Emergency material distribution vehicle scheduling method based on collaborative guarantee

Abstract

The invention discloses an emergency material distribution vehicle scheduling method based on collaborative guarantee, and relates to the technical field of traffic transportation and logistics management, and the method comprises the following steps: uniformly accessing instructions from different platforms into a centralized management scheduling system, and collecting and aggregating scheduling requests and resource information of all departments; and carrying out standardized analysis and preprocessing operation on the obtained scheduling request and resource information, and storing all processed effective scheduling information into a unified data set according to a set data structure so as to support subsequent feature extraction and intelligent analysis. Multi-source scheduling instructions are uniformly accessed and processed in a standardized mode, conflict intelligent identification and dynamic arbitration are achieved in combination with a machine learning model, and repeated resource allocation is avoided; task priority allocation is carried out through an arbitration window mechanism, and the continuity, scheduling stability and cooperation efficiency of emergency material distribution are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of transportation and logistics management, and in particular to a method for dispatching emergency material distribution vehicles based on collaborative security. Background Art

[0002] "Emergency material distribution vehicle scheduling based on collaborative support" refers to a method for scientifically and rationally scheduling and optimizing routes for distribution vehicles through multi-party collaboration and resource guarantee mechanisms to ensure that emergency materials (such as food, medicine, medical equipment, and rescue equipment) can be efficiently and promptly delivered to the affected area or designated location when an emergency occurs (such as a natural disaster, a major accident, or a public health incident). This method not only considers the route planning and transportation efficiency of a single vehicle, but also introduces information sharing and collaboration mechanisms between multiple entities such as government agencies, storage centers, traffic management, and front-line rescue teams. This method achieves the coordinated linkage of people, vehicles, materials, roads, and warehouses, dynamically responds to various emergencies and transportation obstacles, and ensures the reliability, timeliness, and safety of material distribution tasks. It is a comprehensive scheduling optimization strategy for public emergencies.

[0003] Existing technologies have the following shortcomings: Although existing emergency material distribution systems typically have established a unified dispatch coordination mechanism to integrate the dispatch needs of multiple departments and centrally manage transportation resources, in actual high-pressure emergency response scenarios, the dispatch system still lacks the ability to perceive and dynamically handle concurrent dispatch instructions with fine-grained conflict. Specifically, when multiple functional agencies, based on their respective information about the disaster situation on the front line, initiate dispatch requests for the same batch of vehicle resources almost simultaneously, the system can receive all dispatch instructions. However, due to its coarse processing granularity in determining task priority, identifying vehicle resource status, and reasoning about task occupancy timeliness, or due to information update lags, the same vehicle resource may still be repeatedly assigned, resulting in a "conflicting dispatch" phenomenon. Such conflicts not only cause dispatch instructions to fail to execute or overlap, but can also lead to frequent vehicle task switching and increased route reconstruction, affecting the continuity and stability of material distribution, and significantly disrupting the overall emergency response efficiency and the ability to ensure resource security in the disaster area.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0005] The purpose of the present invention is to provide an emergency material distribution vehicle scheduling method based on collaborative guarantee, which realizes intelligent conflict identification and dynamic arbitration through unified access and standardized processing of multi-source scheduling instructions, and avoids repeated resource allocation; adjusts task priorities through the arbitration window mechanism, improves the continuity, scheduling stability and collaborative efficiency of emergency material distribution, and solves the problems in the above-mentioned background technology.

[0006] In order to achieve the above-mentioned object, the present invention provides the following technical solution: a method for dispatching emergency material distribution vehicles based on collaborative guarantee, comprising the following steps:

[0007] Unify instructions from different platforms into a centralized scheduling system, collect and aggregate scheduling requests and resource information from various departments;

[0008] Perform standardized parsing and preprocessing on the acquired scheduling requests and resource information, and store all processed valid scheduling information into a unified data set according to the established data structure to support subsequent feature extraction and intelligent analysis;

[0009] Through feature engineering technology, key indicators reflecting potential resource conflicts between scheduling tasks are extracted from the constructed data set, and a multi-dimensional comprehensive analysis is performed on the extracted key indicators to quantify the potential conflict status of the current scheduling tasks;

[0010] The quantified key scheduling conflict indicators are used as feature vectors and input into a pre-trained machine learning model. The machine learning model then performs an intelligent assessment of the conflict risk of the current scheduling task to determine whether there is a conflict risk.

[0011] When the machine learning model determines that there is a risk of conflict between multiple scheduling tasks, it will not execute all scheduling instructions and enter a short-delay arbitration window. Within the arbitration window, it will dynamically evaluate the urgency, impact scope and vehicle resource occupancy status of each scheduling task, and perform real-time conflict resolution and task fusion processing based on preset task priorities and scheduling impact factors to achieve optimal allocation and efficient scheduling of limited resources.

[0012] Preferably, the instructions from different platforms are uniformly connected to a centrally managed scheduling system, including the following key steps:

[0013] First, an interface module that supports access to multiple data sources was built, enabling each functional department to send scheduling instructions to a unified platform through API calls, data subscriptions, and message buses.

[0014] Secondly, corresponding conversion rules and field mapping relationships are established for the instruction formats of each institution, converting the instruction content in different systems into a unified standard data model;

[0015] Then, all the dispatching instructions that have been connected and standardized are unified into the core command center of the dispatching system and linked with the vehicle, material, and personnel resource database to form a complete task-resource association view.

[0016] Preferably, key indicators reflecting potential resource conflicts between scheduling tasks are extracted from the constructed data set through feature engineering technology. The extracted key indicators include the probability that different agencies issue the same scheduling target for the same resource category and the clarity of the boundary division between the scheduling tasks of multiple functional agencies. The probability that different agencies issue the same scheduling target for the same resource category and the clarity of the boundary division between the scheduling tasks of multiple functional agencies are analyzed under the detection window to generate an organizational command convergence reference value and a scheduling domain boundary fuzzy reference value respectively. The potential conflict status in the current scheduling task is quantified by the organizational command convergence reference value and the scheduling domain boundary fuzzy reference value.

