Real-time commanding and dispatching system based on visual digital-intelligent fusion technology

Abstract

The invention discloses a real-time commanding and dispatching system based on a visual digital-intelligent fusion technology, relates to the technical field of emergency commanding and dispatching, and solves the technical problem that in the prior art, resource dispatching is not accurate enough in response to emergency situations. According to the invention, by collecting the field data of the disaster site and the resource data of each material point, a solid data basis is provided for emergency decision making; the material points and the rescue teams matched with the disaster sites are matched, the calculation amount needing to be calculated can be reduced, the material coefficients and the team coefficients of the matched material points and the matched teams are calculated respectively, and a rescue combination is generated based on the material coefficients and the team coefficients; according to the method, whether the position of the optimal material point is the same as the position of the optimal rescue team or not is judged, if not, the secondary matching team is obtained by taking the material as the weight, the secondary team coefficient is calculated, and the secondary matching team corresponding to the maximum value of the secondary team coefficient, the optimal material point and the rescue team where the optimal material point is located are combined to generate the rescue combination.

Description

Technical Field

[0001] The present invention belongs to the field of emergency management and relates to visualized digital-intelligence fusion technology, specifically a real-time command and dispatch system based on visualized digital-intelligence fusion technology. Background Art

[0002] With the intensification of climate change and the complication of social activities, natural disasters such as earthquakes, floods, and typhoons and man-made emergencies such as industrial accidents and public health incidents have occurred frequently, posing severe challenges to human society; these emergencies are often accompanied by huge casualties and property losses. At this time, efficient emergency command and dispatch becomes the key to reducing losses and protecting people’s lives and property.

[0003] The invention patent with application number CN2020106484367 discloses an emergency command and dispatch system. The invention builds a database of a large amount of emergency knowledge of emergencies through a knowledge base management module, and collects people's emotions and opinions on emergencies; when an emergency occurs, the emergency is matched with the knowledge base, and the matched emergency plans and emergency resources are activated; the personal information of emergency personnel is collected and recorded, and tasks are sent and received to emergency personnel in real time; when handling emergencies, this method obtains emergency plans based on the emergency knowledge base built in advance. When encountering unrecorded and emergency resource dispatching, it is impossible to quickly obtain resource dispatching plans.

[0004] The present invention provides a real-time command and dispatch system based on visualized digital intelligence fusion technology to solve the above technical problems. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes a real-time command and dispatch system based on visual digital intelligence fusion technology, which is used to solve the technical problem of inaccurate resource scheduling in responding to emergencies in the prior art.

[0006] To achieve the above-mentioned purpose, the first aspect of the present invention provides a real-time command and dispatch system based on visual digital intelligence fusion technology, including: a data collection module, an allocation and dispatch module and a visualization module;

[0007] Data collection module: used to collect on-site data and resource data; resource data includes material data and manpower data; on-site data includes the disaster location, number of victims, disaster type, required types of materials, material consumption rate and corresponding real-time remaining amount of materials; material data includes the location of each material point, material type and corresponding material quantity; manpower data includes the location of the rescue team, number of rescuers, historical rescue data and rescue capacity;

[0008] Allocation and scheduling module: used to match the disaster type and required types of materials in the on-site data with the types and quantities of materials in the material data to obtain matching material points, and to match the number of victims and disaster types in the on-site data with the number of rescuers and rescue capabilities in the manpower data to obtain matching teams;

[0009] Calculate the material coefficient of the matching material point based on the on-site data and material data, and calculate the team coefficient of the matching team based on the on-site data and manpower data; generate a rescue combination based on the material coefficient and the team coefficient;

[0010] Visualization module: used to display on-site data, resource data and rescue teams on a visualization screen. The operator directs and dispatches the rescue teams to the disaster site for rescue, and conducts real-time analysis of the disaster and adjusts the dispatch based on the on-site data and resource data.

