Information processing device, information processing method, and program

Abstract

Provided is an information processing device comprising: a video reception unit that receives a video captured by a camera mounted on a vehicle; a determination unit that, in response to the video reception unit receiving the video, determines the status of an AI processing server that executes AI processing for analyzing the video and generating vehicle status data representing the status of the vehicle; and a control unit that causes the AI processing server to analyze the video when the status of the AI processing server determined by the determination unit satisfies a predetermined condition, and stores the video in a video storage unit when the status of the AI processing server does not satisfy the condition.

Description

Information processing device, information processing method, and program

[0001] This invention relates to an information processing device, an information processing method, and a program.

[0002] Patent Document 1 describes performing inference using an inference model with video data captured by a camera installed in a vehicle, and recording the results of the inference in a video file that records the video data. Patent Document 2 describes learning the driving tendencies of each driver of multiple vehicles based on recorded data that includes at least vehicle information acquired for each of the multiple vehicles. Patent Document 3 describes a server that stores and manages various information such as recording information, event information, and information related to the results of aggressive driving judgments, corresponding to image information acquired by a drive recorder. Patent Document 4 describes a terminal having a communication control means for receiving multiple image information transmitted from a camera installed in a vehicle, and an image information storage means for storing the multiple image information received from the camera in a storage means for the terminal when the state of the vehicle satisfies predetermined recording conditions. [Prior Art Documents] [Patent Documents] [Patent Document 1] Japanese Unexamined Patent Publication No. 2024-005859 [Patent Document 2] Japanese Unexamined Patent Publication No. 2023-130253 [Patent Document 3] Japanese Unexamined Patent Publication No. 2022-101447 [Patent Document 4] Japanese Unexamined Patent Publication No. 2022-157491

[0003] Conventional technologies utilize dedicated inference servers for autonomous driving monitoring systems, and inference is not performed on shared servers. With the increasing demand for GPU utilization in autonomous driving monitoring systems, a future migration to shared inference servers is anticipated. This migration raises several issues: large amounts of video data may arrive at the inference server with a delay due to communication network failures; the system may immediately perform inference processing on delayed data that cannot be processed in real time; and as a result, the limited resources of the inference server may be consumed by processing delayed data that has already lost value. This situation could significantly degrade the overall efficiency and performance of the system.

[0004] According to an embodiment of the present invention, an information processing apparatus is provided. The information processing apparatus may include a video receiving unit that receives a video captured by a camera mounted on a vehicle. The information processing apparatus may include a determination unit that determines the status of an AI processing server that executes AI processing to analyze the video and generate vehicle status data representing the status of the vehicle in response to the video receiving unit receiving the video. The information processing apparatus may include a control unit that causes the AI processing server to analyze the video when the status of the AI processing server determined by the determination unit satisfies a predetermined condition, and stores the video in a video storage unit when the status of the AI processing server does not satisfy the condition.

[0005] In the information processing apparatus, the determination unit may determine the processing load of the AI processing server, and the control unit may cause the AI processing server to analyze the video when the processing load is lower than a predetermined processing load threshold, and store the video in the video storage unit when the processing load is higher than the processing load threshold.

[0006] In any of the information processing apparatuses, the control unit may cause the AI processing server to analyze the video stored in the video storage unit in response to the processing load of the AI processing server changing from a state higher than the processing load threshold to a state lower than the processing load threshold.

[0007] In any of the above-mentioned information processing devices, the AI ​​processing server may have a RAN control function for controlling RANs and an AI processing function for performing AI processing. The determination unit may determine the processing load of the RAN control function of the AI ​​processing server in response to the video receiving unit receiving the video. The control unit may have the AI ​​processing server analyze the video if the processing load of the RAN control function is lower than a predetermined threshold, and may store the video in the video storage unit if the processing load of the RAN control function is higher than the threshold. Examples of AI processing include AI processing related to RAN control (sometimes referred to as RAN control AI processing) and AI processing not related to RAN control (sometimes referred to as non-RAN control AI processing). An example of RAN control AI processing is RIC (RAN Intelligent Controller). RIC (Routine Control Unit) is a technology that uses AI to optimize RAN (Range Network) wireless resources and automate RAN operations. RIC includes Non-RT RIC (Non-Real Time RIC) and Near-RT RIC (Near-Real Time RIC). Non-RT RIC is sometimes called Centralized RIC. Non-RT RIC is located within the SMO (Service Management and Orchestration) that manages and orchestrates the RAN. Non-RT RIC generates and notifies policies related to RAN control and transmits information to Near-RT RIC. For example, a Non-RT RIC generates a learning model for RAN control by performing machine learning using data collected from the RAN, and sends it to a Near-RT RIC. A Near-RT RIC is sometimes called a Distributed RIC. Compared to a Non-RT RIC, a Near-RT RIC is located closer to the RAN nodes (RU (Radio Unit), DU (Distributed Unit), CU (Central Unit)) and performs control of the RAN nodes and resources. Compared to a Non-RT RIC, a Near-RT RIC performs processing with higher real-time capabilities.A Near-RT RIC performs inference processing related to RAN control using, for example, a trained model obtained from a Non-RT RIC. RAN control AI processing is not limited to RICs. Non-RAN control AI processing may be a so-called MEC AI application. Non-RAN control AI processing includes training and inference processing of any AI unrelated to RAN control.

[0008] In any of the above-mentioned information processing devices, the control unit may have the AI ​​processing server analyze the video if the elapsed time from when the vehicle transmits the video until when the video receiving unit receives it is shorter than a predetermined time threshold, and the status of the AI ​​processing server determined by the determination unit satisfies the above conditions. The control unit may store the video in the video storage unit if the elapsed time from when the vehicle transmits the video until when the video receiving unit receives it is shorter than the time threshold, and the status of the AI ​​processing server determined by the determination unit does not satisfy the above conditions, or if the elapsed time is longer than the time threshold.

[0009] In any of the above-mentioned information processing devices, the control unit may, when the video receiving unit receives multiple videos from multiple vehicles, cause the AI ​​processing server to analyze the multiple videos in order of priority of the multiple vehicles until the processing load of the AI ​​processing server exceeds a predetermined processing load threshold. The control unit may, when the video receiving unit receives multiple videos from multiple vehicles, cause the AI ​​processing server to analyze the multiple videos in order of increasing risk based on the attributes of the location of each of the multiple vehicles until the processing load of the AI ​​processing server exceeds a predetermined processing load threshold. The control unit may, when the video receiving unit receives multiple videos from multiple vehicles, cause the AI ​​processing server to analyze the multiple videos in order of priority based on the attributes of the passengers of each of the multiple vehicles until the processing load of the AI ​​processing server exceeds a predetermined processing load threshold.