[0017] Preferably, the specific steps of analyzing the probability of different organizations issuing the same scheduling target for the same resource category within the detection window to generate the organizational command convergence reference value are as follows:

[0018] First, the scheduling objectives of different institutions are grouped by resource category. For each resource category, a scheduling objective set for each institution is constructed. Then, the intersection intensity ratio index of all institution scheduling objective sets is generated to indicate the degree of overlap of scheduling objectives between multiple institutions under the same resource category. The generation formula is as follows:

[0019]

[0020] , where ISR is the intersection intensity ratio index, G i and G j are the scheduling target sets issued by the i-th and j-th scheduling agencies for resource categories within the detection window, and n is the total number of agencies participating in the scheduling;

[0021] To further enhance the model's sensitivity to the trend of target consistency, a discrete structure convergence function is introduced to measure the tension between the distribution discreteness of the overall scheduling target and the instruction concentration, and the final organizational command convergence reference value is constructed as follows:

[0022]

[0023] , where OCC-RV is the organizational command convergence reference value, U R is the number of unique scheduling targets.

[0024] Preferably, the specific steps of analyzing the clarity of the boundary divisions between the scheduling tasks of multiple functional agencies under the detection window to generate the fuzzy reference value of the scheduling domain boundary are as follows:

[0025] The scheduling tasks issued by multiple functional agencies within a certain detection window are constructed into a task scheduling domain intersection graph, where each node represents a scheduling task, and the edge represents the duplication relationship of the target area between scheduling tasks. Then, the intersection index of each scheduling task is calculated. The calculation expression is as follows:

[0026] The formula is as follows:

[0027]

[0028] , CI q is the cross-index of the scheduled task q, R q and R p They are the resource sets of scheduling task q and scheduling task p, δ(g q , g p ) is the functional agency difference function, which is used to determine whether two tasks come from different functional agencies. q and g p They represent the organization identifiers of scheduled tasks q and p respectively; Γ(q) is the set of tasks that have resource intersection with task q;

[0029] After obtaining the cross-indices of all tasks, we further extract the degree of boundary fuzziness of the scheduling domain at the global level and generate a scheduling domain boundary fuzziness reference value to quantify the "instruction overlap chaos" of the overall scheduling domain. The generation formula is as follows:

[0030]

[0031] , where DDBF-RV is the fuzzy reference value of the scheduling domain boundary, Φ is the set of cross-indexes of all tasks, Φ={CI q}={CI1,CI2,……,CI m}, m is the total number of all scheduling tasks issued by multiple functional agencies within the current detection window, max(Φ) is the maximum value of the cross-index of all scheduling tasks, and the most serious resource conflict task is found. n is the total number of agencies involved in scheduling, D split It is the degree of splitting of the scheduling responsibility domain.

[0032] Preferably, the quantified organizational command convergence reference value and the scheduling domain boundary fuzzy reference value are used as feature vectors and input into a pre-trained machine learning model. The scheduling task conflict risk coefficient is generated by the machine learning model, and the conflict risk of the current scheduling task is intelligently evaluated by the scheduling task conflict risk coefficient to determine whether the current scheduling task has a conflict risk.

[0033] Preferably, the scheduling task conflict risk coefficient generated by the pre-trained machine learning model when intelligently evaluating the conflict risk of the current scheduling task is compared with the pre-set scheduling task conflict risk coefficient reference threshold to determine whether the current scheduling task has a conflict risk. The judgment logic is as follows:

[0034] If the scheduling task conflict risk coefficient is greater than the preset scheduling task conflict risk coefficient reference threshold, it is judged that there is a conflict risk between the scheduling tasks; if the scheduling task conflict risk coefficient is less than or equal to the preset scheduling task conflict risk coefficient reference threshold, it is judged that there is no conflict risk between the scheduling tasks.

[0035] Preferably, when the machine learning model determines that there is a risk of conflict between multiple scheduling tasks, not all scheduling instructions are executed, and a short-delay arbitration window is entered. Within the arbitration window, the urgency, impact scope, and vehicle resource occupancy status of each scheduling task are dynamically evaluated. Based on the preset task priority and scheduling impact factor, real-time conflict resolution and task fusion processing are performed to achieve optimal allocation and efficient scheduling of limited resources. The specific steps are as follows:

[0036] When resource conflicts are detected among multiple scheduled tasks, an arbitration window is entered to quantify the priorities of all conflicting tasks. To more comprehensively evaluate the urgency of task execution and scheduling value, a priority scoring function is constructed by comprehensively considering the urgency of the task, the remaining schedulable time, and the scope of its impact in the disaster. The formula is as follows:

[0037]

[0038] , where P q is the task priority score, U q is the task urgency coefficient, which is used to measure the urgency of task execution. q is the remaining schedulable time of the task, I q is the task impact range index, λ is the time compression adjustment factor, α1, α2 and α3 are the task urgency coefficients U q , the remaining schedulable time of the task D q And the task impact range index I q The weight coefficient is α1+α2+α3=1;

[0039] After the priority calculation is completed, the degree of competition between tasks at the resource level is evaluated. Focus on the conflict risk when the same resource is called by multiple tasks at the same time. By combining the resource usage flag and the time overlap ratio, a resource conflict intensity model between tasks is constructed. The formula is as follows:

[0040]

[0041] , where C qp is the resource conflict intensity, which indicates the degree of resource-level conflict between scheduled task q and scheduled task p in the scheduling system, h is the total number of resources used by the scheduling tasks, and δ qk and δ pk is a binary variable, indicating whether resource k is used by scheduled task q or scheduled task p, T qk is the actual time interval of resource k occupied by the scheduling task q, T pk They represent the actual occupancy time interval of the scheduled task p on the resource k, and γ is the conflict penalty index;

[0042] After completing the quantification of task priority and resource conflict intensity, each scheduling task is scored fusion-wise to comprehensively judge the rationality of its execution and the cost of resource scheduling. The scheduling fusion scoring function is introduced, and the formula is as follows:

[0043]

[0044] , where S q represents the final scheduling score of task q, β qp It is the conflict influencing factor.