[0011] Preferably, the step of matching the disaster type and the required type of materials in the on-site data with the material type and material quantity in the material data to obtain a matching material point includes:

[0012] A1: Extract the disaster type, required type, material type and material quantity;

[0013] A2: Determine whether the material types include the required types; if yes, jump to A3; if no, mark the corresponding material point as an unmatched material point;

[0014] A3: Set the standard quantity of transported materials; determine whether the material quantity is greater than or equal to the standard quantity of transported materials; if yes, mark the corresponding material point as a matching material point; if no, mark the corresponding material point as an unmatched material point.

[0015] Preferably, the step of matching the number of disaster victims and disaster types in the on-site data with the number of rescuers and rescue capabilities in the manpower data to obtain a matching team includes:

[0016] B1: Extract the number of disaster victims, disaster type, number of rescuers and rescue capacity;

[0017] B2: Determine whether the rescue capability of the rescue team includes the disaster type; if yes, jump to B3; if no, mark the corresponding rescue team as an unmatched team;

[0018] B3: Set the number of rescuers required for a single disaster victim to y; determine whether the number of rescuers is greater than y times the number of disaster victims; if yes, mark the corresponding rescue team as a matching team; if no, mark the corresponding rescue team as an unmatched team.

[0019] Preferably, the step of calculating and obtaining the material coefficient of the matching material point according to the on-site data and the material data includes:

[0020] Extract on-site data and resource data matching material points;

[0021] The quantity of supplies is marked as WZL, and the distance between the disaster site and the supply point is marked as JL;

[0022] By formula The material coefficient WZXi of the material point numbered i is calculated; where i = 1, 2, 3, ... n, and n is a positive integer; α1 and α2 are weight coefficients, which are set according to the influence of material quantity, distance, material consumption rate and material remaining amount on the scheduling decision.

[0023] Preferably, the step of calculating and obtaining the team coefficient of the matching team based on the on-site data and the manpower data includes:

[0024] Extract field and human data;

[0025] The historical rescue data in the manpower data is input into the experience evaluation model to obtain the experience scores of the rescue team members; the distance between the disaster site and the team location is marked as DWL, and the average of the experience scores is marked as JYF; wherein the experience evaluation model is constructed based on the neural network model;

[0026] By formula The team coefficient DWSh of the matching team numbered h is calculated; wherein h=1, 2, 3, ... m, m is a positive integer, β1 and β2 are weight coefficients, which are set according to the importance of distance and experience for selecting the team.

[0027] Preferably, the empirical evaluation model is constructed based on a neural network model, including:

[0028] Several historical rescue data of rescue teams are extracted from the database, and are manually evaluated to obtain historical experience scores. The rescue data of the rescue teams and the corresponding historical experience scores are used as training data and test data. The training data is used to train the initialized neural network model, and the trained neural network model is tested by the test data. According to the test results, the parameters of the neural network model are adjusted to obtain an experience evaluation model whose input data is the rescue data and whose output data is the corresponding experience score.

[0029] Preferably, generating a rescue combination based on the material coefficient and the team coefficient includes:

[0030] S1: Extract material coefficients and team coefficients; sort material points and rescue teams from large to small according to the material coefficients and team coefficients, mark the material point corresponding to the maximum material coefficient as the best material point, and mark the rescue team corresponding to the maximum team coefficient as the best team;

[0031] S2: Determine whether the position of the best material point is the same as the position of the best rescue team; if yes, combine the best material point and the best team to generate a rescue combination; if no, jump to S3;

[0032] S3; Determine whether the number of rescue teams at the best material point is greater than y times the number of victims. If so, combine the best material point with its rescue team to generate a rescue combination; if not, subtract the number of rescue teams at the best material point from y times the number of victims to get the secondary matching number, select the secondary matching number with the highest experience score among other rescue teams as the secondary matching team, and take the average value to calculate the secondary team coefficient; combine the secondary matching team corresponding to the maximum value of the secondary team coefficient, the best material point and the rescue team at the best material point to generate a rescue combination.

