Digital information transmission method and system for public safety

Abstract

The invention provides a digital information transmission method and system for public security, and relates to the field of digital information transmission, and the method comprises the steps: setting a plurality of public security sensing components in a target region according to historical public security information of the target region, and determining a basic priority value of each public security sensing component, setting a plurality of edge computing devices and a plurality of digital information transmission nodes in the target area; determining a dynamic priority value of each public safety sensing component according to the real-time weather information of the target area; the method comprises the steps of determining a public security risk value of each public security sensing component according to public security data collected by a plurality of public security sensing components through a plurality of edge computing devices, determining a digital information transmission path corresponding to the public security sensing component, and transmitting the public security data collected by the public security sensing components to a control center, the method has the advantages that the transmission flexibility of digital information of public safety is improved, and then the real-time performance of public safety early warning is improved.

Description

Technical Field

[0001] The present invention relates to the field of digital information transmission, and in particular to a digital information transmission method and system for public safety. Background Art

[0002] Public safety refers to the stable external environment and order required for society and individual citizens to carry out normal life, work, study, entertainment and communication. In the prior art, the public safety supervision system usually includes public safety sensing equipment (for example, fire detectors, sound sensors, video sensors, etc.), communication modules and control centers. The public safety sensing equipment is used to collect information in public areas, the communication module is used to realize information transmission between the public safety sensing equipment and the control center, and the control center is used to process the information collected by the public safety sensing equipment and issue public safety warnings.

[0003] The current public safety supervision system mainly relies on traditional communication modules for information transmission. Traditional communication modules lack intelligent scheduling and flow control mechanisms and cannot dynamically adjust data transmission strategies according to network conditions and data priorities. When faced with large-scale, high-density information collection and transmission needs, they may appear to be unable to cope with the needs. The limited flexibility of information transmission may lead to data transmission delays, losses or interruptions, which in turn affects the real-time and accuracy of public safety warnings.

[0004] Therefore, there is a need to provide a method and system for transmitting digital information for public safety, so as to improve the flexibility of the transmission of digital information for public safety, and thus improve the real-time performance of public safety warnings. Summary of the invention

[0005] The present invention provides a digital information transmission method for public safety, comprising: obtaining historical public safety information of a target area; according to the historical public safety information of the target area, setting a plurality of public safety perception components in the target area and determining a basic priority value of each of the public safety perception components, wherein the public safety perception components include a plurality of public safety perception devices; according to the device information of the plurality of public safety perception components and the basic priority value of each of the public safety perception components, setting a plurality of edge computing devices in the target area; according to the device information of the plurality of public safety perception components and the basic priority value of each of the public safety perception components, setting a plurality of digital information transmission nodes in the target area; obtaining the target area; According to the real-time meteorological information of the target area, the dynamic priority value of each of the public safety perception components is determined; according to the public safety data collected by the multiple public safety perception components, the public safety risk value of each of the public safety perception components is determined through the multiple edge computing devices; for each of the public safety perception components, according to the basic priority value, dynamic priority value and public safety risk value of each of the public safety perception components, the digital information transmission path corresponding to the public safety perception component is determined; according to the digital information transmission path corresponding to the public safety perception component, the public safety data collected by the public safety perception component is transmitted to the control center through the multiple digital information transmission nodes.

[0006] Furthermore, based on the historical public safety information of the target area, multiple public safety perception components are set in the target area and a basic priority value of each of the public safety perception components is determined, including: determining multiple key locations of the target area and a location risk value of each key location based on the historical public safety information of the target area; determining the public safety association value of any two key locations based on the historical public safety information of the target area; clustering the multiple key locations based on the public safety association values ​​and distances of any two key locations to determine multiple key location clusters, and determining multiple perception locations based on the multiple key location clusters; for each of the perception locations, calculating the basic priority value of the public safety perception component of the perception location based on the location risk value of each key location included in the key location cluster corresponding to the perception location and the public safety association values ​​of any two key locations.

[0007] Furthermore, according to the device information of the multiple public safety perception components and the basic priority value of each of the public safety perception components, multiple edge computing devices are set in the target area, including: for each of the public safety perception components, according to the device information of the public safety perception component, determining the computing power requirement corresponding to the public safety perception component; according to the computing power requirement corresponding to each of the public safety perception components, generating multiple edge computing deployment plans, wherein the edge computing deployment plans include the number of edge computing devices, the location of each edge computing device and the public safety perception component corresponding to each edge computing device; for each edge computing deployment plan, according to each According to the computing power demand corresponding to the public safety perception component corresponding to the edge computing device, the computing power load balancing value and computing power redundancy value of the edge computing deployment plan are determined; according to the location of each edge computing device, the multiple perception locations and the basic priority value of each of the public safety perception components, the computing power delay value of the edge computing deployment plan is determined; according to the computing power load balancing value, computing power redundancy value and computing power delay value of the edge computing deployment plan; according to the computing power load balancing value, computing power redundancy value and computing power delay value of each of the edge computing deployment plans, the target edge computing deployment plan is determined; according to the target edge computing deployment plan, multiple edge computing devices are set in the target area.

[0008] Furthermore, according to the device information of the multiple public safety perception components and the basic priority value of each of the public safety perception components, multiple digital information transmission nodes are set in the target area, including: determining the transmission requirements corresponding to the public safety perception components according to the device information of the public safety perception components; generating multiple transmission node layout schemes according to the transmission requirements corresponding to each of the public safety perception components, wherein the edge computing layout scheme includes the number of digital information transmission nodes and the location of each digital information transmission node; for each transmission node layout scheme, determining the digital information transmission path corresponding to each of the public safety perception components according to the basic priority value and transmission requirements of each of the public safety perception components, and determining the delay and node redundancy of the transmission node layout scheme according to the digital information transmission path corresponding to each of the public safety perception components; determining the target transmission node layout scheme according to the delay and node redundancy of each transmission node layout scheme; and setting multiple digital information transmission nodes in the target area according to the target transmission node layout scheme.