[0045] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0046] The present invention can effectively identify and resolve resource conflicts between dispatch instructions in a multi-department concurrent dispatch environment through unified access, standardized processing and characterization modeling of multi-source dispatch instructions, combined with the intelligent identification of conflict risks and dynamic arbitration mechanism of machine learning models, to avoid task failure and resource waste caused by repeated allocation or dispatch interference; at the same time, by introducing a short-delay arbitration window to achieve flexible control and priority allocation of dispatch instructions, limited emergency vehicle resources can be dynamically reorganized and optimally allocated according to the urgency of the task and the scope of influence, thereby significantly improving the continuity of material distribution, dispatch stability and overall collaborative efficiency during the emergency response process. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction to the drawings required for use in the embodiments will be given below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0048] Figure 1 This is a flow chart of a method for dispatching emergency material distribution vehicles based on collaborative assurance according to the present invention. DETAILED DESCRIPTION

[0049] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of this disclosure will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art.

[0050] The present invention provides Figure 1 The method for dispatching emergency material distribution vehicles based on collaborative support shown in FIG. includes the following steps:

[0051] Unify instructions from different platforms into a centralized scheduling system, collect and aggregate scheduling requests and resource information from various departments;

[0052] Unifying the access of instructions from different platforms to a centrally managed dispatching system means that all dispatching instructions issued by multiple functional agencies (such as emergency management bureaus, transportation departments, medical institutions, storage centers, etc.) through their respective business systems or platforms are aggregated into a unified dispatching system for centralized management and processing. Since the platforms and instruction formats used by various departments are often different, if unified access is not performed, it is easy to cause information fragmentation, instruction omissions, or conflicts that are difficult to identify. Through unified access, it is possible to achieve centralized aggregation and comprehensive control of various dispatching requests and resource status (such as vehicle location, material type, task progress, etc.), ensuring that the dispatching system has a complete information foundation when facing multi-source tasks, which is helpful for subsequent standardized processing, conflict detection and intelligent deployment, thereby improving the coordination of emergency response and overall dispatching efficiency.

[0053] The following key steps are involved in integrating instructions from different platforms into a centrally managed dispatch system: First, an interface module that supports access to multiple data sources is built, enabling each functional agency to send dispatch instructions to a unified platform through API calls, data subscriptions, and message buses; second, corresponding conversion rules and field mapping relationships are established for each agency's instruction format, converting the instruction content (such as task number, dispatch object, destination, time requirements, etc.) in different systems into a unified standard data model; then, all dispatch instructions that have been connected and standardized are unified into the dispatch system's core instruction center and associated with the vehicle, material, and personnel resource databases to form a complete task-resource association view. Through this process, the structured integration and centralized management of cross-departmental dispatch information are achieved, providing a reliable data foundation for the system's subsequent dispatch analysis, task coordination, and intelligent optimization.

[0054] Perform standardized parsing and preprocessing on the acquired scheduling requests and resource information, including field unification, format conversion, outlier removal, and missing information completion. All processed valid scheduling information is stored in a unified data set according to the established data structure to support subsequent feature extraction and intelligent analysis.

[0055] Dispatch instruction formats from different organizations often differ, including in data structure, field naming, and encoding methods. This can easily lead to mismatches or missing information during subsequent analysis. Therefore, it's necessary to pre-define unified field mapping and parsing rules for each organization's instruction structure to convert dispatch information into a common data format across the system. For example, this includes standardizing vehicle IDs, task priority fields, and required material type codes. This standardized parsing ensures that subsequent processing can understand and compare dispatch requirements from various organizations at the same semantic level.

[0056] After completing standardized parsing, the parsed dispatch information requires further preprocessing, including deduplication, error correction, data padding, and timestamp alignment. This preprocessing can filter out poor-quality or obviously erroneous dispatch records and infer missing fields to make the data more complete and reliable. Subsequently, all valid dispatch information is stored in a data set according to a predefined structure, providing a high-quality, highly consistent basic data source for subsequent feature extraction.

[0057] Through feature engineering technology, key indicators reflecting potential resource conflicts between scheduling tasks are extracted from the constructed data set, and a multi-dimensional comprehensive analysis is performed on the extracted key indicators to quantify the potential conflict status of the current scheduling tasks;

[0058] Through feature engineering technology, key indicators reflecting potential resource conflicts between scheduling tasks are extracted from the constructed data set. The extracted key indicators include the probability that different agencies issue the same scheduling target for the same resource category and the clarity of the boundary division between scheduling tasks of multiple functional agencies. The probability that different agencies issue the same scheduling target for the same resource category and the clarity of the boundary division between scheduling tasks of multiple functional agencies are analyzed under the detection window to generate organizational command convergence reference value and scheduling domain boundary fuzzy reference value respectively. The potential conflict status in the current scheduling task is quantified by the organizational command convergence reference value and scheduling domain boundary fuzzy reference value.

[0059] The greater the probability that the same organization issues identical or highly similar dispatch targets for the same resource category, the greater the potential for resource conflicts between dispatch tasks. This phenomenon reflects the tendency of multiple independent command sources, without sufficient coordination, to simultaneously request the same type of critical resources (e.g., the same type of vehicle, material, route, or destination), leading to an increased concentration of resource requests at the system level. Once resource availability is insufficient or the dispatch response mechanism lags, resource competition, task preemption, and duplicate dispatching can arise, leading to a series of scheduling disruptions such as duplicate vehicle assignments, task overlaps, and route conflicts. Especially in emergency response scenarios, where resources are limited and time is tight, this type of "command convergence" can easily lead to increased load on the dispatch system and imbalanced dispatch. Therefore, analyzing the degree of convergence between dispatch commands from different organizations in terms of target resources, time, and region can effectively provide early warning of potential scheduling conflicts and provide key judgment basis for subsequent conflict resolution and task integration.

