system

Abstract

We provide the system. [Solution] A means for acquiring the output generated by the data generation device, In order to evaluate the acquired output, means for transmitting it to an evaluation device, The evaluation device includes means for comparing the output with existing data and evaluating its accuracy, A means for analyzing the evaluation results and providing them to the user terminal, A system that includes this.

Description

Technical Field

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

Background Art

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

Summary of the Invention

Problems to be Solved by the Invention

[0004] The inaccuracy and lack of reliability of the output generated in the conventional data generation technology have been an obstacle to the end-user's information acquisition. When providing particularly important information, there is a risk that incorrect data may affect the user's judgment, so it is necessary to solve these problems.

Means for Solving the Problems

[0005] The present invention provides a system that accurately evaluates the output generated by a data generation device with an evaluation device and provides the result to a user terminal. Thereby, the reliability of the output can be improved and accurate information can be provided to the user. Furthermore, the performance of the entire system is improved by a feedback loop using the evaluation result.

[0006] A "data generation device" is a device that has the function of generating specific output data based on input information from a user.

[0007] "Output" refers to the information or data generated as a result of processing by a data generation device.

[0008] An "evaluation device" is a device equipped with functions for evaluating the accuracy and reliability of the output generated by a data generation device.

[0009] "Reliability" is an indicator of how accurate and error-free the generated output is.

[0010] A "feedback loop" refers to a process for continuously improving the performance and accuracy of a system based on evaluation results.

[0011] A "user terminal" is a device used by a user to input information or receive output results through an interface. [Brief explanation of the drawing]

[0012] [Figure 1] This is a conceptual diagram showing an example of the configuration of a data processing system according to the first embodiment. [Figure 2] This is a conceptual diagram showing an example of the essential functions of a data processing device and a smart device according to the first embodiment. [Figure 3] This is a conceptual diagram showing an example of the configuration of a data processing system according to the second embodiment. [Figure 4] This is a conceptual diagram showing an example of the main functions of a data processing device and smart glasses according to the second embodiment. [Figure 5] This is a conceptual diagram showing an example of the configuration of a data processing system according to the third embodiment. [Figure 6] This is a conceptual diagram showing an example of the main functions of a data processing device and a headset-type terminal according to the third embodiment. [Figure 7]It is a conceptual diagram showing an example of the configuration of a data processing system according to the fourth embodiment. [Figure 8] It is a conceptual diagram showing an example of the main functions of a data processing device and a robot according to the fourth embodiment. [Figure 9] It shows an emotion map to which a plurality of emotions are mapped. [Figure 10] It shows an emotion map to which a plurality of emotions are mapped. [Figure 11] It is a sequence diagram showing the processing flow of the data processing system in Example 1. [Figure 12] It is a sequence diagram showing the processing flow of the data processing system in Application Example 1. [Figure 13] It is a sequence diagram showing the processing flow of the data processing system in Example 2 when an emotion engine is combined. [Figure 14] It is a sequence diagram showing the processing flow of the data processing system in Application Example 2 when an emotion engine is combined.

Modes for Carrying Out the Invention

[0013] Hereinafter, an example of an embodiment of a system according to the technology of the present disclosure will be described with reference to the accompanying drawings.

[0014] First, the language used in the following description will be explained.

[0015] In the following embodiments, the numbered processor (hereinafter simply referred to as "processor") may be a single arithmetic unit or a combination of multiple arithmetic units. Also, the processor may be a single type of arithmetic unit or a combination of multiple types of arithmetic units. Examples of arithmetic units include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), and the like.

[0016] In the following embodiments, the numbered RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a work memory by the processor.

[0017] In the following embodiments, the numbered storage is one or more non-volatile storage devices that store various programs and various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), or magnetic tapes, etc.

[0018] In the following embodiments, the numbered communication I / F (Interface) is an interface including a communication processor and an antenna, etc. The communication I / F manages 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), or Bluetooth (registered trademark), etc.

[0019] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." That is, "A and / or B" means that it may be A alone, or B alone, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" applies when expressing three or more things linked by "and / or."

[0020] [First Embodiment]

[0021] Figure 1 shows an example of the configuration of the data processing system 10 according to the first embodiment.

[0022] As shown in Figure 1, the data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0023] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0024] The smart device 14 comprises a computer 36, a reception device 38, an output device 40, a camera 42, and a communication interface 44. The computer 36 comprises a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The reception device 38, output device 40, and camera 42 are also connected to the bus 52.

[0025] The reception device 38 is equipped with a touch panel 38A and a microphone 38B, etc., and receives user input. The touch panel 38A receives user input by detecting contact with an object (e.g., a pen or finger). The microphone 38B receives user input by detecting the user's voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0026] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form perceptible to the user 20 (e.g., audio and / or text). The display 40A displays visible information such as text and images according to instructions from the processor 46. The speaker 40B outputs audio according to instructions from the processor 46. The camera 42 is a small digital camera equipped with an optical system such as a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0027] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various types of information between processor 46 and processor 28 via network 54.

[0028] Figure 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0029] As shown in Figure 2, in the data processing device 12, a specific processing is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" related to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 according to the specific processing program 56 executed on the RAM 30.

[0030] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0031] In the smart device 14, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The reception output program 60 is used in conjunction with a specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0032] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0033] One embodiment of the present invention is a system that improves the reliability of generated data by evaluating the output generated by a data generation device using an evaluation device and providing the evaluation results to the user. A specific embodiment thereof is described below.

[0034] In this system, the user first inputs specific information or questions through a terminal. The input data is sent by the server to a data generation device, which uses an appropriate algorithm to generate output in response to the user's request. The generated output is monitored by the server and then sent to an evaluation device.

[0035] The evaluation device assesses the accuracy of the output data by comparing it with pre-stored accurate information and existing data sources. This evaluation process allows for the identification of any problems in the generated output, such as errors or hallucinations.

[0036] The evaluation results are analyzed by the server, and feedback is generated, including corrections and points to note as needed. This feedback is provided to the user via the terminal. Based on this feedback, the user can verify the reliability of the provided information and take necessary actions.

[0037] As another concrete example, consider a scenario where a user requests a report on the latest environmental regulations via their device. The server receives this request and generates the report content via a data generation device. The generated report is then validated for reliability by an evaluation device. The evaluation device compares the information with legal databases and government regulatory repositories to verify that the output conforms to current laws and regulations. As a result, the user receives a reliable report that indicates areas that need correction.

[0038] This system provides users with the reassurance that they can always obtain accurate information, and can be used as a foundation for streamlining operations and making accurate decisions. Furthermore, feedback will be used to improve the system in the future.

[0039] The following describes the processing flow.

[0040] Step 1:

[0041] The user uses a terminal to input the information or questions they want as text. This input is sent as a request to the server.

[0042] Step 2:

[0043] The server parses the request received from the user and forwards it to the data generation device. The data generation device uses a specified algorithm to generate information based on the request.

[0044] Step 3:

[0045] The server monitors the output received from the data generation device and transfers the output data to the evaluation device. The evaluation device compares the generated output with an internal database and reliable external sources to verify its accuracy.

[0046] Step 4:

[0047] The evaluation device assesses the accuracy and reliability of each data point in the output and returns the results to the server. The server records and analyzes these evaluation results.

[0048] Step 5:

[0049] The server organizes necessary corrections and warnings based on the evaluation results and generates a feedback message for the user. This feedback includes details about areas with reliability issues and inaccuracies.

[0050] Step 6:

[0051] The terminal receives feedback messages from the server and displays them to the user. This allows the user to verify the reliability of the output and make appropriate decisions or take further actions.

[0052] Step 7:

[0053] The server continuously executes a feedback loop to improve future data generation and evaluation processes based on evaluation results and user feedback. This feedback improves the system's performance and the accuracy of its output.

[0054] (Example 1)

[0055] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0056] Existing information generation systems have faced challenges in quickly evaluating the accuracy and reliability of the generated data. In particular, there was concern that the information output by the generation model might contain errors or hallucinations, potentially negatively impacting user decision-making. Solving this problem necessitates providing a system that allows users to confidently utilize accurate and reliable information.

[0057] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0058] In this invention, the server includes means for receiving information input from a user terminal, generating and transferring prompt messages to a data generation device, means for monitoring the output generated by the data generation device and transmitting it to an evaluation device, and means for generating feedback based on the evaluation results from the evaluation device and providing it to the user terminal. This makes it possible to quickly evaluate the accuracy of the generated data and provide the user with reliable information.

[0059] A "user terminal" is a device used by users to input information or questions and receive feedback.

[0060] A "server" is a device that receives requests from user terminals and acts as an intermediary for information between data generation devices and evaluation devices.

[0061] A "data generation device" is a device that generates output based on prompt sentences using a generation AI model.

[0062] A "generative AI model" is a model equipped with algorithms for generating natural language, and it generates information according to the user's requests.

[0063] A "prompt statement" is an instruction statement that a server uses to instruct a data generation device to generate output.

[0064] An "evaluation device" is a device that has the function of comparing the generated output with existing data and evaluating its accuracy.

[0065] "Feedback" refers to information provided to the user, including points for output correction and precautions, based on the evaluation results obtained from the evaluation device.

[0066] The embodiment of the present invention begins with a user inputting specific information or a question using a terminal. This terminal is a device that the user uses as an interface to the system, and specifically includes personal computers and smartphones. For example, suppose the user inputs, "Please provide me with a report on the latest environmental regulations."

[0067] The server is responsible for receiving this request. The server converts the requested information into the appropriate format and generates a prompt. Based on the generated prompt, the server sends its contents to the data generation device. A possible generative AI model used at this time is, for example, GPT-4 (registered trademark). The generative AI model generates an appropriate response based on the prompt.

[0068] Data generation devices equipped with generative AI models generate information in response to user requests. Because the generated information utilizes natural language processing technology, it provides detailed output tailored to the user's needs.

[0069] The generated output is monitored by a server and then sent to an evaluation device. The evaluation device is designed to assess the accuracy of the generated data. Here, the evaluation device verifies the accuracy by comparing the generated data against pre-stored databases and other reliable sources. For example, it might compare the data with legal databases or government regulatory repositories.

[0070] Finally, based on the evaluation results, the server generates feedback and provides it to the user via the terminal. This feedback may include areas that need correction or important notes. Based on this feedback, the user can verify the reliability of the information and take necessary actions. This allows the user to make decisions based on accurate information with confidence.

[0071] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0072] Step 1:

[0073] The user enters specific information or questions using a terminal. For example, they might enter a request such as, "Please provide a report on the latest environmental regulations." This input is sent to the server via the terminal. At this stage, the user's request is passed to the server as specific text data as output.

[0074] Step 2:

[0075] The server receives the user's request and generates an appropriate prompt. This prompt is then converted into a format that the data generator can easily understand. Specifically, it constructs the necessary syntax and conditions in the generating AI model according to the user's request. This prompt becomes the input from the server to the data generator. As output, a formalized prompt is generated.

[0076] Step 3:

[0077] The data generation device generates information based on prompt messages received from the server. Within this device, a generation AI model operates, analyzing the prompt messages and generating appropriate information. For example, it can generate reports based on user requests. During this process, the model performs natural language processing to generate detailed responses. The output is the generated text data.

[0078] Step 4:

[0079] The server monitors the output from the data generator and prepares it for transmission to the evaluation device. The input here is the output data from the generator. The server structures this data and transmits it to the evaluation device in a format suitable for evaluation. The output in this step is the data used for analysis and evaluation.

[0080] Step 5:

[0081] The evaluation device compares the received output data with pre-stored information to assess its accuracy. The input is generated data transmitted from the server. Here, the evaluation device verifies accuracy based on legal databases and regulatory repositories. This evaluation identifies inconsistencies and errors. The evaluation results are generated as output.

[0082] Step 6:

[0083] The server receives evaluation results returned from the evaluation device and generates feedback as needed. The input is the evaluation results from the evaluation device. Based on this information, the server creates feedback including corrections and precautions that should be provided to the user. This process allows the user to verify the reliability of the information. The output is detailed feedback sent to the user's terminal.

[0084] Step 7:

[0085] Users receive feedback on their devices and evaluate the reliability of the information based on that feedback. The information provided in the feedback is reviewed, and necessary actions are taken. This process allows users to trust the accuracy of the information. The final output is reliable information for the user, along with specific actionable guidelines based on that information.

[0086] (Application Example 1)

[0087] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart device 14 will be referred to as the "terminal."

[0088] In today's consumer environment, the reliability of product and pricing information is crucial. However, inaccurate information can hinder purchasing decisions. There is a need to solve this problem and enable consumers to make quick and accurate product choices based on reliable information.

[0089] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0090] In this invention, the server includes means for acquiring output generated by a data generation device, means for transmitting the acquired output to an evaluation device for evaluation, and means for evaluating the generated product information and outputting it as appropriate purchasing information. This enables consumers to select products based on reliable information and make decisions quickly and efficiently.

[0091] A "data generation device" is a system that generates and provides specific information or data based on user requests.

