Precipitation level estimation system and program

Abstract

To provide a precipitation level estimation system and program that can acquire data related to precipitation acquired from vehicles and accurately calculate a precipitation level using an estimation method based on machine learning.SOLUTION: A precipitation level estimation system 1 includes a calculation section 12 that acquires detection data related to precipitation, which is detected by a plurality of vehicles Mn present in an observation target area RX, and calculates a precipitation amount in a predetermined area Rm included in the observation target area on the basis of the detection data. The calculation section calculates a first feature amount in a first predetermined period, which is past with respect to present, on the basis of first detection data acquired from a first area including the predetermined area, calculates a second feature amount in a second predetermined period, which is past with respect to the first predetermined period, in a second area on the basis of second detection data acquired in the second area adjacent to the first area, calculates the precipitation amount using a precipitation amount estimation model using the first feature amount and the second feature amount as variables, and calculates a precipitation level according to the precipitation amount.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to a precipitation level estimation system and a program capable of estimating the amount of precipitation. [Background technology]

[0002] In recent years, awareness of disaster prevention against the occurrence of localized heavy rain has been increasing. Patent Document 1 describes a technique for calculating an index indicating the intensity of precipitation in an area including a vehicle based on data related to the operation mode of the vehicle's wiper device. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2020-052962 A Summary of the Invention [Problem to be solved by the invention]

[0004] The wiper operation mode has three operation modes, for example, weak, medium, and strong. According to the technology described in Patent Document 1, the intensity of precipitation is estimated based on data related to the wiper operation mode. When heavy precipitation occurs, the wiper operation mode is fixed to the strong stage, and the correlation between the wiper operation mode and the amount of precipitation becomes small. Therefore, according to the technology described in Patent Document 1, there is a possibility that it may be difficult to accurately estimate the precipitation level in a certain area.

[0005] The present invention aims to provide a precipitation level estimation system and program that can accurately calculate precipitation levels using precipitation-related data acquired from a vehicle and an estimation method based on machine learning. [Means for solving the problem]

[0006] One aspect of the present invention is a precipitation level estimation system that includes a calculation unit that acquires detection data related to precipitation detected by a plurality of vehicles present in an observation area, and calculates an amount of precipitation in a specified area included in the observation area based on the detection data, wherein the calculation unit calculates a first characteristic amount for a first predetermined period in the past compared to the present based on first detection data acquired from a first area that includes the specified area, calculates a second characteristic amount for a second predetermined period in the past compared to the first predetermined period in the second area based on second detection data acquired in a second area adjacent to the first area, calculates the precipitation amount using a precipitation estimation model that has the first characteristic amount and the second characteristic amount as variables, and calculates a precipitation level corresponding to the precipitation amount. Effect of the Invention

[0007] According to the present invention, precipitation levels can be accurately calculated using machine learning based estimation methods utilizing precipitation related data acquired from a vehicle. [Brief description of the drawings]

[0008] [Figure 1] 1 is a block diagram showing a configuration of a precipitation level estimation system according to an embodiment. [Diagram 2] FIG. 1 is a diagram showing an observation method in an observation target area. [Diagram 3] FIG. 2 is a diagram showing a predetermined area within an observation target area. [Figure 4] FIG. 2 is a diagram showing the contents of a plurality of feature amounts. [Diagram 5] FIG. 1 shows mapping data with precipitation levels displayed. [Figure 6] FIG. 1 shows the change in precipitation level over time in mapping data. [Figure 7] 1 is a flowchart showing a process flow of a precipitation level estimation method. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] As shown in FIG. 1, the precipitation level estimation system 1 includes a server device 10 connected to a network NW and a plurality of vehicles Mn (n: any natural number). The plurality of vehicles Mn are present in an observation target area RX that is the subject of observation. The observation target area RX is set to, for example, a rectangular area of ​​a predetermined area. The server device 10 communicates with the plurality of vehicles Mn and acquires detection data related to precipitation. The server device 10 calculates the precipitation level in the observation target area RX based on the detection data.

