Prediction device

Abstract

This prediction device comprises a control unit. The control unit sets an extraction range around a target object, and calculates, on the basis of the disaster rate of objects extracted from the extraction range, the disaster rate of the target object at the time of a target disaster to be predicted.

Description

Prediction device

[0001] This disclosure relates to a prediction device.

[0002] Conventionally, technologies for predicting damage to structures and other objects during disasters have been developed. As described in Non-Patent Document 1, the Central Research Institute of Electric Power Industry has developed a typhoon wind speed prediction system (RAMP-T: Risk Assessment and Management system for Power lifeline - Typhoon) to predict wind speed during typhoons. They have also developed an earthquake damage estimation system (RAMP-Er: Risk Assessment and Management system for Power lifeline - Earthquake real time). A technology has also been developed to display the combined analysis results of this earthquake damage estimation system and the typhoon wind speed prediction system on a map (Non-Patent Document 2). In addition, a technology for estimating earthquake damage to wooden houses at the municipal level based on the results of urban planning basic surveys and seismic motion is being researched (Non-Patent Document 3).

[0003] Soichiro Sugimoto et al., "Introduction of a System for Estimating Equipment Damage Caused by Typhoons and Meteorological Simulation," IEEJ Journal, Vol. 138, No. 3, pp. 141-144, 2018. T. Tadokoro et al., "Automatic Generation of Input Data for Distribution System Simulation Programs," IEEE Innovative Smart Grid Technologies - Asia (ISGT Asia), IEEE, 2018. Sho Yokoya et al., "Research on Estimating Earthquake Damage to Wooden Houses Using Basic Urban Planning Survey Data," Transactions of the Japan Association for Earthquake Engineering, Vol. 23, No. 4, 2023.

[0004] Incidentally, it has been confirmed that an object can be involved in the damage suffered by another object and be damaged thereby. However, there is no technology for predicting the damage to an object in consideration of such a point. If the damage that an object suffers by being involved in the damage of another object is taken into account, the damage to the object during a disaster can be predicted more accurately.

[0005] In view of such a point, an object of the present disclosure is to more accurately predict the damage to an object during a disaster.

[0006] A prediction device according to an embodiment of the present disclosure sets an extraction range around a target object, and includes a control unit that calculates the disaster rate of the target object at the time of a target disaster to be predicted based on the disaster rate of the objects extracted from the extraction range.

[0007] According to an embodiment of the present disclosure, the damage to an object during a disaster can be predicted more accurately.

[0008] It is a block diagram showing an example of a prediction device according to an embodiment of the present disclosure. It is a diagram showing an example of disaster rate data of an object. It is a diagram showing an example of disaster rate data of an object. It is a flowchart showing an example of a prediction method according to an embodiment of the present disclosure. It is a diagram for explaining a first example of setting an extraction range. It is a diagram for explaining a second example of setting an extraction range. It is a diagram for explaining a third example of setting an extraction range. It is a diagram for explaining a fourth example of setting an extraction range. It is a diagram for explaining a fifth example of setting an extraction range. It is a diagram for explaining an example of setting a weighting coefficient. It is a diagram for explaining an example of setting a weighting coefficient.

[0009] Hereinafter, embodiments according to the present disclosure will be described with reference to the drawings.

[0010] (Example of Configuration of Prediction Device) A prediction device 10 according to an embodiment of the present disclosure as shown in FIG. 1 can predict the damage to a target object during a disaster. The target object is an object for which damage is to be predicted. The target object is, for example, a utility pole, a reinforced structure, a wooden house, a tree, a road, a signal pole, or a footbridge. The target object may be a ground structure located on the ground. The target object may be a structure on a road. However, the target object may be an object of any type.

[0011] In this embodiment, the prediction device 10 calculates the disaster rate of the target object as a prediction of the damage to the target object. The disaster rate of the target object is the probability that the target object is damaged during a disaster. As will be described later, the prediction device 10 calculates the disaster rate of the target object during the target disaster that is the target of the prediction.