[0092] An "evaluation device" is a device used to compare the generated output with existing data and evaluate its accuracy and reliability.

[0093] "Evaluation results" refer to information obtained after the reliability of the output has been analyzed by the evaluation device.

[0094] A "user terminal" is a device equipped with an interface for providing evaluation results to the user.

[0095] "Product information" refers to detailed information about prices and promotions that consumers need to make purchasing decisions.

[0096] "Purchase information" refers to reliable data generated based on evaluated product information, which serves as a reference for consumers when making their final purchase decisions.

[0097] A "feedback loop" is a process for improving the functions of data generation and evaluation devices based on evaluation results.

[0098] This invention is implemented as a smartphone application equipped with a system for providing consumers with reliable product information. The server generates relevant product data using a data generation device based on product information received from the user's terminal. This data generation device is equipped with a generation AI model and generates information according to the user's requests.

[0099] The generated data is sent to an evaluation device, where it is compared with existing databases and its accuracy is assessed. The evaluation device uses AI-powered analysis to compare the generated data with current pricing and promotional data to measure reliability. Through this process, the server analyzes the evaluation results and generates feedback, including any necessary corrections or points to note.

[0100] The device provides product information through this feedback. This information is presented in a format that users can receive as prompts, helping consumers make purchasing decisions based on accurate and reliable information. Specifically, if a user is looking to buy organic milk at a supermarket, the app allows them to find real-time milk prices, applicable promotions, and the best discounts.

[0101] As an example of a prompt using a generative AI model, "Please tell me the latest price and promotional information for the organic milk I plan to buy." This allows users to experience greater satisfaction in their purchasing activities and reduces misunderstandings and discrepancies in perception.

[0102] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0103] Step 1:

[0104] The user enters information about the product they wish to purchase through their terminal. For example, they can scan the product's barcode or directly enter the product name. The entered product data is then sent to the server.

[0105] Step 2:

[0106] The server sends the received product data to a data generation device, from which detailed product information is generated. At this stage, a generation AI model is used to generate product data, including price and promotions, based on the latest information. The generated data undergoes sophisticated data processing and calculations before being output and sent to an evaluation device.

[0107] Step 3:

[0108] The evaluation system compares the generated product data with existing databases. Here, it performs comparative analysis of the data to assess the accuracy and reliability of the products. This process verifies that the generated data matches current pricing and promotional information. The evaluation results are returned to the server.

[0109] Step 4:

[0110] The server analyzes the evaluation results and generates feedback with necessary corrections and notes added. This feedback includes the reliability of the evaluated product and any special notes to be provided to the user. The generated feedback is sent to the user's terminal.

[0111] Step 5:

[0112] The device displays the received feedback to the user. This feedback includes reliable product information based on the prompt "Please tell me the latest price and promotional information for the organic milk I plan to buy." The user can then use this information to make a purchase decision.

[0113] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0114] One embodiment of the present invention is a system that combines an evaluation device that evaluates the output generated by a data generation device with an emotion engine that recognizes the user's emotions. This improves the accuracy of the generated data and enhances the user experience.

[0115] First, the user requests specific information through the terminal. This request is received by the server and processed by a data generator. The generator proceeds to produce appropriate output that matches the user's request. Simultaneously, the server uses an emotion engine to analyze and recognize the emotions from the user's input text.

[0116] The generated output is sent as input to the evaluation device and compared with existing data to verify its accuracy and reliability. The evaluation device adjusts the output to optimize the user experience based on the emotional information provided by the emotion engine.

[0117] For example, if a user enters "Please give us your feedback on the new product" on their device, the sentiment engine recognizes, based on the input and past interactions, that the user may be expressing decreased customer satisfaction. The server then uses this sentiment information to customize the generator's output, adjusting the evaluation results to highlight specific areas for improvement and positive aspects. This information is ultimately provided to the user to help increase their satisfaction.

[0118] The information provided will be used not only for user feedback but also in a feedback loop to improve the overall system, thereby enhancing the accuracy of future response generation and emotion recognition.

[0119] This system allows users to receive more personalized and reliable information. Companies can improve the quality of their customer service while simultaneously increasing the efficiency of their overall processes.

[0120] The following describes the processing flow.

[0121] Step 1:

[0122] The user enters specific questions or requests as text through their terminal. This input is sent to the server and triggers the start of processing.

[0123] Step 2:

[0124] The server sends the input received from the user to a data generation device and executes a process to generate output data corresponding to the request. The output generated here directly answers the user's question.

[0125] Step 3:

[0126] Simultaneously, the server uses an emotion engine to analyze the user's emotional state from the user's input data. For example, it extracts emotions such as positive, negative, or neutral from keywords and context included in the input.

[0127] Step 4:

[0128] The generated output is sent to an evaluation device. The evaluation device compares this output against pre-defined criteria and a reliable database to verify the accuracy and overall reliability of the content.

[0129] Step 5:

[0130] The server receives evaluation results from the evaluation device and combines them with the user's sentiment analysis results. Based on the evaluation results and sentiment analysis, the server adjusts the output results and considers areas for improvement to optimize the user experience.

[0131] Step 6:

[0132] The terminal receives the final adjusted output and presents the information to the user in an easy-to-understand format. This may include special emphasis or attention tailored to the user's emotions. For example, if negative emotions are detected, the output may include positive information or suggestions.

[0133] Step 7:

[0134] The server stores evaluation results and sentiment analysis data within the system, utilizing it as a feedback loop to improve future response accuracy and output adjustment capabilities. This allows for continuous improvement of the overall system performance.

[0135] (Example 2)

[0136] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the smart device 14 as the "terminal".

[0137] In information systems, a challenge exists in that the information users receive is not personalized, and user emotions are not taken into consideration, making it difficult to improve the user experience. Furthermore, it is necessary to improve the overall response generation and responsiveness of the system while ensuring the reliability of the generated data.

[0138] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0139] In this invention, the server includes means for an information processing device to acquire information requests from a user terminal, means for the information processing device to generate appropriate data using a generated AI model, and means for the information processing device to identify the user's emotions using an emotion analysis engine. This makes it possible to provide personalized information that takes into account the user's emotions and generate reliable data, thereby improving the user experience.

[0140] An "information processing device" is a device that acquires information input from a user terminal and generates and evaluates data.

[0141] A "generative AI model" is an artificial intelligence algorithm that analyzes user prompts and generates appropriate data.

[0142] An "emotion analysis engine" is software or hardware that analyzes user input data and identifies the user's emotional state from that data.

[0143] An "evaluation device" is a device used to compare generated data with existing data and determine its accuracy and reliability.

[0144] A "feedback loop" is a cyclical process that incorporates evaluation results and sentiment analysis data into the system to continuously improve performance and enhance overall quality.

[0145] This invention is a system for providing personalized, highly reliable information in response to user information requests.

[0146] The process begins with the user requesting specific information through their device. This request is received by the server, which then uses a generative AI model via an information processing device to generate data that meets the user's requirements. For example, a generative AI model employing natural language processing technology might be used in this process.

[0147] Simultaneously, the server uses an emotion analysis engine to analyze the user's input text and identify its emotional state. This is done to understand what emotions the user is feeling when seeking information, determining emotions such as "dissatisfaction" or "expectation." The emotion analysis engine can calculate an emotion score from specific keywords and context.

[0148] The generated data is sent to an evaluation device and compared with existing data. This evaluation determines the accuracy and reliability of the information generation. If improvements are found based on the evaluation, the data is adjusted to take user emotions into account, based on emotional information. For example, if negative emotions are detected, positive elements are emphasized.

[0149] Through this process, the server returns the finalized information to the user's terminal. This allows the user to receive appropriate information tailored to their individual needs, resulting in increased satisfaction.

[0150] For example, if a user enters "Please give us your feedback on the new product" into their device, the server generates data using a generative AI model. If the sentiment analysis engine determines the user's emotion to be "dissatisfied," the server provides information focusing on improvement measures and positive aspects based on the evaluation results.

[0151] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0152] Step 1:

[0153] The user sends an information request from their device. For example, the user might enter a prompt message such as, "Please provide feedback on the new product." The device receives this input and sends a request to the server using a secure communication method.

[0154] Step 2:

[0155] The server receives a request from the terminal and forwards it to the information processing unit. The information processing unit analyzes the input prompt text and generates data using a generative AI model. The generative AI model utilizes natural language processing to generate appropriate feedback information based on the user's request. The output of this model is obtained as feedback information.

[0156] Step 3:

[0157] Simultaneously, the server starts up the sentiment analysis engine and analyzes the user's input text. In this process, the sentiment analysis engine analyzes the input prompt text and determines the user's emotional state (e.g., dissatisfaction, interest). This is done by calculating an emotion score using keywords and context within the text. The output provides the type of emotion and its score.

[0158] Step 4:

[0159] The generated data is sent to an evaluation device. The evaluation device assesses the accuracy and reliability of this feedback data by comparing it to an existing database. This process includes data integrity checks and error analysis. The output is a report of the evaluated data and evaluation results.

[0160] Step 5:

[0161] The evaluation device adjusts the generated data based on the obtained emotional information and evaluation results. Specifically, if negative emotions are detected, the data is optimized to emphasize positive elements and improvement measures. This adjusted data is used as the final output.

[0162] Step 6:

[0163] The server returns the adjusted data to the user's device. The device displays the received information to the user. The user can review the personalized feedback, which takes emotions into account, and decide on their next action based on this information.

[0164] (Application Example 2)

[0165] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as a "server" and the smart device 14 as a "terminal".

[0166] In the digital market, recognizing the products and services users desire and providing relevant information is crucial for customer satisfaction and sales promotion. However, traditional systems have struggled to accurately grasp users' emotions and needs and provide information based on them, thus failing to fully meet customer expectations.

[0167] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0168] In this invention, the server includes means for acquiring output generated by a data generation device, means for transmitting the acquired output to an evaluation device, and means for performing emotion recognition processing and adjusting the generated output based on the user's emotions. This makes it possible to provide personalized information that takes the user's emotions into consideration.

[0169] A "data generation device" is a device that generates a specific output based on the input information.

[0170] An "evaluation device" is a device that compares the generated output with existing data to determine its accuracy and reliability.

[0171] "Emotion recognition processing" is the process of analyzing input information from the user to identify and understand the emotions the user is experiencing.

[0172] A "user terminal" refers to a device that a user directly operates to input or retrieve information.

[0173] "Output adjustment" refers to the process of optimizing the content of the generated output to match the user's emotions and needs.

[0174] "Product information" refers to all information related to a specific product and is used when making recommendations.

[0175] "Benefit information" refers to information that provides additional value to users and is intended to promote the sale of products and services.

[0176] The system for realizing this invention is configured to provide information based on the user's emotions and needs, with the aim of improving the customer experience in the digital market.

[0177] The server uses a data generation device to generate output based on requests received from user terminals. The generated output is sent to an evaluation device, where its accuracy and reliability are evaluated by comparing it with existing data. The evaluation results are used to consider the user's emotions through sentiment recognition processing and to personalize and optimize the output.

[0178] This emotion recognition process utilizes APIs commonly used in natural language processing. Specifically, services such as Google Cloud Natural Language API are used to analyze emotions from user input. The analyzed emotion information is then analyzed by a machine learning model using TENSORFLOW® to generate the optimal combination of product and reward information based on data from other users with similar emotions.

[0179] This system activates when a user submits a product review using a smartphone application in response to a prompt such as, "Please tell us your opinion about this product." For example, if a review such as, "This T-shirt is lighter in color than I expected," is submitted, the emotion engine detects the dissatisfied emotion and, based on similar feedback, makes recommendations such as, "How about other T-shirts from this brand?"

[0180] Through this series of processes, the user experience is improved, and more personalized information is delivered.

[0181] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0182] Step 1:

[0183] The terminal receives a request from the user. The user enters feedback and opinions about the product through the terminal. This input data is sent to the server as text information.

[0184] Step 2:

[0185] The server sends the received text information to the Google Cloud Natural Language API for sentiment analysis. The input is text posted by the user, and the output is analyzed sentiment information (e.g., positive, negative, neutral). Through this analysis, the server gains a quantitative understanding of the user's emotions.

[0186] Step 3:

[0187] The server uses a data generation device to generate user-specific information based on the results of sentiment analysis. This device runs a machine learning model using TensorFlow and references past data of similar emotions. The input is sentiment information and existing data, and the output is emotion-based, adjusted information. At this stage, it becomes possible to provide specific information.

[0188] Step 4:

[0189] The server sends the generated output to the evaluation device. The evaluation device compares this output with an existing database and evaluates its accuracy. The input is the generated information, and the output is the result of the reliability evaluation of that information. During the evaluation process, reliability checks and corrections are performed.

[0190] Step 5:

[0191] The server adjusts the generated output based on evaluation results and sentiment information, and provides it to the user's terminal. The terminal then presents this to the user, displaying the most appropriate product and benefit information. The input is the evaluation results and adjusted information, and the output is the final information presentation. Through this process, the user receives a personalized service experience.