[0009] Furthermore, according to the basic priority value and transmission requirement of each of the public safety perception components, the digital information transmission path corresponding to each of the public safety perception components is determined, including: S11, sorting multiple public safety perception components according to the basic priority value of each of the public safety perception components to generate a first sorting result; S12, determining the current public safety perception component according to the first sorting result; S13, using the first path generation model, determining the digital information transmission path corresponding to the current public safety perception component according to the perception position of the current public safety perception component, the position of each digital information transmission node and the current transmission load; S14, updating the current transmission load of each digital information transmission node according to the digital information transmission path corresponding to the current public safety perception component; S15, judging whether the digital information transmission path corresponding to each public safety perception component is determined, and if so, recording the digital information transmission path corresponding to each of the public safety perception components; if not, executing S12.

[0010] Furthermore, based on the real-time meteorological information of the target area, the dynamic priority value of each of the public safety perception components is determined, including: determining key meteorological factors based on the historical public safety information of the target area and the historical meteorological information of the target area; generating a meteorological characteristic matrix of each of the perception locations based on the real-time meteorological information and key meteorological factors of the target area; for each of the public safety perception components, determining the dynamic priority value of the public safety perception component based on the meteorological characteristic matrix of the perception location where the public safety perception component is located.

[0011] Furthermore, the multiple edge computing devices determine the public safety risk value of each of the public safety perception components based on the public safety data collected by the multiple public safety perception components, including: deploying a risk prediction model on the edge computing device; the edge computing device determines the public safety risk value of the public safety perception component based on the public safety data collected by the public safety perception component through the risk prediction model.

[0012] Further, the method also includes: performing intrusion simulation on the multiple digital information transmission nodes to obtain intrusion simulation data; determining the intrusion association value of any two digital information transmission nodes according to the intrusion simulation data; determining the digital information transmission path corresponding to the public safety perception component according to the basic priority value, dynamic priority value and public safety risk value of each public safety perception component, including: S21, obtaining the status data of each public safety perception component, and determining the intrusion risk value of the public safety perception component according to the status data of each public safety perception component; S22, sorting the multiple public safety perception components according to the basic priority value, dynamic priority value and public safety risk value of each public safety perception component to generate a second sorting result; S23, determining the current public safety perception component according to the second sorting result;

[0013] S24. Generate a model through the second path to determine the digital information transmission path corresponding to the current public safety perception component according to the perception position of the current public safety perception component, the position of each digital information transmission node, the current transmission load and intrusion risk value, and the intrusion association value of any two digital information transmission nodes; S25. Update the current transmission load of each digital information transmission node according to the digital information transmission path corresponding to the current public safety perception component; S26. Determine whether the digital information transmission path corresponding to each public safety perception component is determined. If so, record the digital information transmission path corresponding to each of the public safety perception components. If not, execute S23.

[0014] Furthermore, the second path generation model is a deep Q network model, and the reward function of the second path generation model is related to the transmission distance between any two digital information transmission nodes, the current transmission load and intrusion risk value of each digital information transmission node, and the intrusion association value of any two digital information transmission nodes.

[0015] The present invention provides a digital information transmission system for public safety, which is used to execute the above-mentioned digital information transmission method for public safety, including: an architecture optimization module, which is used to obtain historical public safety information of a target area, and according to the historical public safety information of the target area, multiple public safety perception components are set in the target area and a basic priority value of each of the public safety perception components is determined, wherein the public safety perception components include multiple public safety perception devices, and according to the device information of the multiple public safety perception components and the basic priority value of each of the public safety perception components, multiple edge computing devices and multiple digital information transmission nodes are set in the target area; a transmission optimization module, which is used to obtain real-time meteorological information of the target area According to the real-time meteorological information of the target area, the dynamic priority value of each of the public safety perception components is determined; according to the public safety data collected by the multiple public safety perception components, the public safety risk value of each of the public safety perception components is determined through the multiple edge computing devices; for each of the public safety perception components, the digital information transmission path corresponding to the public safety perception component is determined according to the basic priority value, dynamic priority value and public safety risk value of each public safety perception component; an information transmission module is used to transmit the public safety data collected by the public safety perception components to the control center through the multiple digital information transmission nodes according to the digital information transmission path corresponding to the public safety perception components.

[0016] Compared with the prior art, the digital information transmission method and system for public safety provided by the present invention have at least the following beneficial effects:

[0017] 1. By obtaining real-time meteorological information in the target area, the priority value of the public safety perception component can be dynamically adjusted to more accurately reflect the public safety risks in the current environment. The edge computing device can process the data collected by the public safety perception component nearby, reduce data transmission delays, and improve the real-time performance of data processing. Through the preliminary analysis and processing of the edge computing device, important public safety data can be screened out to further improve the accuracy of the data. The digital information transmission path is dynamically determined based on the basic priority value, dynamic priority value, and public safety risk value of the public safety perception component. This dynamic adjustment method can ensure that when a public safety incident occurs, the data can be transmitted to the control center in the fastest and safest way. By setting up multiple edge computing devices and digital information transmission nodes and reasonably allocating them according to the device information and priority value of the public safety perception component, the effective use of resources can be ensured. This allocation method can avoid waste and bottlenecks of resources and improve the operating efficiency of the entire system. Through real-time and accurate public safety data transmission and dynamically adjusted transmission paths, the control center can quickly obtain information about public safety incidents. This helps the control center make decisions and respond quickly, reducing the impact and losses of public safety incidents.

