations based on the results of sentiment analysis. For example, if a user has positive emotions, it prioritizes suggesting success stories and innovative products, while if they have negative emotions, it adjusts its recommendations to prioritize safe and reliable examples and products.

[0708] Finally, the server compiles the refined search results and product recommendations and generates response data. This data includes relevant past cases, a list of products, and sentiment-based recommendations that should be provided to the user. The user then receives the final recommendations through their device.

[0709] Furthermore, based on the user's preferences and sentiment analysis results, the server identifies and recommends the necessary experts and systems to carry out the task. For example, it may recommend "web designers," "SEO specialists," "hosting services," and "security solutions." This allows users to receive comprehensive support, including specific implementation steps.

[0710] As a concrete example, consider a case where a user enters "I want to start an online shop." This information entered by the user on the device is sent from the device to the server. The server uses an NLP module to extract the keywords "online shop" and "start up," and an emotion engine determines that the user's emotion is positive. Then, it searches for past "Shop A launch case studies" and "Shop B launch case studies" and suggests "EC site building tools" and "online payment systems." Finally, it adjusts the suggestions based on the emotion analysis results, sends the adjusted results to the device, and displays them to the user. It also introduces "web designers" and "SEO specialists."

[0711] This system can provide concrete support for users' ideas and offer optimal suggestions tailored to their emotions. Examples of prompts to input into the generative AI model include: "I want to start an online shop, what tools and support do I need? Also, please tell me about any past success stories based on my idea."

[0712] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0713] Step 1:

[0714] The user enters their idea into the device.

[0715] Input: The user enters text data such as "I want to do ○○" into the terminal.

[0716] Specific action: The user enters "I want to set up an online shop" into the input field on the device.

[0717] Output: The user's ideas are saved as text data on the terminal.

[0718] Step 2:

[0719] The terminal sends the entered text data to the server.

[0720] Input: User text data saved on the device.

[0721] Specific operation: The terminal formats the input data into an appropriate format (e.g., JSON format), encrypts it, and sends it to the server over the network.

[0722] Output: User text data sent to the server.

[0723] Step 3:

[0724] The server receives the text data and transfers it to the natural language processing module.

[0725] Input: User text data sent to the server.

[0726] Specific operation: The server parses the received text data using Python's NLTK library or the Google Cloud Natural Language API.

[0727] Output: Extracted keywords (e.g., "online shop", "launch").

[0728] Step 4:

[0729] The server uses an emotion engine to analyze the user's emotions.

[0730] Input: User's text data.

[0731] Specific operation: The server uses IBM Watson's Tone Analyzer API to analyze the input data and determine whether the sentiment is positive or negative.

[0732] Output: User's emotional state (e.g., positive).

[0733] Step 5:

[0734] The server uses the extracted keywords to search the database for past cases.

[0735] Input: Extracted keywords.

[0736] Specific operation: The server uses SQL queries and Elasticsearch to identify and retrieve relevant historical cases from the database.

[0737] Output: A list of past case studies as search results (e.g., "Shop A launch case study", "Shop B launch case study").

[0738] Step 6:

[0739] The server uses keywords to search the database for related products.

[0740] Input: Extracted keywords.

[0741] Specific operation: The server uses SQL queries and Elasticsearch to retrieve relevant product information.

[0742] Output: A list of related products (e.g., "EC site building tools", "online payment systems").

[0743] Step 7:

[0744] The server adjusts the suggestions based on the sentiment analysis results.

[0745] Input: Sentiment analysis results, list of past cases, list of products.

[0746] Specific operation: The server adjusts the priority of suggested products based on whether the user has positive or negative emotions. For example, if the user has positive emotions, innovative products will be prioritized.

[0747] Output: Revised proposal.

[0748] Step 8:

[0749] The server aggregates the adjusted search results and product suggestions to generate response data.

[0750] Input: Adjusted proposal content.

[0751] Specific operation: The server compiles relevant past cases and product lists, and creates response data that includes sentiment-based, tailored suggestions.

[0752] Output: Response data to be provided to the user.

[0753] Step 9:

[0754] The terminal receives response data from the server and displays it to the user.

[0755] Input: Response data from the server.

[0756] Specific operation: The device analyzes the response data it receives and displays it in a user-friendly format. For example, it may display the data through a dedicated app or web interface.

[0757] Output: The suggested content that the user will view.

[0758] (Application Example 2)

[0759] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0760] Currently, there is a lack of systems that provide optimal routes and entertainment content based on the user's emotions and specific preferences when using autonomous vehicles. As a result, user dissatisfaction and anxiety during rides increase, leading to a decline in the overall ride experience. Furthermore, conventional systems are limited to simple suggestions based on user input data, making it difficult to provide advanced customization that addresses individual emotions and needs.

[0761] In Application Example 2, the identification processing by the identification processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving user input data, means for analyzing the received input data and extracting keywords, means for analyzing the user's emotions from the received input data, means for searching past cases using the extracted keywords, means for suggesting related products using the extracted keywords, means for providing the user with the recommended past cases and products, means for adjusting the suggested content based on the emotion analysis results, means for providing suggestions regarding the use of autonomous vehicles, and means for identifying and introducing necessary experts and systems based on the user's wishes. This makes it possible to suggest optimal routes and entertainment content that correspond to the user's emotions and specific wishes, thereby improving the overall riding experience.

[0762] "User input data" refers to information such as text, audio, and images that users input via their devices.

[0763] "Means for extracting keywords" refers to functions or technologies that analyze user input data to identify important words and phrases.

[0764] "Means of searching past cases" refers to functions or technologies for searching previously successful cases and related information from a stored database.

[0765] "Means of proposing products" refers to functions or technologies that propose relevant products or services to users based on extracted keywords.

[0766] "Means of providing to the user" refers to the functions or technologies that allow the server to display analysis results and suggestions on the user's terminal.

[0767] "Means of analyzing emotions" refers to functions or technologies for identifying a user's emotional state from user input data.

[0768] "Means for adjusting the content of suggestions" refers to a function or technology for selecting and adjusting the most suitable suggestions for the user based on the results of sentiment analysis.

[0769] "Means of providing suggestions regarding the use of autonomous vehicles" refers to functions or technologies that suggest optimal ways to use autonomous vehicles, routes, and entertainment content based on the user's wishes and emotions.

[0770] "Means for identifying and introducing experts and systems" refers to functions or technologies for selecting and introducing appropriate experts and systems to users based on their preferences.

[0771] This invention relates to a system for providing optimal suggestions based on the user's emotions and wishes when using an autonomous vehicle. The specific methods and means for realizing this system are described below.

[0772] System Overview

[0773] The system primarily consists of smartphones, servers, and terminals. Users input their travel preferences and feelings using their smartphones, and this data is sent to the server. The server analyzes the data and makes optimal suggestions based on the user's feelings and preferences.

[0774] Hardware used

[0775] Smartphone: A device used to receive user input.

[0776] Server: A central processing unit used for data analysis, sentiment analysis, keyword extraction, past case studies, and product / service recommendations.

[0777] Software used

[0778] Natural Language Processing (NLP) Module: A library for extracting and analyzing keywords from user input data. Specifically, Python's TextBlob library is used.

[0779] Sentiment Analysis Engine: A module for analyzing emotions from user text data. It can obtain emotional polarity.

[0780] Explanation of the process

[0781] 1. User Input: The user uses their smartphone to input their preferences, such as "where they want to go" and "what they want to do," in text format.

[0782] 2. Data Transmission: The smartphone sends the user's input data to the server. The data is packaged in the appropriate format before being transmitted.

[0783] 3. Data Analysis: The server analyzes the received data using a natural language processing (NLP) module and extracts keywords. For example, "tourist spots" and "relaxation" might be extracted.

[0784] 4. Emotion Analysis: The server uses an emotion engine to analyze the user's input data to determine their emotions. Positive, negative, and neutral emotions are identified.

[0785] 5. Searching past cases: The server searches the database for relevant past cases based on the extracted keywords.

[0786] 6. Product Proposal: Based on the extracted keywords, search the database for relevant products (e.g., tourist spot guides, relaxation music, etc.) and propose them.

[0787] 7. Adjusting Suggestions: Based on the emotion analysis results, select and adjust suggestions that are best suited to the user's emotions. Prioritize active suggestions for positive emotions, and suggestions that provide comfort and reassurance for negative emotions.

[0788] 8. Delivery of results: The server sends the adjusted results to the smartphone and displays them to the user.

[0789] Examples of specific cases and prompt statements

[0790] Specific example

[0791] If a user enters "I want to do some leisurely sightseeing today," and the sentiment analysis results are positive, then suggestions such as "popular nearby tourist spots" and "hit music" will be displayed.

[0792] If a user enters "I'm tired today and want to relax," and the sentiment analysis results in a negative tone, suggestions such as "a scenic drive through a forest" or "relaxing music" will be provided.

[0793] Example of a prompt

[0794] text

[0795] User: "Today I want to take it easy and do some sightseeing."

[0796] Server: "Based on the user's emotional state, we will make the following suggestions: popular nearby tourist attractions, hit music."

[0797] In this way, the system proposes the optimal way to use the autonomous vehicle based on user input and emotion analysis results, providing a better riding experience.

[0798] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0799] Step 1:

[0800] User input: The user uses their smartphone to input their wishes, such as "where they want to go" and "what they want to do," in text format.

[0801] Specific action: The user types "I want to take it easy and sightsee today" into the input field and presses the submit button.

[0802] Input: User-generated text (e.g., "I want to take it easy and sightsee today")

[0803] Output: Text data sent from a smartphone

[0804] Step 2:

[0805] Data transmission: The device (smartphone) sends user input data to the server. The data is packaged in an appropriate format, such as JSON, before being transmitted.

[0806] Specific operation: The smartphone packages the input data in JSON format and sends it to the server via an HTTPS request.

[0807] Input: User input data (text format)

[0808] Output: Packaged data received by the server

[0809] Step 3:

[0810] Data Analysis: The server analyzes the received data using a natural language processing (NLP) module and extracts keywords.

[0811] Specific operation: The server's Python script uses the TextBlob library to extract keywords such as "tourism" and "relaxing".

[0812] Input: Packaged user input data

[0813] Output: Extracted keywords (e.g., "tourism", "relaxing")

[0814] Step 4:

[0815] Emotion Analysis: The server uses an emotion engine to analyze the user's input data to determine their emotions. Positive, negative, neutral, and other emotions are identified.

[0816] Specific operation: The server script uses TextBlob's sentiment analysis function to determine a positive sentiment from the text "I want to take it easy and sightsee today."

[0817] Input: User input data (text format)

[0818] Output: Sentiment score (e.g., positive)

[0819] Step 5:

[0820] Searching past cases: The server searches the database for relevant past cases based on the extracted keywords.

[0821] Specific operation: The server executes an SQL statement to retrieve past success stories related to "tourism" and "relaxation" from the database.

[0822] Input: Extracted keywords (e.g., "tourism", "relaxing")

[0823] Output: Relevant past examples (e.g., "Success story of tourist spot A")

[0824] Step 6:

[0825] Product Suggestion: Based on the extracted keywords, the server searches the database for relevant products (e.g., tourist spot guides, relaxation music, etc.) and suggests them.

[0826] Specific operation: The server executes the SQL statement again, searching for and listing relevant products (e.g., "tourist attraction guides").

[0827] Input: Extracted keywords (e.g., "tourism", "relaxing")

[0828] Output: A list of related products (e.g., "Tourist Spot Guide")

[0829] Step 7:

[0830] Suggestion Adjustment: Based on sentiment analysis results, the server selects and adjusts suggestions to best suit the user's emotions.

[0831] Specific operation: The server performs a step of generating a list of items suitable for positive emotions based on the emotion score. The contents of the list are automatically adjusted.

[0832] Input: Sentiment score (e.g., positive), list of related products.

[0833] Output: A list of products suitable for specific emotions.

[0834] Step 8:

[0835] Result delivery: The server packages the adjusted results, sends them to the smartphone, and displays them to the user.

[0836] Specific operation: The server packages the results list in JSON format and sends it to the smartphone via an HTTPS request. The smartphone receives the data and displays it in the user interface.