[0192] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0193] Data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of data generation model 58 is ChatGPT (registered trademark) (Internet search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0194] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart device 14.

[0195] [Second Embodiment]

[0196] Figure 3 shows an example of the configuration of the data processing system 210 according to the second embodiment.

[0197] As shown in Figure 3, the data processing system 210 includes a data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0198] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0199] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication interface 44. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, and camera 42 are also connected to the bus 52.

[0200] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0201] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0202] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0203] Figure 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Figure 4, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0204] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0205] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0206] In the smart glasses 214, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0207] Next, the identification processing performed by the identification processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal".

[0208] One embodiment of the present invention is a system that improves the reliability of generated data by evaluating the output generated by a data generation device using an evaluation device and providing the evaluation results to the user. A specific embodiment thereof is described below.

[0209] In this system, the user first inputs specific information or questions through a terminal. The input data is sent by the server to a data generation device, which uses an appropriate algorithm to generate output in response to the user's request. The generated output is monitored by the server and then sent to an evaluation device.

[0210] The evaluation device assesses the accuracy of the output data by comparing it with pre-stored accurate information and existing data sources. This evaluation process allows for the identification of any problems in the generated output, such as errors or hallucinations.

[0211] The evaluation results are analyzed by the server, and feedback is generated, including corrections and points to note as needed. This feedback is provided to the user via the terminal. Based on this feedback, the user can verify the reliability of the provided information and take necessary actions.

[0212] As another concrete example, consider a scenario where a user requests a report on the latest environmental regulations via their device. The server receives this request and generates the report content via a data generation device. The generated report is then validated for reliability by an evaluation device. The evaluation device compares the information with legal databases and government regulatory repositories to verify that the output conforms to current laws and regulations. As a result, the user receives a reliable report that indicates areas that need correction.

[0213] This system provides users with the reassurance that they can always obtain accurate information, and can be used as a foundation for streamlining operations and making accurate decisions. Furthermore, feedback will be used to improve the system in the future.

[0214] The following describes the processing flow.

[0215] Step 1:

[0216] The user uses a terminal to input the information or questions they want as text. This input is sent as a request to the server.

[0217] Step 2:

[0218] The server parses the request received from the user and forwards it to the data generation device. The data generation device uses a specified algorithm to generate information based on the request.

[0219] Step 3:

[0220] The server monitors the output received from the data generation device and transfers the output data to the evaluation device. The evaluation device compares the generated output with an internal database and reliable external sources to verify its accuracy.

[0221] Step 4:

[0222] The evaluation device assesses the accuracy and reliability of each data point in the output and returns the results to the server. The server records and analyzes these evaluation results.

[0223] Step 5:

[0224] The server organizes necessary corrections and warnings based on the evaluation results and generates a feedback message for the user. This feedback includes details about areas with reliability issues and inaccuracies.

[0225] Step 6:

[0226] The terminal receives feedback messages from the server and displays them to the user. This allows the user to verify the reliability of the output and make appropriate decisions or take further actions.

[0227] Step 7:

[0228] The server continuously executes a feedback loop to improve future data generation and evaluation processes based on evaluation results and user feedback. This feedback improves the system's performance and the accuracy of its output.

[0229] (Example 1)

[0230] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0231] Existing information generation systems have faced challenges in quickly evaluating the accuracy and reliability of the generated data. In particular, there was concern that the information output by the generation model might contain errors or hallucinations, potentially negatively impacting user decision-making. Solving this problem necessitates providing a system that allows users to confidently utilize accurate and reliable information.

[0232] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0233] In this invention, the server includes means for receiving information input from a user terminal, generating and transferring prompt messages to a data generation device, means for monitoring the output generated by the data generation device and transmitting it to an evaluation device, and means for generating feedback based on the evaluation results from the evaluation device and providing it to the user terminal. This makes it possible to quickly evaluate the accuracy of the generated data and provide the user with reliable information.

[0234] A "user terminal" is a device used by users to input information or questions and receive feedback.

[0235] A "server" is a device that receives requests from user terminals and acts as an intermediary for information between data generation devices and evaluation devices.

[0236] A "data generation device" is a device that generates output based on prompt sentences using a generation AI model.

[0237] A "generative AI model" is a model equipped with algorithms for generating natural language, and it generates information according to the user's requests.

[0238] A "prompt statement" is an instruction statement that a server uses to instruct a data generation device to generate output.

[0239] An "evaluation device" is a device that has the function of comparing the generated output with existing data and evaluating its accuracy.

[0240] "Feedback" refers to information provided to the user, including points for output correction and precautions, based on the evaluation results obtained from the evaluation device.

[0241] The embodiment of the present invention begins with a user inputting specific information or a question using a terminal. This terminal is a device that the user uses as an interface to the system, and specifically includes personal computers and smartphones. For example, suppose the user inputs, "Please provide me with a report on the latest environmental regulations."

[0242] The server is responsible for receiving this request. The server converts the requested information into the appropriate format and generates a prompt. Based on the generated prompt, the server sends its contents to the data generation device. A generative AI model such as GPT-4 could be used at this time. The generative AI model generates an appropriate response based on the prompt.

[0243] Data generation devices equipped with generative AI models generate information in response to user requests. Because the generated information utilizes natural language processing technology, it provides detailed output tailored to the user's needs.

[0244] The generated output is monitored by a server and then sent to an evaluation device. The evaluation device is designed to assess the accuracy of the generated data. Here, the evaluation device verifies the accuracy by comparing the generated data against pre-stored databases and other reliable sources. For example, it might compare the data with legal databases or government regulatory repositories.

[0245] Finally, based on the evaluation results, the server generates feedback and provides it to the user via the terminal. This feedback may include areas that need correction or important notes. Based on this feedback, the user can verify the reliability of the information and take necessary actions. This allows the user to make decisions based on accurate information with confidence.

[0246] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0247] Step 1:

[0248] The user enters specific information or questions using a terminal. For example, they might enter a request such as, "Please provide a report on the latest environmental regulations." This input is sent to the server via the terminal. At this stage, the user's request is passed to the server as specific text data as output.

[0249] Step 2:

[0250] The server receives the user's request and generates an appropriate prompt. This prompt is then converted into a format that the data generator can easily understand. Specifically, it constructs the necessary syntax and conditions in the generating AI model according to the user's request. This prompt becomes the input from the server to the data generator. As output, a formalized prompt is generated.

[0251] Step 3:

[0252] The data generation device generates information based on prompt messages received from the server. Within this device, a generation AI model operates, analyzing the prompt messages and generating appropriate information. For example, it can generate reports based on user requests. During this process, the model performs natural language processing to generate detailed responses. The output is the generated text data.

[0253] Step 4:

[0254] The server monitors the output from the data generator and prepares it for transmission to the evaluation device. The input here is the output data from the generator. The server structures this data and transmits it to the evaluation device in a format suitable for evaluation. The output in this step is the data used for analysis and evaluation.

[0255] Step 5:

[0256] The evaluation device compares the received output data with pre-stored information to assess its accuracy. The input is generated data transmitted from the server. Here, the evaluation device verifies accuracy based on legal databases and regulatory repositories. This evaluation identifies inconsistencies and errors. The evaluation results are generated as output.

[0257] Step 6:

[0258] The server receives evaluation results returned from the evaluation device and generates feedback as needed. The input is the evaluation results from the evaluation device. Based on this information, the server creates feedback including corrections and precautions that should be provided to the user. This process allows the user to verify the reliability of the information. The output is detailed feedback sent to the user's terminal.

[0259] Step 7:

[0260] Users receive feedback on their devices and evaluate the reliability of the information based on that feedback. The information provided in the feedback is reviewed, and necessary actions are taken. This process allows users to trust the accuracy of the information. The final output is reliable information for the user, along with specific actionable guidelines based on that information.

[0261] (Application Example 1)

[0262] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0263] In today's consumer environment, the reliability of product and pricing information is crucial. However, inaccurate information can hinder purchasing decisions. There is a need to solve this problem and enable consumers to make quick and accurate product choices based on reliable information.

[0264] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0265] In this invention, the server includes means for acquiring output generated by a data generation device, means for transmitting the acquired output to an evaluation device for evaluation, and means for evaluating the generated product information and outputting it as appropriate purchasing information. This enables consumers to select products based on reliable information and make decisions quickly and efficiently.

[0266] A "data generation device" is a system that generates and provides specific information or data based on user requests.

[0267] An "evaluation device" is a device used to compare the generated output with existing data and evaluate its accuracy and reliability.

[0268] "Evaluation results" refer to information obtained after the reliability of the output has been analyzed by the evaluation device.

[0269] A "user terminal" is a device equipped with an interface for providing evaluation results to the user.

[0270] "Product information" refers to detailed information about prices and promotions that consumers need to make purchasing decisions.

[0271] "Purchase information" refers to reliable data generated based on evaluated product information, which serves as a reference for consumers when making their final purchase decisions.

[0272] A "feedback loop" is a process for improving the functions of data generation and evaluation devices based on evaluation results.

[0273] This invention is implemented as a smartphone application equipped with a system for providing consumers with reliable product information. The server generates relevant product data using a data generation device based on product information received from the user's terminal. This data generation device is equipped with a generation AI model and generates information according to the user's requests.

[0274] The generated data is sent to an evaluation device, where it is compared with existing databases and its accuracy is assessed. The evaluation device uses AI-powered analysis to compare the generated data with current pricing and promotional data to measure reliability. Through this process, the server analyzes the evaluation results and generates feedback, including any necessary corrections or points to note.

[0275] The device provides product information through this feedback. This information is presented in a format that users can receive as prompts, helping consumers make purchasing decisions based on accurate and reliable information. Specifically, if a user is looking to buy organic milk at a supermarket, the app allows them to find real-time milk prices, applicable promotions, and the best discounts.

[0276] As an example of a prompt using a generative AI model, "Please tell me the latest price and promotional information for the organic milk I plan to buy." This allows users to experience greater satisfaction in their purchasing activities and reduces misunderstandings and discrepancies in perception.

[0277] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0278] Step 1:

[0279] The user inputs information about the product they want to purchase through the terminal. For example, they scan the barcode of the product or directly input the product name. The input product data is sent to the server.

[0280] Step 2:

[0281] The server sends the received product data to the data generation device to generate detailed product information. At this stage, the generation AI model is used to generate product data including price and promotion based on the latest information. The generated data is output after refined data processing and calculations and sent to the evaluation device.

[0282] Step 3:

[0283] The evaluation device compares the generated product data with the existing database. Here, a comparative analysis of the data is performed to evaluate the accuracy and reliability of the product. This process checks whether the generated data matches the current price information and promotion information. The evaluation result is returned to the server.

[0284] Step 4:

[0285] The server analyzes the evaluation result and generates feedback with necessary corrections and points to note added. This feedback includes the reliability of the evaluated product and special items to be provided to the user. The generated feedback is sent to the user terminal.

[0286] Step 5:

[0287] The device displays the received feedback to the user. This feedback includes reliable product information based on the prompt "Please tell me the latest price and promotional information for the organic milk I plan to buy." The user can then use this information to make a purchase decision.

[0288] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0289] One embodiment of the present invention is a system that combines an evaluation device that evaluates the output generated by a data generation device with an emotion engine that recognizes the user's emotions. This improves the accuracy of the generated data and enhances the user experience.

[0290] First, the user requests specific information through the terminal. This request is received by the server and processed by a data generator. The generator proceeds to produce appropriate output that matches the user's request. Simultaneously, the server uses an emotion engine to analyze and recognize the emotions from the user's input text.

[0291] The generated output is sent as input to the evaluation device and compared with existing data to verify its accuracy and reliability. The evaluation device adjusts the output to optimize the user experience based on the emotional information provided by the emotion engine.

[0292] For example, if a user enters "Please give us your feedback on the new product" on their device, the sentiment engine recognizes, based on the input and past interactions, that the user may be expressing decreased customer satisfaction. The server then uses this sentiment information to customize the generator's output, adjusting the evaluation results to highlight specific areas for improvement and positive aspects. This information is ultimately provided to the user to help increase their satisfaction.

[0293] The information provided will be used not only for user feedback but also in a feedback loop to improve the overall system, thereby enhancing the accuracy of future response generation and emotion recognition.

[0294] This system allows users to receive more personalized and reliable information. Companies can improve the quality of their customer service while simultaneously increasing the efficiency of their overall processes.

[0295] The following describes the processing flow.

[0296] Step 1:

[0297] The user enters specific questions or requests as text through their terminal. This input is sent to the server and triggers the start of processing.

[0298] Step 2:

[0299] The server sends the input received from the user to a data generation device and executes a process to generate output data corresponding to the request. The output generated here directly answers the user's question.

[0300] Step 3:

[0301] Simultaneously, the server uses an emotion engine to analyze the user's emotional state from the user's input data. For example, it extracts emotions such as positive, negative, or neutral from keywords and context included in the input.

[0302] Step 4:

[0303] The generated output is sent to an evaluation device. The evaluation device compares this output against pre-defined criteria and a reliable database to verify the accuracy and overall reliability of the content.