[0012] The prediction device 10 includes an input unit 11, an output unit 12, a storage unit 13, and a control unit 14.

[0013] The input unit 11 can receive an input from the user. The input unit 11 includes at least one input interface capable of receiving an input from the user. The input interface is, for example, a physical key, a capacitive key, a pointing device, a touch screen provided integrally with the display of the output unit 12, or a microphone or the like.

[0014] The output unit 12 can output data. The output unit 12 includes at least one output interface capable of outputting data. The output interface is, for example, a display or a speaker or the like.

[0015] The storage unit 13 includes at least one semiconductor memory, at least one magnetic memory, at least one optical memory, or a combination of at least two of these. The storage unit 13 may function as a main memory device, an auxiliary memory device, or a cache memory. The storage unit 13 stores data used for the operation of the prediction device 10 and data obtained by the operation of the prediction device 10. A program executed by the control unit 14 may be stored in the storage unit 13.

[0016] Disaster rate data of the object is stored in the storage unit 13. Based on this disaster rate data of the object, the disaster rate of the target object is calculated as will be described later. For example, disaster rate data of the object as shown in FIGS. 2 and 3 is stored in the storage unit 13.

[0017] The object damage rate data associates the type of object with the type of disaster and the object's damage rate. Examples of object types include utility poles, reinforced concrete structures, wooden houses, trees, roads, traffic light poles, or pedestrian bridges. However, the object type can be arbitrary, as long as it is an object that may be involved in the object's damage rate. Examples of disaster types include earthquakes, heavy rain, storms, or landslides. However, the disaster type may be determined based on the target disaster. The object damage rate indicates the probability that the object will be damaged during the disaster associated with that object in the object damage rate data.

[0018] Depending on the type of disaster, the data on the damage rate of objects may include the damage rate of objects for each level indicating the severity of the disaster.

[0019] The level indicating the severity of a disaster, in the case of an earthquake, is, for example, the intensity of the ground motion. Any index indicating the intensity of ground motion may be used. Examples of such indexes include the seismic intensity scale, instrumental seismic intensity, maximum ground surface velocity of the ground motion, ground surface acceleration of the ground motion, waveform displacement converted from instrumental seismic intensity, converted displacement converted from instrumental seismic intensity, etc., the dominant period of the ground motion, or at least two combinations of these. Converted displacement is obtained by dividing the square of the velocity of the seismic wave by the acceleration of the seismic wave. Also, in the case of an earthquake, the level indicating the severity of the disaster may use an index other than an earthquake, either in combination with or instead of an index indicating the intensity of ground motion. Examples of other indexes include ground conditions. An example of a ground condition index is an index indicating the strength of the ground, such as AVS30. AVS30 is the average S-wave velocity from the ground surface to a depth of 30m. In Figure 2, the seismic intensity scale is used as the level indicating the severity of the disaster. The seismic intensity scale includes seismic intensity 5+, seismic intensity 6-, seismic intensity 6+, and seismic intensity 7. In Figure 2, the types of objects include reinforced concrete structures, wooden houses, trees, and roads. In other words, the damage rate data for objects shown in Figure 2 includes the damage rate of these objects for each seismic intensity of 5+, seismic intensity 6-, seismic intensity 6+, and seismic intensity 7.

[0020] The level indicating the degree of the disaster is, for example, the amount of rainfall when the disaster is heavy rain. Any index indicating the amount of rainfall may be used for this amount of rainfall. As the index indicating the amount of rainfall, for example, the maximum rainfall per hour, the soil rainfall index, the 24-hour precipitation amount, or a combination of at least two of these may be used. Further, when the disaster is heavy rain, the level indicating the degree of the disaster may be one using an index other than the amount of rainfall in combination with or instead of the index indicating the amount of rainfall. In FIG. 3, the maximum rainfall per hour is used as the level indicating the degree of the disaster. The maximum rainfall per hour is 0 to f １ mm, f １ to f ２ mm and f ２ to f ３ mm. Also, in FIG. 3, the types of objects include steel structures, wooden houses, trees, roads, etc. That is, the disaster rate data of the objects shown in FIG. 3 is for the objects at 0 to f １ mm, f １ to f ２ mm and f ２ to f ３ mm for each of these objects' disaster rates.

