System

Abstract

A system is provided.SOLUTION: The system includes a reception means for receiving a video to be photographed, a generation means for generating a frame from the video received by the reception means, an analysis means for analyzing the generated frame and performing determination on the basis of a prescribed reference, a generation means for generating a report based on a determination result, and a notification means for notifying the generated report.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 cleanliness inspections and countermeasures for POP violations were mainly manual, and violations were often overlooked due to store staff carelessness or human error. Furthermore, there were limitations to the efficiency and accuracy of inspections, making it difficult to respond quickly when violations were discovered. Furthermore, the burden on store staff to check cleanliness themselves was heavy, reducing the efficiency of overall store operations. [Means for solving the problem]

[0005] The present invention provides a system for automating cleanliness self-checks using video footage taken by store staff. The system includes the following means.

[0006] 1. A receiving means for receiving the captured image.

[0007] 2. A generating means for generating frames from the video received by the receiving means.

[0008] 3. An analysis means for analyzing the generated frames and making a judgment based on specified criteria.

[0009] 4. A generating means for generating a report based on the judgment results.

[0010] 5. Notification means for notifying the generated report.

[0011] This system allows store crew to automatically perform cleanliness checks based on the video footage they have taken, and if any violations are detected, they can immediately receive instructions for correction. The analysis means detects cleanliness violations in specific areas based on the analysis results and includes details of the relevant areas in a report. The receiving means receives the video via a mobile device operated by the user, and the analysis means and generation means operate on a server. The notification means displays the contents of the report on the user's device and includes instructions to correct any cleanliness violations. The receiving means then receives video footage taken by the user again, and the analysis means analyzes it again to confirm the corrections. This significantly improves the efficiency and accuracy of cleanliness management and maximizes the efficiency of store operations.

[0012] The "receiving means" is a device or software that has the function of receiving the video captured by the user and saving it in a format that can be processed within the system.

[0013] The "generating means" is a device or software that divides the video received by the receiving means into frames and generates each frame.

[0014] The "analysis means" is a device or software that analyzes the generated frames and determines whether or not there is a violation based on pre-set cleanliness criteria.

[0015] The "notification means" is a device or software that notifies the user of a report generated based on the determination results of the analysis means.

[0016] A "report" is a document generated by the analysis means that shows the results of frame analysis and details of the violations.

[0017] A "mobile terminal" is a portable electronic device, such as a smartphone or tablet, that is operated by a user.

[0018] A "server" is a remotely located computer system for operating the analysis means and generation means.

[0019] "Cleanliness standards" are defined standards for evaluating the cleanliness and proper layout of the interior and exterior of a store. [Brief explanation of the drawings]

[0020] [Figure 1] 1 is a conceptual diagram showing an example of the configuration of a data processing system according to a first embodiment. [Figure 2] 1 is a conceptual diagram showing an example of main functions of a data processing device and a smart device according to a first embodiment. [Figure 3] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a second embodiment. [Figure 4] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and smart glasses according to a second embodiment. [Figure 5] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a third embodiment. [Figure 6] FIG. 11 is a conceptual diagram showing an example of main functions of a data processing device and a headset-type terminal according to a third embodiment. [Figure 7] FIG. 10 is a conceptual diagram showing an example of the configuration of a data processing system according to a fourth embodiment. [Figure 8] FIG. 10 is a conceptual diagram showing an example of main functions of a data processing device and a robot according to a fourth embodiment. [Figure 9] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 10] 1 shows an emotion map onto which multiple emotions are mapped. [Figure 11] FIG. 3 is a sequence diagram showing a processing flow of the data processing system according to the first embodiment. [Figure 12] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 1. [Figure 13] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system according to the second embodiment when an emotion engine is combined. [Figure 14] FIG. 10 is a sequence diagram showing the flow of processing in the data processing system in Application Example 2 when an emotion engine is combined. DETAILED DESCRIPTION OF THE INVENTION

[0021] 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.

[0022] First, the terms used in the following description will be explained.

[0023] In the following embodiments, a coded processor (hereinafter simply referred to as a "processor") may be a single arithmetic device or a combination of multiple arithmetic devices. Furthermore, a processor may be a single type of arithmetic device or a combination of multiple types of arithmetic devices. Examples of arithmetic devices include a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), a GPGPU (General-Purpose computing on Graphics Processing Units), and an APU (Accelerated Processing Unit).

[0024] 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.

[0025] 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.

[0026] In the following embodiments, a communication I / F (Interface) with a symbol is an interface including a communication processor, an antenna, etc. The communication I / F controls communication between multiple computers. Examples of communication standards applied to the communication I / F include wireless communication standards including 5G (5th Generation Mobile Communication System), Wi-Fi (registered trademark), Bluetooth (registered trademark), etc.

[0027] 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."

[0028] [First embodiment]

[0029] FIG. 1 shows an example of the configuration of a data processing system 10 according to the first embodiment.

[0030] 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.

[0031] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0032] 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.

[0033] The reception device 38 includes a touch panel 38A, a microphone 38B, and the like, and receives user input. The touch panel 38A detects contact with an indicator (for example, a pen or a finger) to receive user input by the touch of the indicator. The microphone 38B detects the user's voice to receive user input by voice. The control unit 46A transmits data indicating the user input received by the touch panel 38A and the microphone 38B to the data processing device 12. In the data processing device 12, the specific processing unit 290 acquires the data indicating the user input.

[0034] The output device 40 includes a display 40A and a speaker 40B, and presents data to the user 20 by outputting the data in a form of expression that the user 20 can perceive (for example, audio and / or text). The display 40A displays visible information such as text and images in accordance with instructions from the processor 46. The speaker 40B outputs audio in accordance with instructions from the processor 46. The camera 42 is a compact digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor.

[0035] 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.

[0036] FIG. 2 shows an example of the main functions of the data processing device 12 and the smart device 14.

[0037] 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.

[0038] 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.

[0039] In the smart device 14, the processor 46 performs the reception output process. The storage 50 stores a reception output program 60. The reception output program 60 is used in conjunction with the specific processing program 56 by the data processing system 10. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0040] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0041] The cleanliness self-check system of the present invention uses video footage taken by store staff to automatically analyze the cleanliness inside and outside a store, identify any violations, and prompt a prompt response. Hereinafter, an embodiment of the present invention will be described.

[0042] System Configuration

[0043] This system mainly consists of the following components:

[0044] 1. User's device

[0045] Users (store crew) use mobile devices such as smartphones and tablets to shoot and upload videos.

[0046] 2. Server

[0047] The server includes a receiving means, a generating means, an analyzing means, and a notifying means, and receives and analyzes the video, and generates and notifies the report. The program running on the server functions as follows.

[0048] Program processing

[0049] Video reception

[0050] Users use their mobile devices to record video of the cleanliness conditions inside and outside the store. The recorded video is uploaded to the server via the application. The server receives the video via a receiving means and stores it.

[0051] Examples:

[0052] Users use their device to take pictures of the inside and outside of the store in the morning under the title "Comprehensive Store Cleanliness Check," and then upload the footage to the server via the app.

[0053] Frame Generation

[0054] The server divides the received video into frames, and the generating means converts the video into individual frames and prepares them for analysis.

[0055] Examples:

[0056] The server divides the five-minute video into 300 frames and stores each frame.

[0057] Video analysis

[0058] The server's analysis means sequentially analyzes each frame and determines whether there is a violation based on the cleanliness criteria. The analysis means checks each frame using the pre-defined cleanliness criteria to detect anomalies.

[0059] Examples:

[0060] At frame 123, it detects that there is trash under the front desk.

[0061] Generate reports

[0062] The analysis tool generates a report based on the results of the analysis, which includes the location of the violation and its details.

[0063] Examples:

[0064] A report is generated stating, "Garbage has been detected under the front desk" or "Unnecessary POPs have been placed in a corner of the warehouse."

[0065] Notifications and Feedback

[0066] The server sends the generated report to the user's terminal using a notification means, and the user receives the report and makes any necessary corrections.

[0067] Examples:

[0068] The user checks the report on the terminal and decides on a countermeasure, such as "I will clean up the trash under the front desk."

[0069] Reconfirmation

[0070] After completing the corrections, the user shoots the video again and uploads it to the server, which then analyzes it again using the receiving means and analyzing means to confirm that the corrections have been made appropriately.

[0071] Examples:

[0072] After the user cleans up the dust, they record the corrected state on video again and upload it to the server, where it analyzes it again and notifies them that the problem has been solved.

[0073] In this way, the system automates cleanliness self-checks and achieves efficient and highly accurate management.

[0074] The processing flow will be explained below.

[0075] Step 1:

[0076] The user uses the device to capture video inside and outside the store. The user launches the application, presses the record button, and captures the area to be checked.

[0077] Step 2:

[0078] The user uploads the video they have taken to the server. The user presses the "Upload" button in the application, selects the video file, and sends it to the server.

[0079] Step 3:

[0080] The server receives and stores the uploaded video. The receiving means receives the video and stores it in a dedicated folder in the server.

[0081] Step 4:

[0082] The server divides the received video into frames. The generation means divides the video into frames at regular intervals (for example, every second) and saves each frame as an image file.

[0083] Step 5:

[0084] The server inputs each frame into the generation AI, and the analysis means passes each generated frame to the AI ​​model in sequence, which analyzes it based on cleanliness criteria.

[0085] Step 6:

[0086] The generator AI analyzes each frame to determine whether there are any cleanliness violations. The AI ​​model checks each element within the frame to detect anomalies such as dust or illegal pop-ups.

[0087] Step 7:

[0088] The server receives the analysis results. The analysis means receives the result data from the generation AI and records the violations and their details.

[0089] Step 8:

[0090] The server generates a report based on the analysis results. The generation method compiles a list of the identified violations and creates a report that lists the specific issues and how to correct them.

[0091] Step 9:

[0092] The server notifies the user of the report, and the notification means transmits the generated report to the user's terminal and instructs the user to make corrections.

[0093] Step 10:

[0094] The user checks the report and corrects any violations that are reported. Based on the report on the terminal, the user can take appropriate action to resolve any cleanliness violations inside and outside the store.

[0095] Step 11:

[0096] The user shoots the video again and uploads the corrected state to the server. The user then starts the application again, shoots the checked area again, and sends it to the server.

[0097] Step 12:

[0098] The server receives, stores, and analyzes the re-uploaded video. It reprocesses the video using the same receiving, generating, and analyzing means as the first time, and verifies that the corrections were made appropriately.

[0099] Step 13:

[0100] The server notifies the user based on the reanalysis results. If the corrections are appropriate based on the analysis results, the server notifies the user of the completion, and if additional corrections are required, the server sends instructions to the user.

[0101] This step allows store crews to efficiently automate cleanliness checks and instantly correct any violations.

[0102] Example 1

[0103] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0104] The current mainstream method of cleanliness management involves store staff manually checking the inside and outside of the store, identifying and reporting any problems. However, this method is time-consuming and prone to human error. Furthermore, delayed feedback can mean that problems are left unaddressed for long periods of time when a prompt response is required. To solve these issues, a system that can efficiently and accurately perform cleanliness checks is needed.

[0105] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0106] In this invention, the server includes a receiving means for receiving the captured video, a generating means for generating frames from the video received by the receiving means, an analyzing means for analyzing the generated frames and making a judgment based on specified criteria, a report generating means for generating a report based on the judgment result, a notifying means for notifying the generated report, and a reanalysis means for reanalyzing the re-captured video and notifying the reanalysis result. This not only automates the cleanliness check but also enables quick and accurate feedback.

[0107] "Receiving means" refers to a device or system that has the function of receiving captured images.

[0108] The "generating means" refers to a device or system that has the function of converting the video received by the receiving means into individual frames for analysis.

[0109] "Analysis means" refers to a device or system that has the function of checking the generated frames based on specified cleanliness standards and determining whether or not there are any violations.

[0110] The "report generation means" refers to a device or system that has the function of creating a report detailing the violation based on the determination results from the analysis means.

[0111] The "notification means" refers to a device or system that has the function of notifying the user of the generated report.

[0112] "Reanalysis means" refers to a device or system that has the function of reanalyzing the re-shot video after correction and notifying the results.

[0113] The cleanliness self-check system of the present invention is a system in which a server analyzes video taken by a user, automatically checks the cleanliness inside and outside a store, identifies any violations, and prompts prompt action. A specific embodiment of this system is described below.

[0114] The system mainly consists of the following components:

[0115] 1. User's device

[0116] Users use mobile devices such as smartphones and tablets to capture and upload videos.

[0117] 2. Server

[0118] The server receives and analyzes the video, generates and notifies reports, and has the functions of a receiving means, a generating means, an analyzing means, a report generating means, a notifying means, and a re-analysis means.

[0119] In terms of specific hardware, the user's device can be the latest smartphone (e.g., an Android (registered trademark) model or an iPhone (registered trademark)). The server is operated on a high-performance cloud server (e.g., AWS (registered trademark) or Azure (registered trademark)), and the analysis method uses AI models and image analysis libraries such as Tensorflow (registered trademark) and OpenCV.

[0120] As a specific example, the system operates in the following manner.

[0121] 1. Filming and uploading the footage

[0122] Users use their mobile devices to record video of the cleanliness conditions inside and outside the store, and once the recording is complete, upload the video to the server through the application.

[0123] Specific operation examples:

[0124] The user launches the app, selects "New Cleanliness Check," takes photos of the inside and outside of the store, and presses the "Upload Video" button.

[0125] 2. Receiving and storing video

[0126] The server receives the uploaded video using the receiving means, and the video is stored in the server's storage.

[0127] Specific behavior:

[0128] The server displays "Receiving video data," and when reception is complete, records "Data saving completed."

[0129] 3. Video frame generation

[0130] The server uses a generation means to divide the stored video into frames, and prepares for analysis.

[0131] Specific behavior:

[0132] The server divides the five minutes of footage into 60 frames per second, generating and storing a total of 300 frames.

[0133] 4. Frame Analysis

[0134] The server's analysis means sequentially analyzes each frame and determines whether there is a violation based on the cleanliness criteria.

[0135] Specific behavior:

[0136] The server uses an AI model (e.g., TensorFlow) to detect debris and clutter in each frame and flags the frame if there is an anomaly.

[0137] 5. Generate reports

[0138] The server's report generation means generates a report based on the analysis results, which includes the violations and their details.

[0139] Specific behavior:

[0140] A report will be generated in PDF format stating, "Debris was detected under the front desk," along with an image of the frame in question.

[0141] 6. Notifications and Feedback

[0142] The report is sent to the user's terminal using a notification means, where the user can review the report and make any necessary corrections.

[0143] Specific operation examples:

[0144] The user checks the report on the terminal and provides feedback such as, "I will clean up the trash under the front desk."

[0145] 7. Re-imaging and re-analysis

[0146] After completing the corrections, the user shoots the video again and uploads it to the server, which then reanalyzes it to verify that the corrections were made properly.

[0147] Specific operation examples:

[0148] The user cleans up the junk and uploads the footage again. The server re-analyzes it and notifies the user that the problem has been resolved.

[0149] Example prompt sentence:

[0150] "A comprehensive cleanliness check of the store revealed trash under the front desk. Please clean up the trash, retake footage and report the results."

[0151] In this way, the system automates the cleanliness check process and provides fast and accurate feedback, allowing for effective management of store cleanliness.

[0152] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0153] Step 1:

[0154] Filming and uploading footage

[0155] Users use their mobile devices to record video of the cleanliness conditions inside and outside the store, and once the recording is complete, upload the video to the server via a dedicated application.

[0156] Input: Video file (recording data)

[0157] Output: Upload video files to the server

[0158] Specific behavior:

[0159] The user launches the app, selects "New Cleanliness Check" and starts recording. After recording, they press the "Upload Video" button to send the video to the server.

[0160] Step 2:

[0161] Receiving and storing video

[0162] The server receives the uploaded video using the receiving means, and the video is stored in the server's storage.

[0163] Input: Uploaded video file

[0164] Output: Video data stored on the server

[0165] Specific behavior:

[0166] The server receives the video data sent from the app and displays "Receiving video data." After reception is complete, it records "Data saving completed."

[0167] Step 3:

[0168] Video frame generation

[0169] The server uses a generation method to divide the stored video into frames, which are then ready for analysis.

[0170] Input: Stored video data

[0171] Output: Image data divided into frames

[0172] Specific behavior:

[0173] The server splits the five-minute video into 60 frames per second, generating a total of 300 frames, each stored in a dedicated folder.

[0174] Step 4:

[0175] Frame Analysis

[0176] The server's analysis means sequentially analyzes each frame and determines whether there is a violation based on the cleanliness criteria.

[0177] Input: Image data divided into frames

[0178] Output: Analysis results for each frame (whether or not there is a violation)

[0179] Specific behavior:

[0180] The server uses an AI model (e.g., TensorFlow) to detect debris and clutter in each frame and flags the frame if there is an anomaly.

[0181] Step 5:

[0182] Generate reports

[0183] The server's report generation means generates a report based on the analysis results, which includes the violation location and its details.

[0184] Input: Analysis results

[0185] Output: Cleanliness Violation Report

[0186] Specific behavior:

[0187] The server generates a report in PDF format stating, "Debris was detected under the front desk," along with an image of the frame in question.

[0188] Step 6:

[0189] Notifications and Feedback

[0190] The server sends the generated report to the user's terminal using a notification means, and the user receives the report and takes appropriate measures.

[0191] Input: Cleanliness Violation Report

[0192] Output: Report notification to user, feedback record

[0193] Specific behavior:

[0194] The server sends the report to the user's device via email or push notification. The user checks the report and provides feedback such as, "I will clean up the trash under the front desk."

[0195] Step 7:

[0196] Re-imaging and re-analysis

[0197] After the user has completed the corrections, they shoot the video again and upload it to the server, where it will be reanalyzed to confirm that the corrections were made properly.

[0198] Input: Corrected video data

[0199] Output: Reanalysis results, final notification

[0200] Specific behavior:

[0201] After making the corrections, the user selects "Check after corrections" to shoot the video again and upload it to the server. The server then reanalyzes the video and notifies the user that the problem has been resolved.

[0202] (Application example 1)

[0203] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0204] To maintain the cleanliness of a store, it is important to regularly check the situation, quickly identify problem areas, and take measures. However, conventional methods for cleanliness checks are inefficient and the reliability of the check results is limited. In addition, there is often no system in place for store staff to voluntarily report problem areas, and even if a problem has been corrected, there is a lack of means to reconfirm its appropriateness. To solve these issues, an automated cleanliness check system is needed.

[0205] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0206] In this invention, the server includes a receiving means for receiving the captured video, a generating means for generating frames from the video received by the receiving means, an analyzing means for analyzing the generated frames and making a judgment based on specified criteria, a generating means for generating a report based on the judgment results, a notifying means for notifying the generated report, and a reconfirming means for allowing the user to recapture and upload video. This enables automation of store cleanliness checks and efficient identification, correction, and reconfirmation of violations.

[0207] 1. "Receiving means" refers to a means for receiving images taken by a user inside and outside a store.

[0208] 2. "Generation means" means a means for generating frames from the video received by the reception means and preparing them for analysis.

[0209] 3. "Analysis means" refers to a means for determining violations based on the generated frames using the specified cleanliness standards.

[0210] 4. "Report generation means" means a means for generating a report based on the results of the analysis means.

[0211] 5. "Notification means" means a means for notifying the user of the generated report.

[0212] 6. "Reconfirmation means" refers to a means for a user to confirm corrections by taking a photo of the corrected state again and uploading it.

[0213] 7. "User" refers to a store crew member who uses the system to conduct cleanliness checks.

[0214] 8. "Mobile device" refers to a mobile device operated by a user, such as a smartphone or tablet.

[0215] 9. "Server" means a computer system that performs the functions of receiving video, generating frames, analyzing, generating reports, and notifying.

[0216] 10. "Cleanliness Standards" means the prescribed standards established to judge the cleanliness of a store.

[0217] The system embodying the present invention has a program for effectively managing the cleanliness of a store. The components of the system and their operation will be described below.

[0218] System Configuration

[0219] The system mainly consists of the following components:

[0220] 1. The user's mobile device

[0221] Users take and upload videos using their smartphones or tablets.

[0222] 2. Server

[0223] The server includes a receiving means, a generating means, an analyzing means, a report generating means, a notifying means, and a reconfirming means, and controls the entire process.

[0224] System Operation

[0225] Video reception and frame generation

[0226] The user's mobile device records the cleanliness status inside and outside the store as video. This video is uploaded to the server using the receiving means. The server divides the received video into frames and prepares them for analysis using the frame generating means.

[0227] Video analysis

[0228] The server's analysis means analyzes each frame based on cleanliness standards and identifies violations. The analysis means uses OpenCV, an image processing library, to detect abnormalities within the frames.

[0229] Report generation and notification

[0230] Based on the results of the analysis, a report is automatically generated by the report generation means. The report includes details of the identified cleanliness violations. The generated report is sent to the user's mobile device using the notification means.

[0231] Corrections and reconfirmation

[0232] Based on the report, the user corrects any cleanliness violations in the store. After the corrections are complete, the user shoots the video again and uploads it to the server via a reconfirmation tool. The server then analyzes the frames again to confirm that the corrections have been made properly.

[0233] Hardware and software used

[0234] Hardware: Smartphones, servers

[0235] Software: Flask (web framework), OpenCV (image processing library)

[0236] Specific examples

[0237] A user takes a video of the area around the trash can in the store with their smartphone and uploads the video to the server via the app. The server analyzes the video and generates a report stating that "the trash can is overflowing" and notifies the user. After the user has cleared the trash, they can take another video and upload it to the server, and receive a notification that "the problem has been resolved."

