Information processing device and information processing method

Abstract

To minimize the amount of video data transmitted from in-vehicle devices while reducing the burden on administrators to monitor drivers' adherence to safe driving practices. [Solution] An information processing device for determining whether or not a driver is performing safe driving actions based on video data, comprising a communication unit that communicates with a vehicle and / or a terminal on the vehicle, and a processing unit that processes data, wherein the communication unit receives mobile information including information about the vehicle's speed and information about its position, the processing unit detects an event related to the vehicle's movement from the mobile information, the communication unit receives video data including the driver's driving actions corresponding to the event, the processing unit identifies a condition corresponding to the event, and the processing unit takes the condition and the video data as input to a determination unit to obtain a determination result.

Description

Technical Field

[0001] The present invention relates to an information processing apparatus and an information processing method.

Background Art

[0002] Conventionally, there is a technology for acquiring a video related to dangerous driving. In Patent Document 1, it is described that "a drive recorder capable of acquiring an arbitrary image when an impact of a strength satisfying a predetermined condition is measured is provided." and "In the drive recorder 1, the travel recording module 51 records the captured moving image data 60 captured by the camera 18 installed in the vehicle. The acceleration sensor 19 measures the acceleration of the vehicle. When the travel recording module 51 determines that the acceleration measured by the acceleration sensor 19 is within an abnormal range, the travel recording module 51 notifies the server 4 at a predetermined timing of the dangerous driving time when the acceleration within the abnormal range is measured. When the travel recording module 51 receives a video transmission request including the dangerous driving time from the server 4, the travel recording module 51 transmits the captured moving image data 60 within a predetermined period including the dangerous driving time included in the video transmission request to the server."

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] Ensuring safety is extremely important in the logistics industry. One way to ensure safety is for managers to review videos of drivers' driving. However, reviewing all of a driver's normal driving would require sending all video data from the in-vehicle device to a server for management review, resulting in a large amount of data traffic. Furthermore, it would be difficult to allocate sufficient time for managers to review all the videos. As a way to reduce the amount of data traffic, as described in Patent Document 1, there is a method in which only videos from time periods detected by the in-vehicle device's sensors are sent to a server, and managers can view only the videos from those time periods. However, this method is limited to videos of abnormal driving detected by the sensors, so it is not possible to confirm from the videos whether drivers are performing safety measures such as pointing and calling out or visual confirmation to prevent accidents. Therefore, there are still challenges in ensuring safety.

[0005] To address the challenge of securing administrators' time, recent advancements in video analysis technology have led to the development of generative AI (Artificial Intelligence), and measures utilizing judgments made by generative AI exist. However, since accurate judgments cannot be made without asking specific questions to the generative AI, it is necessary to ask specific questions, which often include questions that are not relevant to the timing of the video, resulting in a high processing load on the generative AI and posing a challenge. An example of an unnecessary question would be asking about the status of a non-existent traffic light in a video of driving straight on a highway.

[0006] The present invention aims to reduce the server load for judgment processing by generating AI and to reduce the burden on administrators by limiting the communication of video from in-vehicle devices to confirm that normal safety measures are being taken. [Means for solving the problem]

[0007] To achieve the above objective, one representative information processing device of the present invention is an information processing device that determines whether or not a driver is performing safe driving actions based on video data, and comprises a communication unit that communicates with a vehicle and / or a terminal on the vehicle, and a processing unit that processes data, wherein the communication unit receives mobile information including information about the vehicle's speed and information about its position, the processing unit detects an event related to the vehicle's movement from the mobile information, the communication unit receives video data including the driver's driving actions corresponding to the event, the processing unit identifies a condition corresponding to the event, and the processing unit takes the condition and the video data as input to a determination unit to obtain a determination result. Furthermore, one representative information processing method of the present invention is an information processing method for determining whether or not a driver is performing safe driving actions based on video data, characterized in that the information processing device receives mobile information including information about the vehicle's speed and information about its position from the vehicle and / or a terminal on the vehicle; the information processing device detects an event related to the vehicle's movement from the mobile information; the information processing device receives video data including the driver's driving actions corresponding to the event; the information processing device identifies a condition corresponding to the event; and the information processing device obtains a determination result by inputting the condition and the video data to a determination unit. [Effects of the Invention]