[0837] Input: Adjusted results (list of products, past examples)

[0838] Output: Displayed to the user (e.g., "Success Story of Tourist Spot A," "Tourist Spot Guide")

[0839] In this way, the system can suggest the optimal way to use the autonomous vehicle based on user input data and emotion analysis results, thereby improving the user's riding experience.

[0840] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0841] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0842] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0843] [Third Embodiment]

[0844] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0845] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0846] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0847] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0848] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0849] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0850] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0851] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0852] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[0853] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0854] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0855] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0856] Modes for carrying out the invention

[0857] This invention relates to a system that streamlines the process of users materializing their ideas, such as "I want to do XX." This system begins with the user submitting input data, provides past examples and products related to the idea, and further includes functions to identify and introduce the necessary experts and systems for implementation.

[0858] Program processing

[0859] User actions

[0860] The user uses their device to input a specific idea in text format. For example, they might type, "I want to start a new marketing campaign."

[0861] Sending data

[0862] The terminal sends this input data to the server. The input data is a concrete expression of the user's wishes and ideas.

[0863] Data analysis

[0864] The server receives the input data and analyzes it using natural language processing (NLP) techniques. As a result of the analysis, several keywords are extracted from the data. For example, "marketing" and "campaign" might be extracted.

[0865] Searching past cases

[0866] Using the keywords obtained from the analysis, the server searches the database for relevant past cases. For example, "Campaign A" and "Campaign B" may be obtained as search results.

[0867] Product proposals

[0868] The server also searches its database for related products based on keywords and suggests them to the user. For example, "SNS advertising tools" or "email marketing tools" might be suggested.

[0869] Providing results

[0870] The server compiles past case studies and product suggestions and provides them to the user. This result is displayed to the user via their terminal.

[0871] Introduction of Experts and Systems

[0872] Furthermore, the server identifies and recommends the necessary experts and systems based on the user's preferences. For example, it might recommend "marketing personnel," "advertising specialists," "CRM systems," and "data analysis tools" needed for a marketing campaign.

[0873] Specific example

[0874] For example, consider a case where a user enters "I want to start an online shop."

[0875] 1. The user enters "I want to set up an online shop" into their device.

[0876] 2. The terminal sends the input data to the server.

[0877] 3. The server uses NLP to extract the keywords "online shop" and "launch".

[0878] 4. The server searches for past cases such as "Shop A launch case study" and "Shop B launch case study".

[0879] 5. The server proposes "EC site building tools" and "online payment systems" as products.

[0880] 6. The server compiles this information, sends it to the terminal, and displays it to the user.

[0881] 7. Furthermore, the server identifies and introduces specialists such as "web designers" and "SEO experts," as well as systems such as "hosting services" and "security solutions."

[0882] In this way, the present invention realizes a system that supports the effective realization of users' ideas. By using this system, users can acquire the information and resources necessary to advance their projects quickly and efficiently.

[0883] The following describes the processing flow.

[0884] Step 1:

[0885] The user enters specific ideas or wishes, such as "I want to do XX," into the device in text format. For example, they might enter, "I want to start a new marketing campaign."

[0886] Step 2:

[0887] The terminal sends user input data to the server. At this time, the input data is packaged in an appropriate format.

[0888] Step 3:

[0889] The server receives input data and transfers it to a natural language processing (NLP) module for text analysis.

[0890] Step 4:

[0891] The server uses an NLP module to analyze the input data and extract keywords. For example, "marketing" and "campaign" might be extracted.

[0892] Step 5:

[0893] The server searches the database for relevant past cases based on the extracted keywords. This retrieves, for example, "Campaign A" and "Campaign B".

[0894] Step 6:

[0895] The server uses the extracted keywords to search the database for related products and list them. For example, "SNS advertising tools" and "email marketing tools" might be suggested.

[0896] Step 7:

[0897] The server compiles search results and product suggestions, creating response data to provide to the user. This data includes a list of relevant past cases and products.

[0898] Step 8:

[0899] The server sends response data to the terminal. The terminal receives this data and displays it appropriately to the user.

[0900] Step 9:

[0901] The server identifies the necessary experts and systems for implementation based on the user's requests. For example, it searches for "marketing specialists," "advertising specialists," "CRM systems," and "data analysis tools."

[0902] Step 10:

[0903] The server compiles expert and system information and sends it to the terminal as data indicating the next action for the user. The terminal receives this data and displays it to the user.

[0904] (Example 1)

[0905] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0906] The process of transforming users' abstract ideas into concrete ideas is often time-consuming, laborious, and difficult to carry out efficiently. In particular, quickly finding past success stories and relevant resources is a challenge. Furthermore, the process of identifying and introducing necessary experts and systems is cumbersome, resulting in insufficient support for users to effectively advance their projects. A system that addresses these challenges is needed.

[0907] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0908] In this invention, the server includes means for receiving user input data, means for analyzing the received input data and extracting key keywords, means for searching past cases using the extracted keywords, means for suggesting relevant resources using the extracted keywords, means for providing the user with the recommended past cases and resources, and means for identifying and introducing necessary experts and systems based on the user's preferences. This makes it possible for users to quickly and efficiently materialize their abstract ideas and rapidly acquire the necessary information and resources.

[0909] "Input data" refers to information entered by the user in text format, such as ideas and requests.

[0910] "Analysis" is the process of extracting key information and keywords from input data.

[0911] A "keyword" is a word or phrase that represents important information extracted from the input data.

[0912] "Past examples" refer to information about previously successful projects and ideas stored in the database.

[0913] "Resources" is a general term for tools and services that help users realize their ideas.

[0914] An "expert" is a person who possesses advanced knowledge and experience in a particular field.

[0915] A "system" is the technical infrastructure and tools necessary to realize an idea, which are identified according to the user's needs.

[0916] "Suggesting" means that the server selects relevant resources and experts based on the user's needs and introduces them to the user.

[0917] Modes for carrying out the invention

[0918] This invention relates to a system that streamlines the process of materializing a user's idea of ​​"I want to do XX." This system begins with the user submitting input data, provides past examples and resources related to the idea, and further includes functions to identify and introduce the necessary experts and systems for implementation.

[0919] The server plays a central role in this system, working in conjunction with users and terminals to collect, analyze, and provide data. The specific operations at each step are described below.

[0920] 1. Receiving input data

[0921] The user uses a device to input specific ideas in text format. For example, they might type "I want to start a new marketing campaign." Typically, the user enters their idea into the text box displayed on the device and clicks the submit button. At this point, the input data expresses the idea concretely.

[0922] 2. Sending data

[0923] The terminal sends the input data to the server. This process uses the HTTP protocol and involves a POST request. Specifically, a request body containing the user's idea is sent to the URL "https: / / example.com / api / submit".

[0924] 3. Analysis using natural language processing

[0925] The server analyzes the received data using natural language processing (NLP) techniques. The server uses an NLP library (e.g., SpaCy or NLTK) deployed on a Python program to extract key keywords from the user's input text. This process includes text tokenization and part-of-speech tagging. For example, from the input "I want to start a new marketing campaign," the keywords "marketing" and "campaign" are extracted.

[0926] 4. Search past cases

[0927] Next, the server searches its internal database for relevant past cases based on the extracted keywords. This search process is performed using SQL queries. For example, a query such as "SELECT FROM cases WHERE keywords LIKE '%marketing%' AND keywords LIKE '%campaign%'" is executed, and relevant cases such as "Campaign A" and "Campaign B" are retrieved.

[0928] 5. Product Proposal

[0929] The server similarly searches the database for relevant resources based on keywords. SQL queries retrieve a list of relevant tools and services. For example, a query like "SELECT FROM products WHERE keywords LIKE '%marketing%' AND keywords LIKE '%campaign%'" is executed, and "SNS advertising tools" and "email marketing tools" are suggested.

[0930] 6. Providing results

[0931] The server compiles past cases and resource suggestions and provides them to the user. This result is created in HTML format and sent to the user's device. The results are displayed in the user's browser, allowing them to view detailed information about the suggested cases and tools. For example, the results screen might include a "Detailed Description of Campaign A" and a "List of Recommended Tools."

[0932] 7. Introduction to Experts and Systems

[0933] Furthermore, the server identifies and recommends the necessary experts and systems based on the user's preferences. Expert and system information is also retrieved from the database. For example, executing "SELECT FROM experts WHERE expertise LIKE '%marketing%'" will list "marketing specialists" and "advertising experts." Based on this, the user is introduced to contact information for experts such as "web designers" and "SEO specialists," as well as systems such as "hosting services" and "security solutions."

[0934] By using this system, users can acquire the information and resources necessary to advance their projects quickly and efficiently.

[0935] Specific example

[0936] For example, consider a case where a user enters "I want to start an online shop."

[0937] 1. The user enters "I want to set up an online shop" into their device.

[0938] 2. The terminal sends the input data to the server.

[0939] 3. The server uses NLP to extract the keywords "online shop" and "launch".

[0940] 4. The server searches for past cases such as "Shop A launch case study" and "Shop B launch case study".

[0941] 5. The server proposes "EC site building tools" and "online payment systems" as resources.

[0942] 6. The server compiles this information, sends it to the terminal, and displays it to the user.

[0943] 7. Furthermore, the server identifies and introduces specialists such as "web designers" and "SEO experts," as well as systems such as "hosting services" and "security solutions."

[0944] The following are some specific examples of prompt statements that can be input into a generative AI model.

[0945] "We need ideas to develop new products."

[0946] "Please tell me how to start an effective marketing campaign."

[0947] By using these prompts, users can effectively utilize the system.

[0948] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0949] Step 1:

[0950] The user uses their device to input specific ideas in text format. For example, they might input, "I want to start a new marketing campaign." The input data is entered into a text box, and the input is completed by pressing the submit button. Input is performed by the user entering their idea into the text box on their device and clicking the submit button. This generates the user's idea as text data.

[0951] Step 2:

[0952] The terminal sends text data entered by the user to the server. The HTTP protocol is used for data transmission, and a POST request is made. Specifically, the entered text data is included in the request body and sent to the URL "https: / / example.com / api / submit". The input for this step is the text data entered by the user, and the output is the completion of data transmission to the server.

[0953] Step 3:

[0954] The server analyzes the received text data using natural language processing (NLP) techniques. The server uses NLP libraries such as Python's SpaCy or NLTK to tokenize the text data and extract key keywords. For example, from the text "I want to start a new marketing campaign," it extracts the keywords "marketing" and "campaign." The input for this step is the text data sent to the server, and the output is the extracted keywords.

[0955] Step 4:

[0956] The server uses the extracted keywords to search its internal database for relevant past cases. This search uses SQL queries. For example, it might execute a query like "SELECT FROM cases WHERE keywords LIKE '%marketing%' AND keywords LIKE '%campaign%'" to retrieve the relevant cases. The input for this step is the extracted keywords, and the output is the relevant past case data.

[0957] Step 5:

[0958] The server then searches the database for relevant resources based on keywords. SQL queries are used for this search as well. For example, a query like "SELECT FROM resources WHERE keywords LIKE '%marketing%' AND keywords LIKE '%campaign%'" is executed to retrieve the relevant tools and services. The input for this step is the extracted keywords, and the output is the relevant resource data.

[0959] Step 6:

[0960] The server compiles past case studies and resource data based on keywords and generates results. These results are created in HTML format and sent to the user's terminal. For example, the results screen might include a "Detailed Description of Campaign A" and a "List of Recommended Tools." The input for this step is past case study data and resource data, and the output is the resulting HTML data.

[0961] Step 7:

[0962] Furthermore, the server identifies and recommends the necessary experts and systems based on the user's preferences. It retrieves expert and system information from the database using SQL queries. For example, it might execute "SELECT FROM experts WHERE expertise LIKE '%marketing%'" to list relevant experts. The input for this step is keywords based on the user's preferences, and the output is expert and system information.

[0963] Through the steps outlined above, this system can quickly and efficiently materialize users' ideas and provide the necessary resources.

