Information processing device, information processing method, and program

Abstract

To provide a technique for making it possible to more accurately determine whether or not abnormality has occurred in a target.SOLUTION: An information processing device is provided that includes: an aggregation unit that aggregates the number of first history per spatiotemporal range based on multiple first histories, each containing time and a location at which sensor data satisfying predetermined conditions is detected; and a threshold calculation unit that calculates a threshold for determining whether or not abnormality has occurred within a predetermined spatiotemporal range based on performing statistical processing on a frequency distribution that is the number of the first history of multiple spatiotemporal ranges corresponding to the predetermined spatiotemporal range.SELECTED DRAWING: Figure 1

Description

[Technical Field]

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

[0002] 2. Description of the Related Art In recent years, a technique has become known for determining whether an abnormality has occurred in an object based on sensor data collected by a sensor.

[0003] For example, Patent Document 1 discloses a system including one or more sensors provided on an object, a first processing unit that determines whether or not sensor data detected by each of the one or more sensors provided on the object is abnormal, and a second processing unit that determines whether or not to issue an abnormality alert based on sensor data previously detected by sensors provided on each of the multiple objects when sensor data determined to be abnormal by the first processing unit is present.

[0004] In such a system, the second processing unit learns in advance the relationship between sensor data previously detected by a sensor provided in each of the multiple objects and abnormalities related to the objects, and then uses the learning results to determine whether to issue an abnormality alert for the object equipped with the sensor that detected the sensor data determined to be abnormal by the first processing unit. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Japanese Patent Application Publication No. 2023-3226 Summary of the Invention [Problem to be solved by the invention]

[0006] However, in the technology described in Patent Document 1, the object for which whether or not an abnormality has occurred is determined is sensor data obtained from a sensor provided on a single object. That is, in the technology described in Patent Document 1, whether or not an abnormality has occurred is determined based on the situation at a single time and a single location, and the learning result. In this way, if whether or not an abnormality has occurred is determined without taking into account the situations at other times and other locations, the accuracy of the determination will not improve.

[0007] Therefore, it is desirable to provide a technology that enables more accurate determination of whether or not an abnormality has occurred in a subject. [Means for solving the problem]

[0008] In order to solve the above problem, according to one aspect of the present invention, there is provided an information processing device comprising: an aggregation unit that aggregates the number of first histories for each spatiotemporal range based on a plurality of first histories, each of which includes a time and a location at which sensor data that satisfies a predetermined condition was detected; and a threshold calculation unit that calculates a threshold for determining whether an abnormality has occurred in the predetermined spatiotemporal range based on performing statistical processing on a frequency distribution, which is the number of first histories in a plurality of spatiotemporal ranges corresponding to the predetermined spatiotemporal range.

[0009] The threshold calculation unit may approximate the frequency distribution to a statistical distribution and calculate the threshold based on the statistical distribution.

[0010] The threshold calculation unit may calculate a mean value of the frequency distribution and approximate the frequency distribution to the statistical distribution having the mean value as an expected value.

[0011] The threshold calculation unit may calculate the threshold based on a standard deviation of the statistical distribution.

[0012] The threshold calculation unit may calculate the threshold by multiplying the standard deviation of the statistical distribution by a predetermined coefficient.

[0013] The counting unit may change a time width or a space width of the spatiotemporal range based on a change operation from a user.

[0014] The counting unit may count the number of the first histories for each of the spatiotemporal ranges based on counting the number of the first histories for each of the spatiotemporal ranges.

[0015] The counting unit may count the number of the first histories for each of the spatiotemporal ranges by adding up a weight value according to the sensor data for each of the spatiotemporal ranges.

[0016] The aggregation unit may aggregate the number of second histories in the specified spatiotemporal range based on a plurality of second histories, each of which includes a time and location at which sensor data satisfying the specified conditions was detected, and the information processing device may include a determination unit that determines whether or not an abnormality has occurred in the specified spatiotemporal range based on the number of second histories and the threshold value.

[0017] The determination unit may change the predetermined coefficient based on the abnormality determination that the abnormality has occurred.

[0018] When the determination unit makes an abnormality determination that the abnormality has occurred, it may determine whether the abnormality determination is an incorrect determination, and change the predetermined coefficient based on the determination that the abnormality determination is an incorrect determination.

[0019] The determination unit may determine whether the abnormality determination is an erroneous determination based on whether a spatiotemporal range in which a predetermined event occurred is outside a predetermined range based on the predetermined spatiotemporal range.

[0020] The sensor that detects the sensor data that satisfies the predetermined condition may be mounted on a moving body.