[0010] The precipitation level is set to three levels according to the amount of precipitation, as described later. The server device 10 provides information including the precipitation level to the vehicle Mn in the observation target area RX based on the calculation result. The server device 10 may also provide information to the terminal device 20 connected to the network NW in addition to the vehicle Mn.

[0011] The terminal device 20 is configured, for example, by an information processing terminal device such as a personal computer or a smartphone. The terminal device 20 is provided with, for example, a display unit 26 that displays information. The display unit 26 is provided, for example, by a display device such as a liquid crystal display. The terminal device 20 is provided with a communication unit 28 that can communicate with the network NW. The communication unit 28 is provided with a communication interface that can be connected to the network NW. The terminal device 20 is provided with a control unit 22 that executes communication and information display processing.

[0012] The terminal device 20 includes a storage unit 24 that stores data and programs necessary for control. The control unit 22 is configured with at least one hardware processor such as a CPU (Central Processing Unit). The storage unit 24 is configured with a non-transitory storage medium such as a hard disk drive (HDD) or a solid state disk (SSD).

[0013] The server device 10 is composed of a calculation unit 12 that performs various calculation processes, a storage unit 14 that stores data and programs necessary for the calculation processes, and a communication unit 16 that communicates with the network NW. The calculation unit 12 is composed of at least one hardware processor such as a CPU. The storage unit 14 is composed of a non-transitory storage medium such as a hard disk drive or a solid state disk. The communication unit 16 is composed of a communication interface that can be connected to the network NW.

[0014] The calculation unit 12 acquires detection data related to precipitation detected by a plurality of vehicles Mn present in the observation target area RX. The calculation unit 12 calculates the amount of precipitation in the observation target area RX based on the detection data. The details of the calculation process of the calculation unit 12 will be described later. The calculation unit 12 calculates the distribution of precipitation levels in the observation target area RX based on the calculation results. The calculation unit 12 provides information related to the amount of precipitation to the vehicles Mn used by the user via the network NW.

[0015] The vehicle Mn is configured to be able to communicate with the server device 10 via the network NW. The vehicle Mn is equipped with, for example, a detection unit MS that detects various data. The detection unit MS is composed of vehicle equipment such as a plurality of devices and sensors provided in the vehicle Mn. The detection unit MS is composed of vehicle equipment that can acquire control signals required for control, current values ​​required for operation, and data required for controlling the vehicle Mn. The detection unit MS is equipped with, for example, a wiper device MN that wipes the windows of the vehicle Mn.

[0016] The wiper device MN is provided on the front window or rear window of the vehicle Mn. The wiper device MN operates based on three operating modes, for example, weak, medium, and strong. The operating speed of the operating modes increases in the order of weak, medium, and strong. The operating speed is set, for example, by the number of wipes per unit time (number of wipes / minute). The operating modes may be provided with a speed adjustment mode in which the number of wipes per unit time can be arbitrarily adjusted. The wiper device MN operates based on the operation of an occupant of the vehicle Mn. The wiper device MN operates based on a control signal corresponding to the operation of the occupant. The control signal is set to correspond to the stepwise operating modes and the speed adjustment mode.

[0017] The wiper device MN may be provided with a rain sensor ME that detects rainfall. The rain sensor ME is provided on the inside of the windshield and detects changes in the light transmittance of the windshield. The wiper device MN operates automatically, for example, when rainfall is detected by the rain sensor ME. The wiper device MN operates in an operating mode that is automatically set in response to a change in the signal detected by the rain sensor ME.

[0018] The detection unit MS is provided with a camera MC capable of capturing images. The camera MC captures an image of the external environment of the vehicle Mn. The image data captured by the camera MC is used, for example, to control the vehicle Mn. The detection unit MS is provided with a LIDAR device MD that emits laser waves. The LIDAR device MD receives reflected waves of the emitted laser waves and detects objects present around the vehicle Mn. The detection unit MS is provided with a position sensor MG that detects the current position of the vehicle Mn. The position sensor MG is, for example, configured with a GPS (Global Positioning System) sensor.

