A multi-region operation resource parameterization constraint allocation system and method, electronic equipment and storage medium

Abstract

The present application relates to the technical field of multi-region operation resource configuration and intelligent decision system, and provides a multi-region operation resource parameterization constraint allocation system and method, an electronic device and a storage medium.The method obtains state data and resource constraints of each operation region, generates region characteristics and calculates a yield index to form a yield index vector; a feasible region is constructed according to the resource constraints and the yield index; the region characteristics, the yield index and the feasible region are input into a strategy model to output three-dimensional low-dimensional control quantities, and configuration weights are obtained after mapping three types of proportion parameters; in combination with an unreachable mask, a configuration upper limit, capacity normalization and minimum guarantee supplement, resource configuration results are obtained through constraint projection and guarantee verification; when the guarantee verification is passed, execution is issued; when the guarantee verification is not passed, supplementary redistribution or a resource deficiency identifier is output, and execution feedback is received for next cycle updating.The present application can reduce the output dimension and reasoning calculation amount of the strategy model, and improve the task guarantee yield and facility recovery effect.

Description

Technical Field

[0001] This invention relates to the field of multi-regional operation resource allocation and intelligent decision-making system technology, specifically to a multi-regional operation resource parameterized constraint allocation system and method, electronic device and storage medium. Background Technology

[0002] In emergency repair, inspection and maintenance, and facility support scenarios, the work objects are usually distributed in multiple work area nodes with varying numbers. The system needs to generate executable regional work resource configuration results based on regional work status data and work resource constraint data within a continuous work resource configuration cycle.

[0003] The above scenario is characterized by a large number of nodes in the work area, dynamic changes in status, limited resource types and capacity, unreachability of some nodes, and the coexistence of minimum task requirements. Work resources include work equipment, work vehicles, work personnel, materials, computing resources, drones, or sensors.

[0004] Existing solutions typically use the configuration quantity of nodes in each work area as the direct output of the work resource configuration strategy model. As the number of nodes in the work area increases, the output dimension, the number of model parameters, and the amount of inference computation also increase. At the same time, constraints such as node reachability, resource type capacity, upper limit of regional configuration, minimum guarantee of tasks, and quantification of discrete work units are handled in a scattered manner, making it difficult to stably transform the regional work resource configuration results into field work instructions that can be issued, executed, and updated.

[0005] Therefore, a technical solution is needed that integrates with a multi-regional operation resource allocation system to unify the processing of regional operation status data collection, operation resource constraint data update, revenue indicator calculation, parameterized allocation, constraint projection, configuration distribution, and execution feedback. This would reduce the output dimension of the operation resource allocation strategy model and generate regional operation resource allocation results that can be executed at the operation terminal or equipment control end and used for the next cycle update. Summary of the Invention

[0006] To address the problems and shortcomings of existing technologies, the present invention aims to provide a multi-region job resource parameterized constraint allocation system and method, electronic device, and storage medium. This solves the problems in multi-region job resource configuration such as the output dimension increasing with the number of nodes in the job region, dispersed constraint processing, difficulty in distributing configuration results for execution, and insufficient state feedback updates within continuous cycles.

[0007] The technical solution adopted in this invention is as follows:

[0008] In a first aspect, the present invention provides a method for parameterized constraint allocation of multi-regional operational resources, comprising the following steps:

[0009] S1. In a multi-region operation scenario, obtain the region operation status data and operation resource constraint data of the set of regions to be configured, which contains multiple operation region nodes;

[0010] S2. Generate regional status features or regional map coding features based on regional operation status data, and apply this to all operation region nodes in the set of regions to be configured. Unified calculation of non-negative return indicators To form a vector of revenue indicators ;

[0011] S3. Construct a feasible domain for operation resource allocation based on operation resource constraint data and revenue index vector. Input the regional state characteristics, revenue index vector and feasible domain for operation resource allocation into the operation resource allocation strategy model and output a three-dimensional low-dimensional control quantity.

[0012] S4. Map the three-dimensional low-dimensional control quantity to the revenue indicator concentration parameter, the revenue indicator threshold ratio parameter and the basic coverage mixing ratio parameter. Then, based on the three types of parameters, perform threshold truncation, focused weight transformation and basic coverage mixing processing on the revenue indicator vectors of all work area nodes in sequence to obtain the regional configuration weight vector.

