Notification device, notification system, notification method, and program

Abstract

To enable quick initial response with respect to an analysis target person to be realized.SOLUTION: A notification device (10) according to an embodiment of the present disclosure includes: an accident occurrence detection unit (101) that detects an occurrence of an accident from video captured by one or more cameras; an analysis unit (102) that analyzes the video to derive detailed information about an analysis target person related to the accident; a determination unit (103) that determines a method for coping with the analysis target person based on the detailed information; and a notification unit (104) that notifies a notification target of the determined coping method.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a notification device, a notification system, a notification method, and a non-transitory computer-readable medium. [Background technology]

[0002] Technologies are being considered that can detect the occurrence of an accident and deal with it if an accident occurs.

[0003] For example, Patent Document 1 discloses a recording and analysis system that, if input sound data is from a traffic accident, temporarily records the sound data and video data in a data recording device, and classifies and analyzes the traffic accident based on the recorded data.

[0004] Patent document 2 also discloses a content generation device that, when an emergency call is made from the caller's terminal, selects candidate content to be sent to the caller based on the condition of the patient who is the target of emergency care.

[0005] Furthermore, Patent Document 3 discloses a system that, when a report is received that a specific person has a medical problem, identifies the current location of that specific person and reports the location of that specific person to registered users in the area surrounding the current location. [Prior art documents] [Patent documents]

[0006] [Patent Document 1] International Publication No. 2005 / 101346 [Patent Document 2] JP 2019-101983 A [Patent Document 3] JP2016-096574A Summary of the Invention [Problem to be solved by the invention]

[0007] An object of the present disclosure is to provide a notification device, a notification system, a notification method, and a non-transitory computer-readable medium that are capable of realizing a rapid initial response to a person being analyzed, such as an injured person or a person who suddenly falls ill. [Means for solving the problem]

[0008] A notification device according to one aspect of this embodiment includes an accident detection means for detecting the occurrence of an accident from video footage captured by one or more cameras, an analysis means for analyzing the video footage to derive detailed information about a person being analyzed who is involved in the accident, a decision means for deciding how to deal with the person being analyzed based on the detailed information, and a notification means for notifying the person being notified of the decided way of dealing with the person being notified.

[0009] A notification system according to one embodiment of the present invention includes one or more cameras, a notification device connected to the one or more cameras, and one or more terminals that receive notifications from the notification device. The notification device has an accident detection means for detecting the occurrence of an accident from video footage captured by the one or more cameras, an analysis means for analyzing the video footage and deriving detailed information about a person being analyzed who is involved in the accident, a decision means for deciding how to deal with the person being analyzed based on the detailed information, and a notification means for notifying one or more terminals of the decided way of dealing with the person being analyzed.

[0010] A notification method according to one aspect of this embodiment is one in which a notification device executes the following steps: an accident detection step of detecting the occurrence of an accident from video footage captured by one or more cameras; an analysis step of analyzing the video footage to derive detailed information about a person being analyzed who is involved in the accident; a decision step of deciding how to deal with the person being analyzed based on the detailed information; and a notification step of notifying the person being notified of the decided way of dealing with the person being notified.

[0011] A non-transitory computer-readable medium according to one aspect of this embodiment stores a program that causes a computer to execute an accident detection step of detecting the occurrence of an accident from video footage captured by one or more cameras, an analysis step of analyzing the video footage to derive detailed information about a person being analyzed who is involved in the accident, a decision step of deciding how to deal with the person being analyzed based on the detailed information, and a notification step of notifying a person to be notified of the decided way of dealing with the person to be notified. Effect of the Invention

[0012] According to the present disclosure, it is possible to provide a notification device, a notification system, a notification method, and a non-transitory computer-readable medium that are capable of realizing a rapid initial response to a person being analyzed, such as an injured person or a person who is suddenly ill. [Brief description of the drawings]

[0013] [Figure 1] 1 is a block diagram showing an example of a notification device according to a first embodiment. [Diagram 2] 4 is a flowchart showing an example of a process executed by the notification device according to the first embodiment. [Diagram 3] FIG. 1 is a schematic diagram illustrating an example of a notification system according to a first embodiment. [Figure 4] FIG. 11 is a schematic diagram illustrating an example of a notification system according to a second embodiment. [Diagram 5] FIG. 11 is a block diagram showing an example of a camera according to a second embodiment. [Figure 6] FIG. 11 is a schematic diagram showing an example of a road on which a camera according to a second embodiment is installed. [Figure 7] FIG. 11 is a block diagram showing an example of an MEC server according to the second embodiment. [Figure 8] FIG. 11 is a block diagram showing an example of a notification server according to the second embodiment. [Figure 9] FIG. 11 is a block diagram showing an example of a terminal according to a second embodiment. [Figure 10]FIG. 11 is a sequence diagram showing an example of a representative process of the notification system according to the second embodiment. [Figure 11] 13 is a flowchart illustrating an example of a process executed by a notification server according to the second embodiment. [Figure 12] FIG. 11 is a schematic diagram showing an example of a road on which a camera according to a second embodiment is installed. [Figure 13] FIG. 11 is a schematic diagram illustrating an example of a notification system according to a third embodiment. [Figure 14] FIG. 13 is a block diagram showing an example of a notification server according to a third embodiment. [Figure 15] FIG. 11 is a block diagram showing an example of a terminal according to a third embodiment. [Figure 16] FIG. 13 is a schematic diagram illustrating an example of a notification system according to a fourth embodiment. [Figure 17] FIG. 13 is a block diagram showing an example of a notification server according to a fourth embodiment. [Figure 18] FIG. 13 is a block diagram showing an example of a terminal according to a fourth embodiment. [Figure 19] FIG. 13 is a schematic diagram showing an example of the configuration of a cell of a base station according to a fifth embodiment. [Figure 20] FIG. 2 is a block diagram showing an example of a hardware configuration of an apparatus according to each embodiment. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0014] First embodiment (1A) Hereinafter, a first embodiment of the present disclosure will be described with reference to the drawings. In this embodiment (1A), a notification device that detects the occurrence of an accident and notifies a notification target will be described.

[0015] 1 is a block diagram showing an example of a notification device. The notification device 10 includes an accident occurrence detection unit 101, an analysis unit 102, a decision unit 103, and a notification unit 104. Each unit (each means) of the notification device 10 is controlled by a control unit (controller) not shown. Each component will be described below.

[0016] The accident occurrence detection unit 101 detects the occurrence of an accident from images captured by one or more cameras. In this disclosure, an "accident" refers to an incident in which an injured person or a person suddenly falls ill, whether it is accidental or intentional, and includes, but is not limited to, an accident between a car and a person, an accident between people, an accident between cars, a sudden worsening of a medical condition, and the like. When the accident occurrence detection unit 101 detects an accident, it may determine the type of accident, such as a collision accident, a fire, or a worsening of a chronic illness. Furthermore, the "image" may be either video or still image data.

[0017] One or more cameras may be installed at any location. When multiple cameras are installed, for example, multiple cameras may capture a certain location from different directions, or multiple cameras may capture different locations. The accident occurrence detection unit 101 detects that an accident has occurred at one or more locations by analyzing images captured by one or more cameras. The cameras may be any combination of one or more types of cameras, such as visible light cameras, infrared cameras, and thermal cameras. The accident occurrence detection unit 101 may identify the location of the accident site based on at least one of the location of the camera that is determined to have captured the accident and the range in the video data where the accident occurred.

[0018] When the accident occurrence detection unit 101 detects the occurrence of an accident, the analysis unit 102 derives detailed information of the injured or suddenly ill person (hereinafter, the analysis target person) caused by the accident by analyzing the video in which the accident occurrence is detected. The analysis unit 102 may analyze a video including the location of the accident site in the shooting range instead of or in addition to the video in which the accident occurrence is detected, and derive detailed information of the analysis target person. The analysis unit 102 derives this detailed information based on the video data of the camera during the period from around the timing when the accident occurrence detection unit 101 detects the occurrence of the accident to the time when the analysis process is performed, or based on the video captured by the camera at one or more timings. The detailed information indicates, for example, at least one of information on the physical condition of the analysis target person and personal information of the analysis target person of the accident, but is not limited thereto.

[0019] The information on the physical condition of the person to be analyzed includes, for example, at least one of the consciousness state, breathing state, bleeding state, fracture state, burn state, site of a strong blow, convulsion state, walking state, heartbeat state, pulse state, and body temperature state of the person to be analyzed. Specifically, the consciousness state may indicate at least one of the presence or absence of consciousness and the degree of cloudiness, the breathing state may indicate at least one of the presence or absence of breathing and the normality level, the bleeding state may indicate at least one of the presence or absence, location, and degree of bleeding, and the fracture state may indicate at least one of the presence or absence, location, and degree of fracture. In addition, the burn state may indicate at least one of the presence or absence, location, and degree of a burn, the site of a strong blow may indicate at least one of the site of a strong blow and the degree of the blow, the convulsion state may indicate at least one of the presence or absence and degree of convulsion, the walking state may indicate at least one of the degree of unsteadiness and normality of walking, the heartbeat state may indicate at least one of the presence or absence, number of heartbeats, and normality level, and the pulse state may indicate at least one of the presence or absence, number of heartbeats, and normality level. The body temperature state may also indicate at least one of the presence or absence of fever, temperature, and location.

[0020] The analysis unit 102 may directly or indirectly derive this detailed information based on the video of the person being analyzed. For example, the analysis unit 102 can derive the detailed information by directly determining the bleeding state from the appearance of the bleeding of the person being analyzed in the video. In another example, even if there is no sign of trauma to the person being analyzed, if the person being analyzed is dragging his / her leg and has an expression of pain on his / her face, the analysis unit 102 can indirectly estimate that the person being analyzed has a fractured or bruised leg and derive the detailed information.

[0021] Furthermore, the analysis unit 102 may derive this detailed information not only from the video of the person being analyzed, but also from other video showing the state of the accident. For example, when the camera that filmed the person being analyzed or a different camera captures the state of objects scattered as a result of an explosion, the analysis unit 102 can analyze the state of the accident to determine that the person being analyzed was hit by the blast or an object blown by the blast, and estimate that the person being analyzed has suffered at least one of the following injuries: bleeding, fractures, and bruises.

[0022] Furthermore, the analysis unit 102 may derive this detailed information by further using other information, such as information on the type of accident determined by the accident occurrence detection unit 101 and pre-registered attributes of the area where the camera that captured the accident is installed. For example, when the accident occurrence detection unit 101 determines that the accident is a fire, the analysis unit 102 can determine that the person being analyzed has been burned by taking that information into consideration in analyzing the video.

[0023] Furthermore, the analysis unit 102 may control the camera that captures the video in order to derive accurate detailed information. For example, in order to increase the spatial or temporal imaging resolution, the camera may be controlled to increase the imaging magnification, the resolution, the frame rate, the quantization bit rate, the bit rate, or the like. This allows the camera to capture the state of the person being analyzed more clearly. Also, the camera angle may be controlled so that the person being analyzed or a specific part of the person being analyzed is included in the imaging range.

[0024] Another example of the detailed information may be personal information of a person to be analyzed who caused the accident. The analysis unit 102 may identify the person to be analyzed from among the registered persons based on the result of face recognition using the face image of the person to be analyzed that appears in the video where the accident occurred and the face information of the registered persons, and derive personal information associated with the registered persons as detailed information. The personal information may include, but is not limited to, at least one of medical history, current medical history, pregnancy status, age, sex, blood type, allergy information, personal number, family medical institution, and emergency contact information.

[0025] In the above process, the analysis unit 102 may perform face authentication using a face image of the person to be analyzed and face information of the registrant. Alternatively, the analysis unit 102 may identify the person to be analyzed from among the registrants by acquiring the authentication result of face authentication performed by another device other than the notification device 10. Here, the analysis unit 102 may acquire the personal information stored in another device together with the authentication result, or may acquire the personal information by the analysis unit 102 identifying the personal information from the personal information stored in the storage unit of the notification device 10 based on the authentication result. Note that using a face for authentication is just one example, and other biometric authentication techniques may be used. For example, the analysis unit 102 may perform authentication using the iris, which is a type of physical characteristic, or may perform authentication using gait, which is a type of behavioral characteristic, or may perform authentication using any combination of two or more biometric authentication techniques.

[0026] The determination unit 103 determines how to deal with the person to be analyzed who is shown in the video based on the detailed information derived by the analysis unit 102. The method of dealing with the person to be analyzed includes at least one of first aid, procedure, and other actions for the injury or illness of the person to be analyzed. In this disclosure, "treatment" refers to a concept including life-saving treatment and first aid for the person to be analyzed that can be performed by ordinary people, and "treatment" refers to medical treatment for the person to be analyzed that can be performed by specialists such as doctors and emergency personnel. "Treatment" and "treatment" for a specific injury or illness may be completely different responses, or at least some of the contents of both may overlap. In addition, "other actions" include at least one of a request for an ambulance, a request to dispatch staff to the place where the accident occurred (the accident scene), a request to accept the person to be analyzed, preparation for treatment, and contacting a specified contact point, but are not limited to these. Here, "preparation for treatment" includes, but is not limited to, at least one of preparation for blood transfusion, preparation of necessary medical equipment, and securing medical staff and treatment locations (e.g., hospital rooms, operating rooms, examination rooms, etc.). Furthermore, "prescribed contact points" includes, but is not limited to, at least one of contact points of relatives such as family members, friends, workplaces and related parties, specific medical institutions or care facilities, medical staff, and care staff. The determination unit 103 can determine a countermeasure that is considered appropriate based on the detailed information of the person to be analyzed obtained by the analysis unit 102.

