Quantitative evaluation method for influence degree of geological disaster on road traffic
Through the Bayesian network model, combining geological disasters and vehicle traffic data, a causal relationship was constructed, which solved the problem of lack of quantitative means in traditional evaluation methods, and achieved scientific assessment of the impact of geological disasters on road traffic, improving assessment accuracy and emergency response Response efficiency.
Patent Information
- Application Number
- CN202411069871.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-06
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2044-08-06
AI Technical Summary
Traditional geological disaster impact assessment methods are mostly based on empirical and qualitative analysis, and lack systematic quantitative assessment methods, making it difficult to accurately predict the specific impact of geological disasters on road traffic.
Using Bayesian network model, the impact of geological disasters on road traffic is quantitatively evaluated through data collection and preprocessing, construction of Bayesian network structure, parameter learning and inference evaluation, including the use of gantry to obtain traffic information and collect geological disaster data. , and construct nodes and causal relationships, calculate conditional probability tables, and conduct forward reasoning to evaluate the impact of geological disasters on traffic flow.
It has realized a systematic quantitative assessment of the impact of geological disasters on road traffic, provided scientific and accurate assessment results, improved the application breadth of the model and traffic management decision support, and improved emergency response efficiency.
Smart Images

Figure CN119028146A_ABST
Abstract
Description
Technical Field
[0001] The invention belongs to the field of data processing, and in particular relates to a quantitative evaluation method for the impact of geological disasters on highway traffic. Background Art
[0002] With the rapid development of modern society, the importance of highway transportation in economic and social activities has become increasingly prominent. However, geological disasters such as landslides, mudslides, and earthquakes occur frequently, posing a serious threat to the highway transportation system. These geological disasters may not only cause traffic congestion and reduced traffic volume, but may also cause traffic accidents, endangering people's lives and property. Therefore, how to effectively evaluate the impact of geological disasters on highway transportation has become the focus of attention of transportation management departments and related research institutions.
[0003] Traditional geological disaster impact assessment methods are mostly based on experience and qualitative analysis, lacking systematic quantitative assessment methods, making it difficult to accurately predict the specific impact of geological disasters on transportation. Summary of the invention
[0004] In order to solve the problems in the prior art, the present invention provides a quantitative evaluation method for the impact of geological disasters on highway traffic, the method comprising the following steps:
[0005] Step 1: data collection and preprocessing;
[0006] 1.1 Divide the preset highway into sections according to the gantry position;
[0007] 1.2 Use the camera on the gantry to obtain the traffic flow information of each segment and each time slot;
[0008] 1.3 Collect data on the occurrence time, type and intensity of geological disasters;
[0009] 1.4 Pre-process the traffic flow information and geological disaster information;
[0010] Step 2: construct the Bayesian network structure;
[0011] 2.1 Determine nodes, including a node representing the traffic flow of the i-th section of highway at the t-th time slot and a node representing the geological disaster intensity of the i-th section of highway at the t-th time slot;
[0012] 2.2 Construct the causal relationship between nodes, geological disasters affect the traffic flow, and consider the mutual influence of traffic flow in adjacent segments;
[0013] Step 3: parameter learning;
[0014] 3.1 Construct a data matrix and organize the collected data into a matrix form;
[0015] 3.2 Calculate the conditional probability table of each node based on the data matrix;
[0016] Step 4: Reasoning and evaluation;
[0017] 4.2 Using the Bayesian reasoning method, combined with the current geological disaster data, the forward reasoning of the impact of traffic flow on each section of highway at the current time slot is inferred;
[0018] 4.3 Based on the inference results, calculate the quantitative assessment value of the impact of geological disasters on highway traffic.
[0019] The present invention can produce the following beneficial effects through the above technical solution:
[0020] The present invention systematically quantifies the impact of geological disasters on highway traffic through a Bayesian network model, provides quantitative evaluation results, overcomes the limitations of traditional methods, and makes the evaluation more scientific and accurate.