[0304] Step 5:

[0305] The server receives the evaluation results obtained from the evaluation device and further combines them with the user's sentiment analysis results. Based on the evaluation results and sentiment analysis, the output results are adjusted, and improvement points for optimizing the user experience are considered.

[0306] Step 6:

[0307] The terminal finally receives the adjusted output results and presents the information in a user-friendly format. At this time, special emphasis points or cautions may be added according to the user's sentiment. For example, when detecting a negative sentiment, the output results include positive information or suggestions.

[0308] Step 7:

[0309] The server stores the evaluation results and sentiment analysis data in the system and utilizes them as a feedback loop for improving future response accuracy and output adjustment functions. As a result, the performance of the entire system continues to improve.

[0310] (Example 2)

[0311] Next, Example 2 will be described. In the following description, the data processing device 12 is referred to as the "server", and the smart glasses 214 are referred to as the "terminal".

[0312] In an information system, there is a problem that it is difficult to improve the user experience because the information received by the user is not individualized and the user's sentiment is not taken into account. Also, it is necessary to improve the response generation and reaction accuracy of the entire system while ensuring the reliability of the generated data.

[0313] The specific processing by the specific processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0314] In this invention, the server includes means for an information processing device to acquire information requests from a user terminal, means for the information processing device to generate appropriate data using a generated AI model, and means for the information processing device to identify the user's emotions using an emotion analysis engine. This makes it possible to provide personalized information that takes into account the user's emotions and generate reliable data, thereby improving the user experience.

[0315] An "information processing device" is a device that acquires information input from a user terminal and generates and evaluates data.

[0316] A "generative AI model" is an artificial intelligence algorithm that analyzes user prompts and generates appropriate data.

[0317] An "emotion analysis engine" is software or hardware that analyzes user input data and identifies the user's emotional state from that data.

[0318] An "evaluation device" is a device used to compare generated data with existing data and determine its accuracy and reliability.

[0319] A "feedback loop" is a cyclical process that incorporates evaluation results and sentiment analysis data into the system to continuously improve performance and enhance overall quality.

[0320] This invention is a system for providing personalized, highly reliable information in response to user information requests.

[0321] The process begins with the user requesting specific information through their device. This request is received by the server, which then uses a generative AI model via an information processing device to generate data that meets the user's requirements. For example, a generative AI model employing natural language processing technology might be used in this process.

[0322] Simultaneously, the server uses an emotion analysis engine to analyze the user's input text and identify its emotional state. This is done to understand what emotions the user is feeling when seeking information, determining emotions such as "dissatisfaction" or "expectation." The emotion analysis engine can calculate an emotion score from specific keywords and context.

[0323] The generated data is sent to an evaluation device and compared with existing data. This evaluation determines the accuracy and reliability of the information generation. If improvements are found based on the evaluation, the data is adjusted to take user emotions into account, based on emotional information. For example, if negative emotions are detected, positive elements are emphasized.

[0324] Through this process, the server returns the finalized information to the user's terminal. This allows the user to receive appropriate information tailored to their individual needs, resulting in increased satisfaction.

[0325] For example, if a user enters "Please give us your feedback on the new product" into their device, the server generates data using a generative AI model. If the sentiment analysis engine determines the user's emotion to be "dissatisfied," the server provides information focusing on improvement measures and positive aspects based on the evaluation results.

[0326] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0327] Step 1:

[0328] The user sends an information request from their device. For example, the user might enter a prompt message such as, "Please provide feedback on the new product." The device receives this input and sends a request to the server using a secure communication method.

[0329] Step 2:

[0330] The server receives a request from the terminal and forwards it to the information processing unit. The information processing unit analyzes the input prompt text and generates data using a generative AI model. The generative AI model utilizes natural language processing to generate appropriate feedback information based on the user's request. The output of this model is obtained as feedback information.

[0331] Step 3:

[0332] Simultaneously, the server starts up the sentiment analysis engine and analyzes the user's input text. In this process, the sentiment analysis engine analyzes the input prompt text and determines the user's emotional state (e.g., dissatisfaction, interest). This is done by calculating an emotion score using keywords and context within the text. The output provides the type of emotion and its score.

[0333] Step 4:

[0334] The generated data is sent to an evaluation device. The evaluation device assesses the accuracy and reliability of this feedback data by comparing it to an existing database. This process includes data integrity checks and error analysis. The output is a report of the evaluated data and evaluation results.

[0335] Step 5:

[0336] The evaluation device adjusts the generated data based on the obtained emotional information and evaluation results. Specifically, if negative emotions are detected, the data is optimized to emphasize positive elements and improvement measures. This adjusted data is used as the final output.

[0337] Step 6:

[0338] The server returns the adjusted data to the user's device. The device displays the received information to the user. The user can review the personalized feedback, which takes emotions into account, and decide on their next action based on this information.

[0339] (Application Example 2)

[0340] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the smart glasses 214 will be referred to as the "terminal."

[0341] In the digital market, recognizing the products and services users desire and providing relevant information is crucial for customer satisfaction and sales promotion. However, traditional systems have struggled to accurately grasp users' emotions and needs and provide information based on them, thus failing to fully meet customer expectations.

[0342] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0343] In this invention, the server includes means for acquiring output generated by a data generation device, means for transmitting the acquired output to an evaluation device, and means for performing emotion recognition processing and adjusting the generated output based on the user's emotions. This makes it possible to provide personalized information that takes the user's emotions into consideration.

[0344] A "data generation device" is a device that generates a specific output based on the input information.

[0345] An "evaluation device" is a device that compares the generated output with existing data to determine its accuracy and reliability.

[0346] "Emotion recognition processing" is the process of analyzing input information from the user to identify and understand the emotions the user is experiencing.

[0347] A "user terminal" refers to a device that a user directly operates to input or retrieve information.

[0348] "Output adjustment" refers to the process of optimizing the content of the generated output to match the user's emotions and needs.

[0349] "Product information" refers to all information related to a specific product and is used when making recommendations.

[0350] "Benefit information" refers to information that provides additional value to users and is intended to promote the sale of products and services.

[0351] The system for realizing this invention is configured to provide information based on the user's emotions and needs, with the aim of improving the customer experience in the digital market.

[0352] The server uses a data generation device to generate output based on requests received from user terminals. The generated output is sent to an evaluation device, where its accuracy and reliability are evaluated by comparing it with existing data. The evaluation results are used to consider the user's emotions through sentiment recognition processing and to personalize and optimize the output.

[0353] This emotion recognition process utilizes APIs commonly used in natural language processing. Specifically, services such as the Google Cloud Natural Language API are used to analyze emotions from user input. The analyzed emotion information is then processed by a machine learning model using TensorFlow to generate the optimal combination of product and reward information based on data from other users with similar emotions.

[0354] This system activates when a user submits a product review using a smartphone application in response to a prompt such as, "Please tell us your opinion about this product." For example, if a review such as, "This T-shirt is lighter in color than I expected," is submitted, the emotion engine detects the dissatisfied emotion and, based on similar feedback, makes recommendations such as, "How about other T-shirts from this brand?"

[0355] Through this series of processes, the user experience is improved, and more personalized information is delivered.

[0356] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0357] Step 1:

[0358] The terminal receives a request from the user. The user enters feedback and opinions about the product through the terminal. This input data is sent to the server as text information.

[0359] Step 2:

[0360] The server sends the received text information to the Google Cloud Natural Language API for sentiment analysis. The input is text posted by the user, and the output is analyzed sentiment information (e.g., positive, negative, neutral). Through this analysis, the server gains a quantitative understanding of the user's emotions.

[0361] Step 3:

[0362] The server uses a data generation device to generate user-specific information based on the results of sentiment analysis. This device runs a machine learning model using TensorFlow and references past data of similar emotions. The input is sentiment information and existing data, and the output is emotion-based, adjusted information. At this stage, it becomes possible to provide specific information.

[0363] Step 4:

[0364] The server sends the generated output to the evaluation device. The evaluation device compares this output with an existing database and evaluates its accuracy. The input is the generated information, and the output is the result of the reliability evaluation of that information. During the evaluation process, reliability checks and corrections are performed.

[0365] Step 5:

[0366] The server adjusts the generated output based on evaluation results and sentiment information, and provides it to the user's terminal. The terminal then presents this to the user, displaying the most appropriate product and benefit information. The input consists of evaluation results and adjusted information, while the output is the final information presentation. This process allows the user to obtain a personalized service experience.

[0367] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0368] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0369] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and the specific processing may also be performed by the smart glasses 214.

[0370] [Third Embodiment]

[0371] Figure 5 shows an example of the configuration of the data processing system 310 according to the third embodiment.

[0372] As shown in Figure 5, the data processing system 310 includes a data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0373] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0374] The headset terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a display 343. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and display 343 are also connected to the bus 52.

[0375] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0376] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0377] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0378] Figure 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Figure 6, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0379] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0380] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0381] In the headset terminal 314, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0382] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the headset terminal 314 will be referred to as the "terminal".

[0383] One embodiment of the present invention is a system that improves the reliability of generated data by evaluating the output generated by a data generation device using an evaluation device and providing the evaluation results to the user. A specific embodiment thereof is described below.

[0384] In this system, the user first inputs specific information or questions through a terminal. The input data is sent by the server to a data generation device, which uses an appropriate algorithm to generate output in response to the user's request. The generated output is monitored by the server and then sent to an evaluation device.

[0385] The evaluation device assesses the accuracy of the output data by comparing it with pre-stored accurate information and existing data sources. This evaluation process allows for the identification of any problems in the generated output, such as errors or hallucinations.

[0386] The evaluation results are analyzed by the server, and feedback is generated, including corrections and points to note as needed. This feedback is provided to the user via the terminal. Based on this feedback, the user can verify the reliability of the provided information and take necessary actions.

[0387] As another concrete example, consider a scenario where a user requests a report on the latest environmental regulations via their device. The server receives this request and generates the report content via a data generation device. The generated report is then validated for reliability by an evaluation device. The evaluation device compares the information with legal databases and government regulatory repositories to verify that the output conforms to current laws and regulations. As a result, the user receives a reliable report that indicates areas that need correction.

[0388] This system provides users with the reassurance that they can always obtain accurate information, and can be used as a foundation for streamlining operations and making accurate decisions. Furthermore, feedback will be used to improve the system in the future.

[0389] The following describes the processing flow.

[0390] Step 1:

[0391] The user uses a terminal to input the information or questions they want as text. This input is sent as a request to the server.

[0392] Step 2:

[0393] The server parses the request received from the user and forwards it to the data generation device. The data generation device uses a specified algorithm to generate information based on the request.

[0394] Step 3:

[0395] The server monitors the output received from the data generation device and transfers the output data to the evaluation device. The evaluation device compares the generated output with an internal database and reliable external sources to verify its accuracy.

[0396] Step 4:

[0397] The evaluation device assesses the accuracy and reliability of each data point in the output and returns the results to the server. The server records and analyzes these evaluation results.

[0398] Step 5:

[0399] The server organizes necessary corrections and warnings based on the evaluation results and generates a feedback message for the user. This feedback includes details about areas with reliability issues and inaccuracies.

[0400] Step 6:

[0401] The terminal receives feedback messages from the server and displays them to the user. This allows the user to verify the reliability of the output and make appropriate decisions or take further actions.

[0402] Step 7:

[0403] The server continuously executes a feedback loop to improve future data generation and evaluation processes based on evaluation results and user feedback. This feedback improves the system's performance and the accuracy of its output.

[0404] (Example 1)

[0405] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0406] Existing information generation systems have faced challenges in quickly evaluating the accuracy and reliability of the generated data. In particular, there was concern that the information output by the generation model might contain errors or hallucinations, potentially negatively impacting user decision-making. Solving this problem necessitates providing a system that allows users to confidently utilize accurate and reliable information.

[0407] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0408] In this invention, the server includes means for receiving information input from a user terminal, generating and transferring prompt messages to a data generation device, means for monitoring the output generated by the data generation device and transmitting it to an evaluation device, and means for generating feedback based on the evaluation results from the evaluation device and providing it to the user terminal. This makes it possible to quickly evaluate the accuracy of the generated data and provide the user with reliable information.

[0409] A "user terminal" is a device used by users to input information or questions and receive feedback.

[0410] A "server" is a device that receives requests from user terminals and acts as an intermediary for information between data generation devices and evaluation devices.

[0411] A "data generation device" is a device that generates output based on prompt sentences using a generation AI model.

[0412] A "generative AI model" is a model equipped with algorithms for generating natural language, and it generates information according to the user's requests.

[0413] A "prompt statement" is an instruction statement that a server uses to instruct a data generation device to generate output.

[0414] An "evaluation device" is a device that has the function of comparing the generated output with existing data and evaluating its accuracy.

[0415] "Feedback" refers to information provided to the user, including points for output correction and precautions, based on the evaluation results obtained from the evaluation device.

[0416] The embodiment of the present invention begins with a user inputting specific information or a question using a terminal. This terminal is a device that the user uses as an interface to the system, and specifically includes personal computers and smartphones. For example, suppose the user inputs, "Please provide me with a report on the latest environmental regulations."