[0010] In any of the above-mentioned information processing devices, the control unit may predict the time it takes for the AI ​​processing server to analyze the video, and if the analysis time is shorter than a predetermined time threshold, it may have the AI ​​processing server analyze the video, and if the analysis time is longer than the time threshold, it may store the video in the video storage unit.

[0011] According to one embodiment of the present invention, an information processing method performed by a computer is provided. The information processing method may include a video reception step of receiving a video captured by a camera mounted on a vehicle. The information processing method may include a determination step of determining the status of a processing execution unit that performs AI processing to analyze the video and identify the status of the vehicle, in response to receiving the video in the video reception step. The information processing method may include a control step of causing the processing execution unit to analyze the video if the status of the processing execution unit determined in the determination step satisfies predetermined conditions, and storing the video in a video storage unit if the status of the processing execution unit does not satisfy the conditions.

[0012] According to one embodiment of the present invention, a program is provided for a computer to execute the following steps: a video reception step of receiving a video captured by a camera mounted on a vehicle; a determination step of determining the status of a processing execution unit that performs AI processing to analyze the video and identify the status of the vehicle, in response to receiving the video in the video reception step; and a control step of causing the processing execution unit to analyze the video if the status of the processing execution unit determined in the determination step satisfies predetermined conditions, and storing the video in a storage unit if the status of the processing execution unit does not satisfy the conditions.

[0013] It should be noted that the above summary of the invention does not enumerate all the necessary features of the present invention. Furthermore, subcombinations of these features may also constitute an invention.

[0014] An example of the information processing system 10 is shown in general terms. An example of the processing flow by the information processing device 100 is shown in general terms. An example of the processing flow by the information processing device 100 is shown in general terms. An example of the processing flow by the information processing device 100 is shown in general terms. An example of the processing flow by the information processing device 100 is shown in general terms. An example of the processing flow by the information processing device 100 is shown in general terms. An example of the processing flow by the information processing device 100 is shown in general terms. An example of the network configuration of the information processing device 100 is shown in general terms. An example of the network configuration of the information processing device 100 is shown in general terms. An example of the functional configuration of the information processing device 100 is shown in general terms. An example of the hardware configuration of the computer 1200 that functions as the information processing device 100 or AI processing server 200 is shown in general terms.

[0015] The present invention will be described below through embodiments, but these embodiments are not intended to limit the scope of the claims. Furthermore, not all combinations of features described in the embodiments are necessarily essential to the solution of the invention.

[0016] Figure 1 schematically shows an example of an information processing system 10. The information processing system 10 includes an information processing device 100. The information processing system 10 includes an AI processing server 200. The information processing system 10 may include a relay unit 310. The information processing system 10 may include a DB 320. The information processing system 10 may include an operation PF server 330.

[0017] The information processing device 100 collects video 410 captured by a camera 402 mounted on the vehicle 400. The information processing device 100 may receive the video 410 via a mobile communication network. The video 410 may be transmitted by the camera 402 or by a communication device mounted on the vehicle 400. The information processing device 100 transmits the collected video 410 to the AI ​​processing server 200.

[0018] Vehicle 400 may be a so-called autonomous vehicle. Camera 402 may be a drive recorder. Camera 402 may be a camera that captures images for use in controlling autonomous driving. Camera 402 may be any other type of camera. Vehicle 400 does not have to be an autonomous vehicle.

[0019] The AI ​​processing server 200 analyzes the video 410 received from the information processing device 100 and performs AI processing to generate vehicle status data 220 that represents the status of the vehicle 400. The vehicle status data 220 may be text data that represents the status of the vehicle 400.

[0020] The AI ​​processing server 200 may pre-store a learning model that takes video 410 as input and outputs vehicle status data 220 representing the status of the vehicle 400 equipped with the camera 402 that captured the video 410, by using multiple learning data sets that include video 410 and vehicle status data 220 representing the status of the vehicle 400 equipped with the camera 402 that captured the video 410. The AI ​​processing server 200 may then use this learning model to generate vehicle status data 220 from video 410 received from the information processing device 100.

[0021] The AI ​​processing server 200 may use a text generation AI. The AI ​​processing server 200 may generate vehicle status data 220 by inputting the video 410 received from the information processing device 100 and a prompt to generate vehicle status data 220 representing the status of the vehicle 400 equipped with the camera 402 that captured the video 410, based on the video 410, to the text generation AI.

[0022] The AI ​​processing server 200 may transmit the generated vehicle status data 220 to the relay unit 310. The relay unit 310 may store the received vehicle status data 220 in the DB 320. The AI ​​processing server 200 may also transmit the video 410 that was used to generate the vehicle status data 220 to the relay unit 310. The relay unit 310 may store the received video 410 in the DB 320 in association with the vehicle status data 220.

[0023] The operational PF server 330 manages the data stored in the DB 320. The operational PF server 330 provides vehicle status data 220 and videos 410 to the person in charge 30 who monitors the status of multiple vehicles 400. When the person in charge 30 wants to view the history of vehicle status data 220 and videos 410, they may access the operational PF server 330 via the operational PFWeb 340. When the person in charge 30 wants to view vehicle status data 220 and videos 410 in real time, they may directly access the relay unit 310 via the operational PFWeb 340 to obtain and view the vehicle status data 220 and videos 410 from the relay unit 310.

[0024] By allowing the person in charge 30 to view vehicle status data 220 and video 410 in real time, it becomes possible to issue a warning to the vehicle 400 or control the vehicle 400's autonomous driving if a problem occurs with the vehicle 400 or if a problem is likely to occur.

[0025] When a large number of videos 410 are transmitted to the AI ​​processing server 200, the processing load on the AI ​​processing server 200 may become excessively high. Also, if the AI ​​processing server 200 is a shared server that performs processing other than AI processing, such as analyzing the videos 410 received from the information processing device 100 to generate vehicle status data 220 representing the status of the vehicle 400, the processing load on the AI ​​processing server 200 may become excessively high due to other processing.

[0026] If the processing load on the AI ​​processing server 200 becomes excessively high, it may become difficult to analyze the video 410 in real time, and a significant amount of time may be required to complete the analysis. In cases where the purpose is real-time monitoring of the vehicle 400, if the vehicle status data 220 is provided a long time after the vehicle 400 transmits the video 410, its value may be very low. The limited resources of the AI ​​processing server 200 may be consumed in order to generate the vehicle status data 220, which could significantly reduce the overall efficiency and performance.

