Information processing device, information processing method, and information processing program

Abstract

To provide an information processing device capable of further improving collision prevention between a vehicle and a pedestrian, an information processing method, and an information processing program.SOLUTION: An information processing device comprises an acquisition unit, a prediction unit, and a notification unit. The acquisition unit acquires sensor information, which is information on a pedestrian detected by a sensor. The prediction unit predicts the movement of the pedestrian on the basis of the sensor information acquired by the acquisition unit. The notification unit notifies a traffic-related device, which is a device on traffic around the pedestrian, of movement-related information, which is information on the movement of the pedestrian predicated by the prediction unit.SELECTED DRAWING: Figure 3

Description

[Technical Field]

[0001] The present invention relates to an information processing device, an information processing method, and an information processing program. [Background technology]

[0002] Conventionally, there are known techniques for notifying a vehicle driver of the presence of a pedestrian in order to prevent a collision between the vehicle and the pedestrian. For example, Patent Document 1 discloses a technique for creating area data representing the presence of a person based on a signal transmitted from a mobile device, and transmitting distribution data corresponding to the area data to an in-vehicle device mounted on the vehicle. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2014-071656 Summary of the Invention [Problem to be solved by the invention]

[0004] However, the above-mentioned conventional technology only allows the driver of a vehicle to recognize the presence of people, and there is room for further improvement in terms of preventing collisions between vehicles and pedestrians.

[0005] The present application has been made in consideration of the above, and aims to provide an information processing device, an information processing method, and an information processing program that can further improve collision prevention between vehicles and pedestrians. [Means for solving the problem]

[0006] The information processing device according to the present application includes an acquisition unit, a prediction unit, and a notification unit. The acquisition unit acquires sensor information, which is information about a pedestrian detected by a sensor. The prediction unit predicts the movement of the pedestrian based on the sensor information acquired by the acquisition unit. The notification unit notifies a traffic-related device, which is a device related to traffic around the pedestrian, of movement-related information, which is information about the movement of the pedestrian predicted by the prediction unit. [Effects of the Invention]

[0007] According to one aspect of the embodiment, it is possible to achieve an effect of further improving the prevention of collisions between vehicles and pedestrians. [Brief explanation of the drawings]

[0008] [Figure 1] FIG. 1 is a diagram illustrating an example of information processing according to an embodiment. [Figure 2] FIG. 2 is a diagram illustrating an example of the configuration of an information processing system according to the embodiment. [Figure 3] FIG. 3 is a diagram illustrating an example of the configuration of the information processing device according to the embodiment. [Figure 4] FIG. 4 is a diagram illustrating an example of a pedestrian information table stored in the pedestrian information storage unit according to the embodiment. [Figure 5] FIG. 5 is a diagram illustrating an example of an occupant information table stored in the occupant information storage unit according to the embodiment. [Figure 6] FIG. 6 is a diagram illustrating an example of identification and control of a control target in the control device according to the embodiment. [Figure 7] FIG. 7 is a flowchart showing an example of information processing by the processing unit of the information processing device according to the embodiment. [Figure 8] FIG. 8 is a hardware configuration diagram illustrating an example of a computer that realizes the functions of the information processing device according to the embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0009] Hereinafter, modes for implementing an information processing device, an information processing method, and an information processing program according to the present application (hereinafter referred to as "embodiments") will be described in detail with reference to the drawings. Note that the information processing device, the information processing method, and the information processing program according to the present application are not limited to these embodiments. Furthermore, the respective embodiments can be appropriately combined within the scope of not causing any contradiction in the processing content. Furthermore, the same components in the following embodiments will be assigned the same reference numerals, and redundant explanations will be omitted.

[0010] [1. An example of information processing] First, an example of information processing according to the embodiment will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of information processing according to the embodiment, which is executed by an information processing device 1.

[0011] 1 provides various services via a network such as the Internet. For example, the information processing device 1 provides an accident prevention support service that notifies information about the movement of a pedestrian P to traffic-related devices that are devices related to traffic around the pedestrian P.

[0012] The traffic-related devices are, for example, control devices and vehicles. The control devices are devices that control traffic lights, electronic signs, etc. In FIG. 1, the traffic-related devices include a control device 6 and a plurality of vehicles 9. The control device 6 can control a plurality of traffic lights 7, a plurality of electronic traffic signs 8, etc.

[0013] The traffic light 7 is a traffic signal that emits signals indicating permission to proceed, instructions to stop, etc. A signal indicating permission to proceed is, for example, a green light, and a signal indicating an instruction to stop is, for example, a yellow light or a red light. The traffic light 7 can also emit a signal indicating an arrow. A signal indicating an arrow indicates permission to proceed in the direction of the arrow. The traffic light 7 changes the signal it emits under the control of the control device 6.

[0014] The electronic traffic sign 8 includes, for example, a display such as an LED (Light-Emitting Diode) display for displaying traffic signs, and changes the traffic signs it displays under control from the control device 6. Traffic signs displayed by the electronic traffic sign 8 include, for example, no entry, one-way street, no right turn, no U-turn, etc., but are not limited to these examples.

[0015] In the traffic safety support service, the information processing device 1 repeatedly acquires sensor information, which is information about a pedestrian P detected by a plurality of sensors (step S1). The plurality of sensors may be, for example, a plurality of sensors installed around the roadway (hereinafter, sometimes referred to as installed sensors), or sensors included in devices carried by each of a plurality of pedestrians P (hereinafter, sometimes referred to as portable sensors). Each of the installed sensors and the portable sensors is an example of a sensor that detects and outputs sensor information, which is information about the pedestrian P.

[0016] The installed sensor 5 is, for example, an image sensor (camera) that captures an image of the pedestrian P, a human presence sensor (infrared sensor or radar sensor) that detects the pedestrian P, or an IC tag (Integrated Circuit) detector. The installed sensor 5 has an IC tag communication unit, and acquires information (for example, identification information of the IC tag 4) carried by the pedestrian P within the detection range of the IC tag communication unit.

[0017] The installed sensors 5 are installed, for example, on traffic facilities such as traffic lights 7 and traffic signs (including electronic traffic signs 8), buildings and utility poles around the roadway, vehicles 9 traveling on the roadway, etc. The installed sensors 5 installed on the vehicle 9 are, for example, sensors included in a drive recorder installed on the vehicle 9 or sensors attached inside the vehicle 9 as sensors for the vehicle 9.

[0018] The installed sensor 5 transmits information about an image captured by the image sensor as sensor information to the information processing device 1, and transmits information about a pedestrian P detected by the human presence sensor as sensor information to the information processing device 1. The installed sensor 5 also transmits tag information, which is information about the IC tag 4 acquired by the IC tag communication unit, to the information processing device 1 as sensor information.

[0019] The portable sensor is, for example, a sensor included in the portable terminal 2, a GPS (Global Positioning Satellite) transmitter, etc. The portable terminal 2 is, for example, a smartphone, a tablet PC (Personal Computer), a wearable device, etc., but is not limited to these examples. The wearable device is, for example, a see-through head-mounted display, a smart watch, etc., but is not limited to these examples.

[0020] The mobile terminal 2 includes, but is not limited to, for example, a positioning sensor (position sensor), an acceleration sensor, a gyro sensor, an image sensor, a geomagnetic sensor, etc. The mobile terminal 2 transmits information detected by each sensor included in the mobile terminal 2 to the information processing device 1 as sensor information.

[0021] The GPS transmitter 3 has a positioning sensor, and transmits information indicating the position of the GPS transmitter 3 detected by the positioning sensor as sensor information to the information processing device 1. The position of the GPS transmitter 3 is, for example, information indicating the latitude and longitude of the GPS transmitter 3.

[0022] Next, the information processing device 1 predicts the movement of each pedestrian P based on the sensor information of the multiple sensors acquired in step S1 (step S2). The information processing device 1 predicts the movement of the pedestrian P in real time based on the sensor information of the multiple sensors acquired in step S1, for example.