[0027] In addition, when the analysis unit 102 acquires the above-mentioned personal information as detailed information, the determination unit 103 may determine a method of dealing with the person to be analyzed based on the personal information. For example, the determination unit 103 may determine at least one of treatment, procedure, or other action as a method of dealing with the person to be analyzed based on at least one of the medical history, current medical history, pregnancy status, age, sex, blood type, and allergy information of the person to be analyzed.

[0028] For example, when the analysis unit 102 analyzes the pulse condition of the person to be analyzed and acquires the detailed information, and acquires "heart disease" as the personal information of the person as a current medical history, the determination unit 103 judges that the person to be analyzed needs a countermeasure against an attack of heart disease. Then, the determination unit 103 determines to request an ambulance, to request a medical institution (particularly a medical institution specializing in heart disease) to accept the person to be analyzed, and to specify an AED (Automated External Defibrillator) for heart disease as a medical device to be used for treatment or treatment. Furthermore, the determination unit 103 may determine the countermeasure in consideration of the location information of the accident occurrence. For example, the determination unit 103 may compare the location information of the accident occurrence with the location information of the place where the AED is placed, and then identify the location of the AED in the vicinity of the accident scene and include it as a countermeasure. As another example, the determination unit 103 may determine that the countermeasure is to contact a predetermined contact such as a family medical institution or an emergency contact.

[0029] There may be one or more notification targets as described below, and the handling method includes at least one content for each notification destination. The handling method for each notification destination may include one of treatment, treatment, and other actions, or may include a combination of them. The handling method determined by the determination unit 103 may be the same regardless of the notification destination, or may be different depending on the attributes of the notification destination. Details of this will be described in the second embodiment.

[0030] The notification unit 104 notifies one or more notification targets of the countermeasures determined by the determination unit 103. The notification targets may be notification destinations stored in advance in the notification device 10. The pre-stored notification destinations may be, for example, public or private emergency services and medical institutions (health facilities), but are not limited thereto. The notification unit 104 may notify each analysis target person to the same notification destination, or may select a notification target from among multiple registered destinations based on at least one of the detailed information derived by the analysis unit 102 and the countermeasures determined by the determination unit 103. For example, when the determination unit 103 determines that the analysis target person needs a countermeasure for a heart attack, the notification unit 104 can set at least one of emergency services and medical institutions (particularly medical institutions specializing in heart disease) as the notification targets, as the pre-stored notification destinations. Furthermore, when the analysis target person is a registered person registered in advance, the notification unit 104 may determine the notification target based on personal information associated with the registered person. For example, the notification unit 104 may set a family medical institution or an emergency contact included in the personal information as the notification target. The notification unit 104 can determine such notification targets instead of or in addition to the notification destinations stored in advance.

[0031] The notification unit 104 may also notify the notification target in the surrounding area (first area) including the accident scene of a method of handling the accident. The notification target in the first area may be, for example, a medical professional, a non-medical professional, or a medical institution. Details of this will be described later in the second embodiment.

[0032] The notification unit 104 may notify the location information of the accident site identified by the accident occurrence detection unit 101 (i.e., location information of the person to be analyzed) together with the countermeasure. The notification executed by the notification unit 104 may take any form. For example, the notification unit 104 may notify an application of the terminal to be notified, or may notify by a message such as SMS (Short Message Service) or MMS (Multimedia Messaging Service), e-mail, or telephone call.

[0033] In addition, at least one of the accident occurrence detection unit 101, the analysis unit 102, and the decision unit 103 may use a machine-learned accident detection model to detect the occurrence of an accident, derive detailed information (e.g., information regarding the physical condition of the person being analyzed), and decide on a countermeasure.

[0034] For example, the accident occurrence detection unit 101 may detect the occurrence of an accident by inputting a video taken by one or more cameras into an accident detection model that has been machine-learned so that a video is input as input data and a determination result of the occurrence of an accident is generated as output data. The analysis unit 102 may derive detailed information by inputting a video taken by one or more cameras into an analysis model of detailed information that has been machine-learned so that a video is input as input data and detailed information is generated as output data. The determination unit 103 may derive a countermeasure by inputting the detailed information derived by the analysis unit 102 into a model of a countermeasure that has been machine-learned so that detailed information is input as input data and a countermeasure is generated as output data. The detection model shown above may be provided inside or outside the notification device 10. Furthermore, a separate model may be provided for each process of the accident occurrence detection unit 101, the analysis unit 102, and the determination unit 103, or one model may be used for multiple processes (for example, the processes of the accident occurrence detection unit 101 and the analysis unit 102). However, the accident occurrence detection unit 101, the analysis unit 102, and the determination unit 103 may execute each process by a method other than the above. For example, a table that associates detailed information with countermeasures may be prepared, and after the analysis unit 102 derives the detailed information, the determination unit 103 may refer to the table to determine a countermeasure suitable for the detailed information.

[0035] 2 is a flowchart showing an example of a typical process of the notification device 10, and the process of the notification device 10 will be explained with reference to this flowchart. Details of the processes executed by each unit below are as described above. First, the accident occurrence detection unit 101 detects the occurrence of an accident from video captured by one or more cameras (step S11; accident occurrence detection step). The analysis unit 102 analyzes the video and derives detailed information of a person to be analyzed who is involved in the accident detected by the accident occurrence detection unit 101 (step S12; analysis step).

[0036] The determination unit 13 determines a method of dealing with the person to be analyzed based on the detailed information derived by the analysis unit 102 (step S13; determination step). The notification unit 104 notifies the notification target of the method of dealing determined in step S12 (step S14; notification step). The notification device 10 can operate as described above.

[0037] In this way, when an accident occurs, the notification device 10 can analyze the person being analyzed, determine a method of response, and notify the person, thereby enabling a rapid initial response to the person being analyzed.

[0038] The notification device 10 may have a centralized configuration including a single computer, or may have a distributed configuration in which a plurality of computers share and execute the processes of the accident occurrence detection unit 101 to the notification unit 104. In the distributed configuration, the plurality of devices may be connected via a communication network such as a LAN (Local Area Network), a WAN (Wide Area Network), or the Internet. This example will be described later in the second embodiment.

[0039] (1B) Next, in (1B), a notification system including a notification device 10 will be described.

[0040] 3 is a block diagram showing an example of a notification system. The notification system S1 includes a notification device 10, cameras 11A and 11B, and terminals 12A and 12B. The description of the notification device 10 is the same as that shown in (1A), and therefore will not be repeated.

[0041] Cameras 11A and 11B (hereinafter collectively referred to as camera 11) capture images of any location and transmit the captured image data to notification device 10. In FIG. 3, camera 11 transmits image data via a wired line, but it may transmit image data via a wireless line. Camera 11 and notification device 10 may be directly connected or may be connected via a communication network or the like. Accident occurrence detection unit 101 detects the occurrence of an accident from the image captured by camera 11. Details of this are as shown in (1A). Analysis unit 102, decision unit 103, and notification unit 104 also execute the process shown in (1A). The notification output destination of notification unit 104 is terminals 12A and 12B.

[0042] Terminals 12A and 12B (hereinafter collectively referred to as terminals 12) receive the countermeasure from notification unit 104 of notification device 10. In Fig. 3, the countermeasure is received via wireless lines RA and RB, but the countermeasure may be transmitted via a wired line. Terminal 12 may be any information terminal capable of communication, such as a mobile phone such as a smartphone, a personal computer, a personal digital assistant, a car navigation system, or an in-vehicle communication terminal.

[0043] Although two cameras 11 and two terminals 12 are provided in (1B), three or more of each may be provided, or only one may be provided.

[0044] Moreover, the camera 11 is installed at least one of a traffic light, a roadside device, an intersection, and a railroad crossing, as an example, and can photograph the location. The traffic light may be for vehicles such as automobiles, motorcycles, and bicycles, pedestrians, and railways. The intersection means a location where two or more roads intersect. This "road" may be a road for automobiles, or a road for bicycles or pedestrians. Since these locations are locations where accidents involving automobiles, railways, etc. are expected to occur, even if an accident occurs, the camera 11 can photograph the accident and transmit the video data to the notification device 10, so that the notification device 10 can notify how to deal with the injured in the accident. Therefore, it is possible to realize a rapid response to the injured in the accident.

[0045] However, the camera 11 may be installed in any other outdoor location (for example, a location other than the above-mentioned along a road or a railroad, or an airport or a location nearby), or in any indoor location. In this way, by installing the camera 11 in a location where an accident is likely to occur or where there is some other danger, it is possible to realize a prompt response to injuries in an accident.

[0046] Embodiment 2 (2A) Hereinafter, a second embodiment of the present disclosure will be described with reference to the drawings. In this (2A), a specific example of the above-mentioned first embodiment (1B) will be described.

[0047] 4 is a schematic diagram showing an example of a notification system. The notification system S2 includes cameras 20A to 20N, a MEC (Mobile Edge Computing or Multi-access Edge Computing) server 21, a notification server 22, and terminals 23A to 23D. The cameras 20A to 20N and terminals 23A to 23D are collectively referred to as the camera 20 and the terminal 23, respectively. The camera 20 and the MEC server 21 may be connected by a wired line, or may be connected by a wireless line such as LTE (Long Term Evolution), 5G (5th Generation), or wireless LAN, or may be connected by a combination of a wired line and a wireless line. Similarly, the MEC server 21 and the notification server 22 may be connected by a wired line, or may be connected by a wireless line such as LTE, 5G, or wireless LAN, or may be connected by a combination of a wired line and a wireless line. The MEC server 21 and the notification server 22 are configured such that a plurality of computers share and execute the processes of the accident occurrence detection unit 101 to the notification unit 104. The notification server 22 and the terminal 23 receive notifications via wireless lines RA to RD such as LTE, 5G, and wireless LAN, but are not limited to this and may receive notifications via wired lines, or may receive notifications via both wired and wireless lines. Each unit of each device is controlled by a control unit (controller) in the device (not shown) reading a program. The configuration and processing of each device will be described below.

[0048] 5 is a block diagram showing an example of camera 20. Camera 20 corresponds to camera 11 in (1B), and includes an imaging unit 201, a transmitting / receiving unit (transceiver) 202, and a storage unit 203. Each component of camera 20 will be described below.

[0049] The photographing unit 201 includes a lens, an image sensor, etc. as a hardware configuration, and photographs video. However, the images photographed and transmitted by the camera 20 may be still images photographed at a predetermined interval. The photographing unit 201 may have a function of controlling one or more of the photographing magnification, resolution, frame rate, quantization bit number, bit rate, and camera angle. The video data may also include time information at the time of photographing. The transmitting / receiving unit 202 transmits the video data to the MEC server 21 together with identification information of the camera 20 (for example, information such as the ID of the camera itself and location information). The ID of the camera itself may be an arbitrary character string or number sequence assigned to each camera without duplication, or may be communication address information such as an IP (Internet Protocol) address. The storage unit 203 stores identification information for transmission by the transmitting / receiving unit 202. The identification information may be appropriately changed according to the movement of the camera 20, etc.

[0050] FIG. 6 is a schematic diagram showing an example of a road on which the cameras 20 are installed. In this example, the cameras 20A and 20B are installed at a traffic light at the intersection C1, the cameras 20C and 20D are installed at a traffic light at the intersection C2, and the cameras 20E and 20F are installed at a traffic light at the intersection C3. For example, the cameras 20A and 20B are installed at traffic lights at different positions at the same intersection C1. Therefore, the cameras 20A and 20B transmit video data of the intersection C1 taken from different positions and angles to the MEC server 21. Specifically, the camera 20A includes the intersection C1 and the periphery of the camera 20B in its shooting range, while the camera 20B includes the intersection C1 and the periphery of the camera 20A in its shooting range. For the same reason, the cameras 20C and 20D transmit video data of the intersection C2 taken from different positions and angles to the MEC server 21, and the cameras 20E and 20F transmit video data of the intersection C3 taken from different positions and angles to the MEC server 21. Furthermore, since the intersection C2 is adjacent to the intersection C1, the intersection C2 is included in an area R1 (described below) that includes the intersection C1.

[0051] In the example of FIG. 6, an accident TR occurs at intersection C1. Therefore, cameras 20A and 20B transmit video data capturing the accident TR to the MEC server 21. Furthermore, camera 20A captures medical personnel NA when the accident occurs, and camera 20B captures non-medical personnel NB when the accident occurs. Furthermore, cameras 20C and 20D capture vehicle NC, which is a car owned by hospital C, when the accident occurs. Furthermore, medical personnel NE, non-medical personnel NF, and vehicle NG, which is a car owned by non-medical personnel G, are present around intersection C3. When the accident occurs, cameras 20E and 20F capture medical personnel NE and non-medical personnel NF, and camera 20E captures vehicle NG.