[0008] According to the present invention, it is possible to limit the amount of video data transmitted from the in-vehicle device to the minimum necessary while reducing the burden on the administrator to check the driver's compliance with safe driving practices. Other problems, configurations, and effects will be clarified by the following description of embodiments. [Brief explanation of the drawing]

[0009] [Figure 1] A diagram showing the system's hardware configuration. [Figure 2] A flowchart of the processes performed by an information processing device in a system. [Figure 3]A flowchart illustrating the details of measurement information processing. [Figure 4] A concrete example of a judgment table. [Figure 5] A flowchart for video requests. [Figure 6] A flowchart of the decision-making process. [Figure 7] Flowchart for real-time notifications. [Figure 8] A concrete example of an administration panel (Part 1). [Figure 9] A concrete example of an administration panel (part 2). [Figure 10] A concrete example of an administration panel (part 3). [Figure 11] Specific examples of event result information. [Figure 12] A concrete example of a judgment result table. [Modes for carrying out the invention]

[0010] Embodiments of the present invention will be described below with reference to the drawings. The embodiments are illustrative examples for explaining the present invention, and have been omitted and simplified as appropriate for clarity of explanation. The present invention can also be carried out in various other forms. Unless otherwise specified, each component may be singular or plural.

[0011] The positions, sizes, shapes, and ranges of the components shown in the drawings may not represent their actual positions, sizes, shapes, and ranges in order to facilitate understanding of the invention. Therefore, the present invention is not necessarily limited to the positions, sizes, shapes, and ranges disclosed in the drawings.

[0012] Examples of various types of information may be described using terms such as "table," "list," and "queue," but these types of information may also be represented by other data structures. For example, various types of information such as "XX table," "XX list," and "XX queue" may be referred to as "XX information." When describing identification information, terms such as "identification information," "identifier," "name," "ID," and "number" are used, and these terms are interchangeable.

[0013] When there are a plurality of components having the same or similar functions, they may be described by attaching different subscripts to the same reference numeral. Also, when it is not necessary to distinguish these plurality of components, the subscripts may be omitted in the description.

[0014] In the embodiments, the processes performed by executing a program may be described. Here, the computer executes a program by a processor (e.g., CPU, GPU), and performs the processes defined by the program while using storage resources (e.g., memory) and interface devices (e.g., communication ports), etc. Therefore, the subject of the process performed by executing the program may be the processor. Similarly, the subject of the process performed by executing the program may be a controller, device, system, computer, or node having a processor. The subject of the process performed by executing the program only needs to be an arithmetic unit, and may include a dedicated circuit for performing a specific process. Here, the dedicated circuit is, for example, an FPGA (Field Programmable Gate Array), an ASIC (Application Specific Integrated Circuit), a CPLD (Complex Programmable Logic Device), etc.

[0015] The program may be installed in the computer from a program source. The program source may be, for example, a program distribution server or a storage medium readable by the computer. When the program source is a program distribution server, the program distribution server includes a processor and a storage resource for storing the program to be distributed, and the processor of the program distribution server may distribute the program to be distributed to other computers. Also, in the embodiments, two or more programs may be realized as one program, or one program may be realized as two or more programs.

Embodiments

[0016] FIG. 1 is a diagram showing the hardware configuration of the present system. The present system is configured to include an information processing apparatus 10, a generative artificial intelligence infrastructure 20, and a mobile body 30. The information processing apparatus 10, the generative artificial intelligence infrastructure 20, and the mobile body 30 are interconnected through a network. The information processing apparatus 10 includes, for example, a processor 11, a memory 12, an input device 13, an output device 14, a storage device 15, and an interface device 16. The processor 11 operates as a "processing unit", the memory 12 and the storage device 15 operate as a "storage unit", the input device 13 operates as an "input unit", the output device 14 operates as an "output unit", and the interface device 16 operates as an "interface unit".

[0017] As the hardware configuration of the information processing apparatus 10, it may be composed of one or more computers (electronic computers). The information processing apparatus 10 may be called an information processing system. Each component of the hardware of the information processing apparatus 10 may be singular or plural. The information processing apparatus 10 may be one or more physical computers having hardware such as a processor 11, a memory 12, an input device 13, an output device 14, a storage device 15, and an interface device 16, or may be a system (for example, a cloud computing system) realized on one or more physical computers (for example, a cloud infrastructure). Also, each device included in the information processing apparatus 10 may be arranged on one physical computer or may be arranged on a plurality of physical computers so as to be distributed. Each program and each piece of information included in the storage device 15 may be stored in one storage device or may be stored separately in a plurality of storage devices so as to be distributed.