[0023] For example, based on the sensor information of the sensors acquired in step S1, the information processing device 1 predicts in real time the movement of the pedestrian P as the movement of the pedestrian P. The information processing device 1 has map information that defines roadways, sidewalks, etc., and predicts in real time the movement of the pedestrian P as the movement of the pedestrian P based on the map information and the sensor information of the sensors acquired in step S1.

[0024] Examples of movement patterns include, but are not limited to, pedestrian P running out onto the roadway, pedestrian P stepping out onto the roadway, pedestrian P crossing the roadway, and pedestrian P moving along the sidewalk.

[0025] The movement of the pedestrian P predicted by the information processing device 1 is, for example, the movement of the pedestrian P from the present or a certain point in the future to a predetermined period (for example, 5 seconds or 10 seconds later). The information processing device 1 can predict the movement of the pedestrian P in real time based on, for example, a comparison result between a movement state pattern predetermined for each type of movement state and the movement state of the pedestrian P immediately before.

[0026] The information processing device 1 can predict that the pedestrian P will run out into the roadway, for example, when the movement state (movement position, movement speed, etc.) of the pedestrian P during a predetermined period (for example, the period from 5 seconds ago to the present) is a predetermined first movement state.

[0027] Furthermore, the information processing device 1 can predict that the pedestrian P will step out onto the roadway, for example, when the movement state (movement position, movement speed, etc.) of the pedestrian P during a predetermined period (for example, the period from 5 seconds ago to the present) is a predetermined second movement state.

[0028] Furthermore, the information processing device 1 can predict that pedestrian P will cross the roadway, for example, when the movement state (movement position, movement speed, etc.) of pedestrian P during a predetermined period (for example, the period from 5 seconds ago to the present) is a predetermined third movement state.

[0029] The information processing device 1 can also predict the movement of pedestrian P in real time as the movement of pedestrian P, for example, using a learning model that inputs information indicating the most recent movement state of pedestrian P and outputs information indicating the movement of pedestrian P from a certain point in time in the present or the future up to a predetermined period of time (for example, 5 seconds or 10 seconds later).

[0030] The learning model is generated by machine learning using learning data including, for example, information indicating the movement state of the pedestrian P immediately before a first specific time point and information indicating the movement pattern of the pedestrian P immediately after a second specific time point. The second specific time point is the same as the first specific time point, but may be a time point later than the first specific time point.

[0031] The learning model is, for example, a model that outputs a score for each type of movement behavior. The types of movement behavior include, for example, a pedestrian P running out onto the roadway, a pedestrian P stepping out onto the roadway, a pedestrian P crossing the roadway, a pedestrian P moving along the sidewalk, etc. The information processing device 1 predicts, as the movement behavior of the pedestrian P, a type of movement behavior that corresponds to a score equal to or greater than a threshold value among the scores for each type of movement behavior output from the learning model.

[0032] Furthermore, the information processing device 1 can also determine in real time the movement of the pedestrian P. For example, the information processing device 1 determines in real time the movement pattern of the pedestrian P as the movement of the pedestrian P based on the sensor information of the multiple sensors acquired in step S1.

[0033] Furthermore, the information processing device 1 can determine the past movements of the multiple pedestrians P based on the sensor information of the multiple sensors previously acquired in step S1. The information processing device 1 can also define a geofence based on the past people flow, which is the determined past movements of the multiple pedestrians P.

[0034] For example, based on past pedestrian flow, the information processing device 1 defines the boundary between an area where pedestrian P normally moves (hereinafter, may be referred to as a normal movement area) and an area where pedestrian P normally does not move (hereinafter, may be referred to as an abnormal movement area) as a geofence.

[0035] In this case, the information processing device 1 predicts whether or not the pedestrian P will cross the geofence based on the sensor information of the multiple sensors acquired in step S1. For example, the information processing device 1 determines that the pedestrian P who is predicted to move from a normal movement area to an abnormal movement area is the pedestrian P who will cross the geofence.

[0036] As a result, when a pedestrian P is walking on a road where the distinction between the roadway and the sidewalk is unclear, the information processing device 1 can determine areas on the road that are customarily used as sidewalks, and can determine whether the pedestrian P has run out onto the roadway, whether the pedestrian P has stepped onto the roadway, or whether the pedestrian P has crossed the roadway.

[0037] The above-mentioned normal movement area is, for example, an area where the movement probability is equal to or greater than a first threshold (for example, 99%), and the non-normal movement area is an area other than the normal movement area, but is not limited to such examples. For example, the normal movement area may be an area where a pedestrian P moves who has not been predicted or determined to clearly run out into the roadway, or may be an area where a pedestrian P with a specific attribute moves.

[0038] Furthermore, the geofence defined by the information processing device 1 may be a geofence for each time period, a geofence for each attribute of pedestrian P, or a geofence for each time period and each attribute of pedestrian P.

[0039] Furthermore, the information processing device 1 can also determine the movement pattern of the pedestrian P as the movement of the pedestrian P in real time based on the sensor information of the multiple sensors acquired in step S1 and the geofence described above.

[0040] Next, the information processing device 1 generates movement-related information, which is information related to the movement of the pedestrian P predicted in step S2 (step S3). For example, the information processing device 1 generates the movement-related information when the movement of the pedestrian P predicted in step S2 is a specific movement pattern.

[0041] The types of specific movement patterns are, for example, a pedestrian P running out onto the roadway, a pedestrian P stepping out onto the roadway, a pedestrian P crossing the roadway, etc. The movement-related information includes information indicating the type of specific movement pattern, information indicating the position of a pedestrian P who is predicted to have the specific movement pattern, information indicating the attributes of a pedestrian P who is predicted to have the specific movement pattern, etc.

[0042] Furthermore, the information processing device 1 generates warning information indicating locations and contents requiring caution, based on past people flows, which are past movements of the plurality of pedestrians P determined as described above (step S4).

[0043] For example, based on past pedestrian flows, which are the past movements of multiple pedestrians P determined as described above, the information processing device 1 identifies, as places requiring caution, locations where pedestrians P may jump out onto the roadway, locations where pedestrians P may step out onto the roadway, locations where pedestrians P may cross the roadway, etc. Then, the information processing device 1 generates caution information indicating the identified places requiring caution and their contents.

[0044] For example, when the information processing device 1 identifies a location where a pedestrian P has run out into the roadway, it generates warning information in which the information indicating the location where the pedestrian P has run out into the roadway is treated as information indicating a location where caution is required, and the information indicating the pedestrian P's run out into the roadway is treated as information indicating content that requires caution.

[0045] For example, when the information processing device 1 identifies a location where a pedestrian P is crossing the roadway, it generates warning information in which the information indicating the location where the pedestrian P is crossing the roadway is treated as information indicating a location where caution is required, and the information indicating the pedestrian P's crossing of the roadway is treated as information indicating content that requires caution.

[0046] Furthermore, based on the past pedestrian flow, which is the past movements of multiple pedestrians P determined as described above, the information processing device 1 identifies, as places requiring caution, locations where the frequency of pedestrians P stepping out onto the roadway is equal to or greater than a threshold Th1, locations where the frequency of pedestrians P stepping out onto the roadway is equal to or greater than a threshold Th2, locations where the frequency of pedestrians P crossing the roadway is equal to or greater than a threshold Th3, etc. The frequency is a frequency per unit of time, but may also be a number per number of pedestrians P, etc.

[0047] Furthermore, the information processing device 1 can generate warning information for each time period, or for each attribute of the driver of the vehicle 9. For example, the information processing device 1 identifies places requiring attention for each time period. Then, the information processing device 1 generates information indicating the places requiring attention identified for each time period and their contents as warning information for each time period.

[0048] Furthermore, the information processing device 1 changes at least one of the thresholds Th1, Th2, and Th3 described above for each attribute of the driver of the vehicle 9, and identifies places requiring attention for each attribute of the driver of the vehicle 9. Then, the information processing device 1 generates information indicating the places requiring attention identified for each attribute of the driver of the vehicle 9 and their contents as attention information for each attribute of the driver of the vehicle 9.

