Emergency information release strategy construction method, device and system and storage medium

Abstract

The invention relates to the technical field of information release, and discloses an emergency information release strategy construction method, device and system and a storage medium, and the method comprises the steps: obtaining daily hourly people flow data of a historical time period of a target region; acquiring hourly accumulated rainfall of the meteorological automatic station closest to the straight line of the target area in a historical period; calculating the hourly people flow fluctuation rate based on the daily hourly people flow data; determining a rainfall risk grading basis based on the hourly people flow rate fluctuation ratio and the hourly accumulated rainfall; and determining an emergency information issuing strategy based on the rainfall risk grading basis and a set rainfall threshold value. According to the invention, a more comprehensive and dynamic notification strategy is adopted to effectively deal with the challenges and reduce potential safety risks.

Description

Technical Field

[0001] The present invention relates to the technical field of information release, and in particular to a method, device, system and storage medium for constructing an emergency information release strategy. Background Art

[0002] In the work of urban flood prevention, emergency SMS release is an important supplement to the existing urban flood prevention system. This method can quickly convey information about waterlogging or flooding risks caused by rainfall to the public in the affected areas, ensuring that they are aware of the situation in a timely manner and take risk avoidance measures. However, there are two main ways to notify emergency SMS for rainstorm warnings or emergency warnings: one is to notify group users with fixed numbers; the other is to send information to real-time mobile phone users in specific flooded areas after monitoring flooding. However, both of them lack flexibility in population coverage or lack advance information transmission, and only remind the public in the affected areas. In order to more effectively deal with traffic congestion and crowd gathering effects in large cities, the emergency SMS release strategy needs to be further optimized, especially to strengthen the reminders to potential affected people. For example, when flooding may occur or has occurred in a certain area, the release strategy can send emergency information to potential people who may go to the area, and give suggestions for changing routes or avoiding going there, which can further achieve the purpose of reducing traffic pressure, preventing crowd gathering, and improving the city's ability to respond to emergencies such as flooding.

[0003] In traditional emergency SMS notification methods, time and space factors are often overlooked, which has an important impact on reducing traffic pressure, preventing crowds from gathering, and preventing disasters. Specifically, traditional notification methods do not fully consider the temporal characteristics of regional personnel flow, such as significant changes in passenger flow during peak hours, and the specific distribution of different surrounding places, such as schools and shopping malls. These factors have a direct impact on crowd behavior and risk avoidance needs. At the same time, since the scope of SMS release is relatively fixed and the coverage is limited, it may not reach people who are heading to risk areas, resulting in their inability to obtain information in time to detour in advance, which undoubtedly increases potential risks.

[0004] In order to solve the problem that time and space factors are often ignored in traditional emergency SMS notification methods, it is necessary to fully consider the impact of time and space characteristics on the notification effect, and deeply analyze the time characteristics of regional personnel flow and the distribution of different places around. In addition, due to the fixed and limited scope of SMS release, it is often difficult to notify people who are heading to the risk area in time, making it impossible for them to know the danger in advance and detour. In order to improve this situation, a more comprehensive and dynamic notification strategy is needed to effectively respond to these challenges and reduce potential safety risks. Summary of the invention

[0005] In order to solve the above problems, the present invention provides a method, device, system and storage medium for constructing an emergency information release strategy. The first is to analyze the relationship between regional human flow and rainfall, grasp the specific impact of rainfall weather on human flow in different time periods, and formulate rainfall risk classification based on this, so as to dynamically adjust the SMS release strategy. The second is to evaluate environmental attributes, such as whether the surrounding key places have an impact on the human flow of waterlogging points, and strategically include the responsible persons of the key places with influence in the SMS notification scope, and further subdivide the audience. This can not only improve the pertinence and effectiveness of emergency information, but also promote the construction of a multi-party collaborative emergency management mechanism for waterlogging defense. The third is to consider the accessibility of different distances, and define a potential warning range for people going to waterlogging locations based on different distances. By warning people who may go to dangerous areas in advance, their risk of staying in waterlogging locations is reduced, thereby eliminating potential safety hazards. This strategy aims to timely remind the public of the risk of rainfall and waterlogging, and effectively reduce the probability of people getting involved in high-risk areas of waterlogging, thereby reducing the retention of people and better protecting public safety.

[0006] In order to achieve the above object, the technical solution adopted by the present invention is as follows:

[0007] According to a first solution of the present invention, a method for constructing an emergency information release strategy is provided, the method comprising:

[0008] Obtain the daily hourly flow data of the target area during the historical period;

[0009] Obtain the hourly accumulated rainfall in the historical period of the automatic meteorological station closest to the target area in a straight line;

[0010] Calculate the hourly passenger flow fluctuation rate based on the daily hourly passenger flow data;

[0011] Determine a rainfall risk classification basis based on the hourly passenger flow fluctuation rate and the hourly accumulated rainfall;

[0012] The emergency information release strategy is determined based on the rainfall risk classification basis and the set rainfall threshold.

