System

Abstract

A system is provided.SOLUTION: A system comprising: means for evaluating a patent success probability, a license agreement probability, a market size, and an estimated share of a submitted idea using a generative AI model; means for calculating an expected return value for a patent filing based on the evaluated parameters; and means for comparing the expected return value with a patent filing cost to make a patent filing decision.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] Describe the "problem that the invention aims to solve" and the "means for solving the problem."

[0005] In situations where many ideas are submitted in idea contests and other events, it is necessary to efficiently determine which ideas should be patented. However, patent-related costs are high, and it is not easy to select only promising ideas from the large number of ideas. Therefore, there is a need for a system that optimizes the costs spent on patent applications during the decision-making process and maximizes profits. [Means for solving the problem]

[0006] The present invention provides a means for evaluating submitted ideas using a generative artificial intelligence model to predict the probability of successful patent registration, the probability of concluding a license agreement, market size, and estimated share. It also includes a means for calculating expected returns based on these parameters and comparing them with patent application costs to make a decision on whether to file a patent application. The generative artificial intelligence model also makes an evaluation based on the market size, estimated share, and initial screening score entered by the user, thereby improving the accuracy of the decision. Furthermore, by having a means for continuously monitoring market fluctuations and the competitive advantage of patents even after the patent application has been filed and evaluating the need to maintain the patent, patent-related costs are optimized and profits are maximized.

[0007] A "generative artificial intelligence model" is a computer program that uses machine learning algorithms to make predictions and evaluations based on input data.

[0008] The "probability of successful patent registration" is a parameter that indicates the probability that a submitted idea will be approved as a patent.

[0009] The "probability of a license agreement being concluded" is a parameter that indicates the probability that a technology will be licensed to another company after a patent is obtained.

[0010] "Market size" is an indicator that shows the economic value of the entire market to which the proposed idea belongs.

[0011] "Estimated share" is a ratio that indicates what share of the overall market the proposed idea is expected to occupy.

[0012] "Expected return" is the probabilistic value of the future revenue that will be earned from patent acquisition and licensing.

[0013] "Patent application costs" refers to the total amount of all costs associated with obtaining and maintaining a patent.

[0014] "Means for evaluation" refers to a function for calculating various parameters of submitted ideas using a generative artificial intelligence model.

[0015] The "means for making a decision" refers to the function of comparing the calculated expected return with the cost of filing a patent application and deciding whether or not to file a patent application.

[0016] "Monitoring measures" refers to the function of continuously monitoring market fluctuations and the competitive environment even after a patent is granted, and assessing the need to maintain the patent. [Brief explanation of the drawings]

[0017] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0018] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0019] First, the terms used in the following description will be explained.

[0020] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0021] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0022] In the following embodiments, the coded storage is one or more non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0023] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0024] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0025] [First embodiment]

[0026] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0027] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0028] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0029] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0030] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0031] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0032] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0033] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0034] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0035] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0036] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0037] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0038] The system of this invention uses a generative artificial intelligence model to evaluate the probability of successful patent registration, the probability of concluding a license agreement, the market size, and estimated share of a submitted idea, and then makes optimal decisions about patent applications based on the results. Below, the program's processing is explained in natural language.

[0039] 1. Collect and enter ideas

[0040] The user uses the device to input details of their idea for a new product or service, including a description of the idea, projected market size, estimated share, royalty rate, etc., as well as the initial judging score. This data is then sent from the device to the server.

[0041] 2. Evaluating ideas

[0042] Based on the received idea information, the server uses a generative AI model to evaluate the following parameters:

[0043] Probability of successful patent registration

[0044] License agreement success rate

[0045] market size

[0046] Estimated Share

[0047] Royalty Rate

[0048] Generative AI models use algorithms that have learned from past data to predict these parameters probabilistically. For example, they may predict that a certain idea will have a market size of 50 billion yen, an estimated market share of 10%, and a royalty rate of 5%.

[0049] 3. Calculating expected returns

[0050] The server calculates the expected return based on the evaluated parameters, using the following formula:

[0051] Market Revenue = Market Size Estimated Share

[0052] Expected revenue = Market revenue Probability of license agreement establishment Royalty rate

[0053] For example, if an idea has a market size of 50 billion yen, an estimated market share of 10%, a 50% probability of a license agreement being concluded, and a royalty rate of 5%, the market revenue would be 5 billion yen and the expected revenue would be 125 million yen.

[0054] 4. Patent Application Judgment

[0055] The server compares the calculated expected return with the patent application cost. The standard patent application cost is 1.2 million yen, consisting of 300,000 yen for application costs and 900,000 yen for registration costs. If the expected return exceeds this standard, the server decides to proceed with the patent application.

[0056] 5. Continuous evaluation

[0057] Even after a patent application is filed, the server continues to monitor market fluctuations and the patent's competitive advantage. It will reevaluate the patent within three years of filing to determine whether it is necessary to maintain the patent. This process helps reduce unnecessary patent maintenance costs and maximize profits.

[0058] Specific examples

[0059] For example, suppose a user inputs an "idea for a new, innovative product" into a terminal, along with a market size of 100 million yen, an estimated market share of 10%, a royalty rate of 5%, and an initial screening score of 85. The server receives this data and evaluates it using a generative artificial intelligence model. The evaluation results are a 70% probability of successful patent registration, a 50% probability of a license agreement being concluded, a market size of 50 billion yen, an estimated market share of 10%, and a royalty rate of 5%. The server calculates the expected return based on this and determines that the expected profit is 125 million yen. Since this exceeds the patent application cost of 1.2 million yen, the server proceeds with the patent application. Furthermore, market fluctuations are monitored even after the patent application is filed, and a decision is made three years later on whether to maintain the patent.

[0060] The above is a concrete example of how to implement this invention. By using this system, it is possible to efficiently select promising ideas from a large number of ideas, optimizing patent-related costs while maximizing profits.

[0061] The processing flow will be explained below.

[0062] Step 1:

[0063] The user uses the terminal to input detailed information about the idea, including the name of the idea, its content, market size, estimated share, royalty rate, and initial screening score.

[0064] Step 2:

[0065] The device sends the details of the entered idea to the server, using a secure communication protocol.

[0066] Step 3:

[0067] The server runs a generative AI model based on the received data. Specifically, based on the input market size, estimated market share, and first screening score, it predicts the probability of successful patent registration, the probability of license agreement establishment, market size, and royalty rate.

[0068] Step 4:

[0069] Based on the evaluation results obtained from the generative AI model, the server calculates the expected value of the return as follows: First, market revenue is calculated by multiplying the market size by the estimated market share, and then this result is multiplied by the probability of concluding a license agreement and the royalty rate to obtain the expected revenue.

[0070] Step 5:

[0071] The server compares the expected return with the cost of filing a patent application. The cost of filing a patent application is 1.2 million yen, consisting of the application cost of 300,000 yen and the registration cost of 900,000 yen. If the expected return exceeds this cost, the server decides to proceed with the patent application.

[0072] Step 6:

[0073] The server sends the patent application decision result to the terminal, including whether to proceed with the patent application and the evaluated parameters.

[0074] Step 7:

[0075] The terminal displays the judgment results for the patent application received from the server to the user. The user checks the results through the terminal and proceeds to the next step as necessary.

[0076] Step 8:

[0077] The server will implement a process for continuous monitoring of market trends after the patent application is filed, by periodically collecting market data and evaluating the patent's competitive advantage and market fluctuations.

[0078] Step 9:

[0079] The server will conduct continuous evaluation within three years of filing a patent application to determine whether it is necessary to maintain the patent. It will then decide whether to maintain or abandon the patent based on market conditions and send the results to the terminal.

[0080] This is the specific flow of program processing in this system. This detailed step-by-step process efficiently carries out a series of decisions, from idea evaluation to patent application and patent maintenance.

[0081] Example 1

[0082] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0083] With the current patent application judgment system, it is difficult to efficiently select ideas with high patent value from among the many available. Furthermore, inappropriate decisions about whether to maintain a patent due to market fluctuations after a patent application are made result in unnecessary costs. Furthermore, solving these issues requires highly accurate prediction models and continuous monitoring.

[0084] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0085] In this invention, the server includes: means for a user to input details of an idea for a new product or service using a terminal; means for transmitting the input data from the terminal to the server; means for evaluating the probability of successful patent registration, the probability of concluding a license agreement, the market size, and an estimated share using a generative artificial intelligence model based on the idea information received by the server; means for the server to calculate an expected return based on the evaluated parameters; means for comparing the calculated expected return with the patent application cost and making a decision on whether to apply for a patent; means for continuously monitoring market fluctuations and the competitive advantage of the patent even after the patent application has been filed; and means for reevaluating and deciding whether to maintain the patent. This makes it possible to efficiently select promising ideas from a large number of ideas and maximize profits while optimizing patent-related costs.

[0086] A "user" is a person who uses the system to input ideas for new products or services using a terminal.

[0087] A "terminal" is an input device used by a user, which inputs details of an idea and transmits the data to a server.

[0088] A "server" is a central computer system that receives data sent by users and performs evaluations and calculations using generative artificial intelligence models.

[0089] A "generative artificial intelligence model" is an algorithm installed on a server that learns from past data and has the ability to evaluate the probability of successful patent registration, the probability of a license agreement being concluded, market size, and estimated share.

[0090] The "probability of successful patent registration" is the probability that the idea being evaluated will be officially registered as a patent.

[0091] The "probability of license agreement establishment" is the probability that a license agreement based on the idea being evaluated will be established.

[0092] "Market size" is a numerical representation of the size of the entire market related to the idea being evaluated.

[0093] "Estimated Share" is the predicted share of the overall market that the idea being evaluated will occupy, expressed as a percentage.

[0094] "Expected return" is the revenue expected based on the idea being evaluated, calculated using factors such as the probability of successful patent registration, the probability of a license agreement being concluded, market size, estimated share, and royalty rate.

[0095] "Patent application costs" are the costs incurred from filing a patent application to registering it, and include application costs and registration costs.

[0096] "Patent application decision" refers to comparing expected revenue with the cost of patent application and deciding whether to apply for a patent.

[0097] "Monitoring" refers to the continuous monitoring of market fluctuations and the competitive advantage of patents after a patent application has been filed.

[0098] "Reevaluation" means reanalyzing data at regular intervals after a patent application is filed to determine whether it is necessary to maintain the patent.

[0099] The present invention relates to a system for improving the efficiency of patent application decisions and optimizing patent-related costs. Specific embodiments for carrying out the present invention will be described below.

[0100] 1. Collecting and inputting ideas

[0101] A user uses a terminal to input details of an idea for a new product or service. The information input by the user includes a description of the idea, a projected market size, an estimated share, a royalty rate, and an initial review score. This information is specifically entered and formatted in an input form on the terminal.

[0102] 2. Data transmission

[0103] The entered data is sent from the device to the server using an HTTP POST request, and the API ensures that the data is sent in the correct format to reach the server.

[0104] 3. Evaluate ideas

[0105] The server stores the received data in a database management system (e.g., MySQL or PostgreSQL). Next, the server uses a generative AI model to evaluate the probability of successful patent registration, the probability of a license agreement being concluded, and the market size and estimated share. The generative AI model is built using a deep learning framework such as TensorFlow or PyTorch, and performs evaluations using algorithms based on past data.

[0106] 4. Calculating expected returns

[0107] The server calculates the expected return based on the evaluated parameters, using the following formula:

[0108] Market Revenue = Market Size Estimated Share

[0109] Expected revenue = Market revenue Probability of license agreement establishment Royalty rate

[0110] For example, if the evaluation results are a market size of 50 billion yen, an estimated market share of 10%, a 50% probability of a license agreement being concluded, and a royalty rate of 5%, then the market revenue will be 5 billion yen and the expected revenue will be 125 million yen.

[0111] 5. Patent Application Judgment

[0112] The server compares the calculated expected revenue with the patent application cost (application cost of 300,000 yen and registration cost of 900,000 yen, totaling 1.2 million yen) and makes a decision on whether to apply for a patent. If the expected revenue exceeds the patent application cost, the server decides to proceed with the patent application and notifies the user of the result. Notification methods include displaying an alert on the device or sending an email.

[0113] 6. Continuous evaluation

[0114] Even after a patent application is filed, the server continuously monitors market fluctuations and the patent's competitive advantage. This includes regularly obtaining the latest market information through data feeds and APIs. A reevaluation is conducted within three years of filing the patent application to determine whether the patent needs to be maintained. This allows you to reduce unnecessary patent maintenance costs and maximize profits.

[0115] Specific examples

[0116] For example, suppose a user inputs an "idea for a new, innovative product" into a terminal, along with a market size of 100 million yen, an estimated market share of 10%, a royalty rate of 5%, and an initial screening score of 85. The server receives this data and evaluates it using a generative artificial intelligence model. The evaluation results are a 70% probability of successful patent registration, a 50% probability of a license agreement being concluded, an estimated market size of 50 billion yen, an estimated market share of 10%, and a royalty rate of 5%. The server calculates the expected return based on this and determines that the expected profit is 125 million yen. Since this exceeds the patent application cost of 1.2 million yen, the server decides to proceed with the patent application. Furthermore, market fluctuations are monitored even after the patent application is filed, and a decision is made three years later on whether to maintain the patent.

[0117] Prompt Sentence Examples

[0118] Specifically, you might use a prompt like this:

[0119] "Please enter your idea for a new, innovative product. Please enter the market size, estimated share, and royalty rate in numerical form, as well as your initial screening score."

[0120] The above is a specific embodiment for carrying out the present invention. By using this system, it is possible to efficiently select promising ideas from a large number of ideas, optimizing patent-related costs while maximizing profits.

[0121] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0122] Step 1:

[0123] A user uses a terminal to input details of an idea for a new product or service, including the following information:

[0124] Idea description (text format)

[0125] Estimated market size (numerical format)

[0126] Estimated share (percentage format)

[0127] Royalty Rate (Percentage Format)

[0128] First screening score (numerical format)

[0129] Specifically, the user enters this information into the input form and clicks the submit button. The input information is then formatted by the terminal software.

[0130] Input: User-entered details about the idea

[0131] Output: Formatted data

[0132] Step 2:

[0133] The device sends the entered data to the server using an HTTP POST request, which contains all the entered information in JSON format.

[0134] Specifically, the terminal converts the data into an appropriate format (JSON format) and sends it to the server's API endpoint.

[0135] Input: Formatted data

[0136] Output: Request data sent to the server

[0137] Step 3:

[0138] The server receives the data sent from the terminal and stores it in a database management system (e.g., MySQL or PostgreSQL).

[0139] Specifically, the server parses the received data and executes SQL queries to store it in a database.

[0140] Input: The request data sent

[0141] Output: Data stored in the database

[0142] Step 4:

[0143] The server reads the stored data and inputs it into a generative artificial intelligence model, which is built using TensorFlow and PyTorch. The model evaluates the probability of successful patent registration, the probability of a license agreement being concluded, and the market size and estimated share.

[0144] Specifically, the server uses SQL queries to retrieve data from the database and convert it into a format that can be input to the model. The generative AI model makes predictions based on past data and returns the output.

[0145] Input: Data retrieved from the database

[0146] Output: Evaluated parameters (probability values, numerical values)

[0147] Step 5:

[0148] The server calculates the expected return based on the evaluated parameters using the following formula:

[0149] Market Revenue = Market Size Estimated Share

[0150] Expected revenue = Market revenue Probability of license agreement establishment Royalty rate

[0151] Specifically, the server uses the evaluated parameters to execute program code that executes the calculation formula and calculates the expected profit.

[0152] Input: Evaluated parameters

[0153] Output: Calculated expected return

[0154] Step 6:

[0155] The server compares the calculated expected profit with the patent application cost and makes a decision on whether to apply for a patent. The patent application cost is 1.2 million yen in total, consisting of the application cost of 300,000 yen and the registration cost of 900,000 yen.

[0156] Specifically, the server executes program code with logic that compares the calculated expected profit with the patent application cost and determines whether or not to apply for a patent. The server then notifies the user of the result of this determination.

[0157] Inputs: Calculated expected revenue, patent application costs

[0158] Output: Patent application decision result (promotion / postponement)

[0159] Step 7:

[0160] The server continuously monitors market fluctuations and the competitive advantages of patents even after the patent application has been filed, including the ability to regularly retrieve the latest market information via data feeds and APIs.

[0161] Specifically, the server runs a program that periodically retrieves information from external data sources and updates the status of patents.

[0162] Input: Market information from external data sources

[0163] Output: Updated market and patent landscape data

[0164] Step 8:

[0165] The server will re-evaluate the patent within three years of filing to determine whether it is necessary to maintain the patent. This re-evaluation will again use the generative AI model to make predictions based on the latest data.

[0166] Specifically, the server executes program code that performs data reanalysis and patent maintenance decisions according to the reevaluation schedule.

[0167] Input: Latest market and patent data

[0168] Output: Patent maintenance decision result (maintain / abandon)

[0169] (Application example 1)

[0170] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0171] In the field of electronic payment services, it has been difficult to accurately evaluate the probability of successful patent registration and market feasibility of investment ideas, and to quickly and efficiently make appropriate patent application decisions. In particular, selecting promising investment ideas from the many submitted and optimizing patent-related costs while maximizing profits requires a great deal of time and effort. Unless this challenge is resolved, electronic payment service providers are likely to incur unnecessary patent maintenance costs and opportunity losses.

[0172] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0173] In this invention, the server includes means for using a generative artificial intelligence model to evaluate the probability of successful patent registration, the probability of concluding a license agreement, the market size, and an estimated share of a submitted idea, means for calculating an expected return on a patent application based on the evaluated parameters, means for comparing the expected return with the patent application cost and making a decision on whether to apply for a patent, and means for allowing a user to propose an investment idea in the electronic payment service and evaluating whether it is worthy of patent registration or market launch. This enables the evaluation of investment ideas and decisions on patent applications in the electronic payment service to be made quickly and efficiently, thereby optimizing patent-related costs and maximizing profits.

[0174] A "generative artificial intelligence model" refers to an artificial intelligence algorithm that makes predictions and evaluations based on collected data.

[0175] "Submitted Idea" means a concept for a new product or service conceived by a User.

[0176] "Probability of successful patent registration" refers to the probability that a patent application will be granted as a patent.

[0177] "Probability of license agreement establishment" indicates the probability that a license agreement regarding patented technology will be established.

[0178] "Market size" refers to the size of the potential market when the patented technology is commercially exploited.

[0179] "Estimated share" means the share that the patented technology is expected to occupy in a particular market.

[0180] "Expected return" refers to the expected value of market revenue, royalties, and other revenues from patented technology.

[0181] "Patent application costs" refer to the costs required to apply for a patent.

[0182] "Patent application decision" means the process of deciding whether to file a patent application based on the evaluated parameters and expected return.

[0183] "Electronic payment service" refers to a service for conducting economic transactions using electronic means.

[0184] "Investment Idea" means a concept or strategy for investment purposes relating to a new technology, product or service.

[0185] "Go-to-market" refers to the process of introducing new technologies or products to the market.

[0186] MODE FOR CARRYING OUT THE INVENTION

[0187] The system of this invention uses a generative artificial intelligence model to evaluate the probability of successful patent registration, the probability of concluding a license agreement, the market size and estimated share of an investment idea in electronic payment services, and then makes optimal decisions about patent applications based on the results.

[0188] Program processing explanation

[0189] Details of hardware, software, data processing and calculation

[0190] The present invention is implemented in an environment where a server and a user terminal are mainly used. The specific hardware and software configurations are as follows.

[0191] 1. User Interface (UI)

[0192] Hardware used: Smartphone

[0193] Software used: Flutter (UI framework)

[0194] Users use a form to enter details of their investment idea (idea description, market size, estimated share, royalty rate, preliminary screening score, etc.) This data is sent from the device to the cloud server.

[0195] 2. Data transmission and storage

[0196] Hardware used: Cloud server (e.g. AWS Lambda)

[0197] Software used: Django (backend framework)

[0198] The data received from the device is sent to a cloud server and stored securely.

[0199] 3. Idea Evaluation

[0200] Hardware used: Cloud server

[0201] Software used: PyTorch (to run the generative AI model)

[0202] Using a generative artificial intelligence model (e.g., GPT-4), we evaluate the probability of successful patent registration, the probability of concluding a license agreement, market size, estimated share, and royalty rate.

[0203] 4. Expected return calculation

[0204] Hardware used: Cloud server

[0205] Software used: NumPy (numerical calculation library)

[0206] The expected revenue is calculated based on the evaluated parameters and a decision is made on whether to apply for a patent.

[0207] 5. Displaying the results

[0208] Hardware used: Smartphone

[0209] Software used: Flutter

[0210] The calculation results (expected revenue, patent application recommendation / non-recommendation, etc.) are displayed to the user.

[0211] Specific examples

[0212] For example, a user inputs the following investment idea:

[0213] | Item | Value |

[0214] |-----------------|-----------------------------|

[0215] | Idea Description | Electronic Payment System with New Security Features |

[0216] | Market size | 100 million yen |

[0217] | Estimated share | 10% |

[0218] | Royalty Rate | 5% |

[0219] | First Screening Score | 85 |

[0220] Based on this data, we send the following prompt to the generative AI model:

[0221] For the following ideas, please evaluate the probability of successful patent registration, probability of successful licensing, market size, estimated market share, and royalty rate, and calculate the expected revenue.

[0222] Idea details: Electronic payment system with new security features, market size: 100 million yen, estimated share: 10%, royalty rate: 5%, initial review score: 85

[0223] The generative AI model performs the evaluation and returns the results to the server. The results are displayed on the terminal, and the user makes a decision on patent application. In this way, the evaluation of investment ideas and the optimization of patent applications are carried out quickly and efficiently.

[0224] The above is a detailed description of the mode for carrying out the present invention.

[0225] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0226] Step 1:

[0227] The user uses a smartphone to input details of an investment idea (idea description, market size, estimated share, royalty rate, preliminary screening score, etc.). This input data is collected by a form and sent to the server. The input data includes detailed information about the idea and numerical information such as market size. This data is sent via the device's UI (Flutter).

[0228] Step 2:

[0229] The server securely stores the received user input data. The hardware used is a cloud server, and the software used is Django. The details of the user's investment ideas are recorded in a database and stored. This process ensures that the data is encrypted and stored securely.