[0052] 7 is a block diagram showing an example of the MEC server 21. The MEC server 21 corresponds to a part of the notification device 10 of (1B), and in this example, includes an accident occurrence detection unit 211, a transmission / reception unit (transceiver) 212, and a storage unit 213. Each component of the MEC server 21 will be described below.

[0053] The accident occurrence detection unit 211 corresponds to the accident occurrence detection unit 101 of (1A) and detects the occurrence of an accident from the video data transmitted from each of the cameras 20A to 20N. The accident occurrence detection unit 211 detects that an accident has occurred at a certain time t in the shooting area of ​​the cameras 20A and 20B, i.e., the intersection C1, by analyzing the video captured by the cameras 20A to 20N. Here, the accident occurrence detection unit 211 specifies the position of the accident site based on the positions of the cameras 20A and 20B that are determined to have captured the occurrence of the accident and the range in the video data where the accident occurred. The accident occurrence detection unit 211 may specify the positions of the cameras 20A and 20B by referring to the position information of the cameras 20A and 20B stored in the storage unit 213 described later based on the IDs of the cameras transmitted by the cameras 20A and 20B. When the cameras 20A and 20B transmit the position information of their own cameras, the accident occurrence detection unit 211 can use the position information as it is.

[0054] The accident occurrence detection unit 211 receives video as input data, and uses a machine-learned accident detection model to generate a determination result of whether or not an accident has occurred as output data, and inputs the video data captured by each of the cameras 20A to 20N to the detection model. In this way, the accident occurrence detection unit 211 detects whether or not an accident has occurred in each piece of video data. Other processes executed by the accident occurrence detection unit 211 are similar to those executed by the accident occurrence detection unit 101, and therefore will not be described.

[0055] The transmitting / receiving unit 212 receives the captured video data and identification information from each of the cameras 20A to 20N. When the accident occurrence detection unit 211 detects an accident in the video data of a certain camera 20, the accident occurrence detection unit 211 extracts the video data captured by the camera 20 from time t1 around the time t when the accident was detected to the present (the time when the accident occurrence detection unit 211 executes this process). The transmitting / receiving unit 212 transmits the extracted video data together with the position information of the accident site to the notification server 22. In this example, the transmitting / receiving unit 212 transmits to the notification server 22 the video data captured by the cameras 20A and 20B from the time t1 when the accident was detected to the present, together with the position information of the intersection C. Note that the identification information of the camera 20 that captured the accident may be transmitted as the position information of the accident site.

[0056] Further, the accident occurrence detection unit 211 determines an area R1 (see FIG. 6) including the intersection C, which is the accident site, as a first area including the accident site. Then, the accident occurrence detection unit 211 specifies the camera 20 that captures the area R1 based on the information of the capture location of the camera 20 stored in the storage unit 213. As shown in FIG. 6, the cameras 20 that capture the area R1 are the cameras 20A and 20B installed at the intersection C1 and the cameras 20C and 20D installed near the intersection C1. Therefore, the accident occurrence detection unit 211 determines that not only the video data captured by the cameras 20A and 20B but also the video data captured by the cameras 20C and 20D are necessary for the notification server 22 to detect a notification target, which will be described later. The accident occurrence detection unit 211 also extracts the video data of the cameras 20C and 20D from time t2 to the present, and the transmission / reception unit 212 transmits the video data to the notification server 22. However, since the area around intersection C3 is not included in area R1, the video data captured by cameras 20E and 20F is not transmitted to notification server 22. Therefore, in this case, medical personnel NE, non-medical personnel NF, and vehicles NG are not considered as notification targets.

[0057] The "first area" can be set to any range. For example, the "first area" may be a circular area with a radius of a predetermined distance from the accident site, an area located within a predetermined time from the accident site at a predetermined walking speed or vehicle speed, or a predetermined section including the accident site. Examples of the predetermined section include, but are not limited to, sections for emergency services and administrative sections such as prefectures, cities, towns, villages, wards, and states. The accident occurrence detection unit 211 can set the above-mentioned first area using, for example, the position information of the detected accident site, map information around the accident site stored in the storage unit 213, and a setting criterion for the first area.

[0058] Furthermore, times t1 and t2 may be the same as time t, or may be a predetermined period of time before time t so that the details of the accident are reliably clarified in the notification server 22. The predetermined period of time may be, for example, several seconds to several minutes. Alternatively, a predetermined criterion for determining times t1 and t2 may be set. For example, a possible criterion may be that time t1 is the time when an injured person in the accident is first shown in the video data. The accident occurrence detection unit 211 determines times t1 and t2 using the predetermined period or criterion of timing stored in the storage unit 213, and extracts the video data as described above.

[0059] The storage unit 213 stores information required for the processes executed by the accident occurrence detection unit 211 and the transmission / reception unit 212. Specifically, the following information can be stored: (i) Detection model, map information, and setting criteria for the first area used by the accident occurrence detection unit 211 (ii) Location information of each camera 20 associated with the ID of the camera 20 (iii) Video data captured by the cameras 20A to 20N during a predetermined period of time that is to be detected by the accident occurrence detection unit 211 (iv) Values ​​of the timings t1 and t2 for extracting video data or a criterion for setting the timings

[0060] 8 is a block diagram showing an example of the notification server 22. The notification server 22 corresponds to a part of the notification device 10 of (1B), and includes a notification target detection unit 221, an analysis unit 222, a decision unit 223, a transmission / reception unit (transceiver) 224, and a storage unit 225. Each component of the notification server 22 will be described below.

[0061] The notification target detection unit 221 detects a notification target present in a first area (detection area) including the accident site. Here, the notification target includes at least one of a predetermined organization, an individual, and a vehicle. The predetermined organization that is a candidate for the notification target is, for example, an organization related to medical care or emergency care, which includes medical institutions such as hospitals and clinics, whether public or private, and emergency organizations that dispatch specialized staff such as emergency personnel. Emergency organizations include, for example, fire departments and EMS (Emergency Medical Services), but are not limited to these. Furthermore, the predetermined organization that is a candidate for the notification target may include police stations in charge of accident processing and companies that respond to accidents on roads, railways, etc. (for example, road service companies).

[0062] Furthermore, the specific individuals who are candidates for notification may include at least one of medical personnel such as doctors, nurses, and emergency medical technicians, and non-medical personnel (particularly ordinary people). They may also include people whose job it is to travel to the scene of an accident, such as firefighters, police officers, and company staff who respond to accidents. The specific vehicles that are candidates for notification are, for example, vehicles owned (possessed or temporarily occupied) by the above-mentioned specific institutions or individuals. Examples include ambulances and cars owned by hospitals.

[0063] Information indicating each institution, each individual, and each vehicle that is a candidate for notification is stored in advance in the storage unit 225 together with terminal information of each institution, each individual, and each vehicle to which the notification is actually sent by the transmitting / receiving unit 224. This terminal is a terminal associated with each institution, each individual, and each vehicle (for example, a terminal owned or temporarily occupied by an institution, etc.), and this terminal information can be updated as appropriate by each institution or individual, or even by an administrator.

[0064] However, the notification target detection unit 221 can select as notification targets even predetermined institutions, individuals, and vehicles that are not in the first area including the accident site. When the analysis unit 222 described below acquires information such as a family medical institution and an emergency contact as personal information, the notification target detection unit 221 can add the contact information as notification targets regardless of the location of the family medical institution and the emergency contact.

[0065] Furthermore, for emergency medical institutions, which are a type of predetermined institution, emergency medical institutions that are candidates for notification targets may be stored in the storage unit 225. Based on at least one of the location information of the accident site received from the MEC server 21 and the detailed information acquired by the analysis unit 222, the notification target detection unit 221 may identify one or more emergency medical institutions according to the situation of the accident, regardless of whether they are in the first area including the accident site, and select them as notification targets. The detailed information used to identify the emergency medical institution may be, for example, at least one of personal information such as information on the physical condition of the person to be analyzed (e.g., information on the type or degree of injury or illness), medical history, current medical history, and whether or not pregnant, which is acquired by the analysis unit 222 through analysis of the video data. However, the notification target detection unit 221 may select one or more predetermined institutions that are registered in advance as notification targets as emergency response institutions regardless of the situation, as notification targets.

[0066] There are various possible methods for the notification target detection unit 221 to detect the notification target, and (2A) shows one example. The notification target detection unit 221 analyzes the video data captured by each of the cameras 20A to 20D and received from the MEC server 21, and detects whether or not a candidate for the notification target is captured in the video data.

[0067] Here, storage unit 225 stores specific information for identifying a specific individual or vehicle, so that notification target detection unit 221 can detect a notification target using video data. The specific information is biometric information such as face information for each individual, and is information capable of identifying a vehicle such as a license plate number or video data for each vehicle. Notification target detection unit 221 compares this specific information with the video data captured by cameras 20A-20D to determine whether or not a candidate notification target is captured in each video data within the first area.

[0068] In this example, the notification target detection unit 221 determines that the video data captured by the cameras 20A and 20B captures medical personnel NA and non-medical personnel NB, who are candidates for notification targets. Furthermore, the notification target detection unit 221 detects that the license plate of a vehicle NC, which is a candidate for the notification target, is captured in the video data captured by the cameras 20C and 20D. As a result, the notification target detection unit 221 detects medical personnel NA, non-medical personnel NB, and the vehicle NC owned by hospital C as notification targets present in the first area including the accident scene. These notification targets are notified of the response method.

[0069] The analysis unit 222 corresponds to the analysis unit 102 according to the first embodiment, and derives detailed information of the person to be analyzed who is involved in the accident and is captured in the video data related to the cameras 20A and 20B. Specifically, the analysis unit 222 performs face recognition using the face image of the person to be analyzed captured in the video data and the face information of the registrant stored in the storage unit 225 in advance, thereby identifying the person to be analyzed from among the registrants, and acquiring the personal information of the registrant stored in the storage unit 225 as detailed information. The registrant is a person who has registered his / her personal information in advance, a person who has a chronic illness, or a person who is stored in advance as some important person. Furthermore, the analysis unit 222 acquires information on the physical condition of the person to be analyzed as detailed information by analyzing the video data related to the cameras 20A and 20B. The analysis unit 222 can acquire at least one of the personal information and the information on the physical condition of the person to be analyzed as detailed information. Details of the personal information and the information on the physical condition of the person to be analyzed, and details of other processes executed by the analysis unit 222 are as described in the first embodiment, and therefore will not be described again.

[0070] In this example, the analysis unit 222 acquires, as personal information, information that the person being analyzed has heart disease in his / her current medical history, and contact information for Hospital D, which is his / her regular medical institution. Furthermore, it acquires, as the physical condition of the person being analyzed, that there are abnormalities in his / her respiratory condition and pulse condition.

[0071] In response to the analysis unit 222 acquiring the contact information of Hospital D as personal information, the notification target detection unit 221 adds Hospital D as a notification target. This Hospital D does not need to be located in the first area that includes the accident site.

[0072] The determination unit 223 corresponds to the determination unit 103 according to the first embodiment, and determines a method of dealing with the person to be analyzed. In this example, the determination unit 223 can determine separate methods of dealing with the case where the notification target is a medical personnel NA and a vehicle NC (medical personnel or their vehicle), the case where the notification target is a non-medical personnel NB (general public), and the case where the notification target is a hospital D (medical institution).

[0073] When the notification target is a medical personnel NA and a vehicle NC, the determination unit 223 determines the treatment for the person to be analyzed, and further specifies the location of the medical equipment used in the treatment, which is present in a predetermined area (third area) including the accident site. In this example, the determination unit 223 determines artificial respiration, chest compression (cardiac massage), use of an AED, and treatment that can be performed by a medical personnel, as the treatment for the person to be analyzed. In addition, the determination unit 223 specifies an AED as the medical equipment to be used in the treatment, and specifies the location of the AED present in the predetermined area including the accident site by referring to a list of location information of AEDs stored in the storage unit 225 and the location information of the accident site. The determination unit 223 includes the information on this treatment and the information on the location of the AED present in the predetermined area in the handling method for the medical personnel NA and the vehicle NC as the notification target. Note that the predetermined area (third area) including the accident site where the medical equipment is present may be the same area as the first area, or may be a different area. The setting criteria for this area are stored in the storage unit 225.

[0074] When the notification target is a non-medical personnel NB, the determination unit 223 determines the medical treatment to be given to the person being analyzed, and identifies the location of the medical equipment to be used in the treatment, which is present in a predetermined area including the accident scene. In this example, the determination unit 223 determines the use of artificial respiration, chest compression, and an AED as the medical treatment to be given to the person being analyzed. Furthermore, as described above, the determination unit 223 identifies the location of the AED present in a predetermined area (third area) including the accident scene. The determination unit 223 includes the information on the medical treatment and the information on the location of the AED present in the predetermined area in the response method.