[0021] The disaster rate data of the objects may be generated or acquired by any method and stored in the storage unit 13. As an example, the method for generating the disaster rate data of the objects shown in FIG. 2 will be described.

[0022] The object damage rate data shown in Figure 2 is calculated from data from past large-scale earthquakes. For example, the object damage rate is calculated by dividing the number of objects damaged within the same seismic motion during past large-scale earthquakes by the total number of such objects. Alternatively, the object damage rate may be calculated using a model that regresses the object damage rates from past large-scale earthquakes using a linear or logistic curve according to the intensity of the seismic motion. Yet another example is using the probability of an object breaking, calculated by a prediction model. This prediction model is constructed, for example, using data from past large-scale earthquakes and machine learning. Machine learning methods include, for example, gradient boosting, random forests, or neural networks. However, the machine learning method used to construct the prediction model can be arbitrary. The object damage rate shown in Figure 3 is also calculated from data from past heavy rainfall events in the same or similar manner as in Figure 2.

[0023] Here, the data on the damage rate of objects stored in the memory unit 13 is not limited to the table data shown in Figures 2 and 3. If the level indicating the degree of disaster is a continuous value, instead of the table data, a function of the damage rate of objects with the level indicating the degree of disaster as a variable may be stored in the memory unit 13. The type of object and the type of disaster may be associated with this function of the damage rate of objects.

[0024] The control unit 14 is configured to include at least one processor, at least one dedicated circuit, or a combination thereof. The processor is, for example, a general-purpose processor such as a CPU (Central Processing Unit) or a GPU (Graphics Processing Unit), or a dedicated processor specialized for a specific process. The dedicated circuit is, for example, an FPGA (Field-Programmable Gate Array) or an ASIC (Application Specific Integrated Circuit). The control unit 14 controls each part of the prediction device 10 and executes processes related to the operation of the prediction device 10.

[0025] The control unit 14 obtains the damage rate of objects surrounding the target object from the damage rate data of objects stored in the memory unit 13. Based on the obtained damage rates of objects, the control unit 14 calculates the damage rate of the target object. With this configuration, the calculated damage rate of the target object can reflect the damage the target object may receive from other surrounding objects. As a result, the damage to the target object in the event of a disaster can be predicted with greater accuracy. The processing of the control unit 14 will be described in detail below with reference to Figure 4.

[0026] (Example of operation of the prediction device) Figure 4 is a flowchart showing an example of a prediction method according to one embodiment of the present disclosure. When the control unit 14 receives, for example, an instruction from the user to perform the calculation of the damage rate of the target object via the input unit 11, it starts the process of step S1.

[0027] <Step S1> In the process of step S1, the control unit 14 receives the location information of the target object, the shape information of the target object, the information of the target disaster, the object information, and the terrain information from the user via the input unit 11.

[0028] For example, the elevation information of the target object may be associated with the object's location information. The elevation information may be from the National Land Numerical Information provided by the Ministry of Land, Infrastructure, Transport and Tourism <https: / / www.mlit.go.jp / tochi_fudousan_kensetsugyo / chirikukannjoho / tochi_fudousan_kensetsugyo_tk17_000001_00028.html> or from the Fundamental Geospatial Information Authority of Japan <https: / / fgd.gsi.go.jp / download / ref_dem.html>.

[0029] The shape information of the target object may include, for example, information about the external shape of the target object. The shape information of the target object may also include information about the size of the target object. The size information of the target object may include, for example, information about the width, depth, and height of the target object.