[0018] 2. By analyzing the historical public safety information of the target area, multiple key locations can be accurately identified and a location risk value can be assigned to each key location. This helps to focus limited monitoring resources on high-risk areas and improve the targeted nature of monitoring. The introduction of public safety association values ​​to measure the correlation between any two key locations helps to understand the spread and mutual influence of public safety events between different locations, and provides more information for the optimization of digital information transmission. The perception locations are determined based on the key location clusters, and the public safety perception components of each perception location are assigned a basic priority value. This helps to ensure that monitoring data in high-risk areas can be prioritized when public safety incidents occur.

[0019] 3. Determine the computing power requirements of the public safety perception component based on its device information, thereby generating a variety of edge computing deployment plans. This helps ensure that each public safety perception component can obtain sufficient computing power support to avoid waste or insufficient computing power. By evaluating the computing power load balancing value and computing power redundancy value of each edge computing deployment plan, the optimal deployment plan can be selected. This helps ensure that edge computing devices can maintain stable operation when facing high loads and provide sufficient computing power redundancy to cope with emergencies. Including computing power delay values ​​in the evaluation range helps ensure that data can be transmitted from public safety perception components to edge computing devices for processing in the fastest way. This helps to improve the real-time and accuracy of data processing.

[0020] 4. Generate multiple transmission node layout schemes based on the transmission requirements of the public safety perception components. This helps ensure that each public safety perception component can transmit data to the control center through the optimal transmission path. By evaluating the latency and node redundancy of each transmission node layout scheme, the optimal layout scheme can be selected. This helps ensure the stability and reliability of data during transmission and reduce data loss or delay caused by node failure.

[0021] 5. By integrating real-time meteorological information, the priority value of the public safety perception component can be dynamically adjusted to more accurately reflect the public safety risks in the current environment. This helps the control center make decisions and respond quickly. Deploying risk prediction models on edge computing devices can determine the public safety risk value in real time based on the data collected by the public safety perception component. This helps the control center make quick and accurate decisions and responses when facing public safety incidents. By performing intrusion simulations and determining the intrusion correlation value of any two digital information transmission nodes, the selection of digital information transmission paths can be further optimized. This helps ensure the security of data during transmission and reduce data leakage or damage caused by intrusions.

[0022] 6. Dynamically select the digital information transmission path corresponding to each public safety perception component through the path generation model, and update the load of each digital information transmission node according to the current transmission load. This helps ensure that data can be transmitted to the control center in the most efficient way and avoid bottlenecks and congestion during the transmission process. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] This specification will be further described in the form of exemplary embodiments, which will be described in detail by the accompanying drawings. These embodiments are not restrictive, and in these embodiments, the same number represents the same structure, wherein:

[0024] Figure 1 is a flowchart of a method for transmitting digital information for public safety according to some embodiments of this specification;

[0025] Figure 2 It is a flowchart of a digital information transmission path corresponding to a public safety perception component according to some embodiments of this specification;

[0026] Figure 3 It is a module diagram of a digital information transmission system for public safety according to some embodiments of this specification. DETAILED DESCRIPTION

[0027] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following is a brief introduction to the drawings required for the description of the embodiments. Obviously, the drawings described below are only some examples or embodiments of this specification. For ordinary technicians in this field, this specification can also be applied to other similar scenarios based on these drawings without creative work. Unless it is obvious from the language environment or otherwise explained, the same reference numerals in the figures represent the same structure or operation.

[0028] Figure 1 is a flow chart of a method for transmitting digital information for public safety according to some embodiments of this specification, such as Figure 1 As shown, the digital information transmission method for public safety may include the following steps.

[0029] Step 110, obtaining historical public safety information of the target area.

[0030] Specifically, historical public safety information records detailed information on public safety incidents that occurred in the target area in the past, including the type of public safety incident, time of occurrence, location, etc.

[0031] Step 120, according to the historical public safety information of the target area, multiple public safety perception components are set in the target area and a basic priority value of each public safety perception component is determined.

[0032] The public safety sensing component includes a plurality of public safety sensing devices, for example, the plurality of public safety sensing devices may include at least a fire detector, a camera, a wall vibration sensor, a gas leak detector, an air quality monitor, a water quality monitor, and the like.

[0033] In some embodiments, step 120 specifically includes:

[0034] Determine multiple key locations of the target area and a location risk value of each key location based on historical public safety information of the target area, wherein the key location may be a location in the target area where the number of public safety incidents occurring is greater than a number threshold;

[0035] Determine the public safety association value of any two key locations based on the historical public safety information of the target area;

[0036] Clustering multiple key locations according to the public safety association values ​​and distances between any two key locations to determine multiple key location clusters, and determining multiple sensing locations based on the multiple key location clusters;

[0037] For each sensed location, a basic priority value of the public safety sensed component of the sensed location is calculated according to the location risk value of each key location included in the key location cluster corresponding to the sensed location and the public safety association values ​​of any two key locations.

[0038] Specifically, different identifiers are set for different types of public safety incidents. For example, a fire safety accident is identified as "1", a chemical leakage safety accident is identified as "2", and a fire safety accident that does not occur is identified as "0".

[0039] The public safety association value of two key locations can be calculated according to the following formula:

[0040]

[0041] Among them, V (i,j) is the public safety association value of the i-th key position and the j-th key position, I (i,n) is the type of public safety event that occurred at the i-th key location at the n-th historical time point, I (j,n) is the type of public safety event that occurred at the jth key location at the nth historical time point, and N is the total number of sampled historical time points.