[0018] The processor 11 is a device that controls the operation of the entire information processing device 10. The processor 11 can be any arithmetic unit or control unit, and may consist of a processor such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit), or it may include a dedicated circuit that performs a specific processing task. Here, a dedicated circuit is an FPGA (Field Programmable Gate Array), an ASIC (Application Specific Integrated Circuit), a CPLD (Complex Programmable Logic Device), etc.

[0019] Memory 12 is used as the work memory of the processor 11. The storage device 15 stores programs and various information. In this embodiment, for example, the storage device 15 stores a program 151, judgment result information 152, master information 153, notification setting information 154, measurement information 155, image information 156, judgment condition information 157, and event information 158.

[0020] The input device 13 consists of, for example, a mouse or keyboard, and is used by the operator to input necessary information and instructions to the information processing device 10. The output device 14 may be a display device such as a liquid crystal display or an organic EL (Electro Luminescence) display.

[0021] The interface device 16 is a device that operates as a communication unit that communicates with an external device using a predetermined communication method, and may be composed of, for example, a wireless LAN card. The information processing device 10 can communicate with the generative artificial intelligence platform 20 via the network 41 through the interface device 16. The information processing device 10 can also communicate with the mobile device 30 via the network 40 through the interface device 16.

[0022] Network 40 may be any wireless communication network. Network 41 may be any wired communication network or any wireless communication network. As the wireless communication network, a fifth-generation mobile communication system, so-called 5G (5th Generation), which enables "massive simultaneous connections" and "ultra-low latency," can be used. Furthermore, by taking advantage of the features of new mobile phone systems after 5G, it is expected that the effects of the present invention will be improved.

[0023] The generative artificial intelligence platform 20 is a generative AI comprising, for example, a processor 21, memory 22, storage device 23, and interface device 24. The processor 21 operates as a "processing unit," the memory 22 and storage device 23 as "storage units," and the interface device 24 as an "interface unit." The generative artificial intelligence platform 20 is connected to the information processing device 10 by a network 41, but it may operate on the same device as the information processing device 10, sharing the same processor, memory, and storage device. The generative artificial intelligence platform is a platform that can use previously learned data to provide the optimal response to received instructions. In this embodiment, the generative artificial intelligence platform 20 accepts conditions and video data as input to determine whether the driver is performing safe driving actions. For example, the generative artificial intelligence platform 20 accepts video data before and after the vehicle speed increases from 0 m / s, and the condition "whether the driver is performing pointing and confirming." If the generative artificial intelligence platform 20 determines that the driver is performing pointing and confirming in the video data, it outputs "safe driving." The generative artificial intelligence platform 20 outputs "unsafe driving" if it determines that the driver is not pointing and confirming in the video data.

[0024] The mobile unit 30 is equipped with an in-vehicle device 31. The in-vehicle device 31 may be an in-vehicle terminal mounted on the vehicle, such as a drive recorder or digital tachograph, or it may be a device that moves with the mobile unit (a portable terminal that can be installed on the vehicle), such as a smartphone or smart device. The in-vehicle device 31 includes, for example, a processor 32, memory 33, camera 34, sensor 35, speaker 36, storage device 37, and interface device 38. The processor 32 operates as a "processing unit," the memory 33 and storage device 37 as "storage units," and the interface device 38 as an "interface unit." The sensor is a sensor attached to the in-vehicle device and may be a GPS sensor, gyro sensor, accelerometer, gravity acceleration sensor, etc. Alternatively, the mobile unit 30 may be configured to transmit the output of sensors provided on the vehicle body to the information processing device 10.

[0025] The in-vehicle device 31 stores video or images captured by the camera 34 in image information 373 in the storage device 37, and stores sensor data collected by the sensor 35 in measurement information 372. The collected sensor data is sent to the information processing device 10 via the network 40 through the interface device 38 and is also stored in the measurement information 155 of the storage device 15.