[0049] For example, the information processing device 1 identifies a location requiring caution by increasing at least one of the thresholds Th1, Th2, and Th3 as the age or generation of the driver of the vehicle 9 increases. Furthermore, for example, when the gender of the driver of the vehicle 9 is of a specific gender, the information processing device 1 identifies a location requiring caution by increasing at least one of the thresholds Th1, Th2, and Th3 compared to when the gender of the driver of the vehicle 9 is not of a specific gender.

[0050] The information processing device 1 can generate warning information for each combination of the contents of a plurality of attribute items, such as, but not limited to, teenage male, teenage female, ..., 80s male, 80s female, etc.

[0051] Next, the information processing device 1 notifies the movement-related information generated in step S3 to a traffic-related device, which is a device related to traffic around the pedestrian P (step S5). For example, the information processing device 1 notifies the movement-related information to the control device 6 as a traffic-related device, and causes the control device 6 to change the state of the traffic light 7.

[0052] When the control device 6 acquires the movement-related information notified from the information processing device 1, the control device 6 identifies a traffic light 7 to be controlled from among the multiple traffic lights 7 based on the movement-related information, and controls the identified traffic light 7. Hereinafter, the traffic light 7 to be controlled may be referred to as a target traffic light.

[0053] For example, if the movement pattern of pedestrian P indicated in the movement-related information is pedestrian P running out into the roadway, the control device 6 identifies the traffic light 7 located in front of the pedestrian P's running out position included in the movement-related information as the target traffic light.

[0054] Then, when the signal of the target traffic light, which is traffic light 7 identified as the target traffic light, is a signal indicating permission to proceed, the control device 6 changes the signal of the target traffic light to a signal indicating a stop instruction. Also, when the signal of the target traffic light, which is traffic light 7 identified as the target traffic light, is a signal indicating a stop instruction, the control device 6 maintains the signal of the target traffic light as a signal indicating a stop instruction.

[0055] In addition, when the control device 6 acquires the movement-related information notified from the information processing device 1, it can identify the electronic traffic sign 8 to be controlled from among the multiple electronic traffic signs 8 based on the movement-related information, and control the identified electronic traffic sign 8.

[0056] For example, when the movement mode of pedestrian P indicated in the movement-related information is that pedestrian P has stepped onto the roadway, the control device 6 identifies, as a control target, an electronic traffic sign 8 at the entrance to the roadway at the position of pedestrian P included in the movement-related information. Then, the control device 6 changes the display of the target electronic traffic sign, which is the electronic traffic sign 8 identified as the control target, to a no entry display.

[0057] Furthermore, when the movement mode of the pedestrian P indicated in the movement-related information is that the pedestrian P has stepped onto the roadway, the control device 6 identifies the electronic traffic sign 8 in front of the position where the pedestrian P has stepped out, which is included in the movement-related information, as the target electronic traffic sign. Then, the control device 6 changes the speed limit indicated by the target electronic traffic sign to a speed lower than normal.

[0058] Furthermore, the information processing device 1 identifies a vehicle 9 around the pedestrian P included in the movement-related information as a vehicle to be controlled, and notifies the identified vehicle to be controlled of the movement-related information to change the traveling state of the vehicle 9. For example, the information processing device 1 notifies the vehicle to be controlled of the movement-related information to stop the vehicle to be controlled or reduce its speed. The vehicle to be controlled has an on-board device that receives the movement-related information and controls the vehicle to be controlled based on the received movement-related information, and stops the vehicle to be controlled or reduces its speed based on the received movement-related information.

[0059] Furthermore, the information processing device 1 notifies the notification target of the warning information generated in step S4 (step S6). The notification target in step S6 is the vehicle 9 or the pedestrian P that is present in an area requiring attention.

[0060] For example, the information processing device 1 can notify the vehicles 9 that are in the area requiring attention of the warning information by transmitting the warning information as movement-related information to the vehicles 9 that are in the area requiring attention. The area requiring attention is, for example, the area around the pedestrian P included in the movement-related information.

[0061] The vehicle 9 has an on-board device that receives and displays the movement-related information, and displays the warning information received as the movement-related information, thereby enabling the driver of the vehicle 9 to know that there are places or contents around the vehicle 9 that require attention.

[0062] Furthermore, the information processing device 1 notifies the pedestrian P who is present in the area where caution is required as warning information. For example, the information processing device 1 notifies the pedestrian P who is present in the area where caution is required of the warning information by transmitting the warning information to the mobile terminal 2 of the pedestrian P who is present in the area where caution is required.

[0063] The mobile terminal 2 of the pedestrian P receives the warning information and displays the received warning information. This allows the pedestrian P, who is in an area requiring caution, to know that there are places or contents requiring caution around the pedestrian P. Therefore, the information processing device 1 can issue a warning to the pedestrian P, who is in an area requiring caution.

[0064] In this way, the information processing device 1 predicts the movement of the pedestrian P based on sensor information, which is information about the pedestrian P detected by the sensor, and notifies the movement-related information, which is information about the predicted movement of the pedestrian P, to a traffic-related device, which is a device related to traffic around the pedestrian P. This allows the information processing device 1 to further improve the prevention of collisions between the vehicle 9 and the pedestrian P.

[0065] Below, we will explain in detail the configuration of an information processing system that performs such processing, including an information processing device 1, a mobile terminal 2, a GPS transmitter 3, an IC tag 4, an installed sensor 5, a control device 6, a traffic light 7, an electronic traffic sign 8, and a vehicle 9.

[0066] [2. Information Processing System Configuration] Next, FIG. 2 is a diagram showing an example of the configuration of an information processing system including the information processing device 1 according to the embodiment.

[0067] 2 is a diagram showing an example of the configuration of an information processing system according to an embodiment. As shown in Fig. 2, the information processing system 100 according to the embodiment includes an information processing device 1, a plurality of mobile terminals 2, a plurality of GPS transmitters 3, a plurality of IC tags 4, a plurality of installed sensors 5, a control device 6, a plurality of traffic lights 7, a plurality of electronic traffic signs 8, and a plurality of vehicles 9.

[0068] The information processing device 1 provides an accident prevention support service. The information processing device 1 can also provide various online services such as a web search service, a schedule management service, a route guidance service, a route information providing service, a video distribution service, a music distribution service, a map information providing service, and an e-commerce service.

[0069] Each of the multiple mobile terminals 2 is used by a different pedestrian P. The mobile terminals 2 are, for example, a smartphone, a tablet terminal, or a wearable device. The wearable device is, for example, a see-through head-mounted display, a smart watch, or the like, but is not limited to these examples. An application program for an accident prevention support service (hereinafter, sometimes referred to as an accident prevention support app) is installed on the mobile terminal 2.

[0070] The information processing device 1, the mobile terminal 2, the GPS transmitter 3, the installed sensor 5, the control device 6, and the vehicle 9 are connected to each other via a network N in a wired or wireless manner so as to be able to communicate with each other.

[0071] 2 may include a plurality of information processing devices 1. The network N is, for example, a LAN (Local Area Network) or a WAN (Wide Area Network) such as the Internet.

[0072] Each of the mobile terminal 2, GPS transmitter 3, installed sensor 5, control device 6, and vehicle 9 can connect to the network N via a wireless communication network such as LTE (Long Term Evolution), 4G (4th Generation), or 5G (5th Generation: 5th generation mobile communication system), or via short-range wireless communication such as Bluetooth (registered trademark) or wireless LAN, and can communicate with the information processing device 1.

[0073] 3. Configuration of Information Processing Device 1 3 is a diagram showing an example of the configuration of the information processing device 1 according to the embodiment. As shown in FIG. 3, the information processing device 1 includes a communication unit 10, a storage unit 11, and a processing unit 12.

[0074] [3.1. Communication Unit 10] The communication unit 10 is realized by, for example, a network interface card (NIC), etc. The communication unit 10 is connected to a network N by wire or wirelessly, and transmits and receives information to and from each of the mobile terminal 2, the GPS transmitter 3, the installed sensor 5, the control device 6, and the vehicle 9 via the network N.

[0075] [3.2. Storage section 11] The storage unit 11 is realized by, for example, a semiconductor memory element such as a random access memory (RAM) or a flash memory, or a storage device such as a hard disk or an optical disk. The storage unit 11 has a pedestrian information storage unit 20, an occupant information storage unit 21, and a road-related information storage unit 22.