[0230] Step 3:

[0231] Based on the stored data, the server uses a generative artificial intelligence model (e.g., GPT-4) to evaluate the probability of successful patent registration, the probability of a license agreement being concluded, the market size, estimated share, and royalty rate. For this evaluation, Python is used, running the PyTorch library. The server converts the input data into a prompt format and passes it to the generative artificial intelligence model. Specifically, the prompt is as follows: "For the following idea, please evaluate the probability of successful patent registration, the probability of a license agreement being concluded, the market size, estimated share, and royalty rate, and calculate the expected revenue. Idea details: Electronic payment system with new security features, market size: 100 million yen, estimated share: 10%, royalty rate: 5%, initial review score: 85." The output data is the various evaluation results.

[0232] Step 4:

[0233] The server calculates expected revenue based on the evaluation results. The hardware used is a cloud server, and the software used is NumPy (a numerical calculation library). The input data used for the calculation is the evaluation results output by the generative artificial intelligence model. Specifically, it calculates market revenue (market size x estimated share) and expected revenue (market revenue x probability of license agreement establishment x royalty rate). The output data is the expected value of the return.

[0234] Step 5:

[0235] The server compares the expected return obtained as a result of the calculation with the patent application cost and determines whether to recommend or not to apply for a patent. The input data used are the expected revenue and patent application cost (1.2 million yen) calculated in step 4. The output data is the decision result on whether to recommend or not to apply for a patent.

[0236] Step 6:

[0237] The server displays the results of the decision to the smartphone user. The hardware used is a smartphone, and the software used is Flutter (a UI framework). The displayed information includes expected revenue, whether or not to file a patent application, and evaluated parameters. Based on this information, the user can make a final decision on whether or not to file a patent application.

[0238] The above processing steps enable the evaluation of investment ideas and the optimization of patent applications to be carried out quickly and efficiently.

[0239] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0240] This invention combines an emotion engine with a system that uses a generative artificial intelligence model to evaluate submitted ideas and optimize patent application decisions. Specifically, this system recognizes the user's emotions and reflects them in the evaluation and feedback of ideas, enabling more appropriate patent application decisions. The program's processing is explained in natural language below, with specific examples provided for further details.

[0241] 1. Collect and enter ideas

[0242] The user uses the device to input detailed information about the idea, including the idea's name, content, market size, estimated share, royalty rate, and initial review score. The device also uses an emotion engine to recognize the user's emotional state in real time. The user's emotional data is collected through facial recognition and voice analysis, and is also sent to the server.

[0243] 2. Integrating Idea Ratings and Sentiment Data

[0244] The server operates a generative AI model and emotion engine based on the received idea information and emotion data. The generative AI model predicts the probability of successful patent registration, the probability of license agreement establishment, market size, and royalty rate based on the input market size, estimated market share, and first-stage review score. Meanwhile, the emotion engine analyzes the user's emotion data and evaluates how confident or stressed the user is about their idea. This emotion evaluation is fed back into the idea evaluation results. For example, if the user shows optimistic emotions, the risk assessment will be stricter.

[0245] 3. Calculating and adjusting expected returns

[0246] The server calculates the expected return based on the evaluation results using the following formula:

[0247] Market Revenue = Market Size Estimated Share

[0248] Expected revenue = Market revenue Probability of license agreement establishment Royalty rate

[0249] Furthermore, the expected revenue is adjusted based on the user's emotional data. If the user is overconfident, a more conservative forecast is made, and if the user is stressed, feedback is given to improve the user's care.

[0250] 4. Patent Application Judgment

[0251] The server compares the calculated expected return with the cost of filing a patent application. The standard patent application cost is 1.2 million yen, consisting of 300,000 yen for application costs and 900,000 yen for registration costs. If the expected return exceeds this standard, the server decides to proceed with the patent application. This decision also takes into account the user's emotional data, providing optimal support to the user.

[0252] 5. User Feedback

[0253] The server then sends the judgment results for the patent application to the device. Feedback based on the user's emotional state, analyzed by the emotion engine, is also provided. For example, if the user is losing confidence in their idea, the server may provide encouraging messages or suggestions for improvement.

[0254] 6. Ongoing evaluation and monitoring

[0255] Even after a patent application is filed, the server continues to monitor market trends and periodically evaluates the user's emotional state using an emotion engine. It collects market data and user emotional changes to evaluate the patent's competitive advantage and the need for maintenance. It reevaluates the patent within three years of filing to determine whether it needs to be maintained. This process optimizes patent maintenance costs and increases user satisfaction.

[0256] Specific examples

[0257] For example, suppose a user inputs an idea for a new, innovative product into a terminal, along with a market size of 100 million yen, an estimated market share of 10%, a royalty rate of 5%, and a first-stage review score of 85. In addition to this data, the terminal also detects the user's smile and tone of voice and determines their confidence. Using a generative AI model and an emotion engine, the server predicts a 70% probability of successful patent registration, a 50% probability of license agreement establishment, a market size of 50 billion yen, an estimated market share of 10%, and a royalty rate of 5%. Based on the emotion data, the server adjusts the risk assessment somewhat more stringently and calculates the final expected revenue to be 120 million yen. Because this exceeds the patent application cost of 1.2 million yen, the decision is made to proceed with the patent application. At the same time, the user is given feedback stating, "This idea has high potential, and we recommend filing a patent application."

[0258] The above is a concrete example of how to implement this invention. By using this system, an evaluation process that takes into account the user's feelings can be realized, making it possible to maximize the value of ideas while optimizing patent-related costs.

[0259] The processing flow will be explained below.

[0260] Step 1:

[0261] The user inputs detailed information about their idea using a terminal, including the idea's name, content, market size, estimated share, royalty rate, and initial review score, and the system also collects the user's voice and facial expression data to detect their emotional state.

[0262] Step 2:

[0263] The device sends detailed information about the idea and emotional data to the server using a secure communication protocol.

[0264] Step 3:

[0265] The server runs a generative AI model based on the data it receives. Specifically, it predicts the probability of successful patent registration, the probability of a license agreement being concluded, the market size, and royalty rates based on the market size, estimated market share, and first-stage examination score.

[0266] Step 4:

[0267] The server uses an emotion engine to analyze the user's emotional data. The analysis results include an emotional state indicating whether the user is optimistic or pessimistic. Based on this result, the reliability and risk assessment of the idea evaluation are adjusted.

[0268] Step 5:

[0269] The server combines the evaluation results of the generative AI model with the analysis results of the emotion engine to calculate the expected value of the return. It calculates market revenue from the market size and estimated share, and calculates the expected revenue by multiplying the probability of a license agreement being concluded by the royalty rate. It then makes a final calculation of the expected value of the return adjusted based on the emotion data.

[0270] Step 6:

[0271] The server compares the expected return with the cost of filing a patent application. The server uses the application cost of 300,000 yen and the registration cost of 900,000 yen as the standard, totaling 1.2 million yen, and makes a decision to recommend filing a patent application if the expected return exceeds this.

[0272] Step 7:

[0273] The server sends the patent application decision result to the terminal, which includes whether to proceed with the patent application, detailed evaluation parameters, and feedback from the emotion engine.

[0274] Step 8:

[0275] The terminal displays the judgment results and feedback for the patent application received from the server to the user, who can then check the results through the terminal and decide on the next action if necessary.

[0276] Step 9:

[0277] The server runs a process to continuously monitor market trends even after a patent application has been filed, and periodically evaluates the user's emotional state using an emotion engine to collect data to confirm the need to maintain the patent.

[0278] Step 10:

[0279] The server will reevaluate the patent within three years of filing and determine whether it is necessary to maintain the patent. Based on market conditions and the user's sentiment evaluation, the server will make a final decision on whether to maintain the patent and send the result to the terminal.

[0280] The above is the specific flow of program processing in this system. This detailed step-by-step process efficiently carries out a series of decisions, from idea evaluation to patent application and patent maintenance, and provides optimal support that takes user feelings into consideration.

[0281] Example 2

[0282] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0283] Conventional patent evaluation systems use generative artificial intelligence models to objectively evaluate submitted ideas. However, because they do not consider the emotions and intentions of the user who submitted the idea, the evaluation results can sometimes deviate from the user's actual intentions and emotions. This can lead to lower user satisfaction and potentially undermine motivation to pursue patent applications. Furthermore, while there are methods for monitoring market fluctuations after a patent application to evaluate the patent's competitive advantage, these systems lack reevaluation or feedback that takes into account the user's emotional state, which can lead to problems in alleviating user stress and anxiety. Therefore, there is a need for a system that optimizes patent application decisions and improves user satisfaction through idea evaluation and continuous feedback that takes into account the user's emotions.

[0284] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: a means for inputting detailed idea information and emotional data entered by a user using a terminal into a generative AI model; a means for using the generative AI model to evaluate the probability of successful patent registration, license agreement establishment, market size, and estimated share for the submitted idea; a means for calculating an expected return based on the evaluated parameters and emotional data; a means for adjusting the expected return for a patent application by incorporating the emotional data; and a means for comparing the adjusted expected return with patent application costs to make a decision on whether to apply for a patent. This realizes an evaluation process that takes user emotions into account, enabling the optimization of patent-related costs while maximizing the value of the idea. A "user" is a person who inputs detailed idea information and emotional data.

[0285] A "terminal" is a device that allows a user to input detailed information about an idea and collect emotional data.

[0286] "Detailed idea information" is information entered by the user using a terminal, including the name of the idea, its contents, market size, estimated share, royalty rate, and initial screening score.

[0287] "Emotion data" is data that indicates the emotional state of the user analyzed from facial expressions and voice collected by the terminal.

[0288] A "generative artificial intelligence model" is a part of artificial intelligence technology used to evaluate ideas, and is a model for predicting the probability of successful patent registration, the probability of concluding a license agreement, market size, and estimated share.

[0289] "Expected return" is the expected revenue for a patent application calculated based on the evaluated parameters and sentiment data.

[0290] The "adjusted expected return" is a numerical value that reflects the emotional data and modifies the expected return based on the user's emotional state.

[0291] "Patent application costs" refers to the costs required for patent application and registration, and specifically includes application costs and registration costs.

[0292] "Patent application decision" is a process in which the server compares the calculated expected return with the cost of filing a patent application and determines whether to recommend filing a patent application.

[0293] "Market fluctuations" refer to changes in market size and competitive conditions, and are factors that affect the competitive advantage of patents.

[0294] The "necessity of maintaining a patent" is a criterion for evaluating the competitive advantage and market value of a patent and deciding whether to maintain the patent.

[0295] The above are definitions of important words.

[0296] The present invention is a system for optimizing patent application decisions using a generative artificial intelligence model, and by collecting and integrating user emotional data into the evaluation process, it provides more appropriate feedback to the user. Detailed modes for implementing the invention are described below.

[0297] 1. Collect and enter ideas

[0298] Users use the device to input detailed information about their ideas, including the idea's name, content, market size, estimated share, royalty rate, and initial review score. The device is equipped with an emotion engine that collects the user's emotional data in real time as they input information. The data is collected by analyzing the user's facial expressions and voice using the device's built-in camera and microphone. The user's emotional state is then digitized and sent to the server along with the idea information.

[0299] 2. Integrating Idea Ratings and Sentiment Data

[0300] The server operates a generative AI model and emotion engine based on the received idea information and emotion data. The generative AI model predicts the probability of successful patent registration, the probability of license agreement establishment, market size, and royalty rate based on data such as market size, estimated market share, and initial review score. Meanwhile, the emotion engine analyzes the collected emotion data and evaluates the user's emotional state. For example, if the user is feeling confident or anxious, each emotional state is fed back into the evaluation results.

[0301] 3. Calculating and adjusting expected returns

[0302] The server calculates the expected return based on the evaluation results using the following formula:

[0303] Market Revenue = Market Size Estimated Share

[0304] Expected revenue = Market revenue Probability of license agreement establishment Royalty rate

[0305] Furthermore, the expected revenue is adjusted based on the user's emotional data. If the user is overconfident, a more conservative forecast is made, and if the user is stressed, feedback is given to improve the user's care.

[0306] 4. Patent Application Judgment

[0307] The server compares the calculated expected return with the cost of filing a patent application. The standard patent application cost is 1.2 million yen, consisting of 300,000 yen for application costs and 900,000 yen for registration costs. If the expected return exceeds this standard, the server recommends filing a patent application. This decision also takes into account the user's emotional data, providing optimal support to the user.

[0308] 5. User Feedback

[0309] The server then sends the judgment result of the patent application to the terminal. The judgment result is not only provided, but also feedback based on the user's emotional state as analyzed by the emotion engine. For example, if the user is losing confidence in their idea, the server may provide an encouraging message or suggestions for improvement.

[0310] 6. Ongoing evaluation and monitoring

[0311] Even after a patent application is filed, the server continues to monitor market fluctuations and periodically evaluates the user's emotional state using an emotion engine. It collects market data and user emotional changes to evaluate the patent's competitive advantage and the need for maintenance. It reevaluates the patent within three years of filing to determine whether it needs to be maintained. This process optimizes patent maintenance costs and increases user satisfaction.

[0312] Specific examples

[0313] For example, suppose a user inputs an idea for a new, innovative product into a terminal. Specifically, the inputs are a market size of 100 million yen, an estimated market share of 10%, a royalty rate of 5%, and a first-stage review score of 85. At the same time, the terminal detects the user's smile and tone of voice and determines their confidence. Using a generative AI model and an emotion engine, the server predicts a 70% probability of successful patent registration, a 50% probability of license agreement establishment, a market size of 50 billion yen, an estimated market share of 10%, and a royalty rate of 5%. Based on the emotion data, the server adjusts the risk assessment somewhat more stringently and calculates the final expected revenue to be 120 million yen. Because this exceeds the patent application cost of 1.2 million yen, the decision is made to proceed with the patent application. At the same time, the user is given feedback stating, "This idea has high potential, and we recommend filing a patent application."

[0314] Prompt Sentence Examples

[0315] The prompt to input a "new innovative product idea" into the generative AI model is as follows:

[0316] Evaluate new and innovative product ideas.

[0317] Market size: 100 million yen

[0318] Estimated share: 10%

[0319] Royalty rate: 5%

[0320] First round score: 85

[0321] Emotion Recognition: Confident

[0322] By using this prompt, the generative artificial intelligence model can evaluate the appropriate ideas.

[0323] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0324] Program processing flow

[0325] Step 1: User enters idea details using a terminal

[0326] The user enters the name, content, market size, estimated share, royalty rate, and initial review score of the idea into the input screen of the terminal. The input data is in text format and divided into specific fields. This allows the user's idea to be recorded quantitatively and qualitatively. Input: Detailed information about the idea, Output: Detailed information about the idea data.

[0327] Step 2: The device uses the emotion engine to collect the user's emotion data.

[0328] While the user is inputting their ideas, the device uses the built-in camera and microphone to analyze the user's facial expressions and voice in real time. The emotion engine uses facial recognition and voice analysis algorithms to quantify the user's emotional state. Input: User's facial and voice data, Output: Emotion data.

[0329] Step 3: The user confirms the information they entered and the device sends it to the server

[0330] The user checks the input and presses the send button to send the data to the server. The device sends detailed idea data and emotion data in JSON format to the server. Input: Send instruction, Output: Data sent to the server.

[0331] Step 4: The server analyzes the received idea information

[0332] The server parses the received data and stores it in a database, converting the values ​​of each field to the appropriate data type and preparing it for evaluation. Input: Data sent to the server, Output: Parsed and stored data.

[0333] Step 5: The server inputs the emotion data into the generative AI model

[0334] The server uses the emotion data as input data for the generative AI model, which uses a pre-trained neural network. Input: Emotion data, Output: Emotion data converted into a data format for model input.

[0335] Step 6: The server runs the generative AI model and evaluates the ideas.

[0336] The server launches a generative AI model and predicts the probability of successful patent registration, the probability of a license agreement being concluded, the market size, and royalty rates based on input data such as market size, estimated market share, and first review score. Input: Detailed idea information and converted emotion data, Output: Idea evaluation results.

[0337] Step 7: The server uses the emotion engine to analyze the user's emotion data and integrate it into a rating.

[0338] The server uses an emotion engine to analyze the user's emotional data and evaluate how confident or stressed the user is about their idea. This result is integrated into the idea evaluation results as feedback. Input: User's emotional data and idea evaluation results. Output: Integrated evaluation results.

[0339] Step 8: The server calculates the expected return based on the evaluation results.

[0340] The server calculates the expected revenue using the following formula:

[0341] Market Revenue = Market Size Estimated Share

[0342] Expected revenue = Market revenue Probability of license agreement establishment Royalty rate

[0343] Input: Integrated valuation results, Output: Calculated expected profit.

[0344] Step 9: The server adjusts the expected revenue taking into account the sentiment data

[0345] The server considers the user's emotional data and makes conservative predictions if the user is overconfident, or adjusts the expected revenue while providing caring feedback if the user is feeling stressed. Input: Calculated expected revenue and emotional data, Output: Adjusted expected revenue.

[0346] Step 10: The server compares the calculated expected revenue with the patent application cost and makes a decision on whether to apply for the patent.

[0347] The server evaluates whether the adjusted expected revenue exceeds the standard patent application cost (1.2 million yen) and determines whether to recommend a patent application. Input: adjusted expected revenue and patent application cost, Output: judgment on whether to apply for a patent.

[0348] Step 11: The server sends the result of the decision to the terminal.

[0349] The server generates a result based on the patent application decision in JSON format and sends it to the user's device. This includes the decision result as well as a feedback message based on the user's emotional state. Input: Patent application approval / disapproval decision, Output: Results and feedback sent to the user's device.

[0350] Step 12: User Feedback

[0351] The user receives the results on the terminal and checks the displayed feedback message. For example, if there is a high possibility of success, the message "We recommend you apply for a patent" will be displayed, and if they are feeling less confident, the message will include encouragement and suggestions for improvement. Input: Results and feedback sent from the server. Output: Feedback message displayed on the terminal.

[0352] Step 13: Ongoing evaluation and monitoring after patent application

[0353] The server continues to monitor market fluctuations even after the patent application has been filed, and periodically evaluates the user's emotional state using an emotion engine. A reevaluation is performed within three years to determine whether the patent should be maintained. Input: Market data and emotion data. Output: Reevaluation results and decision on whether to maintain the patent.

[0354] (Application example 2)

[0355] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0356] Conventional patent evaluation systems evaluate ideas without taking the user's emotional state into account, resulting in evaluation results that do not necessarily match the user's actual intentions or circumstances. Furthermore, because emotional data is not used in the evaluation process, appropriate feedback cannot be provided to the user, potentially resulting in suboptimal decisions on patent applications. In response to these issues, the present invention aims to provide a system that integrates user emotional data to provide more appropriate evaluations and feedback.

[0357] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for evaluating the probability of successful patent registration, probability of license agreement establishment, market size, and estimated share of a submitted idea using a generative artificial intelligence model; means for calculating an expected return on a patent application based on the evaluated parameters; means for comparing the expected return with the patent application cost and making a decision on the patent application; emotion recognition means for collecting and analyzing user emotion data; and means for integrating the emotion data obtained by the emotion recognition means into the evaluation and feeding it back into the evaluation result. This allows the evaluation of the submitted idea to reflect the user's emotional state, making it possible to make a more appropriate decision on the patent application.

[0358] A "generative artificial intelligence model" refers to an artificial intelligence algorithm designed to generate new information or predictions based on data.

[0359] "Probability of successful patent registration" refers to the probability that a submitted idea will be granted a patent.

[0360] The "probability of a license agreement being concluded" refers to the probability that, after a patent is obtained, a contract will be concluded to provide the technology or idea to other companies or individuals under a license agreement.

[0361] "Market size" refers to the economic size or value of the entire target market for a particular idea or product.

[0362] "Estimated share" refers to the percentage of the market that the submitted idea or product is expected to occupy.

[0363] "Expected return" refers to the expected amount of profit that an investment in a patent application will bring in the future.

[0364] "Patent application costs" refers to the set of expenses required to apply for a patent.

[0365] "User emotional data" refers to data that indicates the user's emotional state, as obtained through the user's facial expressions, voice, and other physiological data.

[0366] "Emotion recognition means" refers to technology and devices for detecting and analyzing a user's emotions.

[0367] "Means of providing feedback to evaluation results" refers to techniques and methods for reflecting analyzed emotional data in the evaluation process and improving the final evaluation results.

[0368] This invention is a system that uses a generative artificial intelligence model to evaluate submitted feedback and optimize store operations. By recognizing user emotions and reflecting them in the feedback, it is possible to make more appropriate operational decisions. A detailed description of this system is provided below.

[0369] composition

[0370] 1. User Device

[0371] Hardware: Computer, smartphone, smart glasses, or head-mounted display for feedback input.

[0372] Software: A camera to capture the user's face, and an emotion recognition application to collect emotional data.

[0373] 2. Server

[0374] Hardware: High-performance servers.

[0375] Software: Generative AI models, emotion recognition engines, and evaluation and feedback systems.

[0376] Program processing

[0377] The program of this system performs the following main processes.

[0378] 1. Data collection: The user device captures facial expressions and voice along with the customer feedback text to collect emotional data. This emotional data is analyzed in real time and sent to the server.

[0379] Software used: OpenCV (for face recognition), Transformers (Hugging Face emotion analysis model).

[0380] 2. Data analysis: On the server side, a generative AI model evaluates the characteristics of the submitted feedback and analyzes the emotion data obtained by the emotion recognition means.

[0381] Generative artificial intelligence model used: Transformers (Hugging Face generative model).

[0382] 3. Evaluation and integration: The analyzed emotion data is fed back into the evaluation results, and a final evaluation is made.

[0383] Example of feedback: Based on the evaluation results, specific operational improvement instructions such as "Improve the layout and expand the coffee corner" are generated.

[0384] 4. Result feedback: The server sends the evaluation results to the user's device and provides appropriate feedback to the user. For example, if the evaluation result is high, a message such as "This store management approach has a high chance of success!" is displayed.

[0385] Specific examples

[0386] For example, consider a user entering feedback such as, "I like the layout of the store, but the coffee corner is not well-equipped." A webcam captures the customer's face, and an emotion recognition model identifies the expression as "happiness." A generative AI model on the server side generates an evaluation result such as, "Areas for improvement: Improve the layout and expand the coffee corner," and notifies the user as final feedback, "This store management approach has a high chance of success!"

[0387] Prompt Sentence Examples

[0388] A request to develop an application that collects customer feedback and sentiment data and provides suggestions for improving store operations.

[0389] Integrate customer opinions and sentiments to provide optimal feedback to store managers.

[0390] This system allows submitted feedback to reflect the user's emotional state, enabling better decisions to be made about store management.

[0391] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0392] Step 1:

[0393] A user terminal provides an interface for inputting feedback text from a customer. The user inputs the feedback text, and the terminal transmits the text to a server. At this time, the terminal activates a camera and a microphone for collecting emotion data based on the feedback text. The input is the feedback text, and the output is the feedback data transmitted to the server.

