JP6909145B2 - Information processing methods, information processing devices, and programs - Google Patents

Description

The present invention relates to information processing methods, information processing devices, and programs.

Conventionally, when the operation of a railroad or a vehicle is stopped due to an accident, the time until the operation is restored (restarted) is predicted by workers based on the situation of the accident, and the predicted time is used for the railroad or the vehicle. Is being notified.

Further, a technique for predicting the recovery time of the current accident based on the recovery time of the past accident is known (see, for example, Patent Documents 1 and 2).

Japanese Unexamined Patent Publication No. 2005-280411 Japanese Unexamined Patent Publication No. 2012-030756

However, in the prior art, the accuracy of predicting the time until the operation is restored is relatively low, so that it may be difficult for the user to determine whether to wait for the restoration or to take a detour route.

Therefore, on one aspect, it is an object of the present invention to provide a technique capable of improving the prediction accuracy of the time until the operation is restored.

In one plan, the information processing device acquires information on the first place where the first accident of transportation occurred and the date and time when the first accident occurred, and the first accident occurs. The first transition of the degree of difference between the image of the first place at the time before the accident and each image of the first place at a plurality of time points from the occurrence of the first accident to a predetermined time. And the second accident in which the second accident occurred before the second accident occurred, which is calculated for the second accident that has already been restored in the transportation system. Based on a comparison between the second transition of the degree of difference between the image of the place and each image of the second location at a plurality of time points after the occurrence of the second accident and the first transition. The process of estimating the time for the transportation system to recover from the first accident is executed.

According to one aspect, it is possible to improve the accuracy of predicting the time until the operation is restored.

It is a figure which shows the structural example of the information processing system which concerns on embodiment. It is a figure which shows the hardware configuration example of the information processing apparatus which concerns on embodiment. It is a figure which shows an example of the functional structure of the information processing apparatus which concerns on embodiment. It is a flowchart which shows an example of the processing of the information processing apparatus which concerns on embodiment. It is a figure explaining the calculation example of the degree of change. It is a figure explaining the calculation example of the degree of change. It is a figure which shows an example of recovery history information. It is a figure explaining an example of the transition pattern of the degree of change. It is a figure explaining an example of the transition pattern of the degree of change. It is a figure explaining an example of the transition pattern of the degree of change. It is a figure explaining an example of the transition pattern of the degree of change. It is a figure for demonstrating the calculation method of the transition ratio. It is a figure for demonstrating the calculation method of the transition ratio. It is a figure for demonstrating the calculation method of the transition ratio.

Hereinafter, embodiments of the present invention will be described with reference to the drawings.

<System configuration>
FIG. 1 is a diagram showing a configuration example of the information processing system 1 according to the embodiment. In FIG. 1, the information processing system 1 includes an information processing device 10, an image pickup device 20, an external server 30, and a terminal 40. The number of each device is not limited to the example of FIG.

The information processing device 10, the imaging device 20, the external server 30, and the terminal 40 are connected to each other in a communicable state by, for example, a LAN (Local Area Network), a wireless LAN, or a network 50 such as the Internet.

The information processing device 10 is an information processing device (computer) for a server. When the operation of transportation such as railroads and vehicles is stopped due to an accident, the information processing device 10 until the operation is restored (restarted) based on the image of the accident site captured by the image pickup device 20 at each time. The time is estimated and the terminal 40 is notified.

The image pickup device 20 is a camera mounted on a radar satellite, an optical satellite, a drone, an aircraft, a vehicle, or the like, or a surveillance camera fixed on the ground. The image pickup device 20 captures an image before the accident occurs and an image after the accident occurs, and transmits the captured image to the information processing device 10.

The external server 30 is, for example, a server of a business operator that manages or operates transportation, or a server that can be connected via the Internet.

The terminal 40 is, for example, an information processing device such as a desktop PC (Personal Computer), a notebook PC, a tablet PC, or a smartphone. The terminal 40 may be, for example, a device owned by a business operator who manages or operates transportation, or a device owned by a passenger.

<Hardware configuration>
FIG. 2 is a diagram showing a hardware configuration example of the information processing device 10 according to the embodiment. The information processing device 10 of FIG. 2 has a drive device 100, an auxiliary storage device 102, a memory device 103, a CPU 104, an interface device 105, and the like, which are connected to each other by a bus B, respectively.

