System

Abstract

An object of a system according to an embodiment is to quickly and accurately perform legal confirmation of a sales promotion item.SOLUTION: A system according to an embodiment includes a sales promotion item analysis unit, a legal concern indication unit, a correction unit, and a legal check unit. The sales promotion item analysis unit analyzes the content of the sales promotion item. The legal concern indication unit indicates a legally concerned part on the basis of the content analyzed by the sales promotion item analysis unit. The correction unit corrects the legally concerned portion pointed out by the legal concern pointing out unit. A legal confirmation part allows a person in charge of law to confirm the contents of the sales promotion article corrected by the correction part.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] Conventional technology has the drawback of taking time to legally check promotional items, which can lead to oversights when a quick response is required.

[0005] The system according to the embodiment aims to quickly and accurately perform legal verification of promotional items. [Means for solving the problem]

[0006] The system according to the embodiment includes a promotional item analysis unit, a legal concern identification unit, a correction unit, and a legal confirmation unit. The promotional item analysis unit analyzes the content of the promotional item. The legal concern identification unit identifies legal concerns based on the content analyzed by the promotional item analysis unit. The correction unit corrects the legal concerns identified by the legal concern identification unit. The legal confirmation unit has a legal officer review the content of the promotional item corrected by the correction unit. [Effects of the Invention]

[0007] The system according to the embodiment can quickly and accurately perform legal verification of promotional items. [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 non-volatile storage devices that store various programs, various parameters, etc. Examples of non-volatile storage devices include flash memory (SSD (Solid State Drive)), magnetic disks (e.g., hard disks), and magnetic tapes.

[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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[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 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[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 legal review process efficiency improvement system according to an embodiment of the present invention is a system in which the contents of promotional items are automatically analyzed, a generation AI identifies areas of legal concern, corrections are made, and the system is finally reviewed by a legal officer. As a result, the legal review process efficiency improvement system can improve the efficiency of the legal review process and reduce the burden on legal officers.

[0029] A legal review process efficiency improvement system according to an embodiment includes a legal generation AI, a promotional item analysis unit, a legal concern identification unit, a correction unit, and a legal review unit. The legal generation AI includes a promotional item analysis unit that analyzes the content of promotional items. The promotional item analysis unit analyzes input information, such as the design, wording, and images used in the promotional items. The promotional item analysis unit also compares the input information with a database of past cases to identify legal concerns. The legal concern identification unit identifies legal concerns based on the content analyzed by the promotional item analysis unit. For example, the legal concern identification unit makes specific indications such as "This image may infringe copyright" or "This wording is misleading." The correction unit corrects the legal concerns identified by the legal concern identification unit. For example, the correction unit replaces images that may infringe copyright or corrects misleading language. The legal review unit has a legal officer review the content of the promotional items corrected by the correction unit. For example, the legal review unit presents the revised promotional item to a legal officer for final legal review. As a result, the legal review process efficiency improvement system according to the embodiment can improve the efficiency of the legal review process and reduce the burden on the legal officer.

[0030] The promotional product analysis unit can identify legal concerns by referencing past legal precedents or court records. For example, the legal generation AI can refer to a database of past legal precedents to evaluate whether the content of promotional products poses legal risks based on past precedents. For example, if a lawsuit has been filed in a similar case, the promotional product analysis unit can point out the risk. The promotional product analysis unit can also analyze court records to check whether the content of promotional products matches expressions or designs that have been problematic in past court cases. For example, it can issue a warning if a specific phrase or image has previously caused legal issues. The promotional product analysis unit can also automatically identify areas of promotional product content that may pose legal issues based on legal precedents and court records and suggest revisions. For example, it can suggest alternatives if specific wording or design may pose legal issues. This improves the accuracy of legal risk assessment by referring to past legal precedents and court records.

[0031] The promotional product analysis unit can identify industry-specific legal risks based on the legal regulations of different industries. For example, the legal generation AI in the promotional product analysis unit references a database of legal regulations for different industries to evaluate whether the content of promotional products complies with the regulations of each industry. For example, it identifies risks by taking into account regulations specific to the medical and financial industries. The promotional product analysis unit also analyzes legal risks in different industries and identifies areas where the content of promotional products may be problematic in specific industries. For example, it issues a warning if there is a possibility of violating labeling or advertising regulations in the food industry. The promotional product analysis unit also considers industry-specific legal risks and proposes revisions to ensure the content of promotional products complies with the regulations of each industry. For example, it proposes changes to wording or design to avoid legal risks in specific industries. This allows industry-specific legal risks to be reduced by taking into account the legal regulations of different industries.

[0032] The promotional product analysis unit can also analyze audio or video data to identify legal risks in multimedia content. For example, the promotional product analysis unit uses legal generation AI to analyze audio data and evaluate whether it contains copyright infringement or misleading language. For example, it checks whether the use of music or narration is appropriate and suggests corrections if there are any issues. The promotional product analysis unit also analyzes video data to identify areas in which the video or audio may be legally problematic. For example, it evaluates whether the video violates the portrait rights or privacy rights of people in the video and suggests corrections as necessary. The promotional product analysis unit also analyzes the entire multimedia content and identifies areas where there are legal risks. For example, it issues a warning if the text, images, or audio in a video may be legally problematic and suggests corrections. This reduces the legal risks of multimedia content, including audio and video data.