[0021] Using forward reasoning of the Bayesian network to predict the impact of geological disasters on traffic flow provides a comprehensive analytical perspective and improves the breadth of application of the model.
[0022] By analyzing historical data and real-time data, the present invention can timely reflect the actual impact of geological disasters on traffic, provide data-driven decision support for traffic management departments, and improve the efficiency and effectiveness of emergency response. In addition, the entire solution calculation process is simple and convenient, and can be quickly implemented through computer programs. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0024] Figure 1 is a flow chart of the method of the present invention. DETAILED DESCRIPTION
[0025] Below, the invention is preferably described in conjunction with the accompanying drawings and specific implementation methods.
[0026] This embodiment solves the above problem through the following steps:
[0027] In one embodiment, reference Figure 1 The present invention provides a quantitative evaluation method for the impact of geological disasters on highway traffic.
[0028] Geological disasters refer to disasters caused by natural geological processes, including landslides, mudslides, earthquakes, subsidence, etc., which may cause damage or interference to the environment and human activities.
[0029] Highway traffic refers to the movement of vehicles and transportation activities through highways, including indicators such as traffic volume, traffic speed, and traffic density.
[0030] The degree of impact refers to the specific size and scope of the impact of geological disasters on road traffic, which is usually measured by quantitative indicators, such as changes in traffic volume, reduced traffic capacity, and increased accident frequency.
[0031] In this implementation, quantitative assessment refers to the objective and accurate measurement and evaluation of the impact of geological hazards through quantitative indicators and mathematical models, and the use of data analysis and statistical methods to score the impact process.
[0032] Step 1: Data collection and preprocessing.
[0033] In order to quantitatively evaluate the impact of geological disasters on highway traffic, it is necessary to first collect relevant data, including information on the time, location, type and intensity of geological disasters, as well as data on highway traffic volume, traffic speed and traffic accidents.
[0034] 1.1 Divide the preset highway into sections according to the position of the gantry.
[0035] A gantry is a structure installed above a road to support cameras, sensors and other monitoring equipment. These devices are used to collect traffic data such as traffic flow, vehicle speed, license plate recognition, etc.
[0036] The highway is divided according to the location of the gantry, and each segment is a continuous road section. The purpose of segmentation is to facilitate the accurate collection and analysis of traffic data.
[0037] Preset highway segmentation based on gantry position means dividing the entire highway into several segments based on the position of the gantry installed above the highway. This division method is mainly to facilitate the accurate collection and analysis of traffic data, so as to realize the monitoring and evaluation of traffic conditions in different sections.
[0038] Suppose there are multiple gantries on a highway, which are installed at 5 km, 10 km, 15 km, etc. Based on the location of the gantries, the highway can be divided into three sections:
[0039] Segment 1 (S1): from 0 km to 5 km;
[0040] Segment 2 (S2): from 5 km to 10 km;
[0041] Segment 3 (S3): from 10 km to 15 km.
[0042] 1.2 Use the camera on the gantry to obtain the traffic flow information of each segment and each time slot.
[0043] Traffic flow information refers to the number of vehicles passing through a certain road segment within a certain period of time. Traffic flow information is important data for traffic flow analysis and is used to evaluate road usage and traffic load.
[0044] Time slots are preset time intervals that divide the time period for data collection. For example, traffic data can be recorded in minutes, hours, or shorter time intervals.
[0045] The camera continuously captures images and videos of highway sections and uses image processing algorithms to detect and record the number of passing vehicles in real time.
[0046] The data collection time is divided into several fixed time slots (such as every minute, every hour), and the traffic flow information is counted in each time slot.
[0047] The collected traffic flow data is preprocessed, including denoising, deduplication, data format conversion, etc., to ensure the accuracy and consistency of the data.
[0048] 1.3 Collect data on the occurrence time, type and intensity of geological disasters.