[0021] In addition, according to another aspect of the present invention to solve the above problem, there is provided an information processing method executed by a computer, which includes: aggregating the number of first histories for each spatiotemporal range based on a plurality of first histories, each of which includes a time and a location at which sensor data satisfying a predetermined condition was detected; and calculating a threshold value for determining whether an abnormality has occurred in the predetermined spatiotemporal range based on performing statistical processing on a frequency distribution, which is the number of first histories in a plurality of spatiotemporal ranges corresponding to the predetermined spatiotemporal range.

[0022] In addition, according to another aspect of the present invention, in order to solve the above-mentioned problem, there is provided a program that causes a computer to function as an aggregation unit that aggregates the number of first histories for each spatiotemporal range based on a plurality of first histories, each of which includes a time and a location at which sensor data that satisfies a predetermined condition was detected, and a threshold calculation unit that calculates a threshold for determining whether an abnormality has occurred in the predetermined spatiotemporal range based on performing statistical processing on a frequency distribution, which is the number of first histories in a plurality of spatiotemporal ranges corresponding to the predetermined spatiotemporal range. [Effects of the Invention]

[0023] As described above, the present invention provides a technique that enables more accurate determination of whether or not an abnormality has occurred in a target. [Brief explanation of the drawings]

[0024] [Figure 1] 1 is a diagram illustrating an example of a functional configuration of an abnormality determination system 1 according to an embodiment of the present invention. [Figure 2] FIG. 2 is a diagram illustrating an example of the configuration of a behavior history. [Figure 3] This is a graph plotting behavior history in space-time. [Figure 4] FIG. 10 is a diagram illustrating an example of a counting result. [Figure 5] FIG. 10 is a diagram showing an example of a counting result corresponding to a spatiotemporal range of a statistical target. [Figure 6] FIG. 10 is a diagram illustrating an example of changing the coefficient of standard deviation. [Figure 7] 4 is a flowchart showing an example of the operation of the abnormality determination system 1 according to the embodiment of the present invention. [Figure 8] 1 is a diagram showing a hardware configuration of an information processing device 900 as an example of an abnormality determination device 10 according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0025] Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. In this specification and drawings, components having substantially the same functional configurations are designated by the same reference numerals, and redundant explanations will be omitted.

[0026] (1. Details of the embodiment) First, details of the embodiment of the present invention will be described.

[0027] (1-1. Configuration of the abnormality determination system) An example of the configuration of an abnormality determination system according to an embodiment of the present invention will be described with reference to Fig. 1. Fig. 1 is a diagram showing an example of the functional configuration of an abnormality determination system 1 according to an embodiment of the present invention.

[0028] (Vehicles C1 to C3) Referring to Figure 1, vehicles C1 to C3 are shown as examples of one or more vehicles. Furthermore, referring to Figure 1, vehicles C1 and C3 are traveling in the rear lane, and vehicle C2 is traveling in the front lane. Thus, in the embodiment of the present invention, it is mainly assumed that the road is made up of multiple lanes, but the road may also be made up of a single lane.

[0029] Note that a vehicle is merely one example of a moving body. Therefore, a vehicle may be replaced with another moving body (for example, a train, etc.). One or more vehicles are each equipped with a sensor that detects the movement of the vehicle. In the embodiment of the present invention, it is mainly assumed that the sensor equipped in the vehicle is an acceleration sensor. In this case, the sensor data obtained by the sensor is the acceleration detected by the acceleration sensor.

[0030] However, the vehicle speed can be measured by a speedometer mounted on the vehicle. Therefore, acceleration calculated based on the change per unit time of the vehicle speed measured by the speedometer may be used instead of the acceleration obtained by the acceleration sensor. Also, sensor data obtained by a sensor other than the acceleration sensor mounted on the vehicle (for example, angular velocity obtained by a gyro sensor) may be used instead of the acceleration.

[0031] Furthermore, the vehicle has a timekeeping function for measuring the current time and a function for obtaining its own location information. For example, the vehicle is equipped with a GNSS (Global Navigation Satellite System) sensor, and the vehicle obtains the latitude and longitude detected by the GNSS sensor as its own location information. The vehicle has a wireless communication function, and can communicate with the acquisition unit 110 using the communication function.

[0032] In the following, it is mainly assumed that when the acceleration detected by an acceleration sensor mounted on the vehicle satisfies a predetermined condition (hereinafter also referred to as a "history registration condition"), the acceleration, the time when the acceleration was obtained by the acceleration sensor, the latitude and longitude, and the vehicle identifier are transmitted as behavior data from the vehicle to the acquisition unit 110. For example, the history registration condition may be a condition that the acceleration exceeds a predetermined value.

