System

Abstract

An object of a system according to an embodiment is to evaluate a fire risk before a service is released and propose an appropriate countermeasure.SOLUTION: A system according to an embodiment includes an information collection unit, an analysis unit, a risk evaluation unit, a result presentation unit, and a countermeasure proposal unit. The information collection unit collects information on a service scheduled to be released. The analysis unit analyzes the information collected by the information collection unit. The risk evaluation unit evaluates a fire risk based on the information analyzed by the analysis unit. The result presentation unit presents a risk evaluation result evaluated by the risk evaluation unit to the planner. The countermeasure proposal unit proposes a countermeasure based on a risk evaluation result evaluated by the risk evaluation unit.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

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

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

[0004] With conventional technology, it was difficult to properly assess the risk of online outrage and take measures before releasing a service.

[0005] The system according to the embodiment aims to evaluate the risk of a social media outrage before a service is released and to propose appropriate countermeasures. [Means for solving the problem]

[0006] The system according to the embodiment includes an information collection unit, an analysis unit, a risk assessment unit, a result presentation unit, and a countermeasure proposal unit. The information collection unit collects information related to a service to be released. The analysis unit analyzes the information collected by the information collection unit. The risk assessment unit evaluates the risk of a flame war based on the information analyzed by the analysis unit. The result presentation unit presents the risk assessment results evaluated by the risk assessment unit to the planner. The countermeasure proposal unit proposes countermeasures based on the risk assessment results evaluated by the risk assessment unit. [Effects of the Invention]

[0007] The system according to the embodiment can evaluate the risk of a social media outrage before a service is released and propose appropriate countermeasures. [Brief explanation of the drawings]

[0008] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. DETAILED DESCRIPTION OF THE INVENTION

[0009] An example of an embodiment of a system according to the technology of the present disclosure will be described below with reference to the accompanying drawings.

[0010] First, the terms used in the following description will be explained.

[0011] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, the processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), an APU (Accelerated Processing Unit), or a TPU (Tensor Processing Unit).

[0012] In the following embodiments, a coded RAM (Random Access Memory) is a memory in which information is temporarily stored and is used as a working memory by a processor.

[0013] In the following embodiments, the coded storage is one or more nonvolatile storage devices that store various programs, various parameters, etc. Examples of nonvolatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[0014] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), and Bluetooth (registered trademark).

[0015] In the following embodiments, "A and / or B" is synonymous with "at least one of A and B." In other words, "A and / or B" means that it may be only A, only B, or a combination of A and B. Furthermore, in this specification, the same concept as "A and / or B" is also applied when three or more things are expressed connected by "and / or."

[0016] [First embodiment] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0017] 1, a data processing system 10 includes a data processing device 12 and a smart device 14. An example of the data processing device 12 is a server.

[0018] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0019] The smart device 14 includes a computer 36, a reception device 38, an output device 40, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The reception device 38, the output device 40, and the camera 42 are also connected to the bus 52.

[0020] The reception device 38 includes a touch panel 38A and a microphone 38B, and receives user input. The touch panel 38A detects contact with a pointer (for example, a pen or a finger) to receive user input by the touch of the pointer. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 (see FIG. 2) acquires the data indicating the user input.

[0021] Output device 40 includes a display 40A and a speaker 40B, and presents data to a user by outputting the data in a form of expression that the user can perceive (e.g., audio and / or text). Display 40A displays visible information such as text and images in accordance with instructions from processor 46. Speaker 40B outputs audio in accordance with instructions from processor 46. Camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0022] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 control the exchange of various information between the processor 46 and the processor 28 via the network 54.

[0023] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0024] 2, in the data processing device 12, a specific process is performed by the processor 28. A specific processing program 56 is stored in the storage 32. The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific process is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0025] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0026] In the smart device 14, the specific processing is performed by the processor 46. The storage 50 stores a specific processing program 60. The specific processing program 60 is used together with the specific processing program 56 by the data processing system 10. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart device 14 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0027] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device (e.g., a generation server) may have the data generation model 58. In this case, the data processing device 12 obtains a processing result (prediction result, etc.) using the data generation model 58 by communicating with the server device having the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device owned by a user (e.g., a mobile phone, a robot, a home appliance, etc.). Next, an example of processing by the data processing system 10 according to the first embodiment will be described.

[0028] (Example 1) The flame diagnosis system according to an embodiment of the present invention is a system that uses AI to diagnose flames before a service is released and supports planners. This system analyzes information about a service to be released and evaluates the risk of a flame. This allows planners to identify potential problems before release and take appropriate measures.

[0029] A flame war diagnosis system according to an embodiment includes an information collection unit, an analysis unit, a risk assessment unit, a result presentation unit, and a countermeasure proposal unit. The information collection unit collects information about a service to be released. For example, the information collection unit collects service descriptions, promotional videos, and screenshots of user interfaces. The information collection unit also collects past reviews of similar services and social media reaction data. The analysis unit analyzes the information collected by the information collection unit. For example, the analysis unit uses text mining technology to analyze the service descriptions and extract potential problems. The analysis unit can also analyze the content of promotional videos using image analysis technology. The analysis unit can also analyze social media reaction data and evaluate users' emotional reactions. The risk assessment unit assesses the risk of a flame war based on the information analyzed by the analysis unit. For example, the analysis unit identifies the potential for a flame war in a service to be released based on past flame war cases. The risk assessment unit can also calculate a risk score based on the social media reaction data. The result presentation unit presents the risk assessment results evaluated by the risk assessment unit to a planner. For example, a report is generated that includes high-risk points, the reasons for them, past similar cases, etc. The result presentation unit can also present the risk assessment results in a visually easy-to-understand format. The countermeasure proposal unit proposes countermeasures based on the risk assessment results. For example, it can propose a review of the privacy policy, improvements to the user interface, or changes to promotion methods. The countermeasure proposal unit can also present specific improvement measures based on past success cases. This allows the flame war diagnosis system according to the embodiment to enable planners to identify potential problems before release and take appropriate measures. For example, by predicting user backlash before release and taking countermeasures in advance, the success rate of a service can be increased. Furthermore, reducing the risk of flame wars can improve brand image and ensure user trust.

[0030] The information gathering unit can analyze more detailed background information, including internal documents and developer comments from the service development process. The information gathering unit, for example, collects and analyzes internal documents from the service development process. For example, it targets developer design documents, specifications, development logs, etc. to understand the design intent of the service and the background to its development. The information gathering unit can also collect and analyze developer comments. For example, it analyzes comments made by developers about specific features of the service to understand their intent and background. This allows for a detailed analysis of the development background of the service, enabling more accurate risk assessment.