[0042] The multiple key positions may be clustered by a K-means clustering algorithm to determine multiple key position clusters, wherein the distance between any two key positions included in the key position cluster is less than a distance threshold, and the public safety association value is greater than a public safety association value threshold.

[0043] For each key position cluster, the coordinates of the multiple key positions included in the key position cluster may be averaged to serve as the perception position corresponding to the key position cluster.

[0044] The basic priority value of the public safety perception component can be calculated according to the following formula:

[0045]

[0046] Among them, P (i,basic) is the basic priority value of the ith public safety perception component, P (0,basic) is the preset basic priority value, E is the total number of key locations included in the key location cluster corresponding to the i-th public safety perception component, V (e,f) The key position cluster corresponding to the ith public safety perception component includes the public safety association values ​​of the eth key position and the fth key position.

[0047] Step 130, setting multiple edge computing devices in the target area according to the device information of multiple public safety perception components and the basic priority value of each public safety perception component.

[0048] In some embodiments, step 130 specifically includes:

[0049] For each public safety perception component, determine the computing power requirement corresponding to the public safety perception component based on the device information of the public safety perception component;

[0050] Generate multiple edge computing deployment plans based on the computing power requirements corresponding to each public safety perception component, where the edge computing deployment plan includes the number of edge computing devices, the location of each edge computing device, and the public safety perception component corresponding to each edge computing device;

[0051] For each edge computing deployment plan, determine the computing power load balancing value and computing power redundancy value of the edge computing deployment plan according to the computing power requirements corresponding to the public safety perception components corresponding to each edge computing device, determine the computing power delay value of the edge computing deployment plan according to the location of each edge computing device, multiple perception locations and the basic priority value of each public safety perception component, and determine the computing power load balancing value, computing power redundancy value and computing power delay value of the edge computing deployment plan;

[0052] Determine the target edge computing deployment plan according to the computing power load balancing value, computing power redundancy value and computing power delay value of each edge computing deployment plan;

[0053] According to the target edge computing deployment plan, multiple edge computing devices are set up in the target area.

[0054] Specifically, the computing power demand prediction model can be used to determine the computing power demand corresponding to the public safety perception component based on the device information of the public safety perception component (for example, device type, data acquisition parameters (for example, sampling frequency, image resolution, etc.), etc.), where the computing power demand prediction model can be a convolutional neural network model. A variety of edge computing deployment plans can be generated based on multiple perception locations and the computing power demand corresponding to each public safety perception component through machine learning models (for example, decision trees and random forests, etc.).

[0055] The computing power load balancing value of the deployment plan can be calculated according to the following formula:

[0056]

[0057] Among them, Balance i is the computing load balancing value of the i-th computing deployment scheme, P 1 is the preset parameter, P 1 Greater than 0, Load e is the computing power load of the e-th edge computing device under the i-th computing deployment scheme, Load fis the computing power load of the fth edge computing device under the i-th computing deployment scheme, and E is the total number of edge computing devices.

[0058] The computing power redundancy value of the deployment plan can be calculated according to the following formula:

[0059]

[0060] Among them, Redundancy i is the computing power redundancy value of the i-th computing layout scheme, Load (e,Presets) is the preset computing load of the e-th edge computing device under the i-th computing deployment scheme, P 2 is the preset parameter, P 2 Greater than 0.

[0061] The computing power delay value of the layout scheme can be calculated according to the following formula:

[0062]

[0063] Among them, Delay i is the computing power delay value of the i-th computing layout solution, P 3 is the preset parameter, P 3 Greater than 0, P (k,basic) is the basic priority value of the kth public safety perception component, Distance k is the data transmission distance between the kth public safety perception component and the corresponding edge computing device under the i-th computing deployment scheme, and K is the total number of public safety perception components.

[0064] As an example only, for each edge computing deployment plan, the computing power load balancing value, computing power redundancy value and computing power delay value of the edge computing deployment plan can be weighted and summed to determine the comprehensive priority value of the edge computing deployment plan, and the edge computing deployment plan with the largest comprehensive priority value can be used as the target edge computing deployment plan.

[0065] As another example, a target edge computing deployment plan can be generated according to a plurality of edge computing deployment plans and the computing power delay value of each edge computing deployment plan through a first solution optimization model, wherein the first solution optimization model can be a convolutional neural network model.

[0066] Step 140, setting a plurality of digital information transmission nodes in the target area according to the device information of the plurality of public safety perception components and the basic priority value of each public safety perception component.

[0067] In some embodiments, step 140 specifically includes:

[0068] Determine, according to the device information of the public safety perception component, a transmission requirement (e.g., a bandwidth requirement) corresponding to the public safety perception component;

[0069] Generate multiple transmission node deployment plans based on the transmission requirements of each public safety perception component, where the edge computing deployment plan includes the number of digital information transmission nodes and the location of each digital information transmission node;

[0070] For each transmission node deployment scheme, determine the digital information transmission path corresponding to each public safety perception component according to the basic priority value and transmission requirements of each public safety perception component, and determine the delay and node redundancy of the transmission node deployment scheme according to the digital information transmission path corresponding to each public safety perception component;

[0071] Determine the target transmission node deployment plan based on the delay and node redundancy of each transmission node deployment plan;

[0072] According to the target transmission node deployment plan, multiple digital information transmission nodes are set up in the target area.

[0073] Specifically, the transmission demand corresponding to the public safety perception component can be determined according to the device information of the public safety perception component through a transmission demand prediction model, wherein the transmission demand prediction model can be a convolutional neural network model.