[0033] The Promotional Product Analysis Department can simultaneously analyze legal risks in different languages ​​and point out international legal concerns. For example, the Promotional Product Analysis Department uses legal generation AI to analyze the content of promotional products in different languages ​​and evaluate the legal risks in each language. For example, it simultaneously analyzes legal risks in multiple languages, such as English, French, and Chinese. The Promotional Product Analysis Department also takes international legal regulations into account and evaluates whether the content of promotional products in different languages ​​complies with the regulations of each country. For example, it issues a warning if there is a possibility of violating advertising or labeling regulations in a specific country. The Promotional Product Analysis Department also analyzes legal risks in different languages ​​and builds a system that points out international legal concerns. For example, it makes suggestions to modify the content of promotional products taking into account the legal risks in each country. In this way, international legal concerns can be reduced by analyzing legal risks in different languages.

[0034] The correction department can refer to the history of corrections made by legal personnel in the past and automatically suggest similar corrections. For example, when checking the output results of the legal generation AI, the correction department references the history of past corrections and builds a system that automatically suggests similar corrections. For example, it suggests similar corrections based on the corrections made in the past. The correction department also analyzes the history of corrections made by legal personnel in the past, automatically identifies areas that pose similar legal risks, and presents suggested corrections. For example, it suggests corrections to avoid similar risks based on the corrections made in the past. The correction department also builds a database of correction history, and the legal generation AI learns the corrections made in the past, thereby improving the accuracy of correction suggestions from the next time onwards. For example, it automatically generates more appropriate correction suggestions based on the history of past corrections. This makes it possible to make efficient corrections by referring to the history of past corrections.

[0035] The correction department can automatically analyze the scope of impact of the corrections and evaluate the impact of the corrections on other parts. For example, the correction department constructs a system in which legal generation AI automatically analyzes the scope of impact of the corrections and evaluates the impact of the corrections on other parts. For example, it evaluates the impact that correcting a specific expression will have on other parts. The correction department also analyzes the scope of impact of the corrections and visually displays the impact of the corrections on other parts. For example, it highlights parts related to the corrections so that the scope of impact can be intuitively understood. The correction department also evaluates the scope of impact of the corrections and makes suggestions to minimize the impact of the corrections on other parts. For example, it makes suggestions to reduce the impact on other parts by changing the corrections. In this way, by evaluating the scope of impact of the corrections, it is possible to minimize the impact on other parts.

[0036] The correction department can collect feedback from experts in different industries and evaluate the corrections from multiple perspectives. For example, when checking the output results of the legal generation AI, the correction department collects feedback from experts in different industries and builds a system to evaluate the corrections from multiple perspectives. For example, it reflects opinions from experts in the medical and financial industries. The correction department also evaluates the corrections based on feedback from experts in different industries and makes suggestions to minimize legal risks. For example, it adjusts the corrections to comply with regulations in each industry. The correction department also collects feedback from experts in real time and builds a system to dynamically evaluate the corrections. For example, it reevaluates the corrections based on the experts' opinions and updates the priorities. This allows the corrections to be evaluated from multiple perspectives by collecting feedback from experts in different industries.

[0037] The correction department can visualize the corrections and present them in a visually easy-to-understand format. For example, the correction department can visualize the output results of the legal generation AI and build a system that presents the corrections in a visually easy-to-understand format. For example, the corrections can be highlighted to visually show the details of the corrections. The correction department can also visualize the corrections and visually show the impact the corrections will have on other parts. For example, the corrections can be linked to related parts to allow an intuitive understanding of the scope of the impact. The correction department can also visualize the corrections so that legal personnel can quickly grasp the details of the corrections. For example, the context before and after the corrections can be displayed to visually show the need for the corrections. In this way, visualizing the corrections makes it easier to understand visually.

[0038] The legal review department can compare the analysis results of the generation AI with the past judgments of legal personnel and focus on checking inconsistencies. For example, when legal personnel perform their final review, the legal review department builds a system that compares the analysis results of the generation AI with past judgments and focuses on checking inconsistencies. For example, it issues a warning if the points pointed out by the generation AI differ from the judgments of legal personnel. The legal review department also compares the analysis results of the generation AI with the past judgments of legal personnel, automatically identifying inconsistencies and focusing on checking them. For example, it prioritizes checking points that differ from the points pointed out by the generation AI based on the past judgment history. The legal review department also builds a database of past judgment history, and the generation AI learns from past judgments to improve the accuracy of its analysis from the next time onwards. For example, it improves the analysis results of the generation AI based on the past judgment history. This improves the accuracy of the review process by comparing the analysis results of the generation AI with the past judgments of legal personnel.

[0039] The legal review department can automatically present the legal basis for the revisions proposed by the generation AI, making the review process more efficient. For example, the legal review department will build a system that automatically presents the legal basis for the revisions proposed by the generation AI when a legal officer performs the final review. For example, it will display legal provisions and precedents related to the revisions. The legal review department will also make the review process more efficient for legal officers based on the legal basis for the revisions proposed by the generation AI. For example, the legal review department will quickly perform the review process while referring to the legal basis for the revisions. The legal review department will also build a legal basis database and develop a system that allows the generation AI to automatically search for and present the legal basis for the revisions. For example, it will provide legal information related to the revisions in real time. This will make the review process more efficient by automatically presenting the legal basis for the revisions proposed by the generation AI.