[0031] The information gathering unit can add information from the user's perspective, including pre-surveys and focus group feedback from users. For example, the information gathering unit conducts a pre-survey of users and analyzes the results. For example, it collects expectations and concerns about the service and identifies areas for improvement before release. The information gathering unit can also collect and analyze focus group feedback. For example, it provides a prototype of the service to a specific user group and identifies areas for improvement based on that feedback. By adding information from the user's perspective, risk assessment can be performed with greater consideration for users.

[0032] The information gathering department can collect service information from different industries and refer to success stories and failure stories from other industries. For example, the information gathering department collects and analyzes success stories from different industries. For example, it refers to promotion strategies and user engagement methods from other industries. The information gathering department can also collect and analyze failure stories from different industries. For example, it can take measures based on failure stories from other industries to avoid similar failures in services that are scheduled for release. In this way, by referring to success stories and failure stories from other industries, it becomes possible to assess risks from a broader perspective.

[0033] When analyzing past cases of flaming, the risk assessment unit can analyze the timing of the flaming incidents and the effectiveness of subsequent countermeasures in chronological order, and reflect this in the risk assessment. The risk assessment unit, for example, analyzes the timing of the occurrence of past flaming incidents and reflects this in the risk assessment. For example, it evaluates whether flaming incidents are more likely to occur during specific seasons or events. The risk assessment unit can also analyze the effectiveness of countermeasures against past flaming incidents in chronological order, and reflect this in the risk assessment. For example, it evaluates the extent to which specific countermeasures were effective in bringing the flaming to a halt. In this way, by analyzing the timing of the occurrence of past flaming incidents and the effectiveness of countermeasures in chronological order, more accurate risk assessment is possible.

[0034] When analyzing social media reaction data, the risk assessment unit can assess risk based on the frequency of appearance of specific keywords or hashtags. The risk assessment unit, for example, analyzes social media reaction data and assesses risk based on the frequency of appearance of specific keywords. For example, if negative keywords appear frequently, it determines that the risk is high. The risk assessment unit can also assess risk based on the frequency of appearance of specific hashtags. For example, if the number of specific hashtags increases sharply, it determines that the risk is high. In this way, by assessing risk based on social media reaction data, it is possible to more accurately grasp the risk of a flame war.

[0035] The risk assessment unit can evaluate the risk of a flame war from a global perspective by taking into account the reactions of users from different cultural spheres and regions. The risk assessment unit, for example, analyzes the reactions of users from different cultural spheres and reflects them in the risk assessment. For example, it evaluates negative reactions in a specific cultural sphere and considers them as risk factors. The risk assessment unit can also analyze the reactions of users from different regions and reflect them in the risk assessment. For example, it analyzes social media data by region and identifies risk factors. This allows the risk to be evaluated from a global perspective by taking into account the reactions of users from different cultural spheres and regions.

[0036] The risk assessment unit can monitor social media trends in real time and reflect the latest user interests when assessing risks. The risk assessment unit, for example, monitors social media trends in real time and reflects the trends in the risk assessment. For example, risk is assessed based on rapidly increasing topics and hashtags. The risk assessment unit can also use real-time data streaming technology to reflect the latest user interests. For example, real-time social media data is collected and trend analysis is performed. In this way, by monitoring social media trends in real time, the latest user interests can be reflected in the risk assessment.

[0037] The result presentation unit can include specific numerical data and graphs in the generated risk assessment report and present it in a visually easy-to-understand format. The result presentation unit, for example, includes specific numerical data in the generated risk assessment report. For example, the score of the risk of a firestorm or the frequency of past firestorm incidents is displayed numerically. The result presentation unit can also include graphs in the risk assessment report. For example, the progress of the risk score or the distribution of risk factors is displayed in a graph. In this way, by including specific numerical data and graphs, the risk assessment report can be presented in a visually easy-to-understand format.

[0038] The result presentation unit presents the risk assessment results in detail for each element of the service, making it possible to clarify which parts are particularly high risk. The result presentation unit, for example, presents the risk assessment results for each element of the service. For example, it evaluates risk for each element such as the user interface, privacy policy, and promotional video. The result presentation unit can also create a detailed report to clarify parts with particularly high risk. For example, it performs risk scoring and displays the risk level of each element numerically. In this way, by presenting the risk assessment results for each element of the service, it is possible to clarify parts with particularly high risk.

[0039] The result presentation unit can present the risk assessment results to different departments or teams in a customized format, making it easier for each department to take specific measures. The result presentation unit, for example, presents the risk assessment results to different departments or teams in a customized format. For example, it can focus on presenting promotion-related risks to the marketing department and technical risks to the development department. The result presentation unit can also provide a customizable dashboard to make it easier for each department to take specific measures. For example, it can provide a report format tailored to the needs of each department. In this way, presenting the risk assessment results in a customized format makes it easier for each department to take specific measures.

[0040] The result presentation unit can compare the risk assessment results with other projects or services and clearly indicate the relative risk level. The result presentation unit, for example, compares the risk assessment results with other projects or services and clearly indicates the relative risk level. For example, it compares the risk scores of past projects with those of the current project. The result presentation unit can also compare the risk assessment results using benchmark data. For example, it compares them with industry standard risk scores and evaluates the relative risk level. In this way, by comparing the risk assessment results with other projects or services, it is possible to clearly indicate the relative risk level.

[0041] The countermeasure proposal unit can increase the feasibility of the proposed countermeasure by including specific implementation procedures and necessary resources in the proposed countermeasure. The countermeasure proposal unit, for example, includes specific implementation procedures in the proposed countermeasure. For example, it may specify in detail the procedures for reviewing a privacy policy or the procedures for improving a user interface. The countermeasure proposal unit can also include the resources necessary for the proposed countermeasure. For example, it may specify the personnel, budget, and technical resources necessary for implementation. In this way, by including specific implementation procedures and necessary resources, the feasibility of the countermeasure can be increased.

[0042] The countermeasure proposal unit can make the proposed countermeasures more persuasive by including specific examples based on past successes and failures. The countermeasure proposal unit, for example, includes past successes in the proposed countermeasures. For example, it can specifically show successful cases for similar problems to prove the effectiveness of the countermeasures. The countermeasure proposal unit can also include past failures in the proposed countermeasures. For example, it can show failed cases for similar problems to emphasize the need for the countermeasures. In this way, by including specific examples based on past successes and failures, the proposed countermeasures can be made more persuasive.

[0043] The Countermeasure Proposal Department incorporates best practices from different industries and fields when proposing countermeasures, allowing it to present improvement measures from a wide range of perspectives. For example, the Countermeasure Proposal Department may collect best practices from different industries and incorporate them into its countermeasure proposals. For example, it may refer to promotion strategies and user engagement methods that have been successful in other industries. The Countermeasure Proposal Department may also collect best practices from different fields and incorporate them into its countermeasure proposals. For example, it may refer to successful cases in the technical or marketing fields. In this way, by incorporating best practices from different industries and fields, it is possible to present improvement measures from a wide range of perspectives.

