Emergency event prevention and control dispatch method, device, electronic device and storage medium

Abstract

The embodiment of the present disclosure discloses an emergency event prevention and control scheduling method, device, electronic device and storage medium, the method comprising: acquiring monitoring data streams of each traffic road in real time; inputting the monitoring data streams into a trained Bayesian network model to obtain a first probability of an accident occurring at a target road section and a target time, wherein the monitoring data stream includes monitoring data of the target road section; when the first probability reaches a warning threshold, issuing an early warning for the target road section and the target time, so as to perform emergency event prevention and control scheduling for the target road section at the target time; wherein each node in the Bayesian network model and the initial value of the conditional probability of each node are determined based on the correspondence between accident triggering conditions, accident triggering behaviors and accident results in historical accidents that have occurred obtained through a first random forest model. The present disclosure can provide early warning of accidents and effectively prevent and control the occurrence of accidents.

Description

Technical Field

[0001] The present disclosure relates to the field of emergency prevention and control technology, and in particular to an emergency event prevention and control scheduling method, device, electronic device and storage medium. Background Art

[0002] With the rapid development of urban economy, urban population has expanded rapidly. While increasing employment and driving the economy, it has also brought tremendous pressure to urban infrastructure such as traffic and public security.

[0003] However, urban patrol and control manpower is often limited, and the investment in prevention and control is not proportional to the actual success of the work. Existing smart city emergency dispatch technology is limited to conducting incident command and personnel dispatch after an incident occurs. This emergency dispatch method can only reduce the losses caused by accidents, but cannot prevent them from happening. Summary of the Invention

[0004] In order to solve the above technical problems or at least partially solve the above technical problems, the embodiments of the present disclosure provide an emergency event prevention and control scheduling method, device, electronic device and storage medium, which can provide early warning of accidents and effectively prevent the occurrence of accidents.

[0005] In a first aspect, an embodiment of the present disclosure provides an emergency event prevention and control scheduling method, comprising:

[0006] Obtain monitoring data streams of each traffic road in real time;

[0007] Inputting the monitoring data stream into a trained Bayesian network model to obtain a first probability of an accident occurring on a target road section at a target time, wherein the monitoring data stream includes monitoring data of the target road section at the target time;

[0008] When the first probability reaches a warning threshold, issuing a warning for the target road section and the target time, so as to carry out emergency prevention and control scheduling for the target road section at the target time;

[0009] Among them, each node in the Bayesian network model and the initial value of the conditional probability of each node are determined based on the correspondence between the accident triggering conditions, accident triggering behaviors and accident results in historical accidents that have occurred obtained through the first random forest model.

[0010] Optionally, also include:

[0011] Based on detailed record data of historical traffic accidents that have occurred, a first training sample set and a first test sample set are determined; the first training sample set includes accident cause data partitions, the first random forest model is trained based on the first training sample set and tested based on the first test sample set, and the first random forest model is used to determine the correspondence between accident triggering conditions, accident triggering behaviors and accident results.

[0012] Optionally, also include:

[0013] Determine detailed record data of the first traffic accident that has occurred;

[0014] Inputting the detailed record data of the first traffic accident into the trained patrol model to obtain a first target road section and a reference time where the accident rate is greater than a preset threshold;

[0015] Sending the first target road section and reference time to an emergency incident prevention and control scheduling platform to perform emergency incident prevention and control scheduling based on the first target road section and reference time;

[0016] The inspection model includes a second random forest model and a third random forest model; the second random forest model is trained based on the second training sample set and tested based on the second test sample set, and the third random forest model is trained based on the third training sample set and tested based on the third test sample set;

[0017] The second training sample set includes spatial point data partitions, and the second random forest model is used to determine the corresponding relationship between spatial point locations and accident probability;

[0018] The third training sample set includes time period data partitions, and the third random forest model is used to determine the corresponding relationship between time periods and accident probability;

[0019] The second training sample set, the third training sample set, the second test sample set, and the third test sample set are determined based on detailed record data of historical traffic accidents that have occurred.

[0020] Optionally, the first random forest model, the second random forest model, and the third random forest model each include multiple decision trees.

[0021] Optionally, after sending the first target road section and reference time to the emergency prevention and control scheduling platform, the method further includes:

[0022] According to the reference time, the first target road section is marked with multiple layers of points in a geographic information system.