[0033] In the following description, it is mainly assumed that whether or not the acceleration satisfies the history registration condition is determined by an on-board device mounted on the vehicle. However, whether or not the acceleration satisfies the history registration condition may also be determined by the aggregation unit 120 provided in the abnormality determination device 10. In this case, the behavior data may be periodically transmitted from the on-board device to the acquisition unit 110. Furthermore, in the embodiment of the present invention, the vehicle identifier is not particularly essential information.

[0034] The abnormality determination system 1 according to the embodiment of the present invention includes a sensor mounted on each of the one or more vehicles, an acquisition unit 110, and an abnormality determination device 10.

[0035] (Abnormality determination device 10) The abnormality determination device 10 functions as an information processing device, and includes a counting unit 120, a storage unit 130, a threshold calculation unit 140, and a determination unit 150. The acquisition unit 110 is connected to the counting unit 120.

[0036] The aggregation unit 120, threshold calculation unit 140, and determination unit 150 each include a computing device such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit), and their functions can be realized by the computing device expanding a program stored in a ROM (Read Only Memory) into a RAM and executing it. In this case, a computer-readable recording medium on which the program is recorded can also be provided.

[0037] Alternatively, the aggregation unit 120, threshold calculation unit 140, and determination unit 150 may be configured by dedicated hardware, or may be configured by a combination of multiple pieces of hardware. Data necessary for calculations by the calculation device is stored as appropriate in the storage unit 130. The storage unit 130 may be configured by a memory such as a RAM (Random Access Memory), a hard disk drive, or a flash memory.

[0038] (Acquisition part 110) The acquisition unit 110 includes an antenna and acquires a plurality of pieces of behavior data received from one or more vehicles by the antenna. The acquisition unit 110 outputs the plurality of pieces of behavior data received from one or more vehicles by the antenna to the aggregation unit 120. The antenna may be a probe antenna.

[0039] (Counting Unit 120) The aggregation unit 120 acquires a plurality of pieces of behavior data from the acquisition unit 110. The aggregation unit 120 performs a process for each piece of behavior data to replace the latitude and longitude included in the behavior data with the distance from a predetermined starting point to a position corresponding to the latitude and longitude (hereinafter also referred to as "distance from the starting point"). For example, when the latitude and longitude of the starting point are predetermined, the aggregation unit 120 may calculate the difference between the latitude and longitude included in the behavior data and the latitude and longitude of the starting point, and calculate the distance corresponding to the calculated difference as the distance from the starting point.

[0040] In the following description, the behavior data after the latitude and longitude are replaced with the distance from the starting point is also referred to as a "behavior history." Note that the distance from the starting point may correspond to the point where the acceleration sensor detected the acceleration. The aggregation unit 120 stores multiple behavior histories in the storage unit 130. Here, an example of the configuration of the behavior history will be described with reference to FIG. 2.

[0041] Fig. 2 is a diagram showing an example of the configuration of a behavior history. Referring to Fig. 2, a plurality of behavior histories are stored in the storage unit 130, and each of the plurality of behavior histories is configured by associating a time, a distance from a starting point, an acceleration, and a vehicle identifier.

[0042] Returning to FIG. 1, the explanation will be continued. The aggregation unit 120 aggregates the number of behavior histories for each spatiotemporal range by counting the number of behavior histories stored in the storage unit 130 for each spatiotemporal range. Here, a spatiotemporal range may be defined by the start time and end time of the spatiotemporal range and the distance from the origin to each of the start point and end point of the spatiotemporal range. An example of a spatiotemporal range will be described with reference to FIG. 3.

[0043] FIG. 3 is a graph plotting behavior history in space-time. In the graph shown in FIG. 3, the horizontal axis represents distance from the starting point, and the vertical axis represents time. Black circles represent behavior history including the time and distance from the starting point. Also, space-time range R1 is shown as an example of a space-time range.

[0044] The start time of space-time range R1 is "2022 / 02 / 02 / 10:00". The end time of space-time range R1 is "2022 / 02 / 02 / 10:05". The distance from the origin to the start point of space-time range R1 is "11.5". The distance from the origin to the end point of space-time range R1 is "12".

[0045] Here, the start time "2022 / 02 / 02 / 10:00" means 10:00 on February 2, 2022, and the end time "2022 / 02 / 02 / 10:05" means 10:05 on February 2, 2022. Furthermore, the distance from the starting point to the start point "11.5" means 11.5 km, and the distance from the starting point to the end point "12" means 12 km. In other words, the time width of the space-time range R1 is 10:05 - 10:00 = 5 minutes, and the spatial width of the space-time range R1 is 12 km - 11.5 km = 0.5 km = 500 m.