[0019] The vehicle Mn is provided with a control unit MP that executes various controls. The control unit MP executes controls related to the traveling of the vehicle Mn. The control unit MP transmits data related to precipitation among the data detected by the detection unit MS to the server device 10. The control unit MP is configured with at least one hardware processor such as a CPU.

[0020] The vehicle Mn is provided with a notification unit ML that notifies various pieces of information. The notification unit ML is, for example, configured with a display device that can display an image including the notification content. The notification unit ML may be configured with a speaker that outputs the notification content by voice. The vehicle Mn is provided with a communication unit MU that can be connected to a network NW. The communication unit MU is, for example, configured with a communication interface that can perform wireless communication.

[0021] The vehicle Mn acquires various data while traveling by the detection unit MS. The control unit MP controls the traveling of the vehicle Mn based on the acquired data. The control unit MP transmits data related to precipitation among the data acquired by the detection unit MS to the server device 10. The control unit MP transmits, for example, data related to the control of the wiper device MN to the server device 10. In the server device 10, the data is stored in the memory unit 14. The calculation unit 12 calculates the amount of precipitation in the observation target area RX based on the data stored in the memory unit 14.

[0022] As shown in FIG. 2, the map data of the observation target area RX includes an area Rm (m: natural number). The area Rm is set, for example, to a rectangular area of ​​1 km square. The size, position, and shape of the area Rm are set arbitrarily. An ID number is set for the area Rm in accordance with its position. The area Rm is managed by a server device 10. The server device 10 communicates with a plurality of vehicles Mn present within the observation target area RX. In the server device 10, a calculation unit 12 acquires position data of each vehicle Mn and ID data for identifying the vehicle Mn.

[0023] As shown in Fig. 3, the calculation unit 12 compares the ID data RD of the area Rm with data acquired from the vehicle Mn to recognize the vehicle Mn present within the area Rm. The calculation unit 12 acquires detection data related to precipitation from a plurality of vehicles Mn present within the area Rm. The detection data related to precipitation includes, for example, data related to the operation state of the wiper device MN, vehicle ID data, vehicle position data, time data, and other data. The calculation unit 12 acquires detection data from the vehicle Mn present within the area Rm at predetermined intervals (for example, one-minute intervals). The calculation unit 12 stores the acquired detection data in the memory unit 14.

[0024] The calculation unit 12 calculates the amount of precipitation in the region Rm. The region Rm includes a user position where a user who receives information about precipitation from the server device 10 is present. The user's position information is provided to the server device 10 via the vehicle Mn in which the user is currently riding or the terminal device 20 that the user possesses. The calculation unit 12 calculates the amount of precipitation in the region Rm including the user's position, based on the position information provided by the user.

[0025] 4, the calculation unit 12 generates a plurality of feature quantities B to Y used for estimating the amount of precipitation at a predetermined period (e.g., every 10 minutes) based on the detection data. The plurality of feature quantities B to Y are classified into 24 types of elements, such as a speed component of the wiper device MN, a time component, a number component of the vehicles Mn, and an area component. The plurality of feature quantities B to Y are set so that features appear in the calculation of the amount of precipitation at the user position based on data indicating the operation state of the wiper device MN.

[0026] The calculation unit 12 generates a first feature amount Ta (feature amounts B to M) based on, for example, the first detection data acquired from a first region Ra included in the observation target region RX. The first region Ra is set, for example, by a plurality of sample data collection regions including the user position and its surrounding points. The plurality of sample data collection regions are set, for example, by a 1 km square region Rm including the user position and a plurality of 1 km square surrounding regions including surrounding points spaced a predetermined distance from the user position.