[0075] However, the determination unit 223 may include only one of the two pieces of information, that is, the information on the treatment or care and the information on the location of an AED present in a predetermined area, in the response method.

[0076] When the notification target is hospital D, the determination unit 223 determines the countermeasure so as to include measures for the person to be analyzed and a request to accept the person to be analyzed. The measures are the same as those when the notification target is medical personnel NA and vehicle NC. However, the countermeasure is not limited to this example, and the determination unit 223 may determine the countermeasure so as to include at least one of measures for the person to be analyzed, a request to dispatch staff to the accident site, and a request to accept the person to be analyzed. Note that details of other processes executed by the determination unit 223 are as described in embodiment 1, and therefore will not be described here.

[0077] The transmitting / receiving unit 224 corresponds to the notifying unit 104 according to the first embodiment, and notifies the notification target detected by the notification target detecting unit 221 of the handling method determined by the determining unit 223. In this example, the transmitting / receiving unit 224 notifies the terminals 23A and 23C of the handling method including the information on the treatment and the location of the AED present in the predetermined area. The transmitting / receiving unit 224 also notifies the terminal 23B of the handling method including the information on the treatment and the location of the AED present in the predetermined area. Furthermore, the transmitting / receiving unit 224 notifies the terminal 23D of the handling method including the treatment for the person to be analyzed and the request to accept the person to be analyzed. Here, the terminals 23A and 23B are smartphones owned by the medical personnel NA and the non-medical personnel NB, respectively, the terminal 23C is a car navigation system installed in the vehicle NC, and the terminal 23D is a terminal for accepting emergency patients provided in the hospital D. The contact information of terminals 23A, 23B, 23C is associated with medical personnel NA, non-medical personnel NB, and vehicle NC, respectively, and is stored in the memory unit 225 as information on candidates for notification targets, and the transmission / reception unit 224 uses this information for transmission. Also, as described above, the contact information of terminal 23D is included in the personal information acquired by the analysis unit 222, and the transmission / reception unit 224 uses this information for transmission. Note that "contact information" refers to information that includes at least one of the communication address information (e.g., IP address), telephone number, email address, and any other user identifier of each terminal.

[0078] The transmitting / receiving unit 224 transmits the countermeasures to the terminals 23A, 23B, and 23D via the wireless circuits RA, RB, and RD, respectively. The transmitting / receiving unit 224 also transmits the countermeasures to a roadside unit (not shown) in the vicinity of the terminal 23C, which in turn transmits the countermeasures to the terminal 23C via the wireless circuit RC. In this manner, the notification server 22 can transmit the countermeasures to the terminal mounted on the vehicle via the roadside unit. The transmitting / receiving unit 224 may also notify each of the notification target terminals 23 of the location information of the accident site received by the notification server 22 (i.e., location information of the person to be analyzed) together with the countermeasures.

[0079] The storage unit 225 stores information required for the processes executed by the notification target detection unit 221 through the transmission / reception unit 224. Specifically, the following information can be stored. (i) Information on specified institutions, individuals, and vehicles that are candidates for notification, and terminal information on institutions, individuals, and vehicles to which notifications associated with each of the information will be sent (ii) Identification information for identifying a specific individual or vehicle, so that the notification target detection unit 221 can detect a notification target using video data. (iii) facial information of the registrant for the analysis unit 222 to perform face authentication (iv) A list of the locations of various medical devices (e.g., AEDs) and criteria for setting a specified area (third area) that will be the notification range of the location of the various medical devices. However, the storage unit 225 may further store one or more predetermined organizations that are registered in advance as organizations to be notified as emergency response organizations.

[0080] The storage unit 225 may also store map information of the locations where the cameras 20 under the jurisdiction of the notification server 22 are located and setting criteria for the first area. An administrator can update this information, and when updated, the notification server 22 transmits the updated information to the MEC server 21. As a result, the MEC server 21 updates the information stored in the storage unit 213.

[0081] 9 is a block diagram showing an example of the terminal 23. The terminal 23 corresponds to the terminal 12 in (1B), and includes an output unit 231, a transmitting / receiving unit (transceiver) 232, and a storage unit 233. Each component of the terminal 23 will be described below.

[0082] The output unit 231 is an interface that notifies the user of the terminal 23 of information by text, image, sound, etc., and is composed of a display, a speaker, etc. The output unit 231 outputs the response method and the location information of the accident site transmitted to each terminal 23 from the transmitting / receiving unit 224 of the notification server 22 to the user of the terminal 23. For example, if the terminal 23 is a smartphone, the information may be displayed on its display, and if the terminal 23 is a car navigation system, the information may be displayed on its display.

[0083] The transmitting / receiving unit 232 receives the response method and the location information of the accident site notified from the notification server 22. In addition, when the terminal 23 further includes an input unit and the user who visually confirms the response method inputs content indicating that the response method has been confirmed, the transmitting / receiving unit 232 may transmit a notification to the notification server 22 indicating that the response method has been confirmed.

[0084] The storage unit 233 stores information such as a method of response sent from the notification server 22, and also stores information necessary for operating the terminal 23.

[0085] Fig. 10 is a sequence diagram showing an example of a typical process of the notification system S2, and the process of the notification system S2 is explained using this sequence diagram. Details of the process executed by each device below are as described above. Note that, although Fig. 10 shows the camera 20A and the terminal 23A as examples of the camera 20 and the terminal 23, similar processes are performed in the other cameras 20 and terminals 23.

[0086] First, the photographing unit 201 of the camera 20A photographs the intersection C1 (step S21), and the transmitting / receiving unit 202 transmits the photographed video data to the MEC server 21 (step S22).

[0087] The transmitting / receiving unit 212 of the MEC server 21 receives the video data transmitted in step S22. The accident occurrence detection unit 211 detects the occurrence of an accident at the intersection C1 based on the video data of the camera 20A (step S23). As described above, the transmitting / receiving unit 212 transmits the video data of the camera 20A related to the accident to the notification server 22 (step S24).

[0088] The transmitting / receiving unit 224 of the notification server 22 receives the video data transmitted in step S24. The notification server 22 determines a countermeasure for the person to be analyzed based on the received video data (step S25). This will be described in detail later. The transmitting / receiving unit 224 of the notification server 22 transmits the determined countermeasure, etc. to the terminal 23 (step S26).

[0089] The transmitting / receiving unit 232 of the terminal 23A receives the video data transmitted in step S26. The output unit 231 of the terminal 23A outputs a method of dealing with the problem to the user (step S27).

[0090] 11 is a flowchart showing an example of the process of step S25, and this flowchart will be used to explain the process of the notification server 22. First, the notification target detection unit 221 detects a notification target from the video data transmitted from the MEC server 21 (step S251). In addition, the analysis unit 222 analyzes the video data to derive detailed information of a person to be analyzed who is involved in the accident detected by the accident occurrence detection unit 211 of the MEC server 21 (step S252).

[0091] The determination unit 223 determines a method of dealing with the person to be analyzed based on the detailed information derived by the analysis unit 222 (step S253). The transmission / reception unit 224 notifies the notification target detected by the notification target detection unit 221 of the method of dealing determined in step S253 (step S254). Note that either step S251 or S252 may be performed first. However, when personal information of the person to be analyzed is acquired as detailed information in step S252, a notification target may be added based on the personal information, as in the case of Hospital D described above, so step S252 may be performed first. Also, details of the processes in steps S251 to S254 are as described in the description of the notification target detection unit 221 to the transmission / reception unit 224.

[0092] As described above, when an accident occurs, the notification system S2 can analyze the person being analyzed, determine a method of response, and notify the person, thereby enabling a rapid initial response to the person being analyzed.

[0093] Furthermore, the notification target detection unit 221 of the notification server 22 detects notification targets present in a first area including the location where the accident occurred, and the transmission / reception unit 224 can notify the detected notification targets of a method of response. In this way, the notification server 22 detects people and vehicles present around the accident site, rather than the reporter, and provides information to them. Therefore, cooperation in responding to the injured or suddenly ill person can be obtained from non-reporters present around the accident site and people who are unaware of the accident (for example, people in blind spots from the accident site). This makes it possible to increase the survival rate of the injured or suddenly ill person and to prevent poor prognosis.

[0094] Furthermore, the notification server 22 can notify at least one of a person and a vehicle of the countermeasure, so that a person in the vicinity of the scene or a person in a vehicle can immediately recognize the countermeasure and take action.

[0095] In addition, the decision unit 223 of the notification server 22 can execute at least one of the following as the decision of the countermeasure method: deciding the medical treatment or procedure for the person to be analyzed, and identifying the location of the medical equipment to be used in the medical treatment or procedure and present in the area including the accident site. By transmitting this countermeasure method to the notification target by the transmission / reception unit 224, the notification target can take a more appropriate measure against the injured or suddenly ill person.

[0096] Furthermore, the notification target detection unit 221 of the notification server 22 detects a candidate for the notification target as a notification target by determining whether the candidate is captured in the video, and the transmission / reception unit 224 can notify a terminal associated with the detected notification target of a response method. This allows the notification server 22 to notify people present in the vicinity of the accident site, thereby increasing the probability that care will be given to injured or suddenly ill people.

[0097] The notification target may also include medical or emergency facilities. The determination unit 223 can determine the content of the countermeasure to be notified to such facilities to include at least one of the following: treatment for the person to be analyzed, a request to dispatch staff to the location where the accident occurred, a request to accept the person to be analyzed, and preparation for treatment. This allows the notification server 22 to have the medical or emergency facilities deal with the injured or suddenly ill person, so that the injured or suddenly ill person can receive treatment early or appropriately from a specialized facility.

[0098] The analysis unit 222 may also derive personal information associated with the registrant as detailed information by identifying the person to be analyzed from among the registrants based on the result of face authentication using the face image of the person to be analyzed shown in the video and the face information of the registrant. The determination unit 223 can then determine a method of response based on the personal information. Therefore, since the notification server 22 can notify a method of response according to the characteristics of the individual, it is expected that a response according to the circumstances of the injured or suddenly ill person will be made.

[0099] The personal information may include, for example, at least one of the following: medical history, current medical history, pregnancy status, age, sex, blood type, allergy information, personal number, family medical institution, and emergency contact information. Based on such medical-related personal information, the notification server 22 can notify detailed and accurate measures.

[0100] The transmitting / receiving unit 224 may also determine the notification target based on personal information. This allows the notification server 22 to have a person or organization that knows the circumstances of the person being analyzed deal with the person being analyzed, making it possible for the injured or suddenly ill person to receive appropriate care.

[0101] The detailed information may also include at least one of consciousness state, breathing state, bleeding state, fracture state, burn state, site of impact, convulsion state, walking state, heart rate state, pulse state, and body temperature state. Based on such detailed medical information, the notification server 22 can notify detailed and accurate measures.

[0102] Furthermore, the determination unit 223 can notify different measures (treatment or procedure) for a case where the notification target is a non-medical person or their vehicle (first type of candidate) and a case where the notification target is a medical person or their vehicle (second type of candidate). Therefore, the notification server 22 can notify a measure that takes into consideration the expertise of the notification target, thereby increasing the possibility that an injured or suddenly ill person will receive appropriate first aid, and can also provide a notification that takes into consideration the notification target.

[0103] The configuration and processing of the notification system S2 shown in (2A) can be modified as follows. For example, even if the notification target is a vehicle of a non-medical professional, the decision unit 223 can decide the method of response in the same way as when the notification target is a non-medical professional.

[0104] In (2A), the notification target detection unit 221 added Hospital D as a notification target in accordance with the personal information acquired by the analysis unit 222, regardless of the distance from the accident site. However, the notification target detection unit 221 does not need to add Hospital D as a notification target when Hospital D is not included in the area R1 or is not included within a predetermined area from the accident site. The predetermined area is stored in advance in the memory unit 225 as a threshold for determination.

[0105] The notification target detection unit 221 may specify one or more emergency medical institutions according to the circumstances of the accident, instead of or in addition to the hospital D stored as personal information, and set them as notification targets. The response method notified to the emergency medical institution includes at least one of the following: treatment for the person to be analyzed, a request to dispatch staff to the location where the accident occurred, and a request to accept the person to be analyzed. If the emergency medical institution replies to the notification server 22 that it cannot accept the notification from the transmission / reception unit 224, the notification target detection unit 221 may reset another emergency medical institution as a new notification target. The transmission / reception unit 224 notifies the new notification target of the response method. This method of resetting the notification target may be based on the priority order stored in advance in the storage unit 225. Alternatively, the notification target detection unit 221 may determine the priority order based on the criteria for determining the priority order stored in advance in the storage unit 225, and at least one of the location information of the accident site and the detailed information acquired by the analysis unit 222, and reset the notification target based on the priority order.