[0013] Further, calculating the hourly passenger flow fluctuation rate based on the daily hourly passenger flow data includes:

[0014] Divide the historical period into multiple characteristic periods, and assign a characteristic label to each characteristic period; wherein the characteristic period includes at least n characteristic days, n is a positive integer greater than or equal to 1, and the characteristic label is used to characterize the characteristic date corresponding to the characteristic period;

[0015] The real-time average flow of people during the characteristic period is calculated using the following formula:

[0016]

[0017] In the formula, A j represents the mean flow of people at the jth time in the characteristic period, D ij It represents the real-time flow of people at the jth time of the i-th characteristic day in the characteristic period, where i is the serial number of the characteristic day and j is the serial number of the time;

[0018] The characteristic period corresponding to the feature label with the highest mean value of real-time passenger flow is used as the target period, and the ARIMA model is constructed based on the mean value of real-time passenger flow on rainless days in the target period.

[0019] The ARIMA model is used to fit the flow of people on rainy days in the target period, which is used as the daily flow benchmark when rainy weather occurs. The flow benchmark at the time of rain is calculated based on the daily real-time flow data that is supplemented, and the average proportion of the flow of people at each hour of the two days before and after the day is considered to complete the calculation of the flow benchmark at the time of rain.

[0020] The hourly passenger flow fluctuation rate is calculated using the following formula:

[0021]

[0022] In the formula, Indicates the real-time flow fluctuation rate under rainy weather conditions; Flow D(t) Indicates the actual value of the real-time flow of people at the tth moment on the Dth day; BFlow D(t) It represents the real-time passenger flow baseline value at time t on day D.

[0023] Furthermore, determining a rainfall risk classification basis based on the hourly passenger flow fluctuation rate and the hourly accumulated rainfall includes:

[0024] According to the distribution characteristics of commuting time throughout the day, the whole day is divided into at least two sub-periods;

[0025] According to the real-time passenger flow fluctuation rate under the rainy weather conditions in each sub-period, the sub-periods related to the impact of rainfall are selected as target sub-periods;

[0026] The rainfall levels in the target sub-periods are clustered to obtain the rainfall levels and impact levels based on the analysis of hourly passenger flow fluctuation characteristics, which serve as the basis for rainfall risk classification.

[0027] Furthermore, the target sub-period includes the morning peak period and the evening peak period. Based on the rainfall risk classification basis and the set rainfall threshold, the emergency information release strategy is determined as follows:

[0028] If the hourly rainfall exceeds 20 mm during the morning rush hour, or exceeds 10 mm during the evening rush hour, the emergency warning information release mechanism will be activated.

[0029] Furthermore, after determining the emergency information release strategy based on the rainfall risk classification and the set rainfall threshold, the method further includes:

[0030] Acquire evaluation data of a target place; wherein the target place is a place that is spatially within a set range from a target point in a target area, and the evaluation data is a place density;

[0031] Obtaining accessibility data of the target location; wherein the accessibility data of the target location is the accessibility of the target location at a radius of m gradients from the target point, m is a positive integer greater than or equal to 1, and the gradient is a set length value;

[0032] Based on the assessment data and accessibility data of the target place, the spatial scope of emergency information release is determined.

[0033] Furthermore, before determining the spatial scope of emergency information release based on the evaluation data and accessibility data of the target place, the method further includes:

[0034] Correlate the evaluation data and accessibility data of the target place with the average flow of people at a certain time, and determine the influencing factors that are significantly correlated with the flow of people;

[0035] Hierarchical regression analysis was used to determine the impact of influencing factors on real-time pedestrian flow.

[0036] Furthermore, based on the evaluation data and accessibility data of the target location, the spatial scope of emergency information release is determined as:

[0037] During the morning rush hour, if the hourly rainfall exceeds 20 mm, or during the evening rush hour, if the hourly rainfall exceeds 10 mm, the emergency warning information release mechanism is activated, and the release range includes: (i) the circular area with the target point as the center and the radius r1; (ii) the target place within the circular area with the target point as the center and the radius r2; (iii) the annular area with the target point as the center and the radius from r3 to r4;

[0038] On weekends and holidays, when a rainstorm warning takes effect or waterlogging occurs in the area, the release of emergency reminder information is initiated. The release range is: a circular area with a radius of r1 and a target point as the center.

[0039] According to the second technical solution of the present invention, there is provided an emergency information release strategy construction device, the device comprising:

[0040] A first data acquisition module is configured to acquire daily hourly pedestrian flow data of a target area during a historical period;

[0041] The second data acquisition module is configured to obtain the hourly accumulated rainfall in the historical period of the automatic meteorological station closest to the target area in a straight line;

[0042] A volatility calculation module, configured to calculate the hourly passenger flow volatility based on the daily hourly passenger flow data;

[0043] A classification basis determination module is configured to determine a rainfall risk classification basis based on the hourly passenger flow fluctuation rate and the hourly accumulated rainfall;

[0044] The release strategy determination module is configured to determine the emergency information release strategy based on the rainfall risk classification basis and the set rainfall threshold.

[0045] According to a third technical solution of the present invention, there is provided an emergency information release strategy construction system, the system comprising: a memory for storing a computer program; and a processor for executing the computer program to implement the method as described above.

[0046] According to a fourth technical solution of the present invention, a non-transitory computer-readable storage medium storing instructions is provided. When the instructions are executed by a processor, the method described above is executed.