[0044] The countermeasure proposal unit can introduce an agile methodology in which proposed countermeasures are implemented as prototypes and improved based on user feedback. The countermeasure proposal unit, for example, introduces an agile methodology in which proposed countermeasures are implemented as prototypes and improved based on user feedback. For example, a prototype is developed in a short period of time and user opinions are reflected. The countermeasure proposal unit can also use an agile methodology to continuously improve countermeasures. For example, a sprint plan is made, feedback is collected periodically, and the countermeasures are improved. In this way, the quality of the countermeasures can be improved by introducing an agile methodology in which proposed countermeasures are implemented as prototypes and improved based on user feedback.

[0045] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0046] The information gathering department can analyze more detailed background information, including internal documents and developer comments from the service development process. For example, it can analyze the developer's design documents, specifications, development logs, etc. to understand the service's design intent and development background. It can also analyze comments made by developers about specific service functions to understand their intent and background. This allows for a more detailed analysis of the service's development background, enabling more accurate risk assessment.

[0047] The information gathering unit can add information from the user's perspective, including pre-surveys and focus group feedback. For example, a pre-survey of users can be conducted and the results analyzed. Expectations and concerns about the service can be collected and areas for improvement identified before release. Focus group feedback can also be collected, and a prototype of the service can be provided to a specific user group, and areas for improvement identified based on that feedback. By adding information from the user's perspective, risk assessment can be conducted with greater consideration for users.

[0048] The Information Gathering Department collects information on services from different industries and can refer to success stories and failure stories from other industries. For example, they collect success stories from other industries and use them as reference for promotion strategies and user engagement methods. They also collect failure stories from other industries and take measures to prevent similar failures in services that are scheduled for release. In this way, by referring to success stories and failure stories from other industries, risk assessment can be performed from a broader perspective.

[0049] When analyzing past cases of online flaming, the risk assessment unit can analyze the timing of the onset of online flaming and the effectiveness of subsequent countermeasures in chronological order, and reflect this in risk assessment. For example, it can analyze the timing of past online flaming cases to evaluate whether online flaming is more likely to occur during certain seasons or events. It can also analyze the effectiveness of countermeasures taken in past online flaming cases in chronological order, and evaluate how effective a particular countermeasure was in bringing the onset of the flaming to a close. This allows for more accurate risk assessment by analyzing the timing of the onset of online flaming cases in past years and the effectiveness of countermeasures taken in chronological order.

[0050] When analyzing social media reaction data, the risk assessment unit can assess risk based on the frequency of appearance of specific keywords and hashtags. For example, by analyzing social media reaction data, risk is assessed based on the frequency of appearance of specific keywords. If negative keywords appear frequently, the risk is determined to be high. Risk can also be assessed based on the frequency of appearance of specific hashtags. If the number of specific hashtags increases sharply, the risk is determined to be high. In this way, assessing risk based on social media reaction data makes it possible to more accurately grasp the risk of flame wars.

[0051] The risk assessment unit can evaluate the risk of a flame war from a global perspective, taking into account the reactions of users from different cultural spheres and regions. For example, it can analyze the reactions of users from different cultural spheres, evaluate negative reactions in specific cultural spheres, and consider them as risk factors. It can also analyze the reactions of users from different regions and identify risk factors based on social media data by region. This allows risk to be evaluated from a global perspective by taking into account the reactions of users from different cultural spheres and regions.

[0052] The processing flow of the first embodiment will be briefly explained below.

[0053] Step 1: The information gathering department collects information about the service to be released, such as service descriptions, promotional videos, and screenshots of the user interface. They also collect past reviews of similar services and social media reaction data. Step 2: The analysis unit analyzes the information collected by the information collection unit. For example, it can use text mining technology to analyze the service description and extract potential problems. It can also use image analysis technology to analyze the content of promotional videos. It can also analyze social media reaction data to evaluate users' emotional reactions. Step 3: The risk assessment unit assesses the risk of a social media outrage based on the information analyzed by the analysis unit. For example, it identifies the aspects of a service to be released that could potentially cause a social media outrage based on past social media outrage cases. It can also calculate a risk score based on social media reaction data. Step 4: The results presentation unit presents the risk assessment results evaluated by the risk assessment unit to the planner. For example, it generates a report that includes high-risk points, the reasons for them, and past similar cases. It can also present the risk assessment results in a visually easy-to-understand format. Step 5: The countermeasure proposal department proposes countermeasures based on the risk assessment results. For example, they can propose a review of the privacy policy, improvements to the user interface, or changes to promotional methods. They can also present specific improvement measures based on past success stories.

[0054] (Example 2) The flame diagnosis system according to an embodiment of the present invention is a system that uses AI to diagnose flames before a service is released and supports planners. This system analyzes information about a service to be released and evaluates the risk of a flame. This allows planners to identify potential problems before release and take appropriate measures.

[0055] A flame war diagnosis system according to an embodiment includes an information collection unit, an analysis unit, a risk assessment unit, a result presentation unit, and a countermeasure proposal unit. The information collection unit collects information about a service to be released. For example, the information collection unit collects service descriptions, promotional videos, and screenshots of user interfaces. The information collection unit also collects past reviews of similar services and social media reaction data. The analysis unit analyzes the information collected by the information collection unit. For example, the analysis unit uses text mining technology to analyze the service descriptions and extract potential problems. The analysis unit can also analyze the content of promotional videos using image analysis technology. The analysis unit can also analyze social media reaction data and evaluate users' emotional reactions. The risk assessment unit assesses the risk of a flame war based on the information analyzed by the analysis unit. For example, the analysis unit identifies the potential for a flame war in a service to be released based on past flame war cases. The risk assessment unit can also calculate a risk score based on the social media reaction data. The result presentation unit presents the risk assessment results evaluated by the risk assessment unit to a planner. For example, a report is generated that includes high-risk points, the reasons for them, past similar cases, etc. The result presentation unit can also present the risk assessment results in a visually easy-to-understand format. The countermeasure proposal unit proposes countermeasures based on the risk assessment results. For example, it can propose a review of the privacy policy, improvements to the user interface, or changes to promotion methods. The countermeasure proposal unit can also present specific improvement measures based on past success cases. This allows the flame war diagnosis system according to the embodiment to enable planners to identify potential problems before release and take appropriate measures. For example, by predicting user backlash before release and taking countermeasures in advance, the success rate of a service can be increased. Furthermore, reducing the risk of flame wars can improve brand image and ensure user trust.