[0394] Step 2:

[0395] The device uses a camera and microphone to capture the user's face and voice and collect emotion data. Specifically, the camera captures the user's facial expressions in real time and performs facial recognition using OpenCV. The microphone also records audio and the audio data is analyzed using an emotion recognition engine (Transformers emotion analysis model). The input is the user's face and voice, and the output is emotion data.

[0396] Step 3:

[0397] The device sends the collected emotion data and feedback text to the server. Specifically, the results of facial recognition and voice analysis are sent to the server as structured data. In this process, the input is the user's emotion data and feedback text, and the output is the data sent to the server.

[0398] Step 4:

[0399] The server analyzes the received feedback text and emotion data and inputs them into a generative AI model. Specifically, the generative AI model formats the feedback text and emotion data input, integrates them, and performs evaluation. In this process, the input is the feedback text and emotion data, and the output is the evaluation result.

[0400] Step 5:

[0401] The server generates feedback for optimizing store operations based on the evaluation results of the generative AI model. Specifically, it generates appropriate feedback messages based on the evaluation results and makes adjustments taking into account emotional data. In this process, the inputs are the evaluation results and emotional data, and the output is optimization feedback.

[0402] Step 6:

[0403] The server sends the generated feedback to the user's terminal. Specifically, the optimization feedback is sent in a format that is easy to display immediately to the user. In this process, the input is the optimization feedback, and the output is the feedback display on the terminal.

[0404] Step 7:

[0405] The user terminal displays the feedback received from the server and provides the user with instructions for operational improvement. Specifically, the received feedback message is displayed on the user interface for the user to check. In this process, the input is the feedback message, and the output is the feedback display to the user.

[0406] Through these steps, the system provides feedback that reflects the user's emotional state, optimizing store operations.

[0407] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0408] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0409] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0410] [Second embodiment]

[0411] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0412] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0413] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0414] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0415] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0416] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0417] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0418] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0419] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0420] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0421] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0422] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0423] The system of this invention uses a generative artificial intelligence model to evaluate the probability of successful patent registration, the probability of concluding a license agreement, the market size, and estimated share of a submitted idea, and then makes optimal decisions about patent applications based on the results. Below, the program's processing is explained in natural language.

[0424] 1. Collect and enter ideas

[0425] The user uses the device to input details of their idea for a new product or service, including a description of the idea, projected market size, estimated share, royalty rate, etc., as well as the initial judging score. This data is then sent from the device to the server.

[0426] 2. Evaluating ideas

[0427] Based on the received idea information, the server uses a generative AI model to evaluate the following parameters:

[0428] Probability of successful patent registration

[0429] License agreement success rate

[0430] market size

[0431] Estimated Share

[0432] Royalty Rate

[0433] Generative AI models use algorithms that have learned from past data to predict these parameters probabilistically. For example, they may predict that a certain idea will have a market size of 50 billion yen, an estimated market share of 10%, and a royalty rate of 5%.

[0434] 3. Calculating expected returns

[0435] The server calculates the expected return based on the evaluated parameters, using the following formula:

[0436] Market Revenue = Market Size Estimated Share

[0437] Expected revenue = Market revenue Probability of license agreement establishment Royalty rate

[0438] For example, if an idea has a market size of 50 billion yen, an estimated market share of 10%, a 50% probability of a license agreement being concluded, and a royalty rate of 5%, the market revenue would be 5 billion yen and the expected revenue would be 125 million yen.

[0439] 4. Patent Application Judgment

[0440] The server compares the calculated expected return with the patent application cost. The standard patent application cost is 1.2 million yen, consisting of 300,000 yen for application costs and 900,000 yen for registration costs. If the expected return exceeds this standard, the server decides to proceed with the patent application.

[0441] 5. Continuous evaluation

[0442] Even after a patent application is filed, the server continues to monitor market fluctuations and the patent's competitive advantage. It will reevaluate the patent within three years of filing to determine whether it is necessary to maintain the patent. This process helps reduce unnecessary patent maintenance costs and maximize profits.

[0443] Specific examples

[0444] For example, suppose a user inputs an "idea for a new, innovative product" into a terminal, along with a market size of 100 million yen, an estimated market share of 10%, a royalty rate of 5%, and an initial screening score of 85. The server receives this data and evaluates it using a generative artificial intelligence model. The evaluation results are a 70% probability of successful patent registration, a 50% probability of a license agreement being concluded, a market size of 50 billion yen, an estimated market share of 10%, and a royalty rate of 5%. The server calculates the expected return based on this and determines that the expected profit is 125 million yen. Since this exceeds the patent application cost of 1.2 million yen, the server proceeds with the patent application. Furthermore, market fluctuations are monitored even after the patent application is filed, and a decision is made three years later on whether to maintain the patent.

[0445] The above is a concrete example of how to implement this invention. By using this system, it is possible to efficiently select promising ideas from a large number of ideas, optimizing patent-related costs while maximizing profits.

[0446] The processing flow will be explained below.

[0447] Step 1:

[0448] The user uses the terminal to input detailed information about the idea, including the name of the idea, its content, market size, estimated share, royalty rate, and initial screening score.

[0449] Step 2:

[0450] The device sends the details of the entered idea to the server, using a secure communication protocol.

[0451] Step 3:

[0452] The server runs a generative AI model based on the received data. Specifically, based on the input market size, estimated market share, and first screening score, it predicts the probability of successful patent registration, the probability of license agreement establishment, market size, and royalty rate.

[0453] Step 4:

[0454] Based on the evaluation results obtained from the generative AI model, the server calculates the expected value of the return as follows: First, market revenue is calculated by multiplying the market size by the estimated market share, and then this result is multiplied by the probability of concluding a license agreement and the royalty rate to obtain the expected revenue.

[0455] Step 5:

[0456] The server compares the expected return with the cost of filing a patent application. The cost of filing a patent application is 1.2 million yen, consisting of the application cost of 300,000 yen and the registration cost of 900,000 yen. If the expected return exceeds this cost, the server decides to proceed with the patent application.

[0457] Step 6:

[0458] The server sends the patent application decision result to the terminal, including whether to proceed with the patent application and the evaluated parameters.

[0459] Step 7:

[0460] The terminal displays the judgment results for the patent application received from the server to the user. The user checks the results through the terminal and proceeds to the next step as necessary.

[0461] Step 8:

[0462] The server will implement a process for continuous monitoring of market trends after the patent application is filed, by periodically collecting market data and evaluating the patent's competitive advantage and market fluctuations.

[0463] Step 9:

[0464] The server will conduct continuous evaluation within three years of filing a patent application to determine whether it is necessary to maintain the patent. It will then decide whether to maintain or abandon the patent based on market conditions and send the results to the terminal.

[0465] This is the specific flow of program processing in this system. This detailed step-by-step process efficiently carries out a series of decisions, from idea evaluation to patent application and patent maintenance.

[0466] Example 1

[0467] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0468] With the current patent application judgment system, it is difficult to efficiently select ideas with high patent value from among the many available. Furthermore, inappropriate decisions about whether to maintain a patent due to market fluctuations after a patent application are made result in unnecessary costs. Furthermore, solving these issues requires highly accurate prediction models and continuous monitoring.

[0469] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0470] In this invention, the server includes: means for a user to input details of an idea for a new product or service using a terminal; means for transmitting the input data from the terminal to the server; means for evaluating the probability of successful patent registration, the probability of concluding a license agreement, the market size, and an estimated share using a generative artificial intelligence model based on the idea information received by the server; means for the server to calculate an expected return based on the evaluated parameters; means for comparing the calculated expected return with the patent application cost and making a decision on whether to apply for a patent; means for continuously monitoring market fluctuations and the competitive advantage of the patent even after the patent application has been filed; and means for reevaluating and deciding whether to maintain the patent. This makes it possible to efficiently select promising ideas from a large number of ideas and maximize profits while optimizing patent-related costs.

[0471] A "user" is a person who uses the system to input ideas for new products or services using a terminal.

[0472] A "terminal" is an input device used by a user, which inputs details of an idea and transmits the data to a server.

[0473] A "server" is a central computer system that receives data sent by users and performs evaluations and calculations using generative artificial intelligence models.

[0474] A "generative artificial intelligence model" is an algorithm installed on a server that learns from past data and has the ability to evaluate the probability of successful patent registration, the probability of a license agreement being concluded, market size, and estimated share.

[0475] The "probability of successful patent registration" is the probability that the idea being evaluated will be officially registered as a patent.

[0476] The "probability of license agreement establishment" is the probability that a license agreement based on the idea being evaluated will be established.

[0477] "Market size" is a numerical representation of the size of the entire market related to the idea being evaluated.

[0478] "Estimated Share" is the predicted share of the overall market that the idea being evaluated will occupy, expressed as a percentage.

[0479] "Expected return" is the revenue expected based on the idea being evaluated, calculated using factors such as the probability of successful patent registration, the probability of a license agreement being concluded, market size, estimated share, and royalty rate.

[0480] "Patent application costs" are the costs incurred from filing a patent application to registering it, and include application costs and registration costs.

[0481] "Patent application decision" refers to comparing expected revenue with the cost of patent application and deciding whether to apply for a patent.

[0482] "Monitoring" refers to the continuous monitoring of market fluctuations and the competitive advantage of patents after a patent application has been filed.

[0483] "Reevaluation" means reanalyzing data at regular intervals after a patent application is filed to determine whether it is necessary to maintain the patent.

[0484] The present invention relates to a system for improving the efficiency of patent application decisions and optimizing patent-related costs. Specific embodiments for carrying out the present invention will be described below.

[0485] 1. Collecting and inputting ideas

[0486] A user uses a terminal to input details of an idea for a new product or service. The information input by the user includes a description of the idea, a projected market size, an estimated share, a royalty rate, and an initial review score. This information is specifically entered and formatted in an input form on the terminal.

[0487] 2. Data transmission

[0488] The entered data is sent from the device to the server using an HTTP POST request, and the API ensures that the data is sent in the correct format to reach the server.

[0489] 3. Evaluate ideas

[0490] The server stores the received data in a database management system (e.g., MySQL or PostgreSQL). Next, the server uses a generative AI model to evaluate the probability of successful patent registration, the probability of a license agreement being concluded, and the market size and estimated share. The generative AI model is built using a deep learning framework such as TensorFlow or PyTorch, and performs evaluations using algorithms based on past data.

[0491] 4. Calculating expected returns

[0492] The server calculates the expected return based on the evaluated parameters, using the following formula:

[0493] Market Revenue = Market Size Estimated Share

[0494] Expected revenue = Market revenue Probability of license agreement establishment Royalty rate

[0495] For example, if the evaluation results are a market size of 50 billion yen, an estimated market share of 10%, a 50% probability of a license agreement being concluded, and a royalty rate of 5%, then the market revenue will be 5 billion yen and the expected revenue will be 125 million yen.

[0496] 5. Patent Application Judgment

[0497] The server compares the calculated expected revenue with the patent application cost (application cost of 300,000 yen and registration cost of 900,000 yen, totaling 1.2 million yen) and makes a decision on whether to apply for a patent. If the expected revenue exceeds the patent application cost, the server decides to proceed with the patent application and notifies the user of the result. Notification methods include displaying an alert on the device or sending an email.

[0498] 6. Continuous evaluation

[0499] Even after a patent application is filed, the server continuously monitors market fluctuations and the patent's competitive advantage. This includes regularly obtaining the latest market information through data feeds and APIs. A reevaluation is conducted within three years of filing the patent application to determine whether the patent needs to be maintained. This allows you to reduce unnecessary patent maintenance costs and maximize profits.

[0500] Specific examples

[0501] For example, suppose a user inputs an "idea for a new, innovative product" into a terminal, along with a market size of 100 million yen, an estimated market share of 10%, a royalty rate of 5%, and an initial screening score of 85. The server receives this data and evaluates it using a generative artificial intelligence model. The evaluation results are a 70% probability of successful patent registration, a 50% probability of a license agreement being concluded, an estimated market size of 50 billion yen, an estimated market share of 10%, and a royalty rate of 5%. The server calculates the expected return based on this and determines that the expected profit is 125 million yen. Since this exceeds the patent application cost of 1.2 million yen, the server decides to proceed with the patent application. Furthermore, market fluctuations are monitored even after the patent application is filed, and a decision is made three years later on whether to maintain the patent.

[0502] Prompt Sentence Examples

[0503] Specifically, you might use a prompt like this:

[0504] "Please enter your idea for a new, innovative product. Please enter the market size, estimated share, and royalty rate in numerical form, as well as your initial screening score."

[0505] The above is a specific embodiment for carrying out the present invention. By using this system, it is possible to efficiently select promising ideas from a large number of ideas, optimizing patent-related costs while maximizing profits.

[0506] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0507] Step 1:

[0508] A user uses a terminal to input details of an idea for a new product or service, including the following information:

[0509] Idea description (text format)

[0510] Estimated market size (numerical format)

[0511] Estimated share (percentage format)

[0512] Royalty Rate (Percentage Format)

[0513] First screening score (numerical format)

[0514] Specifically, the user enters this information into the input form and clicks the submit button. The input information is then formatted by the terminal software.

[0515] Input: User-entered details about the idea

[0516] Output: Formatted data

[0517] Step 2:

[0518] The device sends the entered data to the server using an HTTP POST request, which contains all the entered information in JSON format.

[0519] Specifically, the terminal converts the data into an appropriate format (JSON format) and sends it to the server's API endpoint.

[0520] Input: Formatted data

[0521] Output: Request data sent to the server

[0522] Step 3:

[0523] The server receives the data sent from the terminal and stores it in a database management system (e.g., MySQL or PostgreSQL).

[0524] Specifically, the server parses the received data and executes SQL queries to store it in a database.

[0525] Input: The request data sent

[0526] Output: Data stored in the database

[0527] Step 4:

[0528] The server reads the stored data and inputs it into a generative artificial intelligence model, which is built using TensorFlow and PyTorch. The model evaluates the probability of successful patent registration, the probability of a license agreement being concluded, and the market size and estimated share.

[0529] Specifically, the server uses SQL queries to retrieve data from the database and convert it into a format that can be input to the model. The generative AI model makes predictions based on past data and returns the output.

[0530] Input: Data retrieved from the database

[0531] Output: Evaluated parameters (probability values, numerical values)

[0532] Step 5:

[0533] The server calculates the expected return based on the evaluated parameters using the following formula:

[0534] Market Revenue = Market Size Estimated Share

[0535] Expected revenue = Market revenue Probability of license agreement establishment Royalty rate

[0536] Specifically, the server uses the evaluated parameters to execute program code that executes the calculation formula and calculates the expected profit.

[0537] Input: Evaluated parameters

[0538] Output: Calculated expected return

[0539] Step 6:

[0540] The server compares the calculated expected profit with the patent application cost and makes a decision on whether to apply for a patent. The patent application cost is 1.2 million yen in total, consisting of the application cost of 300,000 yen and the registration cost of 900,000 yen.

[0541] Specifically, the server executes program code with logic that compares the calculated expected profit with the patent application cost and determines whether or not to apply for a patent. The server then notifies the user of the result of this determination.

[0542] Inputs: Calculated expected revenue, patent application costs

[0543] Output: Patent application decision result (promotion / postponement)

[0544] Step 7:

[0545] The server continuously monitors market fluctuations and the competitive advantages of patents even after the patent application has been filed, including the ability to regularly retrieve the latest market information via data feeds and APIs.

[0546] Specifically, the server runs a program that periodically retrieves information from external data sources and updates the status of patents.

[0547] Input: Market information from external data sources

[0548] Output: Updated market and patent landscape data

[0549] Step 8:

[0550] The server will re-evaluate the patent within three years of filing to determine whether it is necessary to maintain the patent. This re-evaluation will again use the generative AI model to make predictions based on the latest data.

[0551] Specifically, the server executes program code that performs data reanalysis and patent maintenance decisions according to the reevaluation schedule.

[0552] Input: Latest market and patent data

[0553] Output: Patent maintenance decision result (maintain / abandon)

[0554] (Application example 1)

[0555] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0556] In the field of electronic payment services, it has been difficult to accurately evaluate the probability of successful patent registration and market feasibility of investment ideas, and to quickly and efficiently make appropriate patent application decisions. In particular, selecting promising investment ideas from the many submitted and optimizing patent-related costs while maximizing profits requires a great deal of time and effort. Unless this challenge is resolved, electronic payment service providers are likely to incur unnecessary patent maintenance costs and opportunity losses.

[0557] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0558] In this invention, the server includes means for using a generative artificial intelligence model to evaluate the probability of successful patent registration, the probability of concluding a license agreement, the market size, and an estimated share of a submitted idea, means for calculating an expected return on a patent application based on the evaluated parameters, means for comparing the expected return with the patent application cost and making a decision on whether to apply for a patent, and means for allowing a user to propose an investment idea in the electronic payment service and evaluating whether it is worthy of patent registration or market launch. This enables the evaluation of investment ideas and decisions on patent applications in the electronic payment service to be made quickly and efficiently, thereby optimizing patent-related costs and maximizing profits.

[0559] A "generative artificial intelligence model" refers to an artificial intelligence algorithm that makes predictions and evaluations based on collected data.

[0560] "Submitted Idea" means a concept for a new product or service conceived by a User.

[0561] "Probability of successful patent registration" refers to the probability that a patent application will be granted as a patent.

[0562] "Probability of license agreement establishment" indicates the probability that a license agreement regarding patented technology will be established.

[0563] "Market size" refers to the size of the potential market when the patented technology is commercially exploited.

[0564] "Estimated share" means the share that the patented technology is expected to occupy in a particular market.

[0565] "Expected return" refers to the expected value of market revenue, royalties, and other revenues from patented technology.

[0566] "Patent application costs" refer to the costs required to apply for a patent.

[0567] "Patent application decision" means the process of deciding whether to file a patent application based on the evaluated parameters and expected return.

[0568] "Electronic payment service" refers to a service for conducting economic transactions using electronic means.

[0569] "Investment Idea" means a concept or strategy for investment purposes relating to a new technology, product or service.

[0570] "Go-to-market" refers to the process of introducing new technologies or products to the market.

[0571] MODE FOR CARRYING OUT THE INVENTION

[0572] The system of this invention uses a generative artificial intelligence model to evaluate the probability of successful patent registration, the probability of concluding a license agreement, the market size and estimated share of an investment idea in electronic payment services, and then makes optimal decisions about patent applications based on the results.

[0573] Program processing explanation

[0574] Details of hardware, software, data processing and calculation

[0575] The present invention is implemented in an environment where a server and a user terminal are mainly used. The specific hardware and software configurations are as follows.

[0576] 1. User Interface (UI)

[0577] Hardware used: Smartphone

[0578] Software used: Flutter (UI framework)

[0579] Users use a form to enter details of their investment idea (idea description, market size, estimated share, royalty rate, preliminary screening score, etc.) This data is sent from the device to the cloud server.

[0580] 2. Data transmission and storage

[0581] Hardware used: Cloud server (e.g. AWS Lambda)

[0582] Software used: Django (backend framework)

[0583] The data received from the device is sent to a cloud server and stored securely.

[0584] 3. Idea Evaluation

[0585] Hardware used: Cloud server

[0586] Software used: PyTorch (to run the generative AI model)

[0587] Using a generative artificial intelligence model (e.g., GPT-4), we evaluate the probability of successful patent registration, the probability of concluding a license agreement, market size, estimated share, and royalty rate.

[0588] 4. Expected return calculation

[0589] Hardware used: Cloud server

[0590] Software used: NumPy (numerical calculation library)

[0591] The expected revenue is calculated based on the evaluated parameters and a decision is made on whether to apply for a patent.

[0592] 5. Displaying the results

[0593] Hardware used: Smartphone

[0594] Software used: Flutter

[0595] The calculation results (expected revenue, patent application recommendation / non-recommendation, etc.) are displayed to the user.

[0596] Specific examples

[0597] For example, a user inputs the following investment idea:

[0598] | Item | Value |

[0599] |-----------------|-----------------------------|

[0600] | Idea Description | Electronic Payment System with New Security Features |

[0601] | Market size | 100 million yen |

[0602] | Estimated share | 10% |

[0603] | Royalty Rate | 5% |

[0604] | First Screening Score | 85 |

[0605] Based on this data, we send the following prompt to the generative AI model:

[0606] For the following ideas, please evaluate the probability of successful patent registration, probability of successful licensing, market size, estimated market share, and royalty rate, and calculate the expected revenue.

[0607] Idea details: Electronic payment system with new security features, market size: 100 million yen, estimated share: 10%, royalty rate: 5%, initial review score: 85

[0608] The generative AI model performs the evaluation and returns the results to the server. The results are displayed on the terminal, and the user makes a decision on patent application. In this way, the evaluation of investment ideas and the optimization of patent applications are carried out quickly and efficiently.

[0609] The above is a detailed description of the mode for carrying out the present invention.

[0610] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0611] Step 1:

[0612] The user uses a smartphone to input details of an investment idea (idea description, market size, estimated share, royalty rate, preliminary screening score, etc.). This input data is collected by a form and sent to the server. The input data includes detailed information about the idea and numerical information such as market size. This data is sent via the device's UI (Flutter).

[0613] Step 2:

[0614] The server securely stores the received user input data. The hardware used is a cloud server, and the software used is Django. The details of the user's investment ideas are recorded in a database and stored. This process ensures that the data is encrypted and stored securely.

[0615] Step 3:

[0616] Based on the stored data, the server uses a generative artificial intelligence model (e.g., GPT-4) to evaluate the probability of successful patent registration, the probability of a license agreement being concluded, the market size, estimated share, and royalty rate. For this evaluation, Python is used, running the PyTorch library. The server converts the input data into a prompt format and passes it to the generative artificial intelligence model. Specifically, the prompt is as follows: "For the following idea, please evaluate the probability of successful patent registration, the probability of a license agreement being concluded, the market size, estimated share, and royalty rate, and calculate the expected revenue. Idea details: Electronic payment system with new security features, market size: 100 million yen, estimated share: 10%, royalty rate: 5%, initial review score: 85." The output data is the various evaluation results.

[0617] Step 4:

[0618] The server calculates expected revenue based on the evaluation results. The hardware used is a cloud server, and the software used is NumPy (a numerical calculation library). The input data used for the calculation is the evaluation results output by the generative artificial intelligence model. Specifically, it calculates market revenue (market size x estimated share) and expected revenue (market revenue x probability of license agreement establishment x royalty rate). The output data is the expected value of the return.

[0619] Step 5:

[0620] The server compares the expected return obtained as a result of the calculation with the patent application cost and determines whether to recommend or not to apply for a patent. The input data used are the expected revenue and patent application cost (1.2 million yen) calculated in step 4. The output data is the decision result on whether to recommend or not to apply for a patent.