[0040] The Legal Review Department can cooperate with legal personnel from different jurisdictions to comprehensively assess international legal risks. For example, when legal personnel conduct final reviews, the Legal Review Department cooperates with legal personnel from different jurisdictions to build a system for comprehensively assessing international legal risks. For example, legal personnel from each country conduct the review work together. The Legal Review Department also assesses international legal risks based on feedback from legal personnel from different jurisdictions and proposes revisions. For example, it adjusts the revisions to comply with the legal regulations of each country. The Legal Review Department also builds a system for sharing information in real time with legal personnel from different jurisdictions to comprehensively assess international legal risks. For example, it shares information using online meetings and chat functions. This allows cooperation with legal personnel from different jurisdictions to comprehensively assess international legal risks.

[0041] The Legal Review Department can link the generative AI's analysis results with other legal tools to perform comprehensive legal evaluations. For example, when legal personnel perform final review, the Legal Review Department links the generative AI's analysis results with other legal tools to build a system for comprehensive legal evaluations. For example, it links with contract analysis tools and risk assessment tools. The Legal Review Department also integrates the generative AI's analysis results with other legal tools to comprehensively evaluate legal risks. For example, it evaluates legal risks based on data obtained from multiple tools and proposes revisions. The Legal Review Department also complements the generative AI's analysis results by linking them with other legal tools to improve the accuracy of legal evaluations. For example, it reevaluates the generative AI's analysis results based on the results of a contract analysis tool. In this way, linking the generative AI's analysis results with other legal tools makes comprehensive legal evaluations possible.

[0042] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0043] The system for improving the efficiency of the legal review process can further include a user interface unit. The user interface unit is designed to make it easy for legal personnel to operate the system, allowing intuitive operation. For example, corrections can be easily moved using a drag-and-drop function. The user interface unit can also display a preview of the corrections in real time, allowing legal personnel to immediately check the impact of the corrections. Furthermore, the user interface unit can also be equipped with a voice input function, allowing legal personnel to issue instructions by voice. This reduces the operational burden on legal personnel and enables efficient legal review.

[0044] The promotional item analysis unit may further include a natural language processing unit. The natural language processing unit analyzes the text of the promotional item and automatically detects expressions that pose legal risks. For example, it issues a warning if a specific keyword or phrase may be legally problematic. The natural language processing unit can also analyze the text of the promotional item and make suggestions to correct grammatical errors or inappropriate expressions. For example, correcting the expressions to be grammatically correct reduces legal risks. The natural language processing unit can also analyze the text of the promotional item and evaluate its readability and understandability. For example, it can make suggestions to change difficult expressions to simpler expressions. This improves the quality of the text of the promotional item and reduces legal risks.

[0045] The promotional item analysis unit may further include a data mining unit. The data mining unit analyzes past data on promotional items to identify patterns of legal risk. For example, based on past data on promotional items, it extracts patterns of expressions and designs that pose a high legal risk. The data mining unit also analyzes past data on promotional items to identify trends in legal risk. For example, it identifies a trend of increasing legal risk at specific times and suggests preventive measures. The data mining unit also analyzes past data on promotional items to identify factors that cause legal risk. For example, it issues a warning if a specific factor is likely to cause legal risk. This makes it possible to predict legal risks using past data and take preventive measures.

[0046] The correction unit may further include an automatic translation unit. The automatic translation unit automatically translates the corrections into different languages ​​to reduce international legal risks. For example, the corrections may be translated into multiple languages, such as English, French, and Chinese, and adjusted to comply with the legal regulations of each country. The automatic translation unit may also visualize the translation results to make them easier for legal personnel to review. For example, the translation results may be highlighted to visually show the impact of the corrections. The automatic translation unit may also evaluate legal risks in different languages ​​based on the translation results and suggest corrections. For example, the automatic translation unit may suggest changes to wording or design to avoid legal risks in specific languages. This reduces legal risks in different languages ​​and streamlines international legal review.

[0047] The correction department can further include a cloud collaboration department. The cloud collaboration department shares the correction details on the cloud, allowing multiple legal staff to review them simultaneously. For example, the correction details can be uploaded to the cloud, and legal staff can review the correction details in real time and add comments. The cloud collaboration department also performs version control of the correction details, making it easy to refer to past revision history. For example, the change history of the correction details can be managed on the cloud, making it possible to revert to a previous version as needed. Furthermore, by sharing the correction details on the cloud, the cloud collaboration department allows legal staff to review them regardless of location. For example, review work can be performed efficiently even in a remote work environment. This makes the sharing and management of correction details more efficient by utilizing cloud collaboration.

[0048] The correction unit can further include an AI learning unit. The AI ​​learning unit learns the correction content and improves the accuracy of future correction suggestions. For example, it automatically suggests similar corrections based on past correction content. The AI ​​learning unit also evaluates the effectiveness of the correction content and improves the accuracy of future correction suggestions. For example, it collects performance data on promotional products after correction and evaluates the effectiveness of the corrections. The AI ​​learning unit also learns patterns of correction content and improves the accuracy of future correction suggestions. For example, if a specific pattern is highly effective in reducing legal risk, it will preferentially suggest that pattern. This makes it possible to utilize AI learning to improve the accuracy of correction suggestions and enable efficient legal confirmation.

[0049] The processing flow of the first embodiment will be briefly explained below.