[0023] Optionally, also include:

[0024] After determining the accident result corresponding to the monitoring data stream, the Bayesian network model is trained based on the corresponding relationship between the accident triggering condition, the accident triggering behavior and the accident result corresponding to the monitoring data stream.

[0025] Optionally, the issuing of an early warning for the target road section and the target time includes:

[0026] The target road section and the target time are displayed in a geographic information system associated with the emergency safety notification and warning platform. In a second aspect, the embodiment of the present disclosure further provides an emergency event prevention and control scheduling device, which includes:

[0027] Acquisition module, used to obtain the monitoring data stream of each traffic road in real time;

[0028] a prediction module, configured to input the monitoring data stream into a trained Bayesian network model to obtain a first probability of an accident occurring on a target road section at a target time, wherein the monitoring data stream includes monitoring data of the target road section at the target time;

[0029] an early warning module, configured to issue an early warning for the target road section and the target time when the first probability reaches an early warning threshold, so as to perform emergency prevention and control scheduling for the target road section at the target time;

[0030] Among them, each node in the Bayesian network model and the initial value of the conditional probability of each node are determined based on the correspondence between the accident triggering conditions, accident triggering behaviors and accident results in historical accidents that have occurred obtained through the first random forest model.

[0031] In a third aspect, an embodiment of the present disclosure further provides an electronic device, the electronic device comprising:

[0032] one or more processors;

[0033] a storage device for storing one or more programs;

[0034] When the one or more programs are executed by the one or more processors, the one or more processors implement the emergency event prevention and control scheduling method as described above.

[0035] In a fourth aspect, an embodiment of the present disclosure further provides a computer-readable storage medium on which a computer program is stored, which, when executed by a processor, implements the emergency event prevention and control scheduling method as described above.

[0036] In a fifth aspect, an embodiment of the present disclosure further provides a computer program product, which includes a computer program or instructions, and when the computer program or instructions are executed by a processor, implements the emergency event prevention and control scheduling method as described above.

[0037] The technical solution provided by the embodiments of the present disclosure has at least the following advantages compared with the prior art:

[0038] The emergency event prevention and control scheduling method provided by the embodiment of the present disclosure analyzes the real-time acquired monitoring data stream through a trained Bayesian network model to obtain the first probability of an accident occurring on the target road section at the target time. When the first probability reaches the warning threshold, a warning is issued, thereby achieving the purpose of early warning of accidents and effective prevention and control of accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] The above and other features, advantages, and aspects of the various embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and that the originals and elements are not necessarily drawn to scale.

[0040] Figure 1 This is a flow chart of an emergency event prevention and control scheduling method according to an embodiment of the present disclosure;

[0041] Figure 2 Schematic diagram of the structure of an emergency event prevention and control dispatching system in an embodiment of the present disclosure;

[0042] Figure 3 Schematic diagram of the structure of an emergency event prevention and control scheduling device in an embodiment of the present disclosure;

[0043] Figure 4 Schematic diagram of the structure of an electronic device in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0044] The following describes embodiments of the present disclosure in more detail with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments described herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of protection of the present disclosure.

[0045] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0046] As used herein, the term "including" and its variations are open-ended, i.e., "including but not limited to." The term "based on" means "based, at least in part, on." The term "one embodiment" means "at least one embodiment," the term "another embodiment" means "at least one additional embodiment," and the term "some embodiments" means "at least some embodiments." Other terms are defined in the following description.

[0047] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are only used to distinguish different devices, modules or units, and are not used to limit the order or interdependence of the functions performed by these devices, modules or units.

[0048] It should be noted that the modifications of "one" and "multiple" mentioned in the present disclosure are illustrative rather than restrictive, and those skilled in the art should understand that unless otherwise clearly indicated in the context, they should be understood as "one or more".

[0049] The names of the messages or information exchanged between multiple devices in the embodiments of the present disclosure are only used for illustrative purposes and are not used to limit the scope of these messages or information.

[0050] Figure 1 This is a flowchart of an emergency incident prevention and control dispatch method according to an embodiment of the present disclosure. This embodiment is applicable to predicting traffic accidents on the road and providing early warnings. This method can be executed by an emergency incident prevention and control dispatch device, which can be implemented using software and / or hardware and can be configured in an electronic device, such as a server.