[0027] The surrounding points include, for example, a point 5 km away from the user position and a point 10 km away from the user position. The calculation unit 12 collects first detection data of a first region Ra including the user position and surrounding points in any direction from the user position. The direction in which data is collected is set arbitrarily based on the method of collecting sample data. The calculation unit 12 collects data of the first region Ra in four azimuth directions, east, west, south, and north, from the user position. The calculation unit 12 may collect data of the first region including any directional element, such as eight azimuth directions including the east, west, south, and north directions plus the northeast, northwest, southwest, and southeast directions.

[0028] The calculation unit 12 acquires first detection data of the first region Ra in a first predetermined period t1 in the past compared to the present. The first predetermined period t1 is, for example, one hour in the past from the current time. The calculation unit 12 generates feature quantities B to M in each of the four azimuth directions based on the first detection data acquired in the first region Ra, for example. The calculation unit 12 generates feature quantities B to M based on wiper operation data indicating the operation state of a wiper device provided in the vehicle, for example.

[0029] The calculation unit 12 calculates, for example, a feature quantity related to a wiper operation time ratio indicating the operation state of the wiper device MN. The wiper operation time ratio is the ratio of time during which the wiper device is operated in each predetermined period. The wiper operation time ratio includes feature quantities B, C, and D calculated based on the maximum time during which the wiper device is operated in each predetermined period (e.g., 10 minutes), and feature quantities E, F, and G calculated based on the total time during which the wiper device is operated in each predetermined period (e.g., 60 minutes).

[0030] A total of six feature values ​​B, C, and D, which indicate the precipitation level, are sampled over a one-hour period at 10-minute aggregation intervals. By sampling feature values ​​B, C, and D over a short period of time and using the maximum value of those values ​​over the one-hour period and feature values ​​E, F, and G, which indicate the total value over the one-hour period when the wiper device was activated, it is possible to accurately capture the peak value of precipitation, which indicates heavy precipitation.

[0031] Feature values ​​B and E are calculated in a rectangular region of 1 km square including the user position. Feature values ​​C and F are calculated in a rectangular region 5Rm (see FIG. 2) of 1 km square including a point 5 km away from the user position in a predetermined direction. Feature values ​​D and G are calculated in a rectangular region 10Rm (see FIG. 2) of 1 km square including a point 10 km away from the user position in a predetermined direction.

[0032] The above feature value indicating the precipitation level is calculated not only for a 1 km square area Rm including the user position in the first area Ra, but also for areas 5Rm and 10Rm spaced apart in four directions centered on the area Rm. The more the sampling points on which the feature value is calculated are expanded according to the direction, the more the number of vehicles Mn from which data can be collected increases. Also, by sampling according to the direction, it is possible to capture the precipitation trend.

[0033] The calculation unit 12 calculates, for example, a wiper operation number ratio indicating the operation state of the wiper device. The wiper operation number ratio includes feature amounts H, I, and J calculated from the maximum number of vehicles Mn whose wiper devices have been operated in each predetermined period (e.g., 10 minutes), and feature amounts K, L, and M calculated from the sum of the number of vehicles Mn whose wiper devices have been operated in each predetermined period (e.g., 60 minutes).

[0034] For example, if all vehicles Mn operated the wiper speed (e.g., 50 times / min) for 10% of the driving time, the feature value of the wiper operation time ratio is calculated as 10%. In this case, the wiper devices of all vehicles Mn were operated for 60 minutes, so the feature value of the wiper operation number ratio is calculated as 100%.

[0035] In calculating the characteristic amount, by calculating the operation rate [%] of the wiper device MN instead of the operation frequency, it is possible to suppress the variation in the calculated value caused by the difference in the number of vehicles Mn traveling in the area to be calculated. By calculating the characteristic amount related to the wiper operation time rate, it is possible to easily capture heavy precipitation. In calculating the characteristic amount, by using the perspective of "number of vehicles" in addition to the perspective of "time", it is possible to easily capture heavy precipitation.