[0033] Preferably, the averaging is used to calculate the secondary team coefficient, including:

[0034] Extract the number of people x for secondary matching; select the x people with the highest experience score in each rescue team as the secondary matching team; mark the average experience score of the secondary matching team as ECF; through the formula The quadratic coefficient WEj of the secondary matching team numbered j is calculated, where j=1, 2, 3, ...r, and r is a positive integer.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] 1. The present invention provides a solid data foundation for emergency decision-making by collecting on-site data of the disaster site and resource data of each material point; matching the material points and rescue teams that match the disaster site can reduce the amount of calculation required, and separately calculates the material coefficient and team coefficient of each matching material point and matching team to ensure the optimal allocation of resources, which not only improves the efficiency of the use of rescue materials, but also makes rescue operations more accurate and effective, avoiding waste of resources; generating rescue combinations based on the material coefficient and team coefficient can maximize the rescue efficiency and improve the rationality of resource allocation.

[0037] 2. The present invention determines whether the positions of the best material point and the best rescue team are the same. If they are not the same, the secondary matching team is obtained based on the materials, and the secondary team coefficient is calculated. The secondary matching team corresponding to the maximum value of the secondary team coefficient, the best material point and the rescue team where the best material point is located are combined to generate a rescue combination. This can effectively shorten the arrival time of rescue materials, improve rescue efficiency, make the team deployment more reasonable, and enhance the flexibility and pertinence of rescue operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] 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 or the description of the prior art 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.

[0039] Figure 1 The following is a flowchart of an embodiment of the present invention.

[0040] Figure 2 It is a system composition diagram of the present invention.

[0041] Figure 3 A flowchart of obtaining a rescue combination according to an embodiment of the present invention. DETAILED DESCRIPTION

[0042] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than 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.

[0043] See also Figure 1-Figure 3 , the first aspect of the present invention provides a real-time command and dispatch system based on visual digital intelligence fusion technology, including: a data collection module, an allocation and dispatch module and a visualization module;

[0044] Data collection module: used to collect field data and resource data; among which, resource data includes material data and manpower data; field data includes the disaster location, number of victims, disaster type and required types of materials; material data includes the location of each material point, material type and corresponding material quantity; manpower data includes the team location of the rescue team, the number of rescuers, historical rescue data and rescue capabilities.

[0045] For example, a flood disaster occurred in area A, affecting 400 people. The required supplies are emergency food. The current supply efficiency rate is 50 pieces / day, and the current surplus is 300 pieces. There are supply points 1, 2, 3 and 4 around area A. The types of supplies at supply point 1 are 500 pieces of emergency food, 500 pieces of medical supplies and 200 pieces of bedding. The number of rescuers in the No. 1 rescue team stationed at supply point 1 is 100, and the rescue capabilities include flood, earthquake and fire. The types of supplies at supply point 2 are 400 pieces of emergency food, 500 pieces of medical supplies and 200 pieces of bedding. There are 300 pieces of bedding supplies, and there are 150 rescuers in the No. 2 rescue team stationed at supply point 2, with rescue capabilities including floods and earthquakes; the types of supplies at supply point 3 are 400 pieces of emergency food, 400 pieces of medical supplies and 300 pieces of bedding supplies, and there are 130 rescuers in the No. 3 rescue team stationed at supply point 3, with rescue capabilities including earthquakes and fires; the types of supplies at supply point 4 are 600 pieces of emergency food, 500 pieces of medical supplies and 400 pieces of bedding supplies, and there are 200 rescuers in the No. 1 rescue team stationed at supply point 4, with rescue capabilities including floods, earthquakes and fires.

[0046] Allocation and scheduling module: used to match the disaster type and the required types of materials in the on-site data with the types and quantities of materials in the material data to obtain matching material points, and to match the number of victims and disaster types in the on-site data with the number of rescuers and rescue capabilities in the manpower data to obtain matching teams;

[0047] The material coefficient of the matching material point is calculated based on the on-site data and material data, and the team coefficient of the matching team is calculated based on the on-site data and manpower data; a rescue combination is generated based on the material coefficient and the team coefficient; the predicted arrival time of the rescue combination at the disaster site is predicted based on the disaster site, the location of the material point and the location of the team; and a distribution scheduling plan is generated based on the predicted arrival time.

