Emergency industry resource information matching optimization method based on big data

Through big data collection and path planning algorithms, the emergency material replenishment path and quantity are optimized, and the problem of difficult to grasp material demand and low replenishment efficiency in emergencies is solved, and rapid and effective material replenishment and efficient delivery are achieved.

CN118840034BActive Publication Date: 2024-11-15BEIJING RUNXING HANDE EMERGENCY MANAGEMENT TECH CO LTD
View PDF 7 Cites 0 Cited by

Patent Information

Application Number
CN202411322443.2
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-23
Publication Date
2024-11-15
Estimated Expiration
2044-09-23

AI Technical Summary

Technical Problem

The existing emergency material matching methods are difficult to effectively grasp the material demand in the event of sudden disasters, resulting in low supply efficiency and inability to provide efficient supply paths, resulting in low efficiency in delivering materials to the affected areas.

Method used

Through the emergency industry resource information matching optimization method based on big data, material consumption data is collected, consumption degree is generated, material demand is predicted, sub-region priority is determined, the supply path is planned using the path planning algorithm, and the material delivery digital twin model is tested and Multi-objective optimization algorithm optimizes the supply path and quantity to ensure fast and effective material replenishment.

Benefits of technology

A comprehensive evaluation of the material consumption status has been achieved, data collection efficiency has been improved, material demand data quality has been optimized, material supply is targeted and efficient, waste has been reduced, and material transportation has been improved.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118840034B_ABST
    Figure CN118840034B_ABST
Patent Text Reader

Abstract

The present invention discloses an emergency industry resource information matching optimization method based on big data, which relates to the field of information matching technology. The consumption degree of materials in a scheduling area is generated from a material consumption data set. If the consumption degree exceeds a consumption threshold, data is collected from a data source to generate an emergency demand data set, and the data collection frequency is constrained. After predicting and obtaining the material demand in the scheduling area, the priority of each sub-area is determined by the urgency and material demand in the sub-area, and the material supply path in the scheduling area is obtained by planning a trained path planning algorithm in combination with the priority and location information of each sub-area. The material supply path is tested, and if the obtained efficiency is lower than expected, the material supply path in the scheduling area is optimized. When the material transportation efficiency of the material supply path is insufficient, the supply path and the supply amount are optimized, so that material replenishment can be quickly realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of information matching, and in particular to an emergency industry resource information matching optimization method based on big data. Background Art

[0002] Emergency industry resource information matching refers to the integration and optimization of various resources in the emergency industry, including technology, equipment, talents, funds, information, etc., to achieve efficient resource allocation and precise matching. This process aims to improve the speed and efficiency of emergency response, ensure that the required resources can be quickly mobilized when an emergency occurs, effectively respond to emergencies such as disasters and accidents, and protect people’s lives and property and social stability.

[0003] In a Chinese invention patent with application publication number CN116469234A, an emergency management system for urban rainstorm waterlogging disasters is disclosed, including a weather information collection module, a drainage information collection module, a road information collection module, an equipment information collection module, a power information collection module, a data processing module, a master control module and an information sending module; the weather information collection module is used to collect weather information of the monitoring site, and the weather information includes real-time weather information and weather information within a preset time period; the drainage information collection module is used to collect drainage outlet information of the monitoring site, and the drainage outlet information includes drainage outlet quantity information, unit drainage volume information and drainage outlet real-time flow information; the road information collection module is used to collect road information of the monitoring site, and the road information includes real-time water accumulation depth information, road vehicle quantity information and road congestion length information.

[0004] In the Chinese invention patent with application publication number CN117349485A, a material procurement information pre-matching method and device are provided, the method comprising: obtaining multiple material procurement information and information of various materials in inventory; obtaining customer matching priority based on multiple amounts of materials to be purchased and multiple customer information; determining the proportion of materials after matching corresponding to each material to be purchased according to the customer matching priority, multiple material procurement information and information of various materials; obtaining the pre-matching result of each material to be purchased based on the proportion of materials after matching corresponding to each material to be purchased, as well as the preset execution upper limit of each material in inventory and the difference threshold of the shipment ratio between different warehouses.