[0056] The information gathering unit can analyze more detailed background information, including internal documents and developer comments from the service development process. The information gathering unit, for example, collects and analyzes internal documents from the service development process. For example, it targets developer design documents, specifications, development logs, etc. to understand the design intent of the service and the background to its development. The information gathering unit can also collect and analyze developer comments. For example, it analyzes comments made by developers about specific features of the service to understand their intent and background. This allows for a detailed analysis of the development background of the service, enabling more accurate risk assessment.

[0057] When analyzing a promotional video, the information collection unit can analyze facial expressions and voice tones in the video to identify potential controversy factors. The information collection unit, for example, analyzes the facial expressions of the characters in the promotional video to detect changes in emotion. For example, it identifies smiling and angry expressions and evaluates the impression they give to viewers. The information collection unit can also analyze voice tones in the promotional video to identify potential controversy factors. For example, it detects aggressive voice tones or voice tones that cause discomfort and evaluates them as risk factors. In this way, potential controversy factors can be identified in advance by analyzing the video and voice of a promotional video.

[0058] The information collection unit can use the emotion estimation function to analyze users' emotional reactions to service descriptions and promotional videos in real time and identify elements that elicit positive reactions. The information collection unit, for example, analyzes users' emotional reactions to service descriptions in real time and identifies elements that elicit positive reactions. For example, it evaluates whether specific keywords or phrases are perceived favorably by users. The information collection unit can also analyze users' emotional reactions to promotional videos in real time and identify elements that elicit positive reactions. For example, it evaluates whether attractive visuals and positive language are perceived favorably by users. In this way, it is possible to analyze users' emotional reactions in real time and identify elements that elicit positive reactions.

[0059] The information gathering unit can add information from the user's perspective, including pre-surveys and focus group feedback from users. For example, the information gathering unit conducts a pre-survey of users and analyzes the results. For example, it collects expectations and concerns about the service and identifies areas for improvement before release. The information gathering unit can also collect and analyze focus group feedback. For example, it provides a prototype of the service to a specific user group and identifies areas for improvement based on that feedback. By adding information from the user's perspective, risk assessment can be performed with greater consideration for users.

[0060] The information gathering department can collect service information from different industries and refer to success stories and failure stories from other industries. For example, the information gathering department collects and analyzes success stories from different industries. For example, it refers to promotion strategies and user engagement methods from other industries. The information gathering department can also collect and analyze failure stories from different industries. For example, it can take measures based on failure stories from other industries to avoid similar failures in services that are scheduled for release. In this way, by referring to success stories and failure stories from other industries, it becomes possible to assess risks from a broader perspective.

[0061] The information collection unit can use the emotion estimation function to analyze users' emotional reactions to the collected information and eliminate elements that will cause negative reactions in advance. The information collection unit, for example, analyzes users' emotional reactions to the collected information in real time and identifies elements that will cause negative reactions. For example, it evaluates whether specific keywords or phrases cause discomfort to users. The information collection unit can also take measures to eliminate elements that will cause negative reactions in advance. For example, it can modify offensive expressions or visuals that cause discomfort. In this way, the risk of a social media outcry can be reduced by eliminating elements that will cause negative reactions in advance.

[0062] When analyzing past cases of flaming, the risk assessment unit can analyze the timing of the flaming incidents and the effectiveness of subsequent countermeasures in chronological order, and reflect this in the risk assessment. The risk assessment unit, for example, analyzes the timing of the occurrence of past flaming incidents and reflects this in the risk assessment. For example, it evaluates whether flaming incidents are more likely to occur during specific seasons or events. The risk assessment unit can also analyze the effectiveness of countermeasures against past flaming incidents in chronological order, and reflect this in the risk assessment. For example, it evaluates the extent to which specific countermeasures were effective in bringing the flaming to a halt. In this way, by analyzing the timing of the occurrence of past flaming incidents and the effectiveness of countermeasures in chronological order, more accurate risk assessment is possible.

[0063] When analyzing social media reaction data, the risk assessment unit can assess risk based on the frequency of appearance of specific keywords or hashtags. The risk assessment unit, for example, analyzes social media reaction data and assesses risk based on the frequency of appearance of specific keywords. For example, if negative keywords appear frequently, it determines that the risk is high. The risk assessment unit can also assess risk based on the frequency of appearance of specific hashtags. For example, if the number of specific hashtags increases sharply, it determines that the risk is high. In this way, by assessing risk based on social media reaction data, it is possible to more accurately grasp the risk of a flame war.

[0064] The risk assessment unit can use the emotion estimation function to analyze users' emotional reactions to past flaming cases and identify elements that may cause similar emotions. The risk assessment unit, for example, analyzes users' emotional reactions to past flaming cases and identifies elements that may cause similar emotions. For example, it evaluates elements that are associated with strong emotions such as anger and dissatisfaction. The risk assessment unit can also use the emotion estimation function to identify commonalities between past flaming cases and reflect these in the risk assessment. For example, it evaluates whether specific themes or topics are likely to cause flaming cases. In this way, by analyzing users' emotional reactions to past flaming cases, it is possible to identify elements that cause similar emotions.

[0065] The risk assessment unit can evaluate the risk of a flame war from a global perspective by taking into account the reactions of users from different cultural spheres and regions. The risk assessment unit, for example, analyzes the reactions of users from different cultural spheres and reflects them in the risk assessment. For example, it evaluates negative reactions in a specific cultural sphere and considers them as risk factors. The risk assessment unit can also analyze the reactions of users from different regions and reflect them in the risk assessment. For example, it analyzes social media data by region and identifies risk factors. This allows the risk to be evaluated from a global perspective by taking into account the reactions of users from different cultural spheres and regions.

[0066] The risk assessment unit can monitor social media trends in real time and reflect the latest user interests when assessing risks. The risk assessment unit, for example, monitors social media trends in real time and reflects the trends in the risk assessment. For example, risk is assessed based on rapidly increasing topics and hashtags. The risk assessment unit can also use real-time data streaming technology to reflect the latest user interests. For example, real-time social media data is collected and trend analysis is performed. In this way, by monitoring social media trends in real time, the latest user interests can be reflected in the risk assessment.

[0067] The risk assessment unit can use the emotion estimation function to collect the user's emotional reactions to the risk assessment results and improve the accuracy of the assessment. The risk assessment unit, for example, collects the user's emotional reactions to the risk assessment results in real time and improves the accuracy of the assessment. For example, it analyzes positive and negative reactions to the risk assessment results. The risk assessment unit can also use the emotion estimation function to improve the assessment model based on the user's emotional reactions. For example, it introduces a feedback loop to continuously improve the accuracy of the assessment model. In this way, the accuracy of the assessment can be improved by collecting the user's emotional reactions to the risk assessment results.