[0076] 3.2.1. Pedestrian Information Storage Unit 20 The pedestrian information storage unit 20 stores various types of information related to the pedestrian P. Fig. 4 is a diagram showing an example of a pedestrian information table stored in the pedestrian information storage unit 20 according to the embodiment.

[0077] In the example shown in FIG. 4, the pedestrian information table stored in the pedestrian information storage unit 20 includes information on items such as "Pedestrian ID (Identifier)," "Attribute Information," "Sensor Information History," "Caution Level," and "Setting Information."

[0078] The "pedestrian ID" is an identifier that identifies a pedestrian P, and is information that is assigned to each pedestrian P. The "attribute information" is attribute information that indicates the attributes of the pedestrian P associated with the "pedestrian ID." The attributes of the pedestrian P include, for example, demographic attributes and psychographic attributes. The demographic attributes are demographic attributes, and include multiple attribute items such as age, gender, occupation, place of residence, annual income, and family composition.

[0079] Psychographic attributes are psychological attributes and include, for example, multiple attribute items related to lifestyle, values, interests, etc. For example, each of the multiple attribute items in the psychographic attributes is an object of interest to pedestrian P, such as cars, clothes, travel, games, camping, motorcycles, trains, home appliances, or computers.

[0080] The "sensor information history" is a history of sensor information transmitted from the mobile terminal 2 of pedestrian P associated with the "pedestrian ID," and includes information detected by one or more sensors of the mobile terminal 2, information detected by a positioning sensor included in the GPS transmitter 3, an image of a person detected by an installed sensor 5, the person's position, or information indicating the position of an IC tag.

[0081] The "attention level" is information indicating the attention level of the pedestrian P associated with the "pedestrian ID", and is determined by the processing unit 12 based on the sensor information history and set in the pedestrian information table.

[0082] The "setting information" includes, for example, information set by the pedestrian P associated with the "pedestrian ID" as the account of the pedestrian P in the accident prevention support service and the destination of the warning information.

[0083] 3.2.2. Occupant information storage unit 21 The occupant information storage unit 21 stores various types of information related to the occupants of the vehicle 9. Fig. 5 is a diagram showing an example of an occupant information table stored in the occupant information storage unit 21 according to the embodiment.

[0084] In the example shown in FIG. 5, the occupant information table stored in the occupant information storage unit 21 includes information items such as "occupant ID," "attribute information," "vehicle information," and "notification type information." The "occupant ID" is an identifier that identifies an occupant, and is information assigned to each occupant. The occupant is the driver of the vehicle 9, but may also be a passenger.

[0085] "Attribute information" is attribute information indicating the attributes of the occupant associated with the "occupant ID." The attributes of the occupant are the same as the attributes of the pedestrian P described above. "Vehicle information" is information about the vehicle 9 that the occupant is driving or riding in, and includes information for accessing the vehicle 9 that the occupant is driving or riding in.

[0086] "Notification type information" is information indicating the type of information to be notified to the vehicle 9 of the occupant associated with the "occupant ID", for example, information indicating the type of movement-related information or the type of warning information.

[0087] 3.2.3. Road-related information storage unit 22 The road-related information storage unit 22 stores road-related information, which is various information related to traffic, including the position of the roadway, the position and direction of lanes, the position of sidewalks, the position and identification information of installed sensors 5, the position and identification information of traffic lights 7, the position and identification information of electronic traffic signs 8, the position of crosswalks, the position of intersections, the position and display content of traffic signs, etc.

[0088] [3.3. Processing Unit 12] The processing unit 12 is a controller, and is realized, for example, by a CPU (Central Processing Unit) or an MPU (Micro Processing Unit) using RAM as a work area to execute various programs stored in a storage device inside the information processing device 1. The processing unit 12 may be partially or entirely realized by an integrated circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field Programmable Gate Array).

[0089] 3, the processing unit 12 has an acquisition unit 30, a prediction unit 31, a determination unit 32, a definition unit 33, a generation unit 34, and a notification unit 35, and realizes or executes the functions and actions of information processing described below. Note that the internal configuration of the processing unit 12 is not limited to the configuration shown in FIG. 3, and may be any other configuration that performs the information processing described below.

[0090] [3.3.1. Acquisition part 30] The acquisition unit 30 acquires various information from an external information processing device, a mobile terminal 2, a GPS transmitter 3, a stationary sensor 5, etc. via the communication unit 10, and stores the acquired information in the storage unit 11.

[0091] For example, the acquisition unit 30 acquires information about the pedestrian P from an external information processing device or the mobile terminal 2 via the communication unit 10, and adds the acquired information about the pedestrian P to the pedestrian information table in the pedestrian information storage unit 20. The information about the pedestrian P includes, for example, attribute information, sensor information, attention level, setting information, and the like.

[0092] In addition, the acquisition unit 30 acquires information about the occupant from an external information processing device or an on-board device of the vehicle 9 via the communication unit 10, and adds the acquired information about the occupant to an occupant information table stored in the occupant information storage unit 21.

[0093] The acquisition unit 30 also acquires various types of information from the storage unit 11. For example, the acquisition unit 30 acquires information about the pedestrian P from the pedestrian information storage unit 20 or the like. The information about the pedestrian P acquired by the acquisition unit 30 includes, for example, part or all of at least one of the above-mentioned attribute information, sensor information history, attention level information, and setting information. The sensor information history is, for example, a history of sensor information that is information about the pedestrian P detected by a sensor.

[0094] The acquisition unit 30 also acquires occupant information, which is information about occupants, from the occupant information storage unit 21, etc. The occupant information acquired by the acquisition unit 30 includes, for example, part or all of at least one of the above-described attribute information, vehicle information, and notification type information.

[0095] The acquisition unit 30 also acquires road-related information from the road-related information storage unit 22, etc. The road-related information acquired by the acquisition unit 30 includes, for example, part or all of at least one of the above-mentioned information such as the position of the roadway, the position and direction of the lane, the position of the sidewalk, the position and identification information of the installed sensor 5, the position and identification information of the traffic light 7, the position and identification information of the electronic traffic sign 8, the position of the crosswalk, the position of the intersection, and the position and display content of the traffic sign.

[0096] 3.3.2. Prediction Unit 31 The prediction unit 31 predicts the movement of the pedestrian P based on the sensor information acquired by the acquisition unit 30. For example, the prediction unit 31 predicts the movement of the pedestrian P based on the sensor information acquired by the acquisition unit 30 and road-related information.

[0097] The prediction unit 31 predicts at least one of the following as the movement of the pedestrian P: the pedestrian P running out onto the roadway, the pedestrian P stepping out onto the roadway, and the pedestrian P crossing the roadway. For example, the prediction unit 31 predicts the movement of the pedestrian P in real time based on the sensor information of the multiple sensors acquired by the acquisition unit 30.

[0098] For example, the prediction unit 31 predicts in real time the movement of the pedestrian P based on the sensor information of the sensor acquired by the acquisition unit 30. The movement includes, for example, the pedestrian P running out onto the roadway, the pedestrian P stepping out onto the roadway, the pedestrian P crossing the roadway, the pedestrian P moving along the sidewalk, and the like.

[0099] The movement of the pedestrian P predicted by the prediction unit 31 is, for example, the movement of the pedestrian P from the present or a certain point in the future to a predetermined period (for example, 5 seconds or 10 seconds later). The prediction unit 31 can predict the movement mode of the pedestrian P as the movement of the pedestrian P in real time, for example, based on the result of comparing a movement state pattern predetermined for each type of movement mode with the movement state of the pedestrian P immediately before.

[0100] The prediction unit 31 can predict that pedestrian P will run out into the roadway, for example, when the movement state (movement position, movement speed, etc.) of pedestrian P during a predetermined period (for example, the period from 5 seconds ago to the present) is a predetermined first movement state.

[0101] In addition, the prediction unit 31 can predict that the pedestrian P will step out onto the roadway, for example, when the movement state (movement position, movement speed, etc.) of the pedestrian P during a predetermined period (for example, the period from 5 seconds ago to the present) is a predetermined second movement state.