[0013] S5. Determine the total configurable resources for a single cycle based on the operational resource constraints. Combine the regional configuration weight vector to generate the resource configuration amount for each operational region node. Determine the configuration result through feasible domain constraints, minimum guarantee supplementation, and guarantee verification. When the guarantee verification passes, the data is sent to the corresponding operational control terminal and operational data is collected. If the guarantee verification fails but the resource can be supplemented, supplementation and reallocation are performed. If the resource cannot be supplemented due to total amount, upper limit, or reachability limitations, the resource shortage flag and gap amount are output to provide a basis for the next configuration cycle iteration update.

[0014] Further optimization, in step S2, the calculation of the non-negative return indicator includes:

[0015] Regional revenue items are generated based on the task urgency, regional risk, resource gap, facility value, future demand pressure, and neighboring support capacity of each operational area node. Regional cost items are generated based on transportation costs, maintenance difficulty, resource distance, equipment capacity reduction, and operational risks. The calculation is performed according to the following formula. Non-negative revenue metrics for each work area node:

[0016]

[0017] in, Indicates the first Non-negative revenue indicators for each work area node Indicates the first Regional revenue items for each work area node Indicates the first Regional cost item for each work area node Indicates the zero-prevention threshold. .

[0018] Further optimization is achieved in step 3, where the job resource allocation strategy model is a rule-based model, a neural network model, or a reinforcement learning strategy model. When it contains trainable parameters, it is trained in the job resource allocation simulation environment with the goal of maximizing the cumulative task guarantee benefits and risk reduction benefits over multiple consecutive periods.

[0019] Further optimization is achieved in step 3, where the three-dimensional low-dimensional control quantity is a three-dimensional control quantity independent of the number of nodes in the work area:

[0020]

[0021] in, , and These are the original control values ​​for the concentration of revenue indicators, the threshold ratio of revenue indicators, and the mixed ratio of basic coverage, respectively. , and These are the parameters obtained by performing monotonic compression, interval scaling, and neutral value calibration on the low-dimensional control quantity, respectively.

[0022] Further optimization is achieved in step S4, where the threshold for the revenue indicator is:

[0023]

[0024] in, Indicates the threshold of the profitability indicator. This represents the threshold ratio parameter for the profitability indicator. This represents the maximum value of the revenue indicator vector within the current job resource allocation period; based on the node reachability mask. Profitability threshold and the concentration parameter of returns Generate a weighted vector for the revenue metrics:

[0025]

[0026] in, Indicates the first The focus weight of each work area node, This indicates nonnegative normalization based on the normalized denominator threshold.

[0027] The region configuration weight vector:

[0028]

[0029] in, Indicates the first The regional configuration weight of each work area node This represents the weight of the basic coverage distribution.

[0030] Further optimization is achieved in step S5, where the resource allocation for each work area node is as follows:

[0031]

[0032] in, Indicates the first The amount of continuous resource allocation for each work area node. This indicates the total amount of configurable job resources per cycle.

[0033] Secondly, the present invention provides a multi-regional operational resource parameterized constraint allocation system, characterized in that it includes:

[0034] The data acquisition module is used to acquire regional operation status data and operation resource constraint data of all operation area nodes;

[0035] The status feature generation module is used to generate regional status features or regional map coding features based on regional operation status data.

[0036] The revenue indicator calculation module is used to generate revenue indicator vectors for all nodes in the work area.

[0037] The feasible region constraint module is used to construct the feasible region for job resource configuration based on job resource constraint data and revenue indicator vector;

[0038] The job resource allocation strategy model module is used to output low-dimensional control quantities that are independent of the number of nodes in the job area;

[0039] The parameterized allocation module is used to generate the regional configuration weight vector of all work area nodes based on low-dimensional control variables.

[0040] The constraint projection module is used to uniformly generate regional operation resource allocation results and perform minimum guarantee replenishment, guarantee gap calculation and result verification.

[0041] The configuration distribution and periodic feedback module is used to distribute the regional operation resource configuration results that have passed the guarantee verification to the operation terminal or equipment control terminal; for results that cannot fully meet the minimum guarantee, it sends the resource shortage indicator, gap amount and abnormal confirmation record to the management platform for review, and receives execution feedback for the next operation resource configuration cycle update.