[0964] (Application Example 1)

[0965] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0966] In today's world, even if users have concrete ideas, it is difficult to quickly and efficiently gather the information and resources necessary to realize those ideas. Furthermore, finding past success stories, relevant products, and appropriate experts and systems requires a tremendous amount of time and effort. In addition, it is difficult for users to generate prompts using AI models to find the appropriate approach. To solve these challenges, there is a need for a means for users to obtain the necessary information and resources quickly and efficiently.

[0967] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0968] In this invention, the server includes means for receiving user input data, means for analyzing the received input data and extracting keywords, means for searching past cases using the extracted keywords, means for suggesting relevant products using the extracted keywords, means for providing the user with the recommended past cases and products, means for identifying and introducing necessary experts and systems based on the user's wishes, means for generating appropriate prompt sentences using a generative AI model based on the input data, and means for suggesting relevant past cases and products based on the generated prompt sentences. This makes it possible for the user to acquire the necessary information and resources efficiently in a short amount of time, and the process of materializing their ideas is greatly simplified.

[0969] "Means for receiving user input data" refers to interfaces or devices that allow users to input their ideas and wishes in text or other formats.

[0970] "Methods for analyzing received input data and extracting keywords" refers to a system that uses natural language processing technology to identify important words and phrases from user input data and extract them.

[0971] "A means of searching for past cases using extracted keywords" refers to a system that searches for past achievements and cases related to the extracted keywords from information sources such as databases.

[0972] "A method for proposing related products using extracted keywords" refers to a system that selects and proposes products and services that are suitable for the user's needs based on keywords.

[0973] "Means of providing users with recommended past cases and products" refers to a system that provides users with information on past cases and suggested products obtained as search results, allowing them to review the information.

[0974] "A means of identifying and introducing necessary experts and systems based on user requests" refers to a system that selects the necessary experts and systems to address the user's specific requests and ideas, and provides information on them.

[0975] "A means of generating appropriate prompt sentences using a generative AI model based on input data" refers to a system that automatically creates appropriate instructional or question-based text using a generative AI model based on data input by the user.

[0976] "A means of suggesting relevant past cases and products based on generated prompt sentences" refers to a system that uses the generated prompt sentences to search for and suggest even more relevant past cases and products.

[0977] This invention provides a system that efficiently supports the process of realizing a user's specific idea. The embodiments for carrying out this invention will be described in detail below.

[0978] Hardware and software to be used

[0979] Hardware: Cloud servers, smartphones

[0980] Software: React Native (frontend), Python, Flask (backend), NLTK (natural language processing), MongoDB (database management), generative AI model (prompt generation)

[0981] System Configuration

[0982] 1. User actions

[0983] Users use a smartphone application to input their ideas in text format. For example, they might enter specific requests such as, "I want to create a new content series."

[0984] 2. Sending data

[0985] User input data is sent from the smartphone to the cloud server. This communication is performed via API calls using the HTTPS protocol.

[0986] 3. Data Analysis

[0987] The cloud server uses Python and Flask to analyze the input data it receives. Here, natural language processing (NLP) techniques are used, and important keywords are extracted from the input data using the NLTK library.

[0988] 4. Prompt sentence generation using a generative AI model

[0989] Based on the extracted keywords, a generative AI model is used to generate appropriate prompt sentences. These prompt sentences are then used for subsequent search and recommendation processes.

[0990] 5. Search for past cases and products

[0991] The generated prompt is used to search the database stored in MongoDB for relevant past cases and product information.

[0992] 6. Providing results

[0993] Past case studies and suggested products obtained as search results are sent from the server to the smartphone and displayed for the user to review.

[0994] 7. Introduction of Experts and Systems

[0995] Based on the user's preferences, the necessary experts and systems for project implementation are identified and introduced. This information is also displayed on the smartphone.

[0996] Specific example

[0997] For example, if a user enters "I want to create a new podcast series," the process would be as follows:

[0998] 1. User actions

[0999] The user types "I want to create a new podcast series" into their smartphone.

[1000] 2. Sending data

[1001] The text data entered by the user is sent to the cloud server.

[1002] 3. Data Analysis

[1003] The server extracts keywords such as "podcast" and "series."

[1004] 4. Prompt sentence generation using a generative AI model

[1005] Based on the extracted keywords, the AI ​​model generates a prompt message that says, "Please recommend examples of successful podcast series and the necessary equipment."

[1006] 5. Search for past cases and products

[1007] The generated prompt is used to search MongoDB for relevant past cases (e.g., successful podcast series) and products (e.g., recording equipment).

[1008] 6. Providing results

[1009] The search results are displayed on the user's smartphone.

[1010] 7. Introduction of Experts and Systems

[1011] Furthermore, information from experts such as audio engineers and digital marketing specialists will also be provided.

[1012] Example of a prompt:

[1013] "I have an idea for a new podcast series. I'd like some examples of successful podcast series from the past and recommendations for necessary equipment."

[1014] This system allows users to quickly and efficiently acquire the necessary information and resources, and significantly simplifies the process of bringing their ideas to life.

[1015] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1016] Step 1:

[1017] The user uses a smartphone application to input a specific idea in text format. An example input is "I want to create a new podcast series." This input data is then sent to the server.

[1018] Step 2:

[1019] The server analyzes the received input data. Python and Flask are used here. Specifically, the NLTK natural language processing (NLP) library is used to extract important keywords from the input data. For example, keywords such as "podcast" and "series" are extracted.

[1020] Step 3:

[1021] The server uses a generative AI model to generate appropriate prompt sentences based on the extracted keywords. The generative AI model generates a prompt sentence such as, "I want to create a new podcast series. I would like recommendations for successful case studies and necessary equipment that would be helpful in this situation."

[1022] Step 4:

[1023] The server uses the generated prompt to search the database (MongoDB) for relevant past cases. The keywords included in the generated prompt are used as the search query. For example, successful podcast series cases might be retrieved as search results.

[1024] Step 5:

[1025] Similarly, the server uses the generated prompt to search the database for relevant products. The keywords included in the prompt are used as the search query. For example, recommended recording equipment or streaming platforms may be retrieved as search results.

[1026] Step 6:

[1027] The server aggregates search results and provides them to the user. Specifically, information on successful podcast series examples and recommended products is sent to the user's smartphone. This information is then displayed on the user's smartphone.

[1028] Step 7:

[1029] Based on the user's preferences, the server identifies and recommends further necessary experts and systems. For example, information on audio engineers, digital marketing specialists, and related systems is provided to the user. This information is also displayed on the smartphone.

[1030] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1031] Modes for carrying out the invention

[1032] This invention is a system that helps users materialize their "I want to do XX" ideas, and further incorporates an emotion engine that recognizes the user's emotions and makes optimal suggestions based on those emotions. The system of this invention consists of a number of different processing steps.

[1033] Program processing

[1034] User actions

[1035] The user uses their device to input specific ideas or wishes in text format, such as "I want to do XX." For example, they might input, "I want to start a new marketing campaign."

[1036] Sending data

[1037] The terminal sends input data to the server. During this process, the input data is packaged in an appropriate format before being sent.

[1038] Data analysis

[1039] The server receives user input data and forwards it to a natural language processing (NLP) module for text analysis. This analysis extracts multiple keywords. For example, "marketing" and "campaign" might be extracted.

[1040] Emotional analysis

[1041] Simultaneously, the server uses an emotion engine to analyze the user's emotions from the input data. This emotion analysis determines whether the user is expressing positive or negative emotions.

[1042] Searching past cases

[1043] The server uses keywords to search the database for relevant past cases. For example, it might search for "Campaign A" or "Campaign B".

[1044] Product proposals

[1045] The server then searches its database for related products based on the same keywords and lists them. For example, "SNS advertising tools" and "email marketing tools" might be suggested.

[1046] Adjusting the proposal

[1047] Based on the analysis results of the emotion engine, the server adjusts the suggestions for past examples and products that are best suited to the user's emotional state. For example, if the user is expressing negative emotions, the server prioritizes suggesting products and examples that provide a greater sense of security.

[1048] Providing results

[1049] The server compiles tailored search results and product recommendations, creating response data to provide to the user. This data includes relevant past cases, product lists, and sentiment-based recommendations.

[1050] Introduction of Experts and Systems

[1051] Furthermore, based on the user's preferences and sentiment analysis results, the server identifies the necessary experts and systems for implementation. For example, "marketing personnel," "advertising specialists," "CRM systems," and "data analysis tools" may be suggested.

[1052] Specific example

[1053] For example, consider a case where a user enters "I want to start an online shop."

[1054] 1. The user enters "I want to set up an online shop" into their device.

[1055] 2. The device sends data to the server.

[1056] 3. The server uses NLP to extract the keywords "online shop" and "launch".

[1057] 4. The server simultaneously analyzes the user's emotions using an emotion engine. This analysis can, for example, determine if the user is expressing positive emotions.

[1058] 5. The server searches for past examples such as "Shop A launch case study" and "Shop B launch case study".

[1059] 6. The server proposes "EC site building tools" and "online payment systems" as products.

[1060] 7. Based on the emotion analysis results, the server adjusts its settings to prioritize suggesting examples and products that are suitable for positive emotions.

[1061] 8. The server sends the adjusted results to the terminal and displays them to the user.

[1062] 9. Furthermore, the server identifies and recommends "web designers," "SEO specialists," and "hosting services" and "security solutions" based on the user's emotions and preferences.

[1063] In this way, the present invention realizes a system that supports the effective materialization of users' ideas. Furthermore, by providing suggestions tailored to the user's emotional state, it can offer more personalized support.

[1064] The following describes the processing flow.

[1065] Step 1:

[1066] The user enters specific ideas or wishes, such as "I want to do XX," into the device in text format. For example, they might enter, "I want to start a new marketing campaign."

[1067] Step 2:

[1068] The terminal sends input data to the server. At this time, the input data is packaged in an appropriate format, and a request is sent to the server.

[1069] Step 3:

[1070] The server receives input data and transfers it to the natural language processing (NLP) module. The NLP module analyzes the text data and extracts multiple keywords.

[1071] Step 4:

[1072] The server uses an emotion engine to analyze the user's emotions from the input data. The emotion analysis module identifies the user's emotions and classifies them as positive, negative, or neutral.

[1073] Step 5:

[1074] The server searches the database for relevant past cases based on the extracted keywords. This search operation sends the keywords as a query to the database and retrieves matching cases.

[1075] Step 6:

[1076] The server also uses keywords to search the database for related products. This lists the products that match the keywords.

[1077] Step 7:

[1078] Based on the analysis results of the emotion engine, the server adjusts the suggestions for past examples and products that are best suited to the user's emotional state. For example, if the user is expressing negative emotions, the server prioritizes suggesting products and examples that provide a greater sense of security.

[1079] Step 8:

[1080] The server compiles tailored search results and product suggestions to create response data for the user. This response data includes relevant past cases, a list of products, and suggestions tailored based on sentiment.

[1081] Step 9:

[1082] The server sends response data to the terminal. The terminal receives this data and displays it appropriately to the user.

[1083] Step 10:

[1084] The server identifies the necessary experts and systems for implementation based on the user's preferences and sentiment analysis results. To this end, it sends queries to expert and system databases to retrieve relevant information.

[1085] Step 11:

[1086] The server compiles expert and system information and sends it to the terminal as an action plan for the user. The terminal receives this data and displays it to the user, indicating the next steps to take.

[1087] As a concrete example, the following shows how to process a user who enters "I want to start an online shop."

[1088] 1. The user enters "I want to set up an online shop" into their device.

[1089] 2. The terminal sends the input data to the server.

[1090] 3. The server uses an NLP module to extract the keywords "online shop" and "launch".

[1091] 4. The server uses an emotion engine to analyze the user's emotions and determine, for example, whether they are expressing positive emotions.

[1092] 5. The server searches for past case studies such as "Shop A launch case study" and "Shop B launch case study".

[1093] 6. The server proposes "EC site building tools" and "online payment systems" as products.

[1094] 7. Based on the emotion analysis results, the server adjusts its settings to prioritize suggesting examples and products that are suitable for positive emotions.

[1095] 8. The server sends the adjusted results to the terminal and displays them to the user.

[1096] 9. Furthermore, the server identifies and recommends "web designers," "SEO specialists," and "hosting services" and "security solutions."