[0048] Exemplarily, determine whether the material types include the required types; if not, mark the corresponding material point as an unmatched material point; if yes, set the standard quantity of transported materials to 400 pieces; determine whether the material quantity is greater than or equal to the standard quantity of transported materials, if yes, mark the corresponding material point as a matched material point; if not, mark the corresponding material point as an unmatched material point; in this embodiment, it is determined that material point 1, material point 2, material point 3 and material point 4 are matched material points.

[0049] Determine whether the rescue capability of the rescue team includes the disaster type; if not, mark the corresponding rescue team as an unmatched team; if yes, set the number of rescuers required for a single disaster victim y=0.2, and then the rescue personnel are required to continue to judge 80 people, and continue to judge whether the number of rescuers is greater than 80; if yes, mark the corresponding rescue team as a matching team; if not, mark the corresponding rescue team as an unmatched team; in this embodiment, it is determined that the rescue capability of rescue team No. 3 does not include floods, so rescue team No. 3 is an unmatched team; rescue team No. 1, rescue team No. 2 and rescue team No. 4 are matching teams.

[0050] The distance between material point 1 and the disaster site is 120 km, the distance between material point 2 and the disaster site is 170 km, the distance between material point 3 and the disaster site is 90 km, and the distance between material point 4 and the disaster site is 150 km. In this embodiment, α1=1, α2=3 are set by formula The calculated material coefficient of material point 1 is WZX1=1.39, the material coefficient of material point 2 is WZX2=0.78, the material coefficient of material point 3 is WZX3=1.48, and the material coefficient of material point 4 is WZX4=1.33.

[0051] The rescue data of several rescue teams and the corresponding empirical scores obtained by manual scoring are extracted from the database and used as training data and test data; the initialized neural network model is trained using the training data, and the trained neural network model is tested using the test data, and the parameters of the neural network model are adjusted according to the test results to obtain an empirical evaluation model whose input data is the rescue data and whose output data is the corresponding empirical score.

[0052] The historical rescue data of the rescue teams are input into the experience evaluation model, and the average experience score of the No. 1 rescue team is 62 points, the average experience score of the No. 2 rescue team is 70 points, and the average experience score of the No. 4 rescue team is 65 points. In this embodiment, the weight coefficients β1=2, β2=1 are set, and the formula The calculation results show that the team coefficient DWS1 of the No. 1 rescue team is 1.03, the team coefficient DWS2 of the No. 2 rescue team is 0.82, and the team coefficient DWS4 of the No. 4 rescue team is 0.87.

[0053] Sort each material point according to the size of the material coefficient from large to small, mark the material point corresponding to the maximum material coefficient as the best material point, and the best material point is material point 3; sort each rescue team according to the size of the team coefficient from large to small, mark the rescue team corresponding to the maximum team coefficient as the best rescue team, and the best rescue team is rescue team No. 1.

[0054] Determine whether the position of the best material point is the same as the position of the best rescue team; if so, combine the best material point and the best team to generate a rescue combination; if not, count the number of rescue teams in the best material point, and continue to determine whether the number of rescue teams in the best material point is greater than y times the number of victims. If so, combine the best material point with its rescue team to generate a rescue combination; if not, subtract the number of rescue teams in the best material point from y times the number of victims to obtain the secondary matching number, recalculate the secondary matching team and calculate the secondary team coefficient of the secondary matching team, mark the rescue team corresponding to the maximum value of the secondary team coefficient as the alternative team, and combine the best material point and the alternative team to generate a rescue combination.

[0055] In this embodiment, the emphasis is placed on supplies, with priority given to the transportation of supplies, followed by support from rescue teams; in other embodiments, support from rescue teams may also be prioritized, which can be determined based on actual conditions.