[0074] Through machine learning models (for example, decision trees and random forests), multiple transmission node deployment plans can be generated based on multiple sensing locations, the installation locations of multiple edge computing devices, and the corresponding transmission requirements of each public safety sensing component.

[0075] In some embodiments, determining a digital information transmission path corresponding to each public safety awareness component according to a basic priority value and a transmission requirement of each public safety awareness component includes:

[0076] S11. Sort the multiple public safety perception components according to the basic priority value of each public safety perception component to generate a first sorting result. Specifically, the multiple public safety perception components may be sorted from large to small according to the basic priority value;

[0077] S12. Determine a current public safety perception component according to the first ranking result, wherein the current public safety perception component may be a public safety perception component ranked highest among the public safety perception components for which corresponding digital information transmission paths have not been determined;

[0078] S13, determining the digital information transmission path corresponding to the current public safety perception component according to the perception position of the current public safety perception component, the position of each digital information transmission node and the current transmission load through the first path generation model, wherein the first path generation model may be a reinforcement learning model;

[0079] S14. Update the current transmission load of each digital information transmission node according to the digital information transmission path corresponding to the current public safety perception component;

[0080] S15. Determine whether the digital information transmission path corresponding to each public safety perception component is determined. If so, record the digital information transmission path corresponding to each public safety perception component. If not, execute S12.

[0081] Specifically, reinforcement learning learns how to take actions to maximize a certain reward signal by interacting with the environment. In reinforcement learning, the agent takes actions in the environment and learns how to better complete tasks based on the rewards obtained from these actions. This learning method is based on trial and error, and the agent gradually finds the optimal strategy by constantly trying and correcting its behavior.

[0082] The reward function of the first path generation model is:

[0083] R(s,a,s′)=α 11 ×exp(-λ 11 ×Distance (s,s′) )+α 12 ×exp(-λ 12 ×Load s′ )

[0084] Among them, R(s,a,s′) is the comprehensive reward obtained when transferring to the next state s′ after taking action a in the current state s, exp() is the exponential function, and Distance (s,s′) is the transmission distance between the digital information transmission node corresponding to the current state s and the digital information transmission node corresponding to the next state s′, Load s′ is the current transmission load of the digital information transmission node corresponding to the next state s′, α 11 , α 12 is the weight coefficient, α 11 , α 12 Greater than 0, α 11 +α 12 =1,λ 11 and λ1 2 is the second attenuation coefficient, λ 11 and λ1 2 Greater than 0.

[0085] The method of calculating the delay and node redundancy of the transmission node deployment plan is similar to the method of calculating the computing power redundancy value and computing power delay value of the deployment plan, and will not be repeated here.

[0086] As an example only, for each transmission node deployment scheme, the delay and node redundancy of the transmission node deployment scheme can be weighted and summed to determine the comprehensive priority value of the transmission node deployment scheme, and the transmission node deployment scheme with the largest comprehensive priority value can be used as the target transmission node deployment scheme.

[0087] As another example, a target transmission node deployment scheme can be generated through a second scheme optimization model according to multiple transmission node deployment schemes and the delay and node redundancy of each transmission node deployment scheme, wherein the second scheme optimization model can be a convolutional neural network model.

[0088] Step 150, obtaining real-time weather information of the target area, and determining the dynamic priority value of each public safety perception component based on the real-time weather information of the target area.

[0089] In some embodiments, step 150 specifically includes:

[0090] Determine key meteorological factors (e.g., temperature, humidity, wind speed, rainfall, etc.) based on historical public safety information of the target area and historical meteorological information of the target area;

[0091] Generate a meteorological feature matrix of each sensing location according to the real-time meteorological information and key meteorological factors of the target area, wherein a row vector of the meteorological feature matrix includes a characteristic value of a key meteorological factor, for example, a row vector of the meteorological feature matrix includes a minimum value and a maximum value of a wind speed;

[0092] For each public safety perception component, a dynamic priority value of the public safety perception component is determined according to a meteorological characteristic matrix of a perception location where the public safety perception component is located.

[0093] Specifically, statistical methods such as correlation analysis and regression analysis can be used to determine the correlation between public safety events and meteorological factors. The correlation coefficient or regression coefficient can be calculated to determine which meteorological factors have a significant correlation with public safety events, and then the key meteorological factors can be determined based on the significant correlation between meteorological factors and public safety events.

[0094] The meteorological feature matrix of each sensing location can be generated according to the real-time meteorological information of the target area through an interpolation algorithm (for example, inverse distance weighted interpolation, Kriging interpolation, radial basis function interpolation, natural neighbor interpolation, etc.).

[0095] As an example only, the dynamic priority value of the public safety perception component can be determined by a dynamic prediction model based on the meteorological feature matrix of the perception location where the public safety perception component is located, where the dynamic prediction model can be a convolutional neural network model.

[0096] As another example, a standard meteorological characteristic matrix may be determined, and under the meteorological environment corresponding to the standard meteorological characteristic matrix, the probability of a public safety incident occurring is low.

[0097] The dynamic priority value of the public safety awareness component can be determined according to the following formula:

[0098]

[0099] Among them, P (i,dynamics) is the dynamic priority value of the ith public safety perception component, P (0,dynamics) is the preset dynamic priority value, P 4 is the preset parameter, P 4 Greater than 0, M i is the meteorological feature matrix of the sensing location where the ith public safety sensing component is located, M standard is the standard meteorological characteristic matrix, cos(M i ,M standard ) is the cosine similarity between the meteorological feature matrix of the sensing location where the ith public safety sensing component is located and the standard meteorological feature matrix.

[0100] Step 160, determine the public safety risk value of each public safety perception component through multiple edge computing devices based on the public safety data collected by multiple public safety perception components.