[0046] For example, a behavior history that includes a time after the start time "2022 / 02 / 02 / 10:00" and before the end time "2022 / 02 / 02 / 10:05", and a distance from the origin to the start point that is equal to or greater than "11.5" and less than the distance from the origin to the end point that is less than "12", belongs to the spatiotemporal range R1. In the example shown in Figure 3, the number of behavior histories that belong to the spatiotemporal range R1 is one.

[0047] Although not shown in Figure 3, there are one or more other spatiotemporal ranges that have the same time width and spatial width as the spatiotemporal range R1. For example, multiple spatiotemporal ranges that include the spatiotemporal range R1 and the other spatiotemporal ranges may be arranged at predetermined distance intervals (e.g., 500 m intervals) along the horizontal axis of the graph, or at predetermined time intervals (e.g., 5 minutes intervals) along the vertical axis of the graph.

[0048] The aggregation unit 120 stores the number of behavior histories for each spatiotemporal range as an aggregation result in the storage unit 130. For example, the aggregation unit 120 stores in the storage unit 130 an aggregation result in which the end time of the spatiotemporal range R1, "2022 / 02 / 02 / 10:05," the distance from the starting point to the end point of the spatiotemporal range R1, "12," and the number of behavior histories belonging to the spatiotemporal range R1, "1," are associated with each other.

[0049] The distance from the starting point stored in the storage unit 130 does not have to be the distance from the starting point to the end point, "12." For example, the distance from the starting point stored in the storage unit 130 may be the distance from the starting point to the start point, "11.5," or the distance from the starting point to the midpoint, "11.75."

[0050] 4 is a diagram showing an example of the counting result. As shown in FIG. 4, the counting result in which the end time of the spatiotemporal range R1, "2022 / 02 / 02 10:05," the distance from the starting point to the end point of the spatiotemporal range R1, "12," and the number of behavior histories belonging to the spatiotemporal range R1, "1," are associated with each other is stored in the storage unit 130. Similarly, the numbers of behavior histories belonging to other spatiotemporal ranges are also associated with the end times of the spatiotemporal ranges and the distances from the starting point to the end points of the spatiotemporal ranges and stored in the storage unit 130.

[0051] Note that, here, it is mainly assumed that the aggregation unit 120 aggregates the number of behavior histories for each spatiotemporal range by counting the number of behavior histories stored in the storage unit 130 for each spatiotemporal range. However, the aggregation unit 120 may aggregate the number of behavior histories for each spatiotemporal range by adding up, for each spatiotemporal range, a weight value according to acceleration included in the behavior history, instead of the number of behavior histories. For example, the weight value may be larger as the acceleration increases. This allows the magnitude of acceleration to be reflected in the aggregation result.

[0052] Furthermore, the time width or spatial width of the spatiotemporal range may be fixed or variable. When the time width or spatial width of the spatiotemporal range is variable, the aggregation unit 120 may change the time width or spatial width of the spatiotemporal range based on a predetermined change operation input by the user to an input device (e.g., a touch panel or a mouse) connected to the anomaly determination device 10. This allows the granularity of the spatiotemporal range in which an anomaly is determined to exist to be adjusted. For example, if the user wishes to globally monitor whether an anomaly has occurred in the spatiotemporal range, the user may increase the time width or spatial width of the spatiotemporal range. On the other hand, if the user wishes to locally monitor whether an anomaly has occurred in the spatiotemporal range, the user may decrease the time width or spatial width of the spatiotemporal range.

[0053] For example, the predetermined change operation may be an operation to decrease the time width or the space width of the spatiotemporal range (e.g., pressing a button indicating decrease), or an operation to increase the time width or the space width of the spatiotemporal range (e.g., pressing a button indicating increase). In this case, the decrease and increase values ​​of each width may be determined in advance. Alternatively, the changed time width or space width may be input by the user.

[0054] (Storage unit 130) The storage unit 130 stores a plurality of behavior histories (FIG. 2). Furthermore, the storage unit 130 stores a counting result (FIG. 4) in which the end time of a spatiotemporal range, the distance from the start point to the end point of the spatiotemporal range, and the number of behavior histories belonging to the spatiotemporal range are associated with each other.

[0055] (Threshold calculation unit 140) The threshold calculation unit 140 calculates a threshold for determining whether an abnormality has occurred in a predetermined spatiotemporal range by performing statistical processing on a frequency distribution, which is the number of behavior histories in a plurality of spatiotemporal ranges corresponding to the predetermined spatiotemporal range. By calculating the threshold in this manner, it may be possible to more accurately determine whether an abnormality has occurred in the predetermined spatiotemporal range using the threshold.