The program (information processing program) that realizes the processing in the information processing apparatus 10 is provided by the recording medium 101. When the recording medium 101 on which the program is recorded is set in the drive device 100, the program is installed in the auxiliary storage device 102 from the recording medium 101 via the drive device 100. However, the program does not necessarily have to be installed from the recording medium 101, and may be downloaded from another computer via the network. The auxiliary storage device 102 stores the installed program and also stores necessary files, data, and the like.

The memory device 103 reads and stores the program from the auxiliary storage device 102 when the program is instructed to start. The CPU 104 realizes the function related to the information processing device 10 according to the program stored in the memory device 103. The interface device 105 is used as an interface for connecting to a network.

An example of the recording medium 101 is a portable recording medium such as a CD-ROM, a DVD disc, or a USB memory. Further, as an example of the auxiliary storage device 102, an HDD (Hard Disk Drive), a flash memory, or the like can be mentioned. Both the recording medium 101 and the auxiliary storage device 102 correspond to computer-readable recording media.

The hardware configuration of the external server 30 and the terminal 40 may be the same as the hardware configuration example of the information processing device 10 shown in FIG.

<Functional configuration>
Next, with reference to FIG. 3, the functional configuration of the information processing apparatus 10 according to the embodiment will be described. FIG. 3 is a diagram showing an example of the functional configuration of the information processing device 10 according to the embodiment.

The information processing device 10 has a storage unit 11. The storage unit 11 is realized by using, for example, an auxiliary storage device 102 or the like. The storage unit 11 stores data such as recovery history information 111. The recovery history information 111 will be described later.

Further, the information processing device 10 includes an acquisition unit 12, a calculation unit 13, an estimation unit 14, and an output unit 15. Each of these parts is realized by a process in which one or more programs installed in the information processing device 10 are executed by the CPU 104 of the information processing device 10.

When an accident occurs in transportation, the acquisition unit 12 acquires information on the place where the accident occurred and the date and time when the accident occurred from the external server 30.

For this accident (“first accident”) acquired by the acquisition unit 12, the calculation unit 13 has an image of the accident site before the accident occurred and from the time the accident occurred to the present (“first accident”). An example of "predetermined time".) The transition ("first transition") of the degree of change ("degree of difference") from the image at each time point is calculated.

The estimation unit 14 changes the degree of change calculated by the calculation unit 13 for the current accident and the degree of change calculated by the calculation unit 13 for the past accident (“second accident”). The time required for recovery from this accident is estimated based on the transition of (“second transition”).

The output unit 15 notifies the terminal 40 of the recovery time estimated by the estimation unit 14.

<Processing>
Next, the processing of the information processing apparatus 10 according to the embodiment will be described with reference to FIG. FIG. 4 is a flowchart showing an example of processing of the information processing apparatus 10 according to the embodiment.

In step S1, the acquisition unit 12 acquires the accident information from the external server 30. Here, the information of the accident includes information such as a place, a date and time, and a cause.

Subsequently, the acquisition unit 12 includes an image of the location of the accident before the accident (hereinafter, also referred to as "original image") and the accident at each time (for example, every minute) from the time of the accident to the present. An image of the place is acquired from the image pickup apparatus 20 (step S2). Hereinafter, the image of the location of the accident in one time from the time of the accident to the present will be referred to as "the image after the change".

Here, when the image acquired from the image pickup apparatus 20 is a black-and-white image obtained by a radar of an image satellite, the acquisition unit 12 uses, for example, a color image of an optical satellite as learning data, AI (Artificial Intelligence) using deep learning. Etc., the black-and-white image is converted into a color image. The image of each place before the accident may be stored in the storage unit 11 in advance.

Subsequently, the calculation unit 13 calculates the degree of change between the original image and the changed image at each time from the time of the accident to the present (step S3).

5A and 5B are diagrams for explaining a calculation example of the degree of change. FIG. 5A is an example of the original image, and FIG. 5B is an example of the changed image. In the image of FIG. 5B, the work vehicle 501, the blue sheet 502, the cone 503, the cone 505, and the like are shown as compared with the image of FIG. 5A.