[0621] Step 6:

[0622] The server displays the results of the decision to the smartphone user. The hardware used is a smartphone, and the software used is Flutter (a UI framework). The displayed information includes expected revenue, whether or not to file a patent application, and evaluated parameters. Based on this information, the user can make a final decision on whether or not to file a patent application.

[0623] The above processing steps enable the evaluation of investment ideas and the optimization of patent applications to be carried out quickly and efficiently.

[0624] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0625] This invention combines an emotion engine with a system that uses a generative artificial intelligence model to evaluate submitted ideas and optimize patent application decisions. Specifically, this system recognizes the user's emotions and reflects them in the evaluation and feedback of ideas, enabling more appropriate patent application decisions. The program's processing is explained in natural language below, with specific examples provided for further details.

[0626] 1. Collect and enter ideas

[0627] The user uses the device to input detailed information about the idea, including the idea's name, content, market size, estimated share, royalty rate, and initial review score. The device also uses an emotion engine to recognize the user's emotional state in real time. The user's emotional data is collected through facial recognition and voice analysis, and is also sent to the server.

[0628] 2. Integrating Idea Ratings and Sentiment Data

[0629] The server operates a generative AI model and emotion engine based on the received idea information and emotion data. The generative AI model predicts the probability of successful patent registration, the probability of license agreement establishment, market size, and royalty rate based on the input market size, estimated market share, and first-stage review score. Meanwhile, the emotion engine analyzes the user's emotion data and evaluates how confident or stressed the user is about their idea. This emotion evaluation is fed back into the idea evaluation results. For example, if the user shows optimistic emotions, the risk assessment will be stricter.

[0630] 3. Calculating and adjusting expected returns

[0631] The server calculates the expected return based on the evaluation results using the following formula:

[0632] Market Revenue = Market Size Estimated Share

[0633] Expected revenue = Market revenue Probability of license agreement establishment Royalty rate

[0634] Furthermore, the expected revenue is adjusted based on the user's emotional data. If the user is overconfident, a more conservative forecast is made, and if the user is stressed, feedback is given to improve the user's care.

[0635] 4. Patent Application Judgment

[0636] The server compares the calculated expected return with the cost of filing a patent application. The standard patent application cost is 1.2 million yen, consisting of 300,000 yen for application costs and 900,000 yen for registration costs. If the expected return exceeds this standard, the server decides to proceed with the patent application. This decision also takes into account the user's emotional data, providing optimal support to the user.

[0637] 5. User Feedback

[0638] The server then sends the judgment results for the patent application to the device. Feedback based on the user's emotional state, analyzed by the emotion engine, is also provided. For example, if the user is losing confidence in their idea, the server may provide encouraging messages or suggestions for improvement.

[0639] 6. Ongoing evaluation and monitoring

[0640] Even after a patent application is filed, the server continues to monitor market trends and periodically evaluates the user's emotional state using an emotion engine. It collects market data and user emotional changes to evaluate the patent's competitive advantage and the need for maintenance. It reevaluates the patent within three years of filing to determine whether it needs to be maintained. This process optimizes patent maintenance costs and increases user satisfaction.

[0641] Specific examples

[0642] For example, suppose a user inputs an idea for a new, innovative product into a terminal, along with a market size of 100 million yen, an estimated market share of 10%, a royalty rate of 5%, and a first-stage review score of 85. In addition to this data, the terminal also detects the user's smile and tone of voice and determines their confidence. Using a generative AI model and an emotion engine, the server predicts a 70% probability of successful patent registration, a 50% probability of license agreement establishment, a market size of 50 billion yen, an estimated market share of 10%, and a royalty rate of 5%. Based on the emotion data, the server adjusts the risk assessment somewhat more stringently and calculates the final expected revenue to be 120 million yen. Because this exceeds the patent application cost of 1.2 million yen, the decision is made to proceed with the patent application. At the same time, the user is given feedback stating, "This idea has high potential, and we recommend filing a patent application."

[0643] The above is a concrete example of how to implement this invention. By using this system, an evaluation process that takes into account the user's feelings can be realized, making it possible to maximize the value of ideas while optimizing patent-related costs.

[0644] The processing flow will be explained below.

[0645] Step 1:

[0646] The user inputs detailed information about their idea using a terminal, including the idea's name, content, market size, estimated share, royalty rate, and initial review score, and the system also collects the user's voice and facial expression data to detect their emotional state.

[0647] Step 2:

[0648] The device sends detailed information about the idea and emotional data to the server using a secure communication protocol.

[0649] Step 3:

[0650] The server runs a generative AI model based on the data it receives. Specifically, it predicts the probability of successful patent registration, the probability of a license agreement being concluded, the market size, and royalty rates based on the market size, estimated market share, and first-stage examination score.

[0651] Step 4:

[0652] The server uses an emotion engine to analyze the user's emotional data. The analysis results include an emotional state indicating whether the user is optimistic or pessimistic. Based on this result, the reliability and risk assessment of the idea evaluation are adjusted.

[0653] Step 5:

[0654] The server combines the evaluation results of the generative AI model with the analysis results of the emotion engine to calculate the expected value of the return. It calculates market revenue from the market size and estimated share, and calculates the expected revenue by multiplying the probability of a license agreement being concluded by the royalty rate. It then makes a final calculation of the expected value of the return adjusted based on the emotion data.

[0655] Step 6:

[0656] The server compares the expected return with the cost of filing a patent application. The server uses the application cost of 300,000 yen and the registration cost of 900,000 yen as the standard, totaling 1.2 million yen, and makes a decision to recommend filing a patent application if the expected return exceeds this.

[0657] Step 7:

[0658] The server sends the patent application decision result to the terminal, which includes whether to proceed with the patent application, detailed evaluation parameters, and feedback from the emotion engine.

[0659] Step 8:

[0660] The terminal displays the judgment results and feedback for the patent application received from the server to the user, who can then check the results through the terminal and decide on the next action if necessary.

[0661] Step 9:

[0662] The server runs a process to continuously monitor market trends even after a patent application has been filed, and periodically evaluates the user's emotional state using an emotion engine to collect data to confirm the need to maintain the patent.

[0663] Step 10:

[0664] The server will reevaluate the patent within three years of filing and determine whether it is necessary to maintain the patent. Based on market conditions and the user's sentiment evaluation, the server will make a final decision on whether to maintain the patent and send the result to the terminal.

[0665] The above is the specific flow of program processing in this system. This detailed step-by-step process efficiently carries out a series of decisions, from idea evaluation to patent application and patent maintenance, and provides optimal support that takes user feelings into consideration.

[0666] Example 2

[0667] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0668] Conventional patent evaluation systems use generative artificial intelligence models to objectively evaluate submitted ideas. However, because they do not consider the emotions and intentions of the user who submitted the idea, the evaluation results can sometimes deviate from the user's actual intentions and emotions. This can lead to lower user satisfaction and potentially undermine motivation to pursue patent applications. Furthermore, while there are methods for monitoring market fluctuations after a patent application to evaluate the patent's competitive advantage, these systems lack reevaluation or feedback that takes into account the user's emotional state, which can lead to problems in alleviating user stress and anxiety. Therefore, there is a need for a system that optimizes patent application decisions and improves user satisfaction through idea evaluation and continuous feedback that takes into account the user's emotions.

[0669] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: a means for inputting detailed idea information and emotional data entered by a user using a terminal into a generative AI model; a means for using the generative AI model to evaluate the probability of successful patent registration, license agreement establishment, market size, and estimated share for the submitted idea; a means for calculating an expected return based on the evaluated parameters and emotional data; a means for adjusting the expected return for a patent application by incorporating the emotional data; and a means for comparing the adjusted expected return with patent application costs to make a decision on whether to apply for a patent. This realizes an evaluation process that takes user emotions into account, enabling the optimization of patent-related costs while maximizing the value of the idea. A "user" is a person who inputs detailed idea information and emotional data.

[0670] A "terminal" is a device that allows a user to input detailed information about an idea and collect emotional data.

[0671] "Detailed idea information" is information entered by the user using a terminal, including the name of the idea, its contents, market size, estimated share, royalty rate, and initial screening score.

[0672] "Emotion data" is data that indicates the emotional state of the user analyzed from facial expressions and voice collected by the terminal.

[0673] A "generative artificial intelligence model" is a part of artificial intelligence technology used to evaluate ideas, and is a model for predicting the probability of successful patent registration, the probability of concluding a license agreement, market size, and estimated share.

[0674] "Expected return" is the expected revenue for a patent application calculated based on the evaluated parameters and sentiment data.

[0675] The "adjusted expected return" is a numerical value that reflects the emotional data and modifies the expected return based on the user's emotional state.

[0676] "Patent application costs" refers to the costs required for patent application and registration, and specifically includes application costs and registration costs.

[0677] "Patent application decision" is a process in which the server compares the calculated expected return with the cost of filing a patent application and determines whether to recommend filing a patent application.

[0678] "Market fluctuations" refer to changes in market size and competitive conditions, and are factors that affect the competitive advantage of patents.

[0679] The "necessity of maintaining a patent" is a criterion for evaluating the competitive advantage and market value of a patent and deciding whether to maintain the patent.

[0680] The above are definitions of important words.

[0681] The present invention is a system for optimizing patent application decisions using a generative artificial intelligence model, and by collecting and integrating user emotional data into the evaluation process, it provides more appropriate feedback to the user. Detailed modes for implementing the invention are described below.

[0682] 1. Collect and enter ideas

[0683] Users use the device to input detailed information about their ideas, including the idea's name, content, market size, estimated share, royalty rate, and initial review score. The device is equipped with an emotion engine that collects the user's emotional data in real time as they input information. The data is collected by analyzing the user's facial expressions and voice using the device's built-in camera and microphone. The user's emotional state is then digitized and sent to the server along with the idea information.

[0684] 2. Integrating Idea Ratings and Sentiment Data

[0685] The server operates a generative AI model and emotion engine based on the received idea information and emotion data. The generative AI model predicts the probability of successful patent registration, the probability of license agreement establishment, market size, and royalty rate based on data such as market size, estimated market share, and initial review score. Meanwhile, the emotion engine analyzes the collected emotion data and evaluates the user's emotional state. For example, if the user is feeling confident or anxious, each emotional state is fed back into the evaluation results.

[0686] 3. Calculating and adjusting expected returns

[0687] The server calculates the expected return based on the evaluation results using the following formula:

[0688] Market Revenue = Market Size Estimated Share

[0689] Expected revenue = Market revenue Probability of license agreement establishment Royalty rate

[0690] Furthermore, the expected revenue is adjusted based on the user's emotional data. If the user is overconfident, a more conservative forecast is made, and if the user is stressed, feedback is given to improve the user's care.

[0691] 4. Patent Application Judgment

[0692] The server compares the calculated expected return with the cost of filing a patent application. The standard patent application cost is 1.2 million yen, consisting of 300,000 yen for application costs and 900,000 yen for registration costs. If the expected return exceeds this standard, the server recommends filing a patent application. This decision also takes into account the user's emotional data, providing optimal support to the user.

[0693] 5. User Feedback

[0694] The server then sends the judgment result of the patent application to the terminal. The judgment result is not only provided, but also feedback based on the user's emotional state as analyzed by the emotion engine. For example, if the user is losing confidence in their idea, the server may provide an encouraging message or suggestions for improvement.

[0695] 6. Ongoing evaluation and monitoring

[0696] Even after a patent application is filed, the server continues to monitor market fluctuations and periodically evaluates the user's emotional state using an emotion engine. It collects market data and user emotional changes to evaluate the patent's competitive advantage and the need for maintenance. It reevaluates the patent within three years of filing to determine whether it needs to be maintained. This process optimizes patent maintenance costs and increases user satisfaction.

[0697] Specific examples

[0698] For example, suppose a user inputs an idea for a new, innovative product into a terminal. Specifically, the inputs are a market size of 100 million yen, an estimated market share of 10%, a royalty rate of 5%, and a first-stage review score of 85. At the same time, the terminal detects the user's smile and tone of voice and determines their confidence. Using a generative AI model and an emotion engine, the server predicts a 70% probability of successful patent registration, a 50% probability of license agreement establishment, a market size of 50 billion yen, an estimated market share of 10%, and a royalty rate of 5%. Based on the emotion data, the server adjusts the risk assessment somewhat more stringently and calculates the final expected revenue to be 120 million yen. Because this exceeds the patent application cost of 1.2 million yen, the decision is made to proceed with the patent application. At the same time, the user is given feedback stating, "This idea has high potential, and we recommend filing a patent application."

[0699] Prompt Sentence Examples

[0700] The prompt to input a "new innovative product idea" into the generative AI model is as follows:

[0701] Evaluate new and innovative product ideas.

[0702] Market size: 100 million yen

[0703] Estimated share: 10%

[0704] Royalty rate: 5%

[0705] First round score: 85

[0706] Emotion Recognition: Confident

[0707] By using this prompt, the generative artificial intelligence model can evaluate the appropriate ideas.

[0708] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0709] Program processing flow

[0710] Step 1: User enters idea details using a terminal

[0711] The user enters the name, content, market size, estimated share, royalty rate, and initial review score of the idea into the input screen of the terminal. The input data is in text format and divided into specific fields. This allows the user's idea to be recorded quantitatively and qualitatively. Input: Detailed information about the idea, Output: Detailed information about the idea data.

[0712] Step 2: The device uses the emotion engine to collect the user's emotion data.

[0713] While the user is inputting their ideas, the device uses the built-in camera and microphone to analyze the user's facial expressions and voice in real time. The emotion engine uses facial recognition and voice analysis algorithms to quantify the user's emotional state. Input: User's facial and voice data, Output: Emotion data.

[0714] Step 3: The user confirms the information they entered and the device sends it to the server

[0715] The user checks the input and presses the send button to send the data to the server. The device sends detailed idea data and emotion data in JSON format to the server. Input: Send instruction, Output: Data sent to the server.

[0716] Step 4: The server analyzes the received idea information

[0717] The server parses the received data and stores it in a database, converting the values ​​of each field to the appropriate data type and preparing it for evaluation. Input: Data sent to the server, Output: Parsed and stored data.

[0718] Step 5: The server inputs the emotion data into the generative AI model

[0719] The server uses the emotion data as input data for the generative AI model, which uses a pre-trained neural network. Input: Emotion data, Output: Emotion data converted into a data format for model input.

[0720] Step 6: The server runs the generative AI model and evaluates the ideas.

[0721] The server launches a generative AI model and predicts the probability of successful patent registration, the probability of a license agreement being concluded, the market size, and royalty rates based on input data such as market size, estimated market share, and first review score. Input: Detailed idea information and converted emotion data, Output: Idea evaluation results.

[0722] Step 7: The server uses the emotion engine to analyze the user's emotion data and integrate it into a rating.

[0723] The server uses an emotion engine to analyze the user's emotional data and evaluate how confident or stressed the user is about their idea. This result is integrated into the idea evaluation results as feedback. Input: User's emotional data and idea evaluation results. Output: Integrated evaluation results.

[0724] Step 8: The server calculates the expected return based on the evaluation results.

[0725] The server calculates the expected revenue using the following formula:

[0726] Market Revenue = Market Size Estimated Share

[0727] Expected revenue = Market revenue Probability of license agreement establishment Royalty rate

[0728] Input: Integrated valuation results, Output: Calculated expected profit.

[0729] Step 9: The server adjusts the expected revenue taking into account the sentiment data

[0730] The server considers the user's emotional data and makes conservative predictions if the user is overconfident, or adjusts the expected revenue while providing caring feedback if the user is feeling stressed. Input: Calculated expected revenue and emotional data, Output: Adjusted expected revenue.

[0731] Step 10: The server compares the calculated expected revenue with the patent application cost and makes a decision on whether to apply for the patent.

[0732] The server evaluates whether the adjusted expected revenue exceeds the standard patent application cost (1.2 million yen) and determines whether to recommend a patent application. Input: adjusted expected revenue and patent application cost, Output: judgment on whether to apply for a patent.

[0733] Step 11: The server sends the result of the decision to the terminal.

[0734] The server generates a result based on the patent application decision in JSON format and sends it to the user's device. This includes the decision result as well as a feedback message based on the user's emotional state. Input: Patent application approval / disapproval decision, Output: Results and feedback sent to the user's device.

[0735] Step 12: User Feedback

[0736] The user receives the results on the terminal and checks the displayed feedback message. For example, if there is a high possibility of success, the message "We recommend you apply for a patent" will be displayed, and if they are feeling less confident, the message will include encouragement and suggestions for improvement. Input: Results and feedback sent from the server. Output: Feedback message displayed on the terminal.

[0737] Step 13: Ongoing evaluation and monitoring after patent application

[0738] The server continues to monitor market fluctuations even after the patent application has been filed, and periodically evaluates the user's emotional state using an emotion engine. A reevaluation is performed within three years to determine whether the patent should be maintained. Input: Market data and emotion data. Output: Reevaluation results and decision on whether to maintain the patent.

[0739] (Application example 2)

[0740] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0741] Conventional patent evaluation systems evaluate ideas without taking the user's emotional state into account, resulting in evaluation results that do not necessarily match the user's actual intentions or circumstances. Furthermore, because emotional data is not used in the evaluation process, appropriate feedback cannot be provided to the user, potentially resulting in suboptimal decisions on patent applications. In response to these issues, the present invention aims to provide a system that integrates user emotional data to provide more appropriate evaluations and feedback.

[0742] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for evaluating the probability of successful patent registration, probability of license agreement establishment, market size, and estimated share of a submitted idea using a generative artificial intelligence model; means for calculating an expected return on a patent application based on the evaluated parameters; means for comparing the expected return with the patent application cost and making a decision on the patent application; emotion recognition means for collecting and analyzing user emotion data; and means for integrating the emotion data obtained by the emotion recognition means into the evaluation and feeding it back into the evaluation result. This allows the evaluation of the submitted idea to reflect the user's emotional state, making it possible to make a more appropriate decision on the patent application.

[0743] A "generative artificial intelligence model" refers to an artificial intelligence algorithm designed to generate new information or predictions based on data.

[0744] "Probability of successful patent registration" refers to the probability that a submitted idea will be granted a patent.

[0745] The "probability of a license agreement being concluded" refers to the probability that, after a patent is obtained, a contract will be concluded to provide the technology or idea to other companies or individuals under a license agreement.

[0746] "Market size" refers to the economic size or value of the entire target market for a particular idea or product.

[0747] "Estimated share" refers to the percentage of the market that the submitted idea or product is expected to occupy.

[0748] "Expected return" refers to the expected amount of profit that an investment in a patent application will bring in the future.

[0749] "Patent application costs" refers to the set of expenses required to apply for a patent.

[0750] "User emotional data" refers to data that indicates the user's emotional state, as obtained through the user's facial expressions, voice, and other physiological data.

[0751] "Emotion recognition means" refers to technology and devices for detecting and analyzing a user's emotions.

[0752] "Means of providing feedback to evaluation results" refers to techniques and methods for reflecting analyzed emotional data in the evaluation process and improving the final evaluation results.

[0753] This invention is a system that uses a generative artificial intelligence model to evaluate submitted feedback and optimize store operations. By recognizing user emotions and reflecting them in the feedback, it is possible to make more appropriate operational decisions. A detailed description of this system is provided below.

[0754] composition

[0755] 1. User Device

[0756] Hardware: Computer, smartphone, smart glasses, or head-mounted display for feedback input.

[0757] Software: A camera to capture the user's face, and an emotion recognition application to collect emotional data.

[0758] 2. Server

[0759] Hardware: High-performance servers.

[0760] Software: Generative AI models, emotion recognition engines, and evaluation and feedback systems.

[0761] Program processing

[0762] The program of this system performs the following main processes.

[0763] 1. Data collection: The user device captures facial expressions and voice along with the customer feedback text to collect emotional data. This emotional data is analyzed in real time and sent to the server.

[0764] Software used: OpenCV (for face recognition), Transformers (Hugging Face emotion analysis model).

[0765] 2. Data analysis: On the server side, a generative AI model evaluates the characteristics of the submitted feedback and analyzes the emotion data obtained by the emotion recognition means.

[0766] Generative artificial intelligence model used: Transformers (Hugging Face generative model).

[0767] 3. Evaluation and integration: The analyzed emotion data is fed back into the evaluation results, and a final evaluation is made.

[0768] Example of feedback: Based on the evaluation results, specific operational improvement instructions such as "Improve the layout and expand the coffee corner" are generated.

[0769] 4. Result feedback: The server sends the evaluation results to the user's device and provides appropriate feedback to the user. For example, if the evaluation result is high, a message such as "This store management approach has a high chance of success!" is displayed.

[0770] Specific examples

[0771] For example, consider a user entering feedback such as, "I like the layout of the store, but the coffee corner is not well-equipped." A webcam captures the customer's face, and an emotion recognition model identifies the expression as "happiness." A generative AI model on the server side generates an evaluation result such as, "Areas for improvement: Improve the layout and expand the coffee corner," and notifies the user as final feedback, "This store management approach has a high chance of success!"

[0772] Prompt Sentence Examples

[0773] A request to develop an application that collects customer feedback and sentiment data and provides suggestions for improving store operations.

[0774] Integrate customer opinions and sentiments to provide optimal feedback to store managers.

[0775] This system allows submitted feedback to reflect the user's emotional state, enabling better decisions to be made about store management.

[0776] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0777] Step 1:

[0778] A user terminal provides an interface for inputting feedback text from a customer. The user inputs the feedback text, and the terminal transmits the text to a server. At this time, the terminal activates a camera and a microphone for collecting emotion data based on the feedback text. The input is the feedback text, and the output is the feedback data transmitted to the server.

[0779] Step 2:

[0780] The device uses a camera and microphone to capture the user's face and voice and collect emotion data. Specifically, the camera captures the user's facial expressions in real time and performs facial recognition using OpenCV. The microphone also records audio and the audio data is analyzed using an emotion recognition engine (Transformers emotion analysis model). The input is the user's face and voice, and the output is emotion data.

[0781] Step 3:

[0782] The device sends the collected emotion data and feedback text to the server. Specifically, the results of facial recognition and voice analysis are sent to the server as structured data. In this process, the input is the user's emotion data and feedback text, and the output is the data sent to the server.

[0783] Step 4:

[0784] The server analyzes the received feedback text and emotion data and inputs them into a generative AI model. Specifically, the generative AI model formats the feedback text and emotion data input, integrates them, and performs evaluation. In this process, the input is the feedback text and emotion data, and the output is the evaluation result.