[0106] In (2A), a case where the person to be analyzed has heart disease has been described, but the notification system S2 can of course be applied to other situations. For example, when the analysis unit 222 determines that the person to be analyzed hits his / her head in an accident based on the video data captured by the cameras 20A and 20B, the decision unit 223 may include "not moving the head" as a treatment or procedure in the countermeasures. In addition, when the analysis unit 222 determines that the person to be analyzed is bleeding heavily based on the video and further determines that the blood type of the person to be analyzed is type O as personal information, the decision unit 223 may include "need for a transfusion of type O blood" which is preparation for a blood transfusion (preparation for treatment) in the countermeasures.

[0107] The MEC server 21 may be provided at any location on the communication path from the camera 20 to the notification server 22. For example, the MEC server 21 and the camera 20 may be connected by a wired line, and the MEC server 21 may be connected to the notification server 22 via 5G wireless communication. As another example, the camera 20 may be connected to the MEC server 21 provided near a 5G base station via 5G wireless communication, and the MEC server 21 and the notification server 22 may be connected by a wired line. Here, instead of providing the MEC server 21 near the 5G base station, the MEC server 21 may be provided in a predetermined area or in a core network (5GC) of the 5G system. By providing the MEC server 21 closer to the camera 20 on the communication path, the distance over which a series of video data output from each camera 20 flows can be made shorter. Therefore, a large amount of data is prevented from flowing on the network, and the network load can be reduced and communication delays can be suppressed.

[0108] The MEC server 21 may be provided alone, or multiple MEC servers 21 may be provided in a geographically distributed state. The MEC server 21 may also include at least one of a notification target detection unit 221, an analysis unit 222, and a determination unit 223 included in the notification server 22.

[0109] Alternatively, a configuration may be adopted in which the MEC server 21 is not provided, the notification server 22 includes the accident occurrence detection unit 211, and the camera 20 transmits video data directly to the notification server 22.

[0110] In (2A), the MEC server 21 determines that the cameras 20C and 20D are present in the area R1, and thereby determines that the video data captured by the cameras 20C and 20D are also necessary for the processing of the notification server 22, and transmits the video data to the notification server 22. However, the MEC server 21 may not perform the determination, and may transmit only the video data captured by the cameras 20A and 20B that detected the accident to the notification server 22. In this case, the notification target detection unit 221 of the notification server 22 sets the area R1 as the first area including the accident site, using the map information of the area around the accident site stored in the storage unit 225 and the setting criteria for the first area. Then, the notification target detection unit 221 specifies that the cameras 20 capturing the area R1 are the cameras 20A to 20D. As a result, the notification target detection unit 221 determines that the video data captured by the cameras 20C and 20D are also necessary for the notification target detection, and requests the MEC server 21 to output the video data captured by the cameras 20C and 20D. Based on the request, the MEC server 21 transmits the video data captured by the cameras 20C and 20D to the notification server 22. The notification target detection unit 221 uses this video data to perform the above-mentioned processing.

[0111] (2B) In (2B), a variation different from (2A) will be described. In the following explanation, the differences from (2A) will be described, and the explanation of the same points as (2A) will be omitted as appropriate.

[0112] Fig. 12 is a schematic diagram showing an example of a road on which the camera 20 is installed. In addition to the elements shown in Fig. 6, Fig. 12 discloses an area R2 that is larger than the area R1 and includes the area R1 and the periphery of the intersection C3. The processing will be described below using this example.

[0113] As shown in (2A), the accident occurrence detection unit 211 of the MEC server 21 detects the occurrence of an accident from the video data captured by the cameras 20A and 20B. At this time, the accident occurrence detection unit 211 determines an area R1 as a first area including the accident site, and determines an area R2 as a second area including the accident site. Then, the accident occurrence detection unit 211 causes the notification server 22 to transmit, via the transmission / reception unit 212, not only the video data captured by the cameras 20A to 20D related to the area R1, but also the video data captured by the cameras 20E and 20F related to the area R2 from time t3 to the present. Note that the time t3 is set in the same manner as the above-mentioned time t2.

[0114] The "second area" can be set to any range, similar to the "first area". For example, the "second area" may be a circular area with a radius of a predetermined distance from the accident site that is longer than the "first area", or may be an area including the "first area" and located within a predetermined time from the accident site at a predetermined walking speed or vehicle speed. The "second area" may also be a predetermined section that includes the "first area". The accident occurrence detection unit 211 can set the first and second areas, for example, using the location information of the detected accident site, map information around the accident site stored in the storage unit 213, and setting criteria for the first and second areas.

[0115] Notification target detection unit 221 detects, as notification targets, non-medical personnel and their vehicles (first type of candidates) who are candidates for notification targets in a first area, and medical personnel and their vehicles (second type of candidates) who are candidates for notification targets in a second area. Notification target detection unit 221 analyzes the video data captured by cameras 20A-20F and compares specific information with the video data captured by cameras 20A-20F to determine whether or not the notification target is captured in each video data.

[0116] As in (2A), the notification target detection unit 221 detects medical personnel NA, non-medical personnel NB, and a vehicle NC owned by the hospital C as notification targets present in the first area based on the video data captured by the cameras 20A-20D. Furthermore, the notification target detection unit 221 detects medical personnel NE as a notification target present in the second area and not present in the first area based on the video data captured by the cameras 20E-20F. The notification target detection unit 221 may detect medical personnel NE as a notification target present in the second area and not present in the first area but not detect non-medical personnel NF by analyzing specific information of medical personnel, etc. and not analyzing specific information of non-medical personnel, etc., with respect to the video data captured by the cameras 20E-20F. However, although the notification target detection unit 221 analyzes specific information of both medical personnel and non-medical personnel regarding the video data captured by the cameras 20E to 20F, non-medical personnel NF and vehicles NG detected as a result of the analysis may be set as excluded from notification.

[0117] The analysis unit 222 executes the same process as in (2A). The decision unit 223 decides on a different method of response depending on whether the notification target is a medical person NA, a vehicle NC, or a medical person NE (medical person or their vehicle), whether the notification target is a non-medical person NB (general public), or whether the notification target is a hospital D (medical institution). This decision method is as described in (2A).

[0118] The transmitting / receiving unit 224 notifies the terminal 23E of the method of response, including the information on the treatment and the location of an AED present in a predetermined area. Here, the terminal 23E is a smartphone owned by the medical professional NE, and its contact information is associated with the medical professional NE and stored in the storage unit 225. The transmitting / receiving unit 224 notifies the terminals 23A to 23C in the same manner as in (2A). In addition, the transmitting / receiving unit 224 notifies each notification target terminal 23 of the location information of the accident site received by the notification server 22 together with the method of response.

[0119] As described above, the notification target detection unit 221 detects that the first type of candidate exists in the region R1 and that the second type of candidate exists in the region R2 as the notification target candidates, and the transmission / reception unit 224 can notify the first type of candidate existing in the region R1 and the second type of candidate existing in the region R2 as the notification target and notify the countermeasure. Since medical personnel, etc. can be expected to arrive at the accident site even if they are located slightly away from the accident site, since providing first aid to injured or suddenly ill people is part of their job. On the other hand, general volunteers, etc. are inexperienced in providing first aid and may have other jobs, so it may not be realistic for them to request help when they are located slightly away from the accident site. Taking this into consideration, the notification server 22 can change the detection region (i.e., the range for requesting help) according to the attributes of the notification target to increase the possibility that the injured or suddenly ill person will be given help. However, the transmission / reception unit 224 may notify at least one of the first type of candidate existing in the region R1 and the second type of candidate existing in the region R2.

[0120] The attributes of individuals identified as candidates for notification targets are "non-medical personnel" for the first type of candidate and "medical personnel" for the second type of candidate, but are not limited to this example. For example, the second type of candidate may include people whose job is to go to the scene of an accident, such as firefighters, police officers, and company staff who respond to accidents. The number of candidates for notification targets is not limited to two, and three or more types may be set, and correspondingly, three or more types of detection areas in which the notification target detection unit 221 detects each type of candidate may also be set. The specified area (third area) that is the notification target of the location where various medical devices are located may be the same area as any of the multiple set detection areas, or may be an area different from any of them.

[0121] Third embodiment In the third embodiment, an example will be described in which a notification server detects a notification target by acquiring location information from a terminal owned by a candidate for the notification target. In the following description, differences from the second embodiment will be described, and descriptions of the same points as the second embodiment will be omitted as appropriate.

[0122] 13 is a schematic diagram showing an example of a notification system. The notification system S3 includes cameras 20A-20N, an MEC server 21, a notification server 32, and terminals 33A-33C and 23D. The terminals 33A-33C are collectively referred to as terminal 33. The camera 20 and the MEC server 21 have the configurations shown in FIGS.

[0123] The camera 20 transmits the video data to the MEC server 21, similar to (2A). The accident occurrence detection unit 211 of the MEC server 21 also detects the occurrence of an accident using the video data transmitted from the cameras 20A to 20N, similar to (2A). As a result, the transmission / reception unit 212 transmits the video data of the cameras 20A and 20B that captured the intersection C1 where the accident occurred, together with the location information of the accident site to the notification server 22. However, the MEC server 21 does not need to determine the area R1, which is the first area including the accident site, and as a result, does not need to transmit the video data captured by the cameras 20C and 20D to the notification server 22. Therefore, the storage unit 213 does not need to store the setting criteria for the first area, etc.

[0124] 14 is a block diagram showing an example of the notification server 32 according to the embodiment 3. The notification server 32 includes a location information acquisition unit 321 in addition to the configuration of the notification server 22 according to the embodiment 2.

[0125] The location information acquisition unit 321 acquires location information from the terminal 33 of each candidate for notification. The location information acquisition unit 321 receives location information of the terminal 33 acquired by the terminal 33 using a satellite positioning system such as a global positioning system (GPS) or a positioning technology such as an indoor positioning technology from the transmission / reception unit 232 of the terminal 33. This location information is updated at a predetermined timing.

[0126] The notification target detection unit 221 detects a candidate for notification that exists in a first area including the accident site, based on the latest location information of the terminal 33 acquired by the location information acquisition unit 321. The accident occurrence detection unit 211 can set the first area, for example, by using the location information of the detected accident site, map information around the accident site stored in the storage unit 225, and a setting criterion for the first area. Details of this method are as shown in the second embodiment. Furthermore, when the notification target detection unit 221 detects that a terminal associated with the candidate for notification (for example, a terminal held by the candidate) exists in the first area, it detects that the candidate for notification exists in the first area.

[0127] For example, in the example shown in Fig. 6, terminals 33A, 33B, and 33C owned by medical personnel NA, non-medical personnel NB, and vehicle NC, which are candidates for notification targets, are located in the first region R1. Meanwhile, terminals 33E and 33F owned by medical personnel NE and non-medical personnel NF, which are candidates for notification targets, are located outside the region R1. The notification target detection unit 221 analyzes such a positional relationship between the region R1 and each terminal 33 based on the position information of the terminal 33 acquired by the position information acquisition unit 321. Based on this analysis, the notification target detection unit 221 detects medical personnel NA, non-medical personnel NB, and vehicle NC as notification targets present in the region R1.

[0128] The processing executed by the analysis unit 222 and the determination unit 223 is the same as that of (2A). Similarly to (2A), the transmission / reception unit 224 notifies the terminals 33A and 33C of the treatment information and the handling method including the location information of the AED present in the predetermined area, and notifies the terminal 33B of the treatment information and the handling method including the location information of the AED present in the predetermined area. Here, the terminals 33A and 33B are smartphones owned by the medical personnel NA and the non-medical personnel NB, respectively, and the terminal 33C is a car navigation system installed in the vehicle NC. The contact information of the terminals 33A, 33B, and 33C is associated with the medical personnel NA, the non-medical personnel NB, and the vehicle NC, respectively, and is stored in the storage unit 225 as information of candidates for notification targets. Other processing executed by the transmission / reception unit 224 is the same as that of (2A), and therefore will not be described.

[0129] The storage unit 225 stores information necessary for the processes executed by the notification target detection unit 221 to the transmission / reception unit 224. However, since the notification target detection unit 221 does not detect candidates for notification targets from video data of a camera, the storage unit 225 does not need to store specific information for face authentication that identifies a specific individual or vehicle.

[0130] 15 is a block diagram showing an example of the terminal 33. The terminal 33 further includes a position detection unit 331 in addition to the configuration of the terminal 23 according to the second embodiment.

[0131] The position detection unit 331 updates the position information of the terminal 33 itself at a predetermined timing using some positioning technology such as a satellite positioning system or an indoor positioning technology. When the position information is updated, the position detection unit 331 transmits its own position information to the notification server 32 by the transmission / reception unit 232. The timing at which the position detection unit 331 transmits the position information to the notification server 32 can be at least one of a predetermined cycle and a predetermined event detection. The predetermined event may be a change in a base station or cell to which the terminal 33 is connected when the terminal 33 uses cellular wireless communication such as LTE or 5G. The predetermined event may be a movement of the terminal 33 a predetermined distance, a predetermined time, a request from the notification server 32, or the like. The position detection unit 331 is realized, for example, by installing a notification application in the terminal 33 and running the application by the control unit of the terminal 33. The processes executed by the output unit 231 to the storage unit 233 are the same as those in (2A), and therefore will not be described. As an example, when a notification application is installed on the terminal 33, the output unit 231 may display the countermeasures and the location information of the accident site received from the notification server 32 as a push notification on the screen.