[1097] (Example 2)

[1098] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1099] When supporting users in realizing their specific ideas and desires, simply performing keyword analysis and suggesting related products is insufficient; a challenge lies in the need for personalized suggestions that take into account the user's emotions. Conventional systems provide uniform information regardless of whether the user has positive or negative emotions, which tends to lower user satisfaction. To solve this problem, a function is needed that analyzes the user's emotions and provides optimal suggestions based on that analysis.

[1100] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving user input data, means for analyzing the received input data and extracting keywords, means for analyzing the user's emotions from the input data, means for searching past cases using the extracted keywords, means for suggesting related products using the extracted keywords, means for adjusting the suggestions based on the emotion analysis results, means for providing the user with the recommended past cases and products, and means for identifying and introducing necessary experts and systems based on the user's wishes. This makes it possible to further individualize the user's specific ideas and wishes and make optimal suggestions that respond to their emotions.

[1101] "User input data" refers to text-based information that includes specific ideas, wishes, and requests that users provide to the system.

[1102] "Keyword extraction methods" refer to technologies that identify and extract important words and phrases from user input data.

[1103] "Methods for searching past cases" refers to techniques that use extracted keywords to identify and retrieve relevant past cases from a database.

[1104] "Methods for proposing products and services" refers to techniques that identify and propose relevant products and services from a database based on extracted keywords.

[1105] "Means of providing users with recommended past cases and products" refers to technologies that present search and suggestion results to users.

[1106] "Means for identifying and introducing necessary experts and systems" refers to the technology of identifying relevant experts and systems based on the user's preferences and introducing them to the user.

[1107] "Methods for analyzing emotions" refer to technologies that identify and analyze a user's emotional state (positive, negative, etc.) from user input data.

[1108] "Methods for adjusting suggestions" refers to technologies that modify and adjust suggestions to the optimal content based on the user's emotions, using the results of sentiment analysis.

[1109] This invention is a system that helps users materialize their "I want to do XX" ideas, and further incorporates an emotion engine that recognizes the user's emotions and makes optimal suggestions based on those emotions. The system of this invention consists of a terminal, a server, a natural language processing module, an emotion engine, a database, and several related software modules.

[1110] The terminal is a device for users to input specific ideas and wishes. Through the terminal, users input their wishes in text format, such as "I want to do XX." For example, they might input "I want to start an online shop." The terminal then formats the user's input data into the appropriate format and sends it to the server.

[1111] When the server receives user input data, it forwards it to a natural language processing (NLP) module. Specific technologies that can be used include Python's NLTK library and the Google Cloud Natural Language API. The NLP module analyzes the text data and extracts important keywords. For example, it might extract keywords like "online shop" or "launch."

[1112] Simultaneously, the server uses an emotion engine to analyze the user's emotions from the input data. The emotion engine uses tools such as IBM Watson's Tone Analyzer API to determine whether the user is experiencing positive or negative emotions.

[1113] Next, the server searches the database for past relevant cases based on the extracted keywords. For example, it searches for "Shop A launch case study" or "Shop B launch case study." SQL queries or Elasticsearch can be used here. At the same time, it also searches the database for related products based on the keywords. For example, "EC site building tools" or "online payment systems" might be retrieved.

[1114] Furthermore, the server adjusts its recommendations based on the results of sentiment analysis. For example, if a user has positive emotions, it prioritizes suggesting success stories and innovative products, while if they have negative emotions, it adjusts its recommendations to prioritize safe and reliable examples and products.

[1115] Finally, the server compiles the refined search results and product recommendations and generates response data. This data includes relevant past cases, a list of products, and sentiment-based recommendations that should be provided to the user. The user then receives the final recommendations through their device.

[1116] Furthermore, based on the user's preferences and sentiment analysis results, the server identifies and recommends the necessary experts and systems to carry out the task. For example, it may recommend "web designers," "SEO specialists," "hosting services," and "security solutions." This allows users to receive comprehensive support, including specific implementation steps.

[1117] As a concrete example, consider a case where a user enters "I want to start an online shop." This information entered by the user on the device is sent from the device to the server. The server uses an NLP module to extract the keywords "online shop" and "start up," and an emotion engine determines that the user's emotion is positive. Then, it searches for past "Shop A launch case studies" and "Shop B launch case studies" and suggests "EC site building tools" and "online payment systems." Finally, it adjusts the suggestions based on the emotion analysis results, sends the adjusted results to the device, and displays them to the user. It also introduces "web designers" and "SEO specialists."

[1118] This system can provide concrete support for users' ideas and offer optimal suggestions tailored to their emotions. Examples of prompts to input into the generative AI model include: "I want to start an online shop, what tools and support do I need? Also, please tell me about any past success stories based on my idea."

[1119] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1120] Step 1:

[1121] The user enters their idea into the device.

[1122] Input: The user enters text data such as "I want to do ○○" into the terminal.

[1123] Specific action: The user enters "I want to set up an online shop" into the input field on the device.

[1124] Output: The user's ideas are saved as text data on the terminal.

[1125] Step 2:

[1126] The terminal sends the entered text data to the server.

[1127] Input: User text data saved on the device.

[1128] Specific operation: The terminal formats the input data into an appropriate format (e.g., JSON format), encrypts it, and sends it to the server over the network.

[1129] Output: User text data sent to the server.

[1130] Step 3:

[1131] The server receives the text data and transfers it to the natural language processing module.

[1132] Input: User text data sent to the server.

[1133] Specific operation: The server parses the received text data using Python's NLTK library or the Google Cloud Natural Language API.

[1134] Output: Extracted keywords (e.g., "online shop", "launch").

[1135] Step 4:

[1136] The server uses an emotion engine to analyze the user's emotions.

[1137] Input: User's text data.

[1138] Specific operation: The server uses IBM Watson's Tone Analyzer API to analyze the input data and determine whether the sentiment is positive or negative.

[1139] Output: User's emotional state (e.g., positive).

[1140] Step 5:

[1141] The server uses the extracted keywords to search the database for past cases.

[1142] Input: Extracted keywords.

[1143] Specific operation: The server uses SQL queries and Elasticsearch to identify and retrieve relevant historical cases from the database.

[1144] Output: A list of past case studies as search results (e.g., "Shop A launch case study", "Shop B launch case study").

[1145] Step 6:

[1146] The server uses keywords to search the database for related products.

[1147] Input: Extracted keywords.

[1148] Specific operation: The server uses SQL queries and Elasticsearch to retrieve relevant product information.

[1149] Output: A list of related products (e.g., "EC site building tools", "online payment systems").

[1150] Step 7:

[1151] The server adjusts the suggestions based on the sentiment analysis results.

[1152] Input: Sentiment analysis results, list of past cases, list of products.

[1153] Specific operation: The server adjusts the priority of suggested products based on whether the user has positive or negative emotions. For example, if the user has positive emotions, innovative products will be prioritized.

[1154] Output: Revised proposal.

[1155] Step 8:

[1156] The server aggregates the adjusted search results and product suggestions to generate response data.

[1157] Input: Adjusted proposal content.

[1158] Specific operation: The server compiles relevant past cases and product lists, and creates response data that includes sentiment-based, tailored suggestions.

[1159] Output: Response data to be provided to the user.

[1160] Step 9:

[1161] The terminal receives response data from the server and displays it to the user.

[1162] Input: Response data from the server.

[1163] Specific operation: The device analyzes the response data it receives and displays it in a user-friendly format. For example, it may display the data through a dedicated app or web interface.

[1164] Output: The suggested content that the user will view.

[1165] (Application Example 2)

[1166] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[1167] Currently, there is a lack of systems that provide optimal routes and entertainment content based on the user's emotions and specific preferences when using autonomous vehicles. As a result, user dissatisfaction and anxiety during rides increase, leading to a decline in the overall ride experience. Furthermore, conventional systems are limited to simple suggestions based on user input data, making it difficult to provide advanced customization that addresses individual emotions and needs.

[1168] In Application Example 2, the identification processing by the identification processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving user input data, means for analyzing the received input data and extracting keywords, means for analyzing the user's emotions from the received input data, means for searching past cases using the extracted keywords, means for suggesting related products using the extracted keywords, means for providing the user with the recommended past cases and products, means for adjusting the suggested content based on the emotion analysis results, means for providing suggestions regarding the use of autonomous vehicles, and means for identifying and introducing necessary experts and systems based on the user's wishes. This makes it possible to suggest optimal routes and entertainment content that correspond to the user's emotions and specific wishes, thereby improving the overall riding experience.

[1169] "User input data" refers to information such as text, audio, and images that users input via their devices.

[1170] "Means for extracting keywords" refers to functions or technologies that analyze user input data to identify important words and phrases.

[1171] "Means of searching past cases" refers to functions or technologies for searching previously successful cases and related information from a stored database.

[1172] "Means of proposing products" refers to functions or technologies that propose relevant products or services to users based on extracted keywords.

[1173] "Means of providing to the user" refers to the functions or technologies that allow the server to display analysis results and suggestions on the user's terminal.

[1174] "Means of analyzing emotions" refers to functions or technologies for identifying a user's emotional state from user input data.

[1175] "Means for adjusting the content of suggestions" refers to a function or technology for selecting and adjusting the most suitable suggestions for the user based on the results of sentiment analysis.

[1176] "Means of providing suggestions regarding the use of autonomous vehicles" refers to functions or technologies that suggest optimal ways to use autonomous vehicles, routes, and entertainment content based on the user's wishes and emotions.

[1177] "Means for identifying and introducing experts and systems" refers to functions or technologies for selecting and introducing appropriate experts and systems to users based on their preferences.

[1178] This invention relates to a system for providing optimal suggestions based on the user's emotions and wishes when using an autonomous vehicle. The specific methods and means for realizing this system are described below.

[1179] System Overview

[1180] The system primarily consists of smartphones, servers, and terminals. Users input their travel preferences and feelings using their smartphones, and this data is sent to the server. The server analyzes the data and makes optimal suggestions based on the user's feelings and preferences.

[1181] Hardware used

[1182] Smartphone: A device used to receive user input.

[1183] Server: A central processing unit used for data analysis, sentiment analysis, keyword extraction, past case studies, and product / service recommendations.

[1184] Software used

[1185] Natural Language Processing (NLP) Module: A library for extracting and analyzing keywords from user input data. Specifically, Python's TextBlob library is used.

[1186] Sentiment Analysis Engine: A module for analyzing emotions from user text data. It can obtain emotional polarity.

[1187] Explanation of the process

[1188] 1. User Input: The user uses their smartphone to input their preferences, such as "where they want to go" and "what they want to do," in text format.

[1189] 2. Data Transmission: The smartphone sends the user's input data to the server. The data is packaged in the appropriate format before being transmitted.

[1190] 3. Data Analysis: The server analyzes the received data using a natural language processing (NLP) module and extracts keywords. For example, "tourist spots" and "relaxation" might be extracted.

[1191] 4. Emotion Analysis: The server uses an emotion engine to analyze the user's input data to determine their emotions. Positive, negative, and neutral emotions are identified.

[1192] 5. Searching past cases: The server searches the database for relevant past cases based on the extracted keywords.

[1193] 6. Product Proposal: Based on the extracted keywords, search the database for relevant products (e.g., tourist spot guides, relaxation music, etc.) and propose them.

[1194] 7. Adjusting Suggestions: Based on the emotion analysis results, select and adjust suggestions that are best suited to the user's emotions. Prioritize active suggestions for positive emotions, and suggestions that provide comfort and reassurance for negative emotions.

[1195] 8. Delivery of results: The server sends the adjusted results to the smartphone and displays them to the user.

[1196] Examples of specific cases and prompt statements

[1197] Specific example

[1198] If a user enters "I want to do some leisurely sightseeing today," and the sentiment analysis results are positive, then suggestions such as "popular nearby tourist spots" and "hit music" will be displayed.

[1199] If a user enters "I'm tired today and want to relax," and the sentiment analysis results in a negative tone, suggestions such as "a scenic drive through a forest" or "relaxing music" will be provided.

[1200] Example of a prompt

[1201] text

[1202] User: "Today I want to take it easy and do some sightseeing."