[0047] The present invention has at least the following beneficial effects:

[0048] The present invention considers the relationship between regional human flow and rainfall with time period characteristics, and uses this as a strategy for starting the release of emergency text messages. Compared with the real-time monitoring of rainwater accumulation and waterlogging as the starting condition, the present invention provides more advance time for the release of emergency text messages based on time period characteristics and rainfall risk classification, so that the regional human flow can be evacuated and guided more effectively in rainy weather. At the same time, the responsible persons of key places that have an impact on the human flow of waterlogging points in the surrounding areas are strategically included in the scope of text message notifications, and the pertinence of information is significantly improved by segmenting the audience. In addition, the present invention also integrates the accessibility factors of different distances and defines a potential warning range for people going to waterlogging locations. Compared with a single waterlogging monitoring and release strategy, this multi-dimensional emergency text message release method can more comprehensively cover the people who may be affected, timely remind the public of the risk of rainwater accumulation, effectively reduce the probability of people getting involved in high-risk areas of waterlogging, and thus reduce the retention of people and better protect public safety. Finally, the method can dynamically adjust the text message release strategy based on real-time data to adapt to changes in human flow under different weather conditions and time periods. Compared with traditional fixed strategies, this flexibility can better ensure the timeliness and effectiveness of text messages, thereby providing more accurate emergency services to the public. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1A schematic diagram of an application scenario according to the prior art is shown.

[0050] Figure 2 A flow chart of a method for constructing an emergency information release strategy according to an embodiment of the present invention is shown.

[0051] Figure 3 A flow chart for calculating hourly passenger flow fluctuation rate according to an embodiment of the present invention is shown.

[0052] Figure 4 A flow chart for determining a rainfall risk classification basis according to an embodiment of the present invention is shown.

[0053] Figure 5 Another flow chart of a method for constructing an emergency information release strategy according to an embodiment of the present invention is shown.

[0054] Figure 6 A structural diagram of an emergency information release strategy construction device according to an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0055] The following describes the embodiments of the present invention by specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0056] The specific implementation of the present invention is further described in detail below in conjunction with the drawings and examples.

[0057] Figure 1 FIG. 1 is a schematic diagram showing an application scenario according to the prior art. An embodiment of the present invention provides an application scenario. Figure 1 As shown, the application scenario includes a server 101 and multiple terminals 102. In the prior art, the server 101 determines whether waterlogging occurs based on the real-time monitoring of waterlogging caused by rainfall accumulation. In the event of waterlogging, the terminal that may be affected by the waterlogging is determined based on the distance from the waterlogging location, that is, the terminal 102 to be sent is determined based on the waterlogging location and the set distance range, and then the relevant information is sent to the terminal 102 for early warning. Because the release range of this information release method is fixed and limited, it is often difficult to notify people who are heading to the risk area in a timely manner, so that they cannot be aware of the danger in advance and detour.

[0058] Based on this, the embodiment of the present invention provides a method for constructing an emergency information release strategy, which can reduce the risk of people staying in flooded areas by warning people who may go to dangerous areas in advance, thereby eliminating potential safety hazards. This strategy aims to promptly remind the public of the risk of rainwater accumulation and effectively reduce the probability of people setting foot in high-risk areas of flooding, thereby reducing the number of people staying and better protecting public safety. Figure 1 In the application scenario shown, the server 101 is configured to: obtain the daily hourly pedestrian flow data of the target area in the historical period; obtain the hourly accumulated rainfall in the historical period of the automatic meteorological station closest to the target area in a straight line distance; calculate the hourly pedestrian flow fluctuation rate based on the daily hourly pedestrian flow data; determine the rainfall risk classification basis based on the hourly pedestrian flow fluctuation rate and the hourly accumulated rainfall; determine the emergency information release strategy based on the rainfall risk classification basis and the set rainfall threshold.

[0059] When the server 101 has determined the emergency information release strategy, the terminal 102 corresponding to the emergency information release strategy sends out the emergency information. Since the relationship between the regional human flow and rainfall is analyzed, the specific impact of rainfall on the human flow in different time periods is grasped, and the rainfall risk classification basis is formulated accordingly to construct the emergency information release strategy, more advance time can be provided for the release of emergency text messages, so that the regional human flow can be evacuated and guided more effectively in rainy weather, with higher safety.

[0060] It should be noted that the terminal 102 can be implemented as an existing device such as a smart phone, a tablet computer, an office computer, etc. Figure 1 The four terminals 102 shown in FIG. 1 are merely examples. In actual implementation, the number of terminals 102 may be of a higher order of magnitude.

[0061] Figure 2 FIG. 4 is a flow chart showing a method for constructing an emergency information release strategy according to an embodiment of the present invention. Figure 2 As shown, the emergency information release strategy construction method includes the following steps:

[0062] S201. Obtain hourly daily passenger flow data for a target area during a historical period.

[0063] In this embodiment, the complete daily hourly mobile signaling data of the target area (i.e., the flood-prone areas in the city are the target areas) for the past year are collected based on the analysis of the operator's mobile signaling data, that is, the daily hourly pedestrian flow data. For example, the hourly pedestrian flow data of a certain target area from January 2023 to December 2023 is used.

[0064] S202: Obtain the hourly accumulated rainfall in the historical period of the automatic meteorological station that is closest to the target area in a straight line distance.