[0051] like Figure 1 As shown, the method may specifically include:

[0052] Step 110: Acquire the monitoring data stream of each traffic road in real time.

[0053] Among them, the meaning of real-time acquisition can be understood as acquisition according to a set period or frequency. Optionally, the monitoring data stream of each traffic road can be obtained through the cameras currently installed on each road by the Traffic Management Bureau. It is also possible to set up a shooting device for monitoring data streams for the solution of the embodiment of the present disclosure in a targeted manner at an appropriate location. The shooting device includes a chip that supports algorithm implantation and a monitoring camera with edge computing capabilities. It should be noted that the monitoring data stream can be transmitted from the shooting device to the emergency event prevention and control dispatch device through a dedicated video network to ensure transmission speed and transmission reliability.

[0054] Monitoring data streams can be images or videos. They can reflect the current time, weather conditions, road traffic conditions, and road characteristics. For example, whether it's early morning, evening, rush hour, or rush hour. Current weather conditions include rain, snow, or fog. Current road traffic conditions include speeding vehicles and vehicles crossing the road line. Road characteristics include intersections, curves, and streetlights.

[0055] Step 120: Input the monitoring data stream into a trained Bayesian network model to obtain a first probability of an accident occurring on a target road section at a target time, wherein the monitoring data stream includes monitoring data of the target road section.

[0056] Step 130: When the first probability reaches a warning threshold, a warning is issued for the target road section and the target time, so as to carry out emergency prevention and control scheduling for the target road section at the target time.

[0057] Among them, each node in the Bayesian network model and the initial value of the conditional probability of each node are determined based on the correspondence between the accident triggering conditions, accident triggering behaviors and accident results in historical accidents that have occurred obtained through the first random forest model. Historical accidents refer to traffic accidents that have occurred. For traffic accidents that have occurred, there are usually detailed records corresponding to the traffic accidents in the public security traffic network, such as the cause of the traffic accident. Historical accident triggering conditions are, for example, rain, curved road sections, early morning, heavy traffic or heavy pedestrian flow, that is, the triggering conditions for the occurrence of accidents can be determined from dimensions such as weather, location, time period, traffic or pedestrian flow. Historical accident triggering behaviors are, for example, driving over the line multiple times, leaving the lane, running a red light, speeding for a long time, etc. Historical accident results are, for example, rear-end collisions between two vehicles, chain rear-end collisions of three or more vehicles, and scrapes between two vehicles.

[0058] By conducting emergency prevention and control scheduling for the target road section at the target time, the actual incidence of accidents can be effectively reduced. For example, when it is determined that there are many vehicles crossing the line on the target road section at the target time, manual police force will be promptly assigned to the target road section to conduct traffic control and clearing, etc., thereby preventing the actual incidence of traffic accidents. After determining the accident result corresponding to the monitoring data stream, the Bayesian network model is trained based on the corresponding relationship between the accident triggering conditions, accident triggering behaviors and accident results corresponding to the monitoring data stream, that is, sample data is continuously collected, and the Bayesian network model is continuously iterated to continuously improve the output reliability of the Bayesian network model, which can solve the current problem of insufficient sample data.

[0059] Specifically, detailed records of traffic accidents in the past few years (for example, the past 10 years) are obtained through local traffic police networks, that is, the first training sample set and the first test sample set are determined based on the detailed record data of historical traffic accidents that have occurred. The first training sample set includes accident cause data partitions, such as accident cause data partitions with characteristics such as whether it is raining, whether the road is slippery, and whether the person is speeding. The first random forest model is trained based on the first training sample set and tested based on the first test sample set. The first random forest model is used to determine the correspondence between accident triggering conditions, accident triggering behaviors, and accident results. The first random forest model includes multiple decision trees.

[0060] Furthermore, the method further comprises:

[0061] Determine detailed record data of a first traffic accident that has occurred; input the detailed record data of the first traffic accident into a trained patrol model to obtain a first target road section and reference time with an accident rate greater than a preset threshold; send the first target road section and reference time to an emergency incident prevention and control scheduling platform to perform emergency incident prevention and control scheduling based on the first target road section and reference time; wherein the patrol model includes a second random forest model and a third random forest model.

[0062] The second random forest model is trained based on the second training sample set and tested based on the second test sample set, and the third random forest model is trained based on the third training sample set and tested based on the third test sample set.