[0417] The server is responsible for receiving this request. The server converts the requested information into the appropriate format and generates a prompt. Based on the generated prompt, the server sends its contents to the data generation device. A generative AI model such as GPT-4 could be used at this time. The generative AI model generates an appropriate response based on the prompt.

[0418] Data generation devices equipped with generative AI models generate information in response to user requests. Because the generated information utilizes natural language processing technology, it provides detailed output tailored to the user's needs.

[0419] The generated output is monitored by a server and then sent to an evaluation device. The evaluation device is designed to assess the accuracy of the generated data. Here, the evaluation device verifies the accuracy by comparing the generated data against pre-stored databases and other reliable sources. For example, it might compare the data with legal databases or government regulatory repositories.

[0420] Finally, based on the evaluation results, the server generates feedback and provides it to the user via the terminal. This feedback may include areas that need correction or important notes. Based on this feedback, the user can verify the reliability of the information and take necessary actions. This allows the user to make decisions based on accurate information with confidence.

[0421] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0422] Step 1:

[0423] The user enters specific information or questions using a terminal. For example, they might enter a request such as, "Please provide a report on the latest environmental regulations." This input is sent to the server via the terminal. At this stage, the user's request is passed to the server as specific text data as output.

[0424] Step 2:

[0425] The server receives the user's request and generates an appropriate prompt. This prompt is then converted into a format that the data generator can easily understand. Specifically, it constructs the necessary syntax and conditions in the generating AI model according to the user's request. This prompt becomes the input from the server to the data generator. As output, a formalized prompt is generated.

[0426] Step 3:

[0427] The data generation device generates information based on prompt messages received from the server. Within this device, a generation AI model operates, analyzing the prompt messages and generating appropriate information. For example, it can generate reports based on user requests. During this process, the model performs natural language processing to generate detailed responses. The output is the generated text data.

[0428] Step 4:

[0429] The server monitors the output from the data generator and prepares it for transmission to the evaluation device. The input here is the output data from the generator. The server structures this data and transmits it to the evaluation device in a format suitable for evaluation. The output in this step is the data used for analysis and evaluation.

[0430] Step 5:

[0431] The evaluation device compares the received output data with pre-stored information to assess its accuracy. The input is generated data transmitted from the server. Here, the evaluation device verifies accuracy based on legal databases and regulatory repositories. This evaluation identifies inconsistencies and errors. The evaluation results are generated as output.

[0432] Step 6:

[0433] The server receives evaluation results returned from the evaluation device and generates feedback as needed. The input is the evaluation results from the evaluation device. Based on this information, the server creates feedback including corrections and precautions that should be provided to the user. This process allows the user to verify the reliability of the information. The output is detailed feedback sent to the user's terminal.

[0434] Step 7:

[0435] Users receive feedback on their devices and evaluate the reliability of the information based on that feedback. The information provided in the feedback is reviewed, and necessary actions are taken. This process allows users to trust the accuracy of the information. The final output is reliable information for the user, along with specific actionable guidelines based on that information.

[0436] (Application Example 1)

[0437] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0438] In today's consumer environment, the reliability of product and pricing information is crucial. However, inaccurate information can hinder purchasing decisions. There is a need to solve this problem and enable consumers to make quick and accurate product choices based on reliable information.

[0439] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0440] In this invention, the server includes means for acquiring output generated by a data generation device, means for transmitting the acquired output to an evaluation device for evaluation, and means for evaluating the generated product information and outputting it as appropriate purchasing information. This enables consumers to select products based on reliable information and make decisions quickly and efficiently.

[0441] A "data generation device" is a system that generates and provides specific information or data based on user requests.

[0442] An "evaluation device" is a device used to compare the generated output with existing data and evaluate its accuracy and reliability.

[0443] "Evaluation results" refer to information obtained after the reliability of the output has been analyzed by the evaluation device.

[0444] A "user terminal" is a device equipped with an interface for providing evaluation results to the user.

[0445] "Product information" refers to detailed information about prices and promotions that consumers need to make purchasing decisions.

[0446] "Purchase information" refers to reliable data generated based on evaluated product information, which serves as a reference for consumers when making their final purchase decisions.

[0447] A "feedback loop" is a process for improving the functions of data generation and evaluation devices based on evaluation results.

[0448] This invention is implemented as a smartphone application equipped with a system for providing consumers with reliable product information. The server generates relevant product data using a data generation device based on product information received from the user's terminal. This data generation device is equipped with a generation AI model and generates information according to the user's requests.

[0449] The generated data is sent to an evaluation device, where it is compared with existing databases and its accuracy is assessed. The evaluation device uses AI-powered analysis to compare the generated data with current pricing and promotional data to measure reliability. Through this process, the server analyzes the evaluation results and generates feedback, including any necessary corrections or points to note.

[0450] The device provides product information through this feedback. This information is presented in a format that users can receive as prompts, helping consumers make purchasing decisions based on accurate and reliable information. Specifically, if a user is looking to buy organic milk at a supermarket, the app allows them to find real-time milk prices, applicable promotions, and the best discounts.

[0451] As an example of a prompt using a generative AI model, "Please tell me the latest price and promotional information for the organic milk I plan to buy." This allows users to experience greater satisfaction in their purchasing activities and reduces misunderstandings and discrepancies in perception.

[0452] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0453] Step 1:

[0454] The user enters information about the product they wish to purchase through their terminal. For example, they can scan the product's barcode or directly enter the product name. The entered product data is then sent to the server.

[0455] Step 2:

[0456] The server sends the received product data to a data generation device, from which detailed product information is generated. At this stage, a generation AI model is used to generate product data, including price and promotions, based on the latest information. The generated data undergoes sophisticated data processing and calculations before being output and sent to an evaluation device.

[0457] Step 3:

[0458] The evaluation system compares the generated product data with existing databases. Here, it performs comparative analysis of the data to assess the accuracy and reliability of the products. This process verifies that the generated data matches current pricing and promotional information. The evaluation results are returned to the server.

[0459] Step 4:

[0460] The server analyzes the evaluation results and generates feedback with necessary corrections and notes added. This feedback includes the reliability of the evaluated product and any special notes to be provided to the user. The generated feedback is sent to the user's terminal.

[0461] Step 5:

[0462] The device displays the received feedback to the user. This feedback includes reliable product information based on the prompt "Please tell me the latest price and promotional information for the organic milk I plan to buy." The user can then use this information to make a purchase decision.

[0463] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0464] One embodiment of the present invention is a system that combines an evaluation device that evaluates the output generated by a data generation device with an emotion engine that recognizes the user's emotions. This improves the accuracy of the generated data and enhances the user experience.

[0465] First, the user requests specific information through the terminal. This request is received by the server and processed by a data generator. The generator proceeds to produce appropriate output that matches the user's request. Simultaneously, the server uses an emotion engine to analyze and recognize the emotions from the user's input text.

[0466] The generated output is sent as input to the evaluation device and compared with existing data to verify its accuracy and reliability. The evaluation device adjusts the output to optimize the user experience based on the emotional information provided by the emotion engine.

[0467] For example, if a user enters "Please give us your feedback on the new product" on their device, the sentiment engine recognizes, based on the input and past interactions, that the user may be expressing decreased customer satisfaction. The server then uses this sentiment information to customize the generator's output, adjusting the evaluation results to highlight specific areas for improvement and positive aspects. This information is ultimately provided to the user to help increase their satisfaction.

[0468] The information provided will be used not only for user feedback but also in a feedback loop to improve the overall system, thereby enhancing the accuracy of future response generation and emotion recognition.

[0469] This system allows users to receive more personalized and reliable information. Companies can improve the quality of their customer service while simultaneously increasing the efficiency of their overall processes.

[0470] The following describes the processing flow.

[0471] Step 1:

[0472] The user enters specific questions or requests as text through their terminal. This input is sent to the server and triggers the start of processing.

[0473] Step 2:

[0474] The server sends the input received from the user to a data generation device and executes a process to generate output data corresponding to the request. The output generated here directly answers the user's question.

[0475] Step 3:

[0476] Simultaneously, the server uses an emotion engine to analyze the user's emotional state from the user's input data. For example, it extracts emotions such as positive, negative, or neutral from keywords and context included in the input.

[0477] Step 4:

[0478] The generated output is sent to an evaluation device. The evaluation device compares this output against pre-defined criteria and a reliable database to verify the accuracy and overall reliability of the content.

[0479] Step 5:

[0480] The server receives evaluation results from the evaluation device and combines them with the user's sentiment analysis results. Based on the evaluation results and sentiment analysis, the server adjusts the output results and considers areas for improvement to optimize the user experience.

[0481] Step 6:

[0482] The terminal receives the final adjusted output and presents the information to the user in an easy-to-understand format. This may include special emphasis or attention tailored to the user's emotions. For example, if negative emotions are detected, the output may include positive information or suggestions.

[0483] Step 7:

[0484] The server stores evaluation results and sentiment analysis data within the system, utilizing it as a feedback loop to improve future response accuracy and output adjustment capabilities. This allows for continuous improvement of the overall system performance.

[0485] (Example 2)

[0486] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0487] In information systems, a challenge exists in that the information users receive is not personalized, and user emotions are not taken into consideration, making it difficult to improve the user experience. Furthermore, it is necessary to improve the overall response generation and responsiveness of the system while ensuring the reliability of the generated data.

[0488] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0489] In this invention, the server includes means for an information processing device to acquire information requests from a user terminal, means for the information processing device to generate appropriate data using a generated AI model, and means for the information processing device to identify the user's emotions using an emotion analysis engine. This makes it possible to provide personalized information that takes into account the user's emotions and generate reliable data, thereby improving the user experience.

[0490] An "information processing device" is a device that acquires information input from a user terminal and generates and evaluates data.

[0491] A "generative AI model" is an artificial intelligence algorithm that analyzes user prompts and generates appropriate data.

[0492] An "emotion analysis engine" is software or hardware that analyzes user input data and identifies the user's emotional state from that data.

[0493] An "evaluation device" is a device used to compare generated data with existing data and determine its accuracy and reliability.

[0494] A "feedback loop" is a cyclical process that incorporates evaluation results and sentiment analysis data into the system to continuously improve performance and enhance overall quality.

[0495] This invention is a system for providing personalized, highly reliable information in response to user information requests.

[0496] The process begins with the user requesting specific information through their device. This request is received by the server, which then uses a generative AI model via an information processing device to generate data that meets the user's requirements. For example, a generative AI model employing natural language processing technology might be used in this process.

[0497] Simultaneously, the server uses an emotion analysis engine to analyze the user's input text and identify its emotional state. This is done to understand what emotions the user is feeling when seeking information, determining emotions such as "dissatisfaction" or "expectation." The emotion analysis engine can calculate an emotion score from specific keywords and context.

[0498] The generated data is sent to an evaluation device and compared with existing data. This evaluation determines the accuracy and reliability of the information generation. If improvements are found based on the evaluation, the data is adjusted to take user emotions into account, based on emotional information. For example, if negative emotions are detected, positive elements are emphasized.

[0499] Through this process, the server returns the finalized information to the user's terminal. This allows the user to receive appropriate information tailored to their individual needs, resulting in increased satisfaction.

[0500] For example, if a user enters "Please give us your feedback on the new product" into their device, the server generates data using a generative AI model. If the sentiment analysis engine determines the user's emotion to be "dissatisfied," the server provides information focusing on improvement measures and positive aspects based on the evaluation results.

[0501] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0502] Step 1:

[0503] The user sends an information request from their device. For example, the user might enter a prompt message such as, "Please provide feedback on the new product." The device receives this input and sends a request to the server using a secure communication method.

[0504] Step 2:

[0505] The server receives a request from the terminal and forwards it to the information processing unit. The information processing unit analyzes the input prompt text and generates data using a generative AI model. The generative AI model utilizes natural language processing to generate appropriate feedback information based on the user's request. The output of this model is obtained as feedback information.

[0506] Step 3:

[0507] Simultaneously, the server starts up the sentiment analysis engine and analyzes the user's input text. In this process, the sentiment analysis engine analyzes the input prompt text and determines the user's emotional state (e.g., dissatisfaction, interest). This is done by calculating an emotion score using keywords and context within the text. The output provides the type of emotion and its score.

[0508] Step 4:

[0509] The generated data is sent to an evaluation device. The evaluation device assesses the accuracy and reliability of this feedback data by comparing it to an existing database. This process includes data integrity checks and error analysis. The output is a report of the evaluated data and evaluation results.

[0510] Step 5:

[0511] The evaluation device adjusts the generated data based on the obtained emotional information and evaluation results. Specifically, if negative emotions are detected, the data is optimized to emphasize positive elements and improvement measures. This adjusted data is used as the final output.

[0512] Step 6:

[0513] The server returns the adjusted data to the user's device. The device displays the received information to the user. The user can review the personalized feedback, which takes emotions into account, and decide on their next action based on this information.