[0042] Further optimization involves the job resource allocation strategy model being one or more of rule-based models, neural network models, and reinforcement learning strategy models. When trainable parameters are included, the model is trained in a job resource allocation simulation environment with the goal of maximizing the cumulative task guarantee benefits and risk reduction benefits over multiple consecutive periods.

[0043] Thirdly, the present invention provides an electronic device, including a processor and a memory, wherein the memory stores a computer program, and the processor executes the computer program to implement any step in a multi-regional job resource parameterized constraint allocation method.

[0044] Fourthly, the present invention provides a computer-readable storage medium storing a computer program, wherein the computer program, when executed by a computer processor, implements any step in a multi-regional job resource parameterized constraint allocation method.

[0045] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0046] 1. Low-dimensional control variables replace node-level configuration actions in the work area, reducing output dimensions, model parameter count, and inference computation load;

[0047] 2. Unreachable nodes, resource type capacity, regional configuration upper limit, and minimum task guarantee are uniformly handled by revenue indicators, basic coverage, and constraint projection. The configuration results are clearly defined as feasible for execution through guarantee verification, guarantee gap filling, and resource insufficiency identification.

[0048] 3. The parameterized allocation results are combined with the issuance, execution, and feedback updates of the management platform, operation terminals, or equipment control terminals, so that the regional operation resource allocation results affect technical indicators such as emergency repair completion rate, facility restoration capacity, risk node coverage rate, average arrival time, and operation resource consumption. Attached Figure Description

[0049] Figure 1 This is a flowchart of the multi-region operation resource parameterized constraint allocation method of the present invention;

[0050] Figure 2 This is a structural block diagram of the multi-region operation resource parameterized constraint allocation system of the present invention. Detailed Implementation

[0051] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0052] Example 1

[0053] A multi-regional operational resource parameterized constraint allocation system includes:

[0054] The data acquisition module is used to acquire regional operation status data and operation resource constraint data of all operation area nodes;

[0055] The status feature generation module is used to generate regional status features or regional map coding features based on regional operation status data.

[0056] The revenue indicator calculation module is used to generate revenue indicator vectors for all nodes in the work area.

[0057] The feasible region constraint module is used to construct the feasible region for job resource configuration based on job resource constraint data and revenue indicator vector;

[0058] The job resource allocation strategy model module is used to output low-dimensional control quantities that are independent of the number of nodes in the job area;

[0059] The parameterized allocation module is used to generate the regional configuration weight vector of all work area nodes based on low-dimensional control variables.

[0060] The constraint projection module is used to uniformly generate regional operation resource allocation results and perform minimum guarantee replenishment, guarantee gap calculation and result verification.

[0061] The configuration distribution and periodic feedback module is used to distribute the regional operation resource configuration results that have passed the guarantee verification to the operation terminal or equipment control terminal; for results that cannot fully meet the minimum guarantee, it sends the resource shortage indicator, gap amount and abnormal confirmation record to the management platform for review, and receives execution feedback for the next operation resource configuration cycle update.

[0062] Example 2

[0063] A method for parameterized constraint allocation of multi-regional operational resources includes the following steps:

[0064] S1. In a multi-region operation scenario, obtain the region operation status data and operation resource constraint data of the set of regions to be configured, which contains multiple operation region nodes;

[0065] S2. Generate regional status features or regional map coding features based on regional operation status data, and apply this to all operation region nodes in the set of regions to be configured. Unified calculation of non-negative return indicators To form a vector of revenue indicators ;

[0066] S3. Construct a feasible domain for operation resource allocation based on operation resource constraint data and revenue index vector. Input the regional state characteristics, revenue index vector and feasible domain for operation resource allocation into the operation resource allocation strategy model and output a three-dimensional low-dimensional control quantity.

[0067] S4. Map the three-dimensional low-dimensional control quantity to the revenue indicator concentration parameter, the revenue indicator threshold ratio parameter and the basic coverage mixing ratio parameter. Then, based on the three types of parameters, perform threshold truncation, focused weight transformation and basic coverage mixing processing on the revenue indicator vectors of all work area nodes in sequence to obtain the regional configuration weight vector.