[0063] The second training sample set includes spatial point data partitions, such as data partitions based on features such as whether it is an intersection, whether it is a monitored road, and whether there are street lights. The second random forest model is used to determine the correspondence between spatial points and the probability of an accident. The third training sample set includes time period data partitions, such as data partitions based on features such as whether it is evening, whether it is after get off work, and whether it is early morning. The third random forest model is used to determine the correspondence between time periods and the probability of an accident. The second training sample set, the third training sample set, the second test sample set, and the third test sample set are determined based on detailed record data of historical traffic accidents that have occurred.

[0064] The first, second, and third random forest models each include multiple decision trees. Specifically, detailed traffic accident records from the past few years are obtained from local traffic police networks and preprocessed. Multiple decision tree models are then trained using offline batch data training to develop a relatively complete random forest model. The output of this random forest model is then subjected to performance evaluation and data iteration to ensure the reliability of the model's output.

[0065] The random forest model is a supervised learning machine learning algorithm. The aforementioned random forest model includes a first random forest model, a second random forest model, and a third random forest model. The first random forest model is used to determine the correspondence between accident triggering conditions, accident triggering behaviors, and accident outcomes; the second random forest model is used to determine the correspondence between spatial locations and accident probability; and the third random forest model is used to determine the correspondence between time periods and accident probability. In summary, the first, second, and third random forest models are used to assist in emergency prevention and control scheduling decisions and to assist in building the aforementioned Bayesian network model.

[0066] It's understandable that to improve model training speed and performance, it's necessary to perform feature separation on the detailed traffic accident records. For example, the spatial point data partition includes features such as whether the accident occurred at an intersection, on a monitored road, or with streetlights. The time period data partition includes features such as whether the accident occurred at night, after get off work, or in the early morning. The accident cause data partition includes features such as whether it rained, whether the road was slippery, and whether the accident occurred due to speeding. The data set is divided into three training sample sets and several test sets. The training sample sets are sampled N times with replacement, equivalent to the sample size N, to balance errors and ensure data accuracy. Data preprocessing and model training can be performed simultaneously, with multiple iterations. In summary, the data in the training sample set includes spatial point data partitions, time period data partitions, and accident cause data partitions. The spatial point data partitions include features such as whether the accident occurred at an intersection, on a monitored road, or with streetlights. The time period data partitions include features such as whether the accident occurred at night, after get off work, or in the early morning. The accident cause data partitions include features such as whether it rained, whether the road was slippery, and whether the accident occurred due to speeding.

[0067] Use the training set to build several decision trees in the above three random forest models. The test data set needs to pass through the second random forest model and the third random forest model in turn. When the probability of the accident spatial point and time period in the test sample data is greater than the average accident probability, multi-layer GIS marking is performed for different time periods; use different test data sets to mark GIS points, and record the overlap of GIS markings of the same time period layers of different test sets. If the overlap is not high, it means that the model performance is not good, and the model needs to continue training or adjust the model structure. Therefore, the overlap can be used to determine whether to continue data training and model iteration. After summarizing the sample results, the final result is checked and output to the emergency prevention and control dispatch platform to assist the emergency prevention and control dispatch platform in reasonably arranging patrol personnel to the scene for prevention and control in accident-prone sections and time periods.

[0068] Given that traffic accident details are stored in different urban areas with varying standards, the use of a random forest model algorithm can maintain a certain level of accuracy even when data features are missing and is less prone to overfitting than a single decision tree. Furthermore, random forests can determine the mutual influence and importance of different data features, which can assist in the subsequent construction of Bayesian network models.

[0069] The Bayesian network model is an imprecise probability graph model that expresses the dependencies between different events. Based on the observed data sets (i.e., training sample sets and test sample sets) and the first random forest model, it mines the dependencies between relevant factors such as the triggering conditions (weather, location, time period, traffic flow, pedestrian flow, etc.), triggering behaviors (multiple driving over the line, deviation, running red lights, long-term speeding, etc.), and accident results (different emergency prevention and control risk levels are output according to the accident results). A Bayesian network model with the highest degree of fit to the observed data set is built, and the conditional probability of each node of the Bayesian network is taken according to the observed data set. The training data set is then input to optimize and iterate the Bayesian network model. It can be understood that the above-mentioned Bayesian network model, the first random forest model, the second random forest model, and the third random forest model are four independent models. Among them, the first random forest model is used to determine the correspondence between accident triggering conditions, accident triggering behaviors, and accident results. Each node in the Bayesian network model, along with the initial values ​​of its conditional probabilities, is determined based on the correspondence between accident triggering conditions, accident triggering behaviors, and accident outcomes in historical accidents, as derived through the first random forest model. The Bayesian network model is used to determine the initial probability of an accident occurring on a target road section and at a target time based on real-time monitoring data streams from each road. This allows for early warning-level emergency response and scheduling of accidents that have not yet occurred, effectively preventing and controlling accidents.