[0238] Prompt Sentence Examples

[0239] Please conduct a cleanliness check around the trash cans in your store. Upload the video and have it analyzed on the server. If there are any violations, a report will be automatically generated and notified. Please take appropriate action based on the cleanliness standards and record the video again to double-check.

[0240] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0241] Step 1:

[0242] The user takes a video of the cleanliness situation inside and outside the store using a smartphone. The input here is the video file taken by the user, and the output is the video file that will be uploaded to the server.

[0243] Step 2:

[0244] The terminal uploads the captured video file to the server using the receiving means. The path to the video file is input to the terminal, and the data is sent to the server. The output is a video file saved on the server.

[0245] Step 3:

[0246] The server divides the video uploaded by the receiving means into frames. Here, the video file is the input, and the divided multiple frame images are the output. Specifically, the OpenCV library is used to break down the video into frames, and each frame is saved in memory.

[0247] Step 4:

[0248] The server's analysis means analyzes the generated frames and identifies abnormalities based on the cleanliness criteria. The input to this step is the frame images, and the output is the analysis result of whether each frame meets the cleanliness criteria. For example, OpenCV is used to determine whether dust is present in the image.

[0249] Step 5:

[0250] The server creates a report based on the analysis results using a report generation means. The input here is the analysis results, and the output is a report file. The report includes details of the violations.

[0251] Step 6:

[0252] The server sends the generated report to the user's smartphone via a notification method. The input of this step is the report file, and the output is the process of notifying the user's device. Specifically, the report is sent using email or the app's notification function.

[0253] Step 7:

[0254] The user checks the report and corrects any cleanliness violations that are pointed out. The input here is the report content, and the output is the state of the store after the corrections are made.

[0255] Step 8:

[0256] The user then takes another video of the corrected state with their smartphone and uploads the video to the server. The input here is the newly taken video file, and the output is the corrected video file sent to the server.

[0257] Step 9:

[0258] The server splits the received corrected video into frames again and rechecks it using an analysis method. The input here is the corrected video file, and the output is the result of the reanalysis of the frames. It is again determined whether the corrections were made properly.

[0259] Step 10:

[0260] The server then notifies the user based on the final analysis result whether the corrections were successful. The input to this step is the reanalysis result, and the output is a notification that "corrections are complete" or "recorrections are required."

[0261] Through these steps, the system will be able to automate and efficiently manage store cleanliness checks.

[0262] Furthermore, an emotion engine that estimates the user's emotion may be combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59 and perform identification processing using the user's emotion.

[0263] The cleanliness self-check system of the present invention automatically analyzes the cleanliness status based on video footage taken by a user (e.g., a store crew member) and identifies any violations. By combining this system with an emotion engine, it is possible to recognize the user's emotional state and provide feedback accordingly. Detailed embodiments of the present invention are described below.

[0264] System Configuration

[0265] This system consists of the following main components:

[0266] 1. User's device

[0267] A mobile device such as a smartphone or tablet operated by a user, used to capture and upload video and receive notifications.

[0268] 2. Server

[0269] The server includes the following means:

[0270] Receiving means: Receives videos uploaded by users.

[0271] Generation method: Divide the video into frames.

[0272] Analysis method: Analyze the frame to determine if there are any cleanliness violations.

[0273] Notification method: A report is generated based on the judgment results and notified to the user.

[0274] Emotion engine: Recognizes user emotions and adjusts feedback accordingly.

[0275] Program processing

[0276] Video reception

[0277] The user uses the device to record the cleanliness status inside and outside the store. The recorded video is uploaded to the server via the application. The server's receiving means receives and stores the video.

[0278] Examples:

[0279] Users take videos on their devices titled "Store Afternoon Cleanliness Check" and upload them to the server via the app.

[0280] Frame Generation

[0281] The server divides the received video into frames, and the generating means generates frames at regular intervals per second and converts them into data for analysis.

[0282] Examples:

[0283] The server divides the three-minute video into 180 frames and saves each frame as an image file.

[0284] Video analysis

[0285] The server's analysis means inputs each frame into the generation AI, which determines whether or not there is a violation based on the cleanliness standards. The results are recorded in detail, detailing which areas have violations and what kind of violations have occurred.

[0286] Examples:

[0287] At frame 45, it detects that there is trash on the table in the eating area.

[0288] Emotion recognition

[0289] The emotion engine recognizes the user's emotions when shooting video. The emotion engine analyzes the user's emotions from their facial expressions and tone of voice, and sends that information to the analysis means.

[0290] Examples:

[0291] If the user is feeling frustrated or tired while shooting a video, the emotion engine will detect it.

[0292] Generate reports

[0293] The analysis means generates a report based on the information from the emotion engine, which includes details of the violation and feedback that takes into account the user's emotions.

[0294] Examples:

[0295] A report will be generated such as, "Garbage has been detected on the table in the dining area. Thank you for your hard work, please clean this up."

[0296] Notifications and Feedback

[0297] The server's notification means sends the report to the user's terminal, where the user can check the report and make any necessary corrections.

[0298] Examples:

[0299] The user checks the report on their device and decides on a countermeasure, such as "cleaning up the trash on the tables in the dining area."

[0300] Reconfirmation

[0301] After completing the corrections, the user shoots the video again and uploads it to the server, which then analyzes the video again in the same way to confirm that the corrections were made properly.

[0302] Examples:

[0303] After the user cleans up the dust, they record the corrected state on video again and upload it to the server, where it analyzes it again and notifies them that the problem has been solved.

[0304] This system allows users to efficiently perform cleanliness checks and quickly correct any violations. In addition, the introduction of an emotion engine provides feedback that takes into account the user's emotions, reducing the burden of the work.

[0305] The processing flow will be explained below.

[0306] Step 1:

[0307] The user uses the device to take video of the inside and outside of the store. The user launches the dedicated application and presses the capture button to capture the area to be checked.

[0308] Step 2:

[0309] The user uploads the video they have taken to the server. The user presses the "Upload" button in the application to send the video file to the server.

[0310] Step 3:

[0311] The server receives and stores the uploaded video. The receiving means receives the video file and stores it in a specific folder in the server.

[0312] Step 4:

[0313] The server divides the received video into frames. The generation means divides the video into frames at regular intervals (for example, every second) and saves each frame as an image file.

[0314] Step 5:

[0315] The server inputs each frame into the analysis AI, which then passes each generated frame to the AI ​​model in turn, which analyzes it based on cleanliness criteria.

[0316] Step 6:

[0317] The generator AI analyzes each frame to determine whether there are any cleanliness violations. The AI ​​model checks each element within the frame to detect anomalies such as dust or illegal pop-ups.

[0318] Step 7:

[0319] The server also sends the analysis results to the emotion engine, which analyzes the user's emotions. The emotion engine analyzes the user's facial expressions and tone of voice to recognize their emotions.

[0320] Step 8:

[0321] The server generates a report based on the analysis results and emotional information, which includes any cleanliness violations and feedback that takes the user's emotions into consideration.

[0322] Step 9:

[0323] The server notifies the user of the generated report, and the notification means transmits the contents of the report to the user's terminal and instructs the user to make corrections.

[0324] Step 10:

[0325] The user checks the report and corrects any violations that are reported. Based on the report on the terminal, the user can take appropriate action to resolve any cleanliness violations inside and outside the store.

[0326] Step 11:

[0327] The user shoots the video again and uploads the corrected state to the server. The user then starts the application again, shoots the checked area again, and sends it to the server.

[0328] Step 12:

[0329] The server receives, stores, and analyzes the re-uploaded video. It reprocesses the video using the same receiving, generating, and analyzing means as the first time, and verifies that the corrections were made appropriately.

[0330] Step 13:

[0331] The server notifies the user based on the results of the reanalysis. It checks whether the corrections were made appropriately based on the analysis results, and if the problem has been resolved, it sends a final notification to the user, and if additional corrections are required, it sends instructions to the user.

[0332] Example 2

[0333] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0334] Conventional cleanliness check systems allow users to simply check the results of their cleaning, making it difficult to efficiently check and improve. Furthermore, they do not provide feedback that takes into account the user's emotions or fatigue, which increases the burden of the work. There is a need for a system that recognizes the user's emotional state in real time and provides feedback that takes those emotions into consideration, thereby realizing efficient and less burdensome cleanliness checks.

[0335] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0336] In this invention, the server includes receiving means for receiving the captured video, generating means for generating frames from the video received by the receiving means, analyzing means for analyzing the generated frames and making a judgment based on specified criteria, generating means for generating a report based on the judgment results, notifying means for notifying the generated report, emotion recognition means for recognizing the emotion of the user recording the video, and feedback means for adjusting the feedback content based on emotion data recognized by the emotion recognition means. This makes it possible to efficiently identify violations and provide feedback that takes the user's emotions into consideration.

[0337] The "receiving means" is a function for receiving video data uploaded to the server from the user's mobile terminal.

[0338] The "generating means" is a function that generates frames from the video data received by the receiving means and converts the frames into a format suitable for analysis.

[0339] The "analysis means" is a function that inputs the generated frame into the generation AI model and determines whether or not there is a violation based on cleanliness standards.

[0340] The "report generation means" is a function that generates a document to report the violation location and its details to the user based on the judgment results obtained by the analysis means.

[0341] The "notification means" is a function that sends the generated report to the user's mobile terminal and notifies the user.

[0342] The "emotion recognition means" is a function for recognizing the user's emotional state during video shooting from facial expressions and tone of voice.

[0343] The "feedback means" is a function that adjusts the contents of reports and notifications in a way that takes into consideration the user's emotions, based on the emotion data recognized by the emotion recognition means.

[0344] The cleanliness self-check system of the present invention automatically analyzes the cleanliness status based on the video taken by the user and identifies any violations. In addition, by combining it with an emotion engine, it is possible to recognize the user's emotional state and provide feedback that takes those emotions into consideration.

[0345] System Configuration

[0346] This system consists of the following main components:

[0347] 1. User's device

[0348] A mobile device such as a smartphone or tablet operated by the user, which is used to capture and upload video and receive notifications of analysis results.

[0349] 2. Server

[0350] The server includes the following means:

[0351] Receiving means: A function to receive videos uploaded by users.

[0352] Generation method: A function that generates frames from received video.

[0353] Analysis method: The generated frames are analyzed to determine whether cleanliness violations exist. This uses a generative AI model.

[0354] Report generation means: A function to generate a report based on the judgment results.

[0355] Notification method: A function to send the generated report to the user's terminal.

[0356] Emotion recognition: A function that recognizes the emotions of the user when recording video. It analyzes facial expressions and tone of voice.

[0357] Feedback means: A function that adjusts the feedback content based on emotional data from the emotion recognition means.

[0358] Filming and uploading footage

[0359] Users use their mobile devices to record video of the cleanliness status inside and outside the store. The video is then uploaded to the server via a dedicated application. For example, a user can record a video of an "afternoon cleanliness check" and press the send button on the application to upload the video data to the server.

[0360] Video reception, frame generation and analysis

[0361] The server's receiving means receives and saves the uploaded video. Next, the server's generating means divides the video into frames. For example, a three-minute video is divided into frames every second, and all of the frames are saved as JPEG image files. The server's analyzing means inputs the generated frames into a generative AI model and analyzes each frame based on cleanliness standards. It determines whether or not there is a cleanliness violation and records the violation in detail. For example, if garbage is detected on a table in the eating and drinking area in frame 45, the result is recorded on the table.

[0362] Emotional Recognition and Feedback

[0363] The emotion recognition means analyzes the user's emotions while shooting video. It detects the user's emotions from facial expressions and tone of voice and sends that information to the server. For example, if the user expresses fatigue while shooting, the emotion recognition means will determine that the user is "feeling tired." The feedback means adjusts the feedback content based on the emotional data. For example, it provides feedback in the form of "Thank you for your hard work. Please clean this area."

[0364] Report generation and notification

[0365] The report generation means generates a report based on the judgment result obtained by the analysis means and the information from the emotion recognition means. The generated report is sent to the user's mobile device by the notification means. The user checks the report and makes any necessary corrections. For example, the user may decide to "clean up the trash on the tables in the dining area" and then carry out the cleaning.

[0366] Hardware and software used

[0367] Hardware: smartphones, tablets, servers

[0368] Software: Generative AI models, emotion engines, dedicated applications

[0369] Example prompts for generative AI models

[0370] "Detect cleanliness violations from user-captured footage."

[0371] "Analyze each frame in the video and identify areas where there are violations."

[0372] This allows users to efficiently perform cleanliness checks and quickly correct violations. Furthermore, by using an emotion engine, feedback is given taking into account the user's emotions, reducing the burden of the work.

[0373] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0374] Step 1:

[0375] The user uses the device to record the cleanliness conditions inside and outside the store. Specifically, the user launches a dedicated application and records video using the camera function. The input data is the video that was recorded, and the output is a video file saved on the device.

[0376] Step 2:

[0377] The user presses the send button in the application to upload the captured video data to the server. The input data is the video file stored on the device, and the output is the video data transferred to the server. Specifically, the user clicks the "upload" button to start the data transfer process.

[0378] Step 3:

[0379] The server's receiving means receives and stores the uploaded video. The input data is the video data uploaded by the user, and the output is a video file stored in the server's database. The user is notified that the receiving process has been completed successfully.

[0380] Step 4:

[0381] The server's generation means divides the received video into frames. Specifically, it converts the video into still images at a rate of one frame per second and saves all frames as image files. The input data is the video file saved on the server, and the output is a collection of divided frame images.

[0382] Step 5:

[0383] The server's analysis means inputs the generated frames into the generative AI model, which judges whether or not there is a violation for each frame based on the cleanliness criteria. The input data are the divided frame images, and the output is the analysis result (whether or not there is a violation and its details). Specifically, each frame is input into the AI ​​model in sequence, and the judgment result is obtained.

[0384] Step 6:

[0385] The emotion recognition means analyzes the user's emotional state when the video is being taken. The input data is the user's facial expression and tone of voice, and the output is the analysis result of the emotional state. Specifically, it recognizes emotions using a facial expression analysis algorithm and a voice emotion analysis algorithm, and saves the results.

[0386] Step 7:

[0387] The report generation means generates a report based on the data from the analysis means and emotion recognition means. The input data are the violation analysis results and the emotional state analysis results, and the output is the generated report. Specifically, the report reflecting the detailed information of the violation and the user's emotional state is generated according to a template.

[0388] Step 8:

[0389] The notification means sends the generated report to the user's device. The input data is the generated report, and the output is the report received by the user's device. Specifically, the generated report is sent to the user via email or an in-app notification function.

[0390] Step 9:

[0391] The user checks the report on the terminal and makes any necessary corrections. The input data is the received report, and the output is the corrected cleanliness status. The user cleans specific areas according to the instructions in the report and checks the results.

[0392] Step 10:

[0393] The user then records the situation after the correction work on video again and uploads it to the server. The input data is the corrected video, and the output is the re-uploaded video data stored on the server. Specifically, the user uses the dedicated app to record video again and execute the upload process.

[0394] Step 11:

[0395] The server then re-analyzes the video using the same procedure to confirm whether the corrections were made properly. The input data is the frame image for re-analysis, and the output is the re-analysis result (whether the problem was resolved or not). The final analysis result is notified to the user.

[0396] (Application example 2)

[0397] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart device 14 will be referred to as a "terminal."

[0398] Checking cleanliness and identifying violations is often done manually, which takes time and effort. It also leaves users feeling fatigued and stressed, making it difficult to work efficiently. Furthermore, it is difficult to provide feedback that takes into account the user's emotions when reporting violations, which can lead to a decrease in motivation and an increase in stress.

[0399] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a receiving means for receiving captured video, a generating means for generating frames from the video received by the receiving means, an analyzing means for analyzing the generated frames and making a judgment based on specified criteria, a generating means for generating a report based on the judgment results, a notifying means for notifying the generated report, an emotion analyzing means for analyzing the user's emotions, and a feedback adjusting means for adjusting the feedback content based on information from the emotion analyzing means. This makes it possible to automate cleanliness checks, quickly and accurately identify violations, and provide feedback that takes the user's emotions into consideration.

[0400] The "receiving means" is a device or system that receives the captured video from the mobile terminal operated by the user.

[0401] The "generating means" is a device or program that generates frames from the video received by the receiving means.

[0402] The "analysis means" is a device or program that analyzes the generated frames and makes a judgment based on a specified standard.

[0403] The "report generation means" is a device or program that generates a report based on the determination results of the analysis means.

[0404] A "notification means" is a device or system that transmits the generated report to the user's terminal.

[0405] The "emotion analysis means" is a device or program that analyzes the user's emotions.

[0406] The "feedback adjustment means" is a device or program that adjusts the feedback content based on information from the emotion analysis means.

[0407] "Cleanliness" is a term that refers to the cleanliness of a particular area.

[0408] A "frame" refers to a portion of an image that divides a video into a single moment on the time axis.

[0409] MODE FOR CARRYING OUT THE INVENTION

[0410] System Configuration

[0411] The cleanliness self-check system of the present invention is composed of the following main components:

[0412] 1. User's device

[0413] A mobile device operated by a user, including a smartphone or tablet, used to capture and upload video and receive notifications.

[0414] 2. Server

[0415] The server is a system including the following means:

[0416] Receiving means: Receives videos uploaded by users.

[0417] Generation method: Divide the video into frames.

[0418] Analysis method: Analyze the frame to determine if there are any cleanliness violations.

[0419] Report generation means: Generates a report based on the judgment results.

[0420] Notification method: The generated report is sent to the user's terminal.

[0421] Sentiment analysis means: Analyzes the user's emotions.

[0422] Feedback adjustment means: Adjust the feedback content based on the information from the sentiment analysis means.

[0423] Program processing and hardware / software

[0424] 1. Receiving video

[0425] Users use their smartphones to record the cleanliness status inside and outside the store. The recorded video is uploaded to a server via a mobile device application. The server's receiving means receives and stores the video. In this case, it is desirable for the application to be developed using a framework such as Flutter (registered trademark) or React Native.

[0426] 2. Frame Generation

[0427] The server divides the received video into frames. The generator generates frames at regular intervals every second and converts them into data for analysis. This process is performed using Python and image processing libraries such as OpenCV.

[0428] 3. Video Analysis

[0429] The server's analysis tool feeds each frame into a generative AI model (e.g., YOLO or TensorFlow) to determine whether there are any violations based on cleanliness criteria. Any violations detected are logged in detail.

[0430] 4. Emotion Analysis

[0431] The emotion analysis means analyzes the emotions expressed by the user when they shoot the video. For this, emotion recognition engines such as Microsoft® Azure Cognitive Services and Affectiva are used. The emotion is analyzed from the user's facial expressions and tone of voice, and the information is sent to the analysis means.

[0432] 5. Generate reports

[0433] Based on the judgment result and the emotion analysis result, the report generation means generates a report, which includes details of the violation and feedback that takes into account the user's emotions.

[0434] 6. Notifications and Feedback

[0435] The server's notification means sends the generated report to the user's terminal, where the user checks the report and makes any necessary corrections.

[0436] Examples of concrete examples and prompts

[0437] Examples:

[0438] Users film a video titled "Store Afternoon Cleanliness Check" on their smartphone and upload it to the server via the app. The server divides the three-minute video into frames and, in the process of analyzing each frame, detects the presence of trash on the table in the dining area. If the user feels tired while filming the video, the emotion analysis engine detects this and provides feedback such as, "Thank you for your hard work. There is trash on the table in the dining area. Please clean it up."

[0439] Example prompt sentence:

[0440] We have taken video footage to check the cleanliness of our store. Please analyze the video below and identify any cleanliness violations.

[0441] Video URL: [URL of uploaded video]

[0442] The analysis results should include details of the violation (e.g., there is trash on the table in the dining area) and feedback based on the staff member's emotional state (e.g., tired, annoyed). For example, "Thank you for your hard work. There is trash on the table in the dining area. Please clean it up."

[0443] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0444] Step 1:

[0445] The user shoots the video using a smartphone

[0446] Users use their smartphones to take videos to check the cleanliness status inside and outside the store. The videos are saved in the application. The input here is the video that was taken, and the output is the video data saved in the smartphone.

[0447] Step 2:

[0448] Uploading video from a smartphone to a server

[0449] Users upload captured video to a server using a smartphone app. The app sends the video data to the server via an internet connection. The input here is the video data stored on the smartphone, and the output is the video data received by the server.

[0450] Step 3:

[0451] The server divides the video into frames

[0452] The server receives the uploaded video data using a receiving means. Then, it divides the video into frames using a generating means. For example, if a three-minute video is divided into 30 frames per second, 5,400 frames are generated. The input is the video data received by the server, and the output is image data for each frame.

[0453] Step 4:

[0454] The server analyzes the frames and identifies cleanliness violations

[0455] The server uses an analysis method to analyze each generated frame. This analysis uses a generative AI model (e.g., YOLO or TensorFlow) to determine whether there are any violations based on specific cleanliness criteria. The input is the image data for each frame, and the output is the data with the violations identified.

[0456] Step 5:

[0457] The server analyzes the user's emotions

[0458] Emotion analysis tools are used to analyze facial expressions and tone of voice when a user shoots a video. For example, services from Microsoft Azure Cognitive Services or Affectiva are used. The input is the user's facial expressions and voice data, and the output is analyzed emotion data.

[0459] Step 6:

[0460] The server generates the report

[0461] Based on the results of the analysis means and the sentiment analysis means, the report generation means creates a report. The report includes details of the detected cleanliness violations and feedback that takes into account the user's sentiment. The input is data on the violation locations and sentiment data, and the output is the generated report.