[0005] Combined with the above application and the contents of the prior art:

[0006] When emergencies occur in some areas, for example, when continuous large-scale rainfall causes waterlogging or flood disasters, it may be difficult to distribute materials in the corresponding disaster-stricken areas. Therefore, when a request for material supply is received, it is necessary to replenish the various materials in the disaster-stricken areas in a timely manner.

[0007] In the existing emergency material matching methods, in order to increase the targeted nature of material supply, the material needs in the disaster-stricken area are usually collected before the material supply, and then targeted supply is achieved. However, in a disaster situation, it is difficult to collect everyone's material demand information and the corresponding material demand cannot be effectively grasped, resulting in difficulty in achieving the expected results when supplying materials. Moreover, material demand has a certain timeliness, and in the existing emergency matching methods, after completing the emergency material matching, an efficient material supply path cannot be given, resulting in relatively low efficiency in delivering materials to the disaster-stricken area.

[0008] To this end, the present invention provides an emergency industry resource information matching optimization method based on big data. Summary of the invention

[0009] 1. Technical issues to be resolved

[0010] In view of the deficiencies in the prior art, the present invention provides an emergency industry resource information matching optimization method based on big data, which collects data from a data source and generates an emergency demand data set, and constrains the data collection frequency; after predicting and obtaining the material demand in the scheduling area, the priority of each sub-area is determined according to the urgency and material demand in the sub-area, and the material supply path in the scheduling area is obtained by planning the trained path planning algorithm in combination with the priority and location information of each sub-area; the material supply path is tested, and if the obtained efficiency is lower than expected, the material supply path in the scheduling area is optimized, and when the material transportation efficiency of the material supply path is insufficient, the supply path and the supply amount are optimized, so that material replenishment can be quickly realized, thereby solving the technical problems raised in the background technology.

[0011] (II) Technical solution

[0012] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0013] The emergency industry resource information matching optimization method based on big data includes collecting material consumption data in the dispatching area and generating a material consumption data set, and generating a material consumption rate in the dispatching area from the material consumption data set. , if the consumption degree When the consumption threshold is exceeded, a data collection instruction is issued to the outside;

[0014] After determining the data collection target in the dispatching area, collect data from the data source and generate an emergency demand data set, and constrain the data collection frequency;

[0015] Select missing values ​​from the data columns in the emergency demand data set. If the density of missing values ​​is Exceeding expectations, replacing missing values ​​with target replacement values, and after obtaining optimized data, identifying the material usage pattern within the scheduling area from the optimized data;

[0016] After predicting the demand for materials in the dispatching area, the urgency of the sub-areas and material demand , determine the priority of each sub-area , combined with the priorities of each sub-region and location information, the trained path planning algorithm plans the material supply path within the dispatching area; and urgency Under dimensionless conditions, determine the priority within each sub-area , as follows:

[0017] ;

[0018] Weight coefficient, , ;

[0019] Use the digital twin model of material transportation to test the material supply route, and generate efficiency data from the corresponding test data. , if the efficiency If the efficiency threshold is not reached, the material supply path within the dispatch area will be optimized and the optimized supply path will be marked on the electronic map.

[0020] Furthermore, the continuous rainfall area is used as the dispatch area for emergency materials, and several collection points are set in the dispatch area. The consumption speed of various materials is collected at the collection points, and the obtained material consumption speed is summarized to obtain a material consumption data set;

[0021] Generate the consumption rate of materials in the scheduling area from the material consumption data set , among which, the material consumption rate Perform linear normalization and map the corresponding data values ​​to the interval In the following way:

[0022] ;

[0023] in, n is the number of collection points, It is i The material consumption rate at each collection point, is the average value of material consumption; weight coefficient: , ,and .