[0060] The specific steps for analyzing the probability of different organizations issuing the same scheduling target for the same resource category within the detection window to generate a reference value for organizational command convergence are as follows:

[0061] First, the dispatch targets of different agencies are grouped by resource category (e.g., ambulances, cold chain vehicles, unmanned transport equipment, etc.). For each resource category, a set of dispatch targets for each agency is constructed, where the targets can be specific mission points, routes, material delivery points, etc. Next, an intersection intensity ratio index is generated for the dispatch target sets of all agencies. This index represents the degree of overlap of dispatch targets between multiple agencies under the same resource category. The generation formula is as follows:

[0062]

[0063] , where ISR is the intersection intensity ratio index, which is used to measure the degree of actual overlap between the scheduling objectives of multiple agencies under resource category R, G i and G j are the scheduling target sets issued by the i-th and j-th scheduling agencies for resource categories within the detection window, and n is the total number of agencies participating in the scheduling;

[0064] The above steps quantify the strength of target consistency across multiple sources by identifying the degree of overlap in the scheduling objectives of different organizations within the same resource category. By calculating the intersection strength ratio between sets of scheduling objectives, this provides a key structured indicator for determining potential scheduling conflicts.

[0065] To further enhance the model's sensitivity to the trend of target consistency, a discrete structure convergence function is introduced to measure the tension between the distribution discreteness of the overall scheduling target and the instruction concentration, and the final organizational command convergence reference value is constructed as follows:

[0066]

[0067] , where OCC-RV is the organizational command convergence reference value, U R The number of unique scheduling targets, which represents the total number of unique targets obtained after all organization scheduling target sets are merged and duplicates are removed under the resource category.

[0068] The number of unique scheduling targets U R The function of U is to measure the overall distribution range and dispersion of the dispatching task targets of different agencies within the detection window under a certain resource category. It represents the total number of target points (such as destinations, material receiving points, service areas, etc.) in the dispatch instructions of all agencies after duplication. The key significance of this indicator is: when U R A small value indicates that each agency concentrates on scheduling a few targets, which leads to the risk of high concentration and task overlap, and a high possibility of scheduling conflict. R A larger value indicates that the scheduling task objectives are widely distributed and resource usage is decentralized. Even if there is local target overlap, it is more likely to be accidental overlap rather than systematic conflict. R As a regulating factor in the organizational command convergence index, it can effectively suppress the "conflict risk amplification" caused by too few targets, or prevent the phenomenon of "misjudgment as conflict" when the number of targets is too large, thereby enhancing the judgment accuracy and stability of the scheduling system in the conflict identification process.

[0069] The above steps couple the degree of overlap among multiple organizations' dispatch objectives with the complexity of the overall target distribution, generating a reference value for organizational command convergence that accurately reflects the centralization trend of dispatch orders. This reference value not only identifies whether dispatch objectives are converging, but also automatically adjusts sensitivity based on target diversity, avoiding the risk of misjudgment of conflicts due to a large number of targets.

[0070] The larger the organizational command convergence reference value, generated by analyzing the probability of different organizations issuing the same scheduling objectives for the same resource category within a detection window, the greater the overlap in scheduling instructions between different organizations in terms of time, space, or task content. This highly convergent scheduling behavior means that multiple tasks are likely to compete for the same resources, significantly increasing the risk of resource conflicts between scheduled tasks. Conversely, a lower organizational command convergence reference value indicates greater disparity in scheduling instructions in terms of resource type, scheduling objectives, and time windows, resulting in less overlap in resource usage between tasks and a lower likelihood of conflict.

[0071] The unclear demarcation of dispatch tasks across multiple functional agencies is indeed a key manifestation of potential resource conflicts between dispatch tasks. Unclear dispatch boundaries primarily manifest as a lack of clear demarcation between different agencies regarding dispatch objectives, resource usage scope, and spatial and temporal coverage areas. This can lead to overlapping instructions, duplicate resource allocation, or overlapping responsibilities during task execution. For example, if the medical and transportation departments simultaneously dispatch the same fleet of vehicles for different tasks without sharing their respective dispatch intentions and resource allocation information, they may issue conflicting instructions to the same vehicles, causing execution confusion or mission failure. This fuzzy boundary often means that the system lacks the ability to determine command ownership and a unique resource allocation mechanism when receiving dispatch instructions, thus laying the groundwork for potential dispatch conflicts. Particularly in high-intensity emergency response scenarios, unclear boundaries directly impact the accuracy and timeliness of resource allocation and serve as a key signal for identifying the risk of dispatch task conflicts.

[0072] The specific steps for analyzing the clarity of the boundaries between the scheduling tasks of multiple functional agencies under the detection window to generate the fuzzy reference value of the scheduling domain boundary are as follows:

[0073] The scheduling tasks issued by multiple functional agencies within a certain detection window are constructed into a task scheduling domain intersection graph (TOG), where each node represents a scheduling task, and the edge indicates the duplication relationship between scheduling tasks in the target area. Then, the intersection index of each scheduling task is calculated to measure the degree of duplication between the task and other tasks. The calculation expression is as follows:

[0074] The formula is as follows:

[0075]

[0076] , CI q is the cross-index of the scheduled task q, which indicates the intensity of resource overlap between the scheduled task q and other tasks in the current detection window. q and R p They are the resource sets of scheduling task q and scheduling task p, which represent the resource object set called by each scheduling task, including vehicle number, driver ID, warehouse number, road segment number, etc., δ(g q , g p ) is the functional agency difference function, which is used to determine whether two tasks come from different functional agencies. q and g p They represent the organization identifiers of scheduled tasks q and p respectively; Γ(q) is the set of tasks that have resource intersection with task q;

[0077] In constructing a cross-graph of dispatching tasks, a node represents each independent dispatching task in the system. These tasks are typically initiated by different functional departments and contain information such as task objectives, resource requirements, dispatching time windows, and service areas. Each node, as a basic unit in the graph, carries the "physical information" of the task itself. For example, a task transporting medical supplies is a node, while another task dispatching similar vehicles to transport patients to a disaster area is another node. By representing tasks as nodes, the distribution and scale of dispatching activities can be clearly identified within the graph structure.