[0068] The result presentation unit can include specific numerical data and graphs in the generated risk assessment report and present it in a visually easy-to-understand format. The result presentation unit, for example, includes specific numerical data in the generated risk assessment report. For example, the score of the risk of a firestorm or the frequency of past firestorm incidents is displayed numerically. The result presentation unit can also include graphs in the risk assessment report. For example, the progress of the risk score or the distribution of risk factors is displayed in a graph. In this way, by including specific numerical data and graphs, the risk assessment report can be presented in a visually easy-to-understand format.

[0069] The result presentation unit presents the risk assessment results in detail for each element of the service, making it possible to clarify which parts are particularly high risk. The result presentation unit, for example, presents the risk assessment results for each element of the service. For example, it evaluates risk for each element such as the user interface, privacy policy, and promotional video. The result presentation unit can also create a detailed report to clarify parts with particularly high risk. For example, it performs risk scoring and displays the risk level of each element numerically. In this way, by presenting the risk assessment results for each element of the service, it is possible to clarify parts with particularly high risk.

[0070] The result presentation unit can use the emotion estimation function to analyze the user's emotional response to the risk assessment result and suggest improvements to elicit a positive response. The result presentation unit, for example, analyzes the user's emotional response to the risk assessment result and suggests improvements to elicit a positive response. For example, it suggests correcting parts that have a lot of negative responses. The result presentation unit can also use the emotion estimation function to identify improvements based on the user's emotional response. For example, it suggests specific improvement measures based on user test results and emotion analysis data. This makes it possible to analyze the user's emotional response to the risk assessment result and suggest improvements to elicit a positive response.

[0071] The result presentation unit can present the risk assessment results to different departments or teams in a customized format, making it easier for each department to take specific measures. The result presentation unit, for example, presents the risk assessment results to different departments or teams in a customized format. For example, it can focus on presenting promotion-related risks to the marketing department and technical risks to the development department. The result presentation unit can also provide a customizable dashboard to make it easier for each department to take specific measures. For example, it can provide a report format tailored to the needs of each department. In this way, presenting the risk assessment results in a customized format makes it easier for each department to take specific measures.

[0072] The result presentation unit can compare the risk assessment results with other projects or services and clearly indicate the relative risk level. The result presentation unit, for example, compares the risk assessment results with other projects or services and clearly indicates the relative risk level. For example, it compares the risk scores of past projects with those of the current project. The result presentation unit can also compare the risk assessment results using benchmark data. For example, it compares them with industry standard risk scores and evaluates the relative risk level. In this way, by comparing the risk assessment results with other projects or services, it is possible to clearly indicate the relative risk level.

[0073] The result presentation unit can use the emotion estimation function to collect the user's emotional reactions to the risk assessment results and improve the reliability of the assessment results. The result presentation unit, for example, collects the user's emotional reactions to the risk assessment results in real time and improves the reliability of the assessment results. For example, it analyzes positive and negative reactions to the risk assessment results. The result presentation unit can also use the emotion estimation function to improve the assessment model based on the user's emotional reactions. For example, it introduces a feedback loop to continuously improve the accuracy of the assessment model. In this way, by collecting the user's emotional reactions to the risk assessment results, the reliability of the assessment results can be improved.

[0074] The countermeasure proposal unit can increase the feasibility of the proposed countermeasure by including specific implementation procedures and necessary resources in the proposed countermeasure. The countermeasure proposal unit, for example, includes specific implementation procedures in the proposed countermeasure. For example, it may specify in detail the procedures for reviewing a privacy policy or the procedures for improving a user interface. The countermeasure proposal unit can also include the resources necessary for the proposed countermeasure. For example, it may specify the personnel, budget, and technical resources necessary for implementation. In this way, by including specific implementation procedures and necessary resources, the feasibility of the countermeasure can be increased.

[0075] The countermeasure proposal unit can make the proposed countermeasures more persuasive by including specific examples based on past successes and failures. The countermeasure proposal unit, for example, includes past successes in the proposed countermeasures. For example, it can specifically show successful cases for similar problems to prove the effectiveness of the countermeasures. The countermeasure proposal unit can also include past failures in the proposed countermeasures. For example, it can show failed cases for similar problems to emphasize the need for the countermeasures. In this way, by including specific examples based on past successes and failures, the proposed countermeasures can be made more persuasive.

[0076] The countermeasure suggestion unit can use the emotion estimation function to predict the user's emotional reaction to the proposed countermeasures and prioritize countermeasures that will elicit a positive reaction. The countermeasure suggestion unit, for example, predicts the user's emotional reaction to the proposed countermeasures and prioritizes countermeasures that will elicit a positive reaction. For example, countermeasures with high emotion scores are prioritized for implementation. The countermeasure suggestion unit can also use the emotion estimation function to determine the priority of countermeasures based on the user's emotional reaction. For example, the optimal countermeasure is selected based on user test results and emotion analysis data. This makes it possible to predict the user's emotional reaction to the proposed countermeasures and prioritize countermeasures that will elicit a positive reaction.

[0077] The Countermeasure Proposal Department incorporates best practices from different industries and fields when proposing countermeasures, allowing it to present improvement measures from a wide range of perspectives. For example, the Countermeasure Proposal Department may collect best practices from different industries and incorporate them into its countermeasure proposals. For example, it may refer to promotion strategies and user engagement methods that have been successful in other industries. The Countermeasure Proposal Department may also collect best practices from different fields and incorporate them into its countermeasure proposals. For example, it may refer to successful cases in the technical or marketing fields. In this way, by incorporating best practices from different industries and fields, it is possible to present improvement measures from a wide range of perspectives.

[0078] The countermeasure proposal unit can introduce an agile methodology in which proposed countermeasures are implemented as prototypes and improved based on user feedback. The countermeasure proposal unit, for example, introduces an agile methodology in which proposed countermeasures are implemented as prototypes and improved based on user feedback. For example, a prototype is developed in a short period of time and user opinions are reflected. The countermeasure proposal unit can also use an agile methodology to continuously improve countermeasures. For example, a sprint plan is made, feedback is collected periodically, and the countermeasures are improved. In this way, the quality of the countermeasures can be improved by introducing an agile methodology in which proposed countermeasures are implemented as prototypes and improved based on user feedback.

[0079] The countermeasure proposal unit can use the emotion estimation function to monitor the user's emotional reaction to the proposed countermeasures in real time and continuously search for optimal countermeasures. The countermeasure proposal unit, for example, uses the emotion estimation function to monitor the user's emotional reaction to the proposed countermeasures in real time. For example, it analyzes the user's facial expressions and voice and calculates an emotion score. The countermeasure proposal unit can also continuously search for optimal countermeasures based on the emotional reactions collected in real time. For example, it prioritizes implementing countermeasures with high emotion scores and adjusts the countermeasures based on the user's reaction. This makes it possible to monitor the user's emotional reaction to the proposed countermeasures in real time and continuously search for optimal countermeasures.