[0056] In this embodiment, the material point location of the best material point is different from the team location of the best rescue team, and the number of rescue team members at the best material point is greater than 80, so material point 1 and rescue team number one are combined to generate a rescue combination.

[0057] In some other embodiments, if the number of rescue teams at the best resource point is less than y times the number of victims, it is necessary to subtract the number of rescue teams at the best resource point from the number of victims to obtain the secondary matching number, and use the secondary matching number as the required number; select the required number of people with the highest experience score from other rescue teams, and take the average value to calculate the secondary team coefficient, and use the formula The secondary coefficient WEj of the secondary matching team numbered j is calculated; the secondary matching team corresponding to the maximum value of the secondary team coefficient, the best material point and the rescue team where the best material point is located are combined to generate a rescue combination; the materials and rescue team at the best material point set out together to the disaster site for rescue, and the other selected alternative teams go to the disaster site at the same time.

[0058] Visualization module: used to display the on-site data, resource data and rescue team on the visualization screen. The operator directs and dispatches the rescue team to the disaster site for rescue, and conducts real-time analysis of the disaster and adjusts the dispatch based on the on-site data and resource data.

[0059] Exemplarily, the data of the disaster point, the data of each material point and the resulting rescue combination are displayed on the command screen. The operator directs material point 1 to transport materials and rescue team No. 1 to disaster area A for rescue, and observes the data of the disaster site in real time, and decides whether to continue to send reinforcements based on the actual situation.

[0060] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0061] Working principle of the present invention:

[0062] The present invention collects on-site data of the disaster site and resource data of each material point, compares the material data in the material point with the material types and quantities in the on-site data, and obtains matching material points and matching teams; calculates material coefficients and team coefficients of matching material points and matching teams according to the on-site data and resource data, generates a rescue combination based on the material coefficients and team coefficients, and if the best material point and the best rescue team are at different locations, calculates and obtains a secondary matching team and a secondary team coefficient, selects the secondary matching team, the best material point, and the rescue team where the best material point is located to form a rescue combination, and visualizes the rescue combination, on-site data, and resource data, so that operators can make adjustments based on real-time conditions.

[0063] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A real-time command and dispatch system based on visual digital intelligence fusion technology, characterized by: include: Data collection module, allocation scheduling module and visualization module; Data collection module: used to collect on-site data and resource data; resource data includes material data and manpower data; on-site data includes the disaster location, number of victims, disaster type, required types of materials, material consumption rate and corresponding real-time remaining amount of materials; material data includes the location of each material point, material type and corresponding material quantity; manpower data includes the location of the rescue team, number of rescuers, historical rescue data and rescue capacity; Allocation and scheduling module: used to match the disaster type and the required types of materials in the on-site data with the types and quantities of materials in the material data to obtain matching material points, and to match the number of victims and disaster types in the on-site data with the number of rescuers and rescue capabilities in the manpower data to obtain matching teams; Calculate the material coefficient of the matching material point based on the on-site data and material data, and calculate the team coefficient of the matching team based on the on-site data and manpower data; generate a rescue combination based on the material coefficient and the team coefficient; Visualization module: used to display on-site data, resource data and rescue teams on a visualization screen. The operator directs and dispatches the rescue teams to the disaster site for rescue, and conducts real-time analysis of the disaster and adjusts the dispatch based on the on-site data and resource data.

2. The real-time command and dispatch system based on visual digital intelligence fusion technology according to claim 1 is characterized in that: The method of matching the disaster type and the required types of materials in the on-site data with the types and quantities of materials in the material data to obtain matching material points includes: A1: Extract the disaster type, required type, material type and material quantity; A2: Determine whether the material types include the required types; if yes, jump to A3; if no, mark the corresponding material point as an unmatched material point; A3: Set the standard quantity of transported materials; determine whether the material quantity is greater than or equal to the standard quantity of transported materials; if yes, mark the corresponding material point as a matching material point; if no, mark the corresponding material point as an unmatched material point.