[0102] In addition, the prediction unit 31 can predict that pedestrian P will cross the roadway, for example, when the movement state (movement position, movement speed, etc.) of pedestrian P during a predetermined period (for example, the period from 5 seconds ago to the present) is a predetermined third movement state.

[0103] The prediction unit 31 can also predict the movement of pedestrian P in real time as the movement of pedestrian P, for example, using a learning model that takes as input information indicating the most recent movement state of pedestrian P and outputs information indicating the movement of pedestrian P from the present or a certain point in the future up to a predetermined period of time (for example, 5 seconds or 10 seconds later).

[0104] The learning model is generated by machine learning using learning data including, for example, information indicating the movement state of the pedestrian P immediately before a first specific time point and information indicating the movement pattern of the pedestrian P immediately after a second specific time point. The second specific time point is the same as the first specific time point, but may be a time point later than the first specific time point.

[0105] The learning model is, for example, a model that outputs a score for each type of movement behavior. The types of movement behavior include, for example, a pedestrian P running out onto the roadway, a pedestrian P stepping out onto the roadway, a pedestrian P crossing the roadway, a pedestrian P moving along the sidewalk, etc. The prediction unit 31 predicts, as the movement behavior of the pedestrian P, a type of movement behavior that corresponds to a score equal to or greater than a threshold value among the scores for each type of movement behavior output from the learning model.

[0106] The learning model is generated by machine learning using a neural network such as a convolutional neural network, a recurrent neural network, or a deep neural network, but is not limited to these examples. For example, instead of a neural network, the learning model may be generated using machine learning using a learning algorithm such as a gradient boosting decision tree (GBDT), linear regression, or logistic regression.

[0107] The prediction unit 31 can also determine in real time the movement of the pedestrian P. For example, the prediction unit 31 determines in real time the movement pattern of the pedestrian P as the movement of the pedestrian P based on the sensor information of the multiple sensors acquired by the acquisition unit 30.

[0108] Furthermore, the prediction unit 31 can also predict the movement pattern of the pedestrian P as the movement of the pedestrian P, using the geofence defined by the definition unit 33. For example, the prediction unit 31 predicts whether the pedestrian P will cross the geofence defined by the definition unit 33. For example, the definition unit 33 determines that the pedestrian P, whose movement pattern is predicted to be from a normal movement area to an abnormal movement area, is the pedestrian P who will cross the geofence.

[0109] As a result, the prediction unit 31 can determine whether the pedestrian P runs out onto the roadway, whether the pedestrian P steps out onto the roadway, whether the pedestrian P crosses the roadway, etc., even when the pedestrian P is walking on a road where the distinction between the roadway and the sidewalk is unclear.

[0110] [3.3.3. Judgment unit 32] The determination unit 32 determines a past people flow, which is the past movements of multiple pedestrians P, based on the sensor information acquired by the acquisition unit 30. The people flow determined by the determination unit 32 may be represented, for example, by the positions of multiple pedestrians P for each predetermined time period, by the movement trajectories of multiple pedestrians P for each predetermined period, or by the average movement trajectory of pedestrians P for each predetermined period.

[0111] The determination unit 32 can, for example, determine past pedestrian flow for each time period, which is the past movements of multiple pedestrians P for each time period, or determine past pedestrian flow for each attribute of pedestrians P, which is the past movements of multiple pedestrians P for each attribute of pedestrians P. Furthermore, the determination unit 32 can also determine past pedestrian flow for each time period and each attribute of pedestrians P, for example.

[0112] The determination unit 32 can also determine past pedestrian flows, which are the past movements of multiple pedestrians P who have previously exhibited the above-described specific movement patterns. In this case, the determination unit 32 determines past pedestrian flows, which are the past movements of multiple pedestrians P who have previously stepped out onto the roadway, or past pedestrian flows, which are the past movements of multiple pedestrians P who have previously stepped out onto the roadway. The determination unit 32 also determines past pedestrian flows, which are the past movements of multiple pedestrians P who have previously crossed the roadway.

[0113] Furthermore, the determination unit 32 can determine the attention level of the pedestrian P based on the past movements of the pedestrian P. For example, the determination unit 32 determines that the attention level of the pedestrian P is higher as the pedestrian P has performed a particular movement pattern more frequently.

[0114] The determination unit 32 can also determine the level of caution of the pedestrian P for each type of specific movement mode. For example, the determination unit 32 determines the level of caution against running out onto the roadway, the level of caution against running out onto the roadway, or the level of caution against crossing the roadway.

[0115] The determination unit 32 determines that the pedestrian P should have a higher level of caution regarding running out onto the roadway the more times the pedestrian P has run out onto the roadway. Also, the determination unit 32 determines that the pedestrian P should have a higher level of caution regarding running out onto the roadway the more times the pedestrian P has run out onto the roadway. Also, the determination unit 32 determines that the pedestrian P should have a higher level of caution regarding crossing the roadway the more times the pedestrian P has crossed the roadway.

[0116] [3.3.4. Definition section 33] The demarcation unit 33 demarcates a geofence based on past people flow, which is the past movements of multiple pedestrians P determined by the determination unit 32.

[0117] For example, the demarcation unit 33 defines, based on past pedestrian flow, the boundary between a normal movement area, which is an area where pedestrian P usually moves, and an abnormal movement area, which is an area where pedestrian P usually does not move, as a geofence.

[0118] This allows the demarcation unit 33 to determine areas on the road that are customarily used as sidewalks, for example, when a pedestrian P is walking on a road where the distinction between a roadway and a sidewalk is unclear.

[0119] [3.3.5. Generation unit 34] The generation unit 34 generates movement-related information, which is information relating to the movement of the pedestrian P predicted by the prediction unit 31. For example, the generation unit 34 generates movement-related information when the movement of the pedestrian P predicted by the prediction unit 31 is a specific movement pattern.

[0120] The types of specific movement patterns are, for example, a pedestrian P running out onto the roadway, a pedestrian P stepping out onto the roadway, a pedestrian P crossing the roadway, etc. The movement-related information includes information indicating the type of specific movement pattern, information indicating the position of a pedestrian P who is predicted to have the specific movement pattern, information indicating the attributes of a pedestrian P who is predicted to have the specific movement pattern, etc.

[0121] Furthermore, the generation unit 34 can also include, in the movement-related information, information indicating the above-mentioned level of caution for the pedestrian P who is predicted to move in a specific manner. For example, when the movement of the pedestrian P predicted by the prediction unit 31 is running out onto the roadway, the generation unit 34 includes, in the movement-related information, information indicating the above-mentioned level of caution for the pedestrian P who is predicted to run out onto the roadway.

[0122] Furthermore, the generation unit 34 generates warning information indicating locations and contents requiring attention based on past people flows, which are past movements of the plurality of pedestrians P determined by the determination unit 32.

[0123] For example, the generation unit 34 identifies, as places requiring caution, locations where pedestrians P may jump out onto the roadway, locations where pedestrians P may step out onto the roadway, locations where pedestrians P may cross the roadway, and the like, based on the past pedestrian flow determined by the determination unit 32. Then, the generation unit 34 generates caution information indicating the identified places requiring caution and their contents.

[0124] For example, when the generation unit 34 identifies a location where a pedestrian P has run out into the roadway, it generates warning information in which the information indicating the location where the pedestrian P has run out into the roadway is treated as information indicating a location where caution is required, and the information indicating the pedestrian P's run out into the roadway is treated as information indicating content that requires caution.

[0125] For example, when the generation unit 34 identifies a location where a pedestrian P is crossing the roadway, it generates warning information in which the information indicating the location where the pedestrian P is crossing the roadway is treated as information indicating a location where caution is required, and the information indicating the pedestrian P's crossing of the roadway is treated as information indicating content that requires caution.

[0126] Furthermore, based on the past pedestrian flow, which is the past movements of multiple pedestrians P determined as described above, the generation unit 34 identifies, as places requiring caution, locations where the frequency of pedestrians P stepping out onto the roadway is equal to or greater than a threshold Th1, locations where the frequency of pedestrians P stepping out onto the roadway is equal to or greater than a threshold Th2, locations where the frequency of pedestrians P crossing the roadway is equal to or greater than a threshold Th3, etc. The frequency is a frequency per unit of time, but may also be a number per number of pedestrians P, etc.