[0785] Step 5:

[0786] The server generates feedback for optimizing store operations based on the evaluation results of the generative AI model. Specifically, it generates appropriate feedback messages based on the evaluation results and makes adjustments taking into account emotional data. In this process, the inputs are the evaluation results and emotional data, and the output is optimization feedback.

[0787] Step 6:

[0788] The server sends the generated feedback to the user's terminal. Specifically, the optimization feedback is sent in a format that is easy to display immediately to the user. In this process, the input is the optimization feedback, and the output is the feedback display on the terminal.

[0789] Step 7:

[0790] The user terminal displays the feedback received from the server and provides the user with instructions for operational improvement. Specifically, the received feedback message is displayed on the user interface for the user to check. In this process, the input is the feedback message, and the output is the feedback display to the user.

[0791] Through these steps, the system provides feedback that reflects the user's emotional state, optimizing store operations.

[0792] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0793] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0794] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0795] [Third embodiment]

[0796] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0797] 5, the data processing system 310 includes the data processing device 12 and a headset type terminal 314. An example of the data processing device 12 is a server.

[0798] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0799] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0800] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0801] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0802] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0803] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0804] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0805] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0806] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0807] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0808] The system of this invention uses a generative artificial intelligence model to evaluate the probability of successful patent registration, the probability of concluding a license agreement, the market size, and estimated share of a submitted idea, and then makes optimal decisions about patent applications based on the results. Below, the program's processing is explained in natural language.

[0809] 1. Collect and enter ideas

[0810] The user uses the device to input details of their idea for a new product or service, including a description of the idea, projected market size, estimated share, royalty rate, etc., as well as the initial judging score. This data is then sent from the device to the server.

[0811] 2. Evaluating ideas

[0812] Based on the received idea information, the server uses a generative AI model to evaluate the following parameters:

[0813] Probability of successful patent registration

[0814] License agreement success rate

[0815] market size

[0816] Estimated Share

[0817] Royalty Rate

[0818] Generative AI models use algorithms that have learned from past data to predict these parameters probabilistically. For example, they may predict that a certain idea will have a market size of 50 billion yen, an estimated market share of 10%, and a royalty rate of 5%.

[0819] 3. Calculating expected returns

[0820] The server calculates the expected return based on the evaluated parameters, using the following formula:

[0821] Market Revenue = Market Size Estimated Share

[0822] Expected revenue = Market revenue Probability of license agreement establishment Royalty rate

[0823] For example, if an idea has a market size of 50 billion yen, an estimated market share of 10%, a 50% probability of a license agreement being concluded, and a royalty rate of 5%, the market revenue would be 5 billion yen and the expected revenue would be 125 million yen.

[0824] 4. Patent Application Judgment

[0825] The server compares the calculated expected return with the patent application cost. The standard patent application cost is 1.2 million yen, consisting of 300,000 yen for application costs and 900,000 yen for registration costs. If the expected return exceeds this standard, the server decides to proceed with the patent application.

[0826] 5. Continuous evaluation

[0827] Even after a patent application is filed, the server continues to monitor market fluctuations and the patent's competitive advantage. It will reevaluate the patent within three years of filing to determine whether it is necessary to maintain the patent. This process helps reduce unnecessary patent maintenance costs and maximize profits.

[0828] Specific examples

[0829] For example, suppose a user inputs an "idea for a new, innovative product" into a terminal, along with a market size of 100 million yen, an estimated market share of 10%, a royalty rate of 5%, and an initial screening score of 85. The server receives this data and evaluates it using a generative artificial intelligence model. The evaluation results are a 70% probability of successful patent registration, a 50% probability of a license agreement being concluded, a market size of 50 billion yen, an estimated market share of 10%, and a royalty rate of 5%. The server calculates the expected return based on this and determines that the expected profit is 125 million yen. Since this exceeds the patent application cost of 1.2 million yen, the server proceeds with the patent application. Furthermore, market fluctuations are monitored even after the patent application is filed, and a decision is made three years later on whether to maintain the patent.

[0830] The above is a concrete example of how to implement this invention. By using this system, it is possible to efficiently select promising ideas from a large number of ideas, optimizing patent-related costs while maximizing profits.

[0831] The processing flow will be explained below.

[0832] Step 1:

[0833] The user uses the terminal to input detailed information about the idea, including the name of the idea, its content, market size, estimated share, royalty rate, and initial screening score.

[0834] Step 2:

[0835] The device sends the details of the entered idea to the server, using a secure communication protocol.

[0836] Step 3:

[0837] The server runs a generative AI model based on the received data. Specifically, based on the input market size, estimated market share, and first screening score, it predicts the probability of successful patent registration, the probability of license agreement establishment, market size, and royalty rate.

[0838] Step 4:

[0839] Based on the evaluation results obtained from the generative AI model, the server calculates the expected value of the return as follows: First, market revenue is calculated by multiplying the market size by the estimated market share, and then this result is multiplied by the probability of concluding a license agreement and the royalty rate to obtain the expected revenue.

[0840] Step 5:

[0841] The server compares the expected return with the cost of filing a patent application. The cost of filing a patent application is 1.2 million yen, consisting of the application cost of 300,000 yen and the registration cost of 900,000 yen. If the expected return exceeds this cost, the server decides to proceed with the patent application.

[0842] Step 6:

[0843] The server sends the patent application decision result to the terminal, including whether to proceed with the patent application and the evaluated parameters.

[0844] Step 7:

[0845] The terminal displays the judgment results for the patent application received from the server to the user. The user checks the results through the terminal and proceeds to the next step as necessary.

[0846] Step 8:

[0847] The server will implement a process for continuous monitoring of market trends after the patent application is filed, by periodically collecting market data and evaluating the patent's competitive advantage and market fluctuations.

[0848] Step 9:

[0849] The server will conduct continuous evaluation within three years of filing a patent application to determine whether it is necessary to maintain the patent. It will then decide whether to maintain or abandon the patent based on market conditions and send the results to the terminal.

[0850] This is the specific flow of program processing in this system. This detailed step-by-step process efficiently carries out a series of decisions, from idea evaluation to patent application and patent maintenance.

[0851] Example 1

[0852] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0853] With the current patent application judgment system, it is difficult to efficiently select ideas with high patent value from among the many available. Furthermore, inappropriate decisions about whether to maintain a patent due to market fluctuations after a patent application are made result in unnecessary costs. Furthermore, solving these issues requires highly accurate prediction models and continuous monitoring.

[0854] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0855] In this invention, the server includes: means for a user to input details of an idea for a new product or service using a terminal; means for transmitting the input data from the terminal to the server; means for evaluating the probability of successful patent registration, the probability of concluding a license agreement, the market size, and an estimated share using a generative artificial intelligence model based on the idea information received by the server; means for the server to calculate an expected return based on the evaluated parameters; means for comparing the calculated expected return with the patent application cost and making a decision on whether to apply for a patent; means for continuously monitoring market fluctuations and the competitive advantage of the patent even after the patent application has been filed; and means for reevaluating and deciding whether to maintain the patent. This makes it possible to efficiently select promising ideas from a large number of ideas and maximize profits while optimizing patent-related costs.

[0856] A "user" is a person who uses the system to input ideas for new products or services using a terminal.

[0857] A "terminal" is an input device used by a user, which inputs details of an idea and transmits the data to a server.

[0858] A "server" is a central computer system that receives data sent by users and performs evaluations and calculations using generative artificial intelligence models.

[0859] A "generative artificial intelligence model" is an algorithm installed on a server that learns from past data and has the ability to evaluate the probability of successful patent registration, the probability of a license agreement being concluded, market size, and estimated share.

[0860] The "probability of successful patent registration" is the probability that the idea being evaluated will be officially registered as a patent.

[0861] The "probability of license agreement establishment" is the probability that a license agreement based on the idea being evaluated will be established.

[0862] "Market size" is a numerical representation of the size of the entire market related to the idea being evaluated.

[0863] "Estimated Share" is the predicted share of the overall market that the idea being evaluated will occupy, expressed as a percentage.

[0864] "Expected return" is the revenue expected based on the idea being evaluated, calculated using factors such as the probability of successful patent registration, the probability of a license agreement being concluded, market size, estimated share, and royalty rate.

[0865] "Patent application costs" are the costs incurred from filing a patent application to registering it, and include application costs and registration costs.

[0866] "Patent application decision" refers to comparing expected revenue with the cost of patent application and deciding whether to apply for a patent.

[0867] "Monitoring" refers to the continuous monitoring of market fluctuations and the competitive advantage of patents after a patent application has been filed.

[0868] "Reevaluation" means reanalyzing data at regular intervals after a patent application is filed to determine whether it is necessary to maintain the patent.

[0869] The present invention relates to a system for improving the efficiency of patent application decisions and optimizing patent-related costs. Specific embodiments for carrying out the present invention will be described below.

[0870] 1. Collecting and inputting ideas

[0871] A user uses a terminal to input details of an idea for a new product or service. The information input by the user includes a description of the idea, a projected market size, an estimated share, a royalty rate, and an initial review score. This information is specifically entered and formatted in an input form on the terminal.

[0872] 2. Data transmission

[0873] The entered data is sent from the device to the server using an HTTP POST request, and the API ensures that the data is sent in the correct format to reach the server.

[0874] 3. Evaluate ideas

[0875] The server stores the received data in a database management system (e.g., MySQL or PostgreSQL). Next, the server uses a generative AI model to evaluate the probability of successful patent registration, the probability of a license agreement being concluded, and the market size and estimated share. The generative AI model is built using a deep learning framework such as TensorFlow or PyTorch, and performs evaluations using algorithms based on past data.

[0876] 4. Calculating expected returns

[0877] The server calculates the expected return based on the evaluated parameters, using the following formula:

[0878] Market Revenue = Market Size Estimated Share

[0879] Expected revenue = Market revenue Probability of license agreement establishment Royalty rate

[0880] For example, if the evaluation results are a market size of 50 billion yen, an estimated market share of 10%, a 50% probability of a license agreement being concluded, and a royalty rate of 5%, then the market revenue will be 5 billion yen and the expected revenue will be 125 million yen.

[0881] 5. Patent Application Judgment

[0882] The server compares the calculated expected revenue with the patent application cost (application cost of 300,000 yen and registration cost of 900,000 yen, totaling 1.2 million yen) and makes a decision on whether to apply for a patent. If the expected revenue exceeds the patent application cost, the server decides to proceed with the patent application and notifies the user of the result. Notification methods include displaying an alert on the device or sending an email.

[0883] 6. Continuous evaluation

[0884] Even after a patent application is filed, the server continuously monitors market fluctuations and the patent's competitive advantage. This includes regularly obtaining the latest market information through data feeds and APIs. A reevaluation is conducted within three years of filing the patent application to determine whether the patent needs to be maintained. This allows you to reduce unnecessary patent maintenance costs and maximize profits.

[0885] Specific examples

[0886] For example, suppose a user inputs an "idea for a new, innovative product" into a terminal, along with a market size of 100 million yen, an estimated market share of 10%, a royalty rate of 5%, and an initial screening score of 85. The server receives this data and evaluates it using a generative artificial intelligence model. The evaluation results are a 70% probability of successful patent registration, a 50% probability of a license agreement being concluded, an estimated market size of 50 billion yen, an estimated market share of 10%, and a royalty rate of 5%. The server calculates the expected return based on this and determines that the expected profit is 125 million yen. Since this exceeds the patent application cost of 1.2 million yen, the server decides to proceed with the patent application. Furthermore, market fluctuations are monitored even after the patent application is filed, and a decision is made three years later on whether to maintain the patent.

[0887] Prompt Sentence Examples

[0888] Specifically, you might use a prompt like this:

[0889] "Please enter your idea for a new, innovative product. Please enter the market size, estimated share, and royalty rate in numerical form, as well as your initial screening score."

[0890] The above is a specific embodiment for carrying out the present invention. By using this system, it is possible to efficiently select promising ideas from a large number of ideas, optimizing patent-related costs while maximizing profits.

[0891] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0892] Step 1:

[0893] A user uses a terminal to input details of an idea for a new product or service, including the following information:

[0894] Idea description (text format)

[0895] Estimated market size (numerical format)

[0896] Estimated share (percentage format)

[0897] Royalty Rate (Percentage Format)

[0898] First screening score (numerical format)

[0899] Specifically, the user enters this information into the input form and clicks the submit button. The input information is then formatted by the terminal software.

[0900] Input: User-entered details about the idea

[0901] Output: Formatted data

[0902] Step 2:

[0903] The device sends the entered data to the server using an HTTP POST request, which contains all the entered information in JSON format.

[0904] Specifically, the terminal converts the data into an appropriate format (JSON format) and sends it to the server's API endpoint.

[0905] Input: Formatted data

[0906] Output: Request data sent to the server

[0907] Step 3:

[0908] The server receives the data sent from the terminal and stores it in a database management system (e.g., MySQL or PostgreSQL).

[0909] Specifically, the server parses the received data and executes SQL queries to store it in a database.

[0910] Input: The request data sent

[0911] Output: Data stored in the database

[0912] Step 4:

[0913] The server reads the stored data and inputs it into a generative artificial intelligence model, which is built using TensorFlow and PyTorch. The model evaluates the probability of successful patent registration, the probability of a license agreement being concluded, and the market size and estimated share.

[0914] Specifically, the server uses SQL queries to retrieve data from the database and convert it into a format that can be input to the model. The generative AI model makes predictions based on past data and returns the output.

[0915] Input: Data retrieved from the database

[0916] Output: Evaluated parameters (probability values, numerical values)

[0917] Step 5:

[0918] The server calculates the expected return based on the evaluated parameters using the following formula:

[0919] Market Revenue = Market Size Estimated Share

[0920] Expected revenue = Market revenue Probability of license agreement establishment Royalty rate

[0921] Specifically, the server uses the evaluated parameters to execute program code that executes the calculation formula and calculates the expected profit.

[0922] Input: Evaluated parameters

[0923] Output: Calculated expected return

[0924] Step 6:

[0925] The server compares the calculated expected profit with the patent application cost and makes a decision on whether to apply for a patent. The patent application cost is 1.2 million yen in total, consisting of the application cost of 300,000 yen and the registration cost of 900,000 yen.

[0926] Specifically, the server executes program code with logic that compares the calculated expected profit with the patent application cost and determines whether or not to apply for a patent. The server then notifies the user of the result of this determination.

[0927] Inputs: Calculated expected revenue, patent application costs

[0928] Output: Patent application decision result (promotion / postponement)

[0929] Step 7:

[0930] The server continuously monitors market fluctuations and the competitive advantages of patents even after the patent application has been filed, including the ability to regularly retrieve the latest market information via data feeds and APIs.

[0931] Specifically, the server runs a program that periodically retrieves information from external data sources and updates the status of patents.

[0932] Input: Market information from external data sources

[0933] Output: Updated market and patent landscape data

[0934] Step 8:

[0935] The server will re-evaluate the patent within three years of filing to determine whether it is necessary to maintain the patent. This re-evaluation will again use the generative AI model to make predictions based on the latest data.

[0936] Specifically, the server executes program code that performs data reanalysis and patent maintenance decisions according to the reevaluation schedule.

[0937] Input: Latest market and patent data

[0938] Output: Patent maintenance decision result (maintain / abandon)

[0939] (Application example 1)

[0940] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0941] In the field of electronic payment services, it has been difficult to accurately evaluate the probability of successful patent registration and market feasibility of investment ideas, and to quickly and efficiently make appropriate patent application decisions. In particular, selecting promising investment ideas from the many submitted and optimizing patent-related costs while maximizing profits requires a great deal of time and effort. Unless this challenge is resolved, electronic payment service providers are likely to incur unnecessary patent maintenance costs and opportunity losses.

[0942] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0943] In this invention, the server includes means for using a generative artificial intelligence model to evaluate the probability of successful patent registration, the probability of concluding a license agreement, the market size, and an estimated share of a submitted idea, means for calculating an expected return on a patent application based on the evaluated parameters, means for comparing the expected return with the patent application cost and making a decision on whether to apply for a patent, and means for allowing a user to propose an investment idea in the electronic payment service and evaluating whether it is worthy of patent registration or market launch. This enables the evaluation of investment ideas and decisions on patent applications in the electronic payment service to be made quickly and efficiently, thereby optimizing patent-related costs and maximizing profits.

[0944] A "generative artificial intelligence model" refers to an artificial intelligence algorithm that makes predictions and evaluations based on collected data.

[0945] "Submitted Idea" means a concept for a new product or service conceived by a User.

[0946] "Probability of successful patent registration" refers to the probability that a patent application will be granted as a patent.

[0947] "Probability of license agreement establishment" indicates the probability that a license agreement regarding patented technology will be established.

[0948] "Market size" refers to the size of the potential market when the patented technology is commercially exploited.

[0949] "Estimated share" means the share that the patented technology is expected to occupy in a particular market.

[0950] "Expected return" refers to the expected value of market revenue, royalties, and other revenues from patented technology.

[0951] "Patent application costs" refer to the costs required to apply for a patent.

[0952] "Patent application decision" means the process of deciding whether to file a patent application based on the evaluated parameters and expected return.

[0953] "Electronic payment service" refers to a service for conducting economic transactions using electronic means.

[0954] "Investment Idea" means a concept or strategy for investment purposes relating to a new technology, product or service.

[0955] "Go-to-market" refers to the process of introducing new technologies or products to the market.

[0956] MODE FOR CARRYING OUT THE INVENTION

[0957] The system of this invention uses a generative artificial intelligence model to evaluate the probability of successful patent registration, the probability of concluding a license agreement, the market size and estimated share of an investment idea in electronic payment services, and then makes optimal decisions about patent applications based on the results.

[0958] Program processing explanation

[0959] Details of hardware, software, data processing and calculation

[0960] The present invention is implemented in an environment where a server and a user terminal are mainly used. The specific hardware and software configurations are as follows.

[0961] 1. User Interface (UI)

[0962] Hardware used: Smartphone

[0963] Software used: Flutter (UI framework)

[0964] Users use a form to enter details of their investment idea (idea description, market size, estimated share, royalty rate, preliminary screening score, etc.) This data is sent from the device to the cloud server.

[0965] 2. Data transmission and storage

[0966] Hardware used: Cloud server (e.g. AWS Lambda)

[0967] Software used: Django (backend framework)

[0968] The data received from the device is sent to a cloud server and stored securely.

[0969] 3. Idea Evaluation

[0970] Hardware used: Cloud server

[0971] Software used: PyTorch (to run the generative AI model)

[0972] Using a generative artificial intelligence model (e.g., GPT-4), we evaluate the probability of successful patent registration, the probability of concluding a license agreement, market size, estimated share, and royalty rate.

[0973] 4. Expected return calculation

[0974] Hardware used: Cloud server

[0975] Software used: NumPy (numerical calculation library)

[0976] The expected revenue is calculated based on the evaluated parameters and a decision is made on whether to apply for a patent.

[0977] 5. Displaying the results

[0978] Hardware used: Smartphone

[0979] Software used: Flutter

[0980] The calculation results (expected revenue, patent application recommendation / non-recommendation, etc.) are displayed to the user.

[0981] Specific examples

[0982] For example, a user inputs the following investment idea:

[0983] | Item | Value |

[0984] |-----------------|-----------------------------|

[0985] | Idea Description | Electronic Payment System with New Security Features |

[0986] | Market size | 100 million yen |

[0987] | Estimated share | 10% |

[0988] | Royalty Rate | 5% |

[0989] | First Screening Score | 85 |

[0990] Based on this data, we send the following prompt to the generative AI model:

[0991] For the following ideas, please evaluate the probability of successful patent registration, probability of successful licensing, market size, estimated market share, and royalty rate, and calculate the expected revenue.

[0992] Idea details: Electronic payment system with new security features, market size: 100 million yen, estimated share: 10%, royalty rate: 5%, initial review score: 85

[0993] The generative AI model performs the evaluation and returns the results to the server. The results are displayed on the terminal, and the user makes a decision on patent application. In this way, the evaluation of investment ideas and the optimization of patent applications are carried out quickly and efficiently.

[0994] The above is a detailed description of the mode for carrying out the present invention.

[0995] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0996] Step 1:

[0997] The user uses a smartphone to input details of an investment idea (idea description, market size, estimated share, royalty rate, preliminary screening score, etc.). This input data is collected by a form and sent to the server. The input data includes detailed information about the idea and numerical information such as market size. This data is sent via the device's UI (Flutter).

[0998] Step 2:

[0999] The server securely stores the received user input data. The hardware used is a cloud server, and the software used is Django. The details of the user's investment ideas are recorded in a database and stored. This process ensures that the data is encrypted and stored securely.

[1000] Step 3:

[1001] Based on the stored data, the server uses a generative artificial intelligence model (e.g., GPT-4) to evaluate the probability of successful patent registration, the probability of a license agreement being concluded, the market size, estimated share, and royalty rate. For this evaluation, Python is used, running the PyTorch library. The server converts the input data into a prompt format and passes it to the generative artificial intelligence model. Specifically, the prompt is as follows: "For the following idea, please evaluate the probability of successful patent registration, the probability of a license agreement being concluded, the market size, estimated share, and royalty rate, and calculate the expected revenue. Idea details: Electronic payment system with new security features, market size: 100 million yen, estimated share: 10%, royalty rate: 5%, initial review score: 85." The output data is the various evaluation results.

[1002] Step 4:

[1003] The server calculates expected revenue based on the evaluation results. The hardware used is a cloud server, and the software used is NumPy (a numerical calculation library). The input data used for the calculation is the evaluation results output by the generative artificial intelligence model. Specifically, it calculates market revenue (market size x estimated share) and expected revenue (market revenue x probability of license agreement establishment x royalty rate). The output data is the expected value of the return.

[1004] Step 5:

[1005] The server compares the expected return obtained as a result of the calculation with the patent application cost and determines whether to recommend or not to apply for a patent. The input data used are the expected revenue and patent application cost (1.2 million yen) calculated in step 4. The output data is the decision result on whether to recommend or not to apply for a patent.

[1006] Step 6:

[1007] The server displays the results of the decision to the smartphone user. The hardware used is a smartphone, and the software used is Flutter (a UI framework). The displayed information includes expected revenue, whether or not to file a patent application, and evaluated parameters. Based on this information, the user can make a final decision on whether or not to file a patent application.

[1008] The above processing steps enable the evaluation of investment ideas and the optimization of patent applications to be carried out quickly and efficiently.

[1009] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1010] This invention combines an emotion engine with a system that uses a generative artificial intelligence model to evaluate submitted ideas and optimize patent application decisions. Specifically, this system recognizes the user's emotions and reflects them in the evaluation and feedback of ideas, enabling more appropriate patent application decisions. The program's processing is explained in natural language below, with specific examples provided for further details.