[0070] The second random forest model is used to determine the correspondence between spatial points and accident probability. The third random forest model is used to determine the correspondence between time periods and accident probability. Based on the second and third random forest models, a patrol model based on the spatial and temporal characteristics of past accidents is obtained. This patrol model is used to analyze detailed record data of past traffic accidents to obtain high-accident sections and time periods. These points are marked in a geographic information system (GIS), resulting in a multi-layer GIS point mark based on time periods. These are then output to the emergency prevention and control dispatch platform for reference, allowing for the rational deployment of patrol police forces and effective accident prevention and control.

[0071] After sending the first target road section and reference time to the emergency event prevention and control scheduling platform, it also includes: according to the reference time, marking the first target road section with multiple layers of points in the geographic information system and / or digital twin intelligent operation center (Intelligent Operations Center, IOC) for easy viewing.

[0072] The warning of the target road section and the target time includes displaying the target road section and the target time on a geographic information system and / or a digital twin intelligent operation center associated with the emergency safety notification and warning platform. By using the digital twin intelligent operation center, the display granularity can be accurate to buildings, terrain, bridges, rivers, or vegetation.

[0073] The emergency response and prevention dispatch method provided by the disclosed embodiments uses historical traffic accident data and real-time monitoring data streams as a foundation. It utilizes a random forest algorithm model and a Bayesian network probabilistic model to provide emergency response and prevention dispatch decisions, thereby reducing the incidence of accidents. A multi-layered geographic information system (GIS) identifier, primarily based on spatial points and time periods, incorporates external factors such as weather and environmental factors as Bayesian network node conditions, assigning different risk levels and improving the accuracy of response and prevention dispatch decisions.

[0074] Based on the above embodiments, Figure 2The schematic diagram of the structure of an emergency incident prevention and control dispatch system is shown, which includes a data input module, a machine learning model processing module, and a result output module. This includes offline database data input, which refers to the collected detailed records of past traffic accidents. This is followed by data preprocessing, including sample data classification and cleaning, to obtain a sample training dataset and a sample test dataset. Based on the sample training dataset, a first random forest model, a second random forest model, and a third random forest model are trained. The trained second and third random forest models are integrated into a patrol model. The patrol model is tested and iterated using the sample test dataset to obtain a patrol model based on the spatial and temporal characteristics of past accidents. This patrol model is then used to analyze the detailed records of past traffic accidents to identify high-incidence road sections and time periods, mark them in a geographic information system, and obtain multi-layered GIS point markings based on time periods. These are then output to the emergency prevention and control dispatch platform for reference, enabling the rational deployment of patrol police forces and effectively controlling the probability of accidents.

[0075] On the other hand, a Bayesian network prediction model is built based on the output results of the first random forest model to predict and warn of traffic accidents that have not yet occurred. Specifically, the initial values ​​of the conditional probabilities of each node and each node in the Bayesian network model are determined based on the correspondence between the accident triggering conditions, accident triggering behaviors and accident results in historical accidents that have occurred obtained through the first random forest model. The Bayesian network model is then used to predict accidents on real-time monitoring stream data, and after the accident results are known, the real-time monitoring stream data is used as a new training sample to train the Bayesian network model online to continuously improve the output accuracy of the Bayesian network model. During the prediction, if it is determined that the probability of an accident has reached the warning threshold, the triggering location and time (i.e., the target road section and target time) are displayed in real time and sent to the emergency safety notification and warning system to provide reference data for prevention and control scheduling.

[0076] Figure 3 The figure is a schematic diagram of the structure of an emergency event prevention and control scheduling device in an embodiment of the present disclosure. The emergency event prevention and control scheduling device provided in the embodiment of the present disclosure can be configured in a client or a server. The emergency event prevention and control scheduling device 300 specifically includes: an acquisition module 310, a prediction module 320, and an early warning module 330.