[0078] An edge represents a "relationship link" between two scheduled tasks. Specifically, in this scenario, this refers to overlapping resources or target areas. If two tasks utilize the same fleet of vehicles, dispatch to the same warehouse, or have overlapping service areas, an edge is established between their corresponding nodes. The presence of an edge indicates that these tasks may interfere with each other or compete for resources during execution, serving as a key signal of potential conflict. By constructing these edges, isolated task nodes can be connected into a complex relationship network, facilitating the subsequent calculation of task overlap and the degree of scheduling conflict.

[0079] This step identifies the degree of resource overlap between tasks across multiple functional agencies and filters the "natural overlap" of scheduling within the same agency using heterogeneous agency factors. This allows for highly sensitive detection of weak signals of cross-agency resource conflicts, generating a task-level structural cross-index. This provides a "node perspective" for subsequent global assessments of boundary ambiguity.

[0080] After obtaining the cross-indices of all tasks, we further extract the degree of boundary fuzziness of the scheduling domain at the global level and generate a scheduling domain boundary fuzziness reference value to quantify the "instruction overlap chaos" of the overall scheduling domain. The generation formula is as follows:

[0081]

[0082] , where DDBF-RV is the fuzzy reference value of the scheduling domain boundary, Φ is the set of cross-indexes of all tasks, Φ={CI q}={CI1,CI2,……,CI m}, m is the total number of all scheduling tasks issued by multiple functional agencies within the current detection window, max(Φ) is the maximum value of the cross-index of all scheduling tasks, and the most serious resource conflict task is found. n is the total number of agencies involved in scheduling, D split It is the degree of splitting of the scheduling responsibility domain, which indicates the number of tasks from different functional agencies that simultaneously schedule the same resource category (such as similar vehicles, warehouses, access routes, etc.).

[0083] By integrating the maximum cross-task index with the degree of fragmentation in multi-agency resource scheduling, this method comprehensively quantifies the degree of ambiguity in scheduling task boundaries across the entire scheduling system. It can accurately identify high-risk conflict areas within the scheduling domain caused by overlapping responsibilities or chaotic resource allocation between agencies, thereby providing effective early warning and support for optimizing scheduling strategies.

[0084] The larger the scheduling domain boundary fuzzy reference value generated by analyzing the clarity of the boundary divisions between the scheduling tasks of multiple functional agencies under the detection window, the higher the degree of responsibilities overlap or resource coverage overlaps between the tasks of different agencies, the poorer the independence between scheduling tasks, and the more likely it is that the same resource is repeatedly called or that the scheduling goals of multiple parties conflict, thereby causing potential resource conflicts; on the contrary, when the reference value is smaller, it means that the scheduling task boundaries are clear, the responsibilities are clear, the tasks do not interfere with each other, and the scheduling resource allocation is more orderly. Therefore, it can be considered that there is no significant resource conflict risk between tasks.

[0085] The quantified key scheduling conflict indicators are used as feature vectors and input into a pre-trained machine learning model. The machine learning model then performs an intelligent assessment of the conflict risk of the current scheduling task to determine whether there is a conflict risk.

[0086] The quantified organizational command convergence reference value and the scheduling domain boundary fuzzy reference value are used as feature vectors and input into the pre-trained machine learning model. The scheduling task conflict risk coefficient is generated by the machine learning model. The conflict risk of the current scheduling task is intelligently evaluated based on the scheduling task conflict risk coefficient to determine whether the current scheduling task has a conflict risk.

[0087] A "pre-trained machine learning model" means that before the current scheduling system is officially put into operation, the model has been fully trained and optimized based on historical data, so that it has the ability to accurately judge and predict input features. In this system, the training phase usually uses a large number of past scheduling instructions, resource status and conflict result samples to construct a training set, and through supervised learning, the task features are matched one-to-one with the actual results of whether a conflict occurs, and input into the machine learning algorithm for learning. During the training process, the model will automatically identify the complex relationship between features and conflicts, and form an internal parameter structure (such as decision tree structure, weight matrix, neural network connection weights, etc.), so that it has the ability to perform "analogy reasoning" and risk assessment on new scheduling tasks. The training process also includes steps such as cross-validation, model evaluation and tuning to ensure that the model has good generalization capabilities and can adapt to scheduling conflict identification in different scenarios in the future.

[0088] The key to "pre-training" is that it eliminates the need for complex data modeling or manual rule-based judgment when faced with new scheduling tasks in real time. Instead, the system can quickly and automatically perform intelligent conflict risk assessments. In this system, the organizational command convergence index and the scheduling domain boundary fuzziness index are two key input features that reflect potential conflicts within scheduling instructions at the organizational and spatial management levels. When these metrics are fed into the trained model, the model, based on its learned knowledge, makes a quantitative assessment of the potential conflict risk of the current task and outputs a scheduling conflict risk coefficient. This risk coefficient serves as a core decision-making factor before scheduling execution, determining whether to enter the arbitration window, whether task fusion or priority adjustment is necessary, and other factors. Compared to traditional rule engines based on manually set thresholds, pre-trained models offer greater adaptability and judgment accuracy. This significantly improves the system's intelligence and actual scheduling efficiency, particularly in emergency scheduling scenarios where multivariate interactions are complex and conflict characteristics are difficult to explicitly express.

[0089] The machine learning model is not limited here. Any machine learning model that can perform a comprehensive analysis of the organization command convergence reference value OCC-RV and the scheduling domain boundary fuzzy reference value DDBF-RV to generate a scheduling task conflict risk coefficient DCRC can be used. In order to realize the technical solution of the present invention, the present invention provides a specific implementation method.

[0090] The scheduling task conflict risk coefficient DCRC is generated by the following formula: DCRC = δ1·OCC-RV+δ2·DDBF-RV, where δ1 and δ2 are the preset proportional coefficients of the organization command convergence reference value OCC-RV and the scheduling domain boundary fuzzy reference value DDBF-RV, respectively, and both δ1 and δ2 are greater than 0.