[0132] As described above, the location information acquisition unit 321 acquires location information of the terminal from the terminal 33 owned by the candidate notification target, and the notification target detection unit 221 can detect the notification target based on the location information acquired by the location information acquisition unit 321. This allows the notification server 22 to detect candidate notification targets not captured by the camera 20 and notify them of how to deal with the situation, thereby further increasing the number of notification destinations to which the response method can be notified. Therefore, more people can be expected to cooperate in rescue efforts.

[0133] In the third embodiment, as shown in (2B), two or more types of candidates to be notified may be set, and correspondingly, two or more types of areas to be detected by the notification target detection unit 221 for each type of candidate may also be set. In addition, in the third embodiment, the variations described in the second embodiment can be applied as appropriate.

[0134] Fourth embodiment In the fourth embodiment, an example will be described in which a terminal that has been notified of a countermeasure controls whether or not to output the notified countermeasure. In the following description, differences from the third embodiment will be described, and explanations of the same points as the third embodiment will be omitted as appropriate.

[0135] 16 is a schematic diagram showing an example of a notification system. The notification system S4 includes cameras 20A to 20N, an MEC server 21, a notification server 42, and terminals 43A to 43C and 23D. The terminals 43A to 43C are collectively referred to as terminal 43. The camera 20 and the MEC server 21 execute the same processes as those in the third embodiment.

[0136] 17 is a block diagram showing an example of a notification server 42 according to the fourth embodiment. The notification server 42 includes a notification area specification unit 421 instead of the notification target detection unit 221 of the notification server 22 according to the second embodiment. In the second and third embodiments, the notification server selects, as the notification target, a target that exists in a predetermined detection area from among candidates for the notification target, whereas this notification server 42 notifies all notification targets related to registered people and vehicles of a countermeasure method. Therefore, the notification server 42 does not need to include the notification target detection unit 221 for detecting the notification target.

[0137] The notification area specifying unit 421 sets the area R1 to be notified based on the location information of the accident site and the setting criteria for the first area stored in the storage unit 225. The details of this setting are as described above.

[0138] The analysis unit 222 of the notification server 42 executes the same process as in the embodiment 2. Similarly to the embodiment 2, the decision unit 223 also decides a different response method depending on whether the notification target is a first type (e.g., a medical professional or his / her vehicle), a second type (e.g., a general public), or a medical institution.

[0139] The transmitting / receiving unit 224 notifies all notification targets related to people and vehicles stored in the storage unit 225 of the handling method determined by the determining unit 223. In this way, the transmitting / receiving unit 224 notifies the first type of notification targets including the terminals 43A and 43C of the handling method including the information on the treatment and the location of the AED present in the specified area. The transmitting / receiving unit 224 also notifies the second type of notification targets including the terminal 43B of the handling method including the information on the treatment and the location of the AED present in the specified area. Furthermore, the transmitting / receiving unit 224 notifies the terminal 23D of the handling method including the treatment for the person to be analyzed and the request to accept the person to be analyzed. The notification to the first and second types of notification targets may be performed by unicast communication for each terminal, may be performed by multicast communication for each first or second type of notification target, or may be performed by multicast communication in units of base stations or cells.

[0140] Furthermore, the transmission / reception unit 224 notifies the location information of the accident site and information on the area R1 set by the notification area specification unit 421, together with the countermeasure, to each of the notification target terminals 43A to 43C, 23D.

[0141] The storage unit 225 stores information necessary for the processes executed by the notification area specification unit 421 through the transmission / reception unit 224. For example, the storage unit 225 stores the following information. (i) Information on the specified institutions, individuals, and vehicles that are the subject of notifications, and the terminal information of the institutions, individuals, and vehicles to which notifications associated with each of those information are sent (ii) facial information of the registrant for the analysis unit 222 to perform face authentication (iii) A list of the locations of various medical devices (e.g., AEDs) and the criteria for setting a specified area (third area) that is the subject of notification of the location of various medical devices. (iv) Criteria for setting the first area The method in which the transmitting / receiving unit 224 determines the predetermined organization to notify of the countermeasure based on the information in (i) is as described in the embodiment 2. In addition, the storage unit 225 does not need to store specific information that identifies a specific individual or vehicle.

[0142] 18 is a block diagram showing an example of the terminal 43. The terminal 43 further includes an output control unit 431 in addition to the configuration of the terminal 33 according to the third embodiment.

[0143] The transmitting / receiving unit 232 receives the countermeasure, the position information of the accident site, and the information on the area R1 transmitted to each terminal 43 from the transmitting / receiving unit 224 of the notification server 42. The output control unit 431 compares the latest position information of the terminal itself detected by the position detection unit 331 with the received information on the area R1, and determines whether the terminal itself is within the area R1.

[0144] When it is determined that the terminal 43 is within the region R1, the output control unit 431 controls the output unit 231 to output the countermeasure and the location information of the accident site received from the notification server 42. The output is performed, for example, as a push notification of an application. This allows the user of the terminal 43 (i.e., the notification target) to know the information on the countermeasure and the like. On the other hand, when it is determined that the terminal 43 is outside the region R1, the output control unit 431 controls the output unit 231 not to output the countermeasure and the location information of the accident site received from the notification server 42. Therefore, the user of the terminal 43 does not know the information on the countermeasure and the like. Other processes executed by the terminal 43 are the same as those in the third embodiment, and therefore will not be described.

[0145] In this embodiment, since the notification server 42 does not need to specify the notification target, the notification server 42 can be configured more simply. Also, while the method of response is output to the notification target who is close to the accident scene, the method of response is not output to the notification target who is far from the accident scene. Therefore, the burden on the notification target who is far from the accident scene can be reduced.

[0146] In the fourth embodiment, as shown in (2B), two or more types of candidates to be notified may be set, and the notification area specification unit 421 may set two or more types of areas to be notified for each type of candidate accordingly. For example, the notification area specification unit 421 sets an area R1 in which a first type of notification target is notified of a countermeasure method and an area R2 in which a second type of notification target is notified of a countermeasure method based on the location information of the accident site and the setting criteria of the first and second areas stored in the storage unit 225. When the notification target is the first type, the transmission / reception unit 224 notifies information on the area R1 together with the countermeasure method, etc., and when the notification target is the second type, notifies information on the area R2 together with the countermeasure method, etc.

[0147] The transmitting / receiving unit 232 receives the countermeasure, the location information of the accident site, and the information on the region R1 or R2 transmitted from the transmitting / receiving unit 224 of the notification server 42 to each terminal 43. The output control unit 431 compares the latest location information of the terminal detected by the location detection unit 331 with the received location information of the region R1 or R2 to determine whether the terminal is in the region R1 or R2. Depending on the determination result, the output control unit 431 performs the above-mentioned control. Note that the storage unit 233 of the terminal 43 may store attribute information indicating whether the terminal is a first type or a second type of notification target. The output control unit 431 may determine whether the region R1 or the region R2 is to be used in the above-mentioned determination regarding the location of the terminal based on this attribute information. This allows, for example, a countermeasure to be output to a terminal of a medical professional even if the terminal is somewhat far from the accident site, whereas a countermeasure to be output to a terminal of a general volunteer, etc., if the terminal is somewhat far from the accident site.

[0148] The notification server 42 may not include the notification area specification unit 421. In this case, for example, the transmission / reception unit 224 notifies each notification target terminal 43 of the location information of the accident site and the setting criteria of the first area together with the method of response. The output control unit 431 sets the area R1 to be notified based on the received location information of the accident site and the setting criteria of the first area. Then, the latest location information of the terminal detected by the location detection unit 331 is compared with the location information of the area R1 to determine whether the terminal is in the area R1. Even in this way, it is possible to prevent the notification target person who is far from the accident site from outputting the method of response, etc. This control is naturally possible even when another area such as the area R2 is set instead of the area R1. The setting criteria of the first area may be stored in advance in the storage unit 233 of the terminal 43. In this case, the transmission / reception unit 224 does not need to notify the terminal 43 of the setting criteria of the first area together with the method of response and the location information of the accident site.

[0149] As for other variations of the fourth embodiment, what has been described in the second and third embodiments can be applied as appropriate.

[0150] Fifth embodiment (5A) In the fifth embodiment, an example will be described in which a notification server uses a network configuration to notify notification targets near the accident site of how to deal with the accident. In the following explanation, differences from the second embodiment will be explained, and explanations of the same points as the second embodiment will be omitted as appropriate.

[0151] The notification system according to the fifth embodiment is as shown in Fig. 4, and the configuration of each device according to Fig. 4 is as shown in Figs. 5, 7, 8, and 9. However, notification server 22 executes a process different from that of the second embodiment, as follows.

[0152] The notification target detection unit 221 identifies one or more base stations that include the location of the accident site within its own cell. The notification target detection unit 221 performs this identification by comparing the location information covered by the cell of each base station, which is associated with the identification information of each base station, with the location of the accident site. The location information covered by the cell of each base station may be stored in the storage unit 225, or may be acquired and used by the notification target detection unit 221 from another database or the like. In this way, the notification target detection unit 221 detects the notification targets by setting all terminals under the identified base station as notification targets.

[0153] The analysis unit 222 executes the same process as in the second embodiment. When the notification target is all terminals under the specified base station, the determination unit 223 determines a countermeasure method including both a countermeasure method for the first type of candidate (non-medical personnel) and a countermeasure method for the second type of candidate (medical personnel). However, the determination unit 223 may include either one of the countermeasure method for the first type of candidate and the countermeasure method for the second type of candidate in the countermeasure method. The details are as described in the fourth embodiment. Also, when the notification target is hospital D, the determination unit 223 determines a countermeasure method as described in the second embodiment.

[0154] The transmitting / receiving unit 224 may notify all terminals under the base station identified by the notification target detection unit 221 of the countermeasure method determined by the determination unit 223 and the location information of the accident site by broadcast communication or multicast communication. For example, eMBMS (evolved Multimedia Broadcast Multicast System) or SC-PTM (Single Cell Point To Multipoint) may be used for the LTE network, and FeMBMS (Further evolved Multimedia Broadcast Multicast Service) may be used for the 5G network as the broadcast communication or multicast communication. Note that, for the hospital D that is the notification target, the countermeasure method and the location information of the accident site are notified as described in the second embodiment.

[0155] The storage unit 225 stores information necessary for the processes executed by the notification target detection unit 221 through the transmission / reception unit 224. Specifically, the following information is stored: (i) Information on the designated institutions that are candidates for notification and the terminal information of the institutions to which the associated notifications will be sent (ii) facial information of the registrant for the analysis unit 222 to perform face authentication (iii) A list of the locations of various medical devices (e.g., AEDs) and criteria for setting a specified area (third area) that is the subject of notification of the location of various medical devices.

[0156] Furthermore, the storage unit 225 may store location information about the areas covered by the cells of each base station, and map information about the locations where the cameras 20 under the jurisdiction of the notification server 22 are located.

[0157] Terminal 23, which has received the response method and the location information of the accident site from notification server 22, outputs the information on a display or the like, as described in embodiment 2. By doing as described above, notification server 22 can notify an unspecified number of users who have terminals and are under the control of the base station of the response method, etc. This can increase the probability that injured or suddenly ill people will receive first aid.

[0158] The one or more base stations identified by the notification target detection unit 221 may be either a macrocell base station having the largest cell size, or a small cell base station having a smaller cell size (for example, a microcell, a picocell, or a femtocell), or may include both. Furthermore, the notification target detection unit 221 may specify not only a base station that includes the location of the accident site in its own cell, but also neighboring base stations such as adjacent base stations. For other variations, the same as those described in the previous embodiments may be applied as appropriate.

[0159] (5B) The notification target detection unit 221 may not treat all terminals under the specified base station as notification targets, but may obtain information on terminals under the base station and provided with services by a specific mobile communication operator (communication carrier), and detect the terminals as notification targets. For example, in a 4G network, a Home Subscriber Server (HSS) in a core network manages subscriber information of the communication carrier, and a Mobility Management Entity (MME) in the core network manages location information of terminals and handovers between base stations (user mobility management). Therefore, the notification target detection unit 221 can obtain information on terminals under a specific base station and provided with services by a specific communication carrier by communicating with the HSS and MME.

[0160] As another example, in a 5G network, UDM (Unified Data Management), which is one of the network functions, manages subscriber information of a communication carrier, and AMF (Access and Mobility Management Function), which is one of the network functions, manages terminal location information and handover between base stations (user mobility management). Therefore, the notification target detection unit 221 can acquire information on a terminal that is under a specific base station and is provided with a service by a specific communication carrier by communicating with the UDM and AMF. In addition, in the case of a 5G network, the notification target detection unit 221 may acquire information on the terminal via NEF (Network Exposure Function), which is a mechanism for disclosing network functions and information in the 5G system to applications outside the 5G system.