[0127] The generation unit 34 can also generate warning information for each time period, or for each attribute of the driver of the vehicle 9. For example, the information processing device 1 identifies places requiring attention for each time period. Then, the generation unit 34 generates information indicating the places requiring attention identified for each time period and their contents as warning information for each time period.

[0128] Furthermore, the generation unit 34 changes at least one of the thresholds Th1, Th2, and Th3 described above for each attribute of the driver of the vehicle 9, and identifies a place requiring attention for each attribute of the driver of the vehicle 9. Then, the generation unit 34 generates information indicating the place requiring attention identified for each attribute of the driver of the vehicle 9 and its content as attention information for each attribute of the driver of the vehicle 9.

[0129] For example, the generation unit 34 identifies a location requiring caution by increasing at least one of the thresholds Th1, Th2, and Th3 as the age or generation of the driver of the vehicle 9 increases. Furthermore, for example, when the gender of the driver of the vehicle 9 is of a specific gender, the generation unit 34 identifies a location requiring caution by increasing at least one of the thresholds Th1, Th2, and Th3 compared to when the gender of the driver of the vehicle 9 is not of a specific gender.

[0130] The generating unit 34 can generate warning information for each combination of the contents of a plurality of attribute items, such as, but not limited to, a teenage male, a teenage female, ..., a male in his 80s, and a female in her 80s.

[0131] [3.3.6. Notification section 35] The notification unit 35 notifies the traffic-related devices, which are devices related to traffic around the pedestrian P, of movement-related information, which is information related to the movement of the pedestrian P predicted by the prediction unit 31.

[0132] For example, the notification unit 35 acts as a traffic-related device to the control device 6 that changes the state of a traffic light 7 around the pedestrian P, notifying the control device 6 of related information and causing the control device 6 to change the state of the traffic light 7.

[0133] When the control device 6 acquires the movement-related information notified from the information processing device 1, it identifies a traffic light 7 to be controlled from among the multiple traffic lights 7 based on the movement-related information, and controls the identified traffic light 7.

[0134] For example, if the movement pattern of pedestrian P indicated in the movement-related information is pedestrian P running out into the roadway, the control device 6 identifies the traffic light 7 located in front of the pedestrian P's running out position included in the movement-related information as the target traffic light.

[0135] The jump-out position included in the movement-related information is, for example, the position per unit time predicted by the prediction unit 31, and the control device 6 identifies the traffic light 7 that is located in front of the direction of travel on the road at the position per unit time predicted by the prediction unit 31 as the target traffic light.

[0136] If the signal of the target traffic light, which is the traffic light 7 identified as the control target, is a signal indicating permission to proceed, the control device 6 changes the signal of the target traffic light to a signal indicating a stop instruction. Also, if the signal of the target traffic light is a signal indicating a stop instruction, the control device 6 maintains the signal of the target traffic light as a signal indicating a stop instruction.

[0137] 6 is a diagram showing an example of identification and control of a control target in the control device 6 according to the embodiment. As shown in Fig. 6, the control device 6 identifies a traffic light 7 located in front of the target traffic light in the direction of travel on the road at the position per unit time predicted by the information processing device 1 as the target traffic light, and controls the target traffic light.

[0138] In addition, when the movement pattern of pedestrian P indicated in the movement-related information is the position where pedestrian P crosses the roadway, the control device 6 identifies the traffic light 7 located just before the position where pedestrian P crosses the roadway, which is included in the movement-related information, as the target traffic light.

[0139] The crossing position of the roadway included in the movement-related information is, for example, the position per unit time predicted by the prediction unit 31, and the control device 6 identifies as the target traffic light the traffic light 7 that is located in front of the position per unit time predicted by the prediction unit 31 in the direction of travel on the roadway. In this case, the control device 6 controls the target traffic light in the same way as when the position included in the movement-related information is the jump-out position.

[0140] In addition, when the control device 6 acquires the movement-related information notified from the information processing device 1, it can identify the electronic traffic sign 8 to be controlled among the multiple electronic traffic signs 8 as the target electronic traffic sign based on the movement-related information, and control the identified target electronic traffic sign.

[0141] For example, when the movement mode of the pedestrian P indicated in the movement-related information is that the pedestrian P has stepped onto the roadway, the control device 6 identifies the electronic traffic sign 8 at the entrance to the roadway at the position of the pedestrian P included in the movement-related information as the target electronic traffic sign. Then, the control device 6 changes the display of the target electronic traffic sign identified as the control target to a no entry display.

[0142] In addition, when the movement pattern of pedestrian P indicated in the movement-related information is pedestrian P stepping out onto the roadway, the control device 6 identifies the electronic traffic sign 8 located in front of the pedestrian P's stepping out position included in the movement-related information as the target electronic traffic sign.

[0143] The protruding position included in the movement-related information is, for example, a position per unit time predicted by the information processing device 1, and the control device 6 identifies, as the target electronic traffic sign, an electronic traffic sign 8 that is located in a position in front of the direction of travel on the road at the position per unit time predicted by the information processing device 1. Then, the control device 6 changes the speed limit indicated by the target electronic traffic sign to a speed lower than normal.

[0144] Furthermore, the notification unit 35 notifies the movement-related information to vehicles 9 around the pedestrian P, causing them to change the running state of the vehicles 9. For example, the notification unit 35 identifies the vehicles 9 around the pedestrian P, which are included in the movement-related information, as vehicles to be controlled, and notifies the identified vehicles to be controlled of the movement-related information, causing them to change the running state of the vehicles 9.

[0145] The notification unit 35 notifies the control target vehicle of the movement-related information to stop the control target vehicle or reduce the speed of the control target vehicle. The control target vehicle has an on-board device that receives the movement-related information and controls the control target vehicle based on the received movement-related information, and stops the control target vehicle or reduces the speed of the control target vehicle based on the received movement-related information.

[0146] The notification unit 35 can also notify the traffic-related device of information based on the geofence defined by the definition unit 33 as movement-related information. For example, the notification unit 35 notifies the traffic-related device of information on the movement pattern of the pedestrian P predicted by the prediction unit 31 based on the geofence defined by the definition unit 33 as movement-related information.

[0147] In this case, the movement-related information notified to the traffic-related device includes, for example, information indicating the type of specific movement pattern, information indicating the position of pedestrian P who is predicted to move in a specific movement pattern, and information indicating the attributes of pedestrian P who is predicted to move in a specific movement pattern.

[0148] Furthermore, the notification unit 35 notifies the vehicle 9 of the warning information generated by the generation unit 34. For example, the notification unit 35 can notify the vehicle 9 that is in the area where attention is required of the warning information by transmitting the warning information as movement-related information to the vehicle 9 that is in the area where attention is required. The area where attention is required is, for example, a place where attention is required or an area around the place.

[0149] The vehicle 9 has an on-board device that receives and displays the movement-related information, and displays the warning information received as the movement-related information, thereby enabling the driver of the vehicle 9 to know that there are places or contents around the vehicle 9 that require attention.

[0150] Furthermore, the notification unit 35 notifies the pedestrian P who is in the area where caution is required of the warning information. For example, the notification unit 35 notifies the pedestrian P who is in the area where caution is required of the warning information by transmitting the warning information to the mobile terminal 2 of the pedestrian P who is in the area where caution is required.

[0151] The mobile terminal 2 of the pedestrian P receives the warning information and displays the received warning information. This allows the pedestrian P who is in an area where caution is required to know that there are places or contents that require caution around the pedestrian P. Therefore, the notification unit 35 can issue a warning to the pedestrian P who is in an area where caution is required.

[0152] [4. Processing Procedure] Next, a procedure of information processing by the processing unit 12 of the information processing device 1 according to the embodiment will be described. Fig. 7 is a flowchart showing an example of information processing by the processing unit 12 of the information processing device 1 according to the embodiment.