[0056] The predetermined spatiotemporal range is also referred to as the "spatiotemporal range to be determined," and each of the multiple spatiotemporal ranges corresponding to the predetermined spatiotemporal range is also referred to as the "spatiotemporal range to be statistically determined." A behavior history that belongs to the spatiotemporal range to be statistically determined may correspond to the first history. On the other hand, a behavior history that belongs to the spatiotemporal range to be determined may correspond to the second history.

[0057] The spatiotemporal range to be determined may be determined arbitrarily. For example, the spatiotemporal range to be determined may be specified by a user. Furthermore, the spatiotemporal range to be used as the statistical target may have an end time earlier than the spatiotemporal range to be determined and may be the same distance from the starting point.

[0058] Fig. 5 is a diagram showing an example of a counting result corresponding to a spatiotemporal range of a statistical target. Referring to Fig. 5, the counting result corresponding to the spatiotemporal range of a statistical target shows the end time of the spatiotemporal range of a statistical target, the distance from the start point to the end point, and the number of behavior histories belonging to the spatiotemporal range of a statistical target, all of which are associated with each other.

[0059] Here, it is mainly assumed that the spatiotemporal range to be determined has a start time of "2022 / 02 / 02 / 11:55", an end time of "2022 / 02 / 02 / 12:00", the distance from the origin to the start point is "11.5", and the distance from the origin to the end point is "12". Furthermore, the time width of the spatiotemporal range to be statistically analyzed does not need to be limited, but here it is assumed to be 2 hours (i.e., 120 minutes).

[0060] In this case, as shown in Figure 5, the spatiotemporal range to be statistically analyzed may have a start time ranging from "2022 / 02 / 02 / 10:00", two hours before the end time of the spatiotemporal range to be evaluated, "2022 / 02 / 02 / 12:00", to "11:55", just before the end time, and the distance from the starting point to the end point is the same as the distance from the starting point to the end point of the spatiotemporal range to be evaluated, "12".

[0061] The threshold calculation unit 140 generates a frequency distribution of the number of behavior histories for each spatiotemporal range of the statistical target, and calculates a threshold for determining whether an abnormality has occurred in the spatiotemporal range of the target based on statistical processing of the generated frequency distribution.

[0062] More specifically, the threshold calculation unit 140 may approximate the generated frequency distribution to a predetermined statistical distribution and calculate the threshold based on the statistical distribution. Note that the type of statistical distribution is not limited, and may be a Poisson distribution, a normal distribution, or another statistical distribution.

[0063] More specifically, the threshold calculation unit 140 may calculate the average value of the generated frequency distribution and approximate the frequency distribution to a statistical distribution whose expected value is the calculated average value. Furthermore, the threshold calculation unit 140 may calculate the threshold based on the standard deviation of the statistical distribution. For example, the threshold calculation unit 140 may calculate the threshold by multiplying the standard deviation of the statistical distribution by a predetermined coefficient (hereinafter also referred to as the "coefficient of standard deviation").

[0064] Here, it is mainly assumed that the threshold calculation unit 140 calculates two thresholds. Hereinafter, of the two thresholds, the relatively larger threshold will also be referred to as the "upper limit of the normal range," and the relatively smaller threshold will also be referred to as the "lower limit of the normal range." The threshold calculation unit 140 can calculate the two thresholds, the upper limit of the normal range and the lower limit of the normal range, as shown in the following equations (1) and (2).

[0065] (Upper limit of normal range) = (expected value) + (standard deviation coefficient) × (standard deviation)…(1) (Lower limit of normal range) = (Expected value) - (Standard deviation coefficient) x (Standard deviation)...(2)

[0066] In the above formulas (1) and (2), the standard deviation is the positive square root of the expected value. If the calculated expected value is less than 1, the threshold calculation section 140 may correct the expected value to 1.

[0067] The threshold calculation unit 140 may use a standard deviation coefficient determined by the user or the threshold calculation unit 140. For example, the standard deviation coefficient may be determined according to the type of abnormality to be determined. The type of abnormality may be an accident, a fire, or the presence of an obstacle on the road. For example, the lower the importance of the abnormality to be determined, the larger the value determined as the standard deviation coefficient, making it more difficult to determine the abnormality.

[0068] (Judgment section 150) The determination unit 150 determines whether or not an abnormality has occurred in the spatiotemporal range to be determined based on the number of behavior histories in the spatiotemporal range to be determined and the threshold calculated by the threshold calculation unit 140, and obtains a determination result. The determination unit 150 may output the determination result to a predetermined output device connected to the abnormality determination device 10, thereby causing the output device to output the determination result. For example, the output device may be a display or the like.