[0024] Further, after receiving the data collection instruction, the dispatch area and its status information are used as data collection targets, and the data source is determined according to the collection targets;

[0025] Preset a data collection cycle containing several collection nodes, constrain each collection node, and collect data from each data source on the selected collection node in the following way:

[0026] ;

[0027] in, n is the number of data collection nodes, It is i The collection node to the j The time interval of each collection node, is the average value of the time interval, For consumption.

[0028] Furthermore, the data in the emergency demand data set is preprocessed, the acquired data values ​​are arranged along the time axis to generate corresponding data columns, missing values ​​are screened out in the data columns, and the positions of the missing values ​​are marked in the data columns;

[0029] Get the marked data column and analyze the density of missing values ​​in the corresponding data column , if the density of missing values When the density threshold is exceeded, a mean filling instruction is issued to the outside.

[0030] Furthermore, after obtaining the location of the missing values, the density of missing values ​​in the data column is The way to obtain is as follows:

[0031] ;

[0032] in, n is the number of missing values, is the shortest distance between two missing values, is the average distance, is the acceptable value of the distance, the weight coefficient is: , ,and .

[0033] Further, after receiving the mean filling instruction, the missing values ​​in the data column are predicted using the K nearest neighbor algorithm, and the missing values ​​at the missing positions are obtained, and the corresponding missing values ​​are obtained using the linear interpolation method, and the two are used as the first and second replacement values ​​respectively;

[0034] The first and second replacement values ​​determine the corresponding weights according to the ratio of the data volume on the left and right sides of the missing value; the first and second replacement values ​​are weighted averaged according to the weights to generate a target replacement value, and the missing value is replaced with the target replacement value to obtain an optimized data column.

[0035] Furthermore, a number of optimized data columns are aggregated to establish a material information database: feature engineering is performed on the data in the material information database to extract pattern features; a material usage pattern recognition model in the scheduling area is trained to obtain the pattern features, and the material usage pattern recognition model recognizes the current material usage pattern using the pattern features as input.

[0036] Furthermore, under the current material usage mode, the dispatch area is divided into several sub-areas; the trained material demand prediction model is used to predict the future material demand for dispatch, and the material demand in each sub-area is obtained. , the amount of material demand to be obtained Aggregate and generate a material forecast data set.

[0037] Furthermore, after collecting the cumulative rainfall at each monitoring point in the sub-area, the accumulated rainfall is Perform linear normalization and then calculate the urgency in the sub-region as follows :

[0038] ;

[0039] Weight coefficient: , ; For the i The accumulated rainfall at each monitoring point is is the acceptable value of cumulative rainfall, n is the number of monitoring points.

[0040] Furthermore, in the scenario of continuous rainfall, the material transportation digital twin model is used to test the material supply path, obtain the corresponding test data, and aggregate the test data to generate a path test data set;

[0041] The efficiency of test data generation from the path test data set , if the efficiency If the efficiency threshold is not reached, optimization instructions are issued externally.

[0042] Furthermore, the delivery time and resource consumption Perform linear normalization and map the corresponding data values ​​to the interval The efficiency is generated according to the following formula :

[0043] ;

[0044] in, is the weight coefficient, For the i The delivery time during the test, is the target value of the delivery time, For the i Resource consumption during each test, is the target value for resource consumption.

[0045] Furthermore, after receiving the optimization instruction, the supply path and each supply amount in the scheduling area are optimized using a multi-objective optimization algorithm with the improvement of transportation efficiency as the optimization goal, the optimized supply path and the corresponding supply amount are obtained, and the optimized supply path is marked on the electronic map.

[0046] (III) Beneficial effects

[0047] The present invention provides an emergency industry resource information matching optimization method based on big data, which has the following beneficial effects:

[0048] 1. Based on consumption Comprehensively evaluate the material consumption status in the target area to determine whether the current material consumption rate is too high. If the material consumption rate is high and cannot be effectively replenished, timely replenishment can be carried out and corresponding emergency materials can be matched.