[0514] (Application Example 2)

[0515] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server," and the headset-type terminal 314 will be referred to as the "terminal."

[0516] In the digital market, recognizing the products and services users desire and providing relevant information is crucial for customer satisfaction and sales promotion. However, traditional systems have struggled to accurately grasp users' emotions and needs and provide information based on them, thus failing to fully meet customer expectations.

[0517] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0518] In this invention, the server includes means for acquiring output generated by a data generation device, means for transmitting the acquired output to an evaluation device, and means for performing emotion recognition processing and adjusting the generated output based on the user's emotions. This makes it possible to provide personalized information that takes the user's emotions into consideration.

[0519] A "data generation device" is a device that generates a specific output based on the input information.

[0520] An "evaluation device" is a device that compares the generated output with existing data to determine its accuracy and reliability.

[0521] "Emotion recognition processing" is the process of analyzing input information from the user to identify and understand the emotions the user is experiencing.

[0522] A "user terminal" refers to a device that a user directly operates to input or retrieve information.

[0523] "Output adjustment" refers to the process of optimizing the content of the generated output to match the user's emotions and needs.

[0524] "Product information" refers to all information related to a specific product and is used when making recommendations.

[0525] "Benefit information" refers to information that provides additional value to users and is intended to promote the sale of products and services.

[0526] The system for realizing this invention is configured to provide information based on the user's emotions and needs, with the aim of improving the customer experience in the digital market.

[0527] The server uses a data generation device to generate output based on requests received from user terminals. The generated output is sent to an evaluation device, where its accuracy and reliability are evaluated by comparing it with existing data. The evaluation results are used to consider the user's emotions through sentiment recognition processing and to personalize and optimize the output.

[0528] This emotion recognition process utilizes APIs commonly used in natural language processing. Specifically, services such as the Google Cloud Natural Language API are used to analyze emotions from user input. The analyzed emotion information is then processed by a machine learning model using TensorFlow to generate the optimal combination of product and reward information based on data from other users with similar emotions.

[0529] This system activates when a user submits a product review using a smartphone application in response to a prompt such as, "Please tell us your opinion about this product." For example, if a review such as, "This T-shirt is lighter in color than I expected," is submitted, the emotion engine detects the dissatisfied emotion and, based on similar feedback, makes recommendations such as, "How about other T-shirts from this brand?"

[0530] Through this series of processes, the user experience is improved, and more personalized information is delivered.

[0531] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0532] Step 1:

[0533] The terminal receives a request from the user. The user enters feedback and opinions about the product through the terminal. This input data is sent to the server as text information.

[0534] Step 2:

[0535] The server sends the received text information to the Google Cloud Natural Language API for sentiment analysis. The input is text posted by the user, and the output is analyzed sentiment information (e.g., positive, negative, neutral). Through this analysis, the server gains a quantitative understanding of the user's emotions.

[0536] Step 3:

[0537] The server uses a data generation device to generate user-specific information based on the results of sentiment analysis. This device runs a machine learning model using TensorFlow and references past data of similar emotions. The input is sentiment information and existing data, and the output is emotion-based, adjusted information. At this stage, it becomes possible to provide specific information.

[0538] Step 4:

[0539] The server sends the generated output to the evaluation device. The evaluation device compares this output with an existing database and evaluates its accuracy. The input is the generated information, and the output is the result of the reliability evaluation of that information. During the evaluation process, reliability checks and corrections are performed.

[0540] Step 5:

[0541] The server adjusts the generated output based on evaluation results and sentiment information, and provides it to the user's terminal. The terminal then presents this to the user, displaying the most appropriate product and benefit information. The input consists of evaluation results and adjusted information, while the output is the final information presentation. This process allows the user to obtain a personalized service experience.

[0542] The specific processing unit 290 transmits the result of the specific processing to the headset terminal 314. In the headset terminal 314, the control unit 46A causes the speaker 240 and display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0543] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0544] In the above embodiment, an example was given in which specific processing is performed by the data processing device 12, but the technology of this disclosure is not limited thereto, and specific processing may also be performed by the headset terminal 314.

[0545] [Fourth Embodiment]

[0546] Figure 7 shows an example of the configuration of the data processing system 410 according to the fourth embodiment.

[0547] As shown in Figure 7, the data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[0548] The data processing device 12 comprises a computer 22, a database 24, and a communication interface 26. The computer 22 is an example of a "computer" related to the technology of this disclosure. The computer 22 comprises a processor 28, RAM 30, and storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication interface 26 are also connected to the bus 34. The communication interface 26 is connected to a network 54. An example of the network 54 is a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0549] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication interface 44, and a controlled object 443. The computer 36 includes a processor 46, RAM 48, and storage 50. The processor 46, RAM 48, and storage 50 are connected to a bus 52. The microphone 238, speaker 240, camera 42, and controlled object 443 are also connected to the bus 52.

[0550] The microphone 238 receives voice signals from the user 20 and receives instructions from the user 20. The microphone 238 captures the voice signals from the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to the instructions from the processor 46.

[0551] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an image sensor such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the area around the user 20 (for example, an imaging range defined by a field of view equivalent to the width of a typical healthy person's field of vision).

[0552] Communication interface 44 is connected to network 54. Communication interfaces 44 and 26 are responsible for the exchange of various information between processor 46 and processor 28 via network 54. The exchange of various information between processor 46 and processor 28 using communication interfaces 44 and 26 is performed in a secure manner.

[0553] The controlled object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors in the arms, hands, and feet. Some of the robot 414's emotions can be expressed by controlling these motors. Furthermore, the robot 414's facial expressions can also be expressed by controlling the illumination state of the LEDs in its eyes.

[0554] Figure 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Figure 8, the data processing device 12 performs specific processing using the processor 28. The storage 32 stores the specific processing program 56.

[0555] The specific processing program 56 is an example of a "program" relating to the technology of this disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0556] The storage 32 stores the data generation model 58 and the emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290.

[0557] In robot 414, the processor 46 performs the reception output processing. The storage 50 stores the reception output program 60. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output processing is realized by the processor 46 operating as a control unit 46A according to the reception output program 60 executed on the RAM 48.

[0558] Next, the specific processing performed by the specific processing unit 290 of the data processing device 12 will be described. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0559] One embodiment of the present invention is a system that improves the reliability of generated data by evaluating the output generated by a data generation device using an evaluation device and providing the evaluation results to the user. A specific embodiment thereof is described below.

[0560] In this system, the user first inputs specific information or questions through a terminal. The input data is sent by the server to a data generation device, which uses an appropriate algorithm to generate output in response to the user's request. The generated output is monitored by the server and then sent to an evaluation device.

[0561] The evaluation device assesses the accuracy of the output data by comparing it with pre-stored accurate information and existing data sources. This evaluation process allows for the identification of any problems in the generated output, such as errors or hallucinations.

[0562] The evaluation results are analyzed by the server, and feedback is generated, including corrections and points to note as needed. This feedback is provided to the user via the terminal. Based on this feedback, the user can verify the reliability of the provided information and take necessary actions.

[0563] As another concrete example, consider a scenario where a user requests a report on the latest environmental regulations via their device. The server receives this request and generates the report content via a data generation device. The generated report is then validated for reliability by an evaluation device. The evaluation device compares the information with legal databases and government regulatory repositories to verify that the output conforms to current laws and regulations. As a result, the user receives a reliable report that indicates areas that need correction.

[0564] This system provides users with the reassurance that they can always obtain accurate information, and can be used as a foundation for streamlining operations and making accurate decisions. Furthermore, feedback will be used to improve the system in the future.

[0565] The following describes the processing flow.

[0566] Step 1:

[0567] The user uses a terminal to input the information or questions they want as text. This input is sent as a request to the server.

[0568] Step 2:

[0569] The server parses the request received from the user and forwards it to the data generation device. The data generation device uses a specified algorithm to generate information based on the request.

[0570] Step 3:

[0571] The server monitors the output received from the data generation device and transfers the output data to the evaluation device. The evaluation device compares the generated output with an internal database and reliable external sources to verify its accuracy.

[0572] Step 4:

[0573] The evaluation device assesses the accuracy and reliability of each data point in the output and returns the results to the server. The server records and analyzes these evaluation results.

[0574] Step 5:

[0575] The server organizes necessary corrections and warnings based on the evaluation results and generates a feedback message for the user. This feedback includes details about areas with reliability issues and inaccuracies.

[0576] Step 6:

[0577] The terminal receives feedback messages from the server and displays them to the user. This allows the user to verify the reliability of the output and make appropriate decisions or take further actions.

[0578] Step 7:

[0579] The server continuously executes a feedback loop to improve future data generation and evaluation processes based on evaluation results and user feedback. This feedback improves the system's performance and the accuracy of its output.

[0580] (Example 1)

[0581] Next, we will describe Example 1. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0582] Existing information generation systems have faced challenges in quickly evaluating the accuracy and reliability of the generated data. In particular, there was concern that the information output by the generation model might contain errors or hallucinations, potentially negatively impacting user decision-making. Solving this problem necessitates providing a system that allows users to confidently utilize accurate and reliable information.

[0583] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 1 is realized by the following means.

[0584] In this invention, the server includes means for receiving information input from a user terminal, generating and transferring prompt messages to a data generation device, means for monitoring the output generated by the data generation device and transmitting it to an evaluation device, and means for generating feedback based on the evaluation results from the evaluation device and providing it to the user terminal. This makes it possible to quickly evaluate the accuracy of the generated data and provide the user with reliable information.

[0585] A "user terminal" is a device used by users to input information or questions and receive feedback.

[0586] A "server" is a device that receives requests from user terminals and acts as an intermediary for information between data generation devices and evaluation devices.

[0587] A "data generation device" is a device that generates output based on prompt sentences using a generation AI model.

[0588] A "generative AI model" is a model equipped with algorithms for generating natural language, and it generates information according to the user's requests.

[0589] A "prompt statement" is an instruction statement that a server uses to instruct a data generation device to generate output.

[0590] An "evaluation device" is a device that has the function of comparing the generated output with existing data and evaluating its accuracy.

[0591] "Feedback" refers to information provided to the user, including points for output correction and precautions, based on the evaluation results obtained from the evaluation device.

[0592] The embodiment of the present invention begins with a user inputting specific information or a question using a terminal. This terminal is a device that the user uses as an interface to the system, and specifically includes personal computers and smartphones. For example, suppose the user inputs, "Please provide me with a report on the latest environmental regulations."

[0593] The server is responsible for receiving this request. The server converts the requested information into the appropriate format and generates a prompt. Based on the generated prompt, the server sends its contents to the data generation device. A generative AI model such as GPT-4 could be used at this time. The generative AI model generates an appropriate response based on the prompt.

[0594] Data generation devices equipped with generative AI models generate information in response to user requests. Because the generated information utilizes natural language processing technology, it provides detailed output tailored to the user's needs.

[0595] The generated output is monitored by a server and then sent to an evaluation device. The evaluation device is designed to assess the accuracy of the generated data. Here, the evaluation device verifies the accuracy by comparing the generated data against pre-stored databases and other reliable sources. For example, it might compare the data with legal databases or government regulatory repositories.

[0596] Finally, based on the evaluation results, the server generates feedback and provides it to the user via the terminal. This feedback may include areas that need correction or important notes. Based on this feedback, the user can verify the reliability of the information and take necessary actions. This allows the user to make decisions based on accurate information with confidence.

[0597] The flow of the specific processing in Example 1 will be explained using Figure 11.

[0598] Step 1:

[0599] The user enters specific information or questions using a terminal. For example, they might enter a request such as, "Please provide a report on the latest environmental regulations." This input is sent to the server via the terminal. At this stage, the user's request is passed to the server as specific text data as output.

[0600] Step 2:

[0601] The server receives the user's request and generates an appropriate prompt. This prompt is then converted into a format that the data generator can easily understand. Specifically, it constructs the necessary syntax and conditions in the generating AI model according to the user's request. This prompt becomes the input from the server to the data generator. As output, a formalized prompt is generated.

[0602] Step 3:

[0603] The data generation device generates information based on prompt messages received from the server. Within this device, a generation AI model operates, analyzing the prompt messages and generating appropriate information. For example, it can generate reports based on user requests. During this process, the model performs natural language processing to generate detailed responses. The output is the generated text data.

[0604] Step 4:

[0605] The server monitors the output from the data generator and prepares it for transmission to the evaluation device. The input here is the output data from the generator. The server structures this data and transmits it to the evaluation device in a format suitable for evaluation. The output in this step is the data used for analysis and evaluation.

[0606] Step 5:

[0607] The evaluation device compares the received output data with pre-stored information to assess its accuracy. The input is generated data transmitted from the server. Here, the evaluation device verifies accuracy based on legal databases and regulatory repositories. This evaluation identifies inconsistencies and errors. The evaluation results are generated as output.

[0608] Step 6:

[0609] The server receives evaluation results returned from the evaluation device and generates feedback as needed. The input is the evaluation results from the evaluation device. Based on this information, the server creates feedback including corrections and precautions that should be provided to the user. This process allows the user to verify the reliability of the information. The output is detailed feedback sent to the user's terminal.