[0030] As mentioned above, the information on the target disaster is information on the disaster that is the subject of the prediction. In other words, the damage rate of the target object during the target disaster is calculated. The information on the target disaster includes, for example, information on the type of target disaster. Examples of target disaster types include earthquakes, heavy rain, storms, or landslides. If the type of target disaster is a storm, the information on the target disaster may include information on wind direction and wind speed.

[0031] Object information includes, for example, information about objects located around the target object. Object information includes, for example, information about the type of object, information about the weight of the object, information about the location of the object, and information about the shape of the object. Examples of object types include utility poles, reinforced concrete structures, wooden houses, trees, roads, traffic light poles, or pedestrian bridges. Object shape information includes information about the external shape of the object. Object shape information may include information about the size of the object. Object size information includes, for example, information about the width, depth, and height of the object.

[0032] Topographic information refers to information about the shape of the land on which the object in question is located. Topographic information may include elevation information of the land. For elevation information, the same or similar information as the location information of the object in question may be used, such as national land numerical information provided by the Ministry of Land, Infrastructure, Transport and Tourism or fundamental map information provided by the Geospatial Information Authority of Japan.

[0033] <Step S2> In step S2, the control unit 14 sets an extraction range around the target object based on at least one of the various pieces of information acquired in step S1. This extraction range is the range from which object data is extracted in step S3. The control unit 14 may set the extraction range based on at least one of the type of target disaster and the shape information of the target object acquired in step S1. Examples of setting the extraction range will be explained below with reference to Figures 5 to 9. In Figures 5 to 8, the target object is a utility pole.

[0034] [Setting Example 1] As shown in Figure 5, the control unit 14 sets the extraction range to an area with a predetermined radius r1 centered on the target object if the target object can be approximated by a point in a plan view. The predetermined radius r1 may be set according to the type of target disaster. The control unit 14 may also determine whether the target object can be approximated by a point in a plan view based on the shape information of the target object. The control unit 14 determines that the target object can be approximated by a point in a plan view if the area of ​​the target object in a top view is below a first area threshold. The first area threshold may be set according to the shape of the land on which the target object is located.

[0035] [Setting Example 2] When the type of disaster to be detected is a landslide, the control unit 14 sets the extraction range to the area within a predetermined radius r2 centered on the target object, where the elevation is higher than the location of the target object, as shown in Figure 6. The predetermined radius r2 may be set based on the area where landslides have occurred in the past. For example, the control unit 14 sets the extraction range to the area where the elevation is higher than the location of the target object, based on the location information and terrain information of the target object.

[0036] [Setting Example 3] When the type of target disaster is a storm, the control unit 14 weights the area around a predetermined radius r3 centered on the target object based on the wind direction W1 and wind speed V1 in the storm, as shown in Figure 7. The control unit 14 sets the extraction range by weighting the area around a predetermined radius r3 centered on the target object based on the wind direction W1 and wind speed V1 included in the information on the target disaster. The predetermined radius r3 may be set based on the area that has been affected by storms in the past. For example, the control unit 14 sets the weighting of the predetermined radius r3 to increase as the direction of the vector of the predetermined radius r3 moving outward from the center of the target object approaches the opposite direction to the wind direction W1. The maximum weighting may be set based on the wind speed V1. In Figure 7, the control unit 14 sets the weighting of the predetermined radius r3 to (1 + V1) when the direction of the vector of the predetermined radius r3 moving outward from the center of the target object is opposite to the wind direction W1. Furthermore, the control unit 14 is configured such that the weighting of the predetermined radius r3 decreases as the direction of the vector of the predetermined radius r3, which extends outward from the center of the target object, approaches the same direction as the wind direction W1. In Figure 7, the control unit 14 sets the weighting of the predetermined radius r3 to 1 when the direction of the vector of the predetermined radius r3, which extends outward from the center of the target object, is the same direction as the wind direction W1.