[0036] The calculation unit 12 generates the second feature amount Tb (feature amounts N to Y) based on, for example, second detection data acquired from a second region Rb adjacent to the first region Ra included in the observation target region RX. The second region Rb is set by, for example, a plurality of data collection regions including surrounding points adjacent to the first region Ra. The plurality of data collection regions is set by, for example, a rectangular region of 1 km square including surrounding points separated by a predetermined distance from the user position. The surrounding points include, for example, a point separated by 10 km in a predetermined direction from the user position, a point separated by 20 km from the user position, and a point separated by 30 km in a predetermined direction from the user position.

[0037] The above feature value indicating the precipitation level is calculated for the second region Rb in regions 10Rm, 20Rm, and 30Rm spaced apart in four directions centered on the region Rm. The wider the sampling points that are the basis for calculating the feature value according to the direction, the more vehicles Mn that can collect data. In addition, by sampling the region Rm according to the direction, the precipitation trend can be captured.

[0038] The calculation unit 12, for example, collects second detection data of the second region Rb from the user position. The calculation unit 12 acquires the second detection data of the second region Rb in a second predetermined period t2 that is earlier than the first predetermined period t1. The second predetermined period t2 is, for example, one hour in the past from the start time of the first predetermined period t1. The calculation unit 12, for example, generates feature quantities N to Y in each of the four azimuth directions based on the second detection data acquired in the second region Rb. The calculation unit 12, for example, generates feature quantities N to Y based on wiper operation data that indicates the operation state of a wiper device provided in the vehicle.

[0039] The calculation unit 12 calculates, for example, a wiper operation time ratio indicating the operation state of the wiper device MN. The wiper operation time ratio includes the characteristic quantities N, O, and P calculated from the maximum time that the wiper device MN was operated in each predetermined period (e.g., 10 minutes), and the characteristic quantities Q, R, and S calculated from the sum of the time that the wiper device MN was operated in each predetermined period (e.g., 60 minutes).

[0040] The feature amount N and the feature amount Q are calculated in a rectangular area 10Rm (see FIG. 2) that is 1 km square and includes a point 10 km away from the user position. The feature amount O and the feature amount R are calculated in a rectangular area 20Rm (see FIG. 2) that is 1 km square and includes a point 20 km away from the user position. The feature amount P and the feature amount S are calculated in a rectangular area 30Rm (see FIG. 2) that is 1 km square and includes a point 30 km away from the user position.

[0041] The calculation unit 12 calculates, for example, a wiper operation number ratio indicating the operation state of the wiper device MN. The wiper operation number ratio includes feature amounts T, U, and V calculated from the maximum number of vehicles Mn whose wiper devices have been operated in each predetermined period (e.g., 10 minutes), and feature amounts W, X, and Y calculated from the total number of vehicles Mn whose wiper devices have been operated in a predetermined period (e.g., 60 minutes). The calculation unit 12 calculates feature amounts including the first feature amount Ta and the second feature amount Tb in four directions from the user position.

[0042] As described above, the first feature amount Ta in the first region Ra including the user position is calculated in the most recent first predetermined period t1. The second feature amount Tb in the second region Rb farther from the user position is calculated in the second predetermined period t2 that is earlier than the first predetermined period t1. The calculation unit 12 inputs the calculated first feature amount and second feature amount to a preset precipitation estimation model and calculates the amount of precipitation from the present to the future in the first region Ra included in the observation target region RX.

[0043] The precipitation estimation model is set, for example, by a polynomial nonlinear regression equation that calculates an estimated value of the precipitation in the region Rm including the user position using multiple feature quantities as variables. The nonlinear regression equation is set arbitrarily to a function that can calculate the precipitation quantity. The relationship between the precipitation quantity and the feature quantities related to the operating state of the wiper device MN gradually changes from a linear relationship to a curvilinear relationship. Therefore, the precipitation estimation model using nonlinear regression can more accurately reproduce the different trends between heavy precipitation levels and light precipitation levels.

[0044] In the precipitation estimation model, a plurality of parameters corresponding to a polynomial consisting of a plurality of feature quantities are set based on machine learning performed in advance in the calculation unit 12. The calculation unit 12 repeatedly executes machine learning by, for example, deep learning using a neural network.