[0077] Among them, the acquisition module 310 is used to obtain the monitoring data stream of each traffic road in real time; the prediction module 320 is used to input the monitoring data stream into the trained Bayesian network model to obtain the first probability of an accident occurring on the target section and the target time, and the monitoring data stream includes the monitoring data of the target section at the target time; the early warning module 330 is used to issue an early warning to the target section and the target time when the first probability reaches the early warning threshold, so as to carry out emergency prevention and control scheduling for the target section at the target time; wherein, each node in the Bayesian network model and the initial value of the conditional probability of each node are determined based on the correspondence between the accident triggering conditions, accident triggering behaviors and accident results in historical accidents that have occurred obtained through the first random forest model.

[0078] Optionally, it also includes: a first determination module, used to determine a first training sample set and a first test sample set based on detailed record data of historical traffic accidents that have occurred; the first training sample set includes accident cause data partitioning, the first random forest model is trained based on the first training sample set and tested based on the first test sample set, and the first random forest model is used to determine the correspondence between accident triggering conditions, accident triggering behaviors and accident results.

[0079] Optionally, it also includes: a second determination module for determining detailed record data of a first traffic accident that has occurred; an analysis module for inputting the detailed record data of the first traffic accident into a trained patrol model to obtain a first target road section and reference time with an accident rate greater than a preset threshold; a sending module for sending the first target road section and reference time to an emergency incident prevention and control scheduling platform to perform emergency incident prevention and control scheduling based on the first target road section and reference time; wherein the patrol model includes a second random forest model and a third random forest model; the second random forest model is trained based on the second training sample set and tested based on the second test sample set, and the third random forest model is trained based on the third training sample set and tested based on the third test sample set; the second training sample set includes spatial point data partitions, and the second random forest model is used to determine the correspondence between spatial points and accident probability; the third training sample set includes time period data partitions, and the third random forest model is used to determine the correspondence between time periods and accident probability; the second training sample set, the third training sample set, the second test sample set, and the third test sample set are determined based on detailed record data of historical traffic accidents that have occurred.

[0080] Optionally, the first random forest model, the second random forest model, and the third random forest model each include multiple decision trees.

[0081] Optionally, it also includes: a marking module, which is used to mark the first target road section with multiple layers of points in the geographic information system according to the reference time after sending the first target road section and reference time to the emergency event prevention and control scheduling platform.

[0082] Optionally, it also includes: a training module, which is used to train the Bayesian network model based on the correspondence between the accident triggering conditions, accident triggering behaviors and accident results corresponding to the monitoring data stream after determining the accident results corresponding to the monitoring data stream; each node condition in the Bayesian network model includes weather type and environment type.

[0083] Optionally, the warning module 330 includes a display unit for displaying the target road section and the target time in a geographic information system associated with the emergency safety notification and warning platform.

[0084] The emergency response and dispatch device provided by the disclosed embodiments uses historical traffic accident data and real-time monitoring data streams to provide emergency response and dispatch decisions using a random forest algorithm model and a Bayesian network probability model, thereby reducing the incidence of accidents. A multi-layered geographic information system (GIS) identifier based on spatial points and time periods, along with external factors such as weather and environmental factors as Bayesian network node conditions, provides different risk levels and improves the accuracy of response and dispatch decisions.

[0085] The emergency event prevention and control scheduling device provided in the embodiment of the present disclosure can execute the steps of the emergency event prevention and control scheduling method provided in the method embodiment of the present disclosure. The execution steps and beneficial effects are no longer repeated here.

[0086] Figure 4 This is a schematic diagram of the structure of an electronic device in the embodiment of the present disclosure. Figure 4 , which shows a schematic structural diagram of an electronic device 500 suitable for implementing the embodiments of the present disclosure. The electronic device 500 in the embodiments of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), wearable electronic devices, and the like, as well as fixed terminals such as digital TVs, desktop computers, smart home devices, and the like. Figure 4 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present disclosure.