[1011] 1. Collect and enter ideas

[1012] The user uses the device to input detailed information about the idea, including the idea's name, content, market size, estimated share, royalty rate, and initial review score. The device also uses an emotion engine to recognize the user's emotional state in real time. The user's emotional data is collected through facial recognition and voice analysis, and is also sent to the server.

[1013] 2. Integrating Idea Ratings and Sentiment Data

[1014] The server operates a generative AI model and emotion engine based on the received idea information and emotion data. The generative AI model predicts the probability of successful patent registration, the probability of license agreement establishment, market size, and royalty rate based on the input market size, estimated market share, and first-stage review score. Meanwhile, the emotion engine analyzes the user's emotion data and evaluates how confident or stressed the user is about their idea. This emotion evaluation is fed back into the idea evaluation results. For example, if the user shows optimistic emotions, the risk assessment will be stricter.

[1015] 3. Calculating and adjusting expected returns

[1016] The server calculates the expected return based on the evaluation results using the following formula:

[1017] Market Revenue = Market Size Estimated Share

[1018] Expected revenue = Market revenue Probability of license agreement establishment Royalty rate

[1019] Furthermore, the expected revenue is adjusted based on the user's emotional data. If the user is overconfident, a more conservative forecast is made, and if the user is stressed, feedback is given to improve the user's care.

[1020] 4. Patent Application Judgment

[1021] The server compares the calculated expected return with the cost of filing a patent application. The standard patent application cost is 1.2 million yen, consisting of 300,000 yen for application costs and 900,000 yen for registration costs. If the expected return exceeds this standard, the server decides to proceed with the patent application. This decision also takes into account the user's emotional data, providing optimal support to the user.

[1022] 5. User Feedback

[1023] The server then sends the judgment results for the patent application to the device. Feedback based on the user's emotional state, analyzed by the emotion engine, is also provided. For example, if the user is losing confidence in their idea, the server may provide encouraging messages or suggestions for improvement.

[1024] 6. Ongoing evaluation and monitoring

[1025] Even after a patent application is filed, the server continues to monitor market trends and periodically evaluates the user's emotional state using an emotion engine. It collects market data and user emotional changes to evaluate the patent's competitive advantage and the need for maintenance. It reevaluates the patent within three years of filing to determine whether it needs to be maintained. This process optimizes patent maintenance costs and increases user satisfaction.

[1026] Specific examples

[1027] For example, suppose a user inputs an idea for a new, innovative product into a terminal, along with a market size of 100 million yen, an estimated market share of 10%, a royalty rate of 5%, and a first-stage review score of 85. In addition to this data, the terminal also detects the user's smile and tone of voice and determines their confidence. Using a generative AI model and an emotion engine, the server predicts a 70% probability of successful patent registration, a 50% probability of license agreement establishment, a market size of 50 billion yen, an estimated market share of 10%, and a royalty rate of 5%. Based on the emotion data, the server adjusts the risk assessment somewhat more stringently and calculates the final expected revenue to be 120 million yen. Because this exceeds the patent application cost of 1.2 million yen, the decision is made to proceed with the patent application. At the same time, the user is given feedback stating, "This idea has high potential, and we recommend filing a patent application."

[1028] The above is a concrete example of how to implement this invention. By using this system, an evaluation process that takes into account the user's feelings can be realized, making it possible to maximize the value of ideas while optimizing patent-related costs.

[1029] The processing flow will be explained below.

[1030] Step 1:

[1031] The user inputs detailed information about their idea using a terminal, including the idea's name, content, market size, estimated share, royalty rate, and initial review score, and the system also collects the user's voice and facial expression data to detect their emotional state.

[1032] Step 2:

[1033] The device sends detailed information about the idea and emotional data to the server using a secure communication protocol.

[1034] Step 3:

[1035] The server runs a generative AI model based on the data it receives. Specifically, it predicts the probability of successful patent registration, the probability of a license agreement being concluded, the market size, and royalty rates based on the market size, estimated market share, and first-stage examination score.

[1036] Step 4:

[1037] The server uses an emotion engine to analyze the user's emotional data. The analysis results include an emotional state indicating whether the user is optimistic or pessimistic. Based on this result, the reliability and risk assessment of the idea evaluation are adjusted.

[1038] Step 5:

[1039] The server combines the evaluation results of the generative AI model with the analysis results of the emotion engine to calculate the expected value of the return. It calculates market revenue from the market size and estimated share, and calculates the expected revenue by multiplying the probability of a license agreement being concluded by the royalty rate. It then makes a final calculation of the expected value of the return adjusted based on the emotion data.

[1040] Step 6:

[1041] The server compares the expected return with the cost of filing a patent application. The server uses the application cost of 300,000 yen and the registration cost of 900,000 yen as the standard, totaling 1.2 million yen, and makes a decision to recommend filing a patent application if the expected return exceeds this.

[1042] Step 7:

[1043] The server sends the patent application decision result to the terminal, which includes whether to proceed with the patent application, detailed evaluation parameters, and feedback from the emotion engine.

[1044] Step 8:

[1045] The terminal displays the judgment results and feedback for the patent application received from the server to the user, who can then check the results through the terminal and decide on the next action if necessary.

[1046] Step 9:

[1047] The server runs a process to continuously monitor market trends even after a patent application has been filed, and periodically evaluates the user's emotional state using an emotion engine to collect data to confirm the need to maintain the patent.

[1048] Step 10:

[1049] The server will reevaluate the patent within three years of filing and determine whether it is necessary to maintain the patent. Based on market conditions and the user's sentiment evaluation, the server will make a final decision on whether to maintain the patent and send the result to the terminal.

[1050] The above is the specific flow of program processing in this system. This detailed step-by-step process efficiently carries out a series of decisions, from idea evaluation to patent application and patent maintenance, and provides optimal support that takes user feelings into consideration.

[1051] Example 2

[1052] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1053] Conventional patent evaluation systems use generative artificial intelligence models to objectively evaluate submitted ideas. However, because they do not consider the emotions and intentions of the user who submitted the idea, the evaluation results can sometimes deviate from the user's actual intentions and emotions. This can lead to lower user satisfaction and potentially undermine motivation to pursue patent applications. Furthermore, while there are methods for monitoring market fluctuations after a patent application to evaluate the patent's competitive advantage, these systems lack reevaluation or feedback that takes into account the user's emotional state, which can lead to problems in alleviating user stress and anxiety. Therefore, there is a need for a system that optimizes patent application decisions and improves user satisfaction through idea evaluation and continuous feedback that takes into account the user's emotions.

[1054] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: a means for inputting detailed idea information and emotional data entered by a user using a terminal into a generative AI model; a means for using the generative AI model to evaluate the probability of successful patent registration, license agreement establishment, market size, and estimated share for the submitted idea; a means for calculating an expected return based on the evaluated parameters and emotional data; a means for adjusting the expected return for a patent application by incorporating the emotional data; and a means for comparing the adjusted expected return with patent application costs to make a decision on whether to apply for a patent. This realizes an evaluation process that takes user emotions into account, enabling the optimization of patent-related costs while maximizing the value of the idea. A "user" is a person who inputs detailed idea information and emotional data.

[1055] A "terminal" is a device that allows a user to input detailed information about an idea and collect emotional data.

[1056] "Detailed idea information" is information entered by the user using a terminal, including the name of the idea, its contents, market size, estimated share, royalty rate, and initial screening score.

[1057] "Emotion data" is data that indicates the emotional state of the user analyzed from facial expressions and voice collected by the terminal.

[1058] A "generative artificial intelligence model" is a part of artificial intelligence technology used to evaluate ideas, and is a model for predicting the probability of successful patent registration, the probability of concluding a license agreement, market size, and estimated share.

[1059] "Expected return" is the expected revenue for a patent application calculated based on the evaluated parameters and sentiment data.

[1060] The "adjusted expected return" is a numerical value that reflects the emotional data and modifies the expected return based on the user's emotional state.

[1061] "Patent application costs" refers to the costs required for patent application and registration, and specifically includes application costs and registration costs.

[1062] "Patent application decision" is a process in which the server compares the calculated expected return with the cost of filing a patent application and determines whether to recommend filing a patent application.

[1063] "Market fluctuations" refer to changes in market size and competitive conditions, and are factors that affect the competitive advantage of patents.

[1064] The "necessity of maintaining a patent" is a criterion for evaluating the competitive advantage and market value of a patent and deciding whether to maintain the patent.

[1065] The above are definitions of important words.

[1066] The present invention is a system for optimizing patent application decisions using a generative artificial intelligence model, and by collecting and integrating user emotional data into the evaluation process, it provides more appropriate feedback to the user. Detailed modes for implementing the invention are described below.

[1067] 1. Collect and enter ideas

[1068] Users use the device to input detailed information about their ideas, including the idea's name, content, market size, estimated share, royalty rate, and initial review score. The device is equipped with an emotion engine that collects the user's emotional data in real time as they input information. The data is collected by analyzing the user's facial expressions and voice using the device's built-in camera and microphone. The user's emotional state is then digitized and sent to the server along with the idea information.

[1069] 2. Integrating Idea Ratings and Sentiment Data

[1070] The server operates a generative AI model and emotion engine based on the received idea information and emotion data. The generative AI model predicts the probability of successful patent registration, the probability of license agreement establishment, market size, and royalty rate based on data such as market size, estimated market share, and initial review score. Meanwhile, the emotion engine analyzes the collected emotion data and evaluates the user's emotional state. For example, if the user is feeling confident or anxious, each emotional state is fed back into the evaluation results.

[1071] 3. Calculating and adjusting expected returns

[1072] The server calculates the expected return based on the evaluation results using the following formula:

[1073] Market Revenue = Market Size Estimated Share

[1074] Expected revenue = Market revenue Probability of license agreement establishment Royalty rate

[1075] Furthermore, the expected revenue is adjusted based on the user's emotional data. If the user is overconfident, a more conservative forecast is made, and if the user is stressed, feedback is given to improve the user's care.

[1076] 4. Patent Application Judgment

[1077] The server compares the calculated expected return with the cost of filing a patent application. The standard patent application cost is 1.2 million yen, consisting of 300,000 yen for application costs and 900,000 yen for registration costs. If the expected return exceeds this standard, the server recommends filing a patent application. This decision also takes into account the user's emotional data, providing optimal support to the user.

[1078] 5. User Feedback

[1079] The server then sends the judgment result of the patent application to the terminal. The judgment result is not only provided, but also feedback based on the user's emotional state as analyzed by the emotion engine. For example, if the user is losing confidence in their idea, the server may provide an encouraging message or suggestions for improvement.

[1080] 6. Ongoing evaluation and monitoring

[1081] Even after a patent application is filed, the server continues to monitor market fluctuations and periodically evaluates the user's emotional state using an emotion engine. It collects market data and user emotional changes to evaluate the patent's competitive advantage and the need for maintenance. It reevaluates the patent within three years of filing to determine whether it needs to be maintained. This process optimizes patent maintenance costs and increases user satisfaction.

[1082] Specific examples

[1083] For example, suppose a user inputs an idea for a new, innovative product into a terminal. Specifically, the inputs are a market size of 100 million yen, an estimated market share of 10%, a royalty rate of 5%, and a first-stage review score of 85. At the same time, the terminal detects the user's smile and tone of voice and determines their confidence. Using a generative AI model and an emotion engine, the server predicts a 70% probability of successful patent registration, a 50% probability of license agreement establishment, a market size of 50 billion yen, an estimated market share of 10%, and a royalty rate of 5%. Based on the emotion data, the server adjusts the risk assessment somewhat more stringently and calculates the final expected revenue to be 120 million yen. Because this exceeds the patent application cost of 1.2 million yen, the decision is made to proceed with the patent application. At the same time, the user is given feedback stating, "This idea has high potential, and we recommend filing a patent application."

[1084] Prompt Sentence Examples

[1085] The prompt to input a "new innovative product idea" into the generative AI model is as follows:

[1086] Evaluate new and innovative product ideas.

[1087] Market size: 100 million yen

[1088] Estimated share: 10%

[1089] Royalty rate: 5%

[1090] First round score: 85

[1091] Emotion Recognition: Confident

[1092] By using this prompt, the generative artificial intelligence model can evaluate the appropriate ideas.

[1093] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1094] Program processing flow

[1095] Step 1: User enters idea details using a terminal

[1096] The user enters the name, content, market size, estimated share, royalty rate, and initial review score of the idea into the input screen of the terminal. The input data is in text format and divided into specific fields. This allows the user's idea to be recorded quantitatively and qualitatively. Input: Detailed information about the idea, Output: Detailed information about the idea data.

[1097] Step 2: The device uses the emotion engine to collect the user's emotion data.

[1098] While the user is inputting their ideas, the device uses the built-in camera and microphone to analyze the user's facial expressions and voice in real time. The emotion engine uses facial recognition and voice analysis algorithms to quantify the user's emotional state. Input: User's facial and voice data, Output: Emotion data.

[1099] Step 3: The user confirms the information they entered and the device sends it to the server

[1100] The user checks the input and presses the send button to send the data to the server. The device sends detailed idea data and emotion data in JSON format to the server. Input: Send instruction, Output: Data sent to the server.

[1101] Step 4: The server analyzes the received idea information

[1102] The server parses the received data and stores it in a database, converting the values ​​of each field to the appropriate data type and preparing it for evaluation. Input: Data sent to the server, Output: Parsed and stored data.

[1103] Step 5: The server inputs the emotion data into the generative AI model

[1104] The server uses the emotion data as input data for the generative AI model, which uses a pre-trained neural network. Input: Emotion data, Output: Emotion data converted into a data format for model input.

[1105] Step 6: The server runs the generative AI model and evaluates the ideas.

[1106] The server launches a generative AI model and predicts the probability of successful patent registration, the probability of a license agreement being concluded, the market size, and royalty rates based on input data such as market size, estimated market share, and first review score. Input: Detailed idea information and converted emotion data, Output: Idea evaluation results.

[1107] Step 7: The server uses the emotion engine to analyze the user's emotion data and integrate it into a rating.

[1108] The server uses an emotion engine to analyze the user's emotional data and evaluate how confident or stressed the user is about their idea. This result is integrated into the idea evaluation results as feedback. Input: User's emotional data and idea evaluation results. Output: Integrated evaluation results.

[1109] Step 8: The server calculates the expected return based on the evaluation results.

[1110] The server calculates the expected revenue using the following formula:

[1111] Market Revenue = Market Size Estimated Share

[1112] Expected revenue = Market revenue Probability of license agreement establishment Royalty rate

[1113] Input: Integrated valuation results, Output: Calculated expected profit.

[1114] Step 9: The server adjusts the expected revenue taking into account the sentiment data

[1115] The server considers the user's emotional data and makes conservative predictions if the user is overconfident, or adjusts the expected revenue while providing caring feedback if the user is feeling stressed. Input: Calculated expected revenue and emotional data, Output: Adjusted expected revenue.

[1116] Step 10: The server compares the calculated expected revenue with the patent application cost and makes a decision on whether to apply for the patent.

[1117] The server evaluates whether the adjusted expected revenue exceeds the standard patent application cost (1.2 million yen) and determines whether to recommend a patent application. Input: adjusted expected revenue and patent application cost, Output: judgment on whether to apply for a patent.

[1118] Step 11: The server sends the result of the decision to the terminal.

[1119] The server generates a result based on the patent application decision in JSON format and sends it to the user's device. This includes the decision result as well as a feedback message based on the user's emotional state. Input: Patent application approval / disapproval decision, Output: Results and feedback sent to the user's device.

[1120] Step 12: User Feedback

[1121] The user receives the results on the terminal and checks the displayed feedback message. For example, if there is a high possibility of success, the message "We recommend you apply for a patent" will be displayed, and if they are feeling less confident, the message will include encouragement and suggestions for improvement. Input: Results and feedback sent from the server. Output: Feedback message displayed on the terminal.

[1122] Step 13: Ongoing evaluation and monitoring after patent application

[1123] The server continues to monitor market fluctuations even after the patent application has been filed, and periodically evaluates the user's emotional state using an emotion engine. A reevaluation is performed within three years to determine whether the patent should be maintained. Input: Market data and emotion data. Output: Reevaluation results and decision on whether to maintain the patent.

[1124] (Application example 2)

[1125] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1126] Conventional patent evaluation systems evaluate ideas without taking the user's emotional state into account, resulting in evaluation results that do not necessarily match the user's actual intentions or circumstances. Furthermore, because emotional data is not used in the evaluation process, appropriate feedback cannot be provided to the user, potentially resulting in suboptimal decisions on patent applications. In response to these issues, the present invention aims to provide a system that integrates user emotional data to provide more appropriate evaluations and feedback.

[1127] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for evaluating the probability of successful patent registration, probability of license agreement establishment, market size, and estimated share of a submitted idea using a generative artificial intelligence model; means for calculating an expected return on a patent application based on the evaluated parameters; means for comparing the expected return with the patent application cost and making a decision on the patent application; emotion recognition means for collecting and analyzing user emotion data; and means for integrating the emotion data obtained by the emotion recognition means into the evaluation and feeding it back into the evaluation result. This allows the evaluation of the submitted idea to reflect the user's emotional state, making it possible to make a more appropriate decision on the patent application.

[1128] A "generative artificial intelligence model" refers to an artificial intelligence algorithm designed to generate new information or predictions based on data.

[1129] "Probability of successful patent registration" refers to the probability that a submitted idea will be granted a patent.

[1130] The "probability of a license agreement being concluded" refers to the probability that, after a patent is obtained, a contract will be concluded to provide the technology or idea to other companies or individuals under a license agreement.

[1131] "Market size" refers to the economic size or value of the entire target market for a particular idea or product.

[1132] "Estimated share" refers to the percentage of the market that the submitted idea or product is expected to occupy.

[1133] "Expected return" refers to the expected amount of profit that an investment in a patent application will bring in the future.

[1134] "Patent application costs" refers to the set of expenses required to apply for a patent.

[1135] "User emotional data" refers to data that indicates the user's emotional state, as obtained through the user's facial expressions, voice, and other physiological data.

[1136] "Emotion recognition means" refers to technology and devices for detecting and analyzing a user's emotions.

[1137] "Means of providing feedback to evaluation results" refers to techniques and methods for reflecting analyzed emotional data in the evaluation process and improving the final evaluation results.

[1138] This invention is a system that uses a generative artificial intelligence model to evaluate submitted feedback and optimize store operations. By recognizing user emotions and reflecting them in the feedback, it is possible to make more appropriate operational decisions. A detailed description of this system is provided below.

[1139] composition

[1140] 1. User Device

[1141] Hardware: Computer, smartphone, smart glasses, or head-mounted display for feedback input.

[1142] Software: A camera to capture the user's face, and an emotion recognition application to collect emotional data.

[1143] 2. Server

[1144] Hardware: High-performance servers.

[1145] Software: Generative AI models, emotion recognition engines, and evaluation and feedback systems.

[1146] Program processing

[1147] The program of this system performs the following main processes.

[1148] 1. Data collection: The user device captures facial expressions and voice along with the customer feedback text to collect emotional data. This emotional data is analyzed in real time and sent to the server.

[1149] Software used: OpenCV (for face recognition), Transformers (Hugging Face emotion analysis model).

[1150] 2. Data analysis: On the server side, a generative AI model evaluates the characteristics of the submitted feedback and analyzes the emotion data obtained by the emotion recognition means.

[1151] Generative artificial intelligence model used: Transformers (Hugging Face generative model).

[1152] 3. Evaluation and integration: The analyzed emotion data is fed back into the evaluation results, and a final evaluation is made.

[1153] Example of feedback: Based on the evaluation results, specific operational improvement instructions such as "Improve the layout and expand the coffee corner" are generated.

[1154] 4. Result feedback: The server sends the evaluation results to the user's device and provides appropriate feedback to the user. For example, if the evaluation result is high, a message such as "This store management approach has a high chance of success!" is displayed.

[1155] Specific examples

[1156] For example, consider a user entering feedback such as, "I like the layout of the store, but the coffee corner is not well-equipped." A webcam captures the customer's face, and an emotion recognition model identifies the expression as "happiness." A generative AI model on the server side generates an evaluation result such as, "Areas for improvement: Improve the layout and expand the coffee corner," and notifies the user as final feedback, "This store management approach has a high chance of success!"

[1157] Prompt Sentence Examples

[1158] A request to develop an application that collects customer feedback and sentiment data and provides suggestions for improving store operations.

[1159] Integrate customer opinions and sentiments to provide optimal feedback to store managers.

[1160] This system allows submitted feedback to reflect the user's emotional state, enabling better decisions to be made about store management.

[1161] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1162] Step 1:

[1163] A user terminal provides an interface for inputting feedback text from a customer. The user inputs the feedback text, and the terminal transmits the text to a server. At this time, the terminal activates a camera and a microphone for collecting emotion data based on the feedback text. The input is the feedback text, and the output is the feedback data transmitted to the server.

[1164] Step 2:

[1165] The device uses a camera and microphone to capture the user's face and voice and collect emotion data. Specifically, the camera captures the user's facial expressions in real time and performs facial recognition using OpenCV. The microphone also records audio and the audio data is analyzed using an emotion recognition engine (Transformers emotion analysis model). The input is the user's face and voice, and the output is emotion data.

[1166] Step 3:

[1167] The device sends the collected emotion data and feedback text to the server. Specifically, the results of facial recognition and voice analysis are sent to the server as structured data. In this process, the input is the user's emotion data and feedback text, and the output is the data sent to the server.

[1168] Step 4:

[1169] The server analyzes the received feedback text and emotion data and inputs them into a generative AI model. Specifically, the generative AI model formats the feedback text and emotion data input, integrates them, and performs evaluation. In this process, the input is the feedback text and emotion data, and the output is the evaluation result.

[1170] Step 5:

[1171] The server generates feedback for optimizing store operations based on the evaluation results of the generative AI model. Specifically, it generates appropriate feedback messages based on the evaluation results and makes adjustments taking into account emotional data. In this process, the inputs are the evaluation results and emotional data, and the output is optimization feedback.

[1172] Step 6:

[1173] The server sends the generated feedback to the user's terminal. Specifically, the optimization feedback is sent in a format that is easy to display immediately to the user. In this process, the input is the optimization feedback, and the output is the feedback display on the terminal.

[1174] Step 7:

[1175] The user terminal displays the feedback received from the server and provides the user with instructions for operational improvement. Specifically, the received feedback message is displayed on the user interface for the user to check. In this process, the input is the feedback message, and the output is the feedback display to the user.

[1176] Through these steps, the system provides feedback that reflects the user's emotional state, optimizing store operations.