[0049] Record the specific time point or time period when the geological disaster actually occurred, which is used to record the time information of the disaster event to facilitate subsequent analysis and response.
[0050] Specific categories or forms of geological disasters, such as landslides, mudslides, earthquakes, etc. Different types of geological disasters have different causes, characteristics and impact ranges.
[0051] The destructive power or impact of geological disasters is usually expressed in quantitative indicators, such as the volume of landslides, the flow of debris flows, the magnitude of earthquakes, etc., which are used to assess the severity of the disaster.
[0052] Real-time geological disaster data can be collected through monitoring equipment installed in geological disaster-prone areas, such as seismographs, rain gauges, and landslide monitors. Satellite remote sensing technology can be used to monitor the occurrence and development of geological disasters through high-resolution images. After a disaster occurs, first-hand geological disaster information, including disaster type, impact range, and intensity, can be obtained through on-site investigation. Historical data and literature can be consulted to collect data on the occurrence time, type, and intensity of previous geological disasters.
[0053] For example, suppose a geological disaster monitoring station collects the following geological disaster data through installed monitoring equipment and on-site investigation:
[0054] 2024-01-15 10:30 Landslide volume 5000 cubic meters
[0055] 2024-02-20 14:00 Debris flow rate 3000 cubic meters / hour
[0056] 2024-03-05 08:15 Earthquake magnitude 5.6
[0057] 1.4 Pre-process the traffic flow information and geological disaster information.
[0058] Ensure the accuracy, consistency and availability of the data by cleaning, converting and organizing the raw data. The purpose of this step is to transform the collected raw data into high-quality data suitable for subsequent analysis and modeling. Specifically:
[0059] Choose an appropriate missing value processing method based on the characteristics of the data set and analysis requirements. Common methods include deleting records with a large number of missing values, filling missing values with the mean or median, and estimating missing values using interpolation or regression methods.
[0060] Depending on the nature of the outlier, you can choose to delete, modify, or replace it. For example, for an abnormal peak in traffic flow data, you can combine the context data to determine whether it is an erroneous record and take corresponding measures.
[0061] Detect whether there are duplicate records in the data set, especially when merging data from multiple sources, as duplicate data will affect the accuracy of the analysis results. Identify and remove duplicate data through unique identifiers (such as timestamps, road segment numbers, etc.).
[0062] Convert data from different sources into a unified unit. For example, convert traffic flow data in different units (such as vehicles per hour and vehicles per minute) into vehicles per hour.
[0063] Ensure that all data types are consistent, such as converting string-formatted timestamps to date-time format for time series analysis. For example, converting traffic flow data from string format (such as "1000 cars / hour") to numeric format (such as 1000) for subsequent statistical analysis.
[0064] Convert data of different dimensions to the same scale range to eliminate the impact of dimension differences on the analysis results. Common methods include minimum-maximum normalization and Z-score normalization. For example, normalize traffic flow data and geological disaster intensity data to scale their value range to between 0 and 1.
[0065] Ensure that data from different data sources are aligned in time and space to ensure data consistency and comparability. For example, align the timestamps of vehicle flow data and geological disaster data to ensure that the vehicle flow at the same time point is consistent with the corresponding geological disaster intensity.
[0066] Step 2: Construct the Bayesian network structure.
[0067] A Bayesian network is a probabilistic graph model consisting of nodes and edges that is used to represent causal relationships and conditional probabilities between variables. Bayesian networks can effectively handle dependencies in uncertainties and complex systems.
[0068] In this embodiment, a Bayesian network model is established to describe and quantify the complex dependency between geological disasters and traffic flow. By determining the nodes and edges of the network and calculating the conditional probability table, the impact of geological disasters on highway traffic can be effectively quantitatively evaluated.
[0069] 2.1 Determine the nodes, including the traffic volume of the i-th section of highway at the t-th time slot and the geological disaster intensity of the i-th section of highway at the t-th time slot.