[0027] The information processing device 100 according to this embodiment provides technology that can contribute to solving such problems. For example, the information processing device 100 continuously receives status data 210 indicating the status of the AI ​​processing server 200, and when it determines that the AI ​​processing server 200 can analyze the video 410 in real time, it has the AI ​​processing server 200 analyze the video 410. When it determines that the AI ​​processing server 200 cannot analyze the video 410 in real time, it stores the video 410 in the video storage unit 110. The information processing device 100 then controls the analysis of the video 410 stored in the video storage unit 110 in a way that does not interfere with the AI ​​processing server 200. For example, when the processing load on the AI ​​processing server 200 is low, the information processing device 100 has the AI ​​processing server 200 analyze the video 410 in the video storage unit 110. For example, the information processing device 100 causes another device capable of performing AI processing similar to that of the AI ​​processing server 200 to analyze the video 410 in the video storage unit 110.

[0028] Figure 2 schematically shows an example of the processing flow by the information processing device 100. Here, the state in which the information processing device 100 is waiting for video 410 from the vehicle 400 is described as the starting state.

[0029] In step 102 (steps may be abbreviated as S), the information processing device 100 receives video 410 from the vehicle 400. In step S104, the information processing device 100 determines, based on the status data 210 of the AI ​​processing server 200, whether the processing load of the AI ​​processing server 200 is below a predetermined threshold.

[0030] The threshold may be set to a processing load value that indicates a high probability that the AI ​​processing server 200 can process the video 410 in real time. This threshold may be arbitrarily set and may be changeable. Real-time processing means that the video 410 can be processed within a predetermined time. This predetermined time depends on the monitoring targets of the vehicle 400, but may be, for example, in units of one second or ten seconds.

[0031] The status data 210 may represent the processing load of the AI ​​processing server 200. The processing load of the AI ​​processing server 200 may be the GPU utilization rate of the AI ​​processing server 200. The processing load of the AI ​​processing server 200 may be the CPU utilization rate of the AI ​​processing server 200. The processing load of the AI ​​processing server 200 may be the CPU utilization rate and the GPU utilization rate of the AI ​​processing server 200. Not limited to these, the processing load of the AI ​​processing server 200 may be other information that represents the processing load of the AI ​​processing server 200. If it is determined that the processing load of the AI ​​processing server 200 is below a predetermined threshold, the process proceeds to S106; if it is determined that it is not below the threshold, the process proceeds to S108.

[0032] In S106, the information processing device 100 transmits the video 410 to the AI ​​processing server 200, causing the AI ​​processing server 200 to perform analysis of the video 410. In S108, the information processing device 100 stores the video 410 in the video storage unit 110.

[0033] This allows the AI ​​processing server 200 to analyze the video 410 when its processing load is low and there is a high probability that it can process the video 410 in real time. Conversely, when the processing load on the AI ​​processing server 200 is high and there is a high probability that it cannot process the video 410 in real time, the video 410 can be temporarily stored in the video storage unit 110 without being analyzed by the AI ​​processing server 200. This reduces the likelihood of situations where the processing load on the AI ​​processing server 200 increases further by having it analyze videos 410 that cannot be analyzed in real time, making it impossible to analyze subsequent videos 410 in real time as well.

[0034] Figure 3 schematically shows an example of the processing flow by the information processing device 100. Here, the state in which an unanalyzed video 410 is stored in the video storage unit 110 is described as the starting state. The information processing device 100 may, for example, periodically check whether an unanalyzed video 410 is stored in the video storage unit 110, and if it is stored, execute the processing shown in Figure 3.

[0035] In S202, the information processing device 100 determines, based on the status data 210 of the AI ​​processing server 200, whether the processing load of the AI ​​processing server 200 is below a predetermined threshold. If it is determined to be below the threshold, the process proceeds to S204; otherwise, the process terminates.

[0036] In S204, the information processing device 100 transmits the video 410 from the video storage unit 110 to the AI ​​processing server 200 for analysis. For example, if the video storage unit 110 has multiple videos 410 stored in it, the information processing device 100 transmits either one of the videos 410 or a predetermined number of videos 410 to the AI ​​processing server 200 for analysis.

[0037] In S206, the information processing device 100 determines whether the analysis of the unanalyzed video 410 in the video storage unit 110 has been completed. If it has not been completed, the process returns to S202 and determines whether the processing load of the AI ​​processing server 200 is below a predetermined threshold. If it has been completed, the process is terminated.

[0038] Even if the analysis results of video 410 cannot be performed in real time, they can be used to analyze autonomous driving control or to identify the past state of vehicle 400. When the information processing device 100 performs the processing shown in Figure 3, the processing load on the AI ​​processing server 200 is low and does not affect the real-time analysis by the AI ​​processing server 200, allowing the AI ​​processing server 200 to analyze the video 410 in the video storage unit 110.

[0039] Figure 4 schematically shows an example of the processing flow by the information processing device 100. Here, we will mainly explain the differences from Figure 2.

[0040] In S302, the information processing device 100 receives the video 410 from the vehicle 400. In S304, the information processing device 100 predicts the analysis time of the video 410 received in S302 by the AI ​​processing server 200. The information processing device 100 predicts the analysis time, for example, from the data size of the video 410 and the processing load of the AI ​​processing server 200.

[0041] In S306, the information processing apparatus 100 determines whether the predicted analysis time predicted in S304 is less than or equal to a predetermined time threshold. As the time threshold, a time that can determine whether real-time processing is possible may be set. As the threshold, a time in units of 1 second, 10 seconds, etc. may be set. The threshold may be set arbitrarily and may be changeable. If it is determined that the time is less than or equal to the threshold, the process proceeds to S308. If it is determined that the time is not less than or equal to the threshold, the process proceeds to S310.

[0042] In S308, the information processing apparatus 100 transmits the video 410 to the AI processing server 200 and causes the AI processing server 200 to execute analysis of the video 410. In S310, the information processing apparatus 100 stores the video 410 in the video storage unit 110.

[0043] Thereby, when it is predicted that real-time processing is possible based on the data size of the video 410 and the processing load of the AI processing server 200, the AI processing server 200 is caused to analyze the video 410. Otherwise, the video 410 can be temporarily stored in the video storage unit 110 without causing the AI processing server 200 to analyze the video 410. Thereby, by causing the AI processing server 200 to analyze the video 410 that cannot be analyzed in real time, it is possible to reduce the occurrence of a situation where the processing load of the AI processing server 200 further increases and subsequent videos 410 cannot be analyzed in real time.