[0153] 7, the processing unit 12 of the information processing device 1 determines whether or not sensor information transmitted from the mobile terminal 2 or the like has been acquired (step S10). If the processing unit 12 determines that the sensor information has been acquired (step S10: Yes), the processing unit 12 stores the acquired sensor information in the storage unit 11 (step S11).

[0154] When the processing of step S11 is completed or when it is determined that the sensor information has not been acquired (step S10: No), the processing unit 12 determines whether or not the prediction timing has arrived (step S12). The prediction timing is, for example, a timing that arrives at every predetermined period, but is not limited to such an example.

[0155] When it is determined that the prediction timing has arrived (step S12: Yes), the processing unit 12 predicts the movement of the pedestrian P based on the sensor information stored in the storage unit 11 in step S11 (step S13).

[0156] When the process of step S13 is completed or when it is determined that the predicted timing has not arrived (step S12: No), the processing unit 12 determines whether the determination timing has arrived (step S14). The determination timing is, for example, a timing that arrives at every predetermined period, but is not limited to this example.

[0157] If the processing unit 12 determines that the time for judgment has arrived (step S14: Yes), it determines the past pedestrian flow, which is the past movements of multiple pedestrians P, based on the sensor information stored in the memory unit 11 in step S11 (step S15).

[0158] When the processing of step S15 is completed or when it is determined that the determination timing has not yet arrived (step S14: No), the processing unit 12 determines whether the first notification timing has arrived (step S16). The first notification timing is, for example, a timing that arrives at every predetermined period or a timing when the movement of the pedestrian P is predicted to be a specific movement pattern in step S12, but is not limited to such examples.

[0159] When the processing unit 12 determines that the first notification timing has arrived (step S16: Yes), the processing unit 12 generates movement-related information, which is information relating to the movement of the pedestrian P predicted in step S12, based on the movement of the pedestrian P predicted in step S12 (step S17). Then, the processing unit 12 notifies the traffic-related device of the movement-related information generated in step S15 (step S18).

[0160] When the processing of step S18 is completed or when it is determined that the first notification timing has not arrived (step S16: No), the processing unit 12 determines whether the second notification timing has arrived (step S19). The second notification timing is, for example, a timing that arrives at predetermined intervals or a timing when the movement of the pedestrian P is predicted to be a specific movement pattern in step S12, but is not limited to such examples.

[0161] When the processing unit 12 determines that the second notification timing has arrived (step S19: Yes), the processing unit 12 generates warning information based on the past people flow determined in step S15 (step S20). Then, the processing unit 12 notifies the vehicle 9 and the pedestrian P of the warning information generated in step S20 (step S21).

[0162] When the processing of step S21 is completed or when it is determined that the second notification timing has not come (step S19: No), the processing unit 12 determines whether the operation end timing has come (step S22). The processing unit 12 determines that the operation end timing has come when, for example, the power of the information processing device 1 is turned off.

[0163] If the processing unit 12 determines that the operation end time has not yet arrived (step S22: No), it proceeds to step S10, and if it determines that the operation end time has arrived (step S22: Yes), it terminates the processing shown in Figure 7.

[0164] [5. Other] Furthermore, the control device 6 can also display a left-turn or right-turn arrow on the traffic light 7 or electronic traffic sign 8 located before the position where the pedestrian P will jump out, the position where the pedestrian P will step out, or the crossing position, so that vehicles traveling toward the position where the pedestrian P will jump out, the position where the pedestrian P will step out, or the crossing position can turn left or right. This allows vehicles traveling toward the position where the pedestrian P will jump out to evacuate from the road where the pedestrian P is predicted to jump out.

[0165] The prediction unit 31 predicts the movement of the pedestrian P while using the content on the mobile terminal 2, and determines the movement of the pedestrian P while using the content on the mobile terminal 2, as the movement mode of the pedestrian P.

[0166] For example, the acquisition unit 30 acquires online service usage information, which is information indicating the usage status (e.g., browsing, searching, operation, etc.) of online services provided by an external information processing device. The prediction unit 31 predicts the movement of the pedestrian P while using specific content on the mobile terminal 2, or determines the movement of the pedestrian P while using the content on the mobile terminal 2, based on the online service usage information.

[0167] For example, if the pedestrian P has been using the content in a predetermined period (for example, the period from 5 seconds ago to the present), the prediction unit 31 can predict that the pedestrian P will continue to use the content.

[0168] The notification unit 35 can also notify information including information indicating the movement of the pedestrian P while using the content on the mobile terminal 2 predicted or determined by the prediction unit 31 as movement-related information or caution information.

[0169] Furthermore, when the prediction unit 31 predicts the movement of the pedestrian P while using content on the mobile terminal 2, it increases the probability of determining that the pedestrian P will run out into the roadway, step out onto the roadway, or cross the roadway.

[0170] The prediction unit 31 can also predict the movement mode of the pedestrian P as the movement of the pedestrian P in real time using a learning model that receives, as input, for example, information indicating the most recent movement state of the pedestrian P and information indicating whether the pedestrian P has moved while using content on the mobile device 2, and outputs information indicating the movement mode of the pedestrian P from a current or future point in time to a predetermined period of time. Such a learning model may be, for example, a model for each type of content used by the pedestrian P. The types of content include, for example, news content, video content, game content, etc., but are not limited to these examples.

[0171] In addition, for example, if the prediction unit 31 predicts a specific movement pattern and then determines that the specific movement pattern has disappeared, the notification unit 35 can notify information including information indicating that the specific movement pattern has disappeared as movement-related information or warning information.

[0172] In the above-described example, the traffic lights 7 and electronic traffic signs 8 are controlled by the control device 6 based on the movement-related information transmitted from the information processing device 1 to the control device 6, but the traffic lights 7 and electronic traffic signs 8 may also be controlled directly by the information processing device 1. In this case, the processing unit 12 of the information processing device 1 has a control unit that realizes the functions of the control device 6.

[0173] [6. Hardware Configuration] The information processing device according to the embodiment described above is realized by, for example, a computer 200 configured as shown in Fig. 8. Fig. 8 is a hardware configuration diagram showing an example of the computer 200 that realizes the functions of the information processing device 1 according to the embodiment. The computer 200 has a CPU 201, a RAM 202, a ROM (Read Only Memory) 203, an HDD (Hard Disk Drive) 204, a communication interface (I / F) 205, an input / output interface (I / F) 206, and a media interface (I / F) 207.

[0174] The CPU 201 operates and controls each unit based on programs stored in the ROM 203 or the HDD 204. The ROM 203 stores a boot program executed by the CPU 201 when the computer 200 starts up, programs dependent on the hardware of the computer 200, and the like.

[0175] The HDD 204 stores programs executed by the CPU 201, data used by such programs, etc. The communication interface 205 receives data from other devices via the network N (see FIG. 2) and sends it to the CPU 201, and transmits data generated by the CPU 201 to other devices via the network N.

[0176] The CPU 201 controls output devices such as a display and a printer, and input devices such as a keyboard and a mouse, via the input / output interface 206. The CPU 201 acquires data from the input devices via the input / output interface 206. The CPU 201 also outputs generated data to the output devices via the input / output interface 206.

[0177] The media interface 207 reads a program or data stored in the recording medium 208 and provides it to the CPU 201 via the RAM 202. The CPU 201 loads the program or data from the recording medium 208 onto the RAM 202 via the media interface 207 and executes the loaded program. The recording medium 208 is, for example, an optical recording medium such as a DVD (Digital Versatile Disc) or a PD (Phase Change Rewritable Disc), a magneto-optical recording medium such as an MO (Magneto-Optical disk), a tape medium, a magnetic recording medium, or a semiconductor memory.

[0178] For example, when the computer 200 functions as the information processing device 1 according to the embodiment, the CPU 201 of the computer 200 executes programs loaded onto the RAM 202 to realize the functions of the processing unit 12. In addition, the HDD 204 stores data in the storage unit 11. The CPU 201 of the computer 200 reads and executes these programs from the recording medium 208, but as another example, the CPU 201 may obtain these programs from another device via the network N.