[0610] Step 7:

[0611] Users receive feedback on their devices and evaluate the reliability of the information based on that feedback. The information provided in the feedback is reviewed, and necessary actions are taken. This process allows users to trust the accuracy of the information. The final output is reliable information for the user, along with specific actionable guidelines based on that information.

[0612] (Application Example 1)

[0613] Next, we will explain Application Example 1. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0614] In today's consumer environment, the reliability of product and pricing information is crucial. However, inaccurate information can hinder purchasing decisions. There is a need to solve this problem and enable consumers to make quick and accurate product choices based on reliable information.

[0615] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 1 is realized by the following means.

[0616] In this invention, the server includes means for acquiring output generated by a data generation device, means for transmitting the acquired output to an evaluation device for evaluation, and means for evaluating the generated product information and outputting it as appropriate purchasing information. This enables consumers to select products based on reliable information and make decisions quickly and efficiently.

[0617] A "data generation device" is a system that generates and provides specific information or data based on user requests.

[0618] An "evaluation device" is a device used to compare the generated output with existing data and evaluate its accuracy and reliability.

[0619] "Evaluation results" refer to information obtained after the reliability of the output has been analyzed by the evaluation device.

[0620] A "user terminal" is a device equipped with an interface for providing evaluation results to the user.

[0621] "Product information" refers to detailed information about prices and promotions that consumers need to make purchasing decisions.

[0622] "Purchase information" refers to reliable data generated based on evaluated product information, which serves as a reference for consumers when making their final purchase decisions.

[0623] A "feedback loop" is a process for improving the functions of data generation and evaluation devices based on evaluation results.

[0624] This invention is implemented as a smartphone application equipped with a system for providing consumers with reliable product information. The server generates relevant product data using a data generation device based on product information received from the user's terminal. This data generation device is equipped with a generation AI model and generates information according to the user's requests.

[0625] The generated data is sent to an evaluation device, where it is compared with existing databases and its accuracy is assessed. The evaluation device uses AI-powered analysis to compare the generated data with current pricing and promotional data to measure reliability. Through this process, the server analyzes the evaluation results and generates feedback, including any necessary corrections or points to note.

[0626] The device provides product information through this feedback. This information is presented in a format that users can receive as prompts, helping consumers make purchasing decisions based on accurate and reliable information. Specifically, if a user is looking to buy organic milk at a supermarket, the app allows them to find real-time milk prices, applicable promotions, and the best discounts.

[0627] As an example of a prompt using a generative AI model, "Please tell me the latest price and promotional information for the organic milk I plan to buy." This allows users to experience greater satisfaction in their purchasing activities and reduces misunderstandings and discrepancies in perception.

[0628] The flow of a specific process in Application Example 1 will be explained using Figure 12.

[0629] Step 1:

[0630] The user enters information about the product they wish to purchase through their terminal. For example, they can scan the product's barcode or directly enter the product name. The entered product data is then sent to the server.

[0631] Step 2:

[0632] The server sends the received product data to a data generation device, from which detailed product information is generated. At this stage, a generation AI model is used to generate product data, including price and promotions, based on the latest information. The generated data undergoes sophisticated data processing and calculations before being output and sent to an evaluation device.

[0633] Step 3:

[0634] The evaluation system compares the generated product data with existing databases. Here, it performs comparative analysis of the data to assess the accuracy and reliability of the products. This process verifies that the generated data matches current pricing and promotional information. The evaluation results are returned to the server.

[0635] Step 4:

[0636] The server analyzes the evaluation results and generates feedback with necessary corrections and notes added. This feedback includes the reliability of the evaluated product and any special notes to be provided to the user. The generated feedback is sent to the user's terminal.

[0637] Step 5:

[0638] The device displays the received feedback to the user. This feedback includes reliable product information based on the prompt "Please tell me the latest price and promotional information for the organic milk I plan to buy." The user can then use this information to make a purchase decision.

[0639] Furthermore, an emotion engine that estimates the user's emotions may be incorporated. That is, the identification processing unit 290 may use the emotion identification model 59 to estimate the user's emotions and perform identification processing using the user's emotions.

[0640] One embodiment of the present invention is a system that combines an evaluation device that evaluates the output generated by a data generation device with an emotion engine that recognizes the user's emotions. This improves the accuracy of the generated data and enhances the user experience.

[0641] First, the user requests specific information through the terminal. This request is received by the server and processed by a data generator. The generator proceeds to produce appropriate output that matches the user's request. Simultaneously, the server uses an emotion engine to analyze and recognize the emotions from the user's input text.

[0642] The generated output is sent as input to the evaluation device and compared with existing data to verify its accuracy and reliability. The evaluation device adjusts the output to optimize the user experience based on the emotional information provided by the emotion engine.

[0643] For example, if a user enters "Please give us your feedback on the new product" on their device, the sentiment engine recognizes, based on the input and past interactions, that the user may be expressing decreased customer satisfaction. The server then uses this sentiment information to customize the generator's output, adjusting the evaluation results to highlight specific areas for improvement and positive aspects. This information is ultimately provided to the user to help increase their satisfaction.

[0644] The information provided will be used not only for user feedback but also in a feedback loop to improve the overall system, thereby enhancing the accuracy of future response generation and emotion recognition.

[0645] This system allows users to receive more personalized and reliable information. Companies can improve the quality of their customer service while simultaneously increasing the efficiency of their overall processes.

[0646] The following describes the processing flow.

[0647] Step 1:

[0648] The user enters specific questions or requests as text through their terminal. This input is sent to the server and triggers the start of processing.

[0649] Step 2:

[0650] The server sends the input received from the user to a data generation device and executes a process to generate output data corresponding to the request. The output generated here directly answers the user's question.

[0651] Step 3:

[0652] Simultaneously, the server uses an emotion engine to analyze the user's emotional state from the user's input data. For example, it extracts emotions such as positive, negative, or neutral from keywords and context included in the input.

[0653] Step 4:

[0654] The generated output is sent to an evaluation device. The evaluation device compares this output against pre-defined criteria and a reliable database to verify the accuracy and overall reliability of the content.

[0655] Step 5:

[0656] The server receives evaluation results from the evaluation device and combines them with the user's sentiment analysis results. Based on the evaluation results and sentiment analysis, the server adjusts the output results and considers areas for improvement to optimize the user experience.

[0657] Step 6:

[0658] The terminal receives the final adjusted output and presents the information to the user in an easy-to-understand format. This may include special emphasis or attention tailored to the user's emotions. For example, if negative emotions are detected, the output may include positive information or suggestions.

[0659] Step 7:

[0660] The server stores evaluation results and sentiment analysis data within the system, utilizing it as a feedback loop to improve future response accuracy and output adjustment capabilities. This allows for continuous improvement of the overall system performance.

[0661] (Example 2)

[0662] Next, we will describe Example 2. In the following description, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0663] In information systems, a challenge exists in that the information users receive is not personalized, and user emotions are not taken into consideration, making it difficult to improve the user experience. Furthermore, it is necessary to improve the overall response generation and responsiveness of the system while ensuring the reliability of the generated data.

[0664] The identification process performed by the identification processing unit 290 of the data processing device 12 in Example 2 is realized by the following means.

[0665] In this invention, the server includes means for an information processing device to acquire information requests from a user terminal, means for the information processing device to generate appropriate data using a generated AI model, and means for the information processing device to identify the user's emotions using an emotion analysis engine. This makes it possible to provide personalized information that takes into account the user's emotions and generate reliable data, thereby improving the user experience.

[0666] An "information processing device" is a device that acquires information input from a user terminal and generates and evaluates data.

[0667] A "generative AI model" is an artificial intelligence algorithm that analyzes user prompts and generates appropriate data.

[0668] An "emotion analysis engine" is software or hardware that analyzes user input data and identifies the user's emotional state from that data.

[0669] An "evaluation device" is a device used to compare generated data with existing data and determine its accuracy and reliability.

[0670] A "feedback loop" is a cyclical process that incorporates evaluation results and sentiment analysis data into the system to continuously improve performance and enhance overall quality.

[0671] This invention is a system for providing personalized, highly reliable information in response to user information requests.

[0672] The process begins with the user requesting specific information through their device. This request is received by the server, which then uses a generative AI model via an information processing device to generate data that meets the user's requirements. For example, a generative AI model employing natural language processing technology might be used in this process.

[0673] Simultaneously, the server uses an emotion analysis engine to analyze the user's input text and identify its emotional state. This is done to understand what emotions the user is feeling when seeking information, determining emotions such as "dissatisfaction" or "expectation." The emotion analysis engine can calculate an emotion score from specific keywords and context.

[0674] The generated data is sent to an evaluation device and compared with existing data. This evaluation determines the accuracy and reliability of the information generation. If improvements are found based on the evaluation, the data is adjusted to take user emotions into account, based on emotional information. For example, if negative emotions are detected, positive elements are emphasized.

[0675] Through this process, the server returns the finalized information to the user's terminal. This allows the user to receive appropriate information tailored to their individual needs, resulting in increased satisfaction.

[0676] For example, if a user enters "Please give us your feedback on the new product" into their device, the server generates data using a generative AI model. If the sentiment analysis engine determines the user's emotion to be "dissatisfied," the server provides information focusing on improvement measures and positive aspects based on the evaluation results.

[0677] The flow of the specific processing in Example 2 will be explained using Figure 13.

[0678] Step 1:

[0679] The user sends an information request from their device. For example, the user might enter a prompt message such as, "Please provide feedback on the new product." The device receives this input and sends a request to the server using a secure communication method.

[0680] Step 2:

[0681] The server receives a request from the terminal and forwards it to the information processing unit. The information processing unit analyzes the input prompt text and generates data using a generative AI model. The generative AI model utilizes natural language processing to generate appropriate feedback information based on the user's request. The output of this model is obtained as feedback information.

[0682] Step 3:

[0683] Simultaneously, the server starts up the sentiment analysis engine and analyzes the user's input text. In this process, the sentiment analysis engine analyzes the input prompt text and determines the user's emotional state (e.g., dissatisfaction, interest). This is done by calculating an emotion score using keywords and context within the text. The output provides the type of emotion and its score.

[0684] Step 4:

[0685] The generated data is sent to an evaluation device. The evaluation device assesses the accuracy and reliability of this feedback data by comparing it to an existing database. This process includes data integrity checks and error analysis. The output is a report of the evaluated data and evaluation results.

[0686] Step 5:

[0687] The evaluation device adjusts the generated data based on the obtained emotional information and evaluation results. Specifically, if negative emotions are detected, the data is optimized to emphasize positive elements and improvement measures. This adjusted data is used as the final output.

[0688] Step 6:

[0689] The server returns the adjusted data to the user's device. The device displays the received information to the user. The user can review the personalized feedback, which takes emotions into account, and decide on their next action based on this information.

[0690] (Application Example 2)

[0691] Next, we will explain application example 2. In the following explanation, the data processing device 12 will be referred to as the "server" and the robot 414 as the "terminal".

[0692] In the digital market, recognizing the products and services users desire and providing relevant information is crucial for customer satisfaction and sales promotion. However, traditional systems have struggled to accurately grasp users' emotions and needs and provide information based on them, thus failing to fully meet customer expectations.

[0693] The specific processing performed by the specific processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means.

[0694] In this invention, the server includes means for acquiring output generated by a data generation device, means for transmitting the acquired output to an evaluation device, and means for performing emotion recognition processing and adjusting the generated output based on the user's emotions. This makes it possible to provide personalized information that takes the user's emotions into consideration.

[0695] A "data generation device" is a device that generates a specific output based on the input information.

[0696] An "evaluation device" is a device that compares the generated output with existing data to determine its accuracy and reliability.

[0697] "Emotion recognition processing" is the process of analyzing input information from the user to identify and understand the emotions the user is experiencing.

[0698] A "user terminal" refers to a device that a user directly operates to input or retrieve information.

[0699] "Output adjustment" refers to the process of optimizing the content of the generated output to match the user's emotions and needs.

[0700] "Product information" refers to all information related to a specific product and is used when making recommendations.

[0701] "Benefit information" refers to information that provides additional value to users and is intended to promote the sale of products and services.

[0702] The system for realizing this invention is configured to provide information based on the user's emotions and needs, with the aim of improving the customer experience in the digital market.

[0703] The server uses a data generation device to generate output based on requests received from user terminals. The generated output is sent to an evaluation device, where its accuracy and reliability are evaluated by comparing it with existing data. The evaluation results are used to consider the user's emotions through sentiment recognition processing and to personalize and optimize the output.

[0704] This emotion recognition process utilizes APIs commonly used in natural language processing. Specifically, services such as the Google Cloud Natural Language API are used to analyze emotions from user input. The analyzed emotion information is then processed by a machine learning model using TensorFlow to generate the optimal combination of product and reward information based on data from other users with similar emotions.