[1203] Server: "Based on the user's emotional state, we will make the following suggestions: popular nearby tourist attractions, hit music."

[1204] In this way, the system proposes the optimal way to use the autonomous vehicle based on user input and emotion analysis results, providing a better riding experience.

[1205] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1206] Step 1:

[1207] User input: The user uses their smartphone to input their wishes, such as "where they want to go" and "what they want to do," in text format.

[1208] Specific action: The user types "I want to take it easy and sightsee today" into the input field and presses the submit button.

[1209] Input: User-generated text (e.g., "I want to take it easy and sightsee today")

[1210] Output: Text data sent from a smartphone

[1211] Step 2:

[1212] Data transmission: The device (smartphone) sends user input data to the server. The data is packaged in an appropriate format, such as JSON, before being transmitted.

[1213] Specific operation: The smartphone packages the input data in JSON format and sends it to the server via an HTTPS request.

[1214] Input: User input data (text format)

[1215] Output: Packaged data received by the server

[1216] Step 3:

[1217] Data Analysis: The server analyzes the received data using a natural language processing (NLP) module and extracts keywords.

[1218] Specific operation: The server's Python script uses the TextBlob library to extract keywords such as "tourism" and "relaxing".

[1219] Input: Packaged user input data

[1220] Output: Extracted keywords (e.g., "tourism", "relaxing")

[1221] Step 4:

[1222] Emotion Analysis: The server uses an emotion engine to analyze the user's input data to determine their emotions. Positive, negative, neutral, and other emotions are identified.

[1223] Specific operation: The server script uses TextBlob's sentiment analysis function to determine a positive sentiment from the text "I want to take it easy and sightsee today."

[1224] Input: User input data (text format)

[1225] Output: Sentiment score (e.g., positive)

[1226] Step 5:

[1227] Searching past cases: The server searches the database for relevant past cases based on the extracted keywords.

[1228] Specific operation: The server executes an SQL statement to retrieve past success stories related to "tourism" and "relaxation" from the database.

[1229] Input: Extracted keywords (e.g., "tourism", "relaxing")

[1230] Output: Relevant past examples (e.g., "Success story of tourist spot A")

[1231] Step 6:

[1232] Product Suggestion: Based on the extracted keywords, the server searches the database for relevant products (e.g., tourist spot guides, relaxation music, etc.) and suggests them.

[1233] Specific operation: The server executes the SQL statement again, searching for and listing relevant products (e.g., "tourist attraction guides").

[1234] Input: Extracted keywords (e.g., "tourism", "relaxing")

[1235] Output: A list of related products (e.g., "Tourist Spot Guide")

[1236] Step 7:

[1237] Suggestion Adjustment: Based on sentiment analysis results, the server selects and adjusts suggestions to best suit the user's emotions.

[1238] Specific operation: The server performs a step of generating a list of items suitable for positive emotions based on the emotion score. The contents of the list are automatically adjusted.

[1239] Input: Sentiment score (e.g., positive), list of related products.

[1240] Output: A list of products suitable for specific emotions.

[1241] Step 8:

[1242] Result delivery: The server packages the adjusted results, sends them to the smartphone, and displays them to the user.

[1243] Specific operation: The server packages the results list in JSON format and sends it to the smartphone via an HTTPS request. The smartphone receives the data and displays it in the user interface.

[1244] Input: Adjusted results (list of products, past examples)

[1245] Output: Displayed to the user (e.g., "Success Story of Tourist Spot A," "Tourist Spot Guide")

[1246] In this way, the system can suggest the optimal way to use the autonomous vehicle based on user input data and emotion analysis results, thereby improving the user's riding experience.

[1247] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1248] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1249] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[1250] [Fourth Embodiment]

[1251] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[1252] As shown in Figure 7, the 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.

[1253] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1254] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[1255] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[1256] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[1257] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[1258] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[1259] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[1260] The specific processing program 56 is an example of a "program" relating to the technology of this 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.

[1261] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1262] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. 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 processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[1263] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1264] Modes for carrying out the invention

[1265] This invention relates to a system that streamlines the process of users materializing their ideas, such as "I want to do XX." This system begins with the user submitting input data, provides past examples and products related to the idea, and further includes functions to identify and introduce the necessary experts and systems for implementation.

[1266] Program processing

[1267] User actions

[1268] The user uses their device to input a specific idea in text format. For example, they might type, "I want to start a new marketing campaign."

[1269] Sending data

[1270] The terminal sends this input data to the server. The input data is a concrete expression of the user's wishes and ideas.

[1271] Data analysis

[1272] The server receives the input data and analyzes it using natural language processing (NLP) techniques. As a result of the analysis, several keywords are extracted from the data. For example, "marketing" and "campaign" might be extracted.

[1273] Searching past cases

[1274] Using the keywords obtained from the analysis, the server searches the database for relevant past cases. For example, "Campaign A" and "Campaign B" may be obtained as search results.

[1275] Product proposals

[1276] The server also searches its database for related products based on keywords and suggests them to the user. For example, "SNS advertising tools" or "email marketing tools" might be suggested.

[1277] Providing results

[1278] The server compiles past case studies and product suggestions and provides them to the user. This result is displayed to the user via their terminal.

[1279] Introduction of Experts and Systems

[1280] Furthermore, the server identifies and recommends the necessary experts and systems based on the user's preferences. For example, it might recommend "marketing personnel," "advertising specialists," "CRM systems," and "data analysis tools" needed for a marketing campaign.

[1281] Specific example

[1282] For example, consider a case where a user enters "I want to start an online shop."

[1283] 1. The user enters "I want to set up an online shop" into their device.

[1284] 2. The terminal sends the input data to the server.

[1285] 3. The server uses NLP to extract the keywords "online shop" and "launch".

[1286] 4. The server searches for past cases such as "Shop A launch case study" and "Shop B launch case study".

[1287] 5. The server proposes "EC site building tools" and "online payment systems" as products.

[1288] 6. The server compiles this information, sends it to the terminal, and displays it to the user.

[1289] 7. Furthermore, the server identifies and introduces specialists such as "web designers" and "SEO experts," as well as systems such as "hosting services" and "security solutions."

[1290] In this way, the present invention realizes a system that supports the effective realization of users' ideas. By using this system, users can acquire the information and resources necessary to advance their projects quickly and efficiently.

[1291] The following describes the processing flow.

[1292] Step 1:

[1293] The user enters specific ideas or wishes, such as "I want to do XX," into the device in text format. For example, they might enter, "I want to start a new marketing campaign."

[1294] Step 2:

[1295] The terminal sends user input data to the server. At this time, the input data is packaged in an appropriate format.

[1296] Step 3:

[1297] The server receives input data and transfers it to a natural language processing (NLP) module for text analysis.

[1298] Step 4:

[1299] The server uses an NLP module to analyze the input data and extract keywords. For example, "marketing" and "campaign" might be extracted.

[1300] Step 5:

[1301] The server searches the database for relevant past cases based on the extracted keywords. This retrieves, for example, "Campaign A" and "Campaign B".

[1302] Step 6:

[1303] The server uses the extracted keywords to search the database for related products and list them. For example, "SNS advertising tools" and "email marketing tools" might be suggested.

[1304] Step 7:

[1305] The server compiles search results and product suggestions, creating response data to provide to the user. This data includes a list of relevant past cases and products.

[1306] Step 8:

[1307] The server sends response data to the terminal. The terminal receives this data and displays it appropriately to the user.

[1308] Step 9:

[1309] The server identifies the necessary experts and systems for implementation based on the user's requests. For example, it searches for "marketing specialists," "advertising specialists," "CRM systems," and "data analysis tools."

[1310] Step 10:

[1311] The server compiles expert and system information and sends it to the terminal as data indicating the next action for the user. The terminal receives this data and displays it to the user.

[1312] (Example 1)

[1313] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1314] The process of transforming users' abstract ideas into concrete ideas is often time-consuming, laborious, and difficult to carry out efficiently. In particular, quickly finding past success stories and relevant resources is a challenge. Furthermore, the process of identifying and introducing necessary experts and systems is cumbersome, resulting in insufficient support for users to effectively advance their projects. A system that addresses these challenges is needed.

[1315] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[1316] In this invention, the server includes means for receiving user input data, means for analyzing the received input data and extracting key keywords, means for searching past cases using the extracted keywords, means for suggesting relevant resources using the extracted keywords, means for providing the user with the recommended past cases and resources, and means for identifying and introducing necessary experts and systems based on the user's preferences. This makes it possible for users to quickly and efficiently materialize their abstract ideas and rapidly acquire the necessary information and resources.

[1317] "Input data" refers to information entered by the user in text format, such as ideas and requests.

[1318] "Analysis" is the process of extracting key information and keywords from input data.

[1319] A "keyword" is a word or phrase that represents important information extracted from the input data.

[1320] "Past examples" refer to information about previously successful projects and ideas stored in the database.

[1321] "Resources" is a general term for tools and services that help users realize their ideas.

[1322] An "expert" is a person who possesses advanced knowledge and experience in a particular field.

[1323] A "system" is the technical infrastructure and tools necessary to realize an idea, which are identified according to the user's needs.

[1324] "Suggesting" means that the server selects relevant resources and experts based on the user's needs and introduces them to the user.

[1325] Modes for carrying out the invention

[1326] This invention relates to a system that streamlines the process of materializing a user's idea of ​​"I want to do XX." This system begins with the user submitting input data, provides past examples and resources related to the idea, and further includes functions to identify and introduce the necessary experts and systems for implementation.

[1327] The server plays a central role in this system, working in conjunction with users and terminals to collect, analyze, and provide data. The specific operations at each step are described below.

[1328] 1. Receiving input data

[1329] The user uses a device to input specific ideas in text format. For example, they might type "I want to start a new marketing campaign." Typically, the user enters their idea into the text box displayed on the device and clicks the submit button. At this point, the input data expresses the idea concretely.

[1330] 2. Sending data

[1331] The terminal sends the input data to the server. This process uses the HTTP protocol and involves a POST request. Specifically, a request body containing the user's idea is sent to the URL "https: / / example.com / api / submit".

[1332] 3. Analysis using natural language processing

[1333] The server analyzes the received data using natural language processing (NLP) techniques. The server uses an NLP library (e.g., SpaCy or NLTK) deployed on a Python program to extract key keywords from the user's input text. This process includes text tokenization and part-of-speech tagging. For example, from the input "I want to start a new marketing campaign," the keywords "marketing" and "campaign" are extracted.

[1334] 4. Search past cases

[1335] Next, the server searches its internal database for relevant past cases based on the extracted keywords. This search process is performed using SQL queries. For example, a query such as "SELECT FROM cases WHERE keywords LIKE '%marketing%' AND keywords LIKE '%campaign%'" is executed, and relevant cases such as "Campaign A" and "Campaign B" are retrieved.

[1336] 5. Product Proposal

[1337] The server similarly searches the database for relevant resources based on keywords. SQL queries retrieve a list of relevant tools and services. For example, a query like "SELECT FROM products WHERE keywords LIKE '%marketing%' AND keywords LIKE '%campaign%'" is executed, and "SNS advertising tools" and "email marketing tools" are suggested.

[1338] 6. Providing results

[1339] The server compiles past cases and resource suggestions and provides them to the user. This result is created in HTML format and sent to the user's device. The results are displayed in the user's browser, allowing them to view detailed information about the suggested cases and tools. For example, the results screen might include a "Detailed Description of Campaign A" and a "List of Recommended Tools."

[1340] 7. Introduction to Experts and Systems

[1341] Furthermore, the server identifies and recommends the necessary experts and systems based on the user's preferences. Expert and system information is also retrieved from the database. For example, executing "SELECT FROM experts WHERE expertise LIKE '%marketing%'" will list "marketing specialists" and "advertising experts." Based on this, the user is introduced to contact information for experts such as "web designers" and "SEO specialists," as well as systems such as "hosting services" and "security solutions."

[1342] By using this system, users can acquire the information and resources necessary to advance their projects quickly and efficiently.

[1343] Specific example

[1344] For example, consider a case where a user enters "I want to start an online shop."

[1345] 1. The user enters "I want to set up an online shop" into their device.