[0069] For example, the determination unit 150 may determine that an abnormality has occurred in the spatiotemporal range to be determined when the number of behavior histories in the spatiotemporal range to be determined exceeds the upper limit of the normal range or falls below the lower limit of the normal range. On the other hand, the determination unit 150 may determine that an abnormality has not occurred in the spatiotemporal range to be determined when the number of behavior histories in the spatiotemporal range to be determined is equal to or greater than the lower limit of the normal range and is equal to or less than the upper limit of the normal range.

[0070] The determination unit 150 may change the coefficient of the standard deviation based on the determination that an abnormality has occurred. For example, when the determination unit 150 determines that an abnormality has occurred, the determination unit 150 may determine whether the abnormality determination is an erroneous determination.

[0071] Fig. 6 is a diagram illustrating an example of changing the coefficient of standard deviation. Fig. 6 shows a position P1 corresponding to the spatiotemporal range R2 to be determined. Position P1 is a combination of the end time of the spatiotemporal range R2 to be determined, "2022 / 02 / 02 / 10:06," and the distance from the starting point to the end point of the spatiotemporal range R2 to be determined, "12."

[0072] Position P2 is a position corresponding to spatiotemporal range R3 in which a predetermined event occurred. Position P2 is a combination of the end time of spatiotemporal range R3 in which the predetermined event occurred, "2022 / 02 / 02 / 10:02," and the distance from the starting point to the end point of spatiotemporal range R3 in which the predetermined event occurred, "12.5." The predetermined event may also be an accident, a fire, or the presence of an obstacle on the road.

[0073] The reference range Q1 is a predetermined range based on the spatiotemporal range R2 to be determined. Here, the shape of the reference range Q1 does not have to be limited to a rectangular shape. Furthermore, the size of the reference range Q1 does not have to be limited.

[0074] Here, if position P2 corresponding to spatiotemporal range R3 where a predetermined event occurred is outside the reference range Q1, the abnormality determination that an abnormality has occurred in the spatiotemporal range R2 to be determined is considered to be an erroneous determination. On the other hand, if position P2 corresponding to spatiotemporal range R3 where a predetermined event occurred is within the reference range Q1, the abnormality determination that an abnormality has occurred in the spatiotemporal range R2 to be determined is considered not to be an erroneous determination.

[0075] Therefore, the judgment unit 150 may judge whether or not the abnormality judgment that an abnormality has occurred in the spatiotemporal range R2 being judged is an erroneous judgment, depending on whether or not the position P2 corresponding to the spatiotemporal range R3 in which a specified event occurred is outside the reference range Q1.

[0076] Then, the determination unit 150 may change the coefficient of the standard deviation based on the determination that the abnormality determination is an erroneous determination. More specifically, the determination unit 150 may increase the coefficient of the standard deviation based on the determination that the abnormality determination is an erroneous determination, thereby making it more difficult to determine an abnormality.

[0077] The configuration example of the abnormality determination system 1 according to the embodiment of the present invention has been described above.

[0078] (1-2. Configuration of the abnormality determination system) Next, an example of the operation of the abnormality determination system 1 according to the embodiment of the present invention will be described.

[0079] 7 is a flowchart showing an example of the operation of the abnormality determination system 1 according to an embodiment of the present invention. As shown in FIG. 7, in the abnormality determination system 1, the acquisition unit 110 acquires a plurality of pieces of behavior data received from one or more vehicles via an antenna (S11). The acquisition unit 110 outputs the plurality of pieces of behavior data received from one or more vehicles via the antenna to the aggregation unit 120.

[0080] The aggregation unit 120 performs a process of replacing the latitude and longitude included in the behavior data with the distance from the starting point for each of the plurality of behavior data to obtain a plurality of behavior histories (FIG. 2). The aggregation unit 120 counts the number of behavior histories for each spatiotemporal range, and then aggregates the number of behavior histories for each spatiotemporal range (S12). The aggregation unit 120 stores the number of behavior histories for each spatiotemporal range as the aggregation result in the storage unit 130.

[0081] The threshold calculation unit 140 calculates a normal range based on the counting result (FIG. 4) stored in the storage unit 130 (S13). More specifically, the threshold calculation unit 140 calculates a normal range for determining whether an abnormality has occurred in the spatiotemporal range of the determination target, based on performing statistical processing on a frequency distribution that is the number of behavior histories in the spatiotemporal range of the statistical target corresponding to the spatiotemporal range of the determination target.

[0082] The determination unit 150 determines whether or not the number of behavior histories belonging to the spatiotemporal range to be determined is within the normal range calculated by the threshold calculation unit 140 (S14).