[0462] Step 7:

[0463] The server notifies the report

[0464] The server sends the generated report to the user's smartphone using a notification means. The user receives the notification and checks the contents of the report. The input is the generated report, and the output is the report notified to the user.

[0465] Step 8:

[0466] The user makes corrections based on the report.

[0467] Based on the notified report, the user corrects any cleanliness violations within the store. For example, cleaning up trash on the tables in the dining area. The input is the content of the report, and the output is the actual cleaning work.

[0468] Step 9:

[0469] The user takes another photo of the corrected state and uploads it to the server.

[0470] The user then uses their smartphone to record the cleanliness of the area after the corrections and uploads the video to the server. The server then analyzes the video again to confirm that the corrections were made appropriately. The input is the re-recorded video data, and the output is the video data that has been re-uploaded to the server.

[0471] 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.

[0472] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (registered trademark) (Internet search engine).<URL: https: / / openai.com / blog / chatgpt> ), Gemini (registered trademark) (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0473] In the above embodiment, an example in which the specific process is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific process may be performed by the smart device 14.

[0474] [Second embodiment]

[0475] FIG. 3 shows an example of the configuration of a data processing system 210 according to the second embodiment.

[0476] 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.

[0477] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0478] 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.

[0479] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0480] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0481] 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.

[0482] 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.

[0483] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0484] 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.

[0485] In the smart glasses 214, the reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0486] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the smart glasses 214 will be referred to as the "terminal."

[0487] The cleanliness self-check system of the present invention uses video footage taken by store staff to automatically analyze the cleanliness inside and outside a store, identify any violations, and prompt a prompt response. Hereinafter, an embodiment of the present invention will be described.

[0488] System Configuration

[0489] This system mainly consists of the following components:

[0490] 1. User's device

[0491] Users (store crew) use mobile devices such as smartphones and tablets to shoot and upload videos.

[0492] 2. Server

[0493] The server includes a receiving means, a generating means, an analyzing means, and a notifying means, and receives and analyzes the video, and generates and notifies the report. The program running on the server functions as follows.

[0494] Program processing

[0495] Video reception

[0496] Users use their mobile devices to record video of the cleanliness conditions inside and outside the store. The recorded video is uploaded to the server via the application. The server receives the video via a receiving means and stores it.

[0497] Examples:

[0498] Users use their device to take pictures of the inside and outside of the store in the morning under the title "Comprehensive Store Cleanliness Check," and then upload the footage to the server via the app.

[0499] Frame Generation

[0500] The server divides the received video into frames, and the generating means converts the video into individual frames and prepares them for analysis.

[0501] Examples:

[0502] The server divides the five-minute video into 300 frames and stores each frame.

[0503] Video analysis

[0504] The server's analysis means sequentially analyzes each frame and determines whether there is a violation based on the cleanliness criteria. The analysis means checks each frame using the pre-defined cleanliness criteria to detect anomalies.

[0505] Examples:

[0506] At frame 123, it detects that there is trash under the front desk.

[0507] Generate reports

[0508] The analysis tool generates a report based on the results of the analysis, which includes the location of the violation and its details.

[0509] Examples:

[0510] A report is generated stating, "Garbage has been detected under the front desk" or "Unnecessary POPs have been placed in a corner of the warehouse."

[0511] Notifications and Feedback

[0512] The server sends the generated report to the user's terminal using a notification means, and the user receives the report and makes any necessary corrections.

[0513] Examples:

[0514] The user checks the report on the terminal and decides on a countermeasure, such as "I will clean up the trash under the front desk."

[0515] Reconfirmation

[0516] After completing the corrections, the user shoots the video again and uploads it to the server, which then analyzes it again using the receiving means and analyzing means to confirm that the corrections have been made appropriately.

[0517] Examples:

[0518] After the user cleans up the dust, they record the corrected state on video again and upload it to the server, where it analyzes it again and notifies them that the problem has been solved.

[0519] In this way, the system automates cleanliness self-checks and achieves efficient and highly accurate management.

[0520] The processing flow will be explained below.

[0521] Step 1:

[0522] The user uses the device to capture video inside and outside the store. The user launches the application, presses the record button, and captures the area to be checked.

[0523] Step 2:

[0524] The user uploads the video they have taken to the server. The user presses the "Upload" button in the application, selects the video file, and sends it to the server.

[0525] Step 3:

[0526] The server receives and stores the uploaded video. The receiving means receives the video and stores it in a dedicated folder in the server.

[0527] Step 4:

[0528] The server divides the received video into frames. The generation means divides the video into frames at regular intervals (for example, every second) and saves each frame as an image file.

[0529] Step 5:

[0530] The server inputs each frame into the generation AI, and the analysis means passes each generated frame to the AI ​​model in sequence, which analyzes it based on cleanliness criteria.

[0531] Step 6:

[0532] The generator AI analyzes each frame to determine whether there are any cleanliness violations. The AI ​​model checks each element within the frame to detect anomalies such as dust or illegal pop-ups.

[0533] Step 7:

[0534] The server receives the analysis results. The analysis means receives the result data from the generation AI and records the violations and their details.

[0535] Step 8:

[0536] The server generates a report based on the analysis results. The generation method compiles a list of the identified violations and creates a report that lists the specific issues and how to correct them.

[0537] Step 9:

[0538] The server notifies the user of the report, and the notification means transmits the generated report to the user's terminal and instructs the user to make corrections.

[0539] Step 10:

[0540] The user checks the report and corrects any violations that are reported. Based on the report on the terminal, the user can take appropriate action to resolve any cleanliness violations inside and outside the store.

[0541] Step 11:

[0542] The user shoots the video again and uploads the corrected state to the server. The user then starts the application again, shoots the checked area again, and sends it to the server.

[0543] Step 12:

[0544] The server receives, stores, and analyzes the re-uploaded video. It reprocesses the video using the same receiving, generating, and analyzing means as the first time, and verifies that the corrections were made appropriately.

[0545] Step 13:

[0546] The server notifies the user based on the reanalysis results. If the corrections are appropriate based on the analysis results, the server notifies the user of the completion, and if additional corrections are required, the server sends instructions to the user.

[0547] This step allows store crews to efficiently automate cleanliness checks and instantly correct any violations.

[0548] Example 1

[0549] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0550] The current mainstream method of cleanliness management involves store staff manually checking the inside and outside of the store, identifying and reporting any problems. However, this method is time-consuming and prone to human error. Furthermore, delayed feedback can mean that problems are left unaddressed for long periods of time when a prompt response is required. To solve these issues, a system that can efficiently and accurately perform cleanliness checks is needed.

[0551] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0552] In this invention, the server includes a receiving means for receiving the captured video, a generating means for generating frames from the video received by the receiving means, an analyzing means for analyzing the generated frames and making a judgment based on specified criteria, a report generating means for generating a report based on the judgment result, a notifying means for notifying the generated report, and a reanalysis means for reanalyzing the re-captured video and notifying the reanalysis result. This not only automates the cleanliness check but also enables quick and accurate feedback.

[0553] "Receiving means" refers to a device or system that has the function of receiving captured images.

[0554] The "generating means" refers to a device or system that has the function of converting the video received by the receiving means into individual frames for analysis.

[0555] "Analysis means" refers to a device or system that has the function of checking the generated frames based on specified cleanliness standards and determining whether or not there are any violations.

[0556] The "report generation means" refers to a device or system that has the function of creating a report detailing the violation based on the determination results from the analysis means.

[0557] The "notification means" refers to a device or system that has the function of notifying the user of the generated report.

[0558] "Reanalysis means" refers to a device or system that has the function of reanalyzing the re-shot video after correction and notifying the results.

[0559] The cleanliness self-check system of the present invention is a system in which a server analyzes video taken by a user, automatically checks the cleanliness inside and outside a store, identifies any violations, and prompts prompt action. A specific embodiment of this system is described below.

[0560] The system mainly consists of the following components:

[0561] 1. User's device

[0562] Users use mobile devices such as smartphones and tablets to capture and upload videos.

[0563] 2. Server

[0564] The server receives and analyzes the video, generates and notifies reports, and has the functions of a receiving means, a generating means, an analyzing means, a report generating means, a notifying means, and a re-analysis means.

[0565] In terms of specific hardware, users can use the latest smartphones (e.g., Android models or iPhones) as their devices. The server is operated on a high-performance cloud server (e.g., AWS or Azure), and AI models and image analysis libraries such as TensorFlow and OpenCV are used as analysis methods.

[0566] As a specific example, the system operates in the following manner.

[0567] 1. Filming and uploading the footage

[0568] Users use their mobile devices to record video of the cleanliness conditions inside and outside the store, and once the recording is complete, upload the video to the server through the application.

[0569] Specific operation examples:

[0570] The user launches the app, selects "New Cleanliness Check," takes photos of the inside and outside of the store, and presses the "Upload Video" button.

[0571] 2. Receiving and storing video

[0572] The server receives the uploaded video using the receiving means, and the video is stored in the server's storage.

[0573] Specific behavior:

[0574] The server displays "Receiving video data," and when reception is complete, records "Data saving completed."

[0575] 3. Video frame generation

[0576] The server uses a generation means to divide the stored video into frames, and prepares for analysis.

[0577] Specific behavior:

[0578] The server divides the five minutes of footage into 60 frames per second, generating and storing a total of 300 frames.

[0579] 4. Frame Analysis

[0580] The server's analysis means sequentially analyzes each frame and determines whether there is a violation based on the cleanliness criteria.

[0581] Specific behavior:

[0582] The server uses an AI model (e.g., TensorFlow) to detect debris and clutter in each frame and flags the frame if there is an anomaly.

[0583] 5. Generate reports

[0584] The server's report generation means generates a report based on the analysis results, which includes the violations and their details.

[0585] Specific behavior:

[0586] A report will be generated in PDF format stating, "Debris was detected under the front desk," along with an image of the frame in question.

[0587] 6. Notifications and Feedback

[0588] The report is sent to the user's terminal using a notification means, where the user can review the report and make any necessary corrections.

[0589] Specific operation examples:

[0590] The user checks the report on the terminal and provides feedback such as, "I will clean up the trash under the front desk."

[0591] 7. Re-imaging and re-analysis

[0592] After completing the corrections, the user shoots the video again and uploads it to the server, which then reanalyzes it to verify that the corrections were made properly.

[0593] Specific operation examples:

[0594] The user cleans up the junk and uploads the footage again. The server re-analyzes it and notifies the user that the problem has been resolved.

[0595] Example prompt sentence:

[0596] "A comprehensive cleanliness check of the store revealed trash under the front desk. Please clean up the trash, retake footage and report the results."

[0597] In this way, the system automates the cleanliness check process and provides fast and accurate feedback, allowing for effective management of store cleanliness.

[0598] The flow of the identification process in the first embodiment will be described with reference to FIG.

[0599] Step 1:

[0600] Filming and uploading footage

[0601] Users use their mobile devices to record video of the cleanliness conditions inside and outside the store, and once the recording is complete, upload the video to the server via a dedicated application.

[0602] Input: Video file (recording data)

[0603] Output: Upload video files to the server

[0604] Specific behavior:

[0605] The user launches the app, selects "New Cleanliness Check" and starts recording. After recording, they press the "Upload Video" button to send the video to the server.

[0606] Step 2:

[0607] Receiving and storing video

[0608] The server receives the uploaded video using the receiving means, and the video is stored in the server's storage.

[0609] Input: Uploaded video file

[0610] Output: Video data stored on the server

[0611] Specific behavior:

[0612] The server receives the video data sent from the app and displays "Receiving video data." After reception is complete, it records "Data saving completed."

[0613] Step 3:

[0614] Video frame generation

[0615] The server uses a generation method to divide the stored video into frames, which are then ready for analysis.

[0616] Input: Stored video data

[0617] Output: Image data divided into frames

[0618] Specific behavior:

[0619] The server splits the five-minute video into 60 frames per second, generating a total of 300 frames, each stored in a dedicated folder.

[0620] Step 4:

[0621] Frame Analysis

[0622] The server's analysis means sequentially analyzes each frame and determines whether there is a violation based on the cleanliness criteria.

[0623] Input: Image data divided into frames

[0624] Output: Analysis results for each frame (whether or not there is a violation)

[0625] Specific behavior:

[0626] The server uses an AI model (e.g., TensorFlow) to detect debris and clutter in each frame and flags the frame if there is an anomaly.

[0627] Step 5:

[0628] Generate reports

[0629] The server's report generation means generates a report based on the analysis results, which includes the violation location and its details.

[0630] Input: Analysis results

[0631] Output: Cleanliness Violation Report

[0632] Specific behavior:

[0633] The server generates a report in PDF format stating, "Debris was detected under the front desk," along with an image of the frame in question.

[0634] Step 6:

[0635] Notifications and Feedback

[0636] The server sends the generated report to the user's terminal using a notification means, and the user receives the report and takes appropriate measures.

[0637] Input: Cleanliness Violation Report

[0638] Output: Report notification to user, feedback record

[0639] Specific behavior:

[0640] The server sends the report to the user's device via email or push notification. The user checks the report and provides feedback such as, "I will clean up the trash under the front desk."

[0641] Step 7:

[0642] Re-imaging and re-analysis

[0643] After the user has completed the corrections, they shoot the video again and upload it to the server, where it will be reanalyzed to confirm that the corrections were made properly.

[0644] Input: Corrected video data

[0645] Output: Reanalysis results, final notification

[0646] Specific behavior:

[0647] After making the corrections, the user selects "Check after corrections" to shoot the video again and upload it to the server. The server then reanalyzes the video and notifies the user that the problem has been resolved.

[0648] (Application example 1)

[0649] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0650] To maintain the cleanliness of a store, it is important to regularly check the situation, quickly identify problem areas, and take measures. However, conventional methods for cleanliness checks are inefficient and the reliability of the check results is limited. In addition, there is often no system in place for store staff to voluntarily report problem areas, and even if a problem has been corrected, there is a lack of means to reconfirm its appropriateness. To solve these issues, an automated cleanliness check system is needed.

[0651] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[0652] In this invention, the server includes a receiving means for receiving the captured video, a generating means for generating frames from the video received by the receiving means, an analyzing means for analyzing the generated frames and making a judgment based on specified criteria, a generating means for generating a report based on the judgment results, a notifying means for notifying the generated report, and a reconfirming means for allowing the user to recapture and upload video. This enables automation of store cleanliness checks and efficient identification, correction, and reconfirmation of violations.

[0653] 1. "Receiving means" refers to a means for receiving images taken by a user inside and outside a store.

[0654] 2. "Generation means" means a means for generating frames from the video received by the reception means and preparing them for analysis.

[0655] 3. "Analysis means" refers to a means for determining violations based on the generated frames using the specified cleanliness standards.

[0656] 4. "Report generation means" means a means for generating a report based on the results of the analysis means.

[0657] 5. "Notification means" means a means for notifying the user of the generated report.

[0658] 6. "Reconfirmation means" refers to a means for a user to confirm corrections by taking a photo of the corrected state again and uploading it.

[0659] 7. "User" refers to a store crew member who uses the system to conduct cleanliness checks.

[0660] 8. "Mobile device" refers to a mobile device operated by a user, such as a smartphone or tablet.

[0661] 9. "Server" means a computer system that performs the functions of receiving video, generating frames, analyzing, generating reports, and notifying.

[0662] 10. "Cleanliness Standards" means the prescribed standards established to judge the cleanliness of a store.

[0663] The system embodying the present invention has a program for effectively managing the cleanliness of a store. The components of the system and their operation will be described below.

[0664] System Configuration

[0665] The system mainly consists of the following components:

[0666] 1. The user's mobile device

[0667] Users take and upload videos using their smartphones or tablets.

[0668] 2. Server

[0669] The server includes a receiving means, a generating means, an analyzing means, a report generating means, a notifying means, and a reconfirming means, and controls the entire process.

[0670] System Operation

[0671] Video reception and frame generation

[0672] The user's mobile device records the cleanliness status inside and outside the store as video. This video is uploaded to the server using the receiving means. The server divides the received video into frames and prepares them for analysis using the frame generating means.

[0673] Video analysis

[0674] The server's analysis means analyzes each frame based on cleanliness standards and identifies violations. The analysis means uses OpenCV, an image processing library, to detect abnormalities within the frames.

[0675] Report generation and notification

[0676] Based on the results of the analysis, a report is automatically generated by the report generation means. The report includes details of the identified cleanliness violations. The generated report is sent to the user's mobile device using the notification means.

[0677] Corrections and reconfirmation

[0678] Based on the report, the user corrects any cleanliness violations in the store. After the corrections are complete, the user shoots the video again and uploads it to the server via a reconfirmation tool. The server then analyzes the frames again to confirm that the corrections have been made properly.

[0679] Hardware and software used

[0680] Hardware: Smartphones, servers

[0681] Software: Flask (web framework), OpenCV (image processing library)

[0682] Specific examples

[0683] A user takes a video of the area around the trash can in the store with their smartphone and uploads the video to the server via the app. The server analyzes the video and generates a report stating that "the trash can is overflowing" and notifies the user. After the user has cleared the trash, they can take another video and upload it to the server, and receive a notification that "the problem has been resolved."

[0684] Prompt Sentence Examples

[0685] Please conduct a cleanliness check around the trash cans in your store. Upload the video and have it analyzed on the server. If there are any violations, a report will be automatically generated and notified. Please take appropriate action based on the cleanliness standards and record the video again to double-check.

[0686] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[0687] Step 1:

[0688] The user takes a video of the cleanliness situation inside and outside the store using a smartphone. The input here is the video file taken by the user, and the output is the video file that will be uploaded to the server.

[0689] Step 2:

[0690] The terminal uploads the captured video file to the server using the receiving means. The path to the video file is input to the terminal, and the data is sent to the server. The output is a video file saved on the server.

[0691] Step 3:

[0692] The server divides the video uploaded by the receiving means into frames. Here, the video file is the input, and the divided multiple frame images are the output. Specifically, the OpenCV library is used to break down the video into frames, and each frame is saved in memory.

[0693] Step 4:

[0694] The server's analysis means analyzes the generated frames and identifies abnormalities based on the cleanliness criteria. The input to this step is the frame images, and the output is the analysis result of whether each frame meets the cleanliness criteria. For example, OpenCV is used to determine whether dust is present in the image.

[0695] Step 5:

[0696] The server creates a report based on the analysis results using a report generation means. The input here is the analysis results, and the output is a report file. The report includes details of the violations.

[0697] Step 6:

[0698] The server sends the generated report to the user's smartphone via a notification method. The input of this step is the report file, and the output is the process of notifying the user's device. Specifically, the report is sent using email or the app's notification function.

[0699] Step 7:

[0700] The user checks the report and corrects any cleanliness violations that are pointed out. The input here is the report content, and the output is the state of the store after the corrections are made.

[0701] Step 8:

[0702] The user then takes another video of the corrected state with their smartphone and uploads the video to the server. The input here is the newly taken video file, and the output is the corrected video file sent to the server.

[0703] Step 9:

[0704] The server splits the received corrected video into frames again and rechecks it using an analysis method. The input here is the corrected video file, and the output is the result of the reanalysis of the frames. It is again determined whether the corrections were made properly.

[0705] Step 10:

[0706] The server then notifies the user based on the final analysis result whether the corrections were successful. The input to this step is the reanalysis result, and the output is a notification that "corrections are complete" or "recorrections are required."

[0707] Through these steps, the system will be able to automate and efficiently manage store cleanliness checks.

[0708] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[0709] The cleanliness self-check system of the present invention automatically analyzes the cleanliness status based on video footage taken by a user (e.g., a store crew member) and identifies any violations. By combining this system with an emotion engine, it is possible to recognize the user's emotional state and provide feedback accordingly. Detailed embodiments of the present invention are described below.

[0710] System Configuration

[0711] This system consists of the following main components:

[0712] 1. User's device

[0713] A mobile device such as a smartphone or tablet operated by a user, used to capture and upload video and receive notifications.

[0714] 2. Server

[0715] The server includes the following means:

[0716] Receiving means: Receives videos uploaded by users.

[0717] Generation method: Divide the video into frames.

[0718] Analysis method: Analyze the frame to determine if there are any cleanliness violations.

[0719] Notification method: A report is generated based on the judgment results and notified to the user.

[0720] Emotion engine: Recognizes user emotions and adjusts feedback accordingly.

[0721] Program processing

[0722] Video reception

[0723] The user uses the device to record the cleanliness status inside and outside the store. The recorded video is uploaded to the server via the application. The server's receiving means receives and stores the video.

[0724] Examples:

[0725] Users take videos on their devices titled "Store Afternoon Cleanliness Check" and upload them to the server via the app.

[0726] Frame Generation

[0727] The server divides the received video into frames, and the generating means generates frames at regular intervals per second and converts them into data for analysis.

[0728] Examples:

[0729] The server divides the three-minute video into 180 frames and saves each frame as an image file.

[0730] Video analysis

[0731] The server's analysis means inputs each frame into the generation AI, which determines whether or not there is a violation based on the cleanliness standards. The results are recorded in detail, detailing which areas have violations and what kind of violations have occurred.

[0732] Examples:

[0733] At frame 45, it detects that there is trash on the table in the eating area.

[0734] Emotion recognition

[0735] The emotion engine recognizes the user's emotions when shooting video. The emotion engine analyzes the user's emotions from their facial expressions and tone of voice, and sends that information to the analysis means.

[0736] Examples:

[0737] If the user is feeling frustrated or tired while shooting a video, the emotion engine will detect it.