[0065] In this embodiment, the daily hourly rainfall observation data (i.e., the daily hourly accumulated rainfall) of the meteorological automatic station closest to the target area is obtained, and the time period is the same as the data in step S201. For example, the hourly rainfall data of the meteorological automatic station G1001 closest to a certain target area is used, and the time period is the hourly rainfall data from January 2023 to December 2023.

[0066] S203: Calculate hourly passenger flow fluctuation rate based on the daily hourly passenger flow data.

[0067] To calculate the volatility, you need to first determine the baseline value of the flow rate when there is no rainfall, and then calculate the volatility. The volatility is an indicator used to characterize the degree of change between the real-time flow rate under rainfall conditions and the real-time flow rate under normal weather conditions (i.e., no rainfall), and is expressed as the deviation rate between the real-time flow rate under rainfall conditions and the baseline value.

[0068] In some embodiments, Figure 3 FIG. 4 shows a flow chart of calculating the hourly fluctuation rate of human traffic according to an embodiment of the present invention. Figure 3 As shown, calculating the hourly passenger flow fluctuation rate based on the daily hourly passenger flow data includes the following steps:

[0069] S301. Divide the historical period into multiple characteristic periods, and assign a characteristic label to each characteristic period; wherein the characteristic period includes at least n characteristic days, n is a positive integer greater than or equal to 1, and the characteristic label is used to characterize the characteristic date corresponding to the characteristic period.

[0070] Since the real-time flow of people data itself is affected by many factors such as holidays, large-scale events, natural growth of the surrounding population, and weather, considering the sudden changes in the real-time flow of people by large-scale events, holidays, and atypical working days, it is necessary to screen and eliminate each characteristic period. This embodiment compares the mean changes in real-time flow of people between weekends, holidays, and typical working days. On this basis, the characteristic date with the highest mean is screened out to conduct a more detailed exploration of the dynamics of flow of people under the rainfall scene. In this embodiment, weekends specifically refer to Saturdays and Sundays; holidays cover statutory holidays; and typical working days refer to other normal working days after weekends, Fridays, holidays, and working days before and after holidays are removed. Therefore, the feature tags can include weekends, holidays, and typical working days, so that three categories of feature periods can be divided. The feature days included in the feature period of the same category are the same feature dates. For example, the feature period under the feature tag of weekends includes all feature days on weekends, and the feature tags of other categories are also the same, which will not be repeated here.

[0071] S302: Calculate the average of the real-time flow of people during the characteristic period, using the following formula:

[0072]

[0073] In the formula, A j represents the mean flow of people at the jth time in the characteristic period, D ij It represents the real-time flow of people at the jth time on the i-th characteristic day within the characteristic period, where i is the serial number of the characteristic day and j is the serial number of the time.

[0074] S303: Using the feature time period corresponding to the feature label with the highest mean value of real-time passenger flow as the target time period, and constructing an ARIMA model according to the mean value of real-time passenger flow on days without rainfall in the target time period.

[0075] In this embodiment, the characteristic date with the highest mean of real-time human flow is finally selected as the data for formulating rainfall risk classification. In this embodiment, the characteristic date selected is a typical working day, and the mean of real-time human flow on a typical working day is the highest among the three, especially in the period of 08-19, which obviously exceeds the mean of weekends and holidays. Compared with the mean of weekends in the same period, the excess is 14% to 69%. The mean of real-time human flow on weekends and holidays is significantly lower, and the active time of the crowd is basically concentrated between 09 and 19. That is, the target period can be the characteristic period corresponding to the typical working day as the characteristic label, and these characteristic periods are all composed of typical working days.

[0076] Therefore, the real-time daily passenger flow data of typical working days is used as the data for the next step of analysis and processing.

[0077] It should be noted that the types of characteristic time periods determined above are merely examples and are not intended to limit the present invention. In other embodiments, other classifications and methods for determining target time periods may also be used.

[0078] S304. Use the ARIMA model to fit the passenger flow value on rainy days in the target period as the daily passenger flow benchmark value when rainy weather occurs, and calculate the passenger flow benchmark value at the time of rainy weather based on the daily real-time passenger flow data that has been supplemented, taking into account the average proportion of the passenger flow at each hour of the two days before and after the day.

[0079] In this embodiment, the specific implementation steps of step S304 may be:

[0080] After constructing the ARIMA model using the average real-time passenger flow on days without rainfall in the target period, the model is ARIMA(2, 1, 2). The ARIMA(2, 1, 2) after modeling is used to fit the passenger flow value on days with rainfall in the target period, which is used as the daily passenger flow value corresponding to the assumption that there is no rainfall on that day, that is, the daily passenger flow benchmark value. For the hourly passenger flow data, the average proportion of the hourly passenger flow on the two days before and after the day is considered based on the daily real-time passenger flow data that fills in the gaps to complete the calculation of the passenger flow benchmark value at the time of rainfall.

[0081] S305, calculating the hourly passenger flow fluctuation rate, the calculation formula is:

[0082]

[0083] In the formula, Indicates the real-time flow fluctuation rate under rainy weather conditions; Flow D(t) Indicates the actual value of the real-time flow of people at the tth moment on the Dth day; BFlow D(t) It represents the real-time passenger flow baseline value at time t on day D.

[0084] S204: Determine a rainfall risk classification basis based on the hourly passenger flow fluctuation rate and the hourly accumulated rainfall.