[1346] 2. The terminal sends the input data to the server.

[1347] 3. The server uses NLP to extract the keywords "online shop" and "launch".

[1348] 4. The server searches for past cases such as "Shop A launch case study" and "Shop B launch case study".

[1349] 5. The server proposes "EC site building tools" and "online payment systems" as resources.

[1350] 6. The server compiles this information, sends it to the terminal, and displays it to the user.

[1351] 7. Furthermore, the server identifies and introduces specialists such as "web designers" and "SEO experts," as well as systems such as "hosting services" and "security solutions."

[1352] The following are some specific examples of prompt statements that can be input into a generative AI model.

[1353] "We need ideas to develop new products."

[1354] "Please tell me how to start an effective marketing campaign."

[1355] By using these prompts, users can effectively utilize the system.

[1356] The flow of the specific processing in Example 1 will be explained using Figure 11.

[1357] Step 1:

[1358] The user uses their device to input specific ideas in text format. For example, they might input, "I want to start a new marketing campaign." The input data is entered into a text box, and the input is completed by pressing the submit button. Input is performed by the user entering their idea into the text box on their device and clicking the submit button. This generates the user's idea as text data.

[1359] Step 2:

[1360] The terminal sends text data entered by the user to the server. The HTTP protocol is used for data transmission, and a POST request is made. Specifically, the entered text data is included in the request body and sent to the URL "https: / / example.com / api / submit". The input for this step is the text data entered by the user, and the output is the completion of data transmission to the server.

[1361] Step 3:

[1362] The server analyzes the received text data using natural language processing (NLP) techniques. The server uses NLP libraries such as Python's SpaCy or NLTK to tokenize the text data and extract key keywords. For example, from the text "I want to start a new marketing campaign," it extracts the keywords "marketing" and "campaign." The input for this step is the text data sent to the server, and the output is the extracted keywords.

[1363] Step 4:

[1364] The server uses the extracted keywords to search its internal database for relevant past cases. This search uses SQL queries. For example, it might execute a query like "SELECT FROM cases WHERE keywords LIKE '%marketing%' AND keywords LIKE '%campaign%'" to retrieve the relevant cases. The input for this step is the extracted keywords, and the output is the relevant past case data.

[1365] Step 5:

[1366] The server then searches the database for relevant resources based on keywords. SQL queries are used for this search as well. For example, a query like "SELECT FROM resources WHERE keywords LIKE '%marketing%' AND keywords LIKE '%campaign%'" is executed to retrieve the relevant tools and services. The input for this step is the extracted keywords, and the output is the relevant resource data.

[1367] Step 6:

[1368] The server compiles past case studies and resource data based on keywords and generates results. These results are created in HTML format and sent to the user's terminal. For example, the results screen might include a "Detailed Description of Campaign A" and a "List of Recommended Tools." The input for this step is past case study data and resource data, and the output is the resulting HTML data.

[1369] Step 7:

[1370] Furthermore, the server identifies and recommends the necessary experts and systems based on the user's preferences. It retrieves expert and system information from the database using SQL queries. For example, it might execute "SELECT FROM experts WHERE expertise LIKE '%marketing%'" to list relevant experts. The input for this step is keywords based on the user's preferences, and the output is expert and system information.

[1371] Through the steps outlined above, this system can quickly and efficiently materialize users' ideas and provide the necessary resources.

[1372] (Application Example 1)

[1373] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1374] In today's world, even if users have concrete ideas, it is difficult to quickly and efficiently gather the information and resources necessary to realize those ideas. Furthermore, finding past success stories, relevant products, and appropriate experts and systems requires a tremendous amount of time and effort. In addition, it is difficult for users to generate prompts using AI models to find the appropriate approach. To solve these challenges, there is a need for a means for users to obtain the necessary information and resources quickly and efficiently.

[1375] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[1376] In this invention, the server includes means for receiving user input data, means for analyzing the received input data and extracting keywords, means for searching past cases using the extracted keywords, means for suggesting relevant products using the extracted keywords, means for providing the user with the recommended past cases and products, means for identifying and introducing necessary experts and systems based on the user's wishes, means for generating appropriate prompt sentences using a generative AI model based on the input data, and means for suggesting relevant past cases and products based on the generated prompt sentences. This makes it possible for the user to acquire the necessary information and resources efficiently in a short amount of time, and the process of materializing their ideas is greatly simplified.

[1377] "Means for receiving user input data" refers to interfaces or devices that allow users to input their ideas and wishes in text or other formats.

[1378] "Methods for analyzing received input data and extracting keywords" refers to a system that uses natural language processing technology to identify important words and phrases from user input data and extract them.

[1379] "A means of searching for past cases using extracted keywords" refers to a system that searches for past achievements and cases related to the extracted keywords from information sources such as databases.

[1380] "A method for proposing related products using extracted keywords" refers to a system that selects and proposes products and services that are suitable for the user's needs based on keywords.

[1381] "Means of providing users with recommended past cases and products" refers to a system that provides users with information on past cases and suggested products obtained as search results, allowing them to review the information.

[1382] "A means of identifying and introducing necessary experts and systems based on user requests" refers to a system that selects the necessary experts and systems to address the user's specific requests and ideas, and provides information on them.

[1383] "A means of generating appropriate prompt sentences using a generative AI model based on input data" refers to a system that automatically creates appropriate instructional or question-based text using a generative AI model based on data input by the user.

[1384] "A means of suggesting relevant past cases and products based on generated prompt sentences" refers to a system that uses the generated prompt sentences to search for and suggest even more relevant past cases and products.

[1385] This invention provides a system that efficiently supports the process of realizing a user's specific idea. The embodiments for carrying out this invention will be described in detail below.

[1386] Hardware and software to be used

[1387] Hardware: Cloud servers, smartphones

[1388] Software: React Native (frontend), Python, Flask (backend), NLTK (natural language processing), MongoDB (database management), generative AI model (prompt generation)

[1389] System Configuration

[1390] 1. User actions

[1391] Users use a smartphone application to input their ideas in text format. For example, they might enter specific requests such as, "I want to create a new content series."

[1392] 2. Sending data

[1393] User input data is sent from the smartphone to the cloud server. This communication is performed via API calls using the HTTPS protocol.

[1394] 3. Data Analysis

[1395] The cloud server uses Python and Flask to analyze the input data it receives. Here, natural language processing (NLP) techniques are used, and important keywords are extracted from the input data using the NLTK library.

[1396] 4. Prompt sentence generation using a generative AI model

[1397] Based on the extracted keywords, a generative AI model is used to generate appropriate prompt sentences. These prompt sentences are then used for subsequent search and recommendation processes.

[1398] 5. Search for past cases and products

[1399] The generated prompt is used to search the database stored in MongoDB for relevant past cases and product information.

[1400] 6. Providing results

[1401] Past case studies and suggested products obtained as search results are sent from the server to the smartphone and displayed for the user to review.

[1402] 7. Introduction of Experts and Systems

[1403] Based on the user's preferences, the necessary experts and systems for project implementation are identified and introduced. This information is also displayed on the smartphone.

[1404] Specific example

[1405] For example, if a user enters "I want to create a new podcast series," the process would be as follows:

[1406] 1. User actions

[1407] The user types "I want to create a new podcast series" into their smartphone.

[1408] 2. Sending data

[1409] The text data entered by the user is sent to the cloud server.

[1410] 3. Data Analysis

[1411] The server extracts keywords such as "podcast" and "series."

[1412] 4. Prompt sentence generation using a generative AI model

[1413] Based on the extracted keywords, the AI ​​model generates a prompt message that says, "Please recommend examples of successful podcast series and the necessary equipment."

[1414] 5. Search for past cases and products

[1415] The generated prompt is used to search MongoDB for relevant past cases (e.g., successful podcast series) and products (e.g., recording equipment).

[1416] 6. Providing results

[1417] The search results are displayed on the user's smartphone.

[1418] 7. Introduction of Experts and Systems

[1419] Furthermore, information from experts such as audio engineers and digital marketing specialists will also be provided.

[1420] Example of a prompt:

[1421] "I have an idea for a new podcast series. I'd like some examples of successful podcast series from the past and recommendations for necessary equipment."

[1422] This system allows users to quickly and efficiently acquire the necessary information and resources, and significantly simplifies the process of bringing their ideas to life.

[1423] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[1424] Step 1:

[1425] The user uses a smartphone application to input a specific idea in text format. An example input is "I want to create a new podcast series." This input data is then sent to the server.

[1426] Step 2:

[1427] The server analyzes the received input data. Python and Flask are used here. Specifically, the NLTK natural language processing (NLP) library is used to extract important keywords from the input data. For example, keywords such as "podcast" and "series" are extracted.

[1428] Step 3:

[1429] The server uses a generative AI model to generate appropriate prompt sentences based on the extracted keywords. The generative AI model generates a prompt sentence such as, "I want to create a new podcast series. I would like recommendations for successful case studies and necessary equipment that would be helpful in this situation."

[1430] Step 4:

[1431] The server uses the generated prompt to search the database (MongoDB) for relevant past cases. The keywords included in the generated prompt are used as the search query. For example, successful podcast series cases might be retrieved as search results.

[1432] Step 5:

[1433] Similarly, the server uses the generated prompt to search the database for relevant products. The keywords included in the prompt are used as the search query. For example, recommended recording equipment or streaming platforms may be retrieved as search results.

[1434] Step 6:

[1435] The server aggregates search results and provides them to the user. Specifically, information on successful podcast series examples and recommended products is sent to the user's smartphone. This information is then displayed on the user's smartphone.

[1436] Step 7:

[1437] Based on the user's preferences, the server identifies and recommends further necessary experts and systems. For example, information on audio engineers, digital marketing specialists, and related systems is provided to the user. This information is also displayed on the smartphone.

[1438] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[1439] Modes for carrying out the invention

[1440] This invention is a system that helps users materialize their "I want to do XX" ideas, and further incorporates an emotion engine that recognizes the user's emotions and makes optimal suggestions based on those emotions. The system of this invention consists of a number of different processing steps.

[1441] Program processing

[1442] User actions

[1443] The user uses their device to input specific ideas or wishes in text format, such as "I want to do XX." For example, they might input, "I want to start a new marketing campaign."

[1444] Sending data

[1445] The terminal sends input data to the server. During this process, the input data is packaged in an appropriate format before being sent.

[1446] Data analysis

[1447] The server receives user input data and forwards it to a natural language processing (NLP) module for text analysis. This analysis extracts multiple keywords. For example, "marketing" and "campaign" might be extracted.

[1448] Emotional analysis

[1449] Simultaneously, the server uses an emotion engine to analyze the user's emotions from the input data. This emotion analysis determines whether the user is expressing positive or negative emotions.

[1450] Searching past cases

[1451] The server uses keywords to search the database for relevant past cases. For example, it might search for "Campaign A" or "Campaign B".

[1452] Product proposals

[1453] The server then searches its database for related products based on the same keywords and lists them. For example, "SNS advertising tools" and "email marketing tools" might be suggested.

[1454] Adjusting the proposal

[1455] Based on the analysis results of the emotion engine, the server adjusts the suggestions for past examples and products that are best suited to the user's emotional state. For example, if the user is expressing negative emotions, the server prioritizes suggesting products and examples that provide a greater sense of security.

[1456] Providing results

[1457] The server compiles tailored search results and product recommendations, creating response data to provide to the user. This data includes relevant past cases, product lists, and sentiment-based recommendations.

[1458] Introduction of Experts and Systems

[1459] Furthermore, based on the user's preferences and sentiment analysis results, the server identifies the necessary experts and systems for implementation. For example, "marketing personnel," "advertising specialists," "CRM systems," and "data analysis tools" may be suggested.

[1460] Specific example

[1461] For example, consider a case where a user enters "I want to start an online shop."

[1462] 1. The user enters "I want to set up an online shop" into their device.

[1463] 2. The device sends data to the server.

[1464] 3. The server uses NLP to extract the keywords "online shop" and "launch".

[1465] 4. The server simultaneously analyzes the user's emotions using an emotion engine. This analysis can, for example, determine if the user is expressing positive emotions.