[0738] Generate reports

[0739] The analysis means generates a report based on the information from the emotion engine, which includes details of the violation and feedback that takes into account the user's emotions.

[0740] Examples:

[0741] A report will be generated such as, "Garbage has been detected on the table in the dining area. Thank you for your hard work, please clean this up."

[0742] Notifications and Feedback

[0743] The server's notification means sends the report to the user's terminal, where the user can check the report and make any necessary corrections.

[0744] Examples:

[0745] The user checks the report on their device and decides on a countermeasure, such as "cleaning up the trash on the tables in the dining area."

[0746] Reconfirmation

[0747] After completing the corrections, the user shoots the video again and uploads it to the server, which then analyzes the video again in the same way to confirm that the corrections were made properly.

[0748] Examples:

[0749] After the user cleans up the dust, they record the corrected state on video again and upload it to the server, where it analyzes it again and notifies them that the problem has been solved.

[0750] This system allows users to efficiently perform cleanliness checks and quickly correct any violations. In addition, the introduction of an emotion engine provides feedback that takes into account the user's emotions, reducing the burden of the work.

[0751] The processing flow will be explained below.

[0752] Step 1:

[0753] The user uses the device to take video of the inside and outside of the store. The user launches the dedicated application and presses the capture button to capture the area to be checked.

[0754] Step 2:

[0755] The user uploads the video they have taken to the server. The user presses the "Upload" button in the application to send the video file to the server.

[0756] Step 3:

[0757] The server receives and stores the uploaded video. The receiving means receives the video file and stores it in a specific folder in the server.

[0758] Step 4:

[0759] The server divides the received video into frames. The generation means divides the video into frames at regular intervals (for example, every second) and saves each frame as an image file.

[0760] Step 5:

[0761] The server inputs each frame into the analysis AI, which then passes each generated frame to the AI ​​model in turn, which analyzes it based on cleanliness criteria.

[0762] Step 6:

[0763] The generator AI analyzes each frame to determine whether there are any cleanliness violations. The AI ​​model checks each element within the frame to detect anomalies such as dust or illegal pop-ups.

[0764] Step 7:

[0765] The server also sends the analysis results to the emotion engine, which analyzes the user's emotions. The emotion engine analyzes the user's facial expressions and tone of voice to recognize their emotions.

[0766] Step 8:

[0767] The server generates a report based on the analysis results and emotional information, which includes any cleanliness violations and feedback that takes the user's emotions into consideration.

[0768] Step 9:

[0769] The server notifies the user of the generated report, and the notification means transmits the contents of the report to the user's terminal and instructs the user to make corrections.

[0770] Step 10:

[0771] The user checks the report and corrects any violations that are reported. Based on the report on the terminal, the user can take appropriate action to resolve any cleanliness violations inside and outside the store.

[0772] Step 11:

[0773] The user shoots the video again and uploads the corrected state to the server. The user then starts the application again, shoots the checked area again, and sends it to the server.

[0774] Step 12:

[0775] The server receives, stores, and analyzes the re-uploaded video. It reprocesses the video using the same receiving, generating, and analyzing means as the first time, and verifies that the corrections were made appropriately.

[0776] Step 13:

[0777] The server notifies the user based on the results of the reanalysis. It checks whether the corrections were made appropriately based on the analysis results, and if the problem has been resolved, it sends a final notification to the user, and if additional corrections are required, it sends instructions to the user.

[0778] Example 2

[0779] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0780] Conventional cleanliness check systems allow users to simply check the results of their cleaning, making it difficult to efficiently check and improve. Furthermore, they do not provide feedback that takes into account the user's emotions or fatigue, which increases the burden of the work. There is a need for a system that recognizes the user's emotional state in real time and provides feedback that takes those emotions into consideration, thereby realizing efficient and less burdensome cleanliness checks.

[0781] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[0782] In this invention, the server includes receiving means for receiving the captured video, generating means for generating frames from the video received by the receiving means, analyzing means for analyzing the generated frames and making a judgment based on specified criteria, generating means for generating a report based on the judgment results, notifying means for notifying the generated report, emotion recognition means for recognizing the emotion of the user recording the video, and feedback means for adjusting the feedback content based on emotion data recognized by the emotion recognition means. This makes it possible to efficiently identify violations and provide feedback that takes the user's emotions into consideration.

[0783] The "receiving means" is a function for receiving video data uploaded to the server from the user's mobile terminal.

[0784] The "generating means" is a function that generates frames from the video data received by the receiving means and converts the frames into a format suitable for analysis.

[0785] The "analysis means" is a function that inputs the generated frame into the generation AI model and determines whether or not there is a violation based on cleanliness standards.

[0786] The "report generation means" is a function that generates a document to report the violation location and its details to the user based on the judgment results obtained by the analysis means.

[0787] The "notification means" is a function that sends the generated report to the user's mobile terminal and notifies the user.

[0788] The "emotion recognition means" is a function for recognizing the user's emotional state during video shooting from facial expressions and tone of voice.

[0789] The "feedback means" is a function that adjusts the contents of reports and notifications in a way that takes into consideration the user's emotions, based on the emotion data recognized by the emotion recognition means.

[0790] The cleanliness self-check system of the present invention automatically analyzes the cleanliness status based on the video taken by the user and identifies any violations. In addition, by combining it with an emotion engine, it is possible to recognize the user's emotional state and provide feedback that takes those emotions into consideration.

[0791] System Configuration

[0792] This system consists of the following main components:

[0793] 1. User's device

[0794] A mobile device such as a smartphone or tablet operated by the user, which is used to capture and upload video and receive notifications of analysis results.

[0795] 2. Server

[0796] The server includes the following means:

[0797] Receiving means: A function to receive videos uploaded by users.

[0798] Generation method: A function that generates frames from received video.

[0799] Analysis method: The generated frames are analyzed to determine whether cleanliness violations exist. This uses a generative AI model.

[0800] Report generation means: A function to generate a report based on the judgment results.

[0801] Notification method: A function to send the generated report to the user's terminal.

[0802] Emotion recognition: A function that recognizes the emotions of the user when recording video. It analyzes facial expressions and tone of voice.

[0803] Feedback means: A function that adjusts the feedback content based on emotional data from the emotion recognition means.

[0804] Filming and uploading footage

[0805] Users use their mobile devices to record video of the cleanliness status inside and outside the store. The video is then uploaded to the server via a dedicated application. For example, a user can record a video of an "afternoon cleanliness check" and press the send button on the application to upload the video data to the server.

[0806] Video reception, frame generation and analysis

[0807] The server's receiving means receives and saves the uploaded video. Next, the server's generating means divides the video into frames. For example, a three-minute video is divided into frames every second, and all of the frames are saved as JPEG image files. The server's analyzing means inputs the generated frames into a generative AI model and analyzes each frame based on cleanliness standards. It determines whether or not there is a cleanliness violation and records the violation in detail. For example, if garbage is detected on a table in the eating and drinking area in frame 45, the result is recorded on the table.

[0808] Emotional Recognition and Feedback

[0809] The emotion recognition means analyzes the user's emotions while shooting video. It detects the user's emotions from facial expressions and tone of voice and sends that information to the server. For example, if the user expresses fatigue while shooting, the emotion recognition means will determine that the user is "feeling tired." The feedback means adjusts the feedback content based on the emotional data. For example, it provides feedback in the form of "Thank you for your hard work. Please clean this area."

[0810] Report generation and notification

[0811] The report generation means generates a report based on the judgment result obtained by the analysis means and the information from the emotion recognition means. The generated report is sent to the user's mobile device by the notification means. The user checks the report and makes any necessary corrections. For example, the user may decide to "clean up the trash on the tables in the dining area" and then carry out the cleaning.

[0812] Hardware and software used

[0813] Hardware: smartphones, tablets, servers

[0814] Software: Generative AI models, emotion engines, dedicated applications

[0815] Example prompts for generative AI models

[0816] "Detect cleanliness violations from user-captured footage."

[0817] "Analyze each frame in the video and identify areas where there are violations."

[0818] This allows users to efficiently perform cleanliness checks and quickly correct violations. Furthermore, by using an emotion engine, feedback is given taking into account the user's emotions, reducing the burden of the work.

[0819] The flow of the identification process in the second embodiment will be described with reference to FIG.

[0820] Step 1:

[0821] The user uses the device to record the cleanliness conditions inside and outside the store. Specifically, the user launches a dedicated application and records video using the camera function. The input data is the video that was recorded, and the output is a video file saved on the device.

[0822] Step 2:

[0823] The user presses the send button in the application to upload the captured video data to the server. The input data is the video file stored on the device, and the output is the video data transferred to the server. Specifically, the user clicks the "upload" button to start the data transfer process.

[0824] Step 3:

[0825] The server's receiving means receives and stores the uploaded video. The input data is the video data uploaded by the user, and the output is a video file stored in the server's database. The user is notified that the receiving process has been completed successfully.

[0826] Step 4:

[0827] The server's generation means divides the received video into frames. Specifically, it converts the video into still images at a rate of one frame per second and saves all frames as image files. The input data is the video file saved on the server, and the output is a collection of divided frame images.

[0828] Step 5:

[0829] The server's analysis means inputs the generated frames into the generative AI model, which judges whether or not there is a violation for each frame based on the cleanliness criteria. The input data are the divided frame images, and the output is the analysis result (whether or not there is a violation and its details). Specifically, each frame is input into the AI ​​model in sequence, and the judgment result is obtained.

[0830] Step 6:

[0831] The emotion recognition means analyzes the user's emotional state when the video is being taken. The input data is the user's facial expression and tone of voice, and the output is the analysis result of the emotional state. Specifically, it recognizes emotions using a facial expression analysis algorithm and a voice emotion analysis algorithm, and saves the results.

[0832] Step 7:

[0833] The report generation means generates a report based on the data from the analysis means and emotion recognition means. The input data are the violation analysis results and the emotional state analysis results, and the output is the generated report. Specifically, the report reflecting the detailed information of the violation and the user's emotional state is generated according to a template.

[0834] Step 8:

[0835] The notification means sends the generated report to the user's device. The input data is the generated report, and the output is the report received by the user's device. Specifically, the generated report is sent to the user via email or an in-app notification function.

[0836] Step 9:

[0837] The user checks the report on the terminal and makes any necessary corrections. The input data is the received report, and the output is the corrected cleanliness status. The user cleans specific areas according to the instructions in the report and checks the results.

[0838] Step 10:

[0839] The user then records the situation after the correction work on video again and uploads it to the server. The input data is the corrected video, and the output is the re-uploaded video data stored on the server. Specifically, the user uses the dedicated app to record video again and execute the upload process.

[0840] Step 11:

[0841] The server then re-analyzes the video using the same procedure to confirm whether the corrections were made properly. The input data is the frame image for re-analysis, and the output is the re-analysis result (whether the problem was resolved or not). The final analysis result is notified to the user.

[0842] (Application example 2)

[0843] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the smart glasses 214 will be referred to as a "terminal."

[0844] Checking cleanliness and identifying violations is often done manually, which takes time and effort. It also leaves users feeling fatigued and stressed, making it difficult to work efficiently. Furthermore, it is difficult to provide feedback that takes into account the user's emotions when reporting violations, which can lead to a decrease in motivation and an increase in stress.

[0845] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a receiving means for receiving captured video, a generating means for generating frames from the video received by the receiving means, an analyzing means for analyzing the generated frames and making a judgment based on specified criteria, a generating means for generating a report based on the judgment results, a notifying means for notifying the generated report, an emotion analyzing means for analyzing the user's emotions, and a feedback adjusting means for adjusting the feedback content based on information from the emotion analyzing means. This makes it possible to automate cleanliness checks, quickly and accurately identify violations, and provide feedback that takes the user's emotions into consideration.

[0846] The "receiving means" is a device or system that receives the captured video from the mobile terminal operated by the user.

[0847] The "generating means" is a device or program that generates frames from the video received by the receiving means.

[0848] The "analysis means" is a device or program that analyzes the generated frames and makes a judgment based on a specified standard.

[0849] The "report generation means" is a device or program that generates a report based on the determination results of the analysis means.

[0850] A "notification means" is a device or system that transmits the generated report to the user's terminal.

[0851] The "emotion analysis means" is a device or program that analyzes the user's emotions.

[0852] The "feedback adjustment means" is a device or program that adjusts the feedback content based on information from the emotion analysis means.

[0853] "Cleanliness" is a term that refers to the cleanliness of a particular area.

[0854] A "frame" refers to a portion of an image that divides a video into a single moment on the time axis.

[0855] MODE FOR CARRYING OUT THE INVENTION

[0856] System Configuration

[0857] The cleanliness self-check system of the present invention is composed of the following main components:

[0858] 1. User's device

[0859] A mobile device operated by a user, including a smartphone or tablet, used to capture and upload video and receive notifications.

[0860] 2. Server

[0861] The server is a system including the following means:

[0862] Receiving means: Receives videos uploaded by users.

[0863] Generation method: Divide the video into frames.

[0864] Analysis method: Analyze the frame to determine if there are any cleanliness violations.

[0865] Report generation means: Generates a report based on the judgment results.

[0866] Notification method: The generated report is sent to the user's terminal.

[0867] Sentiment analysis means: Analyzes the user's emotions.

[0868] Feedback adjustment means: Adjust the feedback content based on the information from the sentiment analysis means.

[0869] Program processing and hardware / software

[0870] 1. Receiving video

[0871] Users use their smartphones to record the cleanliness status inside and outside the store. The recorded video is uploaded to a server via a mobile device application. The server's receiving means receives and stores the video. In this case, it is desirable for the application to be developed using a framework such as Flutter or React Native.

[0872] 2. Frame Generation

[0873] The server divides the received video into frames. The generator generates frames at regular intervals every second and converts them into data for analysis. This process is performed using Python and image processing libraries such as OpenCV.

[0874] 3. Video Analysis

[0875] The server's analysis tool feeds each frame into a generative AI model (e.g., YOLO or TensorFlow) to determine whether there are any violations based on cleanliness criteria. Any violations detected are logged in detail.

[0876] 4. Emotion Analysis

[0877] The emotion analysis means analyzes the emotions expressed by the user when they shoot video. This uses emotion recognition engines such as Microsoft Azure Cognitive Services and Affectiva. The emotion is analyzed from the user's facial expressions and tone of voice, and the information is sent to the analysis means.

[0878] 5. Generate reports

[0879] Based on the judgment result and the emotion analysis result, the report generation means generates a report, which includes details of the violation and feedback that takes into account the user's emotions.

[0880] 6. Notifications and Feedback

[0881] The server's notification means sends the generated report to the user's terminal, where the user checks the report and makes any necessary corrections.

[0882] Examples of concrete examples and prompts

[0883] Examples:

[0884] Users film a video titled "Store Afternoon Cleanliness Check" on their smartphone and upload it to the server via the app. The server divides the three-minute video into frames and, in the process of analyzing each frame, detects the presence of trash on the table in the dining area. If the user feels tired while filming the video, the emotion analysis engine detects this and provides feedback such as, "Thank you for your hard work. There is trash on the table in the dining area. Please clean it up."

[0885] Example prompt sentence:

[0886] We have taken video footage to check the cleanliness of our store. Please analyze the video below and identify any cleanliness violations.

[0887] Video URL: [URL of uploaded video]

[0888] The analysis results should include details of the violation (e.g., there is trash on the table in the dining area) and feedback based on the staff member's emotional state (e.g., tired, annoyed). For example, "Thank you for your hard work. There is trash on the table in the dining area. Please clean it up."

[0889] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[0890] Step 1:

[0891] The user shoots the video using a smartphone

[0892] Users use their smartphones to take videos to check the cleanliness status inside and outside the store. The videos are saved in the application. The input here is the video that was taken, and the output is the video data saved in the smartphone.

[0893] Step 2:

[0894] Uploading video from a smartphone to a server

[0895] Users upload captured video to a server using a smartphone app. The app sends the video data to the server via an internet connection. The input here is the video data stored on the smartphone, and the output is the video data received by the server.

[0896] Step 3:

[0897] The server divides the video into frames

[0898] The server receives the uploaded video data using a receiving means. Then, it divides the video into frames using a generating means. For example, if a three-minute video is divided into 30 frames per second, 5,400 frames are generated. The input is the video data received by the server, and the output is image data for each frame.

[0899] Step 4:

[0900] The server analyzes the frames and identifies cleanliness violations

[0901] The server uses an analysis method to analyze each generated frame. This analysis uses a generative AI model (e.g., YOLO or TensorFlow) to determine whether there are any violations based on specific cleanliness criteria. The input is the image data for each frame, and the output is the data with the violations identified.

[0902] Step 5:

[0903] The server analyzes the user's emotions

[0904] Emotion analysis tools are used to analyze facial expressions and tone of voice when a user shoots a video. For example, services from Microsoft Azure Cognitive Services or Affectiva are used. The input is the user's facial expressions and voice data, and the output is analyzed emotion data.

[0905] Step 6:

[0906] The server generates the report

[0907] Based on the results of the analysis means and the sentiment analysis means, the report generation means creates a report. The report includes details of the detected cleanliness violations and feedback that takes into account the user's sentiment. The input is data on the violation locations and sentiment data, and the output is the generated report.

[0908] Step 7:

[0909] The server notifies the report

[0910] The server sends the generated report to the user's smartphone using a notification means. The user receives the notification and checks the contents of the report. The input is the generated report, and the output is the report notified to the user.

[0911] Step 8:

[0912] The user makes corrections based on the report.

[0913] Based on the notified report, the user corrects any cleanliness violations within the store. For example, cleaning up trash on the tables in the dining area. The input is the content of the report, and the output is the actual cleaning work.

[0914] Step 9:

[0915] The user takes another photo of the corrected state and uploads it to the server.

[0916] The user then uses their smartphone to record the cleanliness of the area after the corrections and uploads the video to the server. The server then analyzes the video again to confirm that the corrections were made appropriately. The input is the re-recorded video data, and the output is the video data that has been re-uploaded to the server.

[0917] 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.

[0918] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[0919] In the above embodiment, an example in which the specific processing is performed by the data processing device 12 has been given, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the smart glasses 214.

[0920] [Third embodiment]

[0921] FIG. 5 shows an example of the configuration of a data processing system 310 according to the third embodiment.

[0922] 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.

[0923] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[0924] 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.

[0925] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[0926] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[0927] 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.

[0928] 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.

[0929] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[0930] 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.

[0931] In the headset type terminal 314, a reception output process is performed by the processor 46. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[0932] Next, a description will be given of the identification process performed by the identification processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as the "server" and the headset type terminal 314 will be referred to as the "terminal."

[0933] The cleanliness self-check system of the present invention uses video footage taken by store staff to automatically analyze the cleanliness inside and outside a store, identify any violations, and prompt a prompt response. Hereinafter, an embodiment of the present invention will be described.

[0934] System Configuration

[0935] This system mainly consists of the following components:

[0936] 1. User's device

[0937] Users (store crew) use mobile devices such as smartphones and tablets to shoot and upload videos.

[0938] 2. Server

[0939] The server includes a receiving means, a generating means, an analyzing means, and a notifying means, and receives and analyzes the video, and generates and notifies the report. The program running on the server functions as follows.

[0940] Program processing

[0941] Video reception

[0942] Users use their mobile devices to record video of the cleanliness conditions inside and outside the store. The recorded video is uploaded to the server via the application. The server receives the video via a receiving means and stores it.

[0943] Examples:

[0944] Users use their device to take pictures of the inside and outside of the store in the morning under the title "Comprehensive Store Cleanliness Check," and then upload the footage to the server via the app.

[0945] Frame Generation

[0946] The server divides the received video into frames, and the generating means converts the video into individual frames and prepares them for analysis.

[0947] Examples:

[0948] The server divides the five-minute video into 300 frames and stores each frame.

[0949] Video analysis

[0950] The server's analysis means sequentially analyzes each frame and determines whether there is a violation based on the cleanliness criteria. The analysis means checks each frame using the pre-defined cleanliness criteria to detect anomalies.

[0951] Examples:

[0952] At frame 123, it detects that there is trash under the front desk.

[0953] Generate reports

[0954] The analysis tool generates a report based on the results of the analysis, which includes the location of the violation and its details.

[0955] Examples:

[0956] A report is generated stating, "Garbage has been detected under the front desk" or "Unnecessary POPs have been placed in a corner of the warehouse."

[0957] Notifications and Feedback

[0958] The server sends the generated report to the user's terminal using a notification means, and the user receives the report and makes any necessary corrections.

[0959] Examples:

[0960] The user checks the report on the terminal and decides on a countermeasure, such as "I will clean up the trash under the front desk."

[0961] Reconfirmation

[0962] After completing the corrections, the user shoots the video again and uploads it to the server, which then analyzes it again using the receiving means and analyzing means to confirm that the corrections have been made appropriately.

[0963] Examples:

[0964] After the user cleans up the dust, they record the corrected state on video again and upload it to the server, where it analyzes it again and notifies them that the problem has been solved.

[0965] In this way, the system automates cleanliness self-checks and achieves efficient and highly accurate management.

[0966] The processing flow will be explained below.

[0967] Step 1:

[0968] The user uses the device to capture video inside and outside the store. The user launches the application, presses the record button, and captures the area to be checked.

[0969] Step 2:

[0970] The user uploads the video they have taken to the server. The user presses the "Upload" button in the application, selects the video file, and sends it to the server.

[0971] Step 3:

[0972] The server receives and stores the uploaded video. The receiving means receives the video and stores it in a dedicated folder in the server.

[0973] Step 4:

[0974] The server divides the received video into frames. The generation means divides the video into frames at regular intervals (for example, every second) and saves each frame as an image file.