[0101] In some embodiments, step 160 specifically includes:

[0102] Deploy risk prediction models on edge computing devices;

[0103] The edge computing device determines the public safety risk value of the public safety perception component based on the public safety data collected by the public safety perception component through a risk prediction model.

[0104] Specifically, the risk prediction model may include multiple risk prediction sub-models, which are used to predict the probability of public safety accidents based on public safety data collected by at least one public safety sensing device. For example, multiple risk prediction sub-models may include a fire risk prediction sub-model, and the data sources include: fire detectors, cameras, wall vibration sensors, etc. By analyzing the smoke concentration, temperature and other parameters detected by the fire detectors, as well as the flame images captured by the cameras and the vibration signals detected by the wall vibration sensors, a fire risk prediction model is established using machine learning or deep learning algorithms. The model can evaluate the probability of fire in real time and issue an early warning.

[0105] Multiple risk prediction sub-models may include a gas leakage risk prediction sub-model, and the data sources include gas leakage detectors, air quality monitors, etc. Prediction principle: By analyzing the gas concentration data detected by the gas leakage detector and the air quality information provided by the air quality monitor, a gas leakage risk prediction model is established using statistical analysis and machine learning algorithms. The model can identify abnormal gas concentration changes and predict the possibility of gas leakage events.

[0106] Multiple risk prediction sub-models can include a water quality safety risk prediction sub-model, and the data source is: water quality monitoring instrument, etc. Prediction principle: By analyzing the water quality parameters (such as pH value, dissolved oxygen, turbidity, heavy metal content, etc.) detected by the water quality monitoring instrument, a water quality safety risk prediction model is established using a machine learning algorithm. The model can identify abnormal changes in water quality parameters and predict the probability of water quality safety risks.

[0107] The maximum value of the probabilities output by multiple risk prediction sub-models can be taken as the public safety risk value.

[0108] Step 170, for each public safety perception component, determine the digital information transmission path corresponding to the public safety perception component according to the basic priority value, dynamic priority value and public safety risk value of each public safety perception component.

[0109] In some embodiments, the method further comprises:

[0110] Performing intrusion simulation on multiple digital information transmission nodes to obtain intrusion simulation data, wherein the intrusion simulation data may include network traffic of each digital information transmission node at multiple simulated intrusion time points under multiple simulated intrusion scenarios, and there are differences in attack type, attack intensity, attack frequency and attack time under different simulated intrusion scenarios;

[0111] According to the intrusion simulation data, the intrusion correlation value of any two digital information transmission nodes is determined.

[0112] Specifically, the intrusion correlation value of two digital information transmission nodes can be calculated according to the following formula:

[0113]

[0114] Among them, C (i,j) is the intrusion correlation value between the i-th digital information transmission node and the j-th digital information transmission node, C ((i,j),m) is the intrusion correlation value of the i-th digital information transmission node and the j-th digital information transmission node in the m-th simulated intrusion scenario, M is the total number of simulated intrusion scenarios, T (i,n) is the network traffic of the ith digital information transmission node at the nth simulated intrusion time point in the mth simulated intrusion scenario, T (j,n) is the network traffic of the jth digital information transmission node at the nth simulated intrusion time point in the mth simulated intrusion scenario, and N is the total number of simulated intrusion time points sampled in the mth simulated intrusion scenario.

[0115] Figure 2 is a flow chart of a digital information transmission path corresponding to a public safety perception component according to some embodiments of this specification, such as Figure 2 As shown, in some embodiments, step 170 specifically includes:

[0116] S21, obtaining the status data of each public safety perception component, and determining the intrusion risk value of the public safety perception component according to the status data of each public safety perception component (for example, network traffic, CPU, memory, disk and other resource occupancy), for example, the intrusion risk value of the public safety perception component can be determined according to the status data of the public safety perception component through an intrusion risk prediction model, and the intrusion risk prediction model can be a long short-term memory network model;

[0117] S22. Sort multiple public safety perception components according to the basic priority value, dynamic priority value and public safety risk value of each public safety perception component to generate a second sorting result. For example, for each public safety perception component, the comprehensive priority value of the public safety perception component can be calculated according to the basic priority value, dynamic priority value and public safety risk value of the public safety perception component, and the multiple public safety perception components are sorted from large to small according to the comprehensive priority value to generate a second sorting result.

[0118] S23. Determine a current public safety perception component according to the second sorting result, wherein the current public safety perception component may be a public safety perception component that is ranked highest among the public safety perception components for which corresponding digital information transmission paths have not been determined;

[0119] S24, determining the digital information transmission path corresponding to the current public safety perception component through the second path generation model according to the perception position of the current public safety perception component, the position of each digital information transmission node, the current transmission load and the intrusion risk value, and the intrusion association value of any two digital information transmission nodes;

[0120] S25. Update the current transmission load of each digital information transmission node according to the digital information transmission path corresponding to the current public safety perception component;

[0121] S26. Determine whether the digital information transmission path corresponding to each public safety perception component is determined. If so, record the digital information transmission path corresponding to each public safety perception component. If not, execute S23.

[0122] In some embodiments, the second path generation model is a deep Q network model, and the reward function of the second path generation model is related to the transmission distance between any two digital information transmission nodes, the current transmission load and intrusion risk value of each digital information transmission node, and the intrusion association value of any two digital information transmission nodes.