[0068] S5. Determine the total configurable resources for a single cycle based on job resource constraints. Generate resource allocation amounts for each job region node using the regional allocation weight vector. Determine the allocation results through feasible domain constraints, minimum guarantee replenishment, and guarantee verification. If the guarantee verification passes, the allocation is sent to the corresponding job control terminal and operational data is collected. If the guarantee verification fails but replenishment is possible, replenishment and reallocation are performed. If replenishment is not possible due to total amount, upper limit, or reachability limitations, an insufficient resource indicator and gap amount are output for the next configuration cycle. Iterative updates provide a basis for this.

[0069] This embodiment takes the scenario of resource allocation for emergency repair operations in multiple regions after a disaster as an example. The multi-regional operation resource allocation system is deployed on the emergency support management platform. The set of regions to be configured includes operation area nodes such as disaster-stricken roads, power facilities, communication base stations, water supply stations, and temporary support points; operation resources include repair vehicles, maintenance personnel, emergency supplies, drones, and sensors.

[0070] In step S1, the data acquisition module collects data through the following interface:

[0071] By connecting sensors, drones, and vehicle positioning terminals through IoT interfaces, obtaining road networks, spatial adjacency relationships, and regional boundaries through GIS databases, obtaining task status and minimum guarantee requirements through facility operation and maintenance work order systems, and obtaining the quantity, location, and remaining capacity of personnel, vehicles, materials, drones, and sensors through the work resource management system.

[0072] The acquired regional operation status data includes: task status, risk status, operation resource demand status, resource distance status, and relationship with adjacent areas;

[0073] The acquired job resource constraint data includes: total job resources, resource type capacity, regional configuration limit, node reachability, and minimum task guarantee requirements.

[0074] Furthermore, the regional operation status data for the current operation resource allocation cycle is updated based on the regional operation resource allocation results, task completion status, risk change status, and resource demand change status of the previous operation resource allocation cycle; the operation resource constraint data for the current operation resource allocation cycle is updated based on the operation resource consumption and remaining resource capacity of the previous operation resource allocation cycle.

[0075] In step S2, the regional state features or regional graph coding features are generated by the state feature module: when there are spatial adjacency relationships, operation channel relationships or service dependency relationships between nodes in the operation area, the system constructs an adjacency matrix based on the adjacent regional relationships and generates regional graph coding features through the graph feature extraction network; when there are no adjacent regional relationships, the regional state features are generated based on the node features and global statistical features of each node in the operation area.

[0076] Simultaneously, through the revenue indicator calculation module, regional revenue items are generated based on task urgency, regional risk, resource gap, facility value, future demand pressure, and neighboring support capabilities. Regional cost items are generated based on toll costs, maintenance difficulty, resource distance, equipment capacity reduction, and operational risks (each factor is normalized to the 0-1 range). Combining the normalized regional revenue items and regional cost items, all operational area nodes within the set of areas to be configured are processed one by one. Solving for non-negative return indicators Finally, by summing up the indicator values ​​of each node, a revenue indicator vector is constructed. The regional revenue and regional cost items are generated according to the following rules:

[0077]

[0078]

[0079] in, Indicates the urgency of the task. Indicates the level of regional risk. Indicates a resource gap. Indicates the value of the facility. This indicates future demand pressure. Indicates the neighborhood support capability. Indicates toll costs, Indicates the difficulty of repair. Indicates the distance to resources. This indicates a reduction in equipment capacity. Indicates operational risk. Represents the cost smoothing term. to as well as to It is a non-negative weight, which can be preset or calibrated based on historical operation data.

[0080] No. Non-negative revenue metrics for each work area node:

[0081]

[0082] in, Indicates the first Non-negative revenue indicators for each work area node ; Indicates regional revenue items. Indicates the regional cost item. This indicates the zero-threshold protection. In this embodiment, This ensures that each node in the work area has a corresponding revenue indicator component, and the non-negative revenue indicators of all nodes form a revenue indicator vector. .

[0083] In step S3, the feasible domain constraint module constructs a feasible domain for resource allocation based on the job resource constraint data and the revenue indicator vector. This feasible domain for resource allocation includes single-cycle total amount constraints, node reachability constraints, regional configuration upper limit constraints, resource type capacity constraints, and task minimum guarantee constraints.

[0084] The regional state features or regional map encoding features, revenue index vector and feasible domain of job resource allocation generated in step S2 are input into the job resource allocation strategy model module. The model aims to maximize the cumulative task guarantee revenue and risk reduction revenue.

[0085] The job resource allocation strategy model outputs a three-dimensional low-dimensional control quantity that is