[0975] Step 5:

[0976] The server inputs each frame into the generation AI, and the analysis means passes each generated frame to the AI ​​model in sequence, which analyzes it based on cleanliness criteria.

[0977] Step 6:

[0978] The generator AI analyzes each frame to determine whether there are any cleanliness violations. The AI ​​model checks each element within the frame to detect anomalies such as dust or illegal pop-ups.

[0979] Step 7:

[0980] The server receives the analysis results. The analysis means receives the result data from the generation AI and records the violations and their details.

[0981] Step 8:

[0982] The server generates a report based on the analysis results. The generation method compiles a list of the identified violations and creates a report that lists the specific issues and how to correct them.

[0983] Step 9:

[0984] The server notifies the user of the report, and the notification means transmits the generated report to the user's terminal and instructs the user to make corrections.

[0985] Step 10:

[0986] The user checks the report and corrects any violations that are reported. Based on the report on the terminal, the user can take appropriate action to resolve any cleanliness violations inside and outside the store.

[0987] Step 11:

[0988] The user shoots the video again and uploads the corrected state to the server. The user then starts the application again, shoots the checked area again, and sends it to the server.

[0989] Step 12:

[0990] The server receives, stores, and analyzes the re-uploaded video. It reprocesses the video using the same receiving, generating, and analyzing means as the first time, and verifies that the corrections were made appropriately.

[0991] Step 13:

[0992] The server notifies the user based on the reanalysis results. If the corrections are appropriate based on the analysis results, the server notifies the user of the completion, and if additional corrections are required, the server sends instructions to the user.

[0993] This step allows store crews to efficiently automate cleanliness checks and instantly correct any violations.

[0994] Example 1

[0995] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[0996] The current mainstream method of cleanliness management involves store staff manually checking the inside and outside of the store, identifying and reporting any problems. However, this method is time-consuming and prone to human error. Furthermore, delayed feedback can mean that problems are left unaddressed for long periods of time when a prompt response is required. To solve these issues, a system that can efficiently and accurately perform cleanliness checks is needed.

[0997] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[0998] In this invention, the server includes a receiving means for receiving the captured video, a generating means for generating frames from the video received by the receiving means, an analyzing means for analyzing the generated frames and making a judgment based on specified criteria, a report generating means for generating a report based on the judgment result, a notifying means for notifying the generated report, and a reanalysis means for reanalyzing the re-captured video and notifying the reanalysis result. This not only automates the cleanliness check but also enables quick and accurate feedback.

[0999] "Receiving means" refers to a device or system that has the function of receiving captured images.

[1000] The "generating means" refers to a device or system that has the function of converting the video received by the receiving means into individual frames for analysis.

[1001] "Analysis means" refers to a device or system that has the function of checking the generated frames based on specified cleanliness standards and determining whether or not there are any violations.

[1002] The "report generation means" refers to a device or system that has the function of creating a report detailing the violation based on the determination results from the analysis means.

[1003] The "notification means" refers to a device or system that has the function of notifying the user of the generated report.

[1004] "Reanalysis means" refers to a device or system that has the function of reanalyzing the re-shot video after correction and notifying the results.

[1005] The cleanliness self-check system of the present invention is a system in which a server analyzes video taken by a user, automatically checks the cleanliness inside and outside a store, identifies any violations, and prompts prompt action. A specific embodiment of this system is described below.

[1006] The system mainly consists of the following components:

[1007] 1. User's device

[1008] Users use mobile devices such as smartphones and tablets to capture and upload videos.

[1009] 2. Server

[1010] The server receives and analyzes the video, generates and notifies reports, and has the functions of a receiving means, a generating means, an analyzing means, a report generating means, a notifying means, and a re-analysis means.

[1011] In terms of specific hardware, users can use the latest smartphones (e.g., Android models or iPhones) as their devices. The server is operated on a high-performance cloud server (e.g., AWS or Azure), and AI models and image analysis libraries such as TensorFlow and OpenCV are used as analysis methods.

[1012] As a specific example, the system operates in the following manner.

[1013] 1. Filming and uploading the footage

[1014] Users use their mobile devices to record video of the cleanliness conditions inside and outside the store, and once the recording is complete, upload the video to the server through the application.

[1015] Specific operation examples:

[1016] The user launches the app, selects "New Cleanliness Check," takes photos of the inside and outside of the store, and presses the "Upload Video" button.

[1017] 2. Receiving and storing video

[1018] The server receives the uploaded video using the receiving means, and the video is stored in the server's storage.

[1019] Specific behavior:

[1020] The server displays "Receiving video data," and when reception is complete, records "Data saving completed."

[1021] 3. Video frame generation

[1022] The server uses a generation means to divide the stored video into frames, and prepares for analysis.

[1023] Specific behavior:

[1024] The server divides the five minutes of footage into 60 frames per second, generating and storing a total of 300 frames.

[1025] 4. Frame Analysis

[1026] The server's analysis means sequentially analyzes each frame and determines whether there is a violation based on the cleanliness criteria.

[1027] Specific behavior:

[1028] The server uses an AI model (e.g., TensorFlow) to detect debris and clutter in each frame and flags the frame if there is an anomaly.

[1029] 5. Generate reports

[1030] The server's report generation means generates a report based on the analysis results, which includes the violations and their details.

[1031] Specific behavior:

[1032] A report will be generated in PDF format stating, "Debris was detected under the front desk," along with an image of the frame in question.

[1033] 6. Notifications and Feedback

[1034] The report is sent to the user's terminal using a notification means, where the user can review the report and make any necessary corrections.

[1035] Specific operation examples:

[1036] The user checks the report on the terminal and provides feedback such as, "I will clean up the trash under the front desk."

[1037] 7. Re-imaging and re-analysis

[1038] After completing the corrections, the user shoots the video again and uploads it to the server, which then reanalyzes it to verify that the corrections were made properly.

[1039] Specific operation examples:

[1040] The user cleans up the junk and uploads the footage again. The server re-analyzes it and notifies the user that the problem has been resolved.

[1041] Example prompt sentence:

[1042] "A comprehensive cleanliness check of the store revealed trash under the front desk. Please clean up the trash, retake footage and report the results."

[1043] In this way, the system automates the cleanliness check process and provides fast and accurate feedback, allowing for effective management of store cleanliness.

[1044] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1045] Step 1:

[1046] Filming and uploading footage

[1047] Users use their mobile devices to record video of the cleanliness conditions inside and outside the store, and once the recording is complete, upload the video to the server via a dedicated application.

[1048] Input: Video file (recording data)

[1049] Output: Upload video files to the server

[1050] Specific behavior:

[1051] The user launches the app, selects "New Cleanliness Check" and starts recording. After recording, they press the "Upload Video" button to send the video to the server.

[1052] Step 2:

[1053] Receiving and storing video

[1054] The server receives the uploaded video using the receiving means, and the video is stored in the server's storage.

[1055] Input: Uploaded video file

[1056] Output: Video data stored on the server

[1057] Specific behavior:

[1058] The server receives the video data sent from the app and displays "Receiving video data." After reception is complete, it records "Data saving completed."

[1059] Step 3:

[1060] Video frame generation

[1061] The server uses a generation method to divide the stored video into frames, which are then ready for analysis.

[1062] Input: Stored video data

[1063] Output: Image data divided into frames

[1064] Specific behavior:

[1065] The server splits the five-minute video into 60 frames per second, generating a total of 300 frames, each stored in a dedicated folder.

[1066] Step 4:

[1067] Frame Analysis

[1068] The server's analysis means sequentially analyzes each frame and determines whether there is a violation based on the cleanliness criteria.

[1069] Input: Image data divided into frames

[1070] Output: Analysis results for each frame (whether or not there is a violation)

[1071] Specific behavior:

[1072] The server uses an AI model (e.g., TensorFlow) to detect debris and clutter in each frame and flags the frame if there is an anomaly.

[1073] Step 5:

[1074] Generate reports

[1075] The server's report generation means generates a report based on the analysis results, which includes the violation location and its details.

[1076] Input: Analysis results

[1077] Output: Cleanliness Violation Report

[1078] Specific behavior:

[1079] The server generates a report in PDF format stating, "Debris was detected under the front desk," along with an image of the frame in question.

[1080] Step 6:

[1081] Notifications and Feedback

[1082] The server sends the generated report to the user's terminal using a notification means, and the user receives the report and takes appropriate measures.

[1083] Input: Cleanliness Violation Report

[1084] Output: Report notification to user, feedback record

[1085] Specific behavior:

[1086] The server sends the report to the user's device via email or push notification. The user checks the report and provides feedback such as, "I will clean up the trash under the front desk."

[1087] Step 7:

[1088] Re-imaging and re-analysis

[1089] After the user has completed the corrections, they shoot the video again and upload it to the server, where it will be reanalyzed to confirm that the corrections were made properly.

[1090] Input: Corrected video data

[1091] Output: Reanalysis results, final notification

[1092] Specific behavior:

[1093] After making the corrections, the user selects "Check after corrections" to shoot the video again and upload it to the server. The server then reanalyzes the video and notifies the user that the problem has been resolved.

[1094] (Application example 1)

[1095] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1096] To maintain the cleanliness of a store, it is important to regularly check the situation, quickly identify problem areas, and take measures. However, conventional methods for cleanliness checks are inefficient and the reliability of the check results is limited. In addition, there is often no system in place for store staff to voluntarily report problem areas, and even if a problem has been corrected, there is a lack of means to reconfirm its appropriateness. To solve these issues, an automated cleanliness check system is needed.

[1097] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1098] In this invention, the server includes a receiving means for receiving the captured video, a generating means for generating frames from the video received by the receiving means, an analyzing means for analyzing the generated frames and making a judgment based on specified criteria, a generating means for generating a report based on the judgment results, a notifying means for notifying the generated report, and a reconfirming means for allowing the user to recapture and upload video. This enables automation of store cleanliness checks and efficient identification, correction, and reconfirmation of violations.

[1099] 1. "Receiving means" refers to a means for receiving images taken by a user inside and outside a store.

[1100] 2. "Generation means" means a means for generating frames from the video received by the reception means and preparing them for analysis.

[1101] 3. "Analysis means" refers to a means for determining violations based on the generated frames using the specified cleanliness standards.

[1102] 4. "Report generation means" means a means for generating a report based on the results of the analysis means.

[1103] 5. "Notification means" means a means for notifying the user of the generated report.

[1104] 6. "Reconfirmation means" refers to a means for a user to confirm corrections by taking a photo of the corrected state again and uploading it.

[1105] 7. "User" refers to a store crew member who uses the system to conduct cleanliness checks.

[1106] 8. "Mobile device" refers to a mobile device operated by a user, such as a smartphone or tablet.

[1107] 9. "Server" means a computer system that performs the functions of receiving video, generating frames, analyzing, generating reports, and notifying.

[1108] 10. "Cleanliness Standards" means the prescribed standards established to judge the cleanliness of a store.

[1109] The system embodying the present invention has a program for effectively managing the cleanliness of a store. The components of the system and their operation will be described below.

[1110] System Configuration

[1111] The system mainly consists of the following components:

[1112] 1. The user's mobile device

[1113] Users take and upload videos using their smartphones or tablets.

[1114] 2. Server

[1115] The server includes a receiving means, a generating means, an analyzing means, a report generating means, a notifying means, and a reconfirming means, and controls the entire process.

[1116] System Operation

[1117] Video reception and frame generation

[1118] The user's mobile device records the cleanliness status inside and outside the store as video. This video is uploaded to the server using the receiving means. The server divides the received video into frames and prepares them for analysis using the frame generating means.

[1119] Video analysis

[1120] The server's analysis means analyzes each frame based on cleanliness standards and identifies violations. The analysis means uses OpenCV, an image processing library, to detect abnormalities within the frames.

[1121] Report generation and notification

[1122] Based on the results of the analysis, a report is automatically generated by the report generation means. The report includes details of the identified cleanliness violations. The generated report is sent to the user's mobile device using the notification means.

[1123] Corrections and reconfirmation

[1124] Based on the report, the user corrects any cleanliness violations in the store. After the corrections are complete, the user shoots the video again and uploads it to the server via a reconfirmation tool. The server then analyzes the frames again to confirm that the corrections have been made properly.

[1125] Hardware and software used

[1126] Hardware: Smartphones, servers

[1127] Software: Flask (web framework), OpenCV (image processing library)

[1128] Specific examples

[1129] A user takes a video of the area around the trash can in the store with their smartphone and uploads the video to the server via the app. The server analyzes the video and generates a report stating that "the trash can is overflowing" and notifies the user. After the user has cleared the trash, they can take another video and upload it to the server, and receive a notification that "the problem has been resolved."

[1130] Prompt Sentence Examples

[1131] Please conduct a cleanliness check around the trash cans in your store. Upload the video and have it analyzed on the server. If there are any violations, a report will be automatically generated and notified. Please take appropriate action based on the cleanliness standards and record the video again to double-check.

[1132] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1133] Step 1:

[1134] The user takes a video of the cleanliness situation inside and outside the store using a smartphone. The input here is the video file taken by the user, and the output is the video file that will be uploaded to the server.

[1135] Step 2:

[1136] The terminal uploads the captured video file to the server using the receiving means. The path to the video file is input to the terminal, and the data is sent to the server. The output is a video file saved on the server.

[1137] Step 3:

[1138] The server divides the video uploaded by the receiving means into frames. Here, the video file is the input, and the divided multiple frame images are the output. Specifically, the OpenCV library is used to break down the video into frames, and each frame is saved in memory.

[1139] Step 4:

[1140] The server's analysis means analyzes the generated frames and identifies abnormalities based on the cleanliness criteria. The input to this step is the frame images, and the output is the analysis result of whether each frame meets the cleanliness criteria. For example, OpenCV is used to determine whether dust is present in the image.

[1141] Step 5:

[1142] The server creates a report based on the analysis results using a report generation means. The input here is the analysis results, and the output is a report file. The report includes details of the violations.

[1143] Step 6:

[1144] The server sends the generated report to the user's smartphone via a notification method. The input of this step is the report file, and the output is the process of notifying the user's device. Specifically, the report is sent using email or the app's notification function.

[1145] Step 7:

[1146] The user checks the report and corrects any cleanliness violations that are pointed out. The input here is the report content, and the output is the state of the store after the corrections are made.

[1147] Step 8:

[1148] The user then takes another video of the corrected state with their smartphone and uploads the video to the server. The input here is the newly taken video file, and the output is the corrected video file sent to the server.

[1149] Step 9:

[1150] The server splits the received corrected video into frames again and rechecks it using an analysis method. The input here is the corrected video file, and the output is the result of the reanalysis of the frames. It is again determined whether the corrections were made properly.

[1151] Step 10:

[1152] The server then notifies the user based on the final analysis result whether the corrections were successful. The input to this step is the reanalysis result, and the output is a notification that "corrections are complete" or "recorrections are required."

[1153] Through these steps, the system will be able to automate and efficiently manage store cleanliness checks.

[1154] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1155] The cleanliness self-check system of the present invention automatically analyzes the cleanliness status based on video footage taken by a user (e.g., a store crew member) and identifies any violations. By combining this system with an emotion engine, it is possible to recognize the user's emotional state and provide feedback accordingly. Detailed embodiments of the present invention are described below.

[1156] System Configuration

[1157] This system consists of the following main components:

[1158] 1. User's device

[1159] A mobile device such as a smartphone or tablet operated by a user, used to capture and upload video and receive notifications.

[1160] 2. Server

[1161] The server includes the following means:

[1162] Receiving means: Receives videos uploaded by users.

[1163] Generation method: Divide the video into frames.

[1164] Analysis method: Analyze the frame to determine if there are any cleanliness violations.

[1165] Notification method: A report is generated based on the judgment results and notified to the user.

[1166] Emotion engine: Recognizes user emotions and adjusts feedback accordingly.

[1167] Program processing

[1168] Video reception

[1169] The user uses the device to record the cleanliness status inside and outside the store. The recorded video is uploaded to the server via the application. The server's receiving means receives and stores the video.

[1170] Examples:

[1171] Users take videos on their devices titled "Store Afternoon Cleanliness Check" and upload them to the server via the app.

[1172] Frame Generation

[1173] The server divides the received video into frames, and the generating means generates frames at regular intervals per second and converts them into data for analysis.

[1174] Examples:

[1175] The server divides the three-minute video into 180 frames and saves each frame as an image file.

[1176] Video analysis

[1177] The server's analysis means inputs each frame into the generation AI, which determines whether or not there is a violation based on the cleanliness standards. The results are recorded in detail, detailing which areas have violations and what kind of violations have occurred.

[1178] Examples:

[1179] At frame 45, it detects that there is trash on the table in the eating area.

[1180] Emotion recognition

[1181] The emotion engine recognizes the user's emotions when shooting video. The emotion engine analyzes the user's emotions from their facial expressions and tone of voice, and sends that information to the analysis means.

[1182] Examples:

[1183] If the user is feeling frustrated or tired while shooting a video, the emotion engine will detect it.

[1184] Generate reports

[1185] The analysis means generates a report based on the information from the emotion engine, which includes details of the violation and feedback that takes into account the user's emotions.

[1186] Examples:

[1187] A report will be generated such as, "Garbage has been detected on the table in the dining area. Thank you for your hard work, please clean this up."

[1188] Notifications and Feedback

[1189] The server's notification means sends the report to the user's terminal, where the user can check the report and make any necessary corrections.

[1190] Examples:

[1191] The user checks the report on their device and decides on a countermeasure, such as "cleaning up the trash on the tables in the dining area."

[1192] Reconfirmation

[1193] After completing the corrections, the user shoots the video again and uploads it to the server, which then analyzes the video again in the same way to confirm that the corrections were made properly.

[1194] Examples:

[1195] After the user cleans up the dust, they record the corrected state on video again and upload it to the server, where it analyzes it again and notifies them that the problem has been solved.

[1196] This system allows users to efficiently perform cleanliness checks and quickly correct any violations. In addition, the introduction of an emotion engine provides feedback that takes into account the user's emotions, reducing the burden of the work.

[1197] The processing flow will be explained below.

[1198] Step 1:

[1199] The user uses the device to take video of the inside and outside of the store. The user launches the dedicated application and presses the capture button to capture the area to be checked.

[1200] Step 2:

[1201] The user uploads the video they have taken to the server. The user presses the "Upload" button in the application to send the video file to the server.

[1202] Step 3:

[1203] The server receives and stores the uploaded video. The receiving means receives the video file and stores it in a specific folder in the server.

[1204] Step 4:

[1205] The server divides the received video into frames. The generation means divides the video into frames at regular intervals (for example, every second) and saves each frame as an image file.

[1206] Step 5:

[1207] The server inputs each frame into the analysis AI, which then passes each generated frame to the AI ​​model in turn, which analyzes it based on cleanliness criteria.

[1208] Step 6:

[1209] The generator AI analyzes each frame to determine whether there are any cleanliness violations. The AI ​​model checks each element within the frame to detect anomalies such as dust or illegal pop-ups.

[1210] Step 7:

[1211] The server also sends the analysis results to the emotion engine, which analyzes the user's emotions. The emotion engine analyzes the user's facial expressions and tone of voice to recognize their emotions.

[1212] Step 8:

[1213] The server generates a report based on the analysis results and emotional information, which includes any cleanliness violations and feedback that takes the user's emotions into consideration.

[1214] Step 9:

[1215] The server notifies the user of the generated report, and the notification means transmits the contents of the report to the user's terminal and instructs the user to make corrections.

[1216] Step 10:

[1217] The user checks the report and corrects any violations that are reported. Based on the report on the terminal, the user can take appropriate action to resolve any cleanliness violations inside and outside the store.

[1218] Step 11:

[1219] The user shoots the video again and uploads the corrected state to the server. The user then starts the application again, shoots the checked area again, and sends it to the server.

[1220] Step 12:

[1221] The server receives, stores, and analyzes the re-uploaded video. It reprocesses the video using the same receiving, generating, and analyzing means as the first time, and verifies that the corrections were made appropriately.

[1222] Step 13:

[1223] The server notifies the user based on the results of the reanalysis. It checks whether the corrections were made appropriately based on the analysis results, and if the problem has been resolved, it sends a final notification to the user, and if additional corrections are required, it sends instructions to the user.

[1224] Example 2

[1225] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1226] Conventional cleanliness check systems allow users to simply check the results of their cleaning, making it difficult to efficiently check and improve. Furthermore, they do not provide feedback that takes into account the user's emotions or fatigue, which increases the burden of the work. There is a need for a system that recognizes the user's emotional state in real time and provides feedback that takes those emotions into consideration, thereby realizing efficient and less burdensome cleanliness checks.

[1227] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1228] In this invention, the server includes receiving means for receiving the captured video, generating means for generating frames from the video received by the receiving means, analyzing means for analyzing the generated frames and making a judgment based on specified criteria, generating means for generating a report based on the judgment results, notifying means for notifying the generated report, emotion recognition means for recognizing the emotion of the user recording the video, and feedback means for adjusting the feedback content based on emotion data recognized by the emotion recognition means. This makes it possible to efficiently identify violations and provide feedback that takes the user's emotions into consideration.

[1229] The "receiving means" is a function for receiving video data uploaded to the server from the user's mobile terminal.

[1230] The "generating means" is a function that generates frames from the video data received by the receiving means and converts the frames into a format suitable for analysis.

[1231] The "analysis means" is a function that inputs the generated frame into the generation AI model and determines whether or not there is a violation based on cleanliness standards.

[1232] The "report generation means" is a function that generates a document to report the violation location and its details to the user based on the judgment results obtained by the analysis means.