[0044] FIG. 5 schematically shows an example of the processing flow by the information processing apparatus 100. In FIG. 5, the processing flow when the information processing apparatus 100 changes the handling of the video 410 according to how much time has elapsed since the video 410 received from the vehicle 400 was transmitted will be described. Here, the points different from FIG. 2 will be mainly described.

[0045] In S402, the information processing apparatus 100 receives the video 410 from the vehicle 400. In S404, the information processing apparatus 100 determines whether the elapsed time from the transmission to the reception of the video 410 is equal to or less than a predetermined time threshold. For example, the information processing apparatus 100 determines the elapsed time from the transmission to the reception of the video 410 based on the transmission timestamp of the video 410 and the time when the video 410 is received. As the time threshold, a time that can determine that real-time processing of the video 410 is already impossible may be set from the elapsed time. The time threshold may be set arbitrarily and may be changeable. If it is determined that the time is equal to or less than the time threshold, the process proceeds to S406. If it is determined that the time is not equal to or less than the time threshold, the process proceeds to S410.

[0046] In S406, the information processing apparatus 100 determines whether the processing load of the AI processing server 200 is equal to or less than a predetermined threshold based on the status data 210 of the AI processing server 200. If it is determined that the processing load is equal to or less than the threshold, the process proceeds to S406. If it is determined that the processing load is not equal to or less than the threshold, the process proceeds to S410.

[0047] In S408, the information processing apparatus 100 transmits the video 410 to the AI processing server 200 and causes the AI processing server 200 to execute analysis of the video 410. In S410, the information processing apparatus 100 stores the video 410 in the video storage unit 110.

[0048] Thereby, due to the communication delay between the vehicle 400 and the information processing apparatus 100, a certain amount of time has elapsed from the transmission of the video 410, and in a situation where real-time processing is impossible even if the video 410 is analyzed as quickly as possible, it is possible to prevent the AI processing server 200 from analyzing the video 410.

[0049] FIG. 6 schematically shows an example of the processing flow by the information processing apparatus 100. Here, the differences from FIG. 5 will be mainly described.

[0050] In S502, the information processing device 100 receives the video 410 from the vehicle 400. In S504, the information processing device 100 determines whether the elapsed time from transmission to reception of the video 410 is less than or equal to a predetermined time threshold. If it determines that it is less than or equal to the time threshold, the process proceeds to S506; otherwise, the process proceeds to S512.

[0051] In S506, the information processing device 100 predicts the analysis time of the video 410 received in S502 by the AI ​​processing server 200. In S508, the information processing device 100 determines whether the predicted analysis time predicted in S506 is less than or equal to a predetermined time threshold. If it is determined to be less than or equal to the threshold, the process proceeds to S510; otherwise, the process proceeds to S512.

[0052] In S510, the information processing device 100 transmits the video 410 to the AI ​​processing server 200, causing the AI ​​processing server 200 to perform analysis of the video 410. In S512, the information processing device 100 stores the video 410 in the video storage unit 110.

[0053] Figure 7 schematically shows an example of the processing flow by the information processing device 100. Here, we will explain an example of the processing flow when the information processing device 100 receives multiple videos 410 simultaneously or sequentially from multiple vehicles 400.

[0054] In S602, the information processing device 100 receives multiple videos 410 from multiple vehicles 400. In S604, the information processing device 100 determines the order of the multiple videos 410 received in S602.

[0055] The information processing device 100 determines the order of multiple videos 410 in order of priority. The information processing device 100 determines the order of multiple videos 410 in order of risk level based on the location attribute of the vehicle 400 that transmitted the video 410. The information processing device 100 determines the order of multiple videos 410 in order of priority based on the attribute of the passengers of the vehicle 400 that transmitted the video 410. The priority based on the attribute of the passengers of the vehicle 400 may be higher for a larger number of passengers. The information processing device 100 determines the order of multiple videos 410 in order of priority based on the attribute of the vehicle 400 that transmitted the video 410. The priority based on the attribute of the vehicle 400 may be a priority determined from the specifications or model of the vehicle 400.

[0056] In S606, the information processing device 100 determines, based on the status data 210 of the AI ​​processing server 200, whether the processing load of the AI ​​processing server 200 is below a predetermined threshold. If it is determined to be below the threshold, the process proceeds to S608; otherwise, the process proceeds to S612.

[0057] In S608, the information processing device 100 sends the video 410 that was determined to be the first in the sequence determined in S604 among the multiple videos 410 received in S602 to the AI ​​processing server 200 for analysis. In S610, the information processing device 100 determines whether the analysis of the multiple videos 510 received in S602 has been completed. If it determines that it has not been completed, it returns to S606; if it determines that it has been completed, it terminates the process.

[0058] In S612, the information processing device 100 stores the unanalyzed video from the multiple video files 410 received in S602 in the video storage unit 110. Then, it terminates the process.

[0059] This allows the AI ​​processing server 200 to analyze the videos 410 in order of priority until the processing load of the AI ​​processing server 200 reaches a threshold, and then store the remaining videos 410 in the video storage unit 110.

[0060] Figure 8 schematically shows an example of the network configuration of the information processing device 100. In the example shown in Figure 8, the information processing device 100 is connected to a network 50. Network 50 may include a cloud network. Network 50 may include the Internet. Network 50 may include a mobile communication network. The mobile communication network may conform to any of the following mobile communication systems: LTE (Long Term Evolution) communication system, 5G (5th Generation) communication system, 3G (3rd Generation) communication system, and 6G (6th Generation) communication system or later.

[0061] For example, the information processing device 100 may be located in a cloud network. The information processing device 100 may also be located in a mobile communication network. For example, the information processing device 100 may be located in a MEC (Multi-access Edge Computing) system. The information processing device 100 may also be located in a core network.

[0062] The AI ​​processing server 200 may be located on a cloud network. The AI ​​processing server 200 may be located on a mobile communication network. For example, the AI ​​processing server 200 may be located on a MEC. The AI ​​processing server 200 may be located on a core network.

[0063] Although not shown in the diagram, in the example shown in Figure 8, the relay unit 310, DB 320, and operation PF server 330 may be connected to the network 50.