[0026] Figure 2 shows the processing flow performed by the information processing device in this system, which is performed periodically to process measurement information collected from mobile objects. In step S101, the collected measurement information is processed and it is determined whether it matches the judgment conditions in the judgment table in Figure 4. If it matches, an event ID is issued, and the occurrence time, employee, and the command in the judgment table in Figure 4 are saved in the event result information table as shown in Figure 11, in event information 158 in Figure 1. In step S102, if there is data saved in the table in step S101, it is determined that video is required and the process proceeds to step S103. In step S103, video is obtained from the mobile object from the occurrence time stored in the table, covering the time period specified in the judgment described in the command. For example, if the judgment in the command is "previous 30 seconds," video will be obtained from 30 seconds before the occurrence time to the occurrence time. In step S104, the video acquired in step S103 and the command statement acquired in step S101 are given to the generative artificial intelligence platform to obtain a judgment result. If the judgment result is NO, the file path of the video given to the AI, the time of occurrence, and the employee's information are combined and saved as the judgment result table shown in Figure 12, in the judgment result information 152 shown in Figure 1. If the judgment result is YES, the driving is considered safe, and the time of occurrence and the employee's information are combined and saved as the judgment result table shown in Figure 12, in the judgment result information 152 shown in Figure 1.

[0027] In step S105, a notification is sent to the mobile object based on the determination result performed in step S104.

[0028] Figure 3 is a more detailed explanation of step S101 in Figure 2. In step S201, measurement information is obtained from measurement information 155 in Figure 1. Next, in step S202, judgment condition information 157 in Figure 1 is obtained. The judgment condition information is the judgment table in Figure 4. Next, in step S203, master information is obtained from master information in Figure 1. Master information includes intersection information and facility location information. In step S204, the location information of the facility and the location information of the moving object included in the measurement information are compared to determine whether the location information of the moving object is within the facility premises. If the location information of the moving object is within the premises, the process proceeds to step S205; otherwise, the process proceeds to step S301. In step S205, the starting (forward) judgment condition obtained from the judgment information is multiplied by the location information of the moving object included in the measurement information to check whether the condition is met. Speed ​​determination is generally done using speed information from a GPS sensor, but it may also be done by calculation using an acceleration sensor or by calculation from location information. Regarding the direction of travel, it is common to determine it using the value of the acceleration sensor generated when the on-board device is fixed to the moving object, but it may also be determined by other means such as combining position information and the vehicle's reverse signal. (The same method can be used to determine progress reports and speed when dealing with the judgment conditions described later, so the description will be omitted.) If the conditions are met, proceed to step S206; otherwise, proceed to step S207. In step S206, an event ID is issued, and the time of occurrence, employee, and the content of the start (forward) command (on premises) in the judgment table in Figure 4 are saved as an event result information table as shown in Figure 11 to event information 158 in Figure 1, and the process ends. In step S207, the start (reverse) judgment conditions obtained from the judgment information are multiplied by the position information of the moving object included in the measurement information to check if the conditions are met. If they are met, proceed to step S208; otherwise, proceed to step S209. In step S208, an event ID is issued, and the time of occurrence, employee, and the content of the start (reverse) command (on-premises) in the judgment table in Figure 4 are saved in the event information 158 in Figure 1 as an event result information table as shown in Figure 11, and the process ends.In step S209, the determination condition for starting (right turn) obtained from the determination information is multiplied by the position information of the moving object included in the measurement information to check if the condition is met. If it is met, the process proceeds to step S210; otherwise, it proceeds to step S211. In step S210, an event ID is issued, and the time of occurrence, employee, and the content of the right turn command (on premises) in the determination table in Figure 4 are saved as an event result information table as shown in Figure 11, and the process ends. In step S211, the determination condition for left turn obtained from the determination information is multiplied by the position information of the moving object included in the measurement information to check if the condition is met. If it is met, the process proceeds to step S212; otherwise, the process ends. In step S212, an event ID is issued, and the time of occurrence, employee, and the content of the left turn command (on premises) in the determination table in Figure 4 are saved as an event result information table as shown in Figure 11, and the process ends. In step S301, the location information of the moving object included in the measurement information is compared with the information of the intersection to determine whether the location information of the moving object is at an intersection. If it is at an intersection, the process proceeds to step S302; otherwise, it proceeds to step S401. In step S302, the location information of the moving object included in the measurement information is multiplied with the judgment condition for passing straight through the intersection obtained from the judgment information to check if the condition is met. If it is met, the process proceeds to step S303; otherwise, it proceeds to step S304. In step S303, an event ID is issued, and the occurrence time, employee, and the content of passing straight through the intersection in the judgment table in Figure 4 are saved as an event result information table as shown in Figure 11 to event information 158 in Figure 1, and the process ends. In step S304, the location information of the moving object included in the measurement information is multiplied with the judgment condition for turning right at an intersection obtained from the judgment information to check if the condition is met. If it is met, the process proceeds to step S305; otherwise, it proceeds to step S306. In step S305, an event ID is issued, and the time of occurrence, employee, and the details of the right turn at the intersection in the judgment table in Figure 4 are saved as an event result information table in Figure 11, and the process ends.In step S306, the judgment condition for turning left at an intersection obtained from the judgment information is multiplied by the position information of the moving object included in the measurement information to check if the condition is met. If it is met, proceed to step S307; otherwise, the process ends. In step S307, an event ID is issued, and the occurrence time, employee, and the content of turning left at an intersection in the judgment table in Figure 4 are saved as an event result information table as shown in Figure 11, in event information 158 in Figure 1, and the process ends. In step S401, the judgment condition for starting (moving forward) outside the premises obtained from the judgment information is multiplied by the position information of the moving object included in the measurement information to check if the condition is met. If it is met, proceed to step S402; otherwise, the process ends. In step S402, an event ID is issued, and the occurrence time, employee, and the content of the start (move forward) command (outside the premises) in the judgment table in Figure 4 are saved as an event result information table as shown in Figure 11, in event information 158 in Figure 1, and the process ends. Although the process in Figure 3 is structured according to the judgment table in Figure 4, the methods for judging safe driving in Figure 4 vary from company to company, and the processing method needs to be changed depending on the company.