[1466] 5. The server searches for past examples such as "Shop A launch case study" and "Shop B launch case study".

[1467] 6. The server proposes "EC site building tools" and "online payment systems" as products.

[1468] 7. Based on the emotion analysis results, the server adjusts its settings to prioritize suggesting examples and products that are suitable for positive emotions.

[1469] 8. The server sends the adjusted results to the terminal and displays them to the user.

[1470] 9. Furthermore, the server identifies and recommends "web designers," "SEO specialists," and "hosting services" and "security solutions" based on the user's emotions and preferences.

[1471] In this way, the present invention realizes a system that supports the effective materialization of users' ideas. Furthermore, by providing suggestions tailored to the user's emotional state, it can offer more personalized support.

[1472] The following describes the processing flow.

[1473] Step 1:

[1474] The user enters specific ideas or wishes, such as "I want to do XX," into the device in text format. For example, they might enter, "I want to start a new marketing campaign."

[1475] Step 2:

[1476] The terminal sends input data to the server. At this time, the input data is packaged in an appropriate format, and a request is sent to the server.

[1477] Step 3:

[1478] The server receives input data and transfers it to the natural language processing (NLP) module. The NLP module analyzes the text data and extracts multiple keywords.

[1479] Step 4:

[1480] The server uses an emotion engine to analyze the user's emotions from the input data. The emotion analysis module identifies the user's emotions and classifies them as positive, negative, or neutral.

[1481] Step 5:

[1482] The server searches the database for relevant past cases based on the extracted keywords. This search operation sends the keywords as a query to the database and retrieves matching cases.

[1483] Step 6:

[1484] The server also uses keywords to search the database for related products. This lists the products that match the keywords.

[1485] Step 7:

[1486] Based on the analysis results of the emotion engine, the server adjusts the suggestions for past examples and products that are best suited to the user's emotional state. For example, if the user is expressing negative emotions, the server prioritizes suggesting products and examples that provide a greater sense of security.

[1487] Step 8:

[1488] The server compiles tailored search results and product suggestions to create response data for the user. This response data includes relevant past cases, a list of products, and suggestions tailored based on sentiment.

[1489] Step 9:

[1490] The server sends response data to the terminal. The terminal receives this data and displays it appropriately to the user.

[1491] Step 10:

[1492] The server identifies the necessary experts and systems for implementation based on the user's preferences and sentiment analysis results. To this end, it sends queries to expert and system databases to retrieve relevant information.

[1493] Step 11:

[1494] The server compiles expert and system information and sends it to the terminal as an action plan for the user. The terminal receives this data and displays it to the user, indicating the next steps to take.

[1495] As a concrete example, the following shows how to process a user who enters "I want to start an online shop."

[1496] 1. The user enters "I want to set up an online shop" into their device.

[1497] 2. The terminal sends the input data to the server.

[1498] 3. The server uses an NLP module to extract the keywords "online shop" and "launch".

[1499] 4. The server uses an emotion engine to analyze the user's emotions and determine, for example, whether they are expressing positive emotions.

[1500] 5. The server searches for past case studies such as "Shop A launch case study" and "Shop B launch case study".

[1501] 6. The server proposes "EC site building tools" and "online payment systems" as products.

[1502] 7. Based on the emotion analysis results, the server adjusts its settings to prioritize suggesting examples and products that are suitable for positive emotions.

[1503] 8. The server sends the adjusted results to the terminal and displays them to the user.

[1504] 9. Furthermore, the server identifies and recommends "web designers," "SEO specialists," and "hosting services" and "security solutions."

[1505] (Example 2)

[1506] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1507] When supporting users in realizing their specific ideas and desires, simply performing keyword analysis and suggesting related products is insufficient; a challenge lies in the need for personalized suggestions that take into account the user's emotions. Conventional systems provide uniform information regardless of whether the user has positive or negative emotions, which tends to lower user satisfaction. To solve this problem, a function is needed that analyzes the user's emotions and provides optimal suggestions based on that analysis.

[1508] The identification processing performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes means for receiving user input data, means for analyzing the received input data and extracting keywords, means for analyzing the user's emotions from the input data, means for searching past cases using the extracted keywords, means for suggesting related products using the extracted keywords, means for adjusting the suggestions based on the emotion analysis results, means for providing the user with the recommended past cases and products, and means for identifying and introducing necessary experts and systems based on the user's wishes. This makes it possible to further individualize the user's specific ideas and wishes and make optimal suggestions that respond to their emotions.

[1509] "User input data" refers to text-based information that includes specific ideas, wishes, and requests that users provide to the system.

[1510] "Keyword extraction methods" refer to technologies that identify and extract important words and phrases from user input data.

[1511] "Methods for searching past cases" refers to techniques that use extracted keywords to identify and retrieve relevant past cases from a database.

[1512] "Methods for proposing products and services" refers to techniques that identify and propose relevant products and services from a database based on extracted keywords.

[1513] "Means of providing users with recommended past cases and products" refers to technologies that present search and suggestion results to users.

[1514] "Means for identifying and introducing necessary experts and systems" refers to the technology of identifying relevant experts and systems based on the user's preferences and introducing them to the user.

[1515] "Methods for analyzing emotions" refer to technologies that identify and analyze a user's emotional state (positive, negative, etc.) from user input data.

[1516] "Methods for adjusting suggestions" refers to technologies that modify and adjust suggestions to the optimal content based on the user's emotions, using the results of sentiment analysis.

[1517] This invention is a system that helps users materialize their "I want to do XX" ideas, and further incorporates an emotion engine that recognizes the user's emotions and makes optimal suggestions based on those emotions. The system of this invention consists of a terminal, a server, a natural language processing module, an emotion engine, a database, and several related software modules.

[1518] The terminal is a device for users to input specific ideas and wishes. Through the terminal, users input their wishes in text format, such as "I want to do XX." For example, they might input "I want to start an online shop." The terminal then formats the user's input data into the appropriate format and sends it to the server.

[1519] When the server receives user input data, it forwards it to a natural language processing (NLP) module. Specific technologies that can be used include Python's NLTK library and the Google Cloud Natural Language API. The NLP module analyzes the text data and extracts important keywords. For example, it might extract keywords like "online shop" or "launch."

[1520] Simultaneously, the server uses an emotion engine to analyze the user's emotions from the input data. The emotion engine uses tools such as IBM Watson's Tone Analyzer API to determine whether the user is experiencing positive or negative emotions.

[1521] Next, the server searches the database for past relevant cases based on the extracted keywords. For example, it searches for "Shop A launch case study" or "Shop B launch case study." SQL queries or Elasticsearch can be used here. At the same time, it also searches the database for related products based on the keywords. For example, "EC site building tools" or "online payment systems" might be retrieved.

[1522] Furthermore, the server adjusts its recommendations based on the results of sentiment analysis. For example, if a user has positive emotions, it prioritizes suggesting success stories and innovative products, while if they have negative emotions, it adjusts its recommendations to prioritize safe and reliable examples and products.

[1523] Finally, the server compiles the refined search results and product recommendations and generates response data. This data includes relevant past cases, a list of products, and sentiment-based recommendations that should be provided to the user. The user then receives the final recommendations through their device.

[1524] Furthermore, based on the user's preferences and sentiment analysis results, the server identifies and recommends the necessary experts and systems to carry out the task. For example, it may recommend "web designers," "SEO specialists," "hosting services," and "security solutions." This allows users to receive comprehensive support, including specific implementation steps.

[1525] As a concrete example, consider a case where a user enters "I want to start an online shop." This information entered by the user on the device is sent from the device to the server. The server uses an NLP module to extract the keywords "online shop" and "start up," and an emotion engine determines that the user's emotion is positive. Then, it searches for past "Shop A launch case studies" and "Shop B launch case studies" and suggests "EC site building tools" and "online payment systems." Finally, it adjusts the suggestions based on the emotion analysis results, sends the adjusted results to the device, and displays them to the user. It also introduces "web designers" and "SEO specialists."

[1526] This system can provide concrete support for users' ideas and offer optimal suggestions tailored to their emotions. Examples of prompts to input into the generative AI model include: "I want to start an online shop, what tools and support do I need? Also, please tell me about any past success stories based on my idea."

[1527] The flow of the specific processing in Example 2 will be explained using Figure 13.

[1528] Step 1:

[1529] The user enters their idea into the device.

[1530] Input: The user enters text data such as "I want to do ○○" into the terminal.

[1531] Specific action: The user enters "I want to set up an online shop" into the input field on the device.

[1532] Output: The user's ideas are saved as text data on the terminal.

[1533] Step 2:

[1534] The terminal sends the entered text data to the server.

[1535] Input: User text data saved on the device.

[1536] Specific operation: The terminal formats the input data into an appropriate format (e.g., JSON format), encrypts it, and sends it to the server over the network.

[1537] Output: User text data sent to the server.

[1538] Step 3:

[1539] The server receives the text data and transfers it to the natural language processing module.

[1540] Input: User text data sent to the server.

[1541] Specific operation: The server parses the received text data using Python's NLTK library or the Google Cloud Natural Language API.

[1542] Output: Extracted keywords (e.g., "online shop", "launch").

[1543] Step 4:

[1544] The server uses an emotion engine to analyze the user's emotions.

[1545] Input: User's text data.

[1546] Specific operation: The server uses IBM Watson's Tone Analyzer API to analyze the input data and determine whether the sentiment is positive or negative.

[1547] Output: User's emotional state (e.g., positive).

[1548] Step 5:

[1549] The server uses the extracted keywords to search the database for past cases.

[1550] Input: Extracted keywords.

[1551] Specific operation: The server uses SQL queries and Elasticsearch to identify and retrieve relevant historical cases from the database.

[1552] Output: A list of past case studies as search results (e.g., "Shop A launch case study", "Shop B launch case study").

[1553] Step 6:

[1554] The server uses keywords to search the database for related products.

[1555] Input: Extracted keywords.

[1556] Specific operation: The server uses SQL queries and Elasticsearch to retrieve relevant product information.

[1557] Output: A list of related products (e.g., "EC site building tools", "online payment systems").

[1558] Step 7:

[1559] The server adjusts the suggestions based on the sentiment analysis results.

[1560] Input: Sentiment analysis results, list of past cases, list of products.

[1561] Specific operation: The server adjusts the priority of suggested products based on whether the user has positive or negative emotions. For example, if the user has positive emotions, innovative products will be prioritized.

[1562] Output: Revised proposal.

[1563] Step 8:

[1564] The server aggregates the adjusted search results and product suggestions to generate response data.

[1565] Input: Adjusted proposal content.

[1566] Specific operation: The server compiles relevant past cases and product lists, and creates response data that includes sentiment-based, tailored suggestions.

[1567] Output: Response data to be provided to the user.

[1568] Step 9:

[1569] The terminal receives response data from the server and displays it to the user.

[1570] Input: Response data from the server.

[1571] Specific operation: The device analyzes the response data it receives and displays it in a user-friendly format. For example, it may display the data through a dedicated app or web interface.

[1572] Output: The suggested content that the user will view.

[1573] (Application Example 2)

[1574] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[1575] Currently, there is a lack of systems that provide optimal routes and entertainment content based on the user's emotions and specific preferences when using autonomous vehicles. As a result, user dissatisfaction and anxiety during rides increase, leading to a decline in the overall ride experience. Furthermore, conventional systems are limited to simple suggestions based on user input data, making it difficult to provide advanced customization that addresses individual emotions and needs.

[1576] In Application Example 2, the identification processing by the identification processing unit 290 of the data processing device 12 is realized by the following means. In this invention, the server includes means for receiving user input data, means for analyzing the received input data and extracting keywords, means for analyzing the user's emotions from the received input data, means for searching past cases using the extracted keywords, means for suggesting related products using the extracted keywords, means for providing the user with the recommended past cases and products, means for adjusting the suggested content based on the emotion analysis results, means for providing suggestions regarding the use of autonomous vehicles, and means for identifying and introducing necessary experts and systems based on the user's wishes. This makes it possible to suggest optimal routes and entertainment content that correspond to the user's emotions and specific wishes, thereby improving the overall riding experience.

[1577] "User input data" refers to information such as text, audio, and images that users input via their devices.