[0091] The "preset proportional coefficient" (i.e., δ1 and δ2 in the formula) refers to a set of weight parameters set a priori by the system or humans when evaluating the conflict risk of scheduling tasks. It is used to reflect the relative influence of different reference values such as the organizational command convergence reference value OCC-RV and the scheduling domain boundary fuzzy reference value DDBF-RV on the overall conflict risk coefficient DCRC.

[0092] Specifically, δ1 represents the weight of the impact of the degree of convergence of organizational commands on conflict risk in the overall risk assessment, while δ2 represents the weight of the impact of the degree of ambiguity in the scheduling domain boundary on the conflict risk. By assigning different proportional coefficients to these two key indicators, the system's sensitivity to different sources of conflict can be flexibly adjusted, thereby adapting to scheduling strategies in different scenarios. For example, in large-scale scheduling involving multiple agencies at the same time, more attention may be paid to the weight of OCC-RV (larger δ1); while in cross-regional joint scheduling, more attention may be paid to the risks brought about by ambiguous regional boundaries (larger δ2). Therefore, the preset proportional coefficient not only reflects the model designer's understanding and preference of risk sources, but also provides an adjustable intelligent assessment strategy for the scheduling system.

[0093] It can be seen from the scheduling task conflict risk coefficient that the larger the organizational command convergence reference value generated after analyzing the probability of different agencies issuing the same scheduling target for the same resource category under the detection window, and the larger the scheduling domain boundary fuzzy reference value generated after analyzing the clarity of the boundary division between the scheduling tasks of multiple functional agencies under the detection window, the larger the scheduling task conflict risk coefficient generated when the conflict risk of the current scheduling task is intelligently evaluated by the pre-trained machine learning model, indicating that the probability of the current scheduling task having a conflict risk is greater, and vice versa, the smaller the probability of the current scheduling task having a conflict risk.

[0094] The scheduling task conflict risk coefficient generated by the pre-trained machine learning model when performing intelligent assessment of the conflict risk of the current scheduling task is compared with the pre-set scheduling task conflict risk coefficient reference threshold to determine whether the current scheduling task has a conflict risk. The judgment logic is as follows:

[0095] If the scheduling task conflict risk coefficient is greater than the preset scheduling task conflict risk coefficient reference threshold, it is judged that there is a conflict risk between the scheduling tasks; if the scheduling task conflict risk coefficient is less than or equal to the preset scheduling task conflict risk coefficient reference threshold, it is judged that there is no conflict risk between the scheduling tasks.

[0096] When the machine learning model determines that there is a risk of conflict between multiple scheduling tasks, it will not execute all scheduling instructions and enter a short-delay arbitration window. Within the arbitration window, it will dynamically evaluate the urgency, impact scope, and vehicle resource occupancy status of each scheduling task. Based on the preset task priority and scheduling impact factors, it will perform real-time conflict resolution and task fusion processing to achieve optimal allocation and efficient scheduling of limited resources.

[0097] When the machine learning model identifies a resource conflict risk between multiple dispatch tasks, the system does not immediately execute these dispatch instructions. Instead, it enters a short "arbitration window." This provides the dispatch system with a highly real-time decision buffer, preventing issues such as duplicate vehicle resource usage, overlapping instructions, or transportation route conflicts caused by concurrent conflicts. Within this arbitration window, the system dynamically assesses the urgency of each dispatch instruction (e.g., task response time, level of urgency in the disaster area), impact area (e.g., population affected, supply radius), and current vehicle resource occupancy (e.g., availability, active, or in a maintenance cooldown period). These assessment results are then integrated with pre-set task priority levels and scheduling impact factors to calculate a comprehensive dispatch priority index for each task. Based on this index, the system performs conflict resolution operations, such as selecting the optimal task for execution, merging tasks (e.g., route merging, batch delivery), or delaying resource allocation for lower-priority tasks. The core function of this step is to ensure that in emergency scenarios with multiple sources concurrent and resources constrained, the dispatching system can make decisions without blindly deciding and miss high-priority tasks, and truly achieve "allocation on demand and execution on efficiency" for limited resources, significantly improving the dispatching intelligence level and response efficiency of the entire emergency logistics system.

[0098] When the machine learning model determines that there is a risk of conflict between multiple scheduling tasks, it will not execute all scheduling instructions and enter a short-delay arbitration window. Within the arbitration window, it will dynamically evaluate the urgency, impact scope, and vehicle resource occupancy status of each scheduling task. Based on the preset task priority and scheduling impact factors, it will perform real-time conflict resolution and task fusion processing to achieve optimal allocation and efficient scheduling of limited resources. The specific steps are as follows:

[0099] When resource conflicts are detected among multiple scheduled tasks, an arbitration window is entered to quantify the priorities of all conflicting tasks. To more comprehensively evaluate the urgency of task execution and scheduling value, a priority scoring function is constructed by comprehensively considering the urgency of the task, the remaining schedulable time, and the scope of its impact in the disaster. The formula is as follows:

[0100]

[0101] , where P q is the task priority score, which indicates the final priority score of task q and is the core reference value for comparing the priorities of multiple conflicting tasks. q is the task urgency coefficient, which is used to measure the urgency of the task, such as whether it is related to life safety, public health, infrastructure, etc. q Is the remaining schedulable time of the task, which represents the remaining time between the current system time and the time when the task must be completed. qis the task impact range index, which indicates the number of affected people, geographical scope, and material coverage of the task. λ is the time compression adjustment factor, a nonlinear adjustment parameter used to increase the sensitivity to tasks approaching deadlines. α1, α2, and α3 are the task urgency coefficients U, respectively. q , the remaining schedulable time of the task D q And the task impact range index I q The weight coefficient is α1+α2+α3=1;

[0102] The above steps quantify the scheduling urgency and importance of conflicting tasks, helping the system identify the tasks that require the most immediate response. By introducing multi-dimensional metrics to build a priority scoring model, we can uniformly measure task urgency, remaining time, and impact, providing a basis for decision-making in subsequent conflict resolution.