In step S3, the calculation unit 13 may calculate the difference between the value indicating the status of the restoration work in the original image and the value indicating the status of the restoration work in the changed image as the degree of change. A value indicating the status of the restoration work is calculated as the frequency (area, number of pixels) of a predetermined color that appears relatively frequently during the restoration work, such as yellow, blue, and red, increases in the image. NS. The range of colors determined to be each color such as yellow, blue, and red may be set in advance by, for example, numerical values in the RGB color model.

The coefficient values for yellow, blue, red, etc. are set larger than the coefficient values for other colors. For example, the coefficients for yellow, blue, red, and other colors are set to 3, 2, 1.5, and 0.2, respectively. Then, the calculation unit 13 totals the value obtained by multiplying the coefficient of each color by the area of each color for all the pixels, and sets the total value as a value indicating the status of the restoration work.

In the examples of FIGS. 5A and 5B, assuming that a predetermined area in the real space is one block, the other colors are 80 blocks in the image of FIG. 5A, so the value indicating the status of the restoration work is 16 (80 ×). 0.2). In the image of FIG. 5B, assuming that yellow is 8 blocks, blue is 12 blocks, red is 2 blocks, and other colors are 58 blocks, the value indicating the status of restoration work is 62.6 (= 8 × 3 + 12 × 2 + 2). × 1.5 + 58 × 0.2). Therefore, the degree of change is calculated as 46.6 (= 62.6-16).

As a result, for example, when the changed image shows more yellow of the worker's helmet or jacket, or yellow of the work vehicle, blue of the blue sheet, and red of the fire engine or cone, the image is restored. The degree of change from the original image related to the work can be calculated more appropriately.

The calculation unit 13 extracts each pixel that has changed by a predetermined threshold value or more for each pixel of the original image and the changed image, and calculates a coefficient associated with the color of each pixel of each pixel. A value obtained by multiplying a number and dividing by the number of pixels per predetermined area in the real space may be calculated as the degree of change.

Further, the calculation unit 13 may determine that the lower the similarity between the original image and the changed image, the greater the degree of change. The similarity between the two images is, for example, Sum of Squares Difference (SSD), Sum of Absolute Difference (SAD), Normalized Cross-Correlation (NCC), etc. May be calculated using.

Subsequently, the estimation unit 14 extracts the past recovery history that matches the conditions from the recovery history information 111 based on the information of the accident (hereinafter, also referred to as “this accident”) acquired in step S1 (step). S4).

FIG. 6 is a diagram showing an example of recovery history information 111. In the example of FIG. 6, the recovery history information 111 stores the route, cause, section, month, day of the week, time, weather, number of posts, transition pattern, and recovery time in association with the accident ID.

The accident ID is identification information of past accidents. The route is the route where the accident occurred. The cause is the cause of the accident. The section is the section (location) where the accident occurred. The month, day of the week, time, and weather are the month, day of the week, time, and weather at the time of the accident, respectively. The number of posts is the number of posts to social networking services (SNS, Social Networking Service) and the like related to accidents. The transition pattern shows the transition of the degree of change between the original image calculated by the calculation unit 13 and the image after the change in each time from the occurrence of the accident to the recovery for the past accident related to the accident ID. It is the data to show. The restoration time is the time taken from the occurrence of the accident to the restoration (restart) of the operation.

In step S4, the estimation unit 14 determines, for example, the route where the accident occurred, the section where the accident occurred, the month when the accident occurred, the day when the accident occurred, the time zone when the accident occurred, the weather when the accident occurred, and so on. Extract the number of posts related to the accident to SNS, etc., and the past recovery history that matches the conditions of the cause of the accident. Specifically, in the estimation unit 14, for example, among the data stored in the recovery history information 111, the route and the cause of the accident are the same as compared with the current accident, and the section where the accident occurred. The data in which the difference between each item such as, etc. is within a predetermined range is extracted.

In addition, the condition of the number of posts is that posted messages containing keywords related to the accident are considered to be posted relatively early from the occurrence of the accident, and if it is a similar accident, it will be posted to SNS. This is because the number of posts related to the accident can be expected to be the same. In addition, instead of or in addition to the number of posts, the transition of the number of posts since the occurrence of the accident may be a condition.

Subsequently, the estimation unit 14 selects a transition pattern that matches the transition of the degree of change in the current accident from among the transition patterns of the degree of change in the extracted one or more recovery histories (step S5).