[0064] Figure 9 schematically shows an example of the network configuration of the information processing device 100. The information processing device 100 may be deployed in a mobile communication system consisting of a management infrastructure 500, a plurality of distributed infrastructures 600, and a plurality of wireless base stations 700. In this mobile communication system, the management infrastructure 500 and the plurality of distributed infrastructures 600 cooperate to control the RAN 710 and perform AI processing. Mobile communication services are provided to the vehicle 400 by the RAN 710. The RAN 710 may be a virtualized vRAN (Virtual RAN), and the mobile communication system may perform control of the vRAN. The RAN 710 may also be a physical RAN, and the mobile communication system may perform control of the physical RAN.

[0065] The distributed infrastructure 600 may be data centers located in various locations. The distributed infrastructure 600 may be composed of multiple devices. The distributed infrastructure 600 may be implemented on a virtualization infrastructure consisting of multiple devices. The distributed infrastructure 600 may be implemented by a single device. That is, the distributed infrastructure 600 may be a distributed device. The distributed infrastructure 600 may function as a BBU (BaseBand Unit), and the wireless base station 700 may function as an RRU (Remote Radio Unit). The distributed infrastructure 600 may implement a CU. The distributed infrastructure 600 may implement a DU. The distributed infrastructure 600 may implement a UPF (User Plane Function).

[0066] The management infrastructure 500 may be a data center that manages multiple distributed infrastructures 600. The management infrastructure 500 may be composed of multiple devices. The management infrastructure 500 may be implemented on a virtualization infrastructure consisting of multiple devices. The management infrastructure 500 may be implemented by a single device. In other words, the management infrastructure 500 may be a management device.

[0067] The management infrastructure 500 may be called the Core Brain, and the distributed infrastructure 600 may be called the Regional Brain. Note that Figure 9 illustrates a case where a single-layer distributed infrastructure 600 is located below the management infrastructure 500, but it is not limited to this. The distributed infrastructure 600 may have multiple layers. For example, if two layers of distributed infrastructure 600 are located below the management infrastructure 500, the management infrastructure 500 may be called the Core Brain, the lower-layer distributed infrastructure 600 may be called the Regional Brain, and the further lower-layer distributed infrastructure 600 may be called the Sub-Regional Brain.

[0068] The AI ​​processing server 200, located on the distributed infrastructure 600, may have one or more CPUs (Central Processing Units) and one or more GPUs (Graphics Processing Units). The AI ​​processing server 200 may have multiple superchips, each connected by an interconnect. This interconnect may be memory-consistent and capable of achieving high bandwidth and low latency. Thus, the AI ​​processing server 200 may have both CPU resources and GPU resources as computing resources.

[0069] The information processing device 100, located on the distributed infrastructure 600, may have one or more CPUs (Central Processing Units) and one or more GPUs (Graphics Processing Units). The information processing device 100 may have multiple superchips, each connected by an interconnect. This interconnect may be memory-consistent and capable of achieving high bandwidth and low latency. Thus, the information processing device 100 may have both CPU resources and GPU resources as computing resources.

[0070] The AI ​​processing server 200 may have a RAN control function for controlling the RAN 710 and an AI processing function for performing AI processing. Examples of AI processing include RAN-controlled AI processing and non-RAN-controlled AI processing.

[0071] Although not shown in the diagram, in the example shown in Figure 9, the relay unit 310, DB 320, and operation PF server 330 may be located on a cloud network. The relay unit 310, DB 320, and operation PF server 330 may also be connected to the management infrastructure 500 or the distributed infrastructure 600.

[0072] In the example shown in Figure 9, the information processing device 100, upon receiving the video 410, determines the processing load of the RAN control function of the AI ​​processing server 200. If the processing load of the RAN control function is lower than a predetermined threshold, it may have the AI ​​processing server 200 analyze the video 410. If the processing load of the RAN control function is higher than the threshold, it may store the video 410 in the video storage unit 110. This allows the analysis of the video 410 to be performed without interfering with the RAN control of the AI ​​processing server 200.

[0073] Figure 10 schematically shows an example of the functional configuration of the information processing device 100. The information processing device 100 comprises a video storage unit 110, a server data receiving unit 112, a video receiving unit 114, a determination unit 116, a control unit 118, and a server transmission unit 120.

[0074] The server data receiving unit 112 receives data from the AI ​​processing server 200. For example, the server data receiving unit 112 receives status data 210 from the AI ​​processing server 200. The AI ​​processing server 200 may continuously transmit the status data 210 to the information processing device 100. For example, the AI ​​processing server 200 may periodically transmit the status data 210 to the information processing device 100 according to predetermined timings. The AI ​​processing server 200 may also irregularly transmit the status data 210 to the information processing device 100 according to predetermined timings. Instead of continuously transmitting the status data 210 to the information processing device 100, the AI ​​processing server 200 may transmit the status data 210 to the information processing device 100 whenever there is a change in the status of the AI ​​processing server 200.

[0075] The video receiving unit 114 receives video 410 from the vehicle 400. The video receiving unit 114 receives video 410 from each of the multiple vehicles 400. The vehicle 400 may continuously transmit video 410 to the information processing device 100. For example, the vehicle 400 may periodically transmit video 410 to the information processing device 100 according to predetermined timings. The vehicle 400 may also transmit video 410 to the information processing device 100 irregularly according to predetermined timings. Instead of continuously transmitting video 410 to the information processing device 100, the vehicle 400 may transmit video 410 to the information processing device 100 whenever there is a change in the status of the vehicle 400.

[0076] The determination unit 116 determines the status of the AI ​​processing server 200 in response to the video receiving unit 114 receiving the video 410. The determination unit 116 may determine the status of the AI ​​processing server 200 based on the status data 210 received by the server data receiving unit 112. For example, the determination unit 116 determines the processing load of the AI ​​processing server 200.

[0077] The control unit 118 transmits the video 410 to the AI ​​processing server 200 if the status of the AI ​​processing server 200 determined by the determination unit 116 satisfies predetermined conditions, and has the AI ​​processing server 200 analyze the video 410. If the status of the AI ​​processing server 200 does not satisfy the conditions, the control unit 118 stores the video 410 in the video storage unit 110.

[0078] This condition may be one that is met when the processing load of the AI ​​processing server 200 is lower than a predetermined processing load threshold. That is, the control unit 118 may have the AI ​​processing server 200 analyze the video 410 when the processing load of the AI ​​processing server 200 is lower than the processing load threshold, and may store the video 410 in the video storage unit 110 when the processing load is higher than the processing load threshold. As the processing load threshold, for example, a value that can determine whether or not the AI ​​processing server 200 can process the video 410 in real time is set. The processing load threshold may be arbitrarily set and may be changeable.