[0037] [Setting Example 4] When the type of disaster is an earthquake, the control unit 14 identifies a range around a predetermined radius r1 centered on the target object, as in Setting Example 1, and sets a portion of the identified range as the extraction range. For example, as shown in Figure 8, the control unit 14 identifies objects from within the range around the predetermined radius r1, based on the position information and information of the target object, where the distance between the target object and other objects is shorter than the height of the object. The control unit 14 sets the range from the center of the target object to the identified object as the extraction range, within the range around the predetermined radius r1 centered on the target object. The width to include in the range from the center of the target object to the identified object, as indicated by the arrow in Figure 8, may be set based on topographic information. Here, if the object is a structure such as a building, the possibility of the object collapsing in an earthquake increases. Also, if the object collapses in an earthquake, and the distance between the target object and other objects is shorter than the height of the collapsed object, the possibility of the target object being caught in the collapse increases. Therefore, setting such an extraction range is useful when predicting damage to the target object in an earthquake.

[0038] [Setting Example 5] As shown in Figure 9, the control unit 14 sets the extraction range to a predetermined distance r4 from the periphery of the target object if the target object can be approximated linearly in a plan view. The predetermined distance r4 may be set according to the type of target disaster. The control unit 14 may also determine whether the target object can be approximated linearly in a plan view based on the shape information of the target object. For example, the control unit 14 determines that the target object can be approximated linearly if the ratio of the horizontal length to the vertical length of the target object in a plan view is greater than or equal to a ratio threshold. The ratio threshold may be set according to the shape of the land on which the target object is located.

[0039] The control unit 14 may apply setting example 5 to any shape of the target object in plan view. That is, the control unit 14 may set the extraction range to a predetermined distance r4 from the periphery of the target object in plan view, based on the shape information of the target object. As an example, if the area of ​​the target object in plan view is greater than or equal to the second area threshold, the control unit 14 may set the extraction range to a predetermined distance r4 from the periphery of the target object. The control unit 14 may determine, based on the shape information of the target object, whether or not the area of ​​the target object in plan view is greater than or equal to the second area threshold. The second area threshold may be set according to the shape of the land on which the target object is located. The second area threshold may be the same as the first area threshold, or it may be different from the first area threshold.

[0040] In step S2, the control unit 14 may set the extraction range by combining setting examples 1 to 4. The control unit 14 may also apply at least one of setting examples 1 to 4 to an object that can be approximated linearly or planarly in a planar view. The control unit 14 may determine whether the object can be approximated planarly based on the shape information of the object. For example, the control unit 14 determines that the object can be approximated planarly if the curvature of the object with respect to a plane is below a curvature threshold. The curvature threshold may be set based on the shape of the land on which the object is located.

[0041] <Step S3> In step S3, the control unit 14 extracts object data from the extraction range set in step S2. For example, the control unit 14 extracts object data from the extraction range by overlaying the extraction range with a map using a Geographic Information System (GIS). A map generated by a Mobile Mapping System (MMS) may be used as the map.

[0042] In step S3, the objects to be extracted from the extraction range may be predetermined, or they may be set by the control unit 14 according to the target objects.

[0043] For example, the control unit 14 may extract from the extraction range all or some of the objects that have previously caused damage to objects of the same type as the target object. The control unit 14 may receive data from the user via the input unit 11 of objects that have previously caused damage to objects of the same type as the target object. For example, suppose the target disaster is an earthquake and the target object is a utility pole. Also, suppose that in a past earthquake, a wooden house collapsed onto a utility pole of the same type as the target object, causing damage. In this case, the control unit 14 extracts the wooden house from the extraction range. Furthermore, the control unit 14 may extract from the extraction range all or some of the objects that have previously caused damage to objects similar in shape to the target object. The control unit 14 may receive data from the user via the input unit 11 of objects that have previously caused damage to objects similar in shape to the target object.