[0103] After the priority calculation is completed, the degree of competition between tasks at the resource level is evaluated. Focus on the conflict risk when the same resource is called by multiple tasks at the same time. By combining the resource usage flag and the time overlap ratio, a resource conflict intensity model between tasks is constructed. The formula is as follows:

[0104]

[0105] , where C qp is the resource conflict intensity, which indicates the degree of resource-level conflict between scheduled task q and scheduled task p in the scheduling system, h is the total number of resources used by the scheduling tasks, and δ qk and δ pk is a binary variable, indicating whether resource k is used by scheduled task q or scheduled task p, T qk is the actual time interval of resource k occupied by the scheduling task q, T pk They represent the actual time interval of resource k occupied by scheduled task p, and γ is the conflict penalty index, which is used to amplify the conflict risk caused by the larger overlap time;

[0106] The above steps calculate the degree of resource overlap among scheduled tasks, revealing the potential scheduling interference caused by shared resources. By constructing a resource conflict tensor, the system can quantify the scheduling conflict risk across resources, laying the foundation for rational resource allocation.

[0107] After completing the quantification of task priority and resource conflict intensity, each scheduling task is scored fusion-wise to comprehensively judge the rationality of its execution and the cost of resource scheduling. The scheduling fusion scoring function is introduced, and the formula is as follows:

[0108]

[0109] , where S qrepresents the final scheduling score of task q, β qp It is a conflict influencing factor, which is set based on factors such as the level difference and urgency difference between tasks, and is used to adjust different conflicting tasks.

[0110] The above steps are used to combine task priorities with resource conflict intensity to calculate the final scheduling execution score for each task. Based on this score, the system can determine the execution order of tasks, possible fusion, or delay handling strategies, thereby achieving optimal scheduling decisions in conflict environments.

[0111] The present invention can effectively identify and resolve resource conflicts between dispatch instructions in a multi-department concurrent dispatch environment through unified access, standardized processing and characterization modeling of multi-source dispatch instructions, combined with the intelligent identification of conflict risks and dynamic arbitration mechanism of machine learning models, to avoid task failure and resource waste caused by repeated allocation or dispatch interference; at the same time, by introducing a short-delay arbitration window to achieve flexible control and priority allocation of dispatch instructions, limited emergency vehicle resources can be dynamically reorganized and optimally allocated according to the urgency of the task and the scope of influence, thereby significantly improving the continuity of material distribution, dispatch stability and overall collaborative efficiency during the emergency response process.

[0112] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0113] The above description is merely illustrative of certain exemplary embodiments of the present invention. It goes without saying that those skilled in the art will be able to modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and description are illustrative in nature and should not be construed as limiting the scope of protection of the claims.

[0114] It should be noted that, in this document, if there are relational terms such as first and second, etc., they are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "comprises", "comprising" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or device that includes the element.

[0115] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0116] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0117] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0118] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0119] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0120] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0121] The above description is merely illustrative of certain exemplary embodiments of the present invention. It goes without saying that those skilled in the art will be able to modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and description are illustrative in nature and should not be construed as limiting the scope of protection of the claims.

Claims

1. A method for dispatching emergency material distribution vehicles based on collaborative support, characterized in that: The following steps are involved: Unify instructions from different platforms into a centralized scheduling system, collect and aggregate scheduling requests and resource information from various departments; Perform standardized parsing and preprocessing on the acquired scheduling requests and resource information, and store all processed valid scheduling information into a unified data set according to the established data structure to support subsequent feature extraction and intelligent analysis; Through feature engineering technology, key indicators reflecting potential resource conflicts between scheduling tasks are extracted from the constructed data set, and a multi-dimensional comprehensive analysis is performed on the extracted key indicators to quantify the potential conflict status of the current scheduling tasks; The quantified key scheduling conflict indicators are used as feature vectors and input into a pre-trained machine learning model. The machine learning model then performs an intelligent assessment of the conflict risk of the current scheduling task to determine whether there is a conflict risk. When the machine learning model determines that there is a risk of conflict between multiple scheduling tasks, it will not execute all scheduling instructions and enter a short-delay arbitration window. Within the arbitration window, it will dynamically evaluate the urgency, impact scope and vehicle resource occupancy status of each scheduling task, and perform real-time conflict resolution and task fusion processing based on preset task priorities and scheduling impact factors to achieve optimal allocation and efficient scheduling of limited resources.

2. The method for dispatching emergency material distribution vehicles based on collaborative support according to claim 1, characterized in that: Unifying instructions from different platforms into a centralized dispatch system involves the following key steps: First, an interface module that supports access to multiple data sources was built, enabling each functional department to send scheduling instructions to a unified platform through API calls, data subscriptions, and message buses. Secondly, corresponding conversion rules and field mapping relationships are established for the instruction formats of each institution, converting the instruction content in different systems into a unified standard data model; Then, all the dispatching instructions that have been connected and standardized are unified into the core command center of the dispatching system and linked with the vehicle, material, and personnel resource database to form a complete task-resource association view.

3. The method for dispatching emergency material distribution vehicles based on collaborative support according to claim 1, characterized in that: Through feature engineering technology, key indicators reflecting potential resource conflicts between scheduling tasks are extracted from the constructed data set. The extracted key indicators include the probability that different agencies issue the same scheduling target for the same resource category and the clarity of the boundary division between scheduling tasks of multiple functional agencies. The probability that different agencies issue the same scheduling target for the same resource category and the clarity of the boundary division between scheduling tasks of multiple functional agencies are analyzed under the detection window to generate organizational command convergence reference value and scheduling domain boundary fuzzy reference value respectively. The potential conflict status in the current scheduling task is quantified by the organizational command convergence reference value and scheduling domain boundary fuzzy reference value.