[1177] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[1178] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1179] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1180] [Fourth embodiment]

[1181] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1182] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1183] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1184] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[1185] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1186] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1187] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[1188] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1189] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[1190] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1191] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[1192] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1193] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1194] The system of this invention uses a generative artificial intelligence model to evaluate the probability of successful patent registration, the probability of concluding a license agreement, the market size, and estimated share of a submitted idea, and then makes optimal decisions about patent applications based on the results. Below, the program's processing is explained in natural language.

[1195] 1. Collect and enter ideas

[1196] The user uses the device to input details of their idea for a new product or service, including a description of the idea, projected market size, estimated share, royalty rate, etc., as well as the initial judging score. This data is then sent from the device to the server.

[1197] 2. Evaluating ideas

[1198] Based on the received idea information, the server uses a generative AI model to evaluate the following parameters:

[1199] Probability of successful patent registration

[1200] License agreement success rate

[1201] market size

[1202] Estimated Share

[1203] Royalty Rate

[1204] Generative AI models use algorithms that have learned from past data to predict these parameters probabilistically. For example, they may predict that a certain idea will have a market size of 50 billion yen, an estimated market share of 10%, and a royalty rate of 5%.

[1205] 3. Calculating expected returns

[1206] The server calculates the expected return based on the evaluated parameters, using the following formula:

[1207] Market Revenue = Market Size Estimated Share

[1208] Expected revenue = Market revenue Probability of license agreement establishment Royalty rate

[1209] For example, if an idea has a market size of 50 billion yen, an estimated market share of 10%, a 50% probability of a license agreement being concluded, and a royalty rate of 5%, the market revenue would be 5 billion yen and the expected revenue would be 125 million yen.

[1210] 4. Patent Application Judgment

[1211] The server compares the calculated expected return with the patent application cost. The standard patent application cost is 1.2 million yen, consisting of 300,000 yen for application costs and 900,000 yen for registration costs. If the expected return exceeds this standard, the server decides to proceed with the patent application.

[1212] 5. Continuous evaluation

[1213] Even after a patent application is filed, the server continues to monitor market fluctuations and the patent's competitive advantage. It will reevaluate the patent within three years of filing to determine whether it is necessary to maintain the patent. This process helps reduce unnecessary patent maintenance costs and maximize profits.

[1214] Specific examples

[1215] For example, suppose a user inputs an "idea for a new, innovative product" into a terminal, along with a market size of 100 million yen, an estimated market share of 10%, a royalty rate of 5%, and an initial screening score of 85. The server receives this data and evaluates it using a generative artificial intelligence model. The evaluation results are a 70% probability of successful patent registration, a 50% probability of a license agreement being concluded, a market size of 50 billion yen, an estimated market share of 10%, and a royalty rate of 5%. The server calculates the expected return based on this and determines that the expected profit is 125 million yen. Since this exceeds the patent application cost of 1.2 million yen, the server proceeds with the patent application. Furthermore, market fluctuations are monitored even after the patent application is filed, and a decision is made three years later on whether to maintain the patent.

[1216] The above is a concrete example of how to implement this invention. By using this system, it is possible to efficiently select promising ideas from a large number of ideas, optimizing patent-related costs while maximizing profits.

[1217] The processing flow will be explained below.

[1218] Step 1:

[1219] The user uses the terminal to input detailed information about the idea, including the name of the idea, its content, market size, estimated share, royalty rate, and initial screening score.

[1220] Step 2:

[1221] The device sends the details of the entered idea to the server, using a secure communication protocol.

[1222] Step 3:

[1223] The server runs a generative AI model based on the received data. Specifically, based on the input market size, estimated market share, and first screening score, it predicts the probability of successful patent registration, the probability of license agreement establishment, market size, and royalty rate.

[1224] Step 4:

[1225] Based on the evaluation results obtained from the generative AI model, the server calculates the expected value of the return as follows: First, market revenue is calculated by multiplying the market size by the estimated market share, and then this result is multiplied by the probability of concluding a license agreement and the royalty rate to obtain the expected revenue.

[1226] Step 5:

[1227] The server compares the expected return with the cost of filing a patent application. The cost of filing a patent application is 1.2 million yen, consisting of the application cost of 300,000 yen and the registration cost of 900,000 yen. If the expected return exceeds this cost, the server decides to proceed with the patent application.

[1228] Step 6:

[1229] The server sends the patent application decision result to the terminal, including whether to proceed with the patent application and the evaluated parameters.

[1230] Step 7:

[1231] The terminal displays the judgment results for the patent application received from the server to the user. The user checks the results through the terminal and proceeds to the next step as necessary.

[1232] Step 8:

[1233] The server will implement a process for continuous monitoring of market trends after the patent application is filed, by periodically collecting market data and evaluating the patent's competitive advantage and market fluctuations.

[1234] Step 9:

[1235] The server will conduct continuous evaluation within three years of filing a patent application to determine whether it is necessary to maintain the patent. It will then decide whether to maintain or abandon the patent based on market conditions and send the results to the terminal.

[1236] This is the specific flow of program processing in this system. This detailed step-by-step process efficiently carries out a series of decisions, from idea evaluation to patent application and patent maintenance.

[1237] Example 1

[1238] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1239] With the current patent application judgment system, it is difficult to efficiently select ideas with high patent value from among the many available. Furthermore, inappropriate decisions about whether to maintain a patent due to market fluctuations after a patent application are made result in unnecessary costs. Furthermore, solving these issues requires highly accurate prediction models and continuous monitoring.

[1240] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1241] In this invention, the server includes: means for a user to input details of an idea for a new product or service using a terminal; means for transmitting the input data from the terminal to the server; means for evaluating the probability of successful patent registration, the probability of concluding a license agreement, the market size, and an estimated share using a generative artificial intelligence model based on the idea information received by the server; means for the server to calculate an expected return based on the evaluated parameters; means for comparing the calculated expected return with the patent application cost and making a decision on whether to apply for a patent; means for continuously monitoring market fluctuations and the competitive advantage of the patent even after the patent application has been filed; and means for reevaluating and deciding whether to maintain the patent. This makes it possible to efficiently select promising ideas from a large number of ideas and maximize profits while optimizing patent-related costs.

[1242] A "user" is a person who uses the system to input ideas for new products or services using a terminal.

[1243] A "terminal" is an input device used by a user, which inputs details of an idea and transmits the data to a server.

[1244] A "server" is a central computer system that receives data sent by users and performs evaluations and calculations using generative artificial intelligence models.

[1245] A "generative artificial intelligence model" is an algorithm installed on a server that learns from past data and has the ability to evaluate the probability of successful patent registration, the probability of a license agreement being concluded, market size, and estimated share.

[1246] The "probability of successful patent registration" is the probability that the idea being evaluated will be officially registered as a patent.

[1247] The "probability of license agreement establishment" is the probability that a license agreement based on the idea being evaluated will be established.

[1248] "Market size" is a numerical representation of the size of the entire market related to the idea being evaluated.

[1249] "Estimated Share" is the predicted share of the overall market that the idea being evaluated will occupy, expressed as a percentage.

[1250] "Expected return" is the revenue expected based on the idea being evaluated, calculated using factors such as the probability of successful patent registration, the probability of a license agreement being concluded, market size, estimated share, and royalty rate.

[1251] "Patent application costs" are the costs incurred from filing a patent application to registering it, and include application costs and registration costs.

[1252] "Patent application decision" refers to comparing expected revenue with the cost of patent application and deciding whether to apply for a patent.

[1253] "Monitoring" refers to the continuous monitoring of market fluctuations and the competitive advantage of patents after a patent application has been filed.

[1254] "Reevaluation" means reanalyzing data at regular intervals after a patent application is filed to determine whether it is necessary to maintain the patent.

[1255] The present invention relates to a system for improving the efficiency of patent application decisions and optimizing patent-related costs. Specific embodiments for carrying out the present invention will be described below.

[1256] 1. Collecting and inputting ideas

[1257] A user uses a terminal to input details of an idea for a new product or service. The information input by the user includes a description of the idea, a projected market size, an estimated share, a royalty rate, and an initial review score. This information is specifically entered and formatted in an input form on the terminal.

[1258] 2. Data transmission

[1259] The entered data is sent from the device to the server using an HTTP POST request, and the API ensures that the data is sent in the correct format to reach the server.

[1260] 3. Evaluate ideas

[1261] The server stores the received data in a database management system (e.g., MySQL or PostgreSQL). Next, the server uses a generative AI model to evaluate the probability of successful patent registration, the probability of a license agreement being concluded, and the market size and estimated share. The generative AI model is built using a deep learning framework such as TensorFlow or PyTorch, and performs evaluations using algorithms based on past data.

[1262] 4. Calculating expected returns

[1263] The server calculates the expected return based on the evaluated parameters, using the following formula:

[1264] Market Revenue = Market Size Estimated Share

[1265] Expected revenue = Market revenue Probability of license agreement establishment Royalty rate

[1266] For example, if the evaluation results are a market size of 50 billion yen, an estimated market share of 10%, a 50% probability of a license agreement being concluded, and a royalty rate of 5%, then the market revenue will be 5 billion yen and the expected revenue will be 125 million yen.

[1267] 5. Patent Application Judgment

[1268] The server compares the calculated expected revenue with the patent application cost (application cost of 300,000 yen and registration cost of 900,000 yen, totaling 1.2 million yen) and makes a decision on whether to apply for a patent. If the expected revenue exceeds the patent application cost, the server decides to proceed with the patent application and notifies the user of the result. Notification methods include displaying an alert on the device or sending an email.

[1269] 6. Continuous evaluation

[1270] Even after a patent application is filed, the server continuously monitors market fluctuations and the patent's competitive advantage. This includes regularly obtaining the latest market information through data feeds and APIs. A reevaluation is conducted within three years of filing the patent application to determine whether the patent needs to be maintained. This allows you to reduce unnecessary patent maintenance costs and maximize profits.

[1271] Specific examples

[1272] For example, suppose a user inputs an "idea for a new, innovative product" into a terminal, along with a market size of 100 million yen, an estimated market share of 10%, a royalty rate of 5%, and an initial screening score of 85. The server receives this data and evaluates it using a generative artificial intelligence model. The evaluation results are a 70% probability of successful patent registration, a 50% probability of a license agreement being concluded, an estimated market size of 50 billion yen, an estimated market share of 10%, and a royalty rate of 5%. The server calculates the expected return based on this and determines that the expected profit is 125 million yen. Since this exceeds the patent application cost of 1.2 million yen, the server decides to proceed with the patent application. Furthermore, market fluctuations are monitored even after the patent application is filed, and a decision is made three years later on whether to maintain the patent.

[1273] Prompt Sentence Examples

[1274] Specifically, you might use a prompt like this:

[1275] "Please enter your idea for a new, innovative product. Please enter the market size, estimated share, and royalty rate in numerical form, as well as your initial screening score."

[1276] The above is a specific embodiment for carrying out the present invention. By using this system, it is possible to efficiently select promising ideas from a large number of ideas, optimizing patent-related costs while maximizing profits.

[1277] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1278] Step 1:

[1279] A user uses a terminal to input details of an idea for a new product or service, including the following information:

[1280] Idea description (text format)

[1281] Estimated market size (numerical format)

[1282] Estimated share (percentage format)

[1283] Royalty Rate (Percentage Format)

[1284] First screening score (numerical format)

[1285] Specifically, the user enters this information into the input form and clicks the submit button. The input information is then formatted by the terminal software.

[1286] Input: User-entered details about the idea

[1287] Output: Formatted data

[1288] Step 2:

[1289] The device sends the entered data to the server using an HTTP POST request, which contains all the entered information in JSON format.

[1290] Specifically, the terminal converts the data into an appropriate format (JSON format) and sends it to the server's API endpoint.

[1291] Input: Formatted data

[1292] Output: Request data sent to the server

[1293] Step 3:

[1294] The server receives the data sent from the terminal and stores it in a database management system (e.g., MySQL or PostgreSQL).

[1295] Specifically, the server parses the received data and executes SQL queries to store it in a database.

[1296] Input: The request data sent

[1297] Output: Data stored in the database

[1298] Step 4:

[1299] The server reads the stored data and inputs it into a generative artificial intelligence model, which is built using TensorFlow and PyTorch. The model evaluates the probability of successful patent registration, the probability of a license agreement being concluded, and the market size and estimated share.

[1300] Specifically, the server uses SQL queries to retrieve data from the database and convert it into a format that can be input to the model. The generative AI model makes predictions based on past data and returns the output.

[1301] Input: Data retrieved from the database

[1302] Output: Evaluated parameters (probability values, numerical values)

[1303] Step 5:

[1304] The server calculates the expected return based on the evaluated parameters using the following formula:

[1305] Market Revenue = Market Size Estimated Share

[1306] Expected revenue = Market revenue Probability of license agreement establishment Royalty rate

[1307] Specifically, the server uses the evaluated parameters to execute program code that executes the calculation formula and calculates the expected profit.

[1308] Input: Evaluated parameters

[1309] Output: Calculated expected return

[1310] Step 6:

[1311] The server compares the calculated expected profit with the patent application cost and makes a decision on whether to apply for a patent. The patent application cost is 1.2 million yen in total, consisting of the application cost of 300,000 yen and the registration cost of 900,000 yen.

[1312] Specifically, the server executes program code with logic that compares the calculated expected profit with the patent application cost and determines whether or not to apply for a patent. The server then notifies the user of the result of this determination.

[1313] Inputs: Calculated expected revenue, patent application costs

[1314] Output: Patent application decision result (promotion / postponement)

[1315] Step 7:

[1316] The server continuously monitors market fluctuations and the competitive advantages of patents even after the patent application has been filed, including the ability to regularly retrieve the latest market information via data feeds and APIs.

[1317] Specifically, the server runs a program that periodically retrieves information from external data sources and updates the status of patents.

[1318] Input: Market information from external data sources

[1319] Output: Updated market and patent landscape data

[1320] Step 8:

[1321] The server will re-evaluate the patent within three years of filing to determine whether it is necessary to maintain the patent. This re-evaluation will again use the generative AI model to make predictions based on the latest data.

[1322] Specifically, the server executes program code that performs data reanalysis and patent maintenance decisions according to the reevaluation schedule.

[1323] Input: Latest market and patent data

[1324] Output: Patent maintenance decision result (maintain / abandon)

[1325] (Application example 1)

[1326] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1327] In the field of electronic payment services, it has been difficult to accurately evaluate the probability of successful patent registration and market feasibility of investment ideas, and to quickly and efficiently make appropriate patent application decisions. In particular, selecting promising investment ideas from the many submitted and optimizing patent-related costs while maximizing profits requires a great deal of time and effort. Unless this challenge is resolved, electronic payment service providers are likely to incur unnecessary patent maintenance costs and opportunity losses.

[1328] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1329] In this invention, the server includes means for using a generative artificial intelligence model to evaluate the probability of successful patent registration, the probability of concluding a license agreement, the market size, and an estimated share of a submitted idea, means for calculating an expected return on a patent application based on the evaluated parameters, means for comparing the expected return with the patent application cost and making a decision on whether to apply for a patent, and means for allowing a user to propose an investment idea in the electronic payment service and evaluating whether it is worthy of patent registration or market launch. This enables the evaluation of investment ideas and decisions on patent applications in the electronic payment service to be made quickly and efficiently, thereby optimizing patent-related costs and maximizing profits.

[1330] A "generative artificial intelligence model" refers to an artificial intelligence algorithm that makes predictions and evaluations based on collected data.

[1331] "Submitted Idea" means a concept for a new product or service conceived by a User.

[1332] "Probability of successful patent registration" refers to the probability that a patent application will be granted as a patent.

[1333] "Probability of license agreement establishment" indicates the probability that a license agreement regarding patented technology will be established.

[1334] "Market size" refers to the size of the potential market when the patented technology is commercially exploited.

[1335] "Estimated share" means the share that the patented technology is expected to occupy in a particular market.

[1336] "Expected return" refers to the expected value of market revenue, royalties, and other revenues from patented technology.

[1337] "Patent application costs" refer to the costs required to apply for a patent.

[1338] "Patent application decision" means the process of deciding whether to file a patent application based on the evaluated parameters and expected return.

[1339] "Electronic payment service" refers to a service for conducting economic transactions using electronic means.

[1340] "Investment Idea" means a concept or strategy for investment purposes relating to a new technology, product or service.

[1341] "Go-to-market" refers to the process of introducing new technologies or products to the market.

[1342] MODE FOR CARRYING OUT THE INVENTION

[1343] The system of this invention uses a generative artificial intelligence model to evaluate the probability of successful patent registration, the probability of concluding a license agreement, the market size and estimated share of an investment idea in electronic payment services, and then makes optimal decisions about patent applications based on the results.

[1344] Program processing explanation

[1345] Details of hardware, software, data processing and calculation

[1346] The present invention is implemented in an environment where a server and a user terminal are mainly used. The specific hardware and software configurations are as follows.

[1347] 1. User Interface (UI)

[1348] Hardware used: Smartphone

[1349] Software used: Flutter (UI framework)

[1350] Users use a form to enter details of their investment idea (idea description, market size, estimated share, royalty rate, preliminary screening score, etc.) This data is sent from the device to the cloud server.

[1351] 2. Data transmission and storage

[1352] Hardware used: Cloud server (e.g. AWS Lambda)

[1353] Software used: Django (backend framework)

[1354] The data received from the device is sent to a cloud server and stored securely.

[1355] 3. Idea Evaluation

[1356] Hardware used: Cloud server

[1357] Software used: PyTorch (to run the generative AI model)

[1358] Using a generative artificial intelligence model (e.g., GPT-4), we evaluate the probability of successful patent registration, the probability of concluding a license agreement, market size, estimated share, and royalty rate.

[1359] 4. Expected return calculation

[1360] Hardware used: Cloud server

[1361] Software used: NumPy (numerical calculation library)

[1362] The expected revenue is calculated based on the evaluated parameters and a decision is made on whether to apply for a patent.

[1363] 5. Displaying the results

[1364] Hardware used: Smartphone

[1365] Software used: Flutter

[1366] The calculation results (expected revenue, patent application recommendation / non-recommendation, etc.) are displayed to the user.

[1367] Specific examples

[1368] For example, a user inputs the following investment idea:

[1369] | Item | Value |

[1370] |-----------------|-----------------------------|

[1371] | Idea Description | Electronic Payment System with New Security Features |

[1372] | Market size | 100 million yen |

[1373] | Estimated share | 10% |

[1374] | Royalty Rate | 5% |

[1375] | First Screening Score | 85 |

[1376] Based on this data, we send the following prompt to the generative AI model:

[1377] For the following ideas, please evaluate the probability of successful patent registration, probability of successful licensing, market size, estimated market share, and royalty rate, and calculate the expected revenue.

[1378] Idea details: Electronic payment system with new security features, market size: 100 million yen, estimated share: 10%, royalty rate: 5%, initial review score: 85

[1379] The generative AI model performs the evaluation and returns the results to the server. The results are displayed on the terminal, and the user makes a decision on patent application. In this way, the evaluation of investment ideas and the optimization of patent applications are carried out quickly and efficiently.

[1380] The above is a detailed description of the mode for carrying out the present invention.

[1381] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1382] Step 1:

[1383] The user uses a smartphone to input details of an investment idea (idea description, market size, estimated share, royalty rate, preliminary screening score, etc.). This input data is collected by a form and sent to the server. The input data includes detailed information about the idea and numerical information such as market size. This data is sent via the device's UI (Flutter).

[1384] Step 2:

[1385] The server securely stores the received user input data. The hardware used is a cloud server, and the software used is Django. The details of the user's investment ideas are recorded in a database and stored. This process ensures that the data is encrypted and stored securely.

[1386] Step 3:

[1387] Based on the stored data, the server uses a generative artificial intelligence model (e.g., GPT-4) to evaluate the probability of successful patent registration, the probability of a license agreement being concluded, the market size, estimated share, and royalty rate. For this evaluation, Python is used, running the PyTorch library. The server converts the input data into a prompt format and passes it to the generative artificial intelligence model. Specifically, the prompt is as follows: "For the following idea, please evaluate the probability of successful patent registration, the probability of a license agreement being concluded, the market size, estimated share, and royalty rate, and calculate the expected revenue. Idea details: Electronic payment system with new security features, market size: 100 million yen, estimated share: 10%, royalty rate: 5%, initial review score: 85." The output data is the various evaluation results.

[1388] Step 4:

[1389] The server calculates expected revenue based on the evaluation results. The hardware used is a cloud server, and the software used is NumPy (a numerical calculation library). The input data used for the calculation is the evaluation results output by the generative artificial intelligence model. Specifically, it calculates market revenue (market size x estimated share) and expected revenue (market revenue x probability of license agreement establishment x royalty rate). The output data is the expected value of the return.

[1390] Step 5:

[1391] The server compares the expected return obtained as a result of the calculation with the patent application cost and determines whether to recommend or not to apply for a patent. The input data used are the expected revenue and patent application cost (1.2 million yen) calculated in step 4. The output data is the decision result on whether to recommend or not to apply for a patent.

[1392] Step 6:

[1393] The server displays the results of the decision to the smartphone user. The hardware used is a smartphone, and the software used is Flutter (a UI framework). The displayed information includes expected revenue, whether or not to file a patent application, and evaluated parameters. Based on this information, the user can make a final decision on whether or not to file a patent application.

[1394] The above processing steps enable the evaluation of investment ideas and the optimization of patent applications to be carried out quickly and efficiently.

[1395] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1396] This invention combines an emotion engine with a system that uses a generative artificial intelligence model to evaluate submitted ideas and optimize patent application decisions. Specifically, this system recognizes the user's emotions and reflects them in the evaluation and feedback of ideas, enabling more appropriate patent application decisions. The program's processing is explained in natural language below, with specific examples provided for further details.

[1397] 1. Collect and enter ideas

[1398] The user uses the device to input detailed information about the idea, including the idea's name, content, market size, estimated share, royalty rate, and initial review score. The device also uses an emotion engine to recognize the user's emotional state in real time. The user's emotional data is collected through facial recognition and voice analysis, and is also sent to the server.

[1399] 2. Integrating Idea Ratings and Sentiment Data

[1400] The server operates a generative AI model and emotion engine based on the received idea information and emotion data. The generative AI model predicts the probability of successful patent registration, the probability of license agreement establishment, market size, and royalty rate based on the input market size, estimated market share, and first-stage review score. Meanwhile, the emotion engine analyzes the user's emotion data and evaluates how confident or stressed the user is about their idea. This emotion evaluation is fed back into the idea evaluation results. For example, if the user shows optimistic emotions, the risk assessment will be stricter.