[0123] Specifically, the reward function of the second path generation model can be:

[0124]

[0125] Among them, R(s,a,s′) is the comprehensive reward obtained when transferring to the next state s′ after taking action a in the current state s, exp() is the exponential function, and Distance (s,s′) is the transmission distance between the digital information transmission node corresponding to the current state s and the digital information transmission node corresponding to the next state s′, Load s′ is the current transmission load of the digital information transmission node corresponding to the next state s′, R s is the intrusion risk value of the digital information transmission node corresponding to the current state s, R s′ is the intrusion risk value of the digital information transmission node corresponding to the next state s′, C (s,s′) is the intrusion correlation value between the digital information transmission node corresponding to the current state s and the digital information transmission node corresponding to the next state s′, b 11 、b 12 、b 13 is the weight coefficient, b 11 、b 12 、b 13 Greater than 0, b 11 +b 12 +b 13 =1,λ 21 , 22 and23 is the second attenuation coefficient, λ 21 , 22 and 23 Greater than 0.

[0126] Step 180, transmits the public safety data collected by the public safety perception component to the control center through multiple digital information transmission nodes according to the digital information transmission path corresponding to the public safety perception component.

[0127] Figure 3 is a schematic diagram of a module of a digital information transmission system for public safety according to some embodiments of this specification, such as Figure 3 As shown, the digital information transmission system for public safety may include an architecture optimization module, a transmission optimization module and an information transmission module.

[0128] The architecture optimization module can be used to obtain historical public safety information of the target area, set up multiple public safety perception components in the target area and determine the basic priority value of each public safety perception component based on the historical public safety information of the target area, wherein the public safety perception component includes multiple public safety perception devices, and set up multiple edge computing devices and multiple digital information transmission nodes in the target area based on the device information of the multiple public safety perception components and the basic priority value of each public safety perception component.

[0129] The transmission optimization module can be used to obtain real-time meteorological information of the target area, determine the dynamic priority value of each public safety perception component based on the real-time meteorological information of the target area, and determine the public safety risk value of each public safety perception component based on the public safety data collected by multiple public safety perception components through multiple edge computing devices. For each public safety perception component, the digital information transmission path corresponding to the public safety perception component is determined based on the basic priority value, dynamic priority value and public safety risk value of each public safety perception component.

[0130] The information transmission module can be used to transmit the public safety data collected by the public safety perception component to the control center through multiple digital information transmission nodes according to the digital information transmission path corresponding to the public safety perception component.

[0131] The digital information transmission system for public safety can be used to execute the digital information transmission method for public safety. For more descriptions of the digital information transmission system for public safety, please refer to the relevant descriptions of the digital information transmission method for public safety, which will not be repeated here.

[0132] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, as an example and not a limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly introduced and described in this specification.

Claims

1. A method for transmitting digital information for public safety, characterized in that: include: Obtain historical public safety information for the target area; According to the historical public safety information of the target area, a plurality of public safety perception components are arranged in the target area and a basic priority value of each of the public safety perception components is determined, wherein the public safety perception components include a plurality of public safety perception devices; According to the device information of the plurality of public safety sensing components and the basic priority value of each of the public safety sensing components, setting a plurality of edge computing devices in the target area; According to the device information of the plurality of public safety sensing components and the basic priority value of each of the public safety sensing components, setting a plurality of digital information transmission nodes in the target area; Acquire real-time meteorological information of the target area, and determine a dynamic priority value of each of the public safety perception components according to the real-time meteorological information of the target area; Determine, by the multiple edge computing devices, a public safety risk value of each of the public safety perception components based on the public safety data collected by the multiple public safety perception components; For each of the public safety perception components, determining a digital information transmission path corresponding to the public safety perception component according to the basic priority value, dynamic priority value and public safety risk value of each of the public safety perception components; The public safety data collected by the public safety perception component is transmitted to the control center through the multiple digital information transmission nodes according to the digital information transmission path corresponding to the public safety perception component.

2. The method for transmitting digital information for public safety according to claim 1, characterized in that: According to the historical public safety information of the target area, a plurality of public safety perception components are set in the target area and a basic priority value of each of the public safety perception components is determined, including: Determining a plurality of key locations of the target area and a location risk value of each key location according to historical public safety information of the target area; Determining the public safety association value of any two key locations based on the historical public safety information of the target area; Clustering the plurality of key locations according to the public safety association values ​​and distances between any two key locations to determine a plurality of key location clusters, and determining a plurality of sensing locations according to the plurality of key location clusters; For each of the sensed locations, a basic priority value of the public safety sensing component of the sensed location is calculated according to the location risk value of each key location included in the key location cluster corresponding to the sensed location and the public safety association values ​​of any two key locations.

3. The method for transmitting digital information for public safety according to claim 2, characterized in that: According to the device information of the plurality of public safety perception components and the basic priority value of each of the public safety perception components, a plurality of edge computing devices are arranged in the target area, including: For each of the public safety perception components, determining the computing power requirement corresponding to the public safety perception component according to the device information of the public safety perception component; Generate multiple edge computing deployment plans according to the computing power requirements corresponding to each of the public safety perception components, wherein the edge computing deployment plans include the number of edge computing devices, the location of each edge computing device, and the public safety perception component corresponding to each edge computing device; For each edge computing deployment scheme, determine the computing power load balancing value and computing power redundancy value of the edge computing deployment scheme according to the computing power demand corresponding to the public safety perception component corresponding to each edge computing device, determine the computing power delay value of the edge computing deployment scheme according to the location of each edge computing device, the multiple perception locations and the basic priority value of each public safety perception component, and determine the computing power load balancing value, computing power redundancy value and computing power delay value of the edge computing deployment scheme according to the computing power load balancing value, computing power redundancy value and computing power delay value of the edge computing deployment scheme; Determine a target edge computing deployment plan according to a computing power load balancing value, a computing power redundancy value, and a computing power delay value of each edge computing deployment plan; According to the target edge computing deployment plan, multiple edge computing devices are set in the target area.