[0161] The analysis unit 222 and the determination unit 223 execute the same process as in (5A). The transmission / reception unit 224 notifies all terminals identified by the notification target detection unit 221 of the countermeasure method determined by the determination unit 223 and the location information of the accident site. This notification method may be unicast communication, or may use an emergency call mechanism in a mobile network.

[0162] In this manner, notification server 22 can notify a large number of unspecified users who have terminals and are under the control of a base station of measures to be taken.

[0163] (5C) In the fifth embodiment, two or more types of candidates to be notified may be set, and correspondingly, two or more types of areas to which each type of candidate is to be notified by the notification target detection unit 221 may also be set. The first type of notification target is, for example, a non-medical professional, and the second type of notification target is, for example, a medical professional.

[0164] FIG. 19 shows an example of the configuration of a cell of a base station to explain the area to be notified. In this example, the notification target detection unit 221 identifies the base station A that includes the location of the accident site within its own cell A. In addition, the notification target detection unit 221 identifies the cells B to G adjacent to the cell A, thereby further identifying the base stations B to G (base stations located in the vicinity of the base station A) that constitute each cell. The notification target detection unit 221 performs the process of identifying this base station using the location information covered by the cell of each base station, as described in (5A).

[0165] The storage unit 225 stores a correspondence relationship between identification information of the first type and second type candidate terminals and the type of notification target (information indicating whether the notification target is the first type or the second type). Furthermore, the storage unit 225 further stores a setting criterion for a first area, which is an area in which a countermeasure method is notified to the first type, and a setting criterion for a second area, which is an area in which a countermeasure method is notified to the second type candidate.

[0166] The notification target detection unit 221 sets as the notification target a terminal that is accommodated in the cell A and is a candidate stored in the storage unit 225 as a first type candidate, while setting as the notification target a terminal that is accommodated in the cells A to G and is a candidate stored in the storage unit 225 as a second type candidate. In detail, the notification target detection unit 221 specifies the cell A as the first region and the cells A to G as the second region using the setting criteria for each region. In addition, the notification target detection unit 221 acquires identification information (e.g., telephone number) of the terminal connected to each base station from the LTE or 5G network device. Using the acquired identification information of each terminal, the notification target detection unit 221 identifies whether the information of each terminal is stored in the storage unit 225, and if so, what type of notification target the terminal is. The notification target detection unit 221 can detect the terminal of the first type candidate accommodated in the cell A and the terminal of the second type candidate accommodated in the cell B as notification targets based on the identified type of notification target. The method of notifying the notification subjects of the countermeasures is as described above.

[0167] In addition, not only in (5A) but also in (5B), the notification target detection unit 221 can execute the same process. In (5B), the notification target detection unit 221 acquires identification information of a terminal that is under a specific base station and is provided with a service by a specific communication carrier, and identifies the type of notification target in the terminal indicated by the identification information. This allows the notification target detection unit 221 to detect each type of candidate terminal as a notification target. As for other variations of the fifth embodiment, those described in the second to fourth embodiments can be applied as appropriate.

[0168] Sixth embodiment (6A) In the second to fourth embodiments, when notifying a countermeasure method by unicast communication, the notification server 22 may change the area treated as a notification target depending on whether the terminal candidate for notification is owned by an individual or installed in a vehicle.

[0169] For example, in the second embodiment, the notification target detection unit 221 detects non-medical personnel and their vehicles as notification targets when they are located within the region R1, but does not detect them as notification targets when they are located outside the region R1. However, even if the vehicle of a non-medical personnel is located within a predetermined region larger than the region R1, the notification target detection unit 221 may detect the candidate as a notification target. If the region R2 (see FIG. 12) is set as the detection region for vehicles of non-medical personnel, the notification target detection unit 221 can also detect the vehicle NG as a detection target.

[0170] Similarly, even if the candidate for the vehicle of a medical professional is a vehicle and is located within a predetermined area wider than the area R2, the notification target detection unit 221 may detect the vehicle as a notification target. Whether the candidate for the notification target is an individual or a vehicle is included in the terminal information of the candidate for the notification target stored in the storage unit 225. In addition, the setting criteria of the detection area when the candidate for the notification target is a vehicle is also stored in the storage unit 225. The notification target detection unit 221 can set the detection area and detect the notification target using these pieces of information. For example, the notification target detection unit 221 may set the detection area broadly in the order of the detection area related to the vehicle of the medical professional, the detection area related to the vehicle of the non-medical professional, the detection area related to the individual medical professional, and the detection area related to the individual non-medical professional. In this order, the order of the "detection area related to the vehicle of the non-medical professional" and the "detection area related to the individual medical professional" may be reversed, or both may be areas of the same size.

[0171] As described above, the notification server 22 can change and set the detection area depending on whether the candidate for notification is an individual or a vehicle. If the person to be notified is riding in a vehicle that can move faster than walking, it is expected that the injured or ill person can be rescued in time even if they are some distance away from the accident scene. Therefore, by setting a wider detection area for the terminal mounted on the vehicle than for the terminal owned by an individual, it is possible to obtain the cooperation of more people.

[0172] In the above example, the detection area is changed depending on whether the notification target is an individual or a vehicle, but the notification target candidates may be divided into three or more types and a detection area may be set for each. For example, the notification target detection unit 221 may divide the detection target candidates into individuals, bicycles, and automobiles, and set the detection area to be wider for the later types. Also, when the notification target candidate is an individual, the same detection area may be set regardless of whether the notification target candidate is a non-medical professional or a medical professional. The same applies when the notification target candidate is a vehicle. In other words, the "first type of candidate" may be an individual, and the "second type of candidate" may be a vehicle.

[0173] (6B) In the third embodiment, the location information acquisition unit 321 of the notification server 32 may generate a movement history of the terminal user (i.e., the candidate for notification) based on the location information acquired at a predetermined timing. Based on this movement history, the notification target detection unit 221 may analyze the transportation means (walking, car, etc.) and average speed of the candidate for notification, and set a detection area based on the results.

[0174] For example, the notification target detection unit 221 determines, based on the movement history, that the terminal NH owned by a certain medical professional H is moving at an average speed of 30 km / h during a period from the present (the time when the notification target detection unit 221 executes this process) to a predetermined past timing. The storage unit 225 stores "15 km / h" as a threshold value for the average speed. By determining that the average speed of the terminal NH is equal to or greater than the threshold value, the notification target detection unit 221 presumes that the terminal NH (i.e., the medical professional H) is moving by car. Therefore, the notification target detection unit 221 can set the detection area of ​​the terminal NH to a wider area for vehicles, rather than the area R2 for the individual medical professional.

[0175] On the other hand, when the notification target detection unit 221 determines that the terminal NH is moving at an average speed of 5 km per hour during a period from the present to a predetermined past timing, it determines that the average speed of the terminal NH is less than the threshold value. In this case, the notification target detection unit 221 estimates that the terminal NH is moving on foot, and sets the detection area of ​​the terminal NH to the area R2 for individual medical personnel. Note that the notification target detection unit 221 can also change the detection area for terminals owned by non-medical personnel and terminals installed in vehicles using the same logic.

[0176] As described above, when the candidate for notification is in a state where it is easy to move, i.e., in a state where they can move quickly, the notification server 22 can change and set the detection area to be wider, which allows the cooperation of more people to be obtained for rescue.

[0177] The detection area may be changed in three or more stages instead of two stages. Also, if the notification candidates are moving at the same speed, the same detection area may be set regardless of whether they are non-medical personnel or medical personnel.

[0178] The present invention is not limited to the above-described embodiments, and can be modified as appropriate without departing from the spirit and scope of the present invention. For example, the inventions according to the first to sixth embodiments can be combined in whole or in part as appropriate.

[0179] The notification device 10 according to the first embodiment or the notification server according to the second to sixth embodiments may notify the terminal to be notified of detailed information (information on the physical condition of the person to be analyzed, at least some personal information, etc.) that is the analysis result of the analysis unit together with the above-mentioned countermeasures. Also, instead of or in addition to the detailed information, an image of the person to be analyzed captured by a camera may be notified to the terminal to be notified as a still image or a video together with the countermeasures. This allows a user who views the terminal to know the condition of the person to be analyzed, thereby enabling more appropriate rescue.

[0180] Furthermore, the notification device 10 according to the first embodiment or the notification server according to the second to sixth embodiments may further transmit a questionnaire to the terminal notifying the handling method, asking about detailed information about the accident (for example, witness information). The notification device 10 or the notification server can store the detailed information about the accident by receiving the questionnaire response from the terminal. This information can be shared with various parties involved in rescue, such as the hospital to which the person to be analyzed was taken, the emergency response department, the fire department, the police, etc.

[0181] In the second, third, fifth and sixth embodiments, the analysis unit 222 may determine the severity of the accident based on at least one of the degree of injury or illness of the person to be analyzed and the number of people to be analyzed (injured or suddenly ill people). The notification target detection unit 221 can change the detection area based on the severity.

[0182] In the case of the example of (2A), the storage unit 225 may store "four people" as the threshold value of the severity of the accident. Here, if the analysis unit 222 determines that the number of injured people in the accident is one, the analysis unit 222 determines the severity of the accident to be "low" because the number of injured people in the accident is less than the threshold value. In this case, the notification target detection unit 221 keeps the detection area as the area R1. In contrast, if the analysis unit 222 determines that the number of injured people in the accident is seven, the analysis unit 222 determines the severity of the accident to be "high" because the number of injured people in the accident is equal to or greater than the threshold value. In this case, the notification target detection unit 221 sets the detection area to a predetermined area (for example, area R2) that is larger than the area R1. In the third embodiment, the same processing can be performed. Moreover, by dividing the candidates for notification targets into two or more types, even if different detection areas are set in advance for each type of candidate, the notification target detection unit 221 can perform the same processing based on the severity of the accident for at least one of the multiple detection areas.

[0183] In the example of (5A), when the analysis unit 222 judges the severity of the accident to be "low", the notification target detection unit 221 identifies one or more base stations that include the location of the accident site within their own cell. In contrast, when the analysis unit 222 judges the severity of the accident to be "high", the notification target detection unit 221 identifies not only the base station that includes the location of the accident site within its own cell, but also one or more adjacent base stations (e.g., macrocell base stations) and other nearby base stations as specific targets.

[0184] As described above, the notification target detection unit 221 can change the detection area based on the severity of the accident, so the higher the severity of the accident, the more helpers can be gathered. Therefore, it is possible to increase the probability that an appropriate initial response will be made even for a serious accident. Note that the severity of the accident may be determined in three or more stages, and the detection area may be changed in three or more stages accordingly.

[0185] In addition, when the number of notification targets existing in the initial detection area is less than a predetermined threshold, the notification target detection unit 221 may expand the detection area from the initial one and detect candidates of notification targets existing in the newly targeted detection area as new notification targets. The predetermined threshold used for this determination is stored in the storage unit 225. The notification target detection unit 221 can repeat the process of expanding the detection area until the number of notification targets existing becomes equal to or greater than the predetermined threshold. The notification target detection unit 221 can execute this process regardless of the method described in each embodiment, that is, whether the notification target is specified by video data from a camera, location information from the terminal 23, or base station information. In addition, by dividing the notification target candidates into two or more types, even if different detection areas are set in advance for each type of candidate, a similar change process of the detection area can be executed for at least one of the multiple detection areas. This allows the notification server 22 to reliably secure personnel who can participate in the initial response to the accident.

[0186] In addition, the notification device 10 according to the first embodiment or the notification server according to the second to sixth embodiments may notify terminals other than those of individuals, vehicles, and organizations of the countermeasures. Taking the second embodiment as an example, the notification server 22 may notify digital signage terminals in a predetermined area including the accident site of the countermeasures for the first type of notification target (non-medical personnel) and the location information of the accident site based on the location information of the accident site and map information indicating the locations of one or more digital signage terminals stored in the storage unit 225. The digital signage terminal that receives the notification outputs the countermeasures and the location information of the accident site on a screen, by voice, or the like. It is expected that passersby will recognize the digital signage terminal and take initial action to respond to the injured or suddenly ill person. The predetermined area may be stored in the storage unit 225.

[0187] The notification to the digital signage terminal may be performed when the number of notification targets of individuals and vehicles present in the detection area initially set by the notification target detection unit 221 is less than a predetermined threshold. Furthermore, the predetermined area including the digital signage terminals to be notified can be expanded based on the severity of the above-mentioned accident determined by the analysis unit 222, and the higher the severity, the wider the predetermined area can be.

[0188] The notification server 22 may notify the user of the method of response and the location information of the accident site using a speaker of a disaster prevention radio in the same manner as in the example of the digital signage terminal. The method of response and the location information of the accident site are output by voice to people in the vicinity from the speaker.

[0189] In addition, in the second to fourth and sixth embodiments, when the number of notification targets of individuals and vehicles existing in the detection area initially set by the notification target detection unit 221 is less than a predetermined threshold, the process according to the fifth embodiment may be performed.