[0179] [7. Other] Furthermore, among the processes described in the above embodiments, all or part of the processes described as being performed automatically can be performed manually, or all or part of the processes described as being performed manually can be performed automatically using known methods. In addition, the information including the processing procedures, specific names, various data, and parameters shown in the above documents and drawings can be changed as desired unless otherwise specified. For example, the various information shown in each drawing is not limited to the information shown in the drawings.

[0180] Furthermore, the components of each device shown in the figure are conceptual functional components and do not necessarily have to be physically configured as shown in the figure. In other words, the specific form of distribution and integration of each device is not limited to that shown in the figure, and all or part of them can be functionally or physically distributed and integrated in any unit depending on various loads, usage conditions, etc.

[0181] For example, the information processing device 1 described above may be realized by a plurality of server computers, and depending on the function, an external platform may be called using an API or network computing, etc., thereby allowing for flexible changes in configuration.

[0182] Furthermore, the above-described embodiments and modifications can be combined as appropriate within the scope of not causing any contradiction in the processing content.

[0183] [8. Effects] As described above, the information processing device 1 according to the embodiment includes an acquisition unit 30 that acquires sensor information, which is information about the pedestrian P detected by a sensor, a prediction unit 31 that predicts the movement of the pedestrian P based on the sensor information acquired by the acquisition unit 30, and a notification unit 35 that notifies a traffic-related device, which is a device related to traffic around the pedestrian P, of movement-related information, which is information about the movement of the pedestrian P predicted by the prediction unit 31. This enables the information processing device 1 to further improve collision prevention between the vehicle 9 and the pedestrian P.

[0184] Furthermore, the notification unit 35 notifies the control device 6, which changes the state of the traffic lights 7 around the pedestrian P, of the relevant information, acting as a traffic-related device, and causes the control device 6 to change the state of the traffic lights 7. This allows the information processing device 1 to further improve the prevention of collisions between the vehicle 9 and the pedestrian P.

[0185] In addition, the notification unit 35 notifies the vehicles 9 around the pedestrian P of the movement-related information to change the traveling state of the vehicles 9. This allows the information processing device 1 to further improve the prevention of collisions between the vehicles 9 and the pedestrian P.

[0186] Furthermore, the prediction unit 31 predicts at least one of the following as the movement of the pedestrian P: the pedestrian P running out onto the roadway, the pedestrian P stepping out onto the roadway, and the pedestrian P crossing the roadway. This allows the information processing device 1 to further improve the prevention of a collision between the vehicle 9 and the pedestrian P.

[0187] The information processing device 1 includes a determination unit 32 that determines past people flow, which is the past movements of multiple pedestrians P, based on sensor information acquired by the acquisition unit 30, and a demarcation unit 33 that defines a geofence based on the past people flow determined by the determination unit 32. The notification unit 35 notifies the traffic-related device of information based on the geofence defined by the demarcation unit 33 as movement-related information. This enables the information processing device 1 to further improve collision prevention between the vehicle 9 and the pedestrian P.

[0188] The information processing device 1 includes a determination unit 32 that determines past people flows, which are the past movements of multiple pedestrians P, based on sensor information acquired by the acquisition unit 30, and a generation unit 34 that generates warning information indicating locations and contents requiring caution based on the past people flows determined by the determination unit 32, and a notification unit 35 that notifies the warning information generated by the generation unit 34 to vehicles 9 or pedestrians P that are present in locations requiring caution or around those locations. This enables the information processing device 1 to further improve collision prevention between vehicles 9 and pedestrians P.

[0189] Furthermore, the notification unit 35 notifies the in-vehicle devices of the vehicles 9 around the pedestrian P of the warning information as movement-related information, causing the in-vehicle devices to output the warning information. This allows the information processing device 1 to further improve the prevention of collisions between the vehicles 9 and the pedestrian P.

[0190] Furthermore, the generation unit 34 generates the warning information for each time period. This allows the information processing device 1 to further improve the prevention of collisions between the vehicle 9 and the pedestrian P.

[0191] Furthermore, the generation unit 34 generates the attention information for each attribute of the driver of the vehicle 9. This allows the information processing device 1 to further improve the prevention of a collision between the vehicle 9 and the pedestrian P.

[0192] The above describes the embodiments of the present application in detail based on the drawings, but this is merely an example, and the present invention can be implemented in other forms that include the embodiments described in the Disclosure of the Invention section and that have been modified and improved in various ways based on the knowledge of those skilled in the art.

[0193] Furthermore, the above-mentioned "section, module, unit" can be read as "means" or "circuit," etc. For example, an acquisition unit can be read as an acquisition means or an acquisition circuit. [Explanation of symbols]

[0194] 1. Information processing equipment 2. Mobile devices 3 GPS transmitter 4. IC tags 5. Fixed sensors 6. Control device 7. Traffic Lights 8 Electronic traffic signs 9 vehicles 10. Communications Department 11 Storage section 12 Processing section 20 Pedestrian information storage unit 21 Occupant information storage unit 22 Road-related information storage unit 30 Acquisition Department 31 Prediction Department 32 Judgment section 33 Demarcation Section 34 Generation part 35 Notification Department N Network P Pedestrian

Claims

1. an acquisition unit that acquires sensor information that is information about pedestrians detected by a sensor; a prediction unit that predicts the movement of the pedestrian based on the sensor information acquired by the acquisition unit; a notification unit that notifies a traffic-related device that is a device related to traffic around the pedestrian of movement-related information that is information about the movement of the pedestrian predicted by the prediction unit; a determination unit that determines a past people flow, which is past movements of the plurality of pedestrians, based on the sensor information acquired by the acquisition unit; A demarcation unit that defines a geofence based on the past people flow determined by the determination unit, The notification unit The traffic-related device is notified of information based on the geofence defined by the defining unit as the movement-related information.

1. An information processing device comprising:

2. The prediction unit At least one of the pedestrian running out onto the roadway, the pedestrian stepping out onto the roadway, and the pedestrian crossing the roadway is predicted as the pedestrian's movement.

2. The information processing apparatus according to claim 1, wherein:

3. a people flow determination unit that determines a past people flow, which is past movements of the plurality of pedestrians, based on the sensor information acquired by the acquisition unit; a generation unit that generates warning information indicating locations and contents requiring attention based on the past people flow determined by the people flow determination unit, The notification unit The warning information generated by the generating unit is notified to a vehicle or a pedestrian present at the location where attention is required or around the location.

2. The information processing apparatus according to claim 1, wherein:

4. The notification unit The warning information is notified to an in-vehicle device of a vehicle around the pedestrian as the movement-related information, and the warning information is output from the in-vehicle device.

4. The information processing apparatus according to claim 3,

5. The generation unit Generate the warning information for each time period 4. The information processing apparatus according to claim 3,

6. The generation unit The warning information is generated for each attribute of the driver of the vehicle.

4. The information processing apparatus according to claim 3,

7. 1. A computer-implemented information processing method, comprising: an acquisition step of acquiring sensor information that is information about a pedestrian detected by a sensor; a prediction step of predicting a movement of the pedestrian based on the sensor information acquired in the acquisition step; a notification step of notifying a traffic-related device that is a device related to traffic around the pedestrian of movement-related information that is information about the movement of the pedestrian predicted by the prediction step; a determination step of determining a past people flow, which is past movements of the plurality of pedestrians, based on the sensor information acquired by the acquisition step; A defining step of defining a geofence based on the past people flow determined by the determining step, The notification step includes: The traffic-related device is notified of information based on the geofence defined by the defining step as the movement-related information.

1. An information processing method comprising:

8. an acquisition step of acquiring sensor information, which is information about pedestrians detected by a sensor; a prediction step of predicting a movement of the pedestrian based on the sensor information acquired by the acquisition step; a notification step of notifying a traffic-related device, which is a device related to traffic around the pedestrian, of movement-related information, which is information about the movement of the pedestrian predicted by the prediction step; a determination step of determining a past people flow, which is past movements of the plurality of pedestrians, based on the sensor information acquired by the acquisition step; a defining step of defining a geofence based on the past people flow determined by the determining step; The notification procedure includes: and notifying the traffic-related device of information based on the geofence defined by the defining procedure as the movement-related information. An information processing program characterized by:

Images