[0050] Step 1: The Promotional Products Analysis Department analyzes the contents of the promotional products. Specifically, the department analyzes the design, wording, and images used in the promotional products as input information, and compares them with a database of past cases to identify any legal concerns. Step 2: The Legal Concerns Identification Department identifies legal concerns based on the content analyzed by the Promotional Products Analysis Department, making specific recommendations such as "This image may be a copyright infringement" or "This statement is misleading." Step 3: The Correction Department corrects the legal concerns raised by the Legal Concerns Raising Department, for example by replacing images that may be infringing copyrights or correcting misleading statements. Step 4: The Legal Review Department has a legal officer review the content of the promotional items revised by the Revision Department. For example, the revised promotional items are presented to the legal officer for final legal review.

[0051] (Example 2) The legal review process efficiency improvement system according to an embodiment of the present invention is a system in which the contents of promotional items are automatically analyzed, a generation AI identifies areas of legal concern, corrections are made, and the system is finally reviewed by a legal officer. As a result, the legal review process efficiency improvement system can improve the efficiency of the legal review process and reduce the burden on legal officers.

[0052] A legal review process efficiency improvement system according to an embodiment includes a legal generation AI, a promotional item analysis unit, a legal concern identification unit, a correction unit, and a legal review unit. The legal generation AI includes a promotional item analysis unit that analyzes the content of promotional items. The promotional item analysis unit analyzes input information, such as the design, wording, and images used in the promotional items. The promotional item analysis unit also compares the input information with a database of past cases to identify legal concerns. The legal concern identification unit identifies legal concerns based on the content analyzed by the promotional item analysis unit. For example, the legal concern identification unit makes specific indications such as "This image may infringe copyright" or "This wording is misleading." The correction unit corrects the legal concerns identified by the legal concern identification unit. For example, the correction unit replaces images that may infringe copyright or corrects misleading language. The legal review unit has a legal officer review the content of the promotional items corrected by the correction unit. For example, the legal review unit presents the revised promotional item to a legal officer for final legal review. As a result, the legal review process efficiency improvement system according to the embodiment can improve the efficiency of the legal review process and reduce the burden on the legal officer.

[0053] The promotional product analysis unit can use emotion estimation to estimate user emotions and point out parts that may evoke negative emotional responses. For example, the promotional product analysis unit uses legal generation AI to analyze the text of promotional products and uses emotion estimation to identify expressions that may evoke negative emotions in users. For example, it detects offensive language or misleading expressions and suggests modifications. The promotional product analysis unit also uses image analysis technology to evaluate the likelihood that images included in promotional products will evoke negative emotions in users. For example, it identifies images that may be offensive based on past data and suggests alternatives. The promotional product analysis unit also analyzes video and audio data and uses emotion estimation to point out parts that may evoke negative emotions in users. For example, it suggests modifications if the audio tone or video content is inappropriate. This enables legal confirmation that takes user emotions into account, reducing the risk of causing negative responses.

[0054] The promotional product analysis unit can identify legal concerns by referencing past legal precedents or court records. For example, the legal generation AI can refer to a database of past legal precedents to evaluate whether the content of promotional products poses legal risks based on past precedents. For example, if a lawsuit has been filed in a similar case, the promotional product analysis unit can point out the risk. The promotional product analysis unit can also analyze court records to check whether the content of promotional products matches expressions or designs that have been problematic in past court cases. For example, it can issue a warning if a specific phrase or image has previously caused legal issues. The promotional product analysis unit can also automatically identify areas of promotional product content that may pose legal issues based on legal precedents and court records and suggest revisions. For example, it can suggest alternatives if specific wording or design may pose legal issues. This improves the accuracy of legal risk assessment by referring to past legal precedents and court records.

[0055] The promotional product analysis unit can identify industry-specific legal risks based on the legal regulations of different industries. For example, the legal generation AI in the promotional product analysis unit references a database of legal regulations for different industries to evaluate whether the content of promotional products complies with the regulations of each industry. For example, it identifies risks by taking into account regulations specific to the medical and financial industries. The promotional product analysis unit also analyzes legal risks in different industries and identifies areas where the content of promotional products may be problematic in specific industries. For example, it issues a warning if there is a possibility of violating labeling or advertising regulations in the food industry. The promotional product analysis unit also considers industry-specific legal risks and proposes revisions to ensure the content of promotional products complies with the regulations of each industry. For example, it proposes changes to wording or design to avoid legal risks in specific industries. This allows industry-specific legal risks to be reduced by taking into account the legal regulations of different industries.

[0056] The promotional product analysis unit can also analyze audio or video data to identify legal risks in multimedia content. For example, the promotional product analysis unit uses legal generation AI to analyze audio data and evaluate whether it contains copyright infringement or misleading language. For example, it checks whether the use of music or narration is appropriate and suggests corrections if there are any issues. The promotional product analysis unit also analyzes video data to identify areas in which the video or audio may be legally problematic. For example, it evaluates whether the video violates the portrait rights or privacy rights of people in the video and suggests corrections as necessary. The promotional product analysis unit also analyzes the entire multimedia content and identifies areas where there are legal risks. For example, it issues a warning if the text, images, or audio in a video may be legally problematic and suggests corrections. This reduces the legal risks of multimedia content, including audio and video data.