[0045] The calculation unit 12 adjusts parameters set in the precipitation estimation model by repeatedly executing machine learning to calculate an estimated value of precipitation based on the feature amount, using the feature amount calculated based on past detection data as teacher data. The estimated value of precipitation is calculated by inputting the feature amount calculated using the detection data into the precipitation estimation model with adjusted parameters. The precipitation estimation model with adjusted parameters is stored in the storage unit 14 as a computer program. The calculation unit 12 calculates the amount of precipitation at an arbitrary point by inputting the feature amount calculated using the detection data into the precipitation estimation model.

[0046] The calculation unit 12 acquires detection data related to precipitation detected by a plurality of vehicles Mn present in the observation target area RX. The calculation unit 12 calculates the amount of precipitation from the present to the future in a predetermined area included in the observation target area RX based on the detection data.

[0047] The calculation unit 12 calculates a plurality of first feature values ​​Ta for a first predetermined period t1 in the past compared to the present, based on, for example, first detection data acquired from a first region Ra. The calculation unit 12 calculates a second feature value Tb for a second predetermined period t2 in the past compared to the first predetermined period in the second region Rb, based on, for example, second detection data acquired in a second region Rb adjacent to the first region Ra. The calculation unit 12 calculates feature values ​​including a first feature value Ta related to the time ratio when the wiper device MN was operated and a second feature value Tb related to the number ratio when the wiper device was operated, based on wiper operation data indicating the operation state of the wiper device MN provided on the vehicle Mn among the detection data.

[0048] The calculation unit 12 calculates the current precipitation amount in the region Rm using a precipitation estimation model with the first feature amount Ta and the second feature amount Tb as variables. The calculation unit 12 compares the calculated precipitation amount with a precipitation level set according to the precipitation amount to calculate the precipitation level in the region Rm. The calculation unit 12 determines the precipitation level from the following three levels based on the comparison result with a preset reference precipitation amount, for example.

[0049] The calculation unit 12 determines that the precipitation level is "heavy precipitation level (High)" when the precipitation level is equal to or greater than a preset first precipitation level V1 (e.g., 20 mm / h). The heavy precipitation level is set to a precipitation level equal to or greater than a standard requiring attention (e.g., 20 mm / h). The standard is set to an arbitrary precipitation level. The calculation unit 12 determines that the precipitation level is "weak precipitation level (Mid)" when the precipitation level is less than the first precipitation level V1 and equal to or greater than a preset second precipitation level V2 (e.g., 1 mm / h). The calculation unit 12 determines that the precipitation level is "no precipitation (Low)" when the precipitation level is less than the second precipitation level V2 (1 mm / h).

[0050] The calculation unit 12 may calculate not only the precipitation level in the region Rm including the user position, but also the precipitation level in all other regions Rm in the observation target region RX by repeatedly executing the same calculation process as above. The calculation unit 12 does not necessarily need to calculate all other regions Rm in the observation target region RX, and may calculate the observation target region RX using one region Rm included in a rectangular region of any size as a representative value, and generate mapping data of the observation target region RX divided by rectangular regions of any size.

[0051] 5, the calculation unit 12 may generate mapping data PP in which the precipitation level is mapped for each region Rm in the observation target region RX. As shown in the figure, the mapping data PP shows a distribution of regions with a current heavy precipitation level (High), a distribution of regions with a light precipitation level (Mid), and a distribution of regions with no precipitation (Low).

[0052] The precipitation estimation model may be set to calculate not only the current precipitation but also the future precipitation by repeatedly executing machine learning based on past detection data. Therefore, the calculation unit 12 may calculate the past and future precipitation levels in the region Rm based on the precipitation estimation model. The calculation unit 12 may calculate, for example, the precipitation amount a predetermined time ago, the current precipitation amount, and the precipitation amount a predetermined time later in the region Rm including the user position. The calculation unit 12 may calculate the past, current, and future precipitation amounts at any time interval. The calculation unit 12 may update the precipitation level estimation model at a predetermined timing using the accumulated detection data.