[0070] Nodes are the basic units in Bayesian networks and represent random variables. In the assessment of the impact of geological disasters on highway traffic, nodes can represent specific traffic and environmental variables, which in this implementation refer to traffic volume and geological disaster intensity.
[0071] Traffic flow node C i,t : represents the traffic flow of the i-th section of highway at the t-th time slot. Traffic flow is a key traffic indicator that reflects the traffic conditions of a specific section of road at a specific time.
[0072] Example: Assume that a highway is divided into three sections (S1, S2, S3), and the traffic volume of each section is recorded once every hour. Then C 1,1 represents the traffic volume of S1 highway in the first hour, C 2,2 It represents the traffic volume of the S2 section of highway in the second hour, and so on.
[0073] Geological hazard intensity node G i,t , represents the geological disaster intensity of the i-th section of highway at the t-th time slot. The geological disaster intensity is a key indicator for evaluating the impact of geological disasters on highway traffic.
[0074] Example: Assume that the geological disaster intensity at different times and in different segments is recorded in geological disaster monitoring, then G 1,1 It indicates the geological disaster intensity of the S1 section of highway in the first hour, G 2,2 It indicates the geological disaster intensity of the S2 section of highway in the second hour, and so on.
[0075] 2.2 Construct the causal relationship between nodes, geological disasters affect traffic flow, and consider the mutual influence of traffic flow in adjacent segments.
[0076] In a Bayesian network, nodes are connected by directed edges, which represent the causal influence or dependency of one variable (node) on another variable (node). For example, the impact of geological disaster intensity on traffic flow can be represented by a directed edge. Traffic flows in adjacent sections of a highway may affect each other. For example, traffic congestion on an upstream section may lead to reduced traffic flow or lower vehicle speeds on a downstream section.
[0077] In a Bayesian network, nodes are connected by directed edges to represent the causal and dependency relationships between different variables. In particular, it is necessary to clarify the impact of geological disaster intensity on traffic flow and take into account the possible mutual influence of traffic flow between adjacent highway sections. In this way, the impact of geological disasters on highway traffic can be more accurately described and quantified.
[0078] The occurrence and intensity of geological disasters have a direct causal relationship with traffic flow. For example, when a landslide occurs, it will cause the road to be partially or completely blocked, and vehicles cannot pass, thus significantly reducing the traffic flow.
[0079] In the Bayesian network, a directed edge is used from the geological disaster intensity node G i,t Pointing to traffic flow node C i,t , indicating the causal impact of geological disasters on traffic flow.
[0080] The traffic conditions of the upstream section will affect the traffic flow of the downstream section. For example, if the upstream section is congested, vehicles will be stranded upstream, and the traffic flow of the downstream section may decrease.
[0081] In the Bayesian network, the traffic flow nodes of adjacent segments are connected by directed edges. i,t Point to C i+1,t , which represents the impact of the traffic flow of the i-th section of highway on the traffic flow of the i+1-th section of highway.
[0082] Step 3: parameter learning.
[0083] In Bayesian networks, parameter learning refers to using the collected data to estimate the conditional probability distribution of each node in the network. Through parameter learning, the conditional probability table (CPT) in the Bayesian network can be determined, so that the network can accurately perform reasoning and prediction.
[0084] 3.1 Construct a data matrix and organize the collected data into a matrix form.
[0085] In this step, the original traffic flow and geological disaster data need to be cleaned, converted and structured first, and finally formed into a matrix format that is easy to analyze. Each row in the data matrix represents an observation record within a time slot, and each column represents a variable (such as traffic flow, geological disaster intensity, etc.). In this way, the data can be systematically organized to facilitate subsequent statistical analysis and parameter estimation.
[0086] 3.2 Based on the data matrix, calculate the conditional probability table for each node.