[0087] like Figure 4As shown, the electronic device 500 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes to implement the methods of the embodiments described in the present disclosure according to the program stored in the read-only memory (ROM) 502 or the program loaded from the storage device 508 into the random access memory (RAM) 503. Various programs and data required for the operation of the electronic device 500 are also stored in the RAM 503. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0088] Typically, the following devices may be connected to the I / O interface 505: an input device 506 including, for example, a touch screen, a touchpad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 508 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 509. The communication device 509 may allow the electronic device 500 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 4 The electronic device 500 is shown with various devices, but it should be understood that it is not required to implement or possess all of the devices shown. More or fewer devices may be implemented or possessed instead.

[0089] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a non-transitory computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart, thereby realizing the emergency incident prevention and control scheduling method as described above. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 509, or installed from the storage device 508, or installed from the ROM 502. When the computer program is executed by the processing device 501, the above-mentioned functions defined in the method of the embodiment of the present disclosure are performed.

[0090] It should be noted that the computer-readable medium mentioned above in the present disclosure may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, a computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, device, or component. In the present disclosure, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof.

[0091] In some embodiments, the client and server can communicate using any currently known or future developed network protocol, such as HTTP (HyperText Transfer Protocol), and can be interconnected with any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network ("LAN"), a wide area network ("WAN"), an internet (e.g., the Internet), and a peer-to-peer network (e.g., an ad hoc peer-to-peer network), as well as any currently known or future developed network.

[0092] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0093] The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by the electronic device, the electronic device is enabled to: obtain the monitoring data stream of each traffic road in real time; input the monitoring data stream into the trained Bayesian network model to obtain the first probability of an accident occurring on the target section and at the target time, and the monitoring data stream includes the monitoring data of the target section; when the first probability reaches the warning threshold, the target section and the target time are warned, so as to carry out emergency event prevention and control scheduling for the target section at the target time; wherein, each node in the Bayesian network model and the initial value of the conditional probability of each node are determined based on the correspondence between the accident triggering conditions, accident triggering behaviors and accident results in historical accidents that have occurred obtained through the first random forest model.

[0094] Optionally, when the above one or more programs are executed by the electronic device, the electronic device may also execute other steps described in the above embodiments.

[0095] Computer program code for performing the operations of the present disclosure may be written in one or more programming languages, or a combination thereof, including, but not limited to, object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0096] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the module, program segment, or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of the boxes in the block diagram and / or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0097] The units involved in the embodiments described in this disclosure may be implemented in software or hardware, wherein the name of a unit does not necessarily limit the unit itself.

[0098] The functions described above herein may be performed, at least in part, by one or more hardware logic components. For example, and without limitation, exemplary types of hardware logic components that may be used include: field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chip (SOCs), complex programmable logic devices (CPLDs), and the like.

[0099] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0100] The above description is merely a preferred embodiment of the present disclosure and an illustration of the technical principles employed. Those skilled in the art should understand that the scope of disclosure involved in the present disclosure is not limited to the technical solutions formed by the specific combination of the above-mentioned technical features, but also includes other technical solutions formed by any combination of the above-mentioned technical features or their equivalents without departing from the above-mentioned disclosed concepts. For example, a technical solution formed by replacing the above-mentioned features with (but not limited to) technical features with similar functions disclosed in this disclosure.

[0101] In addition, although each operation is described in a specific order, this should not be understood as requiring these operations to be performed in the specific order shown or in a sequential order. Under certain circumstances, multitasking and parallel processing may be advantageous. Similarly, although some specific implementation details have been included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Some features described in the context of a separate embodiment can also be implemented in a single embodiment in combination. On the contrary, the various features described in the context of a single embodiment can also be implemented in multiple embodiments individually or in any suitable sub-combination mode.

[0102] Although the subject matter has been described in language specific to structural features and / or methodological logical acts, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or acts described above. Rather, the specific features and acts described above are merely example forms of implementing the claims.

Claims

1. A method for dispatching emergency incident prevention and control, characterized in that: The method comprises: Obtain monitoring data streams of each traffic road in real time; Inputting the monitoring data stream into a trained Bayesian network model to obtain a first probability of an accident occurring on a target road section and at a target time, wherein the monitoring data stream includes monitoring data of the target road section; When the first probability reaches a warning threshold, issuing a warning for the target road section and the target time, so as to carry out emergency prevention and control scheduling for the target road section at the target time; Each node in the Bayesian network model and the initial value of the conditional probability of each node are determined based on the corresponding relationship between accident triggering conditions, accident triggering behaviors and accident results in historical accidents that have occurred obtained by the first random forest model; The process of determining the initial value of the conditional probability of each node is as follows: According to the observation data set and the first random forest model, the correspondence between the accident triggering conditions, accident triggering behaviors and accident results in historical accidents that have occurred is obtained; based on the correspondence between the accident triggering conditions, accident triggering behaviors and accident results, a Bayesian network model with the highest fit to the observation data set is constructed; according to the observation data set, the conditional probability of each node of the Bayesian network model is evaluated to determine the initial value of the conditional probability of each node; wherein, the observation data set includes a training sample set and a test sample set.