[0044] For example, the control unit 14 may extract from the extraction range objects that are highly likely to cause damage to the target object, even if they have not caused damage to the target object in the past. The control unit 14 may determine that an object is highly likely to cause damage to the target object if there is a high probability that the target object will be caught in the collapse of that object when it collapses. The control unit 14 may determine whether there is a high probability that the target object will be caught in the collapse of that object when it collapses, based on the height or weight of the object included in the object information obtained in the processing of step S1.

[0045] For example, the control unit 14 may extract objects that are the same as or similar in shape to the target object from the extraction range. If an object that is the same as or similar in shape to the target object breaks, there is a high probability that the target object will also break. Based on the shape information of the target object and the shape information of objects included in the object information obtained in the processing of step S1, the control unit 14 may extract objects that are the same as or similar in shape to the target object. For example, if the target object is a utility pole, a signal pole may be extracted from the extraction range as an object that is similar in shape to a utility pole.

[0046] <Step S4> The control unit 14 obtains the damage rate of an object from the damage rate data of the object stored in the storage unit 13, which is associated with the type of target disaster obtained in the processing of step S1, and from the damage rate of the object from which data was extracted in the processing of step S3.

[0047] For example, if the type of disaster acquired in step S1 is an earthquake, the control unit 14 acquires the damage rate of the object from the damage rate data of the object shown in Figure 2 in step S3.

[0048] For example, if the type of disaster acquired in step S1 is heavy rain, the control unit 14 acquires the damage rate of the object from the damage rate data of the object shown in Figure 3 in step S3.

[0049] Here, if the type of disaster acquired in step S1 is an earthquake, and the damage rate data of the object stored in the memory unit 13 uses the above-mentioned indicators such as ground conditions as an indicator of the intensity of the seismic motion, the control unit 14 may acquire the indicators such as ground conditions at the location of the object. For example, if the indicator of ground conditions is an indicator of ground strength, the control unit 14 acquires the indicator of ground strength using the location information of the object, the J-SHIS Map provided by the National Research Institute for Earth Science and Disaster Resilience <https: / / www.j-shis.bosai.go.jp / usage>, and the above-mentioned geographic information system. If the indicator of ground strength is AVS30, the control unit 14 uses the distribution of average S-wave velocity (AVS30) from the ground surface to a depth of 30m in the J-SHIS Map.

[0050] <Step S5> In step S5, the control unit 14 calculates the damage rate of the target object based on the damage rate of the object obtained in step S4. Hereafter, the N objects (where N is an integer satisfying 1 ≤ N) from which data was extracted in step S3 are each referred to as "Object Ob ｋ It is stated that (k is an integer satisfying 1 ≤ k ≤ N). Also, the object Ob obtained in the process of step S4 ｋ The disaster rate is "Disaster rate d ｋIt is written as "Damage Rate D". In addition, the damage rate of the target object is written as "Damage Rate D". In this case, the control unit 14 calculates the damage rate D of the target object using equation (1). D = 1 - (1 - d １ ) × (1 - d ２ ) × ... × (1 - d ｋ ) × ... × (1 - d Ｎ ) (1)