[0057] The Promotional Product Analysis Department can simultaneously analyze legal risks in different languages ​​and point out international legal concerns. For example, the Promotional Product Analysis Department uses legal generation AI to analyze the content of promotional products in different languages ​​and evaluate the legal risks in each language. For example, it simultaneously analyzes legal risks in multiple languages, such as English, French, and Chinese. The Promotional Product Analysis Department also takes international legal regulations into account and evaluates whether the content of promotional products in different languages ​​complies with the regulations of each country. For example, it issues a warning if there is a possibility of violating advertising or labeling regulations in a specific country. The Promotional Product Analysis Department also analyzes legal risks in different languages ​​and builds a system that points out international legal concerns. For example, it makes suggestions to modify the content of promotional products taking into account the legal risks in each country. In this way, international legal concerns can be reduced by analyzing legal risks in different languages.

[0058] The promotional product analysis unit can use the emotion estimation function to suggest expressions that will evoke positive emotions in the user. For example, the promotional product analysis unit uses the emotion estimation function to analyze the text of the promotional product and suggest expressions that will evoke positive emotions in the user. For example, encouraging words or positive messages are added. The promotional product analysis unit also uses image analysis technology to suggest images that are likely to evoke positive emotions in the user. For example, images that include bright colors or smiling people are selected and used for the promotional product. The promotional product analysis unit also analyzes video and audio data to suggest expressions that will evoke positive emotions in the user. For example, it suggests creating a video that includes bright music and a positive message. This improves the effectiveness of the promotional product by suggesting expressions that will evoke positive emotions in the user.

[0059] The correction unit can use the emotion estimation function to prioritize corrections based on the user's emotional response. For example, when reviewing the output results of the legal generation AI, the correction unit uses the emotion estimation function to analyze the user's emotional response and prioritize corrections to sections that evoke negative emotions. For example, it corrects offensive or misleading expressions. The correction unit also uses the emotion estimation data to emphasize sections that evoke positive emotions in users and revise the content of promotional items. For example, adding positive messages and images can improve the user's emotional response. The correction unit also collects user emotional response data in real time and builds a system that dynamically adjusts the priority of corrections. For example, it reevaluates the corrections and updates the priority whenever the user's emotions change. This enables effective corrections by prioritizing corrections based on the user's emotional response.

[0060] The correction department can refer to the history of corrections made by legal personnel in the past and automatically suggest similar corrections. For example, when checking the output results of the legal generation AI, the correction department references the history of past corrections and builds a system that automatically suggests similar corrections. For example, it suggests similar corrections based on the corrections made in the past. The correction department also analyzes the history of corrections made by legal personnel in the past, automatically identifies areas that pose similar legal risks, and presents suggested corrections. For example, it suggests corrections to avoid similar risks based on the corrections made in the past. The correction department also builds a database of correction history, and the legal generation AI learns the corrections made in the past, thereby improving the accuracy of correction suggestions from the next time onwards. For example, it automatically generates more appropriate correction suggestions based on the history of past corrections. This makes it possible to make efficient corrections by referring to the history of past corrections.

[0061] The correction department can automatically analyze the scope of impact of the corrections and evaluate the impact of the corrections on other parts. For example, the correction department constructs a system in which legal generation AI automatically analyzes the scope of impact of the corrections and evaluates the impact of the corrections on other parts. For example, it evaluates the impact that correcting a specific expression will have on other parts. The correction department also analyzes the scope of impact of the corrections and visually displays the impact of the corrections on other parts. For example, it highlights parts related to the corrections so that the scope of impact can be intuitively understood. The correction department also evaluates the scope of impact of the corrections and makes suggestions to minimize the impact of the corrections on other parts. For example, it makes suggestions to reduce the impact on other parts by changing the corrections. In this way, by evaluating the scope of impact of the corrections, it is possible to minimize the impact on other parts.

[0062] The correction department can collect feedback from experts in different industries and evaluate the corrections from multiple perspectives. For example, when checking the output results of the legal generation AI, the correction department collects feedback from experts in different industries and builds a system to evaluate the corrections from multiple perspectives. For example, it reflects opinions from experts in the medical and financial industries. The correction department also evaluates the corrections based on feedback from experts in different industries and makes suggestions to minimize legal risks. For example, it adjusts the corrections to comply with regulations in each industry. The correction department also collects feedback from experts in real time and builds a system to dynamically evaluate the corrections. For example, it reevaluates the corrections based on the experts' opinions and updates the priorities. This allows the corrections to be evaluated from multiple perspectives by collecting feedback from experts in different industries.

[0063] The correction department can visualize the corrections and present them in a visually easy-to-understand format. For example, the correction department can visualize the output results of the legal generation AI and build a system that presents the corrections in a visually easy-to-understand format. For example, the corrections can be highlighted to visually show the details of the corrections. The correction department can also visualize the corrections and visually show the impact the corrections will have on other parts. For example, the corrections can be linked to related parts to allow an intuitive understanding of the scope of the impact. The correction department can also visualize the corrections so that legal personnel can quickly grasp the details of the corrections. For example, the context before and after the corrections can be displayed to visually show the need for the corrections. In this way, visualizing the corrections makes it easier to understand visually.