[0079] The control unit 118 may, in response to a change in the processing load of the AI ​​processing server 200 from a state higher than the processing load threshold to a state lower than the processing load threshold, transmit the video 410 stored in the video storage unit 110 to the AI ​​processing server 200 for analysis.

[0080] These measures allow the AI ​​processing server 200 to analyze the video 410 when its processing load is relatively low, and prevent the AI ​​processing server 200 from generating low-value results by analyzing the video 410 even when it cannot process it in real time, and prevent further increases in the processing load of the AI ​​processing server 200 when its processing load is relatively high and it is not possible or difficult to process the video 410 in real time. Furthermore, when the processing load of the AI ​​processing server 200 is relatively low, the video 410 can be temporarily stored and then analyzed, which can be used to analyze autonomous driving control or to identify the past conditions of the vehicle 400.

[0081] As described above, the AI ​​processing server 200 may have both a RAN control function and an AI processing function. In this case, the determination unit 116 may determine the processing load of the RAN control function of the AI ​​processing server 200 in response to the video receiving unit 114 receiving the video 410. The control unit 118 may have the AI ​​processing server 200 analyze the video 410 if the processing load of the RAN control function is lower than the processing load threshold, and may store the video 410 in the video storage unit 110 if the processing load of the RAN control function is higher than the processing load threshold. The RAN control function will affect many communications, including those of the vehicle 400 and smartphones, and will generally have a greater impact on the overall service than the AI ​​processing function. In contrast, by having the information processing device 100 perform such processing, the analysis of the video 410 can be performed without interfering with the RAN control function of the AI ​​processing server 200, thereby contributing to the improvement of the overall service.

[0082] The control unit 118 may have the AI ​​processing server 200 analyze the video 410 if the elapsed time from when the vehicle 400 transmits the video 410 until when the video receiving unit 114 receives it is shorter than a predetermined time threshold, and the status of the AI ​​processing server 200 determined by the determination unit 116 satisfies predetermined conditions. The control unit 118 may store the video 410 in the video storage unit 110 if the elapsed time from when the vehicle 400 transmits the video 410 until when the video receiving unit 114 receives it is shorter than a predetermined time threshold, and the status of the AI ​​processing server 200 determined by the determination unit 116 does not satisfy the conditions, or if the elapsed time is longer than the time threshold.

[0083] The control unit 118 determines, for example, the elapsed time from the transmission timestamp of the video 410 to the reception of the video 410, based on the transmission timestamp of the video 410 and the time the video 410 was received. The time threshold may be set to a time that allows it to determine from the elapsed time that real-time processing of the video 410 is no longer possible. The time threshold may be arbitrarily set and may be changed.

[0084] The control unit 118 predicts the analysis time of the video 410 by the AI ​​processing server 200. If the predicted analysis time is shorter than a predetermined time threshold, the control unit 118 may have the AI ​​processing server 200 analyze the video 410. If the predicted analysis time is longer than the time threshold, the control unit 118 may store the video 410 in the video storage unit 110. The control unit 118 predicts the analysis time, for example, from the data size of the video 410 and the processing load of the AI ​​processing server 200. The time threshold may be set to a time that allows for the determination of whether or not processing is possible in real time. The threshold may be set to a time in units of 1 second, 10 seconds, etc. The threshold may be arbitrarily set and may be changed.

[0085] When the video receiving unit 114 receives multiple videos 410 from multiple vehicles 400, the control unit 118 may cause the AI ​​processing server 200 to analyze the multiple videos 410 in the order of priority of the multiple vehicles 400 until the processing load of the AI ​​processing server 200 exceeds the processing load threshold.

[0086] The control unit 118 may, for example, arrange the multiple videos 410 in order of increasing risk based on the location attributes of the vehicle 400 that transmitted the videos 410. That is, when the video receiving unit 114 receives multiple videos 410 from multiple vehicles 400, the control unit 118 may cause the AI ​​processing server 200 to analyze the multiple videos 410 in order of increasing risk based on the location attributes of each of the multiple vehicles 400 until the processing load of the AI ​​processing server 200 exceeds a processing load threshold. The risk levels based on location attributes may be set in advance. For example, accident-prone locations may be set to have a high risk level. For example, intersections may be set to have a high risk level. For example, highways may be set to have a high risk level.

[0087] The control unit 118 may, for example, determine the order of the multiple videos 410 based on a priority order determined by the attributes of the passengers of the vehicle 400 that transmitted the videos 410. That is, when the video receiving unit 114 receives multiple videos 410 from multiple vehicles 400, the control unit 118 may cause the AI ​​processing server 200 to analyze the multiple videos 410 in a priority order based on the attributes of the passengers of each of the multiple vehicles 400 until the processing load of the AI ​​processing server 200 exceeds a processing load threshold. The priority order based on the passenger attributes may be set in advance. For example, a higher priority may be set for a larger number of passengers.

[0088] The control unit 118 may, for example, determine the order of the multiple videos 410 based on the priority order of the attributes of the vehicle 400 that transmitted the videos 410. That is, when the video receiving unit 114 receives multiple videos 410 from multiple vehicles 400, the control unit 118 may cause the AI ​​processing server 200 to analyze the multiple videos 410 in the priority order based on the attributes of the multiple vehicles 400 until the processing load of the AI ​​processing server 200 exceeds a processing load threshold. The priority order based on the attributes of the vehicle 400 may be set in advance. For example, a higher price may be assigned a higher priority. For example, a higher rarity may be assigned a higher priority. For example, a larger size may be assigned a higher priority. For example, public transportation vehicles such as buses may be assigned a higher priority compared to general vehicles.

[0089] Figure 11 schematically shows an example of the hardware configuration of a computer 1200 that functions as an information processing device 100 or an AI processing server 200. A program installed on the computer 1200 can cause the computer 1200 to function as one or more "parts" of the device according to this embodiment, or to cause the computer 1200 to execute operations associated with the device according to this embodiment or such one or more "parts", and / or to cause the computer 1200 to execute a process or a stage of such process according to this embodiment. Such a program may be executed by the CPU 1212 to cause the computer 1200 to execute specific operations associated with some or all of the blocks in the flowcharts and block diagrams described herein.