4. The method for dispatching emergency material distribution vehicles based on collaborative support according to claim 3 is characterized in that: The specific steps for analyzing the probability of different organizations issuing the same scheduling target for the same resource category within the detection window to generate a reference value for organizational command convergence are as follows: First, the scheduling objectives of different institutions are grouped by resource category. For each resource category, a scheduling objective set for each institution is constructed. Then, the intersection intensity ratio index of all institution scheduling objective sets is generated to indicate the degree of overlap of scheduling objectives between multiple institutions under the same resource category. The generation formula is as follows: ， Where ISR is the intersection intensity ratio index, G i and G j are the scheduling target sets issued by the i-th and j-th scheduling agencies for resource categories within the detection window, and n is the total number of agencies participating in the scheduling; To further enhance the model's sensitivity to the trend of target consistency, a discrete structure convergence function is introduced to measure the tension between the distribution discreteness of the overall scheduling target and the instruction concentration, and the final organizational command convergence reference value is constructed as follows: ， Where, OCC-RV is the organizational command convergence reference value, U R is the number of unique scheduling targets.

5. The method for dispatching emergency material distribution vehicles based on collaborative support according to claim 3, characterized in that: The specific steps for analyzing the clarity of the boundaries between the scheduling tasks of multiple functional agencies under the detection window to generate the fuzzy reference value of the scheduling domain boundary are as follows: The scheduling tasks issued by multiple functional agencies within a certain detection window are constructed into a task scheduling domain intersection graph, where each node represents a scheduling task, and the edge represents the duplication relationship of the target area between scheduling tasks. Then, the intersection index of each scheduling task is calculated. The calculation expression is as follows: The formula is as follows: ， CI q is the cross-index of the scheduled task q, R q and R p They are the resource sets of scheduling task q and scheduling task p, δ(g q , g p ) is the functional agency difference function, which is used to determine whether two tasks come from different functional agencies. q and g p Respectively represent the organization identifiers of the scheduling task q and the scheduling task p; Γ( q ) is a set of tasks that have resource intersection with task q; After obtaining the cross-indices of all tasks, we further extract the degree of boundary fuzziness of the scheduling domain at the global level and generate a scheduling domain boundary fuzziness reference value to quantify the "instruction overlap chaos" of the entire scheduling domain. The generation formula is as follows: ， Where DDBF-RV is the fuzzy reference value of the scheduling domain boundary, Φ is the set of cross-indexes of all tasks, Φ = {CI q }={CI1,CI2,……,CI m }, m is the total number of all scheduling tasks issued by multiple functional agencies within the current detection window, max(Φ) is the maximum value of the cross-index of all scheduling tasks, and the most serious resource conflict task is found. n is the total number of agencies involved in scheduling, D split It is the degree of splitting of the scheduling responsibility domain.

6. The method for dispatching emergency material distribution vehicles based on collaborative support according to claim 3, characterized in that: The quantified organizational command convergence reference value and the scheduling domain boundary fuzzy reference value are used as feature vectors and input into the pre-trained machine learning model. The scheduling task conflict risk coefficient is generated by the machine learning model. The conflict risk of the current scheduling task is intelligently evaluated based on the scheduling task conflict risk coefficient to determine whether the current scheduling task has a conflict risk.

7. The method for dispatching emergency material distribution vehicles based on collaborative support according to claim 6, characterized in that: The scheduling task conflict risk coefficient generated by the pre-trained machine learning model when performing intelligent assessment of the conflict risk of the current scheduling task is compared with the pre-set scheduling task conflict risk coefficient reference threshold to determine whether the current scheduling task has a conflict risk. The judgment logic is as follows: If the scheduling task conflict risk coefficient is greater than the preset scheduling task conflict risk coefficient reference threshold, it is judged that there is a conflict risk between the scheduling tasks; if the scheduling task conflict risk coefficient is less than or equal to the preset scheduling task conflict risk coefficient reference threshold, it is judged that there is no conflict risk between the scheduling tasks.

8. The method for dispatching emergency material distribution vehicles based on collaborative support according to claim 7, characterized in that: When the machine learning model determines that there is a risk of conflict between multiple scheduling tasks, it will not execute all scheduling instructions and enter a short-delay arbitration window. Within the arbitration window, it will dynamically evaluate the urgency, impact scope, and vehicle resource occupancy status of each scheduling task. Based on the preset task priority and scheduling impact factors, it will perform real-time conflict resolution and task fusion processing to achieve optimal allocation and efficient scheduling of limited resources. The specific steps are as follows: When resource conflicts are detected among multiple scheduled tasks, an arbitration window is entered to quantify the priorities of all conflicting tasks. To more comprehensively evaluate the urgency of task execution and scheduling value, a priority scoring function is constructed by comprehensively considering the urgency of the task, the remaining schedulable time, and the scope of its impact in the disaster. The formula is as follows: ， Where, P q is the task priority score, U q is the task urgency coefficient, which is used to measure the urgency of task execution. q is the remaining schedulable time of the task, I q is the task impact range index, λ is the time compression adjustment factor, α1, α2 and α3 are the task urgency coefficients U q , the remaining schedulable time of the task D q And the task impact range index I q The weight coefficient is α1+α2+α3=1; After the priority calculation is completed, the degree of competition between tasks at the resource level is evaluated. Focus on the conflict risk when the same resource is called by multiple tasks at the same time. By combining the resource usage flag and the time overlap ratio, a resource conflict intensity model between tasks is constructed. The formula is as follows: ， Where C qp is the resource conflict intensity, which indicates the degree of resource-level conflict between scheduled task q and scheduled task p in the scheduling system, h is the total number of resources used by the scheduling tasks, and δ qk and δ pk is a binary variable, indicating whether resource k is used by scheduled task q or scheduled task p, T qk is the actual time interval of resource k occupied by the scheduling task q, T pk They represent the actual occupancy time interval of the scheduled task p on the resource k, and γ is the conflict penalty index; After completing the quantification of task priority and resource conflict intensity, each scheduling task is scored fusion-wise to comprehensively judge the rationality of its execution and the cost of resource scheduling. The scheduling fusion scoring function is introduced, and the formula is as follows: ， Where S q represents the final scheduling score of task q, β qp It is the conflict influencing factor.

Images