[0064] The correction unit can use the emotion estimation function to predict the emotional impact that a revised promotional product will have on a user. For example, when checking the output results of the legal generation AI, the correction unit uses the emotion estimation function to build a system that predicts the emotional impact that a revised promotional product will have on a user. For example, the correction unit simulates the emotional reaction that a revised part will have on a user. The correction unit also predicts the user's emotional reaction to the revised promotional product and proposes revisions to elicit positive emotions. For example, changing the revised part to a more positive expression improves the user's emotional reaction. The correction unit also evaluates the emotional impact that a revised promotional product will have on a user based on the emotion estimation data and selects the optimal revision proposal. For example, the correction unit compares multiple revision proposals and adopts the proposal that elicits the most positive emotional reaction. This enables effective revisions by predicting the emotional impact that a revised promotional product will have on a user.

[0065] The legal review unit can use the emotion estimation function to determine the priority of final review based on the user's emotional response. For example, when a legal officer performs final review, the legal review unit uses the emotion estimation function to analyze the user's emotional response and prioritizes review of sections that may evoke negative emotions. For example, it focuses on reviewing offensive or misleading expressions. The legal review unit also emphasizes sections that evoke positive emotions in the user based on the emotion estimation data and determines the priority of final review. For example, it prioritizes review of positive messages and images. The legal review unit also collects user emotional response data in real time and builds a system that dynamically adjusts the priority of final review. For example, it reevaluates the sections to be reviewed and updates the priority whenever the user's emotions change. This enables effective review by determining the priority of final review based on the user's emotional response.

[0066] The legal review department can compare the analysis results of the generation AI with the past judgments of legal personnel and focus on checking inconsistencies. For example, when legal personnel perform their final review, the legal review department builds a system that compares the analysis results of the generation AI with past judgments and focuses on checking inconsistencies. For example, it issues a warning if the points pointed out by the generation AI differ from the judgments of legal personnel. The legal review department also compares the analysis results of the generation AI with the past judgments of legal personnel, automatically identifying inconsistencies and focusing on checking them. For example, it prioritizes checking points that differ from the points pointed out by the generation AI based on the past judgment history. The legal review department also builds a database of past judgment history, and the generation AI learns from past judgments to improve the accuracy of its analysis from the next time onwards. For example, it improves the analysis results of the generation AI based on the past judgment history. This improves the accuracy of the review process by comparing the analysis results of the generation AI with the past judgments of legal personnel.

[0067] The legal review department can automatically present the legal basis for the revisions proposed by the generation AI, making the review process more efficient. For example, the legal review department will build a system that automatically presents the legal basis for the revisions proposed by the generation AI when a legal officer performs the final review. For example, it will display legal provisions and precedents related to the revisions. The legal review department will also make the review process more efficient for legal officers based on the legal basis for the revisions proposed by the generation AI. For example, the legal review department will quickly perform the review process while referring to the legal basis for the revisions. The legal review department will also build a legal basis database and develop a system that allows the generation AI to automatically search for and present the legal basis for the revisions. For example, it will provide legal information related to the revisions in real time. This will make the review process more efficient by automatically presenting the legal basis for the revisions proposed by the generation AI.

[0068] The Legal Review Department can cooperate with legal personnel from different jurisdictions to comprehensively assess international legal risks. For example, when legal personnel conduct final reviews, the Legal Review Department cooperates with legal personnel from different jurisdictions to build a system for comprehensively assessing international legal risks. For example, legal personnel from each country conduct the review work together. The Legal Review Department also assesses international legal risks based on feedback from legal personnel from different jurisdictions and proposes revisions. For example, it adjusts the revisions to comply with the legal regulations of each country. The Legal Review Department also builds a system for sharing information in real time with legal personnel from different jurisdictions to comprehensively assess international legal risks. For example, it shares information using online meetings and chat functions. This allows cooperation with legal personnel from different jurisdictions to comprehensively assess international legal risks.

[0069] The Legal Review Department can link the generative AI's analysis results with other legal tools to perform comprehensive legal evaluations. For example, when legal personnel perform final review, the Legal Review Department links the generative AI's analysis results with other legal tools to build a system for comprehensive legal evaluations. For example, it links with contract analysis tools and risk assessment tools. The Legal Review Department also integrates the generative AI's analysis results with other legal tools to comprehensively evaluate legal risks. For example, it evaluates legal risks based on data obtained from multiple tools and proposes revisions. The Legal Review Department also complements the generative AI's analysis results by linking them with other legal tools to improve the accuracy of legal evaluations. For example, it reevaluates the generative AI's analysis results based on the results of a contract analysis tool. In this way, linking the generative AI's analysis results with other legal tools makes comprehensive legal evaluations possible.

[0070] The legal review unit can use the emotion estimation function to evaluate the emotional impact of the promotional item after final review on the user. For example, when a legal officer performs the final review, the legal review unit uses the emotion estimation function to build a system that evaluates the emotional impact of the promotional item after final review on the user. For example, the legal review unit simulates the emotional reaction that a correction will have on the user. The legal review unit also predicts the user's emotional reaction to the promotional item after final review and proposes corrections to elicit positive emotions. For example, changing the corrections to positive expressions can improve the user's emotional reaction. The legal review unit also evaluates the emotional impact of the promotional item after final review on the user based on the emotion estimation data and selects the optimal correction. For example, it compares multiple corrections and adopts the one that elicits the most positive emotional reaction. This enables effective review by evaluating the emotional impact of the promotional item after final review on the user.

[0071] The system according to the embodiment is not limited to the above-described example, and various modifications are possible, for example, as follows.