[0190] Furthermore, the notification target detection unit 221 may exclude candidates for notification targets that satisfy a certain condition from the notification targets based on the map information stored in the storage unit 225. For example, if the accident site is on a general road, but a candidate for notification target that is geographically close to the accident site is on a highway or on a train track (i.e., the notification target is on a train), the notification target cannot rush to the accident site immediately. The notification target detection unit 221 detects such a case by referring to information on the location of the candidate for notification from the map information, and excludes the candidate for notification target from the selection of notification targets.

[0191] Furthermore, when informing a vehicle of a countermeasure, whether for a non-medical or medical professional, the transmitting / receiving unit 224 may extract information on parking spaces near the accident site based on map information stored in the storage unit 225, and notify the terminal 23 of the vehicle of the information together with the countermeasure. This allows the user of the vehicle to immediately stop the vehicle and head to the accident site when approaching the accident site, thereby enabling more rapid rescue.

[0192] In the above embodiment, this disclosure has been described as a hardware configuration, but this disclosure is not limited to this. This disclosure can also be realized by having a processor in a computer execute a computer program to execute the processes (steps) of the device (notification device, notification server, MEC server, camera, or terminal) described in the above embodiment.

[0193] 20 is a block diagram showing an example of a hardware configuration of an information processing device (signal processing device) for executing the processes of the above-described embodiments. Referring to FIG. 20, the information processing device 90 includes a signal processing circuit 91, a processor 92, and a memory 93.

[0194] The signal processing circuit 91 is a circuit for processing signals in accordance with the control of the processor 92. The signal processing circuit 91 may include a communication circuit for receiving a signal from a transmitting device.

[0195] The processor 92 performs the processing of the device described in the above embodiment by reading and executing software (computer programs) from the memory 93. As an example of the processor 92, one of a CPU (Central Processing Unit), an MPU (Micro Processing Unit), an FPGA (Field-Programmable Gate Array), a DSP (Demand-Side Platform), and an ASIC (Application Specific Integrated Circuit) may be used, or a plurality of them may be used in parallel.

[0196] The memory 93 is composed of a volatile memory, a non-volatile memory, or a combination thereof. The memory 93 is not limited to one, and a plurality of memories may be provided. The volatile memory may be, for example, a RAM (Random Access Memory) such as a DRAM (Dynamic Random Access Memory) or a SRAM (Static Random Access Memory). The non-volatile memory may be, for example, a ROM (Random Only Memory) such as a PROM (Programmable Random Only Memory) or an EPROM (Erasable Programmable Read Only Memory), or a SSD (Solid State Drive).

[0197] The memory 93 is used to store one or more instructions. Here, the one or more instructions are stored in the memory 93 as a group of software modules. The processor 92 can perform the processes described in the above-mentioned embodiments by reading and executing the group of software modules from the memory 93.

[0198] The memory 93 may include a memory built into the processor 92 in addition to a memory provided outside the processor 92. The memory 93 may also include a storage device disposed away from the processors constituting the processor 92. In this case, the processor 92 can access the memory 93 via an I / O (Input / Output) interface.

[0199] As described above, one or more processors included in each device in the above-mentioned embodiments execute one or more programs including instructions for causing a computer to execute the algorithms described with reference to the drawings. This process realizes the signal processing method described in each embodiment.

[0200] The program can be stored and provided to the computer using various types of non-transitory computer readable media. The non-transitory computer readable media includes various types of tangible storage media. Examples of the non-transitory computer readable media include magnetic recording media (e.g., flexible disks, magnetic tapes, hard disk drives), magneto-optical recording media (e.g., magneto-optical disks), CD-ROM (Read Only Memory), CD-R, CD-R / W, and semiconductor memory (e.g., mask ROM, PROM (Programmable ROM), EPROM (Erasable PROM), flash ROM, RAM (Random Access Memory)). The program may also be provided to the computer by various types of transitory computer readable media. Examples of the transitory computer readable media include electric signals, optical signals, and electromagnetic waves. The transitory computer readable media can provide the program to the computer via a wired communication path such as an electric wire and an optical fiber, or via a wireless communication path.

[0201] A part or all of the above-described embodiments can be described as, but is not limited to, the following supplementary notes. (Appendix 1) An accident occurrence detection means for detecting the occurrence of an accident from images captured by one or more cameras; An analysis means for analyzing the video and deriving detailed information of a person to be analyzed who is involved in the accident; A decision means for deciding how to deal with the person to be analyzed based on the detailed information; and a notification means for notifying a notification target of the determined handling method. Notification device. (Appendix 2) The notification target detection means detects the notification target that exists in a first area including a location where the accident occurred, The notification means notifies the notification target detected by the notification target detection means of the handling method. 2. A notification device as described in claim 1. (Appendix 3) the notification target detection means detects that a first type of candidate that is a candidate for the notification target exists in the first area, and that a second type of candidate that is a candidate for the notification target exists in a second area that is larger than the first area and includes a location where the accident occurred; the notification means notifies the handling method of at least one of the first type candidate present in the first area detected by the notification object detection means and the second type candidate present in the second area detected by the notification object detection means as the notification object. 3. A notification device as described in claim 2. (Appendix 4) The notification target includes at least one of a person and a vehicle. 4. A notification device according to claim 2 or 3. (Appendix 5) The decision means, as the decision of the countermeasure method, executes at least one of deciding the medical treatment or procedure for the person to be analyzed and identifying the location of a medical device to be used in the medical treatment or procedure that is present in a third area including the location where the accident occurred; The notification means notifies the notification target of at least one of the determined treatment or procedure and the location of the identified medical device in the response method. 5. A notification device according to any one of claims 2 to 4. (Appendix 6) The notification target detection means detects the candidate as the notification target by determining whether the candidate is shown in the video; The notification means notifies a terminal associated with the notification target detected by the notification target detection means of the handling method. 6. A notification device according to any one of claims 2 to 5. (Appendix 7) The information acquisition unit further includes a location information acquisition unit that acquires location information of a terminal from a terminal of the candidate for notification, The notification target detection means detects the notification target based on the location information acquired by the location information acquisition means, The notification means notifies the terminal as the notification target detected by the notification target detection means of the handling method. 6. A notification device according to any one of claims 2 to 5. (Appendix 8) The notification target detection means detects the notification target by identifying one or more base stations that include the location where the accident occurred within a cell of the base station; The notification means notifies the terminal as the notification target detected by the notification target detection means of the handling method. 6. A notification device according to any one of claims 2 to 5. (Appendix 9) The notification subjects include at least medical or emergency institutions, The determining means determines the method of response so as to include at least one of taking measures against the person to be analyzed, requesting dispatch of staff to the location where the accident occurred, requesting acceptance of the person to be analyzed, and preparing for measures; The notification means notifies the institution of the method of dealing with the problem. 3. A notification device according to claim 1 or 2. (Appendix 10) The analysis means identifies the person to be analyzed from among the registered persons based on a result of face authentication using a facial image of the person to be analyzed that appears in the video and facial information of the registered persons, and derives personal information associated with the registered persons as the detailed information; The decision means decides the method of handling based on the personal information. 10. A notification device according to any one of claims 1 to 9. (Appendix 11) The personal information includes at least one of the following: medical history, current medical history, pregnancy status, age, sex, blood type, allergy information, personal number, family medical institution, and emergency contact information. 11. The notification device of claim 10. (Appendix 12) The notification means determines the notification target based on the personal information and notifies the determined notification target. 12. The notification device of claim 10 or 11. (Appendix 13) The detailed information includes at least one of consciousness state, breathing state, bleeding state, fracture state, burn state, impact site, convulsion state, walking state, heart rate state, pulse state, and body temperature state. 13. A notification device according to any one of claims 1 to 12. (Appendix 14) One or more cameras; a notification device connected to the one or more cameras; one or more terminals that receive notifications from the notification device; The notification device includes: An accident occurrence detection means for detecting the occurrence of an accident from the images captured by the one or more cameras; An analysis means for analyzing the video and deriving detailed information of a person to be analyzed who is involved in the accident; A decision means for deciding how to deal with the person to be analyzed based on the detailed information; A notification means for notifying the one or more terminals of the determined solution. Notification system. (Appendix 15) The one or more cameras are provided at least one of a traffic light, a roadside device, an intersection, and a railroad crossing. 14. The notification system described in Appendix 14. (Appendix 16) an accident occurrence detection step of detecting the occurrence of an accident from images captured by one or more cameras; An analysis step of analyzing the video to derive detailed information of a person to be analyzed who is involved in the accident; A decision step of deciding how to deal with the person to be analyzed based on the detailed information; a notification step of notifying a notification target of the determined handling method; A notification method executed by a notification device. (Appendix 17) an accident occurrence detection step of detecting the occurrence of an accident from images captured by one or more cameras; An analysis step of analyzing the video to derive detailed information of a person to be analyzed who is involved in the accident; A decision step of deciding how to deal with the person to be analyzed based on the detailed information; a notification step of notifying a notification target of the determined handling method; A non-transitory computer-readable medium on which a program for causing a computer to execute the program is stored.

[0202] Although the present invention has been described above with reference to the embodiment, the present invention is not limited to the above. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the invention. [Explanation of symbols]

[0203] S1~S4 Notification System 10 Notification device 101 Accident occurrence detection unit 102 Analysis unit 103 Decision Division 104 Notification Division 11 Camera 12 Terminal 20 Camera 201 Photographing unit 202 Transmitting and receiving unit 203 Storage section 21 MEC Server 211 Accident occurrence detection unit 212 Transmitter / receiver unit 213 Storage section 22, 32, 42, 52 Notification Server 221 Notification target detection unit 222 Analysis unit 223 Determination unit 224 Transmitting / receiving unit 225 Storage unit 321 Location information acquisition unit 421 Notification area identification part 23, 33, 43, 53 terminals 231 Output section 232 Transmitting / receiving section 233 Storage section 331 Position detection unit 431 Output control unit 90 Information processing equipment 91 Signal processing circuit 92 Processor 93 Memory

Claims

1. A detection means for detecting the occurrence of an event from images captured by one or more cameras; an analysis means for analyzing the video and deriving detailed information of a person to be analyzed who is involved in the event; A decision means for deciding how to deal with the person to be analyzed based on the detailed information; a notification means for notifying a notification target of the determined handling method, The analysis means identifies the person to be analyzed from among the registered persons based on a result of face authentication using a facial image of the person to be analyzed that appears in the video and facial information of the registered persons, and derives personal information associated with the registered persons as the detailed information; The decision means decides the method of handling based on the personal information. Notification device.

2. The personal information includes at least one of the following: medical history, current medical history, pregnancy status, age, sex, blood type, allergy information, personal number, family medical institution, and emergency contact information. The notification device of claim 1 .

3. The notification means determines the notification target based on the personal information, and notifies the determined notification target of the determined handling method.

3. A notification device according to claim 1 or 2.

4. The detailed information includes at least one of consciousness state, breathing state, bleeding state, fracture state, burn state, impact site, convulsion state, walking state, heart rate state, pulse state, and body temperature state. A notification device according to any one of claims 1 to 3.

5. The analysis means identifies the person to be analyzed based on an authentication result obtained by combining two or more biometric authentication techniques. A notification device according to any one of claims 1 to 4.

6. The one or more cameras are provided in a vehicle. A notification device according to any one of claims 1 to 5.

7. The notification object detection means detects the notification object present in a first area including a location where the event has occurred, The notification means notifies the notification target detected by the notification target detection means of the handling method. A notification device according to any one of claims 1 to 6.

8. One or more cameras; a notification device connected to the one or more cameras; one or more terminals that receive notifications from the notification device; The notification device includes: A detection means for detecting the occurrence of an event from images captured by the one or more cameras; an analysis means for analyzing the video and deriving detailed information of a person to be analyzed who is involved in the event; A decision means for deciding how to deal with the person to be analyzed based on the detailed information; a notification means for notifying the one or more terminals of the determined handling method, The analysis means identifies the person to be analyzed from among the registered persons based on a result of face authentication using a facial image of the person to be analyzed that appears in the video and facial information of the registered persons, and derives personal information associated with the registered persons as the detailed information; The decision means decides the method of handling based on the personal information. Notification system.

9. Detecting the occurrence of an event from images captured by one or more cameras; Analyzing the video to derive detailed information of a person to be analyzed who is involved in the event; Deciding how to deal with the person to be analyzed based on the detailed information; notifying the notification target of the determined countermeasure; Based on a result of face authentication using a facial image of the person to be analyzed that appears in the video and facial information of the registrants, the person to be analyzed is identified from among the registrants, and personal information associated with the registrants is derived as the detailed information; determining the method of dealing with the matter based on the personal information; A notification method executed by a notification device.

10. Detecting the occurrence of an event from images captured by one or more cameras; Analyzing the video to derive detailed information of a person to be analyzed who is involved in the event; Deciding how to deal with the person to be analyzed based on the detailed information; notifying the notification target of the determined countermeasure; Based on a result of face authentication using a facial image of the person to be analyzed that appears in the video and facial information of the registrants, the person to be analyzed is identified from among the registrants, and personal information associated with the registrants is derived as the detailed information; determining the method of dealing with the matter based on the personal information; A program that causes a computer to do something.

Images