[0087] In this step, the conditional probability distribution of each node in the Bayesian network is determined through statistical analysis and calculation using the constructed data matrix. Specifically, by statistically analyzing the observation records in the data matrix, the probability of occurrence of each node under different conditions of its parent node is calculated, thereby constructing the conditional probability table (CPT) of each node in the Bayesian network. These conditional probability tables are used to describe the dependencies between variables and play a key role in network reasoning and prediction.
[0088] First, count the frequency and define the joint frequency table: Count the traffic flow C i,t Under different geological disaster intensity G i,t For example, when the geological disaster intensity is 2, the frequency of traffic volume is 100, 150, and 200.
[0089] Example joint frequency table:
[0090] <![CDATA[G i,t ]]> <![CDATA[C i,t (Low)]]> <![CDATA[C i,t (Chinese)]]> <![CDATA[C i,t (High)]]> 1 10 20 5 2 15 25 10 3 5 10 3 4 8 12 2
[0091] Define marginal frequency table: Count the intensity of each geological disaster G i,t For example, the total frequency of all vehicle flows when the geological disaster intensity is 2.
[0092] Example marginal frequency table:
[0093] <![CDATA[G i,t ]]> Total frequency 1 35 2 50 3 18 4 22
[0094] Conditional probability definition: Conditional probability P(C i,t |G i,t ) is in the parent node G i,t Under different conditions, the target node C i,t The probability distribution of .
[0095] Conditional probability formula:
[0096]
[0097] where c j represents the traffic volume, g k Represents geological disaster parameters.
[0098] According to the joint frequency table and marginal frequency table, calculate the conditional probability value under each condition. For example, calculate the conditional probability that the traffic volume is 100 when the geological disaster intensity is 2.
[0099] Example calculation:
[0100] <![CDATA[G i,t ]]> <![CDATA[C i,t (Low)]]> <![CDATA[C i,t (Chinese)]]> <![CDATA[C i,t (High)]]> 1 10 / 35=0.286 20 / 35=0.571 5 / 35=0.143 2 15 / 50=0.300 25 / 50=0.500 10 / 50=0.200 3 5 / 18=0.278 10 / 18=0.556 3 / 18=0.167 4 8 / 22=0.364 12 / 22=0.545 2 / 22=0.091
[0101] Constructing a Conditional Probability Table (CPT)
[0102] Fill the calculated conditional probability values into the conditional probability table. The sum of all target node probability values under each parent node condition should be 1.
[0103] Example conditional probability table:
[0104] <![CDATA[G i,t ]]> <![CDATA[C i,t (Low)]]> <![CDATA[C i,t (Chinese)]]> <![CDATA[C i,t (High)]]> 1 0.286 0.571 0.143 2 0.300 0.500 0.200 3 0.278 0.556 0.167 4 0.364 0.545 0.091
[0105] Step 4: Reasoning and evaluation;
[0106] 4.1 Using the Bayesian reasoning method, combined with the current geological disaster data, the forward reasoning of the impact of each section of highway on the traffic flow in the current time slot is inferred.
[0107] By using Bayesian networks and Bayesian reasoning methods, the current collected geological disaster data is analyzed to calculate and predict the changes in traffic volume in each highway section within the current time slot. Specifically, through forward reasoning, the probability distribution of traffic volume in each section can be predicted based on the known intensity of geological disasters; through backward reasoning, the probability distribution of the intensity of geological disasters can be inferred based on the known traffic volume.
[0108] Through geological monitoring equipment and on-site investigation, obtain geological disaster information at the current time point, including the time, location, type and intensity of occurrence. Organize geological disaster data into a standard format for subsequent analysis and processing.
[0109] In the forward reasoning part, define the forward reasoning goal:
[0110] Known conditions: Current geological disaster intensity G i,t
[0111] Inference target: Traffic flow C i,t The probability distribution of .
[0112] Use conditional probability table: According to the known geological disaster intensity G i,t Using the conditional probability table P(C i,t |G i,t ) Calculate the probability distribution of traffic flow.