[0049] 2. After selecting several data sources, complete the data collection at the data source, constrain each collection node, and constrain the data collection frequency, which will be more efficient during data collection and avoid data omission and loss. Generate density based on the density of missing values , according to the density The data quality of the data column can be evaluated. When the data quality of the data column is poor, corresponding processing methods can be taken to improve the data quality of the data column.

[0050] 3. Generate replacement values ​​based on the position of missing values ​​and the predicted values, and replace the missing values ​​at the corresponding positions with the replacement values. This replacement method can make the generated replacement values ​​have a relatively smaller error than the missing values, and achieve better optimization effects on the data.

[0051] 4. When matching materials, reduce the waste of materials and be more targeted, using rainfall as a representative parameter to generate urgency , by urgency Evaluate the current status and determine the necessity of material distribution; and material demand Determine the priority of material delivery to each sub-area , so that the areas that need supplies the most can get supplies first. Finally, the path planning algorithm plans the corresponding material supply path to improve the efficiency of material transportation when transporting materials to each sub-area.

[0052] 5. Based on efficiency Determine whether the current material supply path is feasible and whether it needs to be optimized to ensure that the corresponding path can quickly realize material transportation after the emergency material matching is completed. When the material transportation efficiency of the material supply path is insufficient, use the multi-objective optimization algorithm to optimize the supply path and supply quantity. After determining the area where materials are needed and completing the emergency material matching, material supply can be quickly realized. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] Figure 1 It is a flow chart of the emergency industry resource information matching optimization method of the present invention. DETAILED DESCRIPTION

[0054] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0055] See also Figure 1 The present invention provides an emergency industry resource information matching optimization method based on big data, including:

[0056] Step 1: Collect material consumption data in the dispatching area and generate a material consumption data set, and generate the material consumption rate in the dispatching area from the material consumption data set. , if the consumption degree When the preset consumption threshold is exceeded, a data collection instruction is issued to the outside;

[0057] The step 1 includes the following contents:

[0058] Step 101: In the case of waterlogging, the continuous rainfall area is used as the dispatch area for emergency materials, and several collection points are set in the dispatch area. The consumption speed of various materials is collected at the collection points, and the obtained material consumption speeds are summarized to obtain a material consumption data set;

[0059] Step 102: Generate the consumption rate of materials in the dispatching area from the material consumption data set , among which, the material consumption rate Perform linear normalization and map the corresponding data values ​​to the interval In the following way:

[0060] ;

[0061] in, n is the number of collection points, It is i The material consumption rate at each collection point, is the average value of material consumption; weight coefficient: , ,and ;

[0062] Based on historical data and expectations for material consumption management, consumption thresholds are set in advance; if the consumption rate obtained is If the consumption threshold is exceeded, it means that the materials in the dispatch area are consumed at a high speed. If the materials in the dispatch area cannot be replenished in time, there may be unexpected risks. At this time, a data collection instruction is issued to the outside.

[0063] When using, combine the contents in steps 101 and 102:

[0064] When the target area is in continuous rainfall, the consumption and demand of materials in the corresponding area are judged, and the consumption data of materials is generated from the collected consumption data. , according to the consumption Comprehensively evaluate the material consumption status in the target area to determine whether the current material consumption rate is too high and whether the material replenishment rate is too low. If the material consumption rate is high and cannot be effectively replenished, timely replenishment can be carried out to match the corresponding emergency materials.

[0065] In the existing emergency material matching methods, in order to increase the targeted nature of material supply, the material needs in the disaster-stricken area are usually collected before the material supply, and then targeted supply is achieved. However, in a disaster situation, it is difficult to collect everyone's material demand information and the corresponding material demand cannot be effectively grasped, resulting in difficulty in achieving the expected results when supplying materials. Moreover, material demand has a certain timeliness, and in the existing emergency matching methods, after completing the emergency material matching, an efficient material supply path cannot be given, resulting in relatively low efficiency in delivering materials to the disaster-stricken area.

[0066] Step 2: After determining the data collection target in the dispatching area, collect data from the data source and generate an emergency demand data set, and constrain the data collection frequency;

[0067] The step 2 includes the following contents:

[0068] Step 201: After receiving the data collection instruction, the dispatch area and its status information are used as data collection targets, such as meteorological data, geographic information data, hydrological data, disaster impact data, and rescue resource data. The data source is determined according to the collection target, including public databases, social media APIs, and IoT sensors. The emergency demand data set is obtained after receiving and aggregating the data from the data source.

[0069] Step 202: pre-set a data collection cycle so that the collection cycle includes a number of collection nodes, constrain each collection node, and collect data from each data source on the selected collection node in the following manner:

[0070] ;

[0071] in, n is the number of data collection nodes, It is i The collection node to the j The time interval of each collection node, is the average value of the time interval, is the consumption degree;

[0072] When using, combine the contents in steps 201 and 202:

[0073] When it is necessary to match the corresponding emergency materials in the dispatching area, in order to improve the pertinence of material matching, after selecting several data sources, various data collections are completed at the data source. At the same time, constraints are imposed on each collection node and the data collection frequency, which makes data collection more efficient and avoids data omissions and losses.

[0074] Step 3: Select missing values ​​from the data column in the emergency demand data set. If the density of missing values ​​is Exceeding expectations, replacing missing values ​​with target replacement values, and after obtaining optimized data, identifying the material usage pattern within the scheduling area from the optimized data;

[0075] The step three includes the following contents:

[0076] Step 301: preprocess the data in the emergency demand data set, including removing duplicate records, correcting errors and standardizing; arranging the acquired data values ​​along the time axis to generate corresponding data columns, filtering out missing values ​​in the data columns, and marking the positions of the missing values ​​in the data columns;

[0077] Step 302: Obtain the marked data column and analyze the density of missing values ​​in the corresponding data column. , as follows:

[0078] ;

[0079] in, n is the number of missing values, is the shortest distance between two missing values, is the average distance, is the acceptable value of the distance, the weight coefficient is: , ,and .

[0080] According to the historical data and the acceptance degree of missing values, the density threshold is pre-set; if the density of missing values If the density threshold is exceeded, it means that there are many missing values ​​in the current data column and the data quality is relatively low. At this time, a mean filling instruction is issued to the outside.

[0081] When using it, after completing data collection, a data column is constructed. After quality analysis of the data column, missing values ​​are screened out in the data column, and a density index is generated based on the density of missing values. , according to the density The data quality of the data column can be evaluated. When the data quality of the data column is poor, corresponding processing methods can be taken to improve the data quality of the data column.

[0082] Step 303: after receiving the mean filling instruction, use the K nearest neighbor algorithm to predict the missing values ​​in the data column, obtain the missing values ​​at the missing positions, and use the linear interpolation method to obtain the corresponding missing values, and use the two as the first and second replacement values ​​respectively;

[0083] The first and second replacement values ​​are used to determine the corresponding weights according to the ratio of the data volume on the left and right ends of the missing value; the first and second replacement values ​​are weighted averaged according to the weights to generate a target replacement value, and the missing value is replaced with the target replacement value to obtain an optimized data column;

[0084] When in use, after filtering out missing values, replacement values ​​are generated based on the position of the missing values ​​combined with the predicted values, and the missing values ​​at the corresponding positions are replaced with replacement values. This replacement method can make the generated replacement values ​​have relatively smaller errors than the missing values, and achieve better optimization effects on the data.

[0085] Step 304: Aggregate several optimized data columns to establish a material information database: perform feature engineering on the data in the material information database to extract key features such as material type, quantity, and status, and use them as pattern features; train a neural convolution network with sample data to train a material usage pattern recognition model in the scheduling area, and use the pattern features as input to identify the current material usage pattern by the material usage pattern recognition model;

[0086] When using, combine the contents in steps 301 to 303:

[0087] Based on feature extraction of the optimized data and acquisition of pattern features, the trained material usage pattern recognition model identifies the current material usage pattern, clarifies the material usage demand in the current scheduling area, and makes material transportation in the scheduling area more targeted.

[0088] Step 4: After predicting the demand for materials in the dispatching area, the urgency of the sub-areas and material demand , determine the priority of each sub-area , combined with the priorities of each sub-region and location information, and the trained path planning algorithm plans the material supply path within the dispatch area;

[0089] The step 4 includes the following contents:

[0090] Step 401: Under the current material usage mode, the dispatch area is divided into several sub-areas; the current material consumption rate and historical data in the sub-areas are used as sample data to train and obtain a material demand prediction model; the trained material demand prediction model is used to predict the future material demand of the dispatch, and the material demand in each sub-area is obtained. , the amount of material demand to be obtained Aggregate and generate a material forecast data set;

[0091] Step 402: After collecting the accumulated rainfall at each monitoring point in the sub-area, the accumulated rainfall is Perform linear normalization and then calculate the urgency in the sub-region as follows :

[0092] ;

[0093] Weight coefficient: , ; The value of the weight coefficient refers to the previous value, For the i The accumulated rainfall at each monitoring point is is the acceptable value of cumulative rainfall,n is the number of monitoring points.

[0094] In terms of material demand and urgency Under dimensionless conditions, determine the priority within each sub-area , as follows:

[0095] ;

[0096] Weight coefficient, , ;The weight coefficient can be obtained by referring to the hierarchical analysis method;

[0097] When in use, after the material demand in each sub-area is predicted, the corresponding distribution quantity can be determined during distribution. When matching materials, the waste of materials can be reduced and the materials can be more targeted. At the same time, the rainfall is used as a representative parameter to generate the urgency , by urgency Evaluate the current status and determine the necessity of material distribution; then, and material demand Determine the priority of material delivery to each sub-area , which can enable the areas that need supplies the most to receive supplies first.

[0098] Step 403: Get the priority Mark each sub-area and obtain the location and priority of each sub-area , the trained path planning algorithm performs path planning, obtains the material supply path for transporting materials to each sub-area, and marks the obtained material supply path on the electronic map;

[0099] When using, combine the contents in steps 401 to 403:

[0100] Prioritize each sub-area in the analysis Finally, the path planning algorithm plans the corresponding material supply path, which can improve the efficiency of material transportation when transporting materials to each sub-area.

[0101] Step 5: Use the material transportation digital twin model to test the material supply path and generate efficiency data from the corresponding test data. , if the efficiency If the efficiency threshold is not reached, the material supply path in the dispatch area is optimized and the optimized supply path is marked on the electronic map;

[0102] Step 5 includes the following:

[0103] Step 501: train the machine learning algorithm with sample data to obtain the trained digital twin model of material transportation; in the scenario of continuous rainfall, use the digital twin model of material transportation to test the material supply path, obtain corresponding test data, including path feasibility data, traffic flow data, real-time traffic conditions, weather forecast data, safety risk data, time efficiency data, estimated arrival time and resource consumption data, and aggregate the test data to generate a path test data set;

[0104] Step 502: Generate efficiency metrics from test data in the path test data set , and use the obtained efficiency to evaluate whether the current supply path is suitable, among which the delivery time is and resource consumption Perform linear normalization and map the corresponding data values ​​to the interval According to the following formula:

[0105] ;

[0106] in, is the weight coefficient, and its value falls into , which can be obtained through simulation software analysis or by referring to the hierarchical analysis method; For the i The delivery time during the test, is the target value of the delivery time, For the i Resource consumption during each test, is the target value of resource consumption;

[0107] Based on historical data and expectations of material transportation efficiency in the dispatching area, the efficiency threshold is set in advance; if the efficiency If the efficiency threshold is not reached, it means that the transportation efficiency along the current supply route is low and the transportation task cannot be completed within the expected time. At this time, an optimization instruction is issued to the outside.

[0108] When in use, after obtaining the material supply path, a simulation test is performed on the obtained material supply path, and the efficiency is generated from the obtained test data. , according to the efficiency Determine whether the current material supply route is feasible and whether it needs to be optimized, so as to ensure that the corresponding path can quickly realize material transportation after completing the emergency material matching.

[0109] Step 503: after receiving the optimization instruction, the multi-objective optimization algorithm is used to optimize the supply path and each supply amount in the scheduling area with the improvement of transportation efficiency as the optimization goal, the optimized supply path and the corresponding supply amount are obtained, and the optimized supply path is marked on the electronic map;

[0110] When using, combine the contents in steps 501 to 503:

[0111] When the material transportation efficiency of the material supply route is insufficient, a multi-objective optimization algorithm is used to optimize the supply route and supply quantity. After determining the area where materials are needed and completing the emergency material matching, material replenishment can be achieved quickly.

[0112] The Analytic Hierarchy Process (AHP) is a decision-making method that decomposes decision-related elements into levels such as goals, criteria, and plans, and conducts qualitative and quantitative analysis on this basis. It is particularly suitable for dealing with target systems with hierarchical and staggered evaluation indicators, and when the target value is difficult to describe quantitatively, the AHP is an effective decision-making tool.

[0113] The core of the hierarchical analysis method is to decompose the decision problem into multiple levels to form a hierarchical structure, which usually includes the target level, the criterion level, the sub-criterion level and the solution level. By solving the eigenvector of the judgment matrix, the priority weight of each element of each level to an element of the previous level is obtained, and the final weight of each alternative solution to the total goal is recursively merged by the weighted sum method, so as to find the optimal solution.

[0114] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. The emergency industry resource information matching optimization method based on big data is characterized by: include, Collect material consumption data in the dispatch area and generate a material consumption data set, and generate a material consumption rate in the dispatch area from the material consumption data set. , if the consumption degree When the consumption threshold is exceeded, a data collection instruction is issued to the outside; After determining the data collection target in the dispatching area, collect data from the data source and generate an emergency demand data set, and constrain the data collection frequency; Select missing values ​​from the data columns in the emergency demand data set. If the density of missing values ​​is Exceeding expectations, replacing missing values ​​with target replacement values, and after obtaining optimized data, identifying the material usage pattern within the scheduling area from the optimized data; After predicting the demand for materials in the dispatching area, the urgency of the sub-areas and material demand , determine the priority of each sub-area , combined with the priorities of each sub-region and location information, the trained path planning algorithm plans the material supply path within the dispatching area; and urgency Under dimensionless conditions, determine the priority within each sub-area , as follows: ; Weight coefficient, , ; Use the digital twin model of material transportation to test the material supply route, and generate efficiency data from the corresponding test data. , if the efficiency If the efficiency threshold is not reached, the material supply path within the dispatch area will be optimized and the optimized supply path will be marked on the electronic map.

2. The method for optimizing emergency industry resource information matching according to claim 1 is characterized in that: The continuous rainfall area is used as the dispatch area for emergency materials. Several collection points are set in the dispatch area. The consumption rates of various materials are collected at the collection points. The obtained material consumption rates are summarized to obtain a material consumption data set. Generate the consumption rate of materials in the scheduling area from the material consumption data set , among which, the material consumption rate Perform linear normalization and map the corresponding data values ​​to the interval In the following way: ; in, n is the number of collection points, It is i The material consumption rate at each collection point, is the average value of material consumption; weight coefficient: , ,and .

3. The method for optimizing emergency industry resource information matching according to claim 2 is characterized in that: After receiving the data collection instruction, the dispatch area and its status information are used as the data collection target, and the data source is determined according to the collection target; Set a data collection cycle that includes several collection nodes, constrain each collection node, and collect data from each data source on the selected collection node. The constraint method is as follows: ; in, n is the number of data collection nodes, It is i The collection node to the j The time interval of each collection node, is the average value of the time interval, For consumption.

4. The method for optimizing emergency industry resource information matching according to claim 3 is characterized in that: Preprocess the data in the emergency demand data set, arrange the acquired data values ​​along the time axis to generate corresponding data columns, filter out missing values ​​in the data columns, and mark the positions of missing values ​​in the data columns; Get the marked data column and analyze the density of missing values ​​in the corresponding data column , if the density of missing values When the density threshold is exceeded, a mean filling instruction is issued to the outside.

5. The method for optimizing emergency industry resource information matching according to claim 4 is characterized in that: After obtaining the location of the missing values, the density of missing values ​​in the data column The way to obtain is as follows: ; in, n is the number of missing values, is the shortest distance between two missing values, is the average distance, is the acceptable value of the distance, the weight coefficient is: , ,and .

6. The method for optimizing emergency industry resource information matching according to claim 5 is characterized in that: After receiving the mean filling instruction, the missing values ​​in the data column are predicted using the K nearest neighbor algorithm to obtain the missing values ​​at the missing position. At the same time, the linear interpolation method is used to obtain the corresponding missing values, and the two are used as the first and second replacement values ​​respectively; The first and second replacement values ​​determine the corresponding weights according to the ratio of the data volume on the left and right sides of the missing value; the first and second replacement values ​​are weighted averaged according to the weights to generate a target replacement value, and the missing value is replaced with the target replacement value to obtain an optimized data column.

7. The method for optimizing emergency industry resource information matching according to claim 6 is characterized in that: After a number of optimized data columns are aggregated, a material information database is established: feature engineering is performed on the data in the material information database to extract pattern features, and a material usage pattern recognition model in the scheduling area is trained to obtain the pattern features. The material usage pattern recognition model uses the pattern features as input to identify the current material usage pattern.

8. The method for optimizing emergency industry resource information matching according to claim 7 is characterized in that: Under the current material usage mode, the dispatch area is divided into several sub-areas, and the trained material demand prediction model is used to predict the future material demand for dispatch, and the material demand in each sub-area is obtained. , the amount of material demand to be obtained Aggregate and generate a material forecast data set.

9. The method for optimizing emergency industry resource information matching according to claim 8 is characterized in that: After collecting the cumulative rainfall at each monitoring point in the sub-area, the accumulated rainfall is Perform linear normalization and then calculate the urgency in the sub-region as follows : ; Weight coefficient: , ; For the i The accumulated rainfall at each monitoring point is is the acceptable value of cumulative rainfall, n is the number of monitoring points.

10. The method for optimizing emergency industry resource information matching according to claim 9, characterized in that: In the scenario of continuous rainfall, the material transportation digital twin model is used to test the material supply route, obtain the corresponding test data, and aggregate the test data to generate a path test data set; The efficiency of test data generation from the path test data set , if the efficiency If the efficiency threshold is not reached, optimization instructions are issued externally.

11. The method for optimizing emergency industry resource information matching according to claim 10, characterized in that: Delivery time for material replenishment and resource consumption Perform linear normalization and map the corresponding data values ​​to the interval The efficiency is generated according to the following formula : ; in, is the weight coefficient, For the i The delivery time during the test, is the target value of the delivery time, For the i Resource consumption during each test, is the target value for resource consumption.

12. The method for optimizing emergency industry resource information matching according to claim 11, characterized in that: After receiving the optimization instruction, the multi-objective optimization algorithm is used to optimize the supply path and each supply amount in the scheduling area with improving the transportation efficiency as the optimization goal, and the optimized supply path and the corresponding supply amount are obtained, and the optimized supply path is marked on the electronic map.

Citation Information

Patent Citations

  • Urban rainstorm waterlogging disaster emergency management system

    CN116469234A

  • Material purchasing information pre-matching method and device

    CN117349485A

  • Low-altitude rescue air traffic dispatching command system and dispatching command method thereof

    CN104143170A

  • Intelligent scheduling method and system for fabricated building components by applying BIM (Building Information Modeling) technology

    CN117592749A

  • Mine emergency command communication information system and method

    CN118524375A