[0083] If the number of behavior histories belonging to the spatiotemporal range to be determined is within the normal range calculated by the threshold calculation unit 140 ("YES" in S14), the determination unit 150 determines that the spatiotemporal range to be determined is normal (S16). On the other hand, if the number of behavior histories belonging to the spatiotemporal range to be determined is outside the normal range calculated by the threshold calculation unit 140 ("NO" in S14), the determination unit 150 determines that an abnormality has occurred in the spatiotemporal range to be determined (S15).

[0084] An example of the operation of the abnormality determination system 1 according to the embodiment of the present invention has been described above.

[0085] (1-3. Effects) As described above, according to an embodiment of the present invention, there is provided an abnormality determination device 10 including: an aggregation unit 120 that aggregates the number of behavior histories for each spatiotemporal range based on a plurality of behavior histories, each of which includes the time at which acceleration that satisfies a history registration condition was detected and the distance from a starting point; and a threshold calculation unit 140 that calculates a threshold for determining whether an abnormality has occurred in the spatiotemporal range of the determination target, based on performing statistical processing on a frequency distribution that is the number of behavior histories in a plurality of spatiotemporal ranges of statistical targets that correspond to the spatiotemporal range of the determination target.

[0086] Unlike configurations that determine whether an abnormality has occurred based on the situation at a single time and a single location, this configuration determines whether an abnormality has occurred by taking into account the situations at other times and other locations, thereby achieving the effect of more accurately determining whether an abnormality has occurred in the target.

[0087] The effects achieved by the abnormality determination system 1 according to the embodiment of the present invention have been described above.

[0088] (2. Hardware configuration example) Next, an example of the hardware configuration of the abnormality determination device 10 according to the embodiment of the present invention will be described.

[0089] An example of the hardware configuration of an information processing device 900 will be described below as an example of the hardware configuration of the abnormality determination device 10 according to an embodiment of the present invention. Note that the example of the hardware configuration of the information processing device 900 described below is merely one example of the hardware configuration of the abnormality determination device 10. Therefore, the hardware configuration of the abnormality determination device 10 may be such that unnecessary components are deleted from the hardware configuration of the information processing device 900 described below, or new components are added.

[0090] 8 is a diagram showing a hardware configuration of an information processing device 900 as an example of the abnormality determination device 10 according to an embodiment of the present invention. The information processing device 900 includes a CPU (Central Processing Unit) 901, a ROM (Read Only Memory) 902, a RAM (Random Access Memory) 903, a host bus 904, a bridge 905, an external bus 906, an interface 907, an input device 908, an output device 909, a storage device 910, and a communication device 911.

[0091] The CPU 901 functions as an arithmetic processing unit and control unit, and controls the overall operation of the information processing device 900 in accordance with various programs. The CPU 901 may also be a microprocessor. The ROM 902 stores programs used by the CPU 901, calculation parameters, etc. The RAM 903 temporarily stores programs used in the execution of the CPU 901, parameters that change as appropriate during the execution, etc. These are interconnected by a host bus 904 that is composed of a CPU bus, etc.

[0092] The host bus 904 is connected to an external bus 906, such as a PCI (Peripheral Component Interconnect / Interface) bus, via a bridge 905. It is not necessary to configure the host bus 904, bridge 905, and external bus 906 separately, and these functions may be implemented on a single bus.

[0093] The input device 908 is composed of input means such as a mouse, keyboard, touch panel, buttons, microphone, switches, and levers that allow the user to input information, and an input control circuit that generates an input signal based on the user's input and outputs it to the CPU 901. By operating this input device 908, the user operating the information processing device 900 can input various data to the information processing device 900 and instruct the information processing device 900 to perform processing operations.

[0094] The output device 909 includes, for example, a display device such as a CRT (Cathode Ray Tube) display device, a liquid crystal display (LCD) device, an OLED (Organic Light Emitting Diode) device, or a lamp, and an audio output device such as a speaker.

[0095] The storage device 910 is a device for storing data. The storage device 910 may include a storage medium, a recording device for recording data on the storage medium, a reading device for reading data from the storage medium, and a deletion device for deleting data recorded on the storage medium. The storage device 910 is configured, for example, with an HDD (Hard Disk Drive). This storage device 910 drives a hard disk and stores programs executed by the CPU 901 and various data.

[0096] The communication device 911 is, for example, a communication interface configured with a communication device for connecting to a network, etc. The communication device 911 may be compatible with either wireless communication or wired communication.

[0097] An example of the hardware configuration of the abnormality determination device 10 according to the embodiment of the present invention has been described above.