[0085] In some embodiments, Figure 4 FIG. 4 shows a flow chart for determining the rainfall risk classification basis according to an embodiment of the present invention. Figure 4 As shown, step S204 specifically includes:

[0086] S401. Divide the whole day into at least two sub-periods according to the distribution characteristics of the whole-day commuting time.

[0087] In step S401, a characteristic day in a characteristic period is divided. Taking a 24-hour day as an example, (i) according to the distribution characteristics of the commuting time throughout the day, the whole day is divided into four sub-periods: the morning peak period (7-9 o'clock), the daytime off-peak period (10-16 o'clock), the evening peak period (17-19 o'clock), and the night off-peak period (0-6 o'clock, 20-24 o'clock). The hourly passenger flow fluctuation characteristics under the rainfall conditions of each period are analyzed to distinguish the periods that are closely related to the rainfall and those that are not closely related.

[0088] S402: According to the real-time passenger flow fluctuation rate under the rainy weather conditions in each sub-period, the sub-periods related to the influence of rainfall are selected as target sub-periods.

[0089] In this embodiment, the analysis shows that the time periods closely related to the influence of rainfall are: the morning peak period and the evening peak period. The fluctuation rate of passenger flow increases with the increase of rainfall, and the fluctuation rate of the other two periods is relatively small. Therefore, the morning peak period and the evening peak period are selected as the target sub-periods.

[0090] S403: Clustering the rainfall levels in the target sub-periods, and obtaining the rainfall levels and impact levels based on the analysis of hourly passenger flow fluctuation characteristics as a basis for rainfall risk classification.

[0091] Exemplarily, this embodiment uses the K-means clustering method to perform cluster analysis on the rainfall levels during the morning and evening peaks, and obtains the rainfall levels and impacts based on the analysis of the hourly passenger flow fluctuation characteristics. The results are shown in Table 1.

[0092] Table 1 Rainfall levels and impacts

[0093]

[0094]

[0095] S205. Determine an emergency information release strategy based on the rainfall risk classification basis and the set rainfall threshold.

[0096] Based on step S201 to step S204, it can be concluded that the strategy for starting the release of the release time and the rainfall threshold is as follows: the strategy for matching the time of the emergency SMS release and the rainfall during the rainstorm emergency targeted service period is as follows: on weekdays, considering that the periods with large traffic flow are mainly concentrated in the morning and evening peaks, it is recommended to use the morning peak period (7-9 o'clock) and the evening peak period (17-19 o'clock) as key service periods. In these two sub-periods, in order to effectively deal with the impact of rainstorms, a specific rainfall threshold can be set to trigger the release of emergency targeted reminder information. Specifically, during the morning peak period, if the hourly rainfall exceeds 20 mm, or during the evening peak period, if the hourly rainfall exceeds 10 mm, the release mechanism of emergency reminder information can be activated. This measure will help alleviate the detention of real-time human (vehicle) flow in key areas. For weekends and holidays, since the real-time human flow will be relatively reduced, and the main active time of the crowd is concentrated in 9-19 o'clock, the release conditions of emergency targeted reminder information can be adjusted according to the actual situation of rainstorm warning or waterlogging. That is, when the rainstorm warning takes effect or waterlogging occurs in the area, the release of emergency reminder information can be activated. Such a strategy will be more targeted and effective, and will help to provide more effective emergency targeted services to the public during rainy weather.

[0097] Therefore, in this embodiment, based on the rainfall risk classification basis and the set rainfall threshold, the emergency information release strategy is determined as follows: during the morning peak period, the hourly rainfall exceeds 20 mm, or during the evening peak period, the hourly rainfall exceeds 10 mm, and the emergency reminder information release mechanism is activated.

[0098] In some embodiments, Figure 5 Another flow chart of a method for constructing an emergency information release strategy according to an embodiment of the present invention is shown. The emergency information release strategy is determined based on the rainfall risk classification and the set rainfall threshold, such as Figure 5 As shown, the emergency information release strategy construction method also includes:

[0099] S501. Obtain evaluation data of a target place; wherein the target place is a place that is spatially within a set range from a target point in a target area, and the evaluation data is the density of the place.

[0100] In this embodiment, the density of the venue is used as the evaluation data, and different types of key venues can be summarized as different POI densities. Different types of venues can be selected for calculation according to local needs. For example, for the purpose of emergency notification on weekdays, schools and hospitals are used as the research objects of key venues. The spatial distance is set to a radius of 1000 to 3000 meters, and 500 meters is used as a gradient. There are five gradients, specifically 1000 meters, 1500 meters, 2000 meters, 2500 meters, and 3000 meters from the target location. Therefore, the POI level includes kindergartens, primary and secondary schools, special education schools and other schools within 3000 meters of the center of the key area, first-, second- and third-class hospitals, and other unrated hospitals and other facilities.

[0101] S502. Obtain accessibility data of the target location; wherein the accessibility data of the target location is the accessibility of the target location at a radius of m gradients from the target point, where m is a positive integer greater than or equal to 1, and the gradient is a set length value.

[0102] In this embodiment, accessibility data based on different distances are obtained so as to define a warning range of people who may potentially go to a flooding location based on different distances. For example, in this example: the accessibility level includes walking accessibility and driving accessibility within 3,000 meters of the center of the key area, which is obtained by spatial analysis of road network data (because there are different methods for accessibility analysis, you can choose one here as needed).