[0705] This system activates when a user submits a product review using a smartphone application in response to a prompt such as, "Please tell us your opinion about this product." For example, if a review such as, "This T-shirt is lighter in color than I expected," is submitted, the emotion engine detects the dissatisfied emotion and, based on similar feedback, makes recommendations such as, "How about other T-shirts from this brand?"

[0706] Through this series of processes, the user experience is improved, and more personalized information is delivered.

[0707] The flow of a specific process in Application Example 2 will be explained using Figure 14.

[0708] Step 1:

[0709] The terminal receives a request from the user. The user enters feedback and opinions about the product through the terminal. This input data is sent to the server as text information.

[0710] Step 2:

[0711] The server sends the received text information to the Google Cloud Natural Language API for sentiment analysis. The input is text posted by the user, and the output is analyzed sentiment information (e.g., positive, negative, neutral). Through this analysis, the server gains a quantitative understanding of the user's emotions.

[0712] Step 3:

[0713] The server uses a data generation device to generate user-specific information based on the results of sentiment analysis. This device runs a machine learning model using TensorFlow and references past data of similar emotions. The input is sentiment information and existing data, and the output is emotion-based, adjusted information. At this stage, it becomes possible to provide specific information.

[0714] Step 4:

[0715] The server sends the generated output to the evaluation device. The evaluation device compares this output with an existing database and evaluates its accuracy. The input is the generated information, and the output is the result of the reliability evaluation of that information. During the evaluation process, reliability checks and corrections are performed.

[0716] Step 5:

[0717] The server adjusts the generated output based on evaluation results and sentiment information, and provides it to the user's terminal. The terminal then presents this to the user, displaying the most appropriate product and benefit information. The input consists of evaluation results and adjusted information, while the output is the final information presentation. This process allows the user to obtain a personalized service experience.

[0718] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the controlled object 443 to output the result of the specific processing. The microphone 238 acquires audio indicating user input for the result of the specific processing. The control unit 46A transmits the audio data indicating user input acquired by the microphone 238 to the data processing unit 12. In the data processing unit 12, the specific processing unit 290 acquires the audio data.

[0719] Data generation model 58 is a type of so-called generative AI (Artificial Intelligence). One example of data generation model 58 is ChatGPT (Internet Search).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search) <url: https: gemini.google.com ?hl="ja">Examples of generative AI include the following. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 is input with prompts containing instructions, and with inference data such as audio data representing speech, text data representing text, and image data representing images. The data generation model 58 infers from the input inference data according to the instructions indicated by the prompts, and outputs the inference results in data formats such as audio data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0720] 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 this disclosure is not limited thereto, and the specific processing may also be performed by the robot 414.

[0721] Furthermore, the emotion identification model 59, acting as an emotion engine, may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to a specific mapping, which is an emotion map (see Figure 9). Similarly, the emotion identification model 59 may also determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0722] Figure 9 shows an emotion map 400 in which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. The closer to the center of the concentric circles, the more primitive the emotions are located. Further out of the concentric circles, emotions representing states and actions arising from mental states are located. Emotion is a concept that includes feelings and mental states. On the left side of the concentric circles, emotions that are generally generated from reactions occurring in the brain are located. On the right side of the concentric circles, emotions that are generally induced by situational judgment are located. Above and below the concentric circles, emotions that are generally generated from reactions occurring in the brain and induced by situational judgment are located. In addition, the emotion of "pleasure" is located on the upper side of the concentric circles, and the emotion of "displeasure" is located on the lower side. Thus, in the emotion map 400, multiple emotions are mapped based on the structure in which emotions arise, and emotions that are likely to occur simultaneously are mapped close together.

[0723] These emotions are distributed at the 3 o'clock position on the Emotion Map 400, and usually fluctuate between feelings of security and anxiety. In the right half of the Emotion Map 400, situational awareness takes precedence over internal feelings, resulting in a calm impression.

[0724] The inside of the Emotion Map 400 represents inner thoughts, while the outside represents actions. Therefore, the further you go from the outside of the Emotion Map 400, the more visible (expressed in actions) your emotions become.

[0725] Here, human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. Similarly, in robots, cars, motorcycles, etc., emotions can be created based on various balances, such as posture and battery level. When these balances deviate from the ideal, it results in discomfort, and when they approach the ideal, it results in pleasure. The emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on a system for analyzing brain physiological signals of speech emotion recognition and emotion, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map contains emotions belonging to a region called "response," where sensation is dominant. The right half of the emotion map contains emotions belonging to a region called "situation," where situational awareness is dominant.

[0726] The emotion map defines two emotions that promote learning. One is the emotion around the middle of the negative "repentance" and "reflection" on the situation side. In other words, it is when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is the emotion around the positive "desire" on the reaction side. In other words, it is when the robot has positive feelings such as "I want more" or "I want to know more."

[0727] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​representing each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple training data sets, which are combinations of user input and emotion values ​​representing each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions located close together have similar values, as shown in the emotion map 900 in Figure 10. Figure 10 shows an example where multiple emotions such as "reassured," "calm," and "confident" have similar emotion values.

[0728] The above description primarily focuses on the functions of the data processing device 12 in relation to this disclosure. However, the system related to this disclosure is not necessarily implemented on a server. The system related to this disclosure may be implemented as a general information processing system. This disclosure may be implemented, for example, as a software program that runs on a personal computer or as an application that runs on a smartphone. The method related to this disclosure may be provided to users in SaaS (Software as a Service) format.

[0729] In the above embodiment, an example was given in which a specific process is performed by a single computer 22. However, the technology of this disclosure is not limited thereto, and a distributed processing of the specific process may be performed by multiple computers, including computer 22. For example, a data generation model 58 may be provided in an external device of the data processing device 12, and the external device may generate data according to the input data.

[0730] In the above embodiment, an example was given in which the specific processing program 56 is stored in the storage 32, but the technology of this disclosure is not limited thereto. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-temporary storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-temporary storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes specific processing according to the specific processing program 56.

[0731] 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.

[0732] Furthermore, it is not necessary to store the entirety of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store the entirety of the specific processing program 56 in the storage 32; it is acceptable to store only a portion of the specific processing program 56.

[0733] The following types of processors can be used as hardware resources to perform specific processing. Examples of processors include a CPU, a general-purpose processor that functions as a hardware resource to perform specific processing by executing software, i.e., a program. Other examples of processors include dedicated electrical circuits, such as FPGAs (Field-Programmable Gate Arrays), PLDs (Programmable Logic Devices), or ASICs (Application Specific Integrated Circuits), which have circuit configurations specifically designed to perform specific processing. All of these processors have built-in or connected memory, and all of them perform specific processing by using memory.

[0734] The hardware resource that performs a specific process may consist of one of these various processors, or it may consist of a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Alternatively, the hardware resource that performs a specific process may consist of a single processor.

[0735] Examples of configurations using a single processor include, firstly, a configuration in which one or more CPUs and software are combined to form a single processor, and this processor functions as a hardware resource that performs a specific process. Secondly, there is a configuration using a processor that realizes the functions of the entire system, including multiple hardware resources that perform a specific process, on a single IC chip, as exemplified by SoCs (System-on-a-chip). In this way, a specific process is realized using one or more of the above types of processors as hardware resources.

[0736] Furthermore, the hardware structure of these various processors can more specifically utilize electrical circuits that combine circuit elements such as semiconductor devices. Also, the specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps can be deleted, new steps added, or the processing order rearranged, as long as it does not deviate from the main purpose.

[0737] The descriptions and illustrations presented above are detailed explanations of the technical aspects of this disclosure and are merely examples of the technical aspects. For example, the above descriptions of the structure, function, operation, and effect are examples of the structure, function, operation, and effect of the technical aspects of this disclosure. Therefore, it goes without saying that you may delete unnecessary parts, add new elements, or replace elements in the descriptions and illustrations presented above, as long as you do not deviate from the essence of the technical aspects of this disclosure. Furthermore, in order to avoid confusion and facilitate understanding of the technical aspects of this disclosure, explanations of common technical knowledge and the like that do not require special explanation to enable the implementation of the technical aspects of this disclosure have been omitted from the descriptions and illustrations presented above.

[0738] All documents, patent applications, and technical standards described herein are incorporated by reference to the same extent as if each individual document, patent application, and technical standard were specifically and individually noted to be incorporated by reference.

[0739] The following is further disclosed regarding the embodiments described above.

[0740] (Claim 1)

[0741] A means for acquiring the output generated by the data generation device,

[0742] In order to evaluate the acquired output, means for transmitting it to an evaluation device,

[0743] The evaluation device includes means for comparing the output with existing data and evaluating its accuracy,

[0744] A means for analyzing the evaluation results and providing them to the user terminal,

[0745] A system that includes this.

[0746] (Claim 2)

[0747] The system according to claim 1, wherein the evaluation device analyzes the reliability of each part of the output and generates information to highlight.

[0748] (Claim 3)

[0749] The system according to claim 1, which provides a feedback loop to improve the performance of the data generation device and the evaluation device using the evaluation results.

[0750] "Example 1"

[0751] (Claim 1)

[0752] A means of inputting specific information or questions from the user terminal,

[0753] A means by which a server receives a user request, generates an appropriate prompt message for a data generation device, and transfers it,

[0754] A means by which a data generation device generates output using a generation AI model,

[0755] A means for monitoring the output generated by the server and transmitting it to the evaluation device,

[0756] The evaluation device compares the output with pre-stored data and provides means for evaluating its accuracy.

[0757] A means by which the server generates feedback based on the evaluation results and provides it to the user terminal,

[0758] A system that includes this.

[0759] (Claim 2)

[0760] The system according to claim 1, wherein the evaluation device analyzes the reliability of each part of the output and generates feedback including corrections and points to note.

[0761] (Claim 3)

[0762] The system according to claim 1, which provides a feedback loop that uses feedback to improve the accuracy of a data generation device and an evaluation device.

[0763] "Application Example 1"

[0764] (Claim 1)

[0765] A means for acquiring the output generated by the data generation device,

[0766] In order to evaluate the acquired output, means for transmitting it to an evaluation device,

[0767] The evaluation device includes means for comparing the output with existing data and evaluating its accuracy,

[0768] A means for analyzing the aforementioned evaluation results, providing them to a data processing terminal, and generating product information,

[0769] A means for evaluating the generated product information and outputting it as appropriate purchasing information,

[0770] A system that includes this.

[0771] (Claim 2)

[0772] The system according to claim 1, wherein the evaluation device analyzes the reliability of each part of the output and generates data that highlights specific information.

[0773] (Claim 3)

[0774] The system according to claim 1, which uses the evaluation results to provide a feedback loop for improving the performance of the data generation device and the evaluation device, and to support the user's purchase decision.

[0775] "Example 2 of combining an emotion engine"

[0776] (Claim 1)

[0777] A means by which an information processing device obtains an information request from a user terminal,

[0778] The aforementioned information processing device includes means for generating appropriate data using a generated AI model,

[0779] The aforementioned information processing device uses an emotion analysis engine to identify the user's emotions,

[0780] The generated data is transmitted to an evaluation device and compared with existing data to evaluate its accuracy and reliability,

[0781] A means for adjusting the generated data based on the emotional information using the evaluation results and providing it to the user terminal as the final output,

[0782] A system that includes this.

[0783] (Claim 2)

[0784] The system according to claim 1, wherein the evaluation device analyzes the reliability of the generated data and generates information that emphasizes the adjustment content based on emotional information.

[0785] (Claim 3)

[0786] The system according to claim 1, which provides a feedback loop to improve the performance of the information processing device and the evaluation device using the evaluation results and sentiment analysis data.

[0787] "Application example 2 when combining with an emotional engine"

[0788] (Claim 1)

[0789] A means for acquiring the output generated by the data generation device,

[0790] In order to evaluate the acquired output, means for transmitting it to an evaluation device,

[0791] The evaluation device includes means for comparing the output with existing data and evaluating its accuracy,

[0792] A means for analyzing the evaluation results and providing them to the user terminal,

[0793] A means for performing emotion recognition processing and adjusting the generated output based on the user's emotions,

[0794] A means of providing product information recommendations or special offer information using newly generated information,

[0795] A system that includes this.

[0796] (Claim 2)

[0797] The system according to claim 1, wherein the evaluation device analyzes the reliability of each part of the output and generates information to highlight.

[0798] (Claim 3)

[0799] The system according to claim 1, which provides a feedback loop to improve the performance of the data generation device and the evaluation device using the evaluation results and emotion recognition results. [Explanation of Symbols]

[0800] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Devices 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robots< / url:> < / url:> < / url:> < / url:>

Claims

1. A means for acquiring the output generated by the data generation device, In order to evaluate the acquired output, means for transmitting it to an evaluation device, The evaluation device includes means for comparing the output with existing data and evaluating its accuracy, A means for analyzing the evaluation results and providing them to the user terminal, A system that includes this.

2. The system according to claim 1, wherein the evaluation device analyzes the reliability of each part of the output and generates information to highlight.

3. The system according to claim 1, which provides a feedback loop to improve the performance of the data generation device and the evaluation device using the evaluation results.

Images