[0090] The computer 1200 according to this embodiment includes a CPU 1212, a GPU 1213, a RAM 1214, and a graphics controller 1216, which are interconnected by a host controller 1210. The computer 1200 also includes input / output units such as a communication interface 1222, a storage device 1224, a DVD drive 1226, and an IC card drive, which are connected to the host controller 1210 via an input / output controller 1220. The DVD drive 1226 may be a DVD-ROM drive and a DVD-RAM drive, etc. The storage device 1224 may be a hard disk drive and a solid-state drive, etc. The computer 1200 also includes legacy input / output units such as a ROM 1230 and a keyboard, which are connected to the input / output controller 1220 via an input / output chip 1240.

[0091] The CPU 1212 operates according to the programs stored in the ROM 1230 and RAM 1214, thereby controlling each unit. The graphics controller 1216 acquires the image data generated by the CPU 1212 and stores it in the frame buffer provided in the RAM 1214 or within itself, so that the image data is displayed on the display device 1218.

[0092] The communication interface 1222 communicates with other electronic devices via a network. The storage device 1224 stores programs and data used by the CPU 1212 in the computer 1200. The DVD drive 1226 reads programs or data from the DVD-ROM 1227, etc., and provides them to the storage device 1224. The IC card drive reads programs and data from the IC card and / or writes programs and data to the IC card.

[0093] The ROM 1230 stores boot programs and / or hardware-dependent programs of the computer 1200, which are executed by the computer 1200 when activated. The input / output chip 1240 may also connect various input / output units to the input / output controller 1220 via USB ports, parallel ports, serial ports, keyboard ports, mouse ports, etc.

[0094] The program is provided on a computer-readable storage medium such as a DVD-ROM 1227 or an IC card. The program is read from the computer-readable storage medium and installed on a storage device 1224, RAM 1214, or ROM 1230, which are examples of computer-readable storage media, and executed by the CPU 1212. The information processing described within these programs is read by the computer 1200, resulting in coordination between the program and the various types of hardware resources described above. The apparatus or method may be configured to realize the operation or processing of information in accordance with the use of the computer 1200.

[0095] For example, when communication is performed between a computer 1200 and an external device, the CPU 1212 may execute a communication program loaded into the RAM 1214 and, based on the processing described in the communication program, instruct the communication interface 1222 to perform communication processing. Under the control of the CPU 1212, the communication interface 1222 reads transmission data stored in a transmission buffer area provided in a recording medium such as the RAM 1214, storage device 1224, DVD-ROM 1227, or IC card, transmits the read transmission data to the network, or writes received data received from the network to a reception buffer area or the like provided on the recording medium.

[0096] Furthermore, the CPU 1212 may read all or necessary parts of a file or database stored on an external recording medium such as a storage device 1224, a DVD drive 1226 (DVD-ROM 1227), or an IC card into the RAM 1214, and perform various types of processing on the data in the RAM 1214. The CPU 1212 may then write the processed data back to the external recording medium.

[0097] Various types of information, such as various types of programs, data, tables, and databases, may be stored on the recording medium and subjected to information processing. The CPU 1212 may perform various types of processing on the data read from the RAM 1214, including various types of operations, information processing, conditional judgments, conditional branching, unconditional branching, information retrieval / replacement, etc., as described throughout this disclosure and specified by the program instruction sequence, and write the results back to the RAM 1214. The CPU 1212 may also retrieve information in files, databases, etc., within the recording medium. For example, if a plurality of entries are stored in the recording medium, each having an attribute value of a first attribute associated with an attribute value of a second attribute, the CPU 1212 may search among the plurality of entries for an entry that matches the specified condition for the attribute value of the first attribute, read the attribute value of the second attribute stored in that entry, and thereby obtain the attribute value of the second attribute associated with the first attribute that satisfies a predetermined condition.

[0098] The program or software module described above may be stored on or near the computer 1200 in a computer-readable storage medium. Alternatively, a recording medium such as a hard disk or RAM provided within a server system connected to a dedicated communication network or the Internet can be used as a computer-readable storage medium, thereby providing the program to the computer 1200 via the network.

[0099] In this embodiment, blocks in the flowchart and block diagram may represent a stage in a process in which an operation is performed or a "part" of a device that has the role of performing an operation. A particular stage and "part" may be implemented by a dedicated circuit, a programmable circuit supplied with computer-readable instructions stored on a computer-readable storage medium, and / or a processor supplied with computer-readable instructions stored on a computer-readable storage medium. The dedicated circuit may include digital and / or analog hardware circuits, and may include integrated circuits (ICs) and / or discrete circuits. The programmable circuit may include reconfigurable hardware circuits, such as field-programmable gate arrays (FPGAs) and programmable logic arrays (PLAs), which include logical AND, logical OR, exclusive OR, negated AND, negated OR, and other logical operations, flip-flops, registers, and memory elements.

[0100] A computer-readable storage medium may include any tangible device capable of storing instructions to be executed by a suitable device, and as a result, a computer-readable storage medium having instructions stored therein will comprise a product that includes instructions that can be executed to create means for performing operations specified in a flowchart or block diagram. Examples of computer-readable storage media may include electronic storage media, magnetic storage media, optical storage media, electromagnetic storage media, semiconductor storage media, etc. More specific examples of computer-readable storage media may include floppy disks (registered trademark), diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), electrically erasable programmable read-only memory (EEPROM), static random access memory (SRAM), compact disk read-only memory (CD-ROM), digital versatile disk (DVD), Blu-ray (registered trademark) disk, memory stick, integrated circuit card, etc.

[0101] Computer-readable instructions may include assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk®, Java®, C++, and conventional procedural programming languages ​​such as the C programming language or similar programming languages.

[0102] Computer-readable instructions may be provided locally or via a wide area network (WAN) such as a local area network (LAN) or the internet to a processor or programmable circuit of a general-purpose computer, a special-purpose computer, or another programmable data processing device, so that the processor or programmable circuit of the programmable data processing device, such as a computer, may execute the computer-readable instructions to generate means for performing operations specified in a flowchart or block diagram. Here, the computer may be a PC (personal computer), a tablet computer, a smartphone, a workstation, a server computer, a general-purpose computer, or a special-purpose computer, and may also be a computer system in which multiple computers are connected. Such a computer system in which multiple computers are connected is also called a distributed computing system and is a computer in a broad sense. In a distributed computing system, multiple computers execute a program collectively by each computer executing a part of the program and passing data during program execution between computers as needed.

[0103] Examples of processors include computer processors, central processing units (CPUs), processing units, microprocessors, digital signal processors, controllers, and microcontrollers. A computer may have one or more processors. In a multiprocessor system with multiple processors, each processor executes a portion of the program, and the processors collectively execute the program by passing program execution data between them as needed. For example, in the execution of multitasks, each of the multiple processors may execute a portion of each task in small chunks by switching tasks at each time slice. In this case, which part of a program each processor executes changes dynamically. Which part of a program each of the multiple processors executes may also be statically determined by multiprocessor-aware programming.