[0029] Figure 4 illustrates the following events: starting (forward), starting (backward), turning right, turning left, passing straight through an intersection, passing a right turn through an intersection, and passing a left turn through an intersection. The judgment conditions in Figure 4 are the conditions for detecting the occurrence of an event. The event judgment conditions use velocity information such as acceleration and location information. For example, starting can be detected by judging that the velocity has increased from 0 m / s. Similarly, passing a right turn through an intersection can be detected by judging that the location information is an intersection and that a right turn has been made.

[0030] The instructions in Figure 4 indicate the time range of video data to be extracted in response to an event, and the verification action to be determined in response to the event. The instructions are divided into on-premises and off-premises. On-premises refers to, for example, the grounds of a factory. Off-premises refers to, for example, a public road. In other words, even for the same event, the instructions will differ depending on whether it is on or off the grounds of a factory. By using different rule sets depending on the location in this way, it is possible to determine whether appropriate safety checks are being performed according to the location.

[0031] In Figure 4, for the departure event within the premises, the time range of the video data to be extracted is the 30 seconds before departure. The departure (forward) event is shown as a confirmation action to determine whether the vehicle has pointed forward and said "ready to depart."

[0032] Figure 5 provides a more detailed explanation of step S203 in Figure 2. In step S501, event information is obtained from event information 158 in Figure 1. Next, in step S502, the status of event information acquisition is checked. If there is an event, the process proceeds to step S503; otherwise, the process ends. In step S503, a process is executed to request the in-vehicle device to provide a video of the current time and the time of determination of the acquired command, and the process proceeds to step S504. In step S504, the in-vehicle device that received the request obtains a video of the specified time from image information 373 in Figure 1. In step S505, the acquired video is sent to the information processing device 10. In step S506, the information processing device receives the video, saves it to image information 156 in Figure 1, and terminates the process.