[1578] "Means for extracting keywords" refers to functions or technologies that analyze user input data to identify important words and phrases.

[1579] "Means of searching past cases" refers to functions or technologies for searching previously successful cases and related information from a stored database.

[1580] "Means of proposing products" refers to functions or technologies that propose relevant products or services to users based on extracted keywords.

[1581] "Means of providing to the user" refers to the functions or technologies that allow the server to display analysis results and suggestions on the user's terminal.

[1582] "Means of analyzing emotions" refers to functions or technologies for identifying a user's emotional state from user input data.

[1583] "Means for adjusting the content of suggestions" refers to a function or technology for selecting and adjusting the most suitable suggestions for the user based on the results of sentiment analysis.

[1584] "Means of providing suggestions regarding the use of autonomous vehicles" refers to functions or technologies that suggest optimal ways to use autonomous vehicles, routes, and entertainment content based on the user's wishes and emotions.

[1585] "Means for identifying and introducing experts and systems" refers to functions or technologies for selecting and introducing appropriate experts and systems to users based on their preferences.

[1586] This invention relates to a system for providing optimal suggestions based on the user's emotions and wishes when using an autonomous vehicle. The specific methods and means for realizing this system are described below.

[1587] System Overview

[1588] The system primarily consists of smartphones, servers, and terminals. Users input their travel preferences and feelings using their smartphones, and this data is sent to the server. The server analyzes the data and makes optimal suggestions based on the user's feelings and preferences.

[1589] Hardware used

[1590] Smartphone: A device used to receive user input.

[1591] Server: A central processing unit used for data analysis, sentiment analysis, keyword extraction, past case studies, and product / service recommendations.

[1592] Software used

[1593] Natural Language Processing (NLP) Module: A library for extracting and analyzing keywords from user input data. Specifically, Python's TextBlob library is used.

[1594] Sentiment Analysis Engine: A module for analyzing emotions from user text data. It can obtain emotional polarity.

[1595] Explanation of the process

[1596] 1. User Input: The user uses their smartphone to input their preferences, such as "where they want to go" and "what they want to do," in text format.

[1597] 2. Data Transmission: The smartphone sends the user's input data to the server. The data is packaged in the appropriate format before being transmitted.

[1598] 3. Data Analysis: The server analyzes the received data using a natural language processing (NLP) module and extracts keywords. For example, "tourist spots" and "relaxation" might be extracted.

[1599] 4. Emotion Analysis: The server uses an emotion engine to analyze the user's input data to determine their emotions. Positive, negative, and neutral emotions are identified.

[1600] 5. Searching past cases: The server searches the database for relevant past cases based on the extracted keywords.

[1601] 6. Product Proposal: Based on the extracted keywords, search the database for relevant products (e.g., tourist spot guides, relaxation music, etc.) and propose them.

[1602] 7. Adjusting Suggestions: Based on the emotion analysis results, select and adjust suggestions that are best suited to the user's emotions. Prioritize active suggestions for positive emotions, and suggestions that provide comfort and reassurance for negative emotions.

[1603] 8. Delivery of results: The server sends the adjusted results to the smartphone and displays them to the user.

[1604] Examples of specific cases and prompt statements

[1605] Specific example

[1606] If a user enters "I want to do some leisurely sightseeing today," and the sentiment analysis results are positive, then suggestions such as "popular nearby tourist spots" and "hit music" will be displayed.

[1607] If a user enters "I'm tired today and want to relax," and the sentiment analysis results in a negative tone, suggestions such as "a scenic drive through a forest" or "relaxing music" will be provided.

[1608] Example of a prompt

[1609] text

[1610] User: "Today I want to take it easy and do some sightseeing."

[1611] Server: "Based on the user's emotional state, we will make the following suggestions: popular nearby tourist attractions, hit music."

[1612] In this way, the system proposes the optimal way to use the autonomous vehicle based on user input and emotion analysis results, providing a better riding experience.

[1613] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[1614] Step 1:

[1615] User input: The user uses their smartphone to input their wishes, such as "where they want to go" and "what they want to do," in text format.

[1616] Specific action: The user types "I want to take it easy and sightsee today" into the input field and presses the submit button.

[1617] Input: User-generated text (e.g., "I want to take it easy and sightsee today")

[1618] Output: Text data sent from a smartphone

[1619] Step 2:

[1620] Data transmission: The device (smartphone) sends user input data to the server. The data is packaged in an appropriate format, such as JSON, before being transmitted.

[1621] Specific operation: The smartphone packages the input data in JSON format and sends it to the server via an HTTPS request.

[1622] Input: User input data (text format)

[1623] Output: Packaged data received by the server

[1624] Step 3:

[1625] Data Analysis: The server analyzes the received data using a natural language processing (NLP) module and extracts keywords.

[1626] Specific operation: The server's Python script uses the TextBlob library to extract keywords such as "tourism" and "relaxing".

[1627] Input: Packaged user input data

[1628] Output: Extracted keywords (e.g., "tourism", "relaxing")

[1629] Step 4:

[1630] Emotion Analysis: The server uses an emotion engine to analyze the user's input data to determine their emotions. Positive, negative, neutral, and other emotions are identified.

[1631] Specific operation: The server script uses TextBlob's sentiment analysis function to determine a positive sentiment from the text "I want to take it easy and sightsee today."

[1632] Input: User input data (text format)

[1633] Output: Sentiment score (e.g., positive)

[1634] Step 5:

[1635] Searching past cases: The server searches the database for relevant past cases based on the extracted keywords.

[1636] Specific operation: The server executes an SQL statement to retrieve past success stories related to "tourism" and "relaxation" from the database.

[1637] Input: Extracted keywords (e.g., "tourism", "relaxing")

[1638] Output: Relevant past examples (e.g., "Success story of tourist spot A")

[1639] Step 6:

[1640] Product Suggestion: Based on the extracted keywords, the server searches the database for relevant products (e.g., tourist spot guides, relaxation music, etc.) and suggests them.

[1641] Specific operation: The server executes the SQL statement again, searching for and listing relevant products (e.g., "tourist attraction guides").

[1642] Input: Extracted keywords (e.g., "tourism", "relaxing")

[1643] Output: A list of related products (e.g., "Tourist Spot Guide")

[1644] Step 7:

[1645] Suggestion Adjustment: Based on sentiment analysis results, the server selects and adjusts suggestions to best suit the user's emotions.

[1646] Specific operation: The server performs a step of generating a list of items suitable for positive emotions based on the emotion score. The contents of the list are automatically adjusted.

[1647] Input: Sentiment score (e.g., positive), list of related products.

[1648] Output: A list of products suitable for specific emotions.

[1649] Step 8:

[1650] Result delivery: The server packages the adjusted results, sends them to the smartphone, and displays them to the user.

[1651] Specific operation: The server packages the results list in JSON format and sends it to the smartphone via an HTTPS request. The smartphone receives the data and displays it in the user interface.

[1652] Input: Adjusted results (list of products, past examples)

[1653] Output: Displayed to the user (e.g., "Success Story of Tourist Spot A," "Tourist Spot Guide")

[1654] In this way, the system can suggest the optimal way to use the autonomous vehicle based on user input data and emotion analysis results, thereby improving the user's riding experience.

[1655] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[1656] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1657] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[1658] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1659] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[1660] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[1661] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[1662] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[1663] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[1664] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[1665] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[1666] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[1667] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[1668] Alternatively, the specific processing program 56 may be stored in a storage device such as a server connected to the data processing device 12 via the network 54, and the specific processing program 56 may be downloaded and installed on the computer 22 in response to a request from the data processing device 12.

[1669] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[1670] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[1671] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[1672] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[1673] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[1674] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[1675] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted as being incorporated by reference.

[1676] The following is further disclosed regarding the embodiments described above.

[1677] (Claim 1)

[1678] A means of receiving user input data,

[1679] A means of analyzing the received input data and extracting keywords,

[1680] A method for searching past cases using extracted keywords,

[1681] A method for suggesting related products using extracted keywords,

[1682] A means of providing users with recommended past case studies and products,

[1683] A means of identifying and introducing the necessary experts and systems based on the user's wishes,

[1684] A system that includes this.

[1685] (Claim 2)

[1686] The system according to claim 1, wherein the means for searching past cases is to obtain past successful cases from a database.

[1687] (Claim 3)

[1688] The system according to claim 1, wherein the means for suggesting related products using extracted keywords is to obtain product information from a database.

[1689] "Example 1"

[1690] (Claim 1)

[1691] A means of receiving user input data,

[1692] A method for analyzing the received input data and extracting key keywords,

[1693] A method for searching past cases using extracted keywords,

[1694] A means of suggesting relevant resources using extracted keywords,

[1695] Means of providing users with recommended past cases and resources,

[1696] A means of identifying and introducing the necessary experts and systems based on the user's wishes,

[1697] A system that includes this.

[1698] (Claim 2)

[1699] The system according to claim 1, wherein the means for searching past cases is to obtain past successful cases from a database.

[1700] (Claim 3)

[1701] The system according to claim 1, wherein the means for suggesting related resources using extracted keywords is to obtain resource information from a database.

[1702] "Application Example 1"

[1703] (Claim 1)

[1704] A means of receiving user input data,

[1705] A means of analyzing the received input data and extracting keywords,

[1706] A method for searching past cases using extracted keywords,

[1707] A method for suggesting related products using extracted keywords,

[1708] A means of providing users with recommended past case studies and products,

[1709] A means of identifying and introducing the necessary experts and systems based on the user's wishes,

[1710] A means of generating appropriate prompt sentences using a generative AI model based on input data,

[1711] Based on the generated prompt message, a means of suggesting relevant past cases and products,

[1712] A system that includes this.

[1713] (Claim 2)

[1714] The system according to claim 1, wherein the means for searching past cases is to obtain past successful cases from a database.

[1715] (Claim 3)

[1716] The system according to claim 1, wherein the means for suggesting related products using extracted keywords is to obtain product information from a database.

[1717] "Example 2 of combining an emotion engine"

[1718] (Claim 1)

[1719] A means of receiving user input data,

[1720] A means of analyzing the received input data and extracting keywords,

[1721] A method for searching past cases using extracted keywords,

[1722] A method for suggesting related products using extracted keywords,

[1723] A means of providing users with recommended past case studies and products,

[1724] A means of identifying and introducing the necessary experts and systems based on the user's wishes,

[1725] A method for analyzing user emotions from input data,

[1726] A means of adjusting proposals based on the results of emotion analysis,

[1727] A system that includes this.

[1728] (Claim 2)

[1729] The system according to claim 1, wherein the means for searching past cases is to obtain past successful cases from a database.

[1730] (Claim 3)

[1731] The system according to claim 1, wherein the means for suggesting related products using extracted keywords is to obtain product information from a database.

[1732] "Application example 2 when combining with an emotional engine"

[1733] (Claim 1)

[1734] A means of receiving user input data,

[1735] A means of analyzing the received input data and extracting keywords,

[1736] A method for searching past cases using extracted keywords,

[1737] A method for suggesting related products using extracted keywords,

[1738] A means of providing users with recommended past case studies and products,

[1739] A means of analyzing user emotions and adjusting suggestions based on those emotions,

[1740] A means of identifying and introducing the necessary experts and systems based on the user's wishes,

[1741] A means of providing proposals regarding the use of autonomous vehicles,

[1742] A system that includes this.

[1743] (Claim 2)

[1744] The system according to claim 1, wherein the means for searching past cases is to obtain past successful cases from a database.

[1745] (Claim 3)

[1746] The system according to claim 1, wherein the means for suggesting related products using extracted keywords is to obtain product information from a database. [Explanation of Symbols]

[1747] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means of receiving user input data, A means of analyzing the received input data and extracting keywords, A method for searching past cases using extracted keywords, A method for suggesting related products using extracted keywords, A means of providing users with recommended past case studies and products, A means of identifying and introducing necessary experts and systems based on the user's preferences, A system that includes this.

2. The system according to claim 1, wherein the means for searching past cases is to obtain past successful cases from a database.

3. The system according to claim 1, wherein the means for suggesting related products using extracted keywords is to obtain product information from a database.

Images