[0103] The evaluation data and accessibility data of the target places obtained are shown in Table 2.

[0104] Table 2 Evaluation data and accessibility data

[0105]

[0106]

[0107] In some embodiments, after obtaining the evaluation data and accessibility data of the target place according to steps S501 and S502, the obtained data is also subjected to a correlation check to prove its explanatory role for the real-time flow of people.

[0108] Specifically, the POI density of step S501, the accessibility data of step S502, and A (the average of the flow of people at a certain time) data are correlated and analyzed to obtain the influencing factors with significant correlation with the flow of people. Next, hierarchical regression analysis is used to discuss the potential impact of significant influencing factors on real-time flow of people. Here, the explanation of different factors on real-time flow of people is analyzed by the degree of model fitting. For example, in this embodiment:

[0109] First, the established regression model is tested to be effective. This result shows that adding two influencing factors, POI and accessibility, can effectively optimize the real-time pedestrian flow fitting model. △R2 represents the degree of fit of the model. For example, in this example, the walking accessibility index category can explain 77.7% of the mean change in pedestrian flow, and the driving accessibility index can explain 22.1% of the mean change in pedestrian flow. Although the school density has the smallest △R2, it can only explain 0.1% of the mean change in pedestrian flow, but the model with POI attribute data is still effective.

[0110] S503: Determine the spatial scope of emergency information release based on the evaluation data and accessibility data of the target place.

[0111] In this embodiment, the spatial scope of emergency information release can be:

[0112] During the morning rush hour, if the hourly rainfall exceeds 20 mm, or during the evening rush hour, if the hourly rainfall exceeds 10 mm, the emergency warning information release mechanism is activated, and the release range includes: (i) the circular area with the target point as the center and the radius r1; (ii) the target place within the circular area with the target point as the center and the radius r2; (iii) the annular area with the target point as the center and the radius from r3 to r4;

[0113] On weekends and holidays, when a rainstorm warning takes effect or waterlogging occurs in the area, the release of emergency reminder information is initiated. The release range is: a circular area with a radius of r1 and a target point as the center.

[0114] It should be noted that the target point mentioned above can be the center point of the target area, for example, it can be a waterlogging location, r1, r2, r3 and r4 are different values, and different values ​​can be taken in different application scenarios, among which r1 is the smallest value and r2 is greater than r3.

[0115] Exemplarily, based on the data obtained in step S501 and step S502, it can be concluded that in terms of the spatial scope of the release circle selection: the scope strategy for the release of emergency text messages for rainstorm prevention is: during typical working days (08-19 o'clock), the targeted text message release range should include surrounding schools within a radius of 3 kilometers from the target location, aiming to remind the corresponding responsible persons and school teachers and students to pay attention to the real-time situation of the target location, and carefully consider whether to go there, so as to reduce unnecessary crowd gathering. The current targeted release range of emergency text messages for rainstorm prevention and waterlogging is mainly within a radius of 1 kilometer from the target location (based on the analysis of the optimal base station range). In order to more effectively convey information to people who may go to the target area, the release strategy should set up a double-layer warning circle: the inner circle is centered on the target location and has a radius of 1 kilometer, and the outer circle is an area with a radius of 2 to 3 kilometers. Such a setting not only covers the immediate area, but also warns a wider range of people. As a supplementary warning, it aims to further reduce unnecessary crowd flow to waterlogging sites.

[0116] In summary: In a specific embodiment, the dynamic publishing strategy that can be obtained is:

[0117] 1) On weekdays, if the hourly rainfall during the morning peak (7-9 am) exceeds 20 mm, or the hourly rainfall during the evening peak (17-19 pm) exceeds 10 mm, the emergency reminder SMS release mechanism will be activated. The release range includes: (i) the area within a 1 km radius of the waterlogged site, (ii) the responsible persons of surrounding schools within a 3 km radius of the waterlogged site, (iii) the inner circle with a radius of 1 km around the waterlogged site, and the outer circle with a radius of 2 to 3 km in the immediate vicinity.

[0118] 2) On weekends and holidays, when a rainstorm warning is in effect or waterlogging occurs in the area, emergency reminder information can be issued. The release range is: an area with a radius of 1 km around the waterlogging location.

[0119] Figure 6 The structure diagram of an emergency information release strategy construction device according to an embodiment of the present invention is shown. The embodiment of the present invention also provides an emergency information release strategy construction device, such as Figure 6 As shown, the device comprises:

[0120] The first data acquisition module 601 is configured to acquire the daily hourly flow data of the target area in the historical period;

[0121] The second data acquisition module 602 is configured to acquire the hourly accumulated rainfall in the historical period of the automatic meteorological station closest to the target area in a straight line;

[0122] A volatility calculation module 603 is configured to calculate the hourly passenger flow volatility based on the daily hourly passenger flow data;

[0123] A classification basis determination module 604 is configured to determine a rainfall risk classification basis based on the hourly passenger flow fluctuation rate and the hourly accumulated rainfall;

[0124] The release strategy determination module 605 is configured to determine the emergency information release strategy based on the rainfall risk classification basis and the set rainfall threshold.