[0072] The system for improving the efficiency of the legal review process can further include a user interface unit. The user interface unit is designed to make it easy for legal personnel to operate the system, allowing intuitive operation. For example, corrections can be easily moved using a drag-and-drop function. The user interface unit can also display a preview of the corrections in real time, allowing legal personnel to immediately check the impact of the corrections. Furthermore, the user interface unit can also be equipped with a voice input function, allowing legal personnel to issue instructions by voice. This reduces the operational burden on legal personnel and enables efficient legal review.

[0073] The promotional product analysis unit can use an emotion estimation function to estimate a user's emotions and highlight parts that are likely to evoke a positive emotional response. For example, the legal generation AI analyzes the text of a promotional product and uses the emotion estimation function to identify expressions that are likely to evoke positive emotions in the user. For example, encouraging words and positive messages are highlighted. The promotional product analysis unit also uses image analysis technology to select and highlight images that are likely to evoke positive emotions in the user. For example, images containing bright colors or smiling people are selected and used for promotional products. The promotional product analysis unit also analyzes video and audio data and uses the emotion estimation function to highlight parts that are likely to evoke positive emotions in the user. For example, it suggests creating a video that includes upbeat music and positive messages. This enables legal verification that takes user emotions into account, thereby increasing the effectiveness of eliciting positive responses.

[0074] The promotional item analysis unit may further include a natural language processing unit. The natural language processing unit analyzes the text of the promotional item and automatically detects expressions that pose legal risks. For example, it issues a warning if a specific keyword or phrase may be legally problematic. The natural language processing unit can also analyze the text of the promotional item and make suggestions to correct grammatical errors or inappropriate expressions. For example, correcting the expressions to be grammatically correct reduces legal risks. The natural language processing unit can also analyze the text of the promotional item and evaluate its readability and understandability. For example, it can make suggestions to change difficult expressions to simpler expressions. This improves the quality of the text of the promotional item and reduces legal risks.

[0075] The promotional product analysis unit can use emotion estimation to suggest revisions to sections that may evoke negative emotions in users. For example, the legal generation AI analyzes the text of promotional products and uses emotion estimation to identify expressions that may evoke negative emotions in users. For example, it detects offensive language or misleading expressions and suggests revisions. The promotional product analysis unit also uses image analysis technology to identify images that may evoke negative emotions in users and suggests alternatives. For example, it identifies images that may be offensive based on past data and suggests alternatives. The promotional product analysis unit also analyzes video and audio data and uses emotion estimation to point out sections that may evoke negative emotions in users. For example, it suggests revisions if the tone of the audio or the content of the video is inappropriate. This enables legal confirmation that takes user emotions into account, reducing the risk of causing negative reactions.

[0076] The promotional item analysis unit may further include a data mining unit. The data mining unit analyzes past data on promotional items to identify patterns of legal risk. For example, based on past data on promotional items, it extracts patterns of expressions and designs that pose a high legal risk. The data mining unit also analyzes past data on promotional items to identify trends in legal risk. For example, it identifies a trend of increasing legal risk at specific times and suggests preventive measures. The data mining unit also analyzes past data on promotional items to identify factors that cause legal risk. For example, it issues a warning if a specific factor is likely to cause legal risk. This makes it possible to predict legal risks using past data and take preventive measures.

[0077] The correction department can use the emotion estimation function to prioritize corrections based on the user's emotional response. For example, when reviewing the output results of the legal generation AI, the emotion estimation function can be used to analyze the user's emotional response and prioritize corrections to sections that evoke negative emotions. For example, offensive or misleading expressions can be corrected. The correction department can also use the emotion estimation data to emphasize sections that evoke positive emotions in users and revise the content of promotional items. For example, adding positive messages and images can improve the user's emotional response. The correction department can also collect user emotional response data in real time and build a system that dynamically adjusts the priority of corrections. For example, the corrections can be reevaluated and the priority updated whenever the user's emotions change. This enables effective corrections by prioritizing corrections based on the user's emotional response.

[0078] The correction unit may further include an automatic translation unit. The automatic translation unit automatically translates the corrections into different languages ​​to reduce international legal risks. For example, the corrections may be translated into multiple languages, such as English, French, and Chinese, and adjusted to comply with the legal regulations of each country. The automatic translation unit may also visualize the translation results to make them easier for legal personnel to review. For example, the translation results may be highlighted to visually show the impact of the corrections. The automatic translation unit may also evaluate legal risks in different languages ​​based on the translation results and suggest corrections. For example, the automatic translation unit may suggest changes to wording or design to avoid legal risks in specific languages. This reduces legal risks in different languages ​​and streamlines international legal review.

[0079] The correction department can use the emotion estimation function to predict the emotional impact that a revised promotional product will have on the user. For example, when checking the output results of the legal generation AI, a system is built that uses the emotion estimation function to predict the emotional impact that a revised promotional product will have on the user. For example, the emotional reaction that the revised parts will have on the user is simulated. The correction department also predicts the user's emotional reaction to the revised promotional product and proposes revisions to elicit positive emotions. For example, changing the revised parts to more positive expressions improves the user's emotional reaction. The correction department also evaluates the emotional impact that a revised promotional product will have on the user based on the emotion estimation data and selects the optimal revision proposal. For example, it compares multiple revision proposals and adopts the proposal that elicits the most positive emotional reaction. This enables effective revisions by predicting the emotional impact that a revised promotional product will have on the user.