[0080] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0081] The information gathering department can analyze more detailed background information, including internal documents and developer comments from the service development process. For example, it can analyze the developer's design documents, specifications, development logs, etc. to understand the service's design intent and development background. It can also analyze comments made by developers about specific service functions to understand their intent and background. This allows for a more detailed analysis of the service's development background, enabling more accurate risk assessment.

[0082] When analyzing promotional videos, the information collection unit analyzes facial expressions and voice tones in the video to identify potential controversy factors. For example, it analyzes the facial expressions of the characters in the promotional video to detect changes in their emotions. It identifies smiling and angry expressions and evaluates the impression they give to viewers. It also analyzes voice tones in the promotional video to detect aggressive voice tones or voice tones that cause discomfort, and evaluates them as risk factors. This makes it possible to identify potential controversy factors in advance by analyzing the video and voice of the promotional video.

[0083] The information gathering unit can add information from the user's perspective, including pre-surveys and focus group feedback. For example, a pre-survey of users can be conducted and the results analyzed. Expectations and concerns about the service can be collected and areas for improvement identified before release. Focus group feedback can also be collected, and a prototype of the service can be provided to a specific user group, and areas for improvement identified based on that feedback. By adding information from the user's perspective, risk assessment can be conducted with greater consideration for users.

[0084] The Information Gathering Department collects information on services from different industries and can refer to success stories and failure stories from other industries. For example, they collect success stories from other industries and use them as reference for promotion strategies and user engagement methods. They also collect failure stories from other industries and take measures to prevent similar failures in services that are scheduled for release. In this way, by referring to success stories and failure stories from other industries, risk assessment can be performed from a broader perspective.

[0085] The information collection unit can use the emotion estimation function to analyze users' emotional reactions to collected information and eliminate elements that may cause negative reactions in advance. For example, it can analyze users' emotional reactions to collected information in real time and evaluate whether specific keywords or phrases cause discomfort to users. It can also take measures to eliminate elements that may cause negative reactions in advance, such as modifying offensive expressions or visuals that cause discomfort. This reduces the risk of a social media outcry by eliminating elements that may cause negative reactions in advance.

[0086] When analyzing past cases of online flaming, the risk assessment unit can analyze the timing of the onset of online flaming and the effectiveness of subsequent countermeasures in chronological order, and reflect this in risk assessment. For example, it can analyze the timing of past online flaming cases to evaluate whether online flaming is more likely to occur during certain seasons or events. It can also analyze the effectiveness of countermeasures taken in past online flaming cases in chronological order, and evaluate how effective a particular countermeasure was in bringing the onset of the flaming to a close. This allows for more accurate risk assessment by analyzing the timing of the onset of online flaming cases in past years and the effectiveness of countermeasures taken in chronological order.

[0087] When analyzing social media reaction data, the risk assessment unit can assess risk based on the frequency of appearance of specific keywords and hashtags. For example, by analyzing social media reaction data, risk is assessed based on the frequency of appearance of specific keywords. If negative keywords appear frequently, the risk is determined to be high. Risk can also be assessed based on the frequency of appearance of specific hashtags. If the number of specific hashtags increases sharply, the risk is determined to be high. In this way, assessing risk based on social media reaction data makes it possible to more accurately grasp the risk of flame wars.

[0088] The risk assessment unit can use the emotion estimation function to analyze users' emotional reactions to past flaming cases and identify elements that cause similar emotions. For example, it can analyze users' emotional reactions to past flaming cases and evaluate elements that cause strong feelings of anger or dissatisfaction. It can also use the emotion estimation function to identify commonalities between past flaming cases and evaluate whether specific themes or topics are likely to cause flaming. In this way, by analyzing users' emotional reactions to past flaming cases, it can identify elements that cause similar emotions.

[0089] The risk assessment unit can evaluate the risk of a flame war from a global perspective, taking into account the reactions of users from different cultural spheres and regions. For example, it can analyze the reactions of users from different cultural spheres, evaluate negative reactions in specific cultural spheres, and consider them as risk factors. It can also analyze the reactions of users from different regions and identify risk factors based on social media data by region. This allows risk to be evaluated from a global perspective by taking into account the reactions of users from different cultural spheres and regions.

[0090] The risk assessment unit can use the emotion estimation function to collect users' emotional responses to the risk assessment results and improve the accuracy of the assessment. For example, the emotion estimation function can collect users' emotional responses to the risk assessment results in real time and analyze positive and negative responses. The emotion estimation function can also be used to improve the assessment model based on the users' emotional responses. A feedback loop is introduced to continuously improve the accuracy of the assessment model. In this way, the accuracy of the assessment can be improved by collecting users' emotional responses to the risk assessment results.

[0091] The processing flow of the second embodiment will be briefly explained below.

[0092] Step 1: The information gathering department collects information about the service to be released, such as service descriptions, promotional videos, and screenshots of the user interface. They also collect past reviews of similar services and social media reaction data. Step 2: The analysis unit analyzes the information collected by the information collection unit. For example, it can use text mining technology to analyze the service description and extract potential problems. It can also use image analysis technology to analyze the content of promotional videos. It can also analyze social media reaction data to evaluate users' emotional reactions. Step 3: The risk assessment unit assesses the risk of a social media outrage based on the information analyzed by the analysis unit. For example, it identifies the aspects of a service to be released that could potentially cause a social media outrage based on past social media outrage cases. It can also calculate a risk score based on social media reaction data. Step 4: The results presentation unit presents the risk assessment results evaluated by the risk assessment unit to the planner. For example, it generates a report that includes high-risk points, the reasons for them, and past similar cases. It can also present the risk assessment results in a visually easy-to-understand format. Step 5: The countermeasure proposal department proposes countermeasures based on the risk assessment results. For example, they can propose a review of the privacy policy, improvements to the user interface, or changes to promotional methods. They can also present specific improvement measures based on past success stories.

[0093] The specific processing unit 290 transmits the result of the specific processing to the smart device 14. In the smart device 14, the control unit 46A causes the output device 40 to output the result of the specific processing. The microphone 38B acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0094] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> Examples of generative AIs include the data generation model 58, such as a neural network model (e.g., a neural network model), and a neural network model (e.g., a neural network model). The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating speech, text data indicating text, and image data indicating an image is also input to the data generation model 58. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The specification processing unit 290 performs the above-mentioned specification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0095] Furthermore, the processing by the data processing system 10 described above is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart device 14, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart device 14. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information necessary for processing from the smart device 14 or an external device, and the smart device 14 acquires or collects information necessary for processing from the data processing device 12 or an external device.