[0053] Generally, heavy precipitation often moves in large chunks from a distance in conjunction with the movement of rain clouds. Therefore, in addition to calculating the first characteristic amount Ta in the first predetermined period t1, the tendency of precipitation to move can be calculated by calculating the second characteristic amount Tb in the second predetermined period t2.

[0054] The calculation unit 12 may extract an area Rm in the observation target area RX where the amount of precipitation is a heavy precipitation level equal to or higher than a reference level, based on the generated mapping data, and provide information on the amount of precipitation to a user in the area Rm. The calculation unit 12 may cause a notification unit ML of a vehicle Mn in which a user in the extracted area Rm is riding to notify predetermined information indicating that the precipitation level is heavy, via a network NW. The calculation unit 12 may extract an area Rm where the amount of precipitation is a heavy precipitation level within a predetermined time period in the future, based on the generated mapping data, and provide information on the amount of precipitation to a user in the area Rm. The predetermined time period in the future may be set arbitrarily.

[0055] The vehicle Mn may perform driving control corresponding to rainfall based on the provided predetermined information. The driving control corresponding to rainfall may be applied to the vehicle Mn that runs based on automatic driving. The driving control corresponding to rainfall may be driving support for the vehicle Mn that runs based on manual driving. The calculation unit 12 may cause the display unit 26 of the user's terminal device 20 to display predetermined information related to the first precipitation level via the network NW.

[0056] For example, information on the state of heavy precipitation level rainfall or information that heavy precipitation level rainfall is approaching is displayed on the display unit 26. The user's terminal device 20 does not necessarily have to be located within the extracted region Rm. The user only needs to be a user of a service that provides information on the precipitation level.

[0057] 7 is a flowchart showing the procedure of the precipitation level estimation method executed in the precipitation level estimation system 1. The precipitation level estimation method is processed based on a program installed in a computer constituting the precipitation level estimation system 1. The program causes the computer to execute the following steps related to the precipitation level estimation method.

[0058] The calculation unit 12 acquires detection data related to precipitation detected by a plurality of vehicles present in the observation target area (step S100). The calculation unit 12 calculates a first characteristic amount for a first predetermined period in the past compared to the present based on the first detection data acquired from a first area Ra included in the observation target area RX (step S102). The calculation unit 12 calculates a second characteristic amount for a second predetermined period t2 in the past compared to the first predetermined period t1 in the second area Rb based on second detection data acquired in a second area Rb adjacent to the first area Ra (step S104).

[0059] The calculation unit 12 calculates the amount of precipitation in a predetermined region Rm included in the observation target region RX using a precipitation estimation model having the first feature amount Ta and the second feature amount Tb as variables (step S106). The calculation unit 12 determines whether the amount of precipitation is equal to or greater than the first precipitation amount V1 (step S108). If the amount of precipitation is equal to or greater than the first precipitation amount V1, the calculation unit 12 determines that the precipitation is at a "heavy precipitation level" (step S110).

[0060] When the amount of precipitation is less than the first precipitation amount V1, the calculation unit 12 determines whether the amount of precipitation is equal to or greater than the second precipitation amount V2 (step S112). When the amount of precipitation is equal to or greater than the second precipitation amount V2, the calculation unit 12 determines that the precipitation level is "light" (step S114). When the amount of precipitation is less than the second precipitation amount V2, the calculation unit 12 determines that there is "no precipitation" (step S116). The calculation unit 12 provides information about the precipitation level to users in an area where the precipitation level is heavy (step S118).

[0061] As described above, the precipitation level estimation system 1 can accurately estimate the precipitation level by calculating multiple feature amounts based on detection data related to the operating state of the wiper device MN. The precipitation level estimation system 1 can accurately estimate the precipitation level by inputting multiple feature amounts into a precipitation estimation model whose parameters have been adjusted based on machine learning. The precipitation level estimation system 1 can accurately estimate the precipitation level by using nonlinear regression in the precipitation estimation model.