[0033] Figure 6 is a more detailed explanation of step S104 in Figure 2. In step S601, command information is obtained from event information 158 in Figure 1. Next, in step S602, video information is obtained from image information 156 in Figure 1. In the next step S603, the generative artificial intelligence platform 20 is instructed to process the command statement and video information of the obtained command information. In step S604, the generative artificial intelligence platform 20 executes the processing of the video information based on the received command statement. In step S605, the generative artificial intelligence platform 20 returns the execution result. In step S606, the information processing device 10 receives the result. In step S607, the AI's response is determined, and if it is Yes, the process proceeds to step S608, and if it is No, it proceeds to step S609. In step S608, the target event information is determined as safe driving, and the occurrence time and employee information are combined and saved as the determination result table shown in Figure 12 in the determination result information 152 shown in Figure 1, and the process ends. In step S609, the target event is identified as unsafe driving, and the file path of the event's video information stored in the image information 156 of Figure 1, along with the time of occurrence and employee information, are combined and saved as the judgment result table shown in Figure 12, in the judgment result information 152 shown in Figure 1, before the process ends.

[0034] Figure 7 provides a more detailed explanation of step S105 in Figure 2. In step S701, the information processing device 10 obtains the real-time notification setting from the notification setting information 154 in Figure 1. In step S702, if the obtained real-time notification setting is On, the process proceeds to step S703; otherwise, the process ends. In step S703, a notification is sent to the in-vehicle device 31. In step S704, the in-vehicle device 31 receives the notification. In step S705, the in-vehicle device 31 uses the speaker 36 in Figure 1 to emit a warning sound, alerting the driver, and then the process ends.

[0035] Figure 8 shows an image of the screen used by an administrator to view the management screen. Based on the administrator's operation, the information processing device 10 retrieves a list of employees from the master information 153 in Figure 1 and displays it in the first column. The second column displays the percentage based on the judgment result obtained from the judgment result information 152 in Figure 1, with the numerator being safe driving and the denominator being the total number of events. The third column displays the file path of the video that was classified as unsafe driving. Clicking on the video file path transitions to the playback screen shown in Figure 9, where the video can be viewed. The administrator can review the video and re-evaluate whether it was safe driving or unsafe driving. If safe driving is selected, the judgment result information 152 in Figure 1 needs to be changed to safe driving, and the screen in Figure 8 is updated. Note that Figure 8 is just one example of a display method; it is also possible to display the information by organization instead of by employee.

[0036] Figure 10 shows the screen where the administrator configures real-time notifications. Turning on the real-time notification setting box enables real-time notifications. By using the mechanism described above, it becomes possible to solve the problem.

[0037] As described above, the information processing device 10 is an information processing device that determines whether or not a driver is performing safe driving actions based on video data, and comprises a communication unit (interface device 16) that communicates with the vehicle and / or a terminal on the vehicle, and a processing unit (processor 11) that processes data, wherein the communication unit receives mobile information including information about the vehicle's speed and information about its position, the processing unit detects events related to the vehicle's movement from the mobile information, the communication unit receives video data including the driver's driving actions corresponding to the event, the processing unit identifies conditions corresponding to the event, and the processing unit takes the conditions and the video data as input to the determination unit to obtain a determination result. This configuration and operation allows for limiting the amount of video data transmitted from the in-vehicle device to the bare minimum while reducing the burden on administrators to monitor the driver's adherence to safe driving practices.

[0038] Furthermore, the terminal on the vehicle continuously captures and stores video data in which the driver is within the shooting range, the processing unit determines the time range of the video data to be requested from the terminal on the vehicle in response to the event, and the communication unit transmits a request for the provision of the video data specifying the time range. This configuration and operation allows for the resizing of video data in response to events, thereby efficiently reducing data usage.

[0039] Furthermore, the mobile information includes information on the vehicle's acceleration and information on the vehicle's position, and the terminal on the vehicle is either an in-vehicle terminal mounted on the vehicle or a portable terminal that can be installed on the vehicle. In other words, information about the vehicle can be obtained from any terminal, or even from the vehicle itself.

[0040] Furthermore, the event includes any of the following: the vehicle starting, turning right or left, or passing through an intersection; the condition includes text indicating a confirmation action that the driver should perform in response to the event; and the determination unit is a generative artificial intelligence platform that takes the text and video data as input to determine whether the driver performed the confirmation action. This configuration and operation improve usability because it is possible to determine whether the driver performed the aforementioned confirmation action by issuing text-based commands to the AI ​​generator.

[0041] Furthermore, the communication unit transmits the conditions and the video data to an external device having the determination unit, and receives the determination result from the external device. This configuration also reduces the amount of communication required when interacting with an external device that has a determination unit.