[1401] 3. Calculating and adjusting expected returns

[1402] The server calculates the expected return based on the evaluation results using the following formula:

[1403] Market Revenue = Market Size Estimated Share

[1404] Expected revenue = Market revenue Probability of license agreement establishment Royalty rate

[1405] Furthermore, the expected revenue is adjusted based on the user's emotional data. If the user is overconfident, a more conservative forecast is made, and if the user is stressed, feedback is given to improve the user's care.

[1406] 4. Patent Application Judgment

[1407] The server compares the calculated expected return with the cost of filing a patent application. The standard patent application cost is 1.2 million yen, consisting of 300,000 yen for application costs and 900,000 yen for registration costs. If the expected return exceeds this standard, the server decides to proceed with the patent application. This decision also takes into account the user's emotional data, providing optimal support to the user.

[1408] 5. User Feedback

[1409] The server then sends the judgment results for the patent application to the device. Feedback based on the user's emotional state, analyzed by the emotion engine, is also provided. For example, if the user is losing confidence in their idea, the server may provide encouraging messages or suggestions for improvement.

[1410] 6. Ongoing evaluation and monitoring

[1411] Even after a patent application is filed, the server continues to monitor market trends and periodically evaluates the user's emotional state using an emotion engine. It collects market data and user emotional changes to evaluate the patent's competitive advantage and the need for maintenance. It reevaluates the patent within three years of filing to determine whether it needs to be maintained. This process optimizes patent maintenance costs and increases user satisfaction.

[1412] Specific examples

[1413] For example, suppose a user inputs an idea for a new, innovative product into a terminal, along with a market size of 100 million yen, an estimated market share of 10%, a royalty rate of 5%, and a first-stage review score of 85. In addition to this data, the terminal also detects the user's smile and tone of voice and determines their confidence. Using a generative AI model and an emotion engine, the server predicts a 70% probability of successful patent registration, a 50% probability of license agreement establishment, a market size of 50 billion yen, an estimated market share of 10%, and a royalty rate of 5%. Based on the emotion data, the server adjusts the risk assessment somewhat more stringently and calculates the final expected revenue to be 120 million yen. Because this exceeds the patent application cost of 1.2 million yen, the decision is made to proceed with the patent application. At the same time, the user is given feedback stating, "This idea has high potential, and we recommend filing a patent application."

[1414] The above is a concrete example of how to implement this invention. By using this system, an evaluation process that takes into account the user's feelings can be realized, making it possible to maximize the value of ideas while optimizing patent-related costs.

[1415] The processing flow will be explained below.

[1416] Step 1:

[1417] The user inputs detailed information about their idea using a terminal, including the idea's name, content, market size, estimated share, royalty rate, and initial review score, and the system also collects the user's voice and facial expression data to detect their emotional state.

[1418] Step 2:

[1419] The device sends detailed information about the idea and emotional data to the server using a secure communication protocol.

[1420] Step 3:

[1421] The server runs a generative AI model based on the data it receives. Specifically, it predicts the probability of successful patent registration, the probability of a license agreement being concluded, the market size, and royalty rates based on the market size, estimated market share, and first-stage examination score.

[1422] Step 4:

[1423] The server uses an emotion engine to analyze the user's emotional data. The analysis results include an emotional state indicating whether the user is optimistic or pessimistic. Based on this result, the reliability and risk assessment of the idea evaluation are adjusted.

[1424] Step 5:

[1425] The server combines the evaluation results of the generative AI model with the analysis results of the emotion engine to calculate the expected value of the return. It calculates market revenue from the market size and estimated share, and calculates the expected revenue by multiplying the probability of a license agreement being concluded by the royalty rate. It then makes a final calculation of the expected value of the return adjusted based on the emotion data.

[1426] Step 6:

[1427] The server compares the expected return with the cost of filing a patent application. The server uses the application cost of 300,000 yen and the registration cost of 900,000 yen as the standard, totaling 1.2 million yen, and makes a decision to recommend filing a patent application if the expected return exceeds this.

[1428] Step 7:

[1429] The server sends the patent application decision result to the terminal, which includes whether to proceed with the patent application, detailed evaluation parameters, and feedback from the emotion engine.

[1430] Step 8:

[1431] The terminal displays the judgment results and feedback for the patent application received from the server to the user, who can then check the results through the terminal and decide on the next action if necessary.

[1432] Step 9:

[1433] The server runs a process to continuously monitor market trends even after a patent application has been filed, and periodically evaluates the user's emotional state using an emotion engine to collect data to confirm the need to maintain the patent.

[1434] Step 10:

[1435] The server will reevaluate the patent within three years of filing and determine whether it is necessary to maintain the patent. Based on market conditions and the user's sentiment evaluation, the server will make a final decision on whether to maintain the patent and send the result to the terminal.

[1436] The above is the specific flow of program processing in this system. This detailed step-by-step process efficiently carries out a series of decisions, from idea evaluation to patent application and patent maintenance, and provides optimal support that takes user feelings into consideration.

[1437] Example 2

[1438] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1439] Conventional patent evaluation systems use generative artificial intelligence models to objectively evaluate submitted ideas. However, because they do not consider the emotions and intentions of the user who submitted the idea, the evaluation results can sometimes deviate from the user's actual intentions and emotions. This can lead to lower user satisfaction and potentially undermine motivation to pursue patent applications. Furthermore, while there are methods for monitoring market fluctuations after a patent application to evaluate the patent's competitive advantage, these systems lack reevaluation or feedback that takes into account the user's emotional state, which can lead to problems in alleviating user stress and anxiety. Therefore, there is a need for a system that optimizes patent application decisions and improves user satisfaction through idea evaluation and continuous feedback that takes into account the user's emotions.

[1440] The identification process by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means. In this invention, the server includes: a means for inputting detailed idea information and emotional data entered by a user using a terminal into a generative AI model; a means for using the generative AI model to evaluate the probability of successful patent registration, license agreement establishment, market size, and estimated share for the submitted idea; a means for calculating an expected return based on the evaluated parameters and emotional data; a means for adjusting the expected return for a patent application by incorporating the emotional data; and a means for comparing the adjusted expected return with patent application costs to make a decision on whether to apply for a patent. This realizes an evaluation process that takes user emotions into account, enabling the optimization of patent-related costs while maximizing the value of the idea. A "user" is a person who inputs detailed idea information and emotional data.

[1441] A "terminal" is a device that allows a user to input detailed information about an idea and collect emotional data.

[1442] "Detailed idea information" is information entered by the user using a terminal, including the name of the idea, its contents, market size, estimated share, royalty rate, and initial screening score.

[1443] "Emotion data" is data that indicates the emotional state of the user analyzed from facial expressions and voice collected by the terminal.

[1444] A "generative artificial intelligence model" is a part of artificial intelligence technology used to evaluate ideas, and is a model for predicting the probability of successful patent registration, the probability of concluding a license agreement, market size, and estimated share.

[1445] "Expected return" is the expected revenue for a patent application calculated based on the evaluated parameters and sentiment data.

[1446] The "adjusted expected return" is a numerical value that reflects the emotional data and modifies the expected return based on the user's emotional state.

[1447] "Patent application costs" refers to the costs required for patent application and registration, and specifically includes application costs and registration costs.

[1448] "Patent application decision" is a process in which the server compares the calculated expected return with the cost of filing a patent application and determines whether to recommend filing a patent application.

[1449] "Market fluctuations" refer to changes in market size and competitive conditions, and are factors that affect the competitive advantage of patents.

[1450] The "necessity of maintaining a patent" is a criterion for evaluating the competitive advantage and market value of a patent and deciding whether to maintain the patent.

[1451] The above are definitions of important words.

[1452] The present invention is a system for optimizing patent application decisions using a generative artificial intelligence model, and by collecting and integrating user emotional data into the evaluation process, it provides more appropriate feedback to the user. Detailed modes for implementing the invention are described below.

[1453] 1. Collect and enter ideas

[1454] Users use the device to input detailed information about their ideas, including the idea's name, content, market size, estimated share, royalty rate, and initial review score. The device is equipped with an emotion engine that collects the user's emotional data in real time as they input information. The data is collected by analyzing the user's facial expressions and voice using the device's built-in camera and microphone. The user's emotional state is then digitized and sent to the server along with the idea information.

[1455] 2. Integrating Idea Ratings and Sentiment Data

[1456] The server operates a generative AI model and emotion engine based on the received idea information and emotion data. The generative AI model predicts the probability of successful patent registration, the probability of license agreement establishment, market size, and royalty rate based on data such as market size, estimated market share, and initial review score. Meanwhile, the emotion engine analyzes the collected emotion data and evaluates the user's emotional state. For example, if the user is feeling confident or anxious, each emotional state is fed back into the evaluation results.

[1457] 3. Calculating and adjusting expected returns

[1458] The server calculates the expected return based on the evaluation results using the following formula:

[1459] Market Revenue = Market Size Estimated Share

[1460] Expected revenue = Market revenue Probability of license agreement establishment Royalty rate

[1461] Furthermore, the expected revenue is adjusted based on the user's emotional data. If the user is overconfident, a more conservative forecast is made, and if the user is stressed, feedback is given to improve the user's care.

[1462] 4. Patent Application Judgment

[1463] The server compares the calculated expected return with the cost of filing a patent application. The standard patent application cost is 1.2 million yen, consisting of 300,000 yen for application costs and 900,000 yen for registration costs. If the expected return exceeds this standard, the server recommends filing a patent application. This decision also takes into account the user's emotional data, providing optimal support to the user.

[1464] 5. User Feedback

[1465] The server then sends the judgment result of the patent application to the terminal. The judgment result is not only provided, but also feedback based on the user's emotional state as analyzed by the emotion engine. For example, if the user is losing confidence in their idea, the server may provide an encouraging message or suggestions for improvement.

[1466] 6. Ongoing evaluation and monitoring

[1467] Even after a patent application is filed, the server continues to monitor market fluctuations and periodically evaluates the user's emotional state using an emotion engine. It collects market data and user emotional changes to evaluate the patent's competitive advantage and the need for maintenance. It reevaluates the patent within three years of filing to determine whether it needs to be maintained. This process optimizes patent maintenance costs and increases user satisfaction.

[1468] Specific examples

[1469] For example, suppose a user inputs an idea for a new, innovative product into a terminal. Specifically, the inputs are a market size of 100 million yen, an estimated market share of 10%, a royalty rate of 5%, and a first-stage review score of 85. At the same time, the terminal detects the user's smile and tone of voice and determines their confidence. Using a generative AI model and an emotion engine, the server predicts a 70% probability of successful patent registration, a 50% probability of license agreement establishment, a market size of 50 billion yen, an estimated market share of 10%, and a royalty rate of 5%. Based on the emotion data, the server adjusts the risk assessment somewhat more stringently and calculates the final expected revenue to be 120 million yen. Because this exceeds the patent application cost of 1.2 million yen, the decision is made to proceed with the patent application. At the same time, the user is given feedback stating, "This idea has high potential, and we recommend filing a patent application."

[1470] Prompt Sentence Examples

[1471] The prompt to input a "new innovative product idea" into the generative AI model is as follows:

[1472] Evaluate new and innovative product ideas.

[1473] Market size: 100 million yen

[1474] Estimated share: 10%

[1475] Royalty rate: 5%

[1476] First round score: 85

[1477] Emotion Recognition: Confident

[1478] By using this prompt, the generative artificial intelligence model can evaluate the appropriate ideas.

[1479] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1480] Program processing flow

[1481] Step 1: User enters idea details using a terminal

[1482] The user enters the name, content, market size, estimated share, royalty rate, and initial review score of the idea into the input screen of the terminal. The input data is in text format and divided into specific fields. This allows the user's idea to be recorded quantitatively and qualitatively. Input: Detailed information about the idea, Output: Detailed information about the idea data.

[1483] Step 2: The device uses the emotion engine to collect the user's emotion data.

[1484] While the user is inputting their ideas, the device uses the built-in camera and microphone to analyze the user's facial expressions and voice in real time. The emotion engine uses facial recognition and voice analysis algorithms to quantify the user's emotional state. Input: User's facial and voice data, Output: Emotion data.

[1485] Step 3: The user confirms the information they entered and the device sends it to the server

[1486] The user checks the input and presses the send button to send the data to the server. The device sends detailed idea data and emotion data in JSON format to the server. Input: Send instruction, Output: Data sent to the server.

[1487] Step 4: The server analyzes the received idea information

[1488] The server parses the received data and stores it in a database, converting the values ​​of each field to the appropriate data type and preparing it for evaluation. Input: Data sent to the server, Output: Parsed and stored data.

[1489] Step 5: The server inputs the emotion data into the generative AI model

[1490] The server uses the emotion data as input data for the generative AI model, which uses a pre-trained neural network. Input: Emotion data, Output: Emotion data converted into a data format for model input.

[1491] Step 6: The server runs the generative AI model and evaluates the ideas.

[1492] The server launches a generative AI model and predicts the probability of successful patent registration, the probability of a license agreement being concluded, the market size, and royalty rates based on input data such as market size, estimated market share, and first review score. Input: Detailed idea information and converted emotion data, Output: Idea evaluation results.

[1493] Step 7: The server uses the emotion engine to analyze the user's emotion data and integrate it into a rating.

[1494] The server uses an emotion engine to analyze the user's emotional data and evaluate how confident or stressed the user is about their idea. This result is integrated into the idea evaluation results as feedback. Input: User's emotional data and idea evaluation results. Output: Integrated evaluation results.

[1495] Step 8: The server calculates the expected return based on the evaluation results.

[1496] The server calculates the expected revenue using the following formula:

[1497] Market Revenue = Market Size Estimated Share

[1498] Expected revenue = Market revenue Probability of license agreement establishment Royalty rate

[1499] Input: Integrated valuation results, Output: Calculated expected profit.

[1500] Step 9: The server adjusts the expected revenue taking into account the sentiment data

[1501] The server considers the user's emotional data and makes conservative predictions if the user is overconfident, or adjusts the expected revenue while providing caring feedback if the user is feeling stressed. Input: Calculated expected revenue and emotional data, Output: Adjusted expected revenue.

[1502] Step 10: The server compares the calculated expected revenue with the patent application cost and makes a decision on whether to apply for the patent.

[1503] The server evaluates whether the adjusted expected revenue exceeds the standard patent application cost (1.2 million yen) and determines whether to recommend a patent application. Input: adjusted expected revenue and patent application cost, Output: judgment on whether to apply for a patent.

[1504] Step 11: The server sends the result of the decision to the terminal.

[1505] The server generates a result based on the patent application decision in JSON format and sends it to the user's device. This includes the decision result as well as a feedback message based on the user's emotional state. Input: Patent application approval / disapproval decision, Output: Results and feedback sent to the user's device.

[1506] Step 12: User Feedback

[1507] The user receives the results on the terminal and checks the displayed feedback message. For example, if there is a high possibility of success, the message "We recommend you apply for a patent" will be displayed, and if they are feeling less confident, the message will include encouragement and suggestions for improvement. Input: Results and feedback sent from the server. Output: Feedback message displayed on the terminal.

[1508] Step 13: Ongoing evaluation and monitoring after patent application

[1509] The server continues to monitor market fluctuations even after the patent application has been filed, and periodically evaluates the user's emotional state using an emotion engine. A reevaluation is performed within three years to determine whether the patent should be maintained. Input: Market data and emotion data. Output: Reevaluation results and decision on whether to maintain the patent.

[1510] (Application example 2)

[1511] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1512] Conventional patent evaluation systems evaluate ideas without taking the user's emotional state into account, resulting in evaluation results that do not necessarily match the user's actual intentions or circumstances. Furthermore, because emotional data is not used in the evaluation process, appropriate feedback cannot be provided to the user, potentially resulting in suboptimal decisions on patent applications. In response to these issues, the present invention aims to provide a system that integrates user emotional data to provide more appropriate evaluations and feedback.

[1513] The specific processing by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes: means for evaluating the probability of successful patent registration, probability of license agreement establishment, market size, and estimated share of a submitted idea using a generative artificial intelligence model; means for calculating an expected return on a patent application based on the evaluated parameters; means for comparing the expected return with the patent application cost and making a decision on the patent application; emotion recognition means for collecting and analyzing user emotion data; and means for integrating the emotion data obtained by the emotion recognition means into the evaluation and feeding it back into the evaluation result. This allows the evaluation of the submitted idea to reflect the user's emotional state, making it possible to make a more appropriate decision on the patent application.

[1514] A "generative artificial intelligence model" refers to an artificial intelligence algorithm designed to generate new information or predictions based on data.

[1515] "Probability of successful patent registration" refers to the probability that a submitted idea will be granted a patent.

[1516] The "probability of a license agreement being concluded" refers to the probability that, after a patent is obtained, a contract will be concluded to provide the technology or idea to other companies or individuals under a license agreement.

[1517] "Market size" refers to the economic size or value of the entire target market for a particular idea or product.

[1518] "Estimated share" refers to the percentage of the market that the submitted idea or product is expected to occupy.

[1519] "Expected return" refers to the expected amount of profit that an investment in a patent application will bring in the future.

[1520] "Patent application costs" refers to the set of expenses required to apply for a patent.

[1521] "User emotional data" refers to data that indicates the user's emotional state, as obtained through the user's facial expressions, voice, and other physiological data.

[1522] "Emotion recognition means" refers to technology and devices for detecting and analyzing a user's emotions.

[1523] "Means of providing feedback to evaluation results" refers to techniques and methods for reflecting analyzed emotional data in the evaluation process and improving the final evaluation results.

[1524] This invention is a system that uses a generative artificial intelligence model to evaluate submitted feedback and optimize store operations. By recognizing user emotions and reflecting them in the feedback, it is possible to make more appropriate operational decisions. A detailed description of this system is provided below.

[1525] composition

[1526] 1. User Device

[1527] Hardware: Computer, smartphone, smart glasses, or head-mounted display for feedback input.

[1528] Software: A camera to capture the user's face, and an emotion recognition application to collect emotional data.

[1529] 2. Server

[1530] Hardware: High-performance servers.

[1531] Software: Generative AI models, emotion recognition engines, and evaluation and feedback systems.

[1532] Program processing

[1533] The program of this system performs the following main processes.

[1534] 1. Data collection: The user device captures facial expressions and voice along with the customer feedback text to collect emotional data. This emotional data is analyzed in real time and sent to the server.

[1535] Software used: OpenCV (for face recognition), Transformers (Hugging Face emotion analysis model).

[1536] 2. Data analysis: On the server side, a generative AI model evaluates the characteristics of the submitted feedback and analyzes the emotion data obtained by the emotion recognition means.

[1537] Generative artificial intelligence model used: Transformers (Hugging Face generative model).

[1538] 3. Evaluation and integration: The analyzed emotion data is fed back into the evaluation results, and a final evaluation is made.

[1539] Example of feedback: Based on the evaluation results, specific operational improvement instructions such as "Improve the layout and expand the coffee corner" are generated.

[1540] 4. Result feedback: The server sends the evaluation results to the user's device and provides appropriate feedback to the user. For example, if the evaluation result is high, a message such as "This store management approach has a high chance of success!" is displayed.

[1541] Specific examples

[1542] For example, consider a user entering feedback such as, "I like the layout of the store, but the coffee corner is not well-equipped." A webcam captures the customer's face, and an emotion recognition model identifies the expression as "happiness." A generative AI model on the server side generates an evaluation result such as, "Areas for improvement: Improve the layout and expand the coffee corner," and notifies the user as final feedback, "This store management approach has a high chance of success!"

[1543] Prompt Sentence Examples

[1544] A request to develop an application that collects customer feedback and sentiment data and provides suggestions for improving store operations.

[1545] Integrate customer opinions and sentiments to provide optimal feedback to store managers.

[1546] This system allows submitted feedback to reflect the user's emotional state, enabling better decisions to be made about store management.

[1547] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1548] Step 1:

[1549] A user terminal provides an interface for inputting feedback text from a customer. The user inputs the feedback text, and the terminal transmits the text to a server. At this time, the terminal activates a camera and a microphone for collecting emotion data based on the feedback text. The input is the feedback text, and the output is the feedback data transmitted to the server.

[1550] Step 2:

[1551] The device uses a camera and microphone to capture the user's face and voice and collect emotion data. Specifically, the camera captures the user's facial expressions in real time and performs facial recognition using OpenCV. The microphone also records audio and the audio data is analyzed using an emotion recognition engine (Transformers emotion analysis model). The input is the user's face and voice, and the output is emotion data.

[1552] Step 3:

[1553] The device sends the collected emotion data and feedback text to the server. Specifically, the results of facial recognition and voice analysis are sent to the server as structured data. In this process, the input is the user's emotion data and feedback text, and the output is the data sent to the server.

[1554] Step 4:

[1555] The server analyzes the received feedback text and emotion data and inputs them into a generative AI model. Specifically, the generative AI model formats the feedback text and emotion data input, integrates them, and performs evaluation. In this process, the input is the feedback text and emotion data, and the output is the evaluation result.

[1556] Step 5:

[1557] The server generates feedback for optimizing store operations based on the evaluation results of the generative AI model. Specifically, it generates appropriate feedback messages based on the evaluation results and makes adjustments taking into account emotional data. In this process, the inputs are the evaluation results and emotional data, and the output is optimization feedback.

[1558] Step 6:

[1559] The server sends the generated feedback to the user's terminal. Specifically, the optimization feedback is sent in a format that is easy to display immediately to the user. In this process, the input is the optimization feedback, and the output is the feedback display on the terminal.

[1560] Step 7:

[1561] The user terminal displays the feedback received from the server and provides the user with instructions for operational improvement. Specifically, the received feedback message is displayed on the user interface for the user to check. In this process, the input is the feedback message, and the output is the feedback display to the user.

[1562] Through these steps, the system provides feedback that reflects the user's emotional state, optimizing store operations.

[1563] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[1564] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1565] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1566] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[1567] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1568] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[1569] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[1570] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, motorcycles, and other devices, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1571] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[1572] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[1573] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1574] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1575] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[1576] 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.

[1577] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[1578] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1579] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource t...

Claims

1. A means for evaluating the probability of successful patent registration, the probability of license agreement establishment, market size, and estimated share of a submitted idea using a generative artificial intelligence model; means for calculating an expected return on a patent application based on the evaluated parameters; A means for comparing the expected value of the return with the patent application cost and making a decision on whether to apply for a patent; A system including:

2. The system according to claim 1, wherein the generative artificial intelligence model performs evaluation based on the market size, estimated share, and initial screening score input by the user.

3. 2. The system according to claim 1, further comprising means for continuously monitoring market fluctuations and the competitive advantage of a patent after filing a patent application, and evaluating the necessity of maintaining the patent.

Images