[0113] Example: Assuming the current geological disaster intensity is 2, use the conditional probability table to calculate the probability of low, medium, and high traffic volume.
[0114] P(C i,t |G i,t =2) = [P(C i,t = Low | G i,t =2),P(C i,t =Medium|G i,t =2),P(C i,t =High|G i,t =2)]
[0115] Based on the calculation results, the probability distribution of traffic flow in each section under the current geological disaster intensity is obtained to evaluate the impact of geological disasters on traffic flow.
[0116] 4.2 Based on the reasoning results, calculate the quantitative assessment value of the impact of geological disasters on highway traffic.
[0117] According to the probability distribution of traffic flow, the expected value of traffic flow E(C i,t )
[0118]
[0119] where c j For different values of traffic flow, P(C i,t =c j |G i,t ) is the corresponding conditional probability.
[0120] For example, it is assumed that: the current geological disaster intensity G i,t =2The conditional probability distribution of traffic flow is
[0121] P(C i,t = Low | G i,t =2)=0.300
[0122] P(C i,t =Medium|G i,t =2)=0.500
[0123] P(C i,t =High|G i,t =2)=0.200
[0124] Expected traffic volume:
[0125] E(C i,t ) = (low × 0.300) + (medium × 0.500) + (high × 0.200)
[0126] Calculate the impact of geological hazards on traffic flow
[0127] The impact of geological disasters on vehicle flow can be expressed as a decrease or increase in vehicle flow. i,t It is defined as the difference between the current expected traffic flow and the expected traffic flow when there is no geological disaster.
[0128] I i,t =E(C i,t ) 当前 -E(C i,t ) 无地质灾害
[0129] Exemplarily
[0130] Expected value of traffic flow when there is no geological disaster: Assume that the expected value of traffic flow when there is no geological disaster is E(C i,t ) 无地质灾害 =15
[0131] Current traffic flow expectation value: According to the above calculation, assume that the current traffic flow expectation value is E(C i,t ) 当前 =120
[0132] Impact of geological disasters on traffic flow:
[0133] I i,t =120-150=-30
[0134] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.
[0135] The present invention does not particularly specify the structure of some modules, which shall be subject to the contents recorded in the prior art. The prior art mentioned in the above background technology section and the specific embodiment section of the present invention can be used as part of the present invention to understand the meaning of some technical features or parameters. The scope of protection of the present invention shall be subject to the contents actually recorded in the claims.
Claims
1. A quantitative assessment method for the impact of geological disasters on highway traffic. Features The method comprises the following steps: Step 1: data collection and preprocessing; 1.1 Divide the preset highway into sections according to the gantry position; 1.2 Use the camera on the gantry to obtain the traffic flow information of each segment and each time slot; 1.3 Collect data on the occurrence time, type and intensity of geological disasters; 1.4 Pre-process the traffic flow information and geological disaster information; Step 2: construct the Bayesian network structure; 2.1 Determine nodes, including a node representing the traffic flow of the i-th section of highway at the t-th time slot and a node representing the geological disaster intensity of the i-th section of highway at the t-th time slot; 2.2 Construct the causal relationship between nodes, geological disasters affect the traffic flow, and consider the mutual influence of traffic flow in adjacent segments; Step 3: parameter learning; 3.1 Construct a data matrix and organize the collected data into a matrix form; 3.2 Calculate the conditional probability table of each node based on the data matrix; Step 4: Reasoning and evaluation; 4.2 Using the Bayesian reasoning method, combined with the current geological disaster data, the forward reasoning of the impact of traffic flow on each section of highway at the current time slot is inferred; 4.3 Based on the inference results, calculate the quantitative assessment value of the impact of geological disasters on highway traffic.
2. A quantitative assessment method for the impact of geological disasters on highway traffic according to claim 1, Features The traffic flow information refers to the number of vehicles passing through a certain highway segment in a time slot.
3. A quantitative assessment method for the impact of geological disasters on highway traffic according to claim 2, Features The one time slot is 1 minute.