[0042] Furthermore, the processing unit switches the rule set indicating the correspondence between the event and the condition according to the position of the vehicle. This configuration and operation allows for the setting of appropriate safe driving behaviors for each location, and enables the determination of whether or not the driver is performing safe driving behaviors.

[0043] Furthermore, the processing unit aggregates and outputs the events and judgment results for each driver. This configuration and operation allows for the comprehensive management of safe driving behavior by multiple drivers.

[0044] Furthermore, the communication unit receives the mobile information in real time and transmits the determination result based on the mobile information to notify the driver. This configuration and operation allows for real-time notification of any omissions in safety checks, etc., and enables the driver to be reminded to adhere to safe driving practices.

[0045] It should be noted that the present invention is not limited to the embodiments described above, and various modifications are included. For example, the embodiments described above are explained in detail to make the present invention easier to understand, and are not necessarily limited to those having all the configurations described. Furthermore, it is possible to replace or add configurations, not just delete them. For example, events and safe driving behaviors are not limited to the examples given in the above embodiment, but can be arbitrarily set. [Explanation of symbols]

[0046] 10: Information processing device, 11: Processor, 12: Memory, 13: Input device, 14: Output device, 15: Storage device, 16: Interface device, 20: Generative artificial intelligence platform, 30: Mobile device, 31: In-vehicle device, 40: Network, 41: Network, 151: Judgment program, 152: Judgment result information, 153: Master information, 154: Notification setting information, 155: Measurement information, 156: Image information, 157: Judgment condition information, 158: Event information, 372: Measurement information, 373: Image information

Claims

1. An information processing device that determines whether or not a driver is engaging in safe driving behavior based on video data, A communication unit that communicates with the vehicle and / or a terminal on the vehicle, It comprises a processing unit for processing data, The communication unit receives mobile information including information regarding the vehicle's speed and information regarding its position. The processing unit detects events related to the movement of the vehicle from the moving object information, The communication unit receives video data including the driver's driving actions corresponding to the event, The processing unit identifies the conditions corresponding to the event, The processing unit is characterized by taking the conditions and the video data as input to the determination unit to obtain a determination result.

2. An information processing apparatus according to claim 1, The terminal on the vehicle continuously captures and stores video data in which the driver is within the shooting range. The processing unit determines the time range of the video data to be requested from the terminal on the vehicle in response to the event. The communication unit transmits a request for the provision of the video data, specifying the time range. An information processing device characterized by the following:

3. An information processing apparatus according to claim 1, The aforementioned moving body information includes information on the acceleration of the vehicle and information on the position of the vehicle. The terminal on the vehicle is either an in-vehicle terminal mounted on the vehicle or a portable terminal that can be installed on the vehicle. An information processing device characterized by the following:

4. An information processing apparatus according to claim 1, The aforementioned event includes any of the following: starting the vehicle, turning right or left, or passing through an intersection. The aforementioned conditions include text indicating the confirmation action that the driver should perform in response to the event, The determination unit is a generative artificial intelligence platform that takes the text and video data as input to determine whether the driver performed the confirmation action. An information processing device characterized by the following:

5. An information processing apparatus according to claim 1, The communication unit transmits the conditions and video data to an external device having the determination unit, and receives the determination result from the external device. An information processing device characterized by the following:

6. An information processing apparatus according to claim 1, The processing unit switches the rule set indicating the correspondence between the event and the condition according to the location of the vehicle. An information processing device characterized by the following:

7. An information processing apparatus according to claim 1, The processing unit is characterized by aggregating and outputting the events and the judgment results for each driver.

8. An information processing apparatus according to claim 1, The information processing device is characterized in that the communication unit receives the mobile information in real time, transmits a determination result based on the mobile information, and notifies the driver.

9. An information processing method for determining whether or not a driver is engaging in safe driving behavior based on video data, The information processing device receives mobile information, including information regarding the vehicle's speed and information regarding its location, from a vehicle and / or a terminal on the vehicle. The information processing device includes the step of detecting an event related to the movement of the vehicle from the moving object information, The information processing device receives video data including the driver's driving actions corresponding to the event, The information processing device includes the step of identifying the conditions corresponding to the event, The information processing device takes the conditions and the video data as input to the determination unit and obtains a determination result. An information processing method characterized by including

Images