[0125] In some embodiments, the volatility calculation module is further configured to:

[0126] Divide the historical period into multiple characteristic periods, and assign a characteristic label to each characteristic period; wherein the characteristic period includes at least n characteristic days, n is a positive integer greater than or equal to 1, and the characteristic label is used to characterize the characteristic date corresponding to the characteristic period;

[0127] The real-time average flow of people during the characteristic period is calculated using the following formula:

[0128]

[0129] In the formula, A j represents the mean flow of people at the jth time in the characteristic period, D ij It represents the real-time flow of people at the jth time of the i-th characteristic day in the characteristic period, where i is the serial number of the characteristic day and j is the serial number of the time;

[0130] The characteristic period corresponding to the feature label with the highest mean value of real-time passenger flow is used as the target period, and the ARIMA model is constructed based on the mean value of real-time passenger flow on rainless days in the target period.

[0131] The ARIMA model is used to fit the flow of people on rainy days in the target period, which is used as the daily flow benchmark when rainy weather occurs. The flow benchmark at the time of rain is calculated based on the daily real-time flow data that is supplemented, and the average proportion of the flow of people at each hour of the two days before and after the day is considered to complete the calculation of the flow benchmark at the time of rain.

[0132] The hourly passenger flow fluctuation rate is calculated using the following formula:

[0133]

[0134] In the formula, Indicates the real-time flow fluctuation rate under rainy weather conditions; FlowD(t) Indicates the actual value of the real-time flow of people at the tth moment on the Dth day; BFlow D(t) It represents the real-time passenger flow baseline value at time t on day D.

[0135] In some embodiments, the classification basis determination module is further configured to:

[0136] According to the distribution characteristics of commuting time throughout the day, the whole day is divided into at least two sub-periods;

[0137] According to the real-time passenger flow fluctuation rate under the rainy weather conditions in each sub-period, the sub-periods related to the impact of rainfall are selected as target sub-periods;

[0138] The rainfall levels in the target sub-periods are clustered to obtain the rainfall levels and impact levels based on the analysis of hourly passenger flow fluctuation characteristics, which serve as the basis for rainfall risk classification.

[0139] In some embodiments, the target sub-period includes a morning peak period and an evening peak period, and the release strategy determination module is further configured to determine the emergency information release strategy based on the rainfall risk classification basis and the set rainfall threshold:

[0140] If the hourly rainfall exceeds 20 mm during the morning rush hour, or exceeds 10 mm during the evening rush hour, the emergency warning information release mechanism will be activated.

[0141] In some embodiments, the apparatus further comprises:

[0142] A third data acquisition module is configured to acquire evaluation data of a target place; wherein the target place is a place that is spatially within a set range from a target point in a target area, and the evaluation data is a place density;

[0143] A fourth data acquisition module is configured to acquire accessibility data of a target location; wherein the accessibility data of the target location is accessibility of m gradients of a radius from the target location to the target point, where m is a positive integer greater than or equal to 1, and the gradient is a set length value;

[0144] The spatial scope determination module is configured to determine the spatial scope of emergency information release based on the assessment data and accessibility data of the target place.

[0145] In some embodiments, the apparatus further comprises a factor verification module configured to:

[0146] Correlate the evaluation data and accessibility data of the target place with the average flow of people at a certain time, and determine the influencing factors that are significantly correlated with the flow of people;

[0147] Hierarchical regression analysis was used to determine the impact of influencing factors on real-time pedestrian flow.

[0148] In some embodiments, the spatial range determination module is further configured to determine the spatial range of emergency information release based on the evaluation data and accessibility data of the target location as follows:

[0149] During the morning rush hour, if the hourly rainfall exceeds 20 mm, or during the evening rush hour, if the hourly rainfall exceeds 10 mm, the emergency warning information release mechanism is activated, and the release range includes: (i) the circular area with the target point as the center and the radius r1; (ii) the target place within the circular area with the target point as the center and the radius r2; (iii) the annular area with the target point as the center and the radius from r3 to r4;

[0150] On weekends and holidays, when a rainstorm warning takes effect or waterlogging occurs in the area, the release of emergency reminder information is initiated. The release range is: a circular area with a radius of r1 and a target point as the center.

[0151] It should be noted that the device described in this embodiment and the method described previously belong to the same technical concept, have the same technical principles, and can achieve the same beneficial effects, so they will not be repeated here.

[0152] An embodiment of the present invention further provides an emergency information release strategy construction system, the system comprising: a memory for storing a computer program; a processor for executing the computer program to implement the method described in any of the above embodiments.

[0153] An embodiment of the present invention further provides a non-transitory computer-readable storage medium storing instructions, and when the instructions are executed by a processor, the method described in any of the above embodiments is executed.

[0154] The above implementation modes are only used to illustrate the present invention, but not to limit the present invention. Ordinary technicians in the relevant technical field can make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, all equivalent technical solutions also belong to the scope of the present invention.

Claims

1. A method for constructing an emergency information release strategy, characterized in that: The method comprises: Obtain the daily hourly flow data of the target area during the historical period; Obtain the hourly accumulated rainfall in the historical period of the automatic meteorological station closest to the target area in a straight line; Calculate the hourly passenger flow fluctuation rate based on the daily hourly passenger flow data; Determine a rainfall risk classification basis based on the hourly passenger flow fluctuation rate and the hourly accumulated rainfall; The emergency information release strategy is determined based on the rainfall risk classification basis and the set rainfall threshold.