7A, 7B, 7C, and 7D are diagrams for explaining an example of a transition pattern of the degree of change, respectively. In FIG. 7A, an example of a transition pattern of the degree of change is shown, with the time (t) from the time of the accident occurring on the horizontal axis and the degree of change between the original image and the image after the change at each time on the vertical axis. It is shown.

In the example of FIG. 7A, the on-site verification is performed when the time (t) is from 0 to t _1, and the removal work is performed when the time (t) is from t ₁ to t _2. Preparations for restoration are being made between (t) t ₂ and t _3.

In the example of FIG. 7A, when the on-site verification is started, as shown by arrow 701, the degree of change gradually increases due to the arrival of the on-site verification workers and the like. Then, when the on-site verification progresses to a certain extent, the degree of change gradually decreases as shown by arrow 702.

Then, when the removal work is started, as shown by arrow 703, the degree of change suddenly increases due to the arrival of work vehicles, workers, etc., and then, as shown by arrow 704, the degree of change gradually increases. It will increase.

Then, when the preparation for restoration is started, the degree of change suddenly decreases due to the withdrawal of the work vehicle, the worker, etc., as shown by arrow 705, and then, as shown by arrow 706, the degree of change is 0. Get closer to.

In FIGS. 7B, 7C, and 7D, similarly to FIG. 7A, the horizontal axis is the time (t) from the time of the accident, and the degree of change between the original image and the image after the change at each time is vertical. An example of a transition pattern of the degree of change is shown as an axis.

In the example of FIG. 7B, the worker or the like who performed the on-site verification did not withdraw, and the worker or the like started the removal work as it was. The decrease in the degree of is small as compared with the arrow 702 in FIG. 7A.

In the example of FIG. 7C, the number of workers and the like performing on-site verification is relatively small and the number of workers and the like is relatively small as compared with FIG. 7A.

In the example of FIG. 7D, since the cause of the accident can be identified and the removal work can be performed immediately, there is no transition pattern indicating on-site verification as compared with FIG. 7A.

In step S5, the estimation unit 14 changes in at least a part of the transition patterns of the degree of change in the extracted one or more recovery histories from the time of the occurrence of this accident to the present. Accidents that match the above aspects are extracted. In this case, for example, the estimation unit 14 expands or contracts the transition of the degree of change from the time of the occurrence of this accident to the present in the time direction, and the estimation unit 14 for the expanded or reduced time in the extracted transition pattern. Calculate the degree of similarity with the transition. The estimation unit 14 may calculate the similarity using, for example, a cross-correlation function or the like. Then, the estimation unit 14 selects the transition pattern having the transition with the highest degree of similarity as the transition pattern that matches the transition of the degree of change in the accident this time.

Subsequently, the estimation unit 14 calculates the ratio between the transition of the degree of change in the accident this time and the transition in the transition pattern selected in step S5 (step S6). Here, the estimation unit 14 compares the time with respect to the portion of the transition in the transition pattern selected in step S5 whose mode of transition matches the mode of transition of the degree of change in the accident this time to the predetermined time. Is calculated. In this case, for example, the estimation unit 14 expands or contracts the transition of the degree of change from the time of the occurrence of this accident to the present in the time direction, and the expanded or reduced time in the transition pattern selected in step S5. Calculate the degree of similarity with the transition of minutes. The estimation unit 14 may calculate the similarity using, for example, a cross-correlation function or the like. Then, the estimation unit 14 sets the ratio of expansion or contraction in the time direction when the degree of similarity is the highest as the ratio.

8A, 8B, and 8C are diagrams for explaining a method of calculating the transition ratio. In Figure 8A, transition 801 of the degree of change from the time of occurrence of the accident until the current time t _m is shown. FIG. 8B shows a transition 802 in which the transition 801 of FIG. 8A is expanded _{t n} / t _{m times in the time (t) direction.} In FIG. 8C, the transition pattern 803 of FIG. 7A selected in step S5 is shown.

Here, among the transitions of the degree of change 801 shown in FIG. 8A from the time of the occurrence of the accident to the present, which are expanded or contracted in the time direction, the transition 802 shown in FIG. 8B is the transition shown in FIG. 8C. similarity between transition 804 of the expanded time t _n min in the pattern 803 is the highest. In this case, the estimation unit 14 _{calculates t m} / t _n as the ratio.

This is because if the restoration work to date for this accident is proceeding at a predetermined ratio to the restoration work for a similar accident in the past, the restoration work for this accident will be for the same accident in the past. This is because it can be expected to be completed in about the time required for the restoration work multiplied by the predetermined ratio.