[0096] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0097] 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.

[0098] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0099] The smart glasses 214 include a computer 36, a microphone 238, a speaker 240, a camera 42, and a communication I / F 44. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, and the camera 42 are also connected to the bus 52.

[0100] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0101] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0102] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0103] Fig. 4 shows an example of the main functions of the data processing device 12 and the smart glasses 214. As shown in Fig. 4, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0104] 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.

[0105] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0106] In the smart glasses 214, the specific processing is performed by the processor 46. A specific processing program 60 is stored in the storage 50. The processor 46 reads the specific processing program 60 from the storage 50 and executes the read specific processing program 60 on the RAM 48. The specific processing is realized by the processor 46 operating as the control unit 46A in accordance with the specific processing program 60 executed on the RAM 48. Note that the smart glasses 214 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0107] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0108] The specific processing unit 290 transmits the result of the specific processing to the smart glasses 214. In the smart glasses 214, the control unit 46A causes the speaker 240 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0109] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0110] The data processing system 210 according to the second embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 210 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the smart glasses 214, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the smart glasses 214. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the smart glasses 214 or an external device, etc., and the smart glasses 214 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0111] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0112] 5, the data processing system 310 includes the data processing device 12 and a headset terminal 314. An example of the data processing device 12 is a server.

[0113] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0114] The headset type terminal 314 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a display 343. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the display 343 are also connected to the bus 52.

[0115] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0116] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0117] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0118] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0119] 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.

[0120] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0121] In the headset type terminal 314, the identification process is performed by the processor 46. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. Note that the headset type terminal 314 may also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0122] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0123] The specific processing unit 290 transmits the result of the specific processing to the headset type terminal 314. In the headset type terminal 314, the control unit 46A causes the speaker 240 and the display 343 to output the result of the specific processing. The microphone 238 acquires audio indicating a user input regarding the result of the specific processing. The control unit 46A transmits audio data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the audio data.

[0124] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0125] The data processing system 310 according to the third embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 310 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the headset type terminal 314, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the headset type terminal 314. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the headset type terminal 314 or an external device, etc., and the headset type terminal 314 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0126] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0127] 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.

[0128] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, RAM 30, and storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN and / or a LAN.

[0129] The robot 414 includes a computer 36, a microphone 238, a speaker 240, a camera 42, a communication I / F 44, and a control target 443. The computer 36 includes a processor 46, a RAM 48, and a storage 50. The processor 46, the RAM 48, and the storage 50 are connected to a bus 52. The microphone 238, the speaker 240, the camera 42, and the control target 443 are also connected to the bus 52.

[0130] The microphone 238 receives instructions and the like from the user by receiving voice uttered by the user. The microphone 238 captures the voice uttered by the user, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio according to instructions from the processor 46.

[0131] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS image sensor or a CCD image sensor, and captures images of the user's surroundings (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0132] The communication I / F 44 is connected to a network 54. The communication I / Fs 44 and 26 are responsible for the exchange of various information between the processor 46 and the processor 28 via the network 54. The exchange of various information between the processor 46 and the processor 28 using the communication I / Fs 44 and 26 is carried out in a secure state.

[0133] The control object 443 includes a display device, LEDs in the eyes, and motors that drive the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[0134] Fig. 8 shows an example of the main functions of the data processing device 12 and the robot 414. As shown in Fig. 8, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0135] 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.

[0136] The storage 32 stores a data generation model 58 and an emotion identification model 59. The data generation model 58 and the emotion identification model 59 are used by the identification processing unit 290. The identification processing unit 290 can estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0137] In the robot 414, the processor 46 performs the identification process. A identification program 60 is stored in the storage 50. The processor 46 reads the identification program 60 from the storage 50 and executes the read identification program 60 on the RAM 48. The identification process is realized by the processor 46 operating as a control unit 46A in accordance with the identification program 60 executed on the RAM 48. The robot 414 may have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59.

[0138] Note that a device other than the data processing device 12 may have the data generation model 58. For example, a server device may have the data generation model 58. In this case, the data processing device 12 communicates with the server device having the data generation model 58 to obtain a processing result (such as a prediction result) using the data generation model 58. Furthermore, the data processing device 12 may be a server device, or may be a terminal device (for example, a mobile phone, a robot, a home appliance, etc.) owned by a user.

[0139] The specific processing unit 290 transmits the result of the specific processing to the robot 414. In the robot 414, the control unit 46A causes the speaker 240 and the control target 443 to output the result of the specific processing. The microphone 238 acquires voice indicating a user input regarding the result of the specific processing. The control unit 46A transmits voice data indicating the user input acquired by the microphone 238 to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the voice data.

[0140] The data generation model 58 is a so-called generative AI. An example of the data generation model 58 is a generative AI such as ChatGPT. The data generation model 58 is obtained by performing deep learning on a neural network. The data generation model 58 receives a prompt containing an instruction, as well as inference data such as voice data representing speech, text data representing text, and image data representing an image. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization. The identification processing unit 290 performs the above-mentioned identification processing using the data generation model 58. The data generation model 58 may be a fine-tuned model so as to output an inference result from a prompt that does not include an instruction. In this case, the data generation model 58 can output an inference result from a prompt that does not include an instruction. The data processing device 12 and the like include multiple types of data generation models 58, and the data generation model 58 includes AIs other than the generative AI. The AI ​​other than the generative AI may be, for example, linear regression, logistic regression, decision tree, random forest, support vector machine (SVM), k-means clustering, convolutional neural network (CNN), recurrent neural network (RNN), generative adversarial network (GAN), or naive Bayes, and can perform various processes, but is not limited to these examples. The AI ​​may also be an AI agent. When the processes of each of the above-mentioned parts are performed by AI, the processes may be performed in part or entirely by AI, but are not limited to these examples. The processes performed by AI, including the generative AI, may be replaced with rule-based processes.

[0141] The data processing system 410 according to the fourth embodiment performs the same processing as the data processing system 10 according to the first embodiment. The processing by the data processing system 410 is executed by the specific processing unit 290 of the data processing device 12 or the control unit 46A of the robot 414, but may also be executed by the specific processing unit 290 of the data processing device 12 and the control unit 46A of the robot 414. Furthermore, the specific processing unit 290 of the data processing device 12 acquires or collects information required for processing from the robot 414 or an external device, etc., and the robot 414 acquires or collects information required for processing from the data processing device 12 or an external device, etc.

[0142] The emotion identification model 59 as an emotion engine may determine the user's emotion according to a specific mapping. Specifically, the emotion identification model 59 may determine the user's emotion according to an emotion map (see FIG. 9), which is a specific mapping. Similarly, the emotion identification model 59 may determine the robot's emotion, and the identification processing unit 290 may perform identification processing using the robot's emotion.