[0098] (3. Various Modifications) Although the preferred embodiments of the present invention have been described in detail above with reference to the accompanying drawings, the present invention is not limited to these examples. It is clear that a person skilled in the art to which the present invention pertains can conceive of various modifications and alterations within the scope of the technical ideas set forth in the claims, and it is understood that these also naturally fall within the technical scope of the present invention.

[0099] For example, in the above description, it is mainly assumed that the sensor for detecting the sensor data is mounted on a mobile object. However, the sensor for detecting the sensor data may not be mounted on a mobile object but may be fixed at a predetermined location.

[0100] For example, if the moving object is a vehicle, a sensor for detecting sensor data may be fixed to the side of a road or the like. In this case, the sensor may be a LiDAR (Light Detection and Ranging) sensor for detecting point cloud data. The aggregation unit 120 may then detect the position of the moving object from the point cloud data detected by the LiDAR sensor and replace the detected position of the moving object with the distance from the starting point. The aggregation unit 120 may also calculate the acceleration based on the amount of change per unit time in the position of the detected moving object. [Explanation of symbols]

[0101] 1. Abnormality detection system 10 Abnormality determination device 110 Acquisition Department 120 Counting Unit 130 Storage section 140 Threshold calculation unit 150 Judgment section

Claims

1. a counting unit that counts the number of first histories for each spatiotemporal range based on a plurality of first histories, each of which includes a time and a location at which sensor data satisfying a predetermined condition was detected; a threshold calculation unit that calculates a threshold for determining whether an abnormality has occurred in a predetermined spatiotemporal range based on a frequency distribution that is the number of first histories in a plurality of spatiotemporal ranges corresponding to the predetermined spatiotemporal range; An information processing device comprising:

2. the threshold calculation unit approximates the frequency distribution to a statistical distribution and calculates the threshold based on the statistical distribution. The information processing device according to claim 1 .

3. the threshold calculation unit calculates an average value of the frequency distribution and approximates the frequency distribution to the statistical distribution having the average value as an expected value; The information processing device according to claim 2 .

4. the threshold calculation unit calculates the threshold based on a standard deviation of the statistical distribution. The information processing device according to claim 2 .

5. the threshold calculation unit calculates the threshold by multiplying the standard deviation of the statistical distribution by a predetermined coefficient; The information processing device according to claim 4 .

6. the aggregation unit changes the time width or the space width of the spatiotemporal range based on a change operation from a user. The information processing device according to claim 1 .

7. the counting unit counts the number of the first histories for each of the spatiotemporal ranges, and then counts the number of the first histories for each of the spatiotemporal ranges. The information processing device according to claim 1 .

8. the tallying unit tallying the number of the first histories for each of the spatio-temporal ranges by adding up weight values ​​according to the sensor data for each of the spatio-temporal ranges; The information processing device according to claim 1 .

9. the counting unit counts the number of second histories in the predetermined spatiotemporal range based on a plurality of second histories, each of which includes a time and a location at which sensor data satisfying the predetermined condition was detected; The information processing device includes: a determination unit that determines whether or not an abnormality has occurred in the predetermined spatiotemporal range based on the number of second histories and the threshold value, The information processing device according to claim 1 .

10. the determination unit changes the predetermined coefficient based on the abnormality determination that the abnormality has occurred. The information processing device according to claim 9 .

11. When the determination unit determines that the abnormality has occurred, the determination unit determines whether the abnormality determination is an erroneous determination, and changes the predetermined coefficient based on the determination that the abnormality determination is an erroneous determination. The information processing device according to claim 10.

12. the determination unit determines whether the abnormality determination is an erroneous determination based on whether a spatiotemporal range in which a predetermined event has occurred is outside a predetermined range based on the predetermined spatiotemporal range. The information processing device according to claim 11.

13. the sensor that detects the sensor data that satisfies the predetermined condition is mounted on a moving body; The information processing device according to claim 1 .

14. tallying the number of first histories for each spatiotemporal range based on a plurality of first histories, each of which includes a time and a point at which sensor data satisfying a predetermined condition was detected; calculating a threshold value for determining whether an abnormality has occurred in a predetermined spatiotemporal range based on a frequency distribution, which is the number of the first histories in a plurality of spatiotemporal ranges corresponding to the predetermined spatiotemporal range, performed statistical processing on the frequency distribution; 2. A computer-implemented information processing method, comprising:

15. Computer, a counting unit that counts the number of first histories for each spatiotemporal range based on a plurality of first histories, each of which includes a time and a location at which sensor data satisfying a predetermined condition was detected; a threshold calculation unit that calculates a threshold for determining whether an abnormality has occurred in a predetermined spatiotemporal range based on a frequency distribution that is the number of first histories in a plurality of spatiotemporal ranges corresponding to the predetermined spatiotemporal range; A program that functions as a

Images