[0051] The control unit 14 controls object Ob ｋ Weighting according to the disaster rate d ｋ The damage rate D of the target object may be calculated by performing the procedure on the object. When using equation (1), (1-d) of equation (1) ｋ Regarding the item ), the control unit 14 controls object Ob ｋ Weighting may be applied accordingly. For example, object Ob ｋ The shorter the distance between the object and the target object, the less likely the object Ob will be affected during a disaster. ｋ This is thought to increase the likelihood of damaging the target object. For example, in Figure 10, object Ob １ The distance a between the object and the target object. １ Rather than object Ob ２ The distance a between the object and the target object. ２ This is shorter. Therefore, in Figure 10, object Ob ２ Object Object Ob １ This is considered to increase the likelihood of damaging the target object during a disaster. Therefore, the control unit 14 sets the weighting coefficient w(a), which is a function of the distance a between the object and the target object, to (1-d) in equation (1). ｋ The weighting coefficient w(a) may be multiplied by the term. The function of this weighting coefficient w(a) is, for example, a logistic curve as shown in Figure 11. The horizontal axis of Figure 11 represents the distance a [m]. The vertical axis of Figure 11 represents the weighting coefficient w [m]. The function of this weighting coefficient w(a) increases as the distance a increases. The function of this weighting coefficient w(a) may be obtained from data of past large-scale disasters. The function of this weighting coefficient w(a) may be stored in the storage unit 13. The control unit 14 may obtain the weighting coefficient w(a) from the storage unit 13. When using the weighting coefficient w(a), the control unit 14 calculates the damage rate D of the target object by equation (2). D = 1 - w(a １ ) (1-d １) × w (a ２ ) (1-d ２ ) × ... × w ( a ｋ ) (1-d ｋ ) ×…×w(a Ｎ ) (1-d Ｎ ) (2) In equation (2), distance a ｋ is object Ob ｋ This is the distance a between the object and the target object. The control unit 14 calculates the distance a based on the object information and the position information of the target object obtained in the processing of step S1. ｋ You may calculate this.

[0052] Here, the function of the weighting coefficient w(a) is not limited to a logistic curve as shown in Figure 5. As another example, the function of the weighting coefficient w(a) may be a step function or a linear function. Also, object Ob ｋ The larger the mass of the object Ob during a disaster, the greater the impact on the object Ob ｋ It is thought that the damage to the target object will be greater when the object collides with it. Therefore, the control unit 14 may calculate the damage rate D of the target object using a weighting coefficient w(M) which is a function of the object's mass M, instead of a weighting coefficient w(a) which is a function of the distance a. For example, object Ob ｋ The mass M of "mass M ｋ If we assume that, then the w(a) in equation (2) ｋ Instead of ) the weighting coefficient w(M ｋ By using ), the control unit 14 calculates the damage rate D of the target object. From the object information obtained in step S1, the control unit 14 calculates the damage rate D of object Ob ｋ Mass M ｋ The weighting coefficient w(M) may be obtained. The function of this weighting coefficient w(M) increases as the mass M decreases. This function of the weighting coefficient w(M) may be stored in the memory unit 13. The control unit 14 may obtain the function of the weighting coefficient w(M) from the memory unit 13. The control unit 14 may also weight equation (1) using a function of weighting coefficients that is constructed using both the weighting coefficient w(a) and the weighting coefficient w(M).

[0053] Another example of the process in step S5 is that, depending on the type of disaster, the target object may be destroyed independently of other objects. For example, if the disaster is an earthquake, the target object may be destroyed by the shaking of the ground, independently of other objects. Therefore, the damage rate D ０ If the damage rate D can be obtained from data from past large-scale disasters, the control unit 14 may calculate the damage rate D of the target object using equation (3). Damage rate D ０ D = D ０ + {1 - (1 - d １ ) × (1 - d ２ ) × ... × (1 - d ｋ ) × ... × (1 - d Ｎ )} (3) In equation (3) as well, at least one of the weighting coefficients w(a) and w(M) described above may be used. In equation (3), the damage rate D ０ The damage rate D may be calculated as the average of at least one of the damage rates of objects of the same type as the target object and the damage rates of objects similar in shape to the target object during past disasters of the same type as the target disaster. The control unit 14 may identify objects similar in shape to the target object based on the shape information and object information of the target object obtained in the processing of step S1. The control unit 14 calculates the damage rate D ０ D may also be calculated using the following formula (4). ０ = (d １ '+d ２ '+...+d' ｐ +...+d Ｌ ') / L (4) In equation (4), the disaster rate d' ｐ (where p satisfies 1 ≤ p ≤ L) is the damage rate of objects of the same type as the target object in past disasters of the same type as the target disaster. The integer L (where L satisfies 1 ≤ L) is the number of objects of the same type as the target object. However, the damage rate d １ '~d ＬIn whole or in part, the damage rate of objects similar in shape to the target object in past disasters of the same type as the target disaster may be used. In this case, the integer L may be set according to the number of objects similar in shape to the target object used. The control unit 14 sets the damage rate d' ｐ The data may be obtained from the storage unit 13.