[0143] FIG. 9 illustrates an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and behaviors arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion encompasses both emotions and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[0144] These emotions are distributed in the 3 o'clock direction on emotion map 400, and typically fluctuate between relief and anxiety. In the right half of emotion map 400, situational awareness dominates over internal sensations, resulting in a sense of calm.

[0145] The inside of emotion map 400 represents what is going on in the mind, and the outside of emotion map 400 represents behavior, so the further you go outside emotion map 400, the more visible the emotions become (the more they are expressed in behavior).

[0146] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. Emotions can also be created for robots, cars, and motorcycles, based on various balances, such as posture and remaining battery life. When these balances deviate from the ideal, a state of discomfort is expressed, and when they approach the ideal, a state of pleasure is expressed. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on speech emotion recognition and brain physiological signal analysis systems for emotions, Tokushima University, doctoral dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the area called "reaction," where sensation is dominant. The right half of the emotion map lists emotions belonging to the area called "situation," where situational awareness is dominant.

[0147] The emotion map defines two emotions that promote learning. One is a negative emotion on the situation side, around the middle of "repentance" or "reflection." In other words, this occurs when the robot experiences negative emotions such as "I never want to feel this way again" or "I don't want to be scolded again." The other is a positive emotion on the response side, around "desire." In other words, this occurs when the robot experiences positive feelings such as "I want more" or "I want to know more."

[0148] The emotion identification model 59 inputs user input into a pre-trained neural network, obtains emotion values ​​indicating each emotion shown in the emotion map 400, and determines the user's emotion. This neural network is pre-trained based on multiple pieces of training data that are combinations of user input and emotion values ​​indicating each emotion shown in the emotion map 400. Furthermore, this neural network is trained so that emotions that are located close to each other have similar values, as in the emotion map 900 shown in FIG. 10. FIG. 10 shows an example in which multiple emotions, "relieved," "calm," and "reassuring," have similar emotion values.

[0149] In the above embodiment, an example was given in which a specific process is performed by one computer 22, but the technology disclosed herein is not limited to this, and distributed processing of the specific process may be performed by multiple computers including computer 22.

[0150] In the above embodiment, an example in which the specific processing program 56 is stored in the storage 32 has been described, but the technology of the present disclosure is not limited to this. For example, the specific processing program 56 may be stored in a portable, computer-readable, non-transitory storage medium such as a USB (Universal Serial Bus) memory. The specific processing program 56 stored in the non-transitory storage medium is installed in the computer 22 of the data processing device 12. The processor 28 executes the specific processing in accordance with the specific processing program 56.

[0151] 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.

[0152] It is not necessary to store all of the specific processing program 56 in a storage device such as a server connected to the data processing device 12 via the network 54, or to store all of the specific processing program 56 in the storage 32; only a portion of the specific processing program 56 may be stored.

[0153] The hardware resource for executing a specific process can be any of the following processors: A CPU is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A dedicated electrical circuit, such as a field-programmable gate array (FPGA), a programmable logic device (PLD), or an application-specific integrated circuit (ASIC), is a processor with a circuit configuration specifically designed to execute a specific process. Each processor has built-in or connected memory, and uses the memory to execute the specific process.

[0154] The hardware resource that executes the specific process may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific process may be a single processor.

[0155] As an example of a system configured with a single processor, first, one processor is configured by combining one or more CPUs and software, and this processor functions as a hardware resource that executes a specific process. Second, there is a system that uses a processor that realizes the functions of an entire system including multiple hardware resources that execute a specific process on a single IC chip, as typified by SoC (System-on-a-chip). In this way, a specific process is realized using one or more of the above-mentioned various processors as hardware resources.

[0156] Furthermore, the hardware structure of these various processors can be, more specifically, an electric circuit that combines circuit elements such as semiconductor devices. The specific processing described above is merely an example. Therefore, it goes without saying that unnecessary steps may be deleted, new steps may be added, or the processing order may be rearranged, without departing from the spirit of the invention.

[0157] In the above example, the first to fourth embodiments have been described separately, but some or all of these embodiments may be combined. The smart device 14, smart glasses 214, headset terminal 314, and robot 414 are merely examples, and they may be combined, or other devices may be used. In the above example, the first and second embodiments have been described separately, but they may be combined.

[0158] The above-described description and illustrations are a detailed explanation of the parts related to the technology of the present disclosure and are merely an example of the technology of the present disclosure. For example, the above description of the configuration, functions, actions, and effects is an explanation of an example of the configuration, functions, actions, and effects of the parts related to the technology of the present disclosure. Therefore, it goes without saying that unnecessary parts may be deleted, new elements may be added, or replacements may be made to the above-described description and illustrations within the scope of the gist of the technology of the present disclosure. Furthermore, to avoid confusion and facilitate understanding of the parts related to the technology of the present disclosure, the above-described description and illustrations omit explanations of common technical knowledge that do not require particular explanation to enable the implementation of the technology of the present disclosure.

[0159] All publications, patent applications, and technical standards mentioned in this specification are herein incorporated by reference to the same extent as if each individual publication, patent application, or technical standard was specifically and individually indicated to be incorporated by reference. [Explanation of symbols]

[0160] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot

Claims

1. an information gathering department that collects information on services to be released; an analysis unit that analyzes the information collected by the information collection unit; a risk assessment unit that assesses a risk of a controversy based on the information analyzed by the analysis unit; a result presentation unit that presents the risk assessment results evaluated by the risk assessment unit to a planner; a countermeasure proposal unit that proposes countermeasures based on the risk assessment result evaluated by the risk assessment unit. A system characterized by:

2. The information collecting unit When analyzing promotional videos, we analyze facial expressions or tone of voice in the footage to identify potential sources of controversy. The system of claim 1 .

3. The risk assessment unit When analyzing past incidents of online outrage, we analyze the timing of the incidents and the effectiveness of countermeasures over time, and reflect this in risk assessment. The system of claim 1 .

4. The result presentation unit Generate risk assessment reports that include specific numerical data or graphs and present them in a visually easy-to-understand format The system of claim 1 .

5. The measure proposal unit Include specific implementation steps or required resources in the proposed measures to increase their feasibility. The system of claim 1 .

6. The information collecting unit Use emotion estimation to analyze users' emotional reactions to service descriptions or promotional videos in real time and identify elements that elicit positive reactions. The system of claim 1 .

7. The risk assessment unit Using emotion estimation, we analyze users' emotional reactions to past online scandals and identify factors that trigger similar emotions. The system of claim 1 .

8. The result presentation unit Using emotion estimation functionality, the system analyzes the user's emotional response to the risk assessment results and suggests improvements to elicit a positive response. The system of claim 1 .

Images