2. The method according to claim 1, characterized in that Also includes: Determine a first training sample set and a first test sample set based on detailed record data of historical traffic accidents that have occurred; The first training sample set includes accident cause data partitions, the first random forest model is trained based on the first training sample set and tested based on the first test sample set, and the first random forest model is used to determine the correspondence between accident triggering conditions, accident triggering behaviors and accident results.

3. The method according to claim 1, characterized in that Also includes: Determine detailed record data of the first traffic accident that has occurred; Inputting the detailed record data of the first traffic accident into the trained patrol model to obtain a first target road section and a reference time where the accident rate is greater than a preset threshold; Sending the first target road section and reference time to an emergency incident prevention and control scheduling platform to perform emergency incident prevention and control scheduling based on the first target road section and reference time; The inspection model includes a second random forest model and a third random forest model; the second random forest model is trained based on the second training sample set and tested based on the second test sample set, and the third random forest model is trained based on the third training sample set and tested based on the third test sample set; The second training sample set includes spatial point data partitions, and the second random forest model is used to determine the corresponding relationship between spatial point locations and accident probability; The third training sample set includes time period data partitions, and the third random forest model is used to determine the corresponding relationship between time periods and accident probability; The second training sample set, the third training sample set, the second test sample set, and the third test sample set are determined based on detailed record data of historical traffic accidents that have occurred.

4. The method according to claim 3, characterized in that The first random forest model, the second random forest model, and the third random forest model each include a plurality of decision trees.

5. The method according to claim 4, characterized in that After sending the first target road section and reference time to the emergency incident prevention and control scheduling platform, the method further includes: According to the reference time, the first target road section is marked with multiple layers of points in the geographic information system and / or the digital twin intelligent operation center.

6. The method according to any one of claims 1 to 4, characterized in that Also includes: After determining the accident result corresponding to the monitoring data stream, training the Bayesian network model based on the corresponding relationship between the accident triggering condition, the accident triggering behavior and the accident result corresponding to the monitoring data stream; Each node condition in the Bayesian network model includes weather type and environment type.

7. The method according to any one of claims 1 to 4, characterized in that The step of providing an early warning for the target road section and the target time includes: The target road section and the target time are displayed in a geographic information system and / or a digital twin intelligent operation center associated with the emergency safety notification and warning platform.

8. An emergency event prevention and control dispatching device, characterized in that: include: Acquisition module, used to obtain the monitoring data stream of each traffic road in real time; a prediction module, configured to input the monitoring data stream into a trained Bayesian network model to obtain a first probability of an accident occurring on a target road section at a target time, wherein the monitoring data stream includes monitoring data of the target road section at the target time; an early warning module, configured to issue an early warning for the target road section and the target time when the first probability reaches an early warning threshold, so as to perform emergency prevention and control scheduling for the target road section at the target time; Each node in the Bayesian network model and the initial value of the conditional probability of each node are determined based on the corresponding relationship between accident triggering conditions, accident triggering behaviors and accident results in historical accidents that have occurred obtained by the first random forest model; The process of determining the initial value of the conditional probability of each node is as follows: According to the observation data set and the first random forest model, the correspondence between the accident triggering conditions, accident triggering behaviors and accident results in historical accidents that have occurred is obtained; based on the correspondence between the accident triggering conditions, accident triggering behaviors and accident results, a Bayesian network model with the highest fit to the observation data set is constructed; according to the observation data set, the conditional probability of each node of the Bayesian network model is evaluated to determine the initial value of the conditional probability of each node; wherein, the observation data set includes a training sample set and a test sample set.

9. An electronic device, characterized in that: The electronic device comprises: one or more processors; a storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

11. A computer program product comprising a computer program or instructions, characterized in that When the computer program or instruction is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images