[1233] The "notification means" is a function that sends the generated report to the user's mobile terminal and notifies the user.

[1234] The "emotion recognition means" is a function for recognizing the user's emotional state during video shooting from facial expressions and tone of voice.

[1235] The "feedback means" is a function that adjusts the contents of reports and notifications in a way that takes into consideration the user's emotions, based on the emotion data recognized by the emotion recognition means.

[1236] The cleanliness self-check system of the present invention automatically analyzes the cleanliness status based on the video taken by the user and identifies any violations. In addition, by combining it with an emotion engine, it is possible to recognize the user's emotional state and provide feedback that takes those emotions into consideration.

[1237] System Configuration

[1238] This system consists of the following main components:

[1239] 1. User's device

[1240] A mobile device such as a smartphone or tablet operated by the user, which is used to capture and upload video and receive notifications of analysis results.

[1241] 2. Server

[1242] The server includes the following means:

[1243] Receiving means: A function to receive videos uploaded by users.

[1244] Generation method: A function that generates frames from received video.

[1245] Analysis method: The generated frames are analyzed to determine whether cleanliness violations exist. This uses a generative AI model.

[1246] Report generation means: A function to generate a report based on the judgment results.

[1247] Notification method: A function to send the generated report to the user's terminal.

[1248] Emotion recognition: A function that recognizes the emotions of the user when recording video. It analyzes facial expressions and tone of voice.

[1249] Feedback means: A function that adjusts the feedback content based on emotional data from the emotion recognition means.

[1250] Filming and uploading footage

[1251] Users use their mobile devices to record video of the cleanliness status inside and outside the store. The video is then uploaded to the server via a dedicated application. For example, a user can record a video of an "afternoon cleanliness check" and press the send button on the application to upload the video data to the server.

[1252] Video reception, frame generation and analysis

[1253] The server's receiving means receives and saves the uploaded video. Next, the server's generating means divides the video into frames. For example, a three-minute video is divided into frames every second, and all of the frames are saved as JPEG image files. The server's analyzing means inputs the generated frames into a generative AI model and analyzes each frame based on cleanliness standards. It determines whether or not there is a cleanliness violation and records the violation in detail. For example, if garbage is detected on a table in the eating and drinking area in frame 45, the result is recorded on the table.

[1254] Emotional Recognition and Feedback

[1255] The emotion recognition means analyzes the user's emotions while shooting video. It detects the user's emotions from facial expressions and tone of voice and sends that information to the server. For example, if the user expresses fatigue while shooting, the emotion recognition means will determine that the user is "feeling tired." The feedback means adjusts the feedback content based on the emotional data. For example, it provides feedback in the form of "Thank you for your hard work. Please clean this area."

[1256] Report generation and notification

[1257] The report generation means generates a report based on the judgment result obtained by the analysis means and the information from the emotion recognition means. The generated report is sent to the user's mobile device by the notification means. The user checks the report and makes any necessary corrections. For example, the user may decide to "clean up the trash on the tables in the dining area" and then carry out the cleaning.

[1258] Hardware and software used

[1259] Hardware: smartphones, tablets, servers

[1260] Software: Generative AI models, emotion engines, dedicated applications

[1261] Example prompts for generative AI models

[1262] "Detect cleanliness violations from user-captured footage."

[1263] "Analyze each frame in the video and identify areas where there are violations."

[1264] This allows users to efficiently perform cleanliness checks and quickly correct violations. Furthermore, by using an emotion engine, feedback is given taking into account the user's emotions, reducing the burden of the work.

[1265] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1266] Step 1:

[1267] The user uses the device to record the cleanliness conditions inside and outside the store. Specifically, the user launches a dedicated application and records video using the camera function. The input data is the video that was recorded, and the output is a video file saved on the device.

[1268] Step 2:

[1269] The user presses the send button in the application to upload the captured video data to the server. The input data is the video file stored on the device, and the output is the video data transferred to the server. Specifically, the user clicks the "upload" button to start the data transfer process.

[1270] Step 3:

[1271] The server's receiving means receives and stores the uploaded video. The input data is the video data uploaded by the user, and the output is a video file stored in the server's database. The user is notified that the receiving process has been completed successfully.

[1272] Step 4:

[1273] The server's generation means divides the received video into frames. Specifically, it converts the video into still images at a rate of one frame per second and saves all frames as image files. The input data is the video file saved on the server, and the output is a collection of divided frame images.

[1274] Step 5:

[1275] The server's analysis means inputs the generated frames into the generative AI model, which judges whether or not there is a violation for each frame based on the cleanliness criteria. The input data are the divided frame images, and the output is the analysis result (whether or not there is a violation and its details). Specifically, each frame is input into the AI ​​model in sequence, and the judgment result is obtained.

[1276] Step 6:

[1277] The emotion recognition means analyzes the user's emotional state when the video is being taken. The input data is the user's facial expression and tone of voice, and the output is the analysis result of the emotional state. Specifically, it recognizes emotions using a facial expression analysis algorithm and a voice emotion analysis algorithm, and saves the results.

[1278] Step 7:

[1279] The report generation means generates a report based on the data from the analysis means and emotion recognition means. The input data are the violation analysis results and the emotional state analysis results, and the output is the generated report. Specifically, the report reflecting the detailed information of the violation and the user's emotional state is generated according to a template.

[1280] Step 8:

[1281] The notification means sends the generated report to the user's device. The input data is the generated report, and the output is the report received by the user's device. Specifically, the generated report is sent to the user via email or an in-app notification function.

[1282] Step 9:

[1283] The user checks the report on the terminal and makes any necessary corrections. The input data is the received report, and the output is the corrected cleanliness status. The user cleans specific areas according to the instructions in the report and checks the results.

[1284] Step 10:

[1285] The user then records the situation after the correction work on video again and uploads it to the server. The input data is the corrected video, and the output is the re-uploaded video data stored on the server. Specifically, the user uses the dedicated app to record video again and execute the upload process.

[1286] Step 11:

[1287] The server then re-analyzes the video using the same procedure to confirm whether the corrections were made properly. The input data is the frame image for re-analysis, and the output is the re-analysis result (whether the problem was resolved or not). The final analysis result is notified to the user.

[1288] (Application example 2)

[1289] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the headset type terminal 314 will be referred to as a "terminal."

[1290] Checking cleanliness and identifying violations is often done manually, which takes time and effort. It also leaves users feeling fatigued and stressed, making it difficult to work efficiently. Furthermore, it is difficult to provide feedback that takes into account the user's emotions when reporting violations, which can lead to a decrease in motivation and an increase in stress.

[1291] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a receiving means for receiving captured video, a generating means for generating frames from the video received by the receiving means, an analyzing means for analyzing the generated frames and making a judgment based on specified criteria, a generating means for generating a report based on the judgment results, a notifying means for notifying the generated report, an emotion analyzing means for analyzing the user's emotions, and a feedback adjusting means for adjusting the feedback content based on information from the emotion analyzing means. This makes it possible to automate cleanliness checks, quickly and accurately identify violations, and provide feedback that takes the user's emotions into consideration.

[1292] The "receiving means" is a device or system that receives the captured video from the mobile terminal operated by the user.

[1293] The "generating means" is a device or program that generates frames from the video received by the receiving means.

[1294] The "analysis means" is a device or program that analyzes the generated frames and makes a judgment based on a specified standard.

[1295] The "report generation means" is a device or program that generates a report based on the determination results of the analysis means.

[1296] A "notification means" is a device or system that transmits the generated report to the user's terminal.

[1297] The "emotion analysis means" is a device or program that analyzes the user's emotions.

[1298] The "feedback adjustment means" is a device or program that adjusts the feedback content based on information from the emotion analysis means.

[1299] "Cleanliness" is a term that refers to the cleanliness of a particular area.

[1300] A "frame" refers to a portion of an image that divides a video into a single moment on the time axis.

[1301] MODE FOR CARRYING OUT THE INVENTION

[1302] System Configuration

[1303] The cleanliness self-check system of the present invention is composed of the following main components:

[1304] 1. User's device

[1305] A mobile device operated by a user, including a smartphone or tablet, used to capture and upload video and receive notifications.

[1306] 2. Server

[1307] The server is a system including the following means:

[1308] Receiving means: Receives videos uploaded by users.

[1309] Generation method: Divide the video into frames.

[1310] Analysis method: Analyze the frame to determine if there are any cleanliness violations.

[1311] Report generation means: Generates a report based on the judgment results.

[1312] Notification method: The generated report is sent to the user's terminal.

[1313] Sentiment analysis means: Analyzes the user's emotions.

[1314] Feedback adjustment means: Adjust the feedback content based on the information from the sentiment analysis means.

[1315] Program processing and hardware / software

[1316] 1. Receiving video

[1317] Users use their smartphones to record the cleanliness status inside and outside the store. The recorded video is uploaded to a server via a mobile device application. The server's receiving means receives and stores the video. In this case, it is desirable for the application to be developed using a framework such as Flutter or React Native.

[1318] 2. Frame Generation

[1319] The server divides the received video into frames. The generator generates frames at regular intervals every second and converts them into data for analysis. This process is performed using Python and image processing libraries such as OpenCV.

[1320] 3. Video Analysis

[1321] The server's analysis tool feeds each frame into a generative AI model (e.g., YOLO or TensorFlow) to determine whether there are any violations based on cleanliness criteria. Any violations detected are logged in detail.

[1322] 4. Emotion Analysis

[1323] The emotion analysis means analyzes the emotions expressed by the user when they shoot video. This uses emotion recognition engines such as Microsoft Azure Cognitive Services and Affectiva. The emotion is analyzed from the user's facial expressions and tone of voice, and the information is sent to the analysis means.

[1324] 5. Generate reports

[1325] Based on the judgment result and the emotion analysis result, the report generation means generates a report, which includes details of the violation and feedback that takes into account the user's emotions.

[1326] 6. Notifications and Feedback

[1327] The server's notification means sends the generated report to the user's terminal, where the user checks the report and makes any necessary corrections.

[1328] Examples of concrete examples and prompts

[1329] Examples:

[1330] Users film a video titled "Store Afternoon Cleanliness Check" on their smartphone and upload it to the server via the app. The server divides the three-minute video into frames and, in the process of analyzing each frame, detects the presence of trash on the table in the dining area. If the user feels tired while filming the video, the emotion analysis engine detects this and provides feedback such as, "Thank you for your hard work. There is trash on the table in the dining area. Please clean it up."

[1331] Example prompt sentence:

[1332] We have taken video footage to check the cleanliness of our store. Please analyze the video below and identify any cleanliness violations.

[1333] Video URL: [URL of uploaded video]

[1334] The analysis results should include details of the violation (e.g., there is trash on the table in the dining area) and feedback based on the staff member's emotional state (e.g., tired, annoyed). For example, "Thank you for your hard work. There is trash on the table in the dining area. Please clean it up."

[1335] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1336] Step 1:

[1337] The user shoots the video using a smartphone

[1338] Users use their smartphones to take videos to check the cleanliness status inside and outside the store. The videos are saved in the application. The input here is the video that was taken, and the output is the video data saved in the smartphone.

[1339] Step 2:

[1340] Uploading video from a smartphone to a server

[1341] Users upload captured video to a server using a smartphone app. The app sends the video data to the server via an internet connection. The input here is the video data stored on the smartphone, and the output is the video data received by the server.

[1342] Step 3:

[1343] The server divides the video into frames

[1344] The server receives the uploaded video data using a receiving means. Then, it divides the video into frames using a generating means. For example, if a three-minute video is divided into 30 frames per second, 5,400 frames are generated. The input is the video data received by the server, and the output is image data for each frame.

[1345] Step 4:

[1346] The server analyzes the frames and identifies cleanliness violations

[1347] The server uses an analysis method to analyze each generated frame. This analysis uses a generative AI model (e.g., YOLO or TensorFlow) to determine whether there are any violations based on specific cleanliness criteria. The input is the image data for each frame, and the output is the data with the violations identified.

[1348] Step 5:

[1349] The server analyzes the user's emotions

[1350] Emotion analysis tools are used to analyze facial expressions and tone of voice when a user shoots a video. For example, services from Microsoft Azure Cognitive Services or Affectiva are used. The input is the user's facial expressions and voice data, and the output is analyzed emotion data.

[1351] Step 6:

[1352] The server generates the report

[1353] Based on the results of the analysis means and the sentiment analysis means, the report generation means creates a report. The report includes details of the detected cleanliness violations and feedback that takes into account the user's sentiment. The input is data on the violation locations and sentiment data, and the output is the generated report.

[1354] Step 7:

[1355] The server notifies the report

[1356] The server sends the generated report to the user's smartphone using a notification means. The user receives the notification and checks the contents of the report. The input is the generated report, and the output is the report notified to the user.

[1357] Step 8:

[1358] The user makes corrections based on the report.

[1359] Based on the notified report, the user corrects any cleanliness violations within the store. For example, cleaning up trash on the tables in the dining area. The input is the content of the report, and the output is the actual cleaning work.

[1360] Step 9:

[1361] The user takes another photo of the corrected state and uploads it to the server.

[1362] The user then uses their smartphone to record the cleanliness of the area after the corrections and uploads the video to the server. The server then analyzes the video again to confirm that the corrections were made appropriately. The input is the re-recorded video data, and the output is the video data that has been re-uploaded to the server.

[1363] 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.

[1364] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1365] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the headset type terminal 314.

[1366] [Fourth embodiment]

[1367] FIG. 7 shows an example of the configuration of a data processing system 410 according to the fourth embodiment.

[1368] 7, a data processing system 410 includes a data processing device 12 and a robot 414. An example of the data processing device 12 is a server.

[1369] The data processing device 12 includes a computer 22, a database 24, and a communication I / F 26. The computer 22 is an example of a "computer" according to the technology of the present disclosure. The computer 22 includes a processor 28, a RAM 30, and a storage 32. The processor 28, the RAM 30, and the storage 32 are connected to a bus 34. The database 24 and the communication I / F 26 are also connected to the bus 34. The communication I / F 26 is connected to a network 54. Examples of the network 54 include a WAN (Wide Area Network) and / or a LAN (Local Area Network).

[1370] 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.

[1371] The microphone 238 receives instructions and the like from the user 20 by receiving voice uttered by the user 20. The microphone 238 captures the voice uttered by the user 20, converts the captured voice into audio data, and outputs it to the processor 46. The speaker 240 outputs audio in accordance with instructions from the processor 46.

[1372] Camera 42 is a small digital camera equipped with an optical system including a lens, aperture, and shutter, and an imaging element such as a CMOS (Complementary Metal-Oxide-Semiconductor) image sensor or a CCD (Charge Coupled Device) image sensor, and captures images of the surroundings of user 20 (for example, an imaging range defined by an angle of view equivalent to the field of vision of a typical healthy person).

[1373] 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.

[1374] The control object 443 includes a display device, LEDs in the eyes, and motors for driving the arms, hands, and feet. The posture and gestures of the robot 414 are controlled by controlling the motors of the arms, hands, and feet. Some of the emotions of the robot 414 can be expressed by controlling these motors. In addition, the facial expressions of the robot 414 can also be expressed by controlling the light emission state of the LEDs in the eyes of the robot 414.

[1375] 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.

[1376] The specific processing program 56 is an example of a "program" according to the technology of the present disclosure. The processor 28 reads the specific processing program 56 from the storage 32 and executes the read specific processing program 56 on the RAM 30. The specific processing is realized by the processor 28 operating as a specific processing unit 290 in accordance with the specific processing program 56 executed on the RAM 30.

[1377] 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.

[1378] In the robot 414, the processor 46 performs the reception output process. A reception output program 60 is stored in the storage 50. The processor 46 reads the reception output program 60 from the storage 50 and executes the read reception output program 60 on the RAM 48. The reception output process is realized by the processor 46 operating as the control unit 46A in accordance with the reception output program 60 executed on the RAM 48.

[1379] Next, a description will be given of the specific processing performed by the specific processing unit 290 of the data processing device 12. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1380] The cleanliness self-check system of the present invention uses video footage taken by store staff to automatically analyze the cleanliness inside and outside a store, identify any violations, and prompt a prompt response. Hereinafter, an embodiment of the present invention will be described.

[1381] System Configuration

[1382] This system mainly consists of the following components:

[1383] 1. User's device

[1384] Users (store crew) use mobile devices such as smartphones and tablets to shoot and upload videos.

[1385] 2. Server

[1386] The server includes a receiving means, a generating means, an analyzing means, and a notifying means, and receives and analyzes the video, and generates and notifies the report. The program running on the server functions as follows.

[1387] Program processing

[1388] Video reception

[1389] Users use their mobile devices to record video of the cleanliness conditions inside and outside the store. The recorded video is uploaded to the server via the application. The server receives the video via a receiving means and stores it.

[1390] Examples:

[1391] Users use their device to take pictures of the inside and outside of the store in the morning under the title "Comprehensive Store Cleanliness Check," and then upload the footage to the server via the app.

[1392] Frame Generation

[1393] The server divides the received video into frames, and the generating means converts the video into individual frames and prepares them for analysis.

[1394] Examples:

[1395] The server divides the five-minute video into 300 frames and stores each frame.

[1396] Video analysis

[1397] The server's analysis means sequentially analyzes each frame and determines whether there is a violation based on the cleanliness criteria. The analysis means checks each frame using the pre-defined cleanliness criteria to detect anomalies.

[1398] Examples:

[1399] At frame 123, it detects that there is trash under the front desk.

[1400] Generate reports

[1401] The analysis tool generates a report based on the results of the analysis, which includes the location of the violation and its details.

[1402] Examples:

[1403] A report is generated stating, "Garbage has been detected under the front desk" or "Unnecessary POPs have been placed in a corner of the warehouse."

[1404] Notifications and Feedback

[1405] The server sends the generated report to the user's terminal using a notification means, and the user receives the report and makes any necessary corrections.

[1406] Examples:

[1407] The user checks the report on the terminal and decides on a countermeasure, such as "I will clean up the trash under the front desk."

[1408] Reconfirmation

[1409] After completing the corrections, the user shoots the video again and uploads it to the server, which then analyzes it again using the receiving means and analyzing means to confirm that the corrections have been made appropriately.

[1410] Examples:

[1411] After the user cleans up the dust, they record the corrected state on video again and upload it to the server, where it analyzes it again and notifies them that the problem has been solved.

[1412] In this way, the system automates cleanliness self-checks and achieves efficient and highly accurate management.

[1413] The processing flow will be explained below.

[1414] Step 1:

[1415] The user uses the device to capture video inside and outside the store. The user launches the application, presses the record button, and captures the area to be checked.

[1416] Step 2:

[1417] The user uploads the video they have taken to the server. The user presses the "Upload" button in the application, selects the video file, and sends it to the server.

[1418] Step 3:

[1419] The server receives and stores the uploaded video. The receiving means receives the video and stores it in a dedicated folder in the server.

[1420] Step 4:

[1421] The server divides the received video into frames. The generation means divides the video into frames at regular intervals (for example, every second) and saves each frame as an image file.

[1422] Step 5:

[1423] The server inputs each frame into the generation AI, and the analysis means passes each generated frame to the AI ​​model in sequence, which analyzes it based on cleanliness criteria.

[1424] Step 6:

[1425] The generator AI analyzes each frame to determine whether there are any cleanliness violations. The AI ​​model checks each element within the frame to detect anomalies such as dust or illegal pop-ups.

[1426] Step 7:

[1427] The server receives the analysis results. The analysis means receives the result data from the generation AI and records the violations and their details.

[1428] Step 8:

[1429] The server generates a report based on the analysis results. The generation method compiles a list of the identified violations and creates a report that lists the specific issues and how to correct them.

[1430] Step 9:

[1431] The server notifies the user of the report, and the notification means transmits the generated report to the user's terminal and instructs the user to make corrections.

[1432] Step 10:

[1433] The user checks the report and corrects any violations that are reported. Based on the report on the terminal, the user can take appropriate action to resolve any cleanliness violations inside and outside the store.

[1434] Step 11:

[1435] The user shoots the video again and uploads the corrected state to the server. The user then starts the application again, shoots the checked area again, and sends it to the server.

[1436] Step 12:

[1437] The server receives, stores, and analyzes the re-uploaded video. It reprocesses the video using the same receiving, generating, and analyzing means as the first time, and verifies that the corrections were made appropriately.

[1438] Step 13:

[1439] The server notifies the user based on the reanalysis results. If the corrections are appropriate based on the analysis results, the server notifies the user of the completion, and if additional corrections are required, the server sends instructions to the user.

[1440] This step allows store crews to efficiently automate cleanliness checks and instantly correct any violations.

[1441] Example 1

[1442] Next, a description will be given of Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1443] The current mainstream method of cleanliness management involves store staff manually checking the inside and outside of the store, identifying and reporting any problems. However, this method is time-consuming and prone to human error. Furthermore, delayed feedback can mean that problems are left unaddressed for long periods of time when a prompt response is required. To solve these issues, a system that can efficiently and accurately perform cleanliness checks is needed.

[1444] The specific processing by the specific processing unit 290 of the data processing device 12 in the first embodiment is realized by the following means.

[1445] In this invention, the server includes a receiving means for receiving the captured video, a generating means for generating frames from the video received by the receiving means, an analyzing means for analyzing the generated frames and making a judgment based on specified criteria, a report generating means for generating a report based on the judgment result, a notifying means for notifying the generated report, and a reanalysis means for reanalyzing the re-captured video and notifying the reanalysis result. This not only automates the cleanliness check but also enables quick and accurate feedback.

[1446] "Receiving means" refers to a device or system that has the function of receiving captured images.