[0054] As yet another example of the process in step S5, depending on the type of disaster, the target object and surrounding objects may be destroyed with roughly the same probability. In this case, the control unit 14 will destroy object Ob ｋ The disaster rate d ｋ The damage rate D of the target object may be calculated using the average value of . For example, the control unit 14 calculates the damage rate D of the target object using equation (5). D = (d １ +d ２ +...+d ｋ +...+d Ｎ ) / N (5) In equation (5), at least one of the weighting coefficients w(a) and w(M) described above may be used.

[0055] <Step S6> In step S6, the control unit 14 displays the damage rate D of the target object calculated in step S5 on the display of the output unit 12. The control unit 14 may also display the damage rate D of the target object on the display of the output unit 12 along with a map. In this case, the control unit 14 may indicate the location of the target object on the map. The control unit 14 may also store the damage rate D of the target object in the storage unit 13.

[0056] In the prediction device 10 according to this embodiment, the control unit 14 sets an extraction range around the target object. The control unit 14 calculates the damage rate of the target object during the target disaster based on the damage rate of objects extracted from the set extraction range. With this configuration, the damage rate of the target object can reflect the damage the target object may receive from other surrounding objects. As a result, the damage to the target object during a disaster can be predicted with greater accuracy. By being able to predict the damage to the target object during a disaster with greater accuracy, preventative measures can be taken more reliably. Furthermore, by calculating the damage rate of the target object based on the damage rate of objects extracted from the extraction range, the damage rate of the target object can be calculated even if there is no data on when the target object has been affected by a disaster in the past.

[0057] This disclosure is not limited to the embodiments described above. For example, two or more blocks described in the block diagram may be combined, or one block may be divided. Instead of executing two or more steps described in the flowchart in chronological order as described, they may be executed in parallel or in a different order, depending on the processing capacity of the device performing each step or as necessary. Other modifications are possible without departing from the spirit of this disclosure.

[0058] The prediction method of this disclosure includes setting an extraction range around a target object and calculating the damage rate of the target object during a target disaster based on the damage rate of the object extracted from the extraction range. In the embodiments described above, the prediction device 10 was described as executing the prediction method of this disclosure. However, the prediction method of this disclosure is applicable to any system or method. For example, the prediction method of this disclosure is applicable to a method that performs image analysis from satellite photographs or the like to obtain information about a target object. Furthermore, the prediction method of this disclosure is applicable to a method that automatically analyzes and acquires data from MMS point cloud data and image data to perform damage prediction.

[0059] The prediction device described herein can also be implemented using a computer and a program, and the program can be recorded on a recording medium or provided via a network.

[0060] For example, an embodiment is also possible in which a general-purpose computer functions as the prediction device 10 according to the above embodiment. Specifically, a program describing the processing content that realizes each function of the prediction device 10 according to the above embodiment is stored in the memory of the general-purpose computer, and the processor reads and executes the program. Therefore, this disclosure can also be realized as a program that can be executed by a processor, or as a non-temporary computer-readable medium that stores the program.

[0061] 10: Prediction device, 11: Input unit, 12: Output unit, 13: Storage unit, 14: Control unit

Claims

1. A prediction device comprising a control unit that sets an extraction range around a target object and calculates the damage rate of the target object during a target disaster to be predicted, based on the damage rate of the object extracted from the extraction range.

2. The prediction device according to claim 1, wherein the control unit sets the extraction range based on at least one of the type of target disaster and the shape information of the target object.

3. The prediction device according to claim 2, wherein the control unit sets the extraction range to a predetermined distance from the periphery of the target object in a plan view.

4. The prediction device according to any one of claims 1 to 3, wherein the control unit applies weights to the damage rate of the extracted objects according to the extracted objects and calculates the damage rate of the target objects.

Images