4. The method for transmitting digital information for public safety according to claim 3, characterized in that: According to the device information of the plurality of public safety perception components and the basic priority value of each of the public safety perception components, a plurality of digital information transmission nodes are set in the target area, including: Determining, according to the device information of the public safety awareness component, a transmission requirement corresponding to the public safety awareness component; Generate multiple transmission node deployment schemes according to the transmission requirements corresponding to each of the public safety perception components, wherein the edge computing deployment scheme includes the number of digital information transmission nodes and the location of each digital information transmission node; For each transmission node deployment scheme, according to the basic priority value and transmission requirements of each public safety perception component, determine the digital information transmission path corresponding to each public safety perception component, and according to the digital information transmission path corresponding to each public safety perception component, determine the delay and node redundancy of the transmission node deployment scheme; Determine the target transmission node deployment plan based on the delay and node redundancy of each transmission node deployment plan; According to the target transmission node deployment plan, a plurality of digital information transmission nodes are arranged in the target area.

5. The method for transmitting digital information for public safety according to claim 4, characterized in that: Determining a digital information transmission path corresponding to each of the public safety perception components according to the basic priority value and transmission requirements of each of the public safety perception components includes: S11. Sort the multiple public safety perception components according to the basic priority value of each of the public safety perception components to generate a first sorting result; S12. Determine a current public safety perception component according to the first sorting result; S13, determining the digital information transmission path corresponding to the current public safety perception component through the first path generation model according to the perception position of the current public safety perception component, the position of each digital information transmission node and the current transmission load; S14. Update the current transmission load of each digital information transmission node according to the digital information transmission path corresponding to the current public safety perception component; S15. Determine whether the digital information transmission path corresponding to each public safety perception component is determined. If so, record the digital information transmission path corresponding to each public safety perception component. If not, execute S12.

6. The method for transmitting digital information for public safety according to any one of claims 1 to 5, characterized in that: Determining the dynamic priority value of each of the public safety perception components according to the real-time meteorological information of the target area includes: Determining key meteorological factors based on historical public safety information of the target area and historical meteorological information of the target area; Generating a meteorological feature matrix of each of the sensing locations according to the real-time meteorological information and key meteorological factors of the target area; For each of the public safety perception components, a dynamic priority value of the public safety perception component is determined according to a meteorological characteristic matrix of a perception location where the public safety perception component is located.

7. The method for transmitting digital information for public safety according to any one of claims 1 to 5, characterized in that: The multiple edge computing devices determine the public safety risk value of each of the public safety perception components according to the public safety data collected by the multiple public safety perception components, including: deploying a risk prediction model on the edge computing device; The edge computing device determines the public safety risk value of the public safety perception component through the risk prediction model according to the public safety data collected by the public safety perception component.

8. The method for transmitting digital information for public safety according to claim 5, characterized in that: Also includes: Performing intrusion simulation on the multiple digital information transmission nodes to obtain intrusion simulation data; Determine the intrusion correlation value of any two digital information transmission nodes according to the intrusion simulation data; Determining a digital information transmission path corresponding to each of the public safety perception components according to the basic priority value, the dynamic priority value, and the public safety risk value of each of the public safety perception components includes: S21, obtaining status data of each of the public safety perception components, and determining the intrusion risk value of the public safety perception component according to the status data of each of the public safety perception components; S22, sorting the multiple public safety perception components according to the basic priority value, dynamic priority value and public safety risk value of each of the public safety perception components to generate a second sorting result; S23. Determine the current public safety perception component according to the second sorting result; S24, determining the digital information transmission path corresponding to the current public safety perception component through the second path generation model according to the perception position of the current public safety perception component, the position of each digital information transmission node, the current transmission load and the intrusion risk value, and the intrusion association value of any two digital information transmission nodes; S25. Update the current transmission load of each digital information transmission node according to the digital information transmission path corresponding to the current public safety perception component; S26. Determine whether the digital information transmission path corresponding to each public safety perception component is determined. If so, record the digital information transmission path corresponding to each public safety perception component. If not, execute S23.

9. The method for transmitting digital information for public safety according to claim 8, characterized in that: The second path generation model is a deep Q network model, and the reward function of the second path generation model is related to the transmission distance between any two digital information transmission nodes, the current transmission load and intrusion risk value of each digital information transmission node, and the intrusion association value of any two digital information transmission nodes.

10. A digital information transmission system for public safety, characterized in that: A method for transmitting digital information for public safety according to any one of claims 1 to 9, comprising: An architecture optimization module, configured to obtain historical public safety information of a target area, and according to the historical public safety information of the target area, to set a plurality of public safety perception components in the target area and determine a basic priority value of each of the public safety perception components, wherein the public safety perception components include a plurality of public safety perception devices, and according to the device information of the plurality of public safety perception components and the basic priority value of each of the public safety perception components, to set a plurality of edge computing devices and a plurality of digital information transmission nodes in the target area; a transmission optimization module, configured to obtain real-time meteorological information of the target area, determine a dynamic priority value of each of the public safety perception components according to the real-time meteorological information of the target area, determine a public safety risk value of each of the public safety perception components according to the public safety data collected by the multiple public safety perception components through the multiple edge computing devices, and for each of the public safety perception components, determine a digital information transmission path corresponding to the public safety perception component according to the basic priority value, dynamic priority value and public safety risk value of each of the public safety perception components; The information transmission module is used to transmit the public safety data collected by the public safety perception component to the control center through the multiple digital information transmission nodes according to the digital information transmission path corresponding to the public safety perception component.

Images