[1447] The "generating means" refers to a device or system that has the function of converting the video received by the receiving means into individual frames for analysis.

[1448] "Analysis means" refers to a device or system that has the function of checking the generated frames based on specified cleanliness standards and determining whether or not there are any violations.

[1449] The "report generation means" refers to a device or system that has the function of creating a report detailing the violation based on the determination results from the analysis means.

[1450] The "notification means" refers to a device or system that has the function of notifying the user of the generated report.

[1451] "Reanalysis means" refers to a device or system that has the function of reanalyzing the re-shot video after correction and notifying the results.

[1452] The cleanliness self-check system of the present invention is a system in which a server analyzes video taken by a user, automatically checks the cleanliness inside and outside a store, identifies any violations, and prompts prompt action. A specific embodiment of this system is described below.

[1453] The system mainly consists of the following components:

[1454] 1. User's device

[1455] Users use mobile devices such as smartphones and tablets to capture and upload videos.

[1456] 2. Server

[1457] The server receives and analyzes the video, generates and notifies reports, and has the functions of a receiving means, a generating means, an analyzing means, a report generating means, a notifying means, and a re-analysis means.

[1458] In terms of specific hardware, users can use the latest smartphones (e.g., Android models or iPhones) as their devices. The server is operated on a high-performance cloud server (e.g., AWS or Azure), and AI models and image analysis libraries such as TensorFlow and OpenCV are used as analysis methods.

[1459] As a specific example, the system operates in the following manner.

[1460] 1. Filming and uploading the footage

[1461] Users use their mobile devices to record video of the cleanliness conditions inside and outside the store, and once the recording is complete, upload the video to the server through the application.

[1462] Specific operation examples:

[1463] The user launches the app, selects "New Cleanliness Check," takes photos of the inside and outside of the store, and presses the "Upload Video" button.

[1464] 2. Receiving and storing video

[1465] The server receives the uploaded video using the receiving means, and the video is stored in the server's storage.

[1466] Specific behavior:

[1467] The server displays "Receiving video data," and when reception is complete, records "Data saving completed."

[1468] 3. Video frame generation

[1469] The server uses a generation means to divide the stored video into frames, and prepares for analysis.

[1470] Specific behavior:

[1471] The server divides the five minutes of footage into 60 frames per second, generating and storing a total of 300 frames.

[1472] 4. Frame Analysis

[1473] The server's analysis means sequentially analyzes each frame and determines whether there is a violation based on the cleanliness criteria.

[1474] Specific behavior:

[1475] The server uses an AI model (e.g., TensorFlow) to detect debris and clutter in each frame and flags the frame if there is an anomaly.

[1476] 5. Generate reports

[1477] The server's report generation means generates a report based on the analysis results, which includes the violations and their details.

[1478] Specific behavior:

[1479] A report will be generated in PDF format stating, "Debris was detected under the front desk," along with an image of the frame in question.

[1480] 6. Notifications and Feedback

[1481] The report is sent to the user's terminal using a notification means, where the user can review the report and make any necessary corrections.

[1482] Specific operation examples:

[1483] The user checks the report on the terminal and provides feedback such as, "I will clean up the trash under the front desk."

[1484] 7. Re-imaging and re-analysis

[1485] After completing the corrections, the user shoots the video again and uploads it to the server, which then reanalyzes it to verify that the corrections were made properly.

[1486] Specific operation examples:

[1487] The user cleans up the junk and uploads the footage again. The server re-analyzes it and notifies the user that the problem has been resolved.

[1488] Example prompt sentence:

[1489] "A comprehensive cleanliness check of the store revealed trash under the front desk. Please clean up the trash, retake footage and report the results."

[1490] In this way, the system automates the cleanliness check process and provides fast and accurate feedback, allowing for effective management of store cleanliness.

[1491] The flow of the identification process in the first embodiment will be described with reference to FIG.

[1492] Step 1:

[1493] Filming and uploading footage

[1494] Users use their mobile devices to record video of the cleanliness conditions inside and outside the store, and once the recording is complete, upload the video to the server via a dedicated application.

[1495] Input: Video file (recording data)

[1496] Output: Upload video files to the server

[1497] Specific behavior:

[1498] The user launches the app, selects "New Cleanliness Check" and starts recording. After recording, they press the "Upload Video" button to send the video to the server.

[1499] Step 2:

[1500] Receiving and storing video

[1501] The server receives the uploaded video using the receiving means, and the video is stored in the server's storage.

[1502] Input: Uploaded video file

[1503] Output: Video data stored on the server

[1504] Specific behavior:

[1505] The server receives the video data sent from the app and displays "Receiving video data." After reception is complete, it records "Data saving completed."

[1506] Step 3:

[1507] Video frame generation

[1508] The server uses a generation method to divide the stored video into frames, which are then ready for analysis.

[1509] Input: Stored video data

[1510] Output: Image data divided into frames

[1511] Specific behavior:

[1512] The server splits the five-minute video into 60 frames per second, generating a total of 300 frames, each stored in a dedicated folder.

[1513] Step 4:

[1514] Frame Analysis

[1515] The server's analysis means sequentially analyzes each frame and determines whether there is a violation based on the cleanliness criteria.

[1516] Input: Image data divided into frames

[1517] Output: Analysis results for each frame (whether or not there is a violation)

[1518] Specific behavior:

[1519] The server uses an AI model (e.g., TensorFlow) to detect debris and clutter in each frame and flags the frame if there is an anomaly.

[1520] Step 5:

[1521] Generate reports

[1522] The server's report generation means generates a report based on the analysis results, which includes the violation location and its details.

[1523] Input: Analysis results

[1524] Output: Cleanliness Violation Report

[1525] Specific behavior:

[1526] The server generates a report in PDF format stating, "Debris was detected under the front desk," along with an image of the frame in question.

[1527] Step 6:

[1528] Notifications and Feedback

[1529] The server sends the generated report to the user's terminal using a notification means, and the user receives the report and takes appropriate measures.

[1530] Input: Cleanliness Violation Report

[1531] Output: Report notification to user, feedback record

[1532] Specific behavior:

[1533] The server sends the report to the user's device via email or push notification. The user checks the report and provides feedback such as, "I will clean up the trash under the front desk."

[1534] Step 7:

[1535] Re-imaging and re-analysis

[1536] After the user has completed the corrections, they shoot the video again and upload it to the server, where it will be reanalyzed to confirm that the corrections were made properly.

[1537] Input: Corrected video data

[1538] Output: Reanalysis results, final notification

[1539] Specific behavior:

[1540] After making the corrections, the user selects "Check after corrections" to shoot the video again and upload it to the server. The server then reanalyzes the video and notifies the user that the problem has been resolved.

[1541] (Application example 1)

[1542] Next, a description will be given of Application Example 1. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1543] To maintain the cleanliness of a store, it is important to regularly check the situation, quickly identify problem areas, and take measures. However, conventional methods for cleanliness checks are inefficient and the reliability of the check results is limited. In addition, there is often no system in place for store staff to voluntarily report problem areas, and even if a problem has been corrected, there is a lack of means to reconfirm its appropriateness. To solve these issues, an automated cleanliness check system is needed.

[1544] The specific processing by the specific processing unit 290 of the data processing device 12 in the application example 1 is realized by the following means.

[1545] In this invention, the server includes a receiving means for receiving the captured video, a generating means for generating frames from the video received by the receiving means, an analyzing means for analyzing the generated frames and making a judgment based on specified criteria, a generating means for generating a report based on the judgment results, a notifying means for notifying the generated report, and a reconfirming means for allowing the user to recapture and upload video. This enables automation of store cleanliness checks and efficient identification, correction, and reconfirmation of violations.

[1546] 1. "Receiving means" refers to a means for receiving images taken by a user inside and outside a store.

[1547] 2. "Generation means" means a means for generating frames from the video received by the reception means and preparing them for analysis.

[1548] 3. "Analysis means" refers to a means for determining violations based on the generated frames using the specified cleanliness standards.

[1549] 4. "Report generation means" means a means for generating a report based on the results of the analysis means.

[1550] 5. "Notification means" means a means for notifying the user of the generated report.

[1551] 6. "Reconfirmation means" refers to a means for a user to confirm corrections by taking a photo of the corrected state again and uploading it.

[1552] 7. "User" refers to a store crew member who uses the system to conduct cleanliness checks.

[1553] 8. "Mobile device" refers to a mobile device operated by a user, such as a smartphone or tablet.

[1554] 9. "Server" means a computer system that performs the functions of receiving video, generating frames, analyzing, generating reports, and notifying.

[1555] 10. "Cleanliness Standards" means the prescribed standards established to judge the cleanliness of a store.

[1556] The system embodying the present invention has a program for effectively managing the cleanliness of a store. The components of the system and their operation will be described below.

[1557] System Configuration

[1558] The system mainly consists of the following components:

[1559] 1. The user's mobile device

[1560] Users take and upload videos using their smartphones or tablets.

[1561] 2. Server

[1562] The server includes a receiving means, a generating means, an analyzing means, a report generating means, a notifying means, and a reconfirming means, and controls the entire process.

[1563] System Operation

[1564] Video reception and frame generation

[1565] The user's mobile device records the cleanliness status inside and outside the store as video. This video is uploaded to the server using the receiving means. The server divides the received video into frames and prepares them for analysis using the frame generating means.

[1566] Video analysis

[1567] The server's analysis means analyzes each frame based on cleanliness standards and identifies violations. The analysis means uses OpenCV, an image processing library, to detect abnormalities within the frames.

[1568] Report generation and notification

[1569] Based on the results of the analysis, a report is automatically generated by the report generation means. The report includes details of the identified cleanliness violations. The generated report is sent to the user's mobile device using the notification means.

[1570] Corrections and reconfirmation

[1571] Based on the report, the user corrects any cleanliness violations in the store. After the corrections are complete, the user shoots the video again and uploads it to the server via a reconfirmation tool. The server then analyzes the frames again to confirm that the corrections have been made properly.

[1572] Hardware and software used

[1573] Hardware: Smartphones, servers

[1574] Software: Flask (web framework), OpenCV (image processing library)

[1575] Specific examples

[1576] A user takes a video of the area around the trash can in the store with their smartphone and uploads the video to the server via the app. The server analyzes the video and generates a report stating that "the trash can is overflowing" and notifies the user. After the user has cleared the trash, they can take another video and upload it to the server, and receive a notification that "the problem has been resolved."

[1577] Prompt Sentence Examples

[1578] Please conduct a cleanliness check around the trash cans in your store. Upload the video and have it analyzed on the server. If there are any violations, a report will be automatically generated and notified. Please take appropriate action based on the cleanliness standards and record the video again to double-check.

[1579] The flow of the specific processing in the application example 1 will be described with reference to FIG.

[1580] Step 1:

[1581] The user takes a video of the cleanliness situation inside and outside the store using a smartphone. The input here is the video file taken by the user, and the output is the video file that will be uploaded to the server.

[1582] Step 2:

[1583] The terminal uploads the captured video file to the server using the receiving means. The path to the video file is input to the terminal, and the data is sent to the server. The output is a video file saved on the server.

[1584] Step 3:

[1585] The server divides the video uploaded by the receiving means into frames. Here, the video file is the input, and the divided multiple frame images are the output. Specifically, the OpenCV library is used to break down the video into frames, and each frame is saved in memory.

[1586] Step 4:

[1587] The server's analysis means analyzes the generated frames and identifies abnormalities based on the cleanliness criteria. The input to this step is the frame images, and the output is the analysis result of whether each frame meets the cleanliness criteria. For example, OpenCV is used to determine whether dust is present in the image.

[1588] Step 5:

[1589] The server creates a report based on the analysis results using a report generation means. The input here is the analysis results, and the output is a report file. The report includes details of the violations.

[1590] Step 6:

[1591] The server sends the generated report to the user's smartphone via a notification method. The input of this step is the report file, and the output is the process of notifying the user's device. Specifically, the report is sent using email or the app's notification function.

[1592] Step 7:

[1593] The user checks the report and corrects any cleanliness violations that are pointed out. The input here is the report content, and the output is the state of the store after the corrections are made.

[1594] Step 8:

[1595] The user then takes another video of the corrected state with their smartphone and uploads the video to the server. The input here is the newly taken video file, and the output is the corrected video file sent to the server.

[1596] Step 9:

[1597] The server splits the received corrected video into frames again and rechecks it using an analysis method. The input here is the corrected video file, and the output is the result of the reanalysis of the frames. It is again determined whether the corrections were made properly.

[1598] Step 10:

[1599] The server then notifies the user based on the final analysis result whether the corrections were successful. The input to this step is the reanalysis result, and the output is a notification that "corrections are complete" or "recorrections are required."

[1600] Through these steps, the system will be able to automate and efficiently manage store cleanliness checks.

[1601] Furthermore, an emotion engine that estimates the user's emotion may be further combined. That is, the identification processing unit 290 may estimate the user's emotion using the emotion identification model 59, and perform identification processing using the user's emotion.

[1602] The cleanliness self-check system of the present invention automatically analyzes the cleanliness status based on video footage taken by a user (e.g., a store crew member) and identifies any violations. By combining this system with an emotion engine, it is possible to recognize the user's emotional state and provide feedback accordingly. Detailed embodiments of the present invention are described below.

[1603] System Configuration

[1604] This system consists of the following main components:

[1605] 1. User's device

[1606] A mobile device such as a smartphone or tablet operated by a user, used to capture and upload video and receive notifications.

[1607] 2. Server

[1608] The server includes the following means:

[1609] Receiving means: Receives videos uploaded by users.

[1610] Generation method: Divide the video into frames.

[1611] Analysis method: Analyze the frame to determine if there are any cleanliness violations.

[1612] Notification method: A report is generated based on the judgment results and notified to the user.

[1613] Emotion engine: Recognizes user emotions and adjusts feedback accordingly.

[1614] Program processing

[1615] Video reception

[1616] The user uses the device to record the cleanliness status inside and outside the store. The recorded video is uploaded to the server via the application. The server's receiving means receives and stores the video.

[1617] Examples:

[1618] Users take videos on their devices titled "Store Afternoon Cleanliness Check" and upload them to the server via the app.

[1619] Frame Generation

[1620] The server divides the received video into frames, and the generating means generates frames at regular intervals per second and converts them into data for analysis.

[1621] Examples:

[1622] The server divides the three-minute video into 180 frames and saves each frame as an image file.

[1623] Video analysis

[1624] The server's analysis means inputs each frame into the generation AI, which determines whether or not there is a violation based on the cleanliness standards. The results are recorded in detail, detailing which areas have violations and what kind of violations have occurred.

[1625] Examples:

[1626] At frame 45, it detects that there is trash on the table in the eating area.

[1627] Emotion recognition

[1628] The emotion engine recognizes the user's emotions when shooting video. The emotion engine analyzes the user's emotions from their facial expressions and tone of voice, and sends that information to the analysis means.

[1629] Examples:

[1630] If the user is feeling frustrated or tired while shooting a video, the emotion engine will detect it.

[1631] Generate reports

[1632] The analysis means generates a report based on the information from the emotion engine, which includes details of the violation and feedback that takes into account the user's emotions.

[1633] Examples:

[1634] A report will be generated such as, "Garbage has been detected on the table in the dining area. Thank you for your hard work, please clean this up."

[1635] Notifications and Feedback

[1636] The server's notification means sends the report to the user's terminal, where the user can check the report and make any necessary corrections.

[1637] Examples:

[1638] The user checks the report on their device and decides on a countermeasure, such as "cleaning up the trash on the tables in the dining area."

[1639] Reconfirmation

[1640] After completing the corrections, the user shoots the video again and uploads it to the server, which then analyzes the video again in the same way to confirm that the corrections were made properly.

[1641] Examples:

[1642] After the user cleans up the dust, they record the corrected state on video again and upload it to the server, where it analyzes it again and notifies them that the problem has been solved.

[1643] This system allows users to efficiently perform cleanliness checks and quickly correct any violations. In addition, the introduction of an emotion engine provides feedback that takes into account the user's emotions, reducing the burden of the work.

[1644] The processing flow will be explained below.

[1645] Step 1:

[1646] The user uses the device to take video of the inside and outside of the store. The user launches the dedicated application and presses the capture button to capture the area to be checked.

[1647] Step 2:

[1648] The user uploads the video they have taken to the server. The user presses the "Upload" button in the application to send the video file to the server.

[1649] Step 3:

[1650] The server receives and stores the uploaded video. The receiving means receives the video file and stores it in a specific folder in the server.

[1651] Step 4:

[1652] The server divides the received video into frames. The generation means divides the video into frames at regular intervals (for example, every second) and saves each frame as an image file.

[1653] Step 5:

[1654] The server inputs each frame into the analysis AI, which then passes each generated frame to the AI ​​model in turn, which analyzes it based on cleanliness criteria.

[1655] Step 6:

[1656] The generator AI analyzes each frame to determine whether there are any cleanliness violations. The AI ​​model checks each element within the frame to detect anomalies such as dust or illegal pop-ups.

[1657] Step 7:

[1658] The server also sends the analysis results to the emotion engine, which analyzes the user's emotions. The emotion engine analyzes the user's facial expressions and tone of voice to recognize their emotions.

[1659] Step 8:

[1660] The server generates a report based on the analysis results and emotional information, which includes any cleanliness violations and feedback that takes the user's emotions into consideration.

[1661] Step 9:

[1662] The server notifies the user of the generated report, and the notification means transmits the contents of the report to the user's terminal and instructs the user to make corrections.

[1663] Step 10:

[1664] The user checks the report and corrects any violations that are reported. Based on the report on the terminal, the user can take appropriate action to resolve any cleanliness violations inside and outside the store.

[1665] Step 11:

[1666] The user shoots the video again and uploads the corrected state to the server. The user then starts the application again, shoots the checked area again, and sends it to the server.

[1667] Step 12:

[1668] The server receives, stores, and analyzes the re-uploaded video. It reprocesses the video using the same receiving, generating, and analyzing means as the first time, and verifies that the corrections were made appropriately.

[1669] Step 13:

[1670] The server notifies the user based on the results of the reanalysis. It checks whether the corrections were made appropriately based on the analysis results, and if the problem has been resolved, it sends a final notification to the user, and if additional corrections are required, it sends instructions to the user.

[1671] Example 2

[1672] Next, a description will be given of Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1673] Conventional cleanliness check systems allow users to simply check the results of their cleaning, making it difficult to efficiently check and improve. Furthermore, they do not provide feedback that takes into account the user's emotions or fatigue, which increases the burden of the work. There is a need for a system that recognizes the user's emotional state in real time and provides feedback that takes those emotions into consideration, thereby realizing efficient and less burdensome cleanliness checks.

[1674] The specific processing by the specific processing unit 290 of the data processing device 12 in the second embodiment is realized by the following means.

[1675] In this invention, the server includes receiving means for receiving the captured video, generating means for generating frames from the video received by the receiving means, analyzing means for analyzing the generated frames and making a judgment based on specified criteria, generating means for generating a report based on the judgment results, notifying means for notifying the generated report, emotion recognition means for recognizing the emotion of the user recording the video, and feedback means for adjusting the feedback content based on emotion data recognized by the emotion recognition means. This makes it possible to efficiently identify violations and provide feedback that takes the user's emotions into consideration.

[1676] The "receiving means" is a function for receiving video data uploaded to the server from the user's mobile terminal.

[1677] The "generating means" is a function that generates frames from the video data received by the receiving means and converts the frames into a format suitable for analysis.

[1678] The "analysis means" is a function that inputs the generated frame into the generation AI model and determines whether or not there is a violation based on cleanliness standards.

[1679] The "report generation means" is a function that generates a document to report the violation location and its details to the user based on the judgment results obtained by the analysis means.

[1680] The "notification means" is a function that sends the generated report to the user's mobile terminal and notifies the user.

[1681] The "emotion recognition means" is a function for recognizing the user's emotional state during video shooting from facial expressions and tone of voice.

[1682] The "feedback means" is a function that adjusts the contents of reports and notifications in a way that takes into consideration the user's emotions, based on the emotion data recognized by the emotion recognition means.

[1683] The cleanliness self-check system of the present invention automatically analyzes the cleanliness status based on the video taken by the user and identifies any violations. In addition, by combining it with an emotion engine, it is possible to recognize the user's emotional state and provide feedback that takes those emotions into consideration.

[1684] System Configuration

[1685] This system consists of the following main components:

[1686] 1. User's device

[1687] A mobile device such as a smartphone or tablet operated by the user, which is used to capture and upload video and receive notifications of analysis results.

[1688] 2. Server

[1689] The server includes the following means:

[1690] Receiving means: A function to receive videos uploaded by users.

[1691] Generation method: A function that generates frames from received video.

[1692] Analysis method: The generated frames are analyzed to determine whether cleanliness violations exist. This uses a generative AI model.

[1693] Report generation means: A function to generate a report based on the judgment results.

[1694] Notification method: A function to send the generated report to the user's terminal.

[1695] Emotion recognition: A function that recognizes the emotions of the user when recording video. It analyzes facial expressions and tone of voice.

[1696] Feedback means: A function that adjusts the feedback content based on emotional data from the emotion recognition means.

[1697] Filming and uploading footage

[1698] Users use their mobile devices to record video of the cleanliness status inside and outside the store. The video is then uploaded to the server via a dedicated application. For example, a user can record a video of an "afternoon cleanliness check" and press the send button on the application to upload the video data to the server.