Subsequently, the estimation unit 14 estimates the recovery time of the current accident based on the recovery time for the transition pattern selected in step S5 and the ratio calculated in step S6 (step S7). Here, the estimation unit 14 multiplies the recovery time for the transition pattern selected in step S5 by the ratio calculated in step S6, and adds a predetermined offset time (for example, 5 minutes) to the recovery time. Presumed to be. In the examples of FIGS. 8A and 8C, when the recovery time for the transition pattern of FIG. 8C is 90 minutes and the above-mentioned _{value of t m} / t _n is 1/2, the recovery time of this accident is 50 minutes ( = 90/2 + 5).

Subsequently, the output unit 15 notifies the terminal 40 of the estimated recovery time (step S8). Here, for example, by notifying the terminal 40 of a transportation business operator, a train transfer guidance service business operator, or the like, the user can browse through the website of the business operator or the like.

The information processing device 10 may repeatedly execute the processes of steps S2 to S8 at predetermined intervals (for example, every 10 minutes) until the accident is recovered.

<Modification example>
The estimation unit 14 may estimate the recovery time of the accident this time by AI using deep learning instead of the processing of steps S4 to S7 described above. In this case, the estimation unit 14 machine-learns the transition of the degree of change calculated by the calculation unit 13 for the past accident in advance, and sets the transition of the degree of change calculated by the calculation unit 13 in step S3. , Estimate the recovery time of this accident based on the result of the machine learning.

Although the examples of the present invention have been described in detail above, the present invention is not limited to such specific embodiments, and various modifications are made within the scope of the gist of the present invention described in the claims.・ Can be changed.

For example, each functional unit of the information processing device 10 may be realized by cloud computing composed of, for example, one or more computers.

With respect to the above description, the following sections will be further disclosed.
(Appendix 1)
Information processing device
The process of acquiring information on the first place where the first accident of transportation occurred and the date and time when the first accident occurred.
Difference between the image of the first place before the first accident occurs and each image of the first place at a plurality of time points from the occurrence of the first accident to a predetermined time. The process of calculating the first transition of the degree of
An image of the second place where the second accident occurred and the second place before the second accident, which is calculated for the second accident that has already been restored in the transportation system. Based on the comparison between the second transition of the degree of difference from each image of the second place at a plurality of time points after the occurrence of the second accident and the first transition, the transportation means the first. An information processing method for estimating the time to recover from the accident of 1 and executing.
(Appendix 2)
The estimation process is
Among the accidents that have already been restored in the transportation system, the image of the place where the accident occurred before the accident occurred and each image of the place at a plurality of time points after the accident occurred. An accident in which the mode of at least a part of the transition of the degree of difference matches the mode of the first transition is selected as the second accident.
The information processing method according to Appendix 1.
(Appendix 3)
The estimation process is
The second accident refers to an accident related to the first accident, the cause of the accident, the place where the accident occurred, the time when the accident occurred, the weather when the accident occurred, and one or more of the number of posts related to the accident. Select as,
The information processing method according to Appendix 1 or 2.
(Appendix 4)
The calculation process is
The ratio of the time to the portion of the second transition in which the mode of transition matches the mode of the first transition and the predetermined time is calculated.
The estimation process is
Based on the ratio and the time when the transportation system recovers from the second accident, the time when the transportation system recovers from the first accident is estimated.
The information processing method according to any one of Appendix 1 to 3.
(Appendix 5)
The calculation process is
The frequency of appearance of a predetermined color in the image of the first place before the first accident occurs, and each image of the first place at a plurality of time points after the first accident occurs. Based on the difference from the appearance frequency of the predetermined color in the above, the image of the first place at the time before the first accident occurs and the image of the first place from the occurrence of the first accident to the predetermined time. Calculate the degree of difference from each image of the first place at a plurality of time points.
The information processing method according to any one of Appendix 1 to 4.
(Appendix 6)
An acquisition unit that acquires information on the first place where the first accident of transportation occurred, and the date and time when the first accident occurred.
Difference between the image of the first place before the first accident occurs and each image of the first place at a plurality of time points from the occurrence of the first accident to a predetermined time. A calculation unit that calculates the first transition of the degree of
An image of the second place where the second accident occurred and the second place before the second accident, which is calculated for the second accident that has already been restored in the transportation system. Based on the comparison between the second transition of the degree of difference from each image of the second place at a plurality of time points after the occurrence of the second accident and the first transition, the transportation means the first. An estimation unit that estimates the time to recover from one accident,
Information processing device with.
(Appendix 7)
For information processing equipment
The process of acquiring information on the first place where the first accident of transportation occurred and the date and time when the first accident occurred.
Difference between the image of the first place before the first accident occurs and each image of the first place at a plurality of time points from the occurrence of the first accident to a predetermined time. The process of calculating the first transition of the degree of
An image of the second place where the second accident occurred and the second place before the second accident occurred, which is calculated for the second accident that has already been restored in the transportation system. Based on the comparison between the second transition of the degree of difference from each image of the second location at a plurality of time points after the occurrence of the second accident and the first transition, the transportation means the first. A program that estimates the time to recover from one accident and executes it.