4. A quantitative assessment method for the impact of geological disasters on highway traffic according to claim 1, Features The preprocessing of the traffic flow information and geological disaster information includes: cleaning, converting and organizing the original data to ensure the accuracy, consistency and availability of the data.
5. A quantitative assessment method for the impact of geological disasters on highway traffic according to claim 1, Features : The traffic flow node is C i,t , represents the traffic flow of the i-th section of highway at the t-th time slot; The geological disaster intensity node is G i,t , which represents the geological disaster intensity of the i-th section of highway at the t-th time slot.
6. A quantitative assessment method for the impact of geological disasters on highway traffic according to claim 5, Features The causal relationship between nodes is constructed, geological disasters affect the traffic flow, and the mutual influence of traffic flow in adjacent segments is considered, including: using directed edges from the geological disaster intensity node G i,t Pointing to traffic flow node C i,t , indicating the causal effect of geological disasters on traffic flow; using directed edges to connect the traffic flow nodes of adjacent segments, from C i,t Point to C i+1,t , which represents the impact of the traffic flow of the i-th section of highway on the traffic flow of the i+1-th section of highway.
7. A quantitative assessment method for the impact of geological disasters on highway traffic according to claim 6, Features The process of arranging the collected data into a matrix form includes: The original traffic flow and geological disaster data need to be cleaned, converted and structured to form a matrix format that is easy to analyze; each row in the data matrix represents an observation record within a time slot, and each column represents a variable, including traffic flow and geological disaster intensity.
8. A quantitative assessment method for the impact of geological disasters on highway traffic according to claim 7, Features Calculating the conditional probability table for each node includes: Traffic statistics C i,t Under different geological disaster intensity G i,t The frequency of occurrence of the following; Statistics of the intensity of each geological disaster G i,t The total frequency of the following; Conditional probability P(C i,t |G i,t ) is in the parent node G i,t Under different conditions, the target node C i,t The probability distribution of where c j represents the traffic volume, g k Indicates geological hazard parameters; According to the joint frequency table and marginal frequency table, calculate the conditional probability value under each condition; Fill the calculated conditional probability values into the conditional probability table. The sum of all target node probability values under each parent node condition should be 1.
9. A quantitative assessment method for the impact of geological disasters on highway traffic according to claim 8, Features Using the Bayesian reasoning method, combined with the current geological disaster data, the forward reasoning to infer the impact of each section of the highway on the traffic flow in the current time slot includes: based on the known geological disaster intensity G i,t Using the conditional probability table P(C i,t |G i,t ) Calculate the probability distribution of traffic flow.
10. A quantitative assessment method for the impact of geological disasters on highway traffic according to claim 9, Features Through the inference results, the quantitative evaluation values of the impact of geological disasters on highway traffic are calculated, including: According to the probability distribution of traffic flow, the expected value of traffic flow E(C i,t ) where c j For different values of traffic flow, P(C i,t =c j |G i,t ) is the corresponding conditional probability; Calculate the impact of geological hazards on traffic flow I i,t =E(C i,t ) 当前 -E(C i,t ) 无地质灾害 Among them I i,t is the impact of geological disasters on highway traffic, E(C i,t ) 当前 is the expected value of the current traffic flow, E(C i,t ) 无地质灾害 is the expected value of traffic flow when there is no disaster.
Citation Information
Patent Citations
Road network evaluation method based on Bayesian model and triple standard deviation criterion
CN109409713A
Earthquake landslide disaster area and disaster chain risk assessment method
CN113554345A
Quantitative evaluation method for influence degree of geological disaster on road traffic
CN114742348A
Channel operation state deduction prediction method based on multi-source information deep fusion
CN117558124A
Technology for evaluating traffic capacity of mountainous road under geological disaster condition
CN118014355A
Cited By
Information processing device, information processing method, and computer program
WO2026014347A1