[0080] The correction department can further include a cloud collaboration department. The cloud collaboration department shares the correction details on the cloud, allowing multiple legal staff to review them simultaneously. For example, the correction details can be uploaded to the cloud, and legal staff can review the correction details in real time and add comments. The cloud collaboration department also performs version control of the correction details, making it easy to refer to past revision history. For example, the change history of the correction details can be managed on the cloud, making it possible to revert to a previous version as needed. Furthermore, by sharing the correction details on the cloud, the cloud collaboration department allows legal staff to review them regardless of location. For example, review work can be performed efficiently even in a remote work environment. This makes the sharing and management of correction details more efficient by utilizing cloud collaboration.

[0081] The correction unit can further include an AI learning unit. The AI ​​learning unit learns the correction content and improves the accuracy of future correction suggestions. For example, it automatically suggests similar corrections based on past correction content. The AI ​​learning unit also evaluates the effectiveness of the correction content and improves the accuracy of future correction suggestions. For example, it collects performance data on promotional products after correction and evaluates the effectiveness of the corrections. The AI ​​learning unit also learns patterns of correction content and improves the accuracy of future correction suggestions. For example, if a specific pattern is highly effective in reducing legal risk, it will preferentially suggest that pattern. This makes it possible to utilize AI learning to improve the accuracy of correction suggestions and enable efficient legal confirmation.

[0082] The processing flow of the second embodiment will be briefly explained below.

[0083] Step 1: The Promotional Products Analysis Department analyzes the contents of the promotional products. Specifically, the department analyzes the design, wording, and images used in the promotional products as input information, and compares them with a database of past cases to identify any legal concerns. Step 2: The Legal Concerns Identification Department identifies legal concerns based on the content analyzed by the Promotional Products Analysis Department, making specific recommendations such as "This image may be a copyright infringement" or "This statement is misleading." Step 3: The Correction Department corrects the legal concerns raised by the Legal Concerns Raising Department, for example by replacing images that may be infringing copyrights or correcting misleading statements. Step 4: The Legal Review Department has a legal officer review the content of the promotional items revised by the Revision Department. For example, the revised promotional items are presented to the legal officer for final legal review.

[0084] 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.

[0085] 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.

[0086] 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.

[0087] [Second embodiment] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0088] 3, the data processing system 210 includes the data processing device 12 and smart glasses 214. An example of the data processing device 12 is a server.

[0089] 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.

[0090] 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.

[0091] 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.

[0092] 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).

[0093] 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.

[0094] 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.

[0095] 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.

[0096] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0097] 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. The smart glasses 214 also have a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can perform processing similar to that of the specific processing unit 290 using these models.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] 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.

[0102] [Third embodiment] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] 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.

[0107] 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).

[0108] 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.

[0109] Fig. 6 shows an example of the main functions of the data processing device 12 and the headset type terminal 314. As shown in Fig. 6, in the data processing device 12, a specific process is performed by the processor 28. A specific process program 56 is stored in the storage 32.

[0110] 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.

[0111] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0112] In the headset type terminal 314, 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 headset type terminal 314 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0113] 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.

[0114] 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.

[0115] 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.

[0116] 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.

[0117] [Fourth embodiment] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[0118] 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.

[0119] 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.

[0120] 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.

[0121] 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.

[0122] 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).

[0123] 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.

[0124] 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.

[0125] 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.

[0126] 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.

[0127] 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 a user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion. The emotion estimation function (emotion identification function) using the emotion identification model 59 performs various estimations and predictions regarding the user's emotion, including estimation and prediction of the user's emotion, but is not limited to these examples. Furthermore, the estimation and prediction of emotion also includes, for example, emotion analysis.

[0128] In the robot 414, 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. The robot 414 has a data generation model and an emotion identification model similar to the data generation model 58 and the emotion identification model 59, and can also perform processing similar to that of the specific processing unit 290 using these models.

[0129] 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.

[0130] 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.

[0131] 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.

[0132] 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.

[0133] 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.

[0134] 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.

[0135] 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.

[0136] 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).

[0137] 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.

[0138] 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."

[0139] 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.

[0140] 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.

[0141] 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.

[0142] 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.

[0143] 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.

[0144] The hardware resource for executing a specific process can be any of the following types of processors: A processor, for example, is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. A processor also includes a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[0145] 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.

[0146] 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.

[0147] 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.

[0148] 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.

[0149] 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.

[0150] 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]

[0151] 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. Equipped with legal generation AI, The legal generation AI is a promotional item analysis unit that analyzes the contents of promotional items; a legal concern indicating unit that indicates legal concerns based on the content analyzed by the sales promotion product analysis unit; a correction unit that corrects the legal concerns pointed out by the legal concern pointing unit; a legal confirmation unit in which a legal officer confirms the content of the promotional item corrected by the correction unit. A system characterized by:

2. The promotional item analysis unit Estimate user emotions and point out areas that trigger negative emotional responses 2. The system of claim 1.

3. The promotional item analysis unit Review past legal precedents or court records to identify areas of legal concern 2. The system of claim 1.

4. The promotional item analysis unit Identify industry-specific legal risks based on legal regulations in different industries 2. The system of claim 1.

5. The promotional item analysis unit Include analysis of audio or video data to identify legal risks associated with multimedia content 2. The system of claim 1.

Images