[1699] Video reception, frame generation and analysis

[1700] The server's receiving means receives and saves the uploaded video. Next, the server's generating means divides the video into frames. For example, a three-minute video is divided into frames every second, and all of the frames are saved as JPEG image files. The server's analyzing means inputs the generated frames into a generative AI model and analyzes each frame based on cleanliness standards. It determines whether or not there is a cleanliness violation and records the violation in detail. For example, if garbage is detected on a table in the eating and drinking area in frame 45, the result is recorded on the table.

[1701] Emotional Recognition and Feedback

[1702] The emotion recognition means analyzes the user's emotions while shooting video. It detects the user's emotions from facial expressions and tone of voice and sends that information to the server. For example, if the user expresses fatigue while shooting, the emotion recognition means will determine that the user is "feeling tired." The feedback means adjusts the feedback content based on the emotional data. For example, it provides feedback in the form of "Thank you for your hard work. Please clean this area."

[1703] Report generation and notification

[1704] The report generation means generates a report based on the judgment result obtained by the analysis means and the information from the emotion recognition means. The generated report is sent to the user's mobile device by the notification means. The user checks the report and makes any necessary corrections. For example, the user may decide to "clean up the trash on the tables in the dining area" and then carry out the cleaning.

[1705] Hardware and software used

[1706] Hardware: smartphones, tablets, servers

[1707] Software: Generative AI models, emotion engines, dedicated applications

[1708] Example prompts for generative AI models

[1709] "Detect cleanliness violations from user-captured footage."

[1710] "Analyze each frame in the video and identify areas where there are violations."

[1711] This allows users to efficiently perform cleanliness checks and quickly correct violations. Furthermore, by using an emotion engine, feedback is given taking into account the user's emotions, reducing the burden of the work.

[1712] The flow of the identification process in the second embodiment will be described with reference to FIG.

[1713] Step 1:

[1714] The user uses the device to record the cleanliness conditions inside and outside the store. Specifically, the user launches a dedicated application and records video using the camera function. The input data is the video that was recorded, and the output is a video file saved on the device.

[1715] Step 2:

[1716] The user presses the send button in the application to upload the captured video data to the server. The input data is the video file stored on the device, and the output is the video data transferred to the server. Specifically, the user clicks the "upload" button to start the data transfer process.

[1717] Step 3:

[1718] The server's receiving means receives and stores the uploaded video. The input data is the video data uploaded by the user, and the output is a video file stored in the server's database. The user is notified that the receiving process has been completed successfully.

[1719] Step 4:

[1720] The server's generation means divides the received video into frames. Specifically, it converts the video into still images at a rate of one frame per second and saves all frames as image files. The input data is the video file saved on the server, and the output is a collection of divided frame images.

[1721] Step 5:

[1722] The server's analysis means inputs the generated frames into the generative AI model, which judges whether or not there is a violation for each frame based on the cleanliness criteria. The input data are the divided frame images, and the output is the analysis result (whether or not there is a violation and its details). Specifically, each frame is input into the AI ​​model in sequence, and the judgment result is obtained.

[1723] Step 6:

[1724] The emotion recognition means analyzes the user's emotional state when the video is being taken. The input data is the user's facial expression and tone of voice, and the output is the analysis result of the emotional state. Specifically, it recognizes emotions using a facial expression analysis algorithm and a voice emotion analysis algorithm, and saves the results.

[1725] Step 7:

[1726] The report generation means generates a report based on the data from the analysis means and emotion recognition means. The input data are the violation analysis results and the emotional state analysis results, and the output is the generated report. Specifically, the report reflecting the detailed information of the violation and the user's emotional state is generated according to a template.

[1727] Step 8:

[1728] The notification means sends the generated report to the user's device. The input data is the generated report, and the output is the report received by the user's device. Specifically, the generated report is sent to the user via email or an in-app notification function.

[1729] Step 9:

[1730] The user checks the report on the terminal and makes any necessary corrections. The input data is the received report, and the output is the corrected cleanliness status. The user cleans specific areas according to the instructions in the report and checks the results.

[1731] Step 10:

[1732] The user then records the situation after the correction work on video again and uploads it to the server. The input data is the corrected video, and the output is the re-uploaded video data stored on the server. Specifically, the user uses the dedicated app to record video again and execute the upload process.

[1733] Step 11:

[1734] The server then re-analyzes the video using the same procedure to confirm whether the corrections were made properly. The input data is the frame image for re-analysis, and the output is the re-analysis result (whether the problem was resolved or not). The final analysis result is notified to the user.

[1735] (Application example 2)

[1736] Next, a description will be given of Application Example 2. In the following description, the data processing device 12 will be referred to as a "server" and the robot 414 will be referred to as a "terminal."

[1737] Checking cleanliness and identifying violations is often done manually, which takes time and effort. It also leaves users feeling fatigued and stressed, making it difficult to work efficiently. Furthermore, it is difficult to provide feedback that takes into account the user's emotions when reporting violations, which can lead to a decrease in motivation and an increase in stress.

[1738] The identification process by the identification processing unit 290 of the data processing device 12 in Application Example 2 is realized by the following means. In this invention, the server includes a receiving means for receiving captured video, a generating means for generating frames from the video received by the receiving means, an analyzing means for analyzing the generated frames and making a judgment based on specified criteria, a generating means for generating a report based on the judgment results, a notifying means for notifying the generated report, an emotion analyzing means for analyzing the user's emotions, and a feedback adjusting means for adjusting the feedback content based on information from the emotion analyzing means. This makes it possible to automate cleanliness checks, quickly and accurately identify violations, and provide feedback that takes the user's emotions into consideration.

[1739] The "receiving means" is a device or system that receives the captured video from the mobile terminal operated by the user.

[1740] The "generating means" is a device or program that generates frames from the video received by the receiving means.

[1741] The "analysis means" is a device or program that analyzes the generated frames and makes a judgment based on a specified standard.

[1742] The "report generation means" is a device or program that generates a report based on the determination results of the analysis means.

[1743] A "notification means" is a device or system that transmits the generated report to the user's terminal.

[1744] The "emotion analysis means" is a device or program that analyzes the user's emotions.

[1745] The "feedback adjustment means" is a device or program that adjusts the feedback content based on information from the emotion analysis means.

[1746] "Cleanliness" is a term that refers to the cleanliness of a particular area.

[1747] A "frame" refers to a portion of an image that divides a video into a single moment on the time axis.

[1748] MODE FOR CARRYING OUT THE INVENTION

[1749] System Configuration

[1750] The cleanliness self-check system of the present invention is composed of the following main components:

[1751] 1. User's device

[1752] A mobile device operated by a user, including a smartphone or tablet, used to capture and upload video and receive notifications.

[1753] 2. Server

[1754] The server is a system including the following means:

[1755] Receiving means: Receives videos uploaded by users.

[1756] Generation method: Divide the video into frames.

[1757] Analysis method: Analyze the frame to determine if there are any cleanliness violations.

[1758] Report generation means: Generates a report based on the judgment results.

[1759] Notification method: The generated report is sent to the user's terminal.

[1760] Sentiment analysis means: Analyzes the user's emotions.

[1761] Feedback adjustment means: Adjust the feedback content based on the information from the sentiment analysis means.

[1762] Program processing and hardware / software

[1763] 1. Receiving video

[1764] Users use their smartphones to record the cleanliness status inside and outside the store. The recorded video is uploaded to a server via a mobile device application. The server's receiving means receives and stores the video. In this case, it is desirable for the application to be developed using a framework such as Flutter or React Native.

[1765] 2. Frame Generation

[1766] The server divides the received video into frames. The generator generates frames at regular intervals every second and converts them into data for analysis. This process is performed using Python and image processing libraries such as OpenCV.

[1767] 3. Video Analysis

[1768] The server's analysis tool feeds each frame into a generative AI model (e.g., YOLO or TensorFlow) to determine whether there are any violations based on cleanliness criteria. Any violations detected are logged in detail.

[1769] 4. Emotion Analysis

[1770] The emotion analysis means analyzes the emotions expressed by the user when they shoot video. This uses emotion recognition engines such as Microsoft Azure Cognitive Services and Affectiva. The emotion is analyzed from the user's facial expressions and tone of voice, and the information is sent to the analysis means.

[1771] 5. Generate reports

[1772] Based on the judgment result and the emotion analysis result, the report generation means generates a report, which includes details of the violation and feedback that takes into account the user's emotions.

[1773] 6. Notifications and Feedback

[1774] The server's notification means sends the generated report to the user's terminal, where the user checks the report and makes any necessary corrections.

[1775] Examples of concrete examples and prompts

[1776] Examples:

[1777] Users film a video titled "Store Afternoon Cleanliness Check" on their smartphone and upload it to the server via the app. The server divides the three-minute video into frames and, in the process of analyzing each frame, detects the presence of trash on the table in the dining area. If the user feels tired while filming the video, the emotion analysis engine detects this and provides feedback such as, "Thank you for your hard work. There is trash on the table in the dining area. Please clean it up."

[1778] Example prompt sentence:

[1779] We have taken video footage to check the cleanliness of our store. Please analyze the video below and identify any cleanliness violations.

[1780] Video URL: [URL of uploaded video]

[1781] The analysis results should include details of the violation (e.g., there is trash on the table in the dining area) and feedback based on the staff member's emotional state (e.g., tired, annoyed). For example, "Thank you for your hard work. There is trash on the table in the dining area. Please clean it up."

[1782] The flow of the specific processing in the application example 2 will be described with reference to FIG.

[1783] Step 1:

[1784] The user shoots the video using a smartphone

[1785] Users use their smartphones to take videos to check the cleanliness status inside and outside the store. The videos are saved in the application. The input here is the video that was taken, and the output is the video data saved in the smartphone.

[1786] Step 2:

[1787] Uploading video from a smartphone to a server

[1788] Users upload captured video to a server using a smartphone app. The app sends the video data to the server via an internet connection. The input here is the video data stored on the smartphone, and the output is the video data received by the server.

[1789] Step 3:

[1790] The server divides the video into frames

[1791] The server receives the uploaded video data using a receiving means. Then, it divides the video into frames using a generating means. For example, if a three-minute video is divided into 30 frames per second, 5,400 frames are generated. The input is the video data received by the server, and the output is image data for each frame.

[1792] Step 4:

[1793] The server analyzes the frames and identifies cleanliness violations

[1794] The server uses an analysis method to analyze each generated frame. This analysis uses a generative AI model (e.g., YOLO or TensorFlow) to determine whether there are any violations based on specific cleanliness criteria. The input is the image data for each frame, and the output is the data with the violations identified.

[1795] Step 5:

[1796] The server analyzes the user's emotions

[1797] Emotion analysis tools are used to analyze facial expressions and tone of voice when a user shoots a video. For example, services from Microsoft Azure Cognitive Services or Affectiva are used. The input is the user's facial expressions and voice data, and the output is analyzed emotion data.

[1798] Step 6:

[1799] The server generates the report

[1800] Based on the results of the analysis means and the sentiment analysis means, the report generation means creates a report. The report includes details of the detected cleanliness violations and feedback that takes into account the user's sentiment. The input is data on the violation locations and sentiment data, and the output is the generated report.

[1801] Step 7:

[1802] The server notifies the report

[1803] The server sends the generated report to the user's smartphone using a notification means. The user receives the notification and checks the contents of the report. The input is the generated report, and the output is the report notified to the user.

[1804] Step 8:

[1805] The user makes corrections based on the report.

[1806] Based on the notified report, the user corrects any cleanliness violations within the store. For example, cleaning up trash on the tables in the dining area. The input is the content of the report, and the output is the actual cleaning work.

[1807] Step 9:

[1808] The user takes another photo of the corrected state and uploads it to the server.

[1809] The user then uses their smartphone to record the cleanliness of the area after the corrections and uploads the video to the server. The server then analyzes the video again to confirm that the corrections were made appropriately. The input is the re-recorded video data, and the output is the video data that has been re-uploaded to the server.

[1810] 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.

[1811] The data generation model 58 is a so-called generative AI (Artificial Intelligence). An example of the data generation model 58 is ChatGPT (Internet Search<URL: https: / / openai.com / blog / chatgpt> ), Gemini (Internet search <url: https: gemini.google.com ?hl="ja">) and other generation AIs. The data generation model 58 is obtained by performing deep learning on a neural network. A prompt including an instruction is input to the data generation model 58, and inference data such as voice data indicating voice, text data indicating text, and image data indicating an image is also input. The data generation model 58 performs inference on the input inference data in accordance with the instruction indicated by the prompt, and outputs the inference result in a data format such as voice data and text data. Here, inference refers to, for example, analysis, classification, prediction, and / or summarization.

[1812] In the above embodiment, an example was given in which the specific processing is performed by the data processing device 12, but the technology of the present disclosure is not limited to this, and the specific processing may be performed by the robot 414.

[1813] 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.

[1814] FIG. 9 is a diagram illustrating an emotion map 400 on which multiple emotions are mapped. In the emotion map 400, emotions are arranged in concentric circles radiating from the center. Emotions closer to the center of the concentric circles are more primitive. Emotions representing states and actions arising from a state of mind are arranged on the outer edges of the concentric circles. The concept of emotion includes both affect and mental states. Emotions generally generated from reactions occurring in the brain are arranged on the left side of the concentric circles. Emotions generally induced by situational judgment are arranged on the right side of the concentric circles. Emotions generally generated from reactions occurring in the brain and induced by situational judgment are arranged on the upper and lower sides of the concentric circles. Furthermore, the emotion of "pleasure" is arranged on the upper side of the concentric circles, and the emotion of "discomfort" is arranged on the lower side. In this way, in the emotion map 400, multiple emotions are mapped based on the structure by which emotions are generated, and emotions that tend to occur simultaneously are mapped close to each other.

[1815] 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.

[1816] 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).

[1817] Human emotions are based on various balances, such as posture and blood sugar levels. When these balances deviate from the ideal, a state of discomfort is indicated, and when they approach the ideal, a state of pleasure is indicated. Emotions can also be created for robots, automobiles, 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 indicated, and when they approach the ideal, a state of pleasure is indicated. An emotion map can be generated, for example, based on Dr. Mitsuyoshi's emotion map (Research on Voice Emotion Recognition and Emotional Brain Physiological Signal Analysis Systems, Tokushima University, Doctoral Dissertation: https: / / ci.nii.ac.jp / naid / 500000375379). The left half of the emotion map lists emotions belonging to the "reaction" domain, where sensation is dominant. The right half of the emotion map lists emotions belonging to the "situation" domain, where situational awareness is dominant.

[1818] 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."

[1819] 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.

[1820] The system according to the present disclosure has been described above mainly with respect to the functions of the data processing device 12, but the system according to the present disclosure is not necessarily implemented on a server. The system according to the present disclosure may be implemented as a general information processing system. The present disclosure may be implemented, for example, as a software program running on a personal computer or an application running on a smartphone, etc. The method according to the present disclosure may be provided to users in the form of SaaS (Software as a Service).

[1821] In the above embodiment, an example was given in which the specific processing is performed by one computer 22, but the technology of the present disclosure is not limited to this, and the specific processing may be distributed and performed by a plurality of computers including the computer 22. For example, the data generation model 58 may be provided in an external device of the data processing device 12, and data may be generated in the external device in accordance with input data.

[1822] 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.

[1823] 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.

[1824] 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.

[1825] The hardware resource for executing a specific process can be any of the following processors: An example of a processor is a CPU, which is a general-purpose processor that functions as a hardware resource for executing a specific process by executing software, i.e., a program. Another example of a processor is a dedicated electrical circuit, such as an FPGA (Field-Programmable Gate Array), a PLD (Programmable Logic Device), or an ASIC (Application Specific Integrated Circuit), which is a processor with a circuit configuration designed specifically for executing a specific process. Each processor has built-in or connected memory, and each processor uses the memory to execute the specific process.

[1826] The hardware resource that executes the specific processing may be configured with one of these various processors, or may be configured with a combination of two or more processors of the same or different types (for example, a combination of multiple FPGAs, or a combination of a CPU and an FPGA). Also, the hardware resource that executes the specific processing may be a single processor.

[1827] 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.

[1828] 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.

[1829] 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.

[1830] 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.

[1831] The following is further disclosed regarding the above embodiment.

[1832] (Claim 1)

[1833] receiving means for receiving the captured image;

[1834] generating means for generating frames from the video received by the receiving means;

[1835] analysis means for analyzing the generated frames and making a determination based on a specified criterion;

[1836] generating means for generating a report based on the determination result;

[1837] a notification means for notifying the generated report;

[1838] A system including:

[1839] (Claim 2)

[1840] The system according to claim 1, wherein the analysis means detects cleanliness violations in specific areas based on the analysis results and includes details of the relevant areas in a report.

[1841] (Claim 3)

[1842] 2. The system according to claim 1, wherein the receiving means receives the video via a mobile terminal operated by a user, and the analyzing means and generating means operate on a server.

[1843] (Claim 4)

[1844] 2. The system according to claim 1, wherein the notification means displays the contents of the report on the user's terminal and includes instructions to prompt the user to correct any cleanliness violations.

[1845] (Claim 5)

[1846] 2. The system according to claim 1, wherein the receiving means receives the video shot by the user again, and the analyzing means analyzes the video again to confirm any corrections.

[1847] "Example 1"

[1848] (Claim 1)

[1849] receiving means for receiving the captured image;

[1850] generating means for generating frames from the video received by the receiving means;

[1851] analysis means for analyzing the generated frames and making a determination based on a specified criterion;

[1852] report generation means for generating a report based on the determination result;

[1853] a notification means for notifying the generated report;

[1854] a reanalysis means for reanalyzing the re-shot video and notifying the user of the reanalysis result;

[1855] A system including:

[1856] (Claim 2)

[1857] The system according to claim 1, wherein the analysis means detects cleanliness violations in specific areas based on the analysis results and includes details of the relevant areas in a report.

[1858] (Claim 3)

[1859] 2. The system according to claim 1, wherein the receiving means receives the video via a mobile terminal operated by a user, and the analyzing means and the report generating means operate on a server.

[1860] "Application Example 1"

[1861] (Claim 1)

[1862] receiving means for receiving the captured image;

[1863] generating means for generating frames from the video received by the receiving means;

[1864] analysis means for analyzing the generated frames and making a determination based on a specified criterion;

[1865] generating means for generating a report based on the determination result;

[1866] a notification means for notifying the generated report;

[1867] A reconfirmation method that allows users to retake and upload footage;

[1868] A system including:

[1869] (Claim 2)

[1870] The system according to claim 1, characterized in that the analysis means detects cleanliness violations in specific areas based on the analysis results, includes details of the relevant areas in a report, and reconfirms whether the violations have been corrected.

[1871] (Claim 3)

[1872] The system described in claim 1, characterized in that the receiving means receives the video via a mobile terminal operated by the user, the analyzing means and generating means operate on a server, and the notification and reconfirmation means corrects and confirms cleanliness violations.

[1873] "Example 2: Combining Emotion Engines"

[1874] (Claim 1)

[1875] receiving means for receiving the captured image;

[1876] generating means for generating frames from the video received by the receiving means;

[1877] analysis means for analyzing the generated frames and making a determination based on a specified criterion;

[1878] generating means for generating a report based on the determination result;

[1879] a notification means for notifying the generated report;

[1880] emotion recognition means for recognizing the emotion of a user who records the video;

[1881] a feedback means for adjusting the feedback content based on the emotion data recognized by the emotion recognition means;

[1882] A system including:

[1883] (Claim 2)

[1884] The system according to claim 1, wherein the analysis means detects cleanliness violations in specific areas based on the analysis results and includes details of the relevant areas in a report.

[1885] (Claim 3)

[1886] 2. The system according to claim 1, wherein the receiving means receives the video via a mobile terminal operated by a user, and the analyzing means and generating means operate on a server.

[1887] "Application example 2 when combining emotion engines"

[1888] (Claim 1)

[1889] receiving means for receiving the captured image;

[1890] generating means for generating frames from the video received by the receiving means;

[1891] analysis means for analyzing the generated frames and making a determination based on a specified criterion;

[1892] generating means for generating a report based on the determination result;

[1893] a notification means for notifying the generated report;

[1894] emotion analysis means for analyzing the emotions of a user;

[1895] a feedback adjustment means for adjusting the feedback content based on information from the emotion analysis means;

[1896] A system including:

[1897] (Claim 2)

[1898] The system of claim 1, wherein the analysis means detects cleanliness violations in specific areas based on the analysis results, includes details of the relevant areas in a report, and further includes feedback in the report that takes into account the user's emotional state.

[1899] (Claim 3)

[1900] 2. The system according to claim 1, wherein the receiving means receives the video via a mobile terminal operated by a user, and the analyzing means, generating means, and emotion analyzing means operate on a server. [Explanation of symbols]

[1901] 10, 210, 310, 410 Data Processing Systems 12 Data Processing Device 14 Smart Devices 214 Smart Glasses 314 Headset-type terminal 414 Robot< / url:> < / url:> < / url:> < / url:>

Claims

1. receiving means for receiving the captured image; generating means for generating frames from the video received by the receiving means; analysis means for analyzing the generated frames and making a determination based on a specified criterion; generating means for generating a report based on the determination result; a notification means for notifying the generated report; A system including:

2. The system according to claim 1, wherein the analysis means detects cleanliness violations in specific areas based on the analysis results and includes details of the violations in a report.

3. 2. The system according to claim 1, wherein the receiving means receives the video via a mobile terminal operated by a user, and the analyzing means and generating means operate on a server.

4. 2. The system according to claim 1, wherein the notification means displays the contents of the report on the user's terminal and includes instructions to prompt the user to correct any cleanliness violations.

5. 2. The system according to claim 1, wherein the receiving means receives the video taken by the user again, and the analyzing means analyzes the video again to confirm the correction.

Images