[0104] By using the invention according to this embodiment, it is possible to improve the energy efficiency required for monitoring the vehicle 400 and to improve the safety level of the vehicle 400, thereby contributing to the achievement of at least one of the Sustainable Development Goals (SDGs): Goal 7 "Affordable and Clean Energy", Goal 9 "Industry, Innovation and Infrastructure", and Goal 11 "Sustainable Cities and Communities".

[0105] Although the present invention has been described above using embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It will be apparent to those skilled in the art that various modifications or improvements can be made to the above embodiments. It will be clear from the claims that such modified or improved forms may also be included in the technical scope of the present invention.

[0106] It should be noted that the execution order of operations, procedures, steps, and stages in the devices, systems, programs, and methods shown in the claims, specifications, and drawings is not explicitly stated as "before" or "prior to," and that these can be performed in any order unless the output of a previous operation is used in a later operation. Even if the operation flow in the claims, specifications, and drawings is described using phrases such as "first," and "next," for convenience, this does not mean that it is mandatory to perform the operations in that order.

[0107] 10 Information processing system, 30 Person in charge, 50 Network, 100 Information processing device, 110 Video storage unit, 112 Server data receiving unit, 114 Video receiving unit, 116 Judgment unit, 118 Control unit, 120 Server transmission unit, 200 AI processing server, 210 Status data, 220 Vehicle status data, 310 Relay unit, 320 DB, 330 Operation PF server, 340 Operation PF Web, 400 Vehicle, 402 Camera, 410 Video, 500 Management infrastructure, 600 Distributed infrastructure, 700 Wireless base station, 710 RAN, 1200 Computer, 1210 Host controller, 1212 CPU, 1213 GPU, 1214 RAM, 1216 Graphics controller, 1218 Display device, 1220 Input / Output controller, 1222 Communication interface, 1224 Storage device, 1226 DVD drive, 1227 DVD-ROM, 1230 ROM, 1240 Input / output chip

Claims

1. An information processing device comprising: a video receiving unit that receives video footage captured by a camera mounted on a vehicle; a determination unit that determines the status of an AI processing server that performs AI processing to analyze the video and generate vehicle status data representing the status of the vehicle, in response to the video receiving unit receiving the video; and a control unit that, if the status of the AI ​​processing server determined by the determination unit satisfies predetermined conditions, causes the AI ​​processing server to analyze the video, and if the status of the AI ​​processing server does not satisfy the conditions, stores the video in a video storage unit.

2. The information processing apparatus according to claim 1, wherein the determination unit determines the processing load of the AI ​​processing server, and the control unit, when the processing load is lower than a predetermined processing load threshold, causes the AI ​​processing server to analyze the video, and when the processing load is higher than the processing load threshold, stores the video in the video storage unit.

3. The information processing apparatus according to claim 2, wherein the control unit causes the AI ​​processing server to analyze the video stored in the video storage unit in response to a change in the processing load of the AI ​​processing server from a state higher than the processing load threshold to a state lower than the processing load threshold.

4. The information processing apparatus according to claim 2, wherein the AI ​​processing server has a RAN control function for controlling RAN and an AI processing function for performing AI processing, the determination unit determines the processing load of the RAN control function of the AI ​​processing server in response to the video receiving unit receiving the video, the control unit causes the AI ​​processing server to analyze the video if the processing load of the RAN control function is lower than a predetermined processing load threshold, and stores the video in the video storage unit if the processing load of the RAN control function is higher than the processing load threshold.

5. The information processing apparatus according to any one of claims 1 to 4, wherein the control unit causes the AI ​​processing server to analyze the video when the elapsed time from when the vehicle transmits the video until when the video receiving unit receives it is shorter than a predetermined time threshold, and the status of the AI ​​processing server determined by the determination unit satisfies the above conditions.

6. The information processing apparatus according to claim 5, wherein the control unit stores the video in the video storage unit when the elapsed time from when the vehicle transmits the video until when the video receiving unit receives it is shorter than the time threshold and the status of the AI ​​processing server determined by the determination unit does not satisfy the conditions, and the elapsed time is longer than the time threshold.

7. The information processing apparatus according to any one of claims 1 to 4, wherein the control unit, when the video receiving unit receives multiple videos from multiple vehicles, causes the AI ​​processing server to analyze the multiple videos in the order of priority of the multiple vehicles until the processing load of the AI ​​processing server exceeds a predetermined processing load threshold.

8. The information processing apparatus according to claim 7, wherein, when the video receiving unit receives multiple videos from multiple vehicles, the control unit causes the AI ​​processing server to analyze the multiple videos in order of increasing risk based on the attributes of the respective locations of the multiple vehicles until the processing load of the AI ​​processing server exceeds a predetermined processing load threshold.

9. The information processing apparatus according to claim 7, wherein, when the video receiving unit receives multiple videos from multiple vehicles, the control unit causes the AI ​​processing server to analyze the multiple videos in an order of priority based on the attributes of each of the multiple vehicles until the processing load of the AI ​​processing server exceeds a predetermined processing load threshold.

10. The information processing apparatus according to claim 1, wherein the control unit predicts the time required for the AI ​​processing server to analyze the video, and if the analysis time is shorter than a predetermined time threshold, it causes the AI ​​processing server to analyze the video, and if the analysis time is longer than the time threshold, it stores the video in the video storage unit.

11. An information processing method performed by a computer, comprising: a video reception step of receiving a video captured by a camera mounted on a vehicle; a determination step of determining the status of a processing execution unit that performs AI processing to analyze the video and identify the status of the vehicle in response to receiving the video in the video reception step; and a control step of causing the processing execution unit to analyze the video if the status of the processing execution unit determined in the determination step satisfies predetermined conditions, and storing the video in a video storage unit if the status of the processing execution unit does not satisfy the conditions.

12. A program for a computer to execute the following steps: a video reception step of receiving video footage captured by a camera mounted on a vehicle; a determination step of determining the status of a processing execution unit that performs AI processing to analyze the video and identify the status of the vehicle, in response to receiving the video in the video reception step; and a control step of causing the processing execution unit to analyze the video if the status of the processing execution unit determined in the determination step satisfies predetermined conditions, and storing the video in a storage unit if the status of the processing execution unit does not satisfy the conditions.

Images