2. The method for constructing an emergency information release strategy according to claim 1, characterized in that: Calculating the hourly passenger flow fluctuation rate based on the daily hourly passenger flow data includes: Divide the historical period into multiple characteristic periods, and assign a characteristic label to each characteristic period; wherein the characteristic period includes at least n characteristic days, n is a positive integer greater than or equal to 1, and the characteristic label is used to characterize the characteristic date corresponding to the characteristic period; The real-time average flow of people during the characteristic period is calculated using the following formula: In the formula, A j represents the mean flow of people at the jth time in the characteristic period, D ij It represents the real-time flow of people at the jth time of the i-th characteristic day in the characteristic period, where i is the serial number of the characteristic day and j is the serial number of the time; The characteristic period corresponding to the feature label with the highest mean value of real-time passenger flow is used as the target period, and the ARIMA model is constructed based on the mean value of real-time passenger flow on rainless days in the target period. The ARIMA model is used to fit the flow of people on rainy days in the target period, which is used as the daily flow benchmark when rainy weather occurs. The flow benchmark at the time of rain is calculated based on the daily real-time flow data that is supplemented, and the average proportion of the flow of people at each hour of the two days before and after the day is considered to complete the calculation of the flow benchmark at the time of rain. The hourly passenger flow fluctuation rate is calculated using the following formula: In the formula, Indicates the real-time flow fluctuation rate under rainy weather conditions; Flow D(t) Indicates the actual value of the real-time flow of people at the tth moment on the Dth day; BFlow D(t) It represents the real-time passenger flow baseline value at time t on day D.

3. The method for constructing an emergency information release strategy according to claim 2, characterized in that: The rainfall risk classification basis is determined based on the hourly passenger flow fluctuation rate and the hourly accumulated rainfall, including: According to the distribution characteristics of commuting time throughout the day, the whole day is divided into at least two sub-periods; According to the real-time passenger flow fluctuation rate under the rainy weather conditions in each sub-period, the sub-periods related to the impact of rainfall are selected as target sub-periods; The rainfall levels in the target sub-periods are clustered to obtain the rainfall levels and impact levels based on the analysis of hourly passenger flow fluctuation characteristics, which serve as the basis for rainfall risk classification.

4. The method for constructing an emergency information release strategy according to claim 3, characterized in that: The target sub-period includes the morning peak period and the evening peak period. Based on the rainfall risk classification basis and the set rainfall threshold, the emergency information release strategy is determined as follows: If the hourly rainfall exceeds 20 mm during the morning rush hour, or exceeds 10 mm during the evening rush hour, the emergency warning information release mechanism will be activated.

5. The method for constructing an emergency information release strategy according to claim 1, characterized in that: After determining the emergency information release strategy based on the rainfall risk classification and the set rainfall threshold, the method further includes: Acquire evaluation data of a target place; wherein the target place is a place that is spatially within a set range from a target point in a target area, and the evaluation data is a place density; Obtaining accessibility data of the target location; wherein the accessibility data of the target location is the accessibility of the target location at a radius of m gradients from the target point, where m is a positive integer greater than or equal to 1, and the gradient is a set length value; Based on the assessment data and accessibility data of the target place, the spatial scope of emergency information release is determined.

6. The method for constructing an emergency information release strategy according to claim 5, characterized in that: Before determining the spatial scope of emergency information release based on the evaluation data and accessibility data of the target place, the method further includes: Correlate the evaluation data and accessibility data of the target place with the average flow of people at a certain time, and determine the influencing factors that are significantly correlated with the flow of people; Hierarchical regression analysis was used to determine the impact of influencing factors on real-time pedestrian flow.

7. The method for constructing an emergency information release strategy according to claim 5, characterized in that: Based on the assessment data and accessibility data of the target sites, the spatial scope of emergency information release is determined as follows: During the morning rush hour, if the hourly rainfall exceeds 20 mm, or during the evening rush hour, if the hourly rainfall exceeds 10 mm, the emergency warning information release mechanism is activated, and the release range includes: (i) the circular area with the target point as the center and the radius r1; (ii) the target place within the circular area with the target point as the center and the radius r2; (iii) the annular area with the target point as the center and the radius from r3 to r4; On weekends and holidays, when a rainstorm warning takes effect or waterlogging occurs in the area, the release of emergency reminder information is initiated. The release range is: a circular area with a radius of r1 and a target point as the center.

8. An emergency information release strategy construction device, characterized in that: The device: A first data acquisition module is configured to acquire hourly daily human traffic data of a target area during a historical period; The second data acquisition module is configured to obtain the hourly accumulated rainfall in the historical period of the automatic meteorological station closest to the target area in a straight line; A volatility calculation module, configured to calculate the hourly passenger flow volatility based on the daily hourly passenger flow data; A classification basis determination module is configured to determine a rainfall risk classification basis based on the hourly passenger flow fluctuation rate and the hourly accumulated rainfall; The release strategy determination module is configured to determine the emergency information release strategy based on the rainfall risk classification basis and the set rainfall threshold.

9. An emergency information release strategy construction system, characterized by: The system comprises: Memory for storing computer programs; A processor, configured to execute the computer program to implement the method according to any one of claims 1 to 7. 10 . A non-transitory computer-readable storage medium storing instructions, which, when executed by a processor, perform the method according to claim 1 .

Images