1 Information processing system 10 Information processing device 11 Storage unit 111 Recovery history information 12 Acquisition unit 13 Calculation unit 14 Estimate unit 15 Output unit

Claims (7)

Information processing device
The process of acquiring information on the first place where the first accident of transportation occurred and the date and time when the first accident occurred.
Difference between the image of the first place before the first accident occurs and each image of the first place at a plurality of time points from the occurrence of the first accident to a predetermined time. The process of calculating the first transition of the degree of
An image of the second place where the second accident occurred and the second place before the second accident, which is calculated for the second accident that has already been restored in the transportation system. Based on the comparison between the second transition of the degree of difference from each image of the second place at a plurality of time points after the occurrence of the second accident and the first transition, the transportation means the first. An information processing method for estimating the time to recover from the accident of 1 and executing. The estimation process is
Among the accidents that have already been restored in the transportation system, the image of the place where the accident occurred before the accident occurred and each image of the place at a plurality of time points after the accident occurred. An accident in which the mode of at least a part of the transition of the degree of difference matches the mode of the first transition is selected as the second accident.
The information processing method according to claim 1. The estimation process is
The second accident refers to an accident related to the first accident, the cause of the accident, the place where the accident occurred, the time when the accident occurred, the weather when the accident occurred, and one or more of the number of posts related to the accident. Select as,
The information processing method according to claim 1 or 2. The calculation process is
The ratio of the time to the portion of the second transition in which the mode of transition matches the mode of the first transition and the predetermined time is calculated.
The estimation process is
Based on the ratio and the time when the transportation system recovers from the second accident, the time when the transportation system recovers from the first accident is estimated.
The information processing method according to any one of claims 1 to 3. The calculation process is
The frequency of appearance of a predetermined color in the image of the first place before the first accident occurs, and each image of the first place at a plurality of time points after the first accident occurs. Based on the difference from the appearance frequency of the predetermined color in the above, the image of the first place at the time before the first accident occurs and the image of the first place from the occurrence of the first accident to the predetermined time. Calculate the degree of difference from each image of the first place at a plurality of time points.
The information processing method according to any one of claims 1 to 4. An acquisition unit that acquires information on the first place where the first accident of transportation occurred, and the date and time when the first accident occurred.
Difference between the image of the first place before the first accident occurs and each image of the first place at a plurality of time points from the occurrence of the first accident to a predetermined time. A calculation unit that calculates the first transition of the degree of
An image of the second place where the second accident occurred and the second place before the second accident, which is calculated for the second accident that has already been restored in the transportation system. Based on the comparison between the second transition of the degree of difference from each image of the second place at a plurality of time points after the occurrence of the second accident and the first transition, the transportation means the first. An estimation unit that estimates the time to recover from one accident,
Information processing device with. For information processing equipment
The process of acquiring information on the first place where the first accident of transportation occurred and the date and time when the first accident occurred.
Difference between the image of the first place before the first accident occurs and each image of the first place at a plurality of time points from the occurrence of the first accident to a predetermined time. The process of calculating the first transition of the degree of
An image of the second place where the second accident occurred and the second place before the second accident occurred, which is calculated for the second accident that has already been restored in the transportation system. Based on the comparison between the second transition of the degree of difference from each image of the second location at a plurality of time points after the occurrence of the second accident and the first transition, the transportation means the first. A program that estimates the time to recover from one accident and executes it.

Images