[0062] In the above-described embodiment, the feature amount is calculated based on data on the operating state of the wiper device MN. The feature amount may be calculated based on not only the detection data of the wiper device MN but also the detection data of the rain sensor ME, the image data of the surrounding environment of the vehicle Mn captured by the camera MC, and the detection data detected by the lidar device MD. The feature amount may be calculated by the calculation unit 12 repeatedly executing machine learning based on the image data of the rainfall state captured by the camera MC.

[0063] The feature amount may be calculated by the calculation unit 12 repeatedly executing machine learning based on the detection data of rainfall detected by the rain sensor ME. Since the detection data of the LIDAR device MD deteriorates due to the occurrence of rainfall, the feature amount may be calculated by the calculation unit 12 repeatedly executing machine learning based on the detection data of the LIDAR device MD. The feature amount may be calculated using a combination of one or more of the detection data of the wiper device MN, the camera MC, the rain sensor ME, and the LIDAR device MD. The feature amount may be calculated using any detection data related to precipitation as long as it can be detected.

[0064] The computer program executed in each component of the precipitation level estimation system 1 may be provided in a form recorded on a computer-readable portable recording medium, such as a semiconductor memory, a magnetic recording medium, or an optical recording medium. [Explanation of symbols]

[0065] 1 Precipitation level estimation system, 10 Server device, 12 Calculation unit, 14 Memory unit, 16 Communication unit, 20 Terminal device, 22 Control unit, 24 Memory unit, 26 Display unit, 28 Communication unit, MC Camera, MD Lidar device, ME Rain sensor, MG Position sensor, ML Notification unit, Mn Vehicle, MN Wiper device, MP Control unit, MS Detection unit, MU Communication unit, NW Network, PP Mapping data, Ra First region, Rb Second region, Rm Region, RX Observation target region

Claims

1. Acquire precipitation-related detection data detected by a plurality of vehicles present in an observation target area; a calculation unit that calculates a precipitation amount in a predetermined area included in the observation target area based on the detection data; The calculation unit is Calculating a first characteristic amount for a first predetermined period in the past compared to the present based on first detection data acquired from a first area including the predetermined area; calculating a second feature amount for a second predetermined period in the second region that is older than the first predetermined period based on second detection data acquired in a second region adjacent to the first region; calculating the amount of precipitation using a precipitation estimation model having the first feature amount and the second feature amount as variables, and calculating a precipitation level according to the amount of precipitation; Precipitation level estimation system.

2. The calculation unit is calculating feature amounts including the first feature amount relating to a time ratio during which the wiper device was in operation and the second feature amount relating to a ratio of the number of vehicles during which the wiper device was in operation based on wiper operation data indicating an operation state of a wiper device provided on the vehicle among the detection data, and calculating the amount of precipitation based on the feature amounts; The precipitation level estimation system of claim 1 .

3. The calculation unit calculates the precipitation level in the region, and generates mapping data in which the precipitation level is mapped for each of the plurality of regions in the observation target region. The precipitation level estimation system of claim 1 .

4. The calculation unit extracts the area where the precipitation level is equal to or higher than a reference level from the observation target area based on the mapping data, and provides information about the precipitation level to a user present in the area. The precipitation level estimation system according to claim 3 .

5. Obtaining detection data related to precipitation detected by a plurality of vehicles present in an observation target area; calculating a first characteristic amount for a first predetermined period in the past based on first detection data acquired from a first area included in the observation target area; calculating a second feature amount for a second predetermined period in the second region that is older than the first predetermined period based on second detection data acquired in a second region adjacent to the first region; A program that causes a computer to execute a process of calculating the amount of precipitation in a specified area included in the observation target area using a precipitation estimation model having the first feature and the second feature as variables, and calculating a precipitation level corresponding to the amount of precipitation.

Images