3. The real-time command and dispatch system based on visual digital intelligence fusion technology according to claim 1 is characterized in that: The matching team is obtained by matching the number of disaster victims and disaster types in the on-site data with the number of rescuers and rescue capabilities in the manpower data, including: B1: Extract the number of disaster victims, disaster type, number of rescuers and rescue capacity; B2: Determine whether the rescue capability of the rescue team includes the disaster type; if yes, jump to B3; if no, mark the corresponding rescue team as an unmatched team; B3: Set the number of rescuers required for a single disaster victim to y; determine whether the number of rescuers is greater than y times the number of disaster victims; if yes, mark the corresponding rescue team as a matching team; if no, mark the corresponding rescue team as an unmatched team.

4. The real-time command and dispatch system based on visual digital intelligence fusion technology according to claim 1 is characterized in that: The method of calculating and obtaining the material coefficient of the matching material point according to the on-site data and the material data includes: Extract on-site data and resource data matching material points; The quantity of supplies is marked as WZL, and the distance between the disaster site and the supply point is marked as JL; By formula The material coefficient WZXi of the material point numbered i is calculated; where i=1, 2, 3, ...n, n is a positive integer; α1 and α2 are weight coefficients.

5. The real-time command and dispatch system based on visual digital intelligence fusion technology according to claim 1 is characterized in that: The method of calculating the team coefficient of the matching team according to the on-site data and the manpower data includes: Extract field and human data; The historical rescue data in the manpower data is input into the experience evaluation model to obtain the experience scores of the rescue team members; the distance between the disaster site and the team location is marked as DWL, and the average of the experience scores is marked as JYF; wherein the experience evaluation model is constructed based on the neural network model; By formula The team coefficient DWSh of the matching team numbered h is calculated; wherein h=1, 2, 3, ...m, m is a positive integer, and β1 and β2 are weight coefficients.

6. The real-time command and dispatch system based on visual digital intelligence fusion technology according to claim 5 is characterized in that: The empirical evaluation model is constructed based on a neural network model, including: Several historical rescue data of rescue teams are extracted from the database, and are manually evaluated to obtain historical experience scores. The rescue data of the rescue teams and the corresponding historical experience scores are used as training data and test data. The training data is used to train the initialized neural network model, and the trained neural network model is tested by the test data. According to the test results, the parameters of the neural network model are adjusted to obtain an experience evaluation model whose input data is the rescue data and whose output data is the corresponding experience score.

7. The real-time command and dispatch system based on visual digital intelligence fusion technology according to claim 1 is characterized in that: The generating of the rescue combination based on the material coefficient and the team coefficient includes: S1: Extract material coefficients and team coefficients; sort material points and rescue teams from large to small according to the material coefficients and team coefficients, mark the material point corresponding to the maximum material coefficient as the best material point, and mark the rescue team corresponding to the maximum team coefficient as the best team; S2: Determine whether the position of the best material point is the same as the position of the best rescue team; if yes, combine the best material point and the best team to generate a rescue combination; if no, jump to S3; S3; Determine whether the number of rescue teams at the best material point is greater than y times the number of victims. If so, combine the best material point with its rescue team to generate a rescue combination; if not, subtract the number of rescue teams at the best material point from y times the number of victims to get the secondary matching number, select the secondary matching number with the highest experience score among other rescue teams as the secondary matching team, and take the average value to calculate the secondary team coefficient; combine the secondary matching team corresponding to the maximum value of the secondary team coefficient, the best material point and the rescue team at the best material point to generate a rescue combination.

8. The real-time command and dispatch system based on visual digital intelligence fusion technology according to claim 7 is characterized in that: The average value is used to calculate the secondary team coefficient, including: Extract the number of people x in the secondary match; select the x people with the highest experience score in each rescue team as the secondary match team; mark the average experience score of the secondary match team as ECF; through the formula The quadratic coefficient WEj of the secondary matching team numbered j is calculated, where j=1, 2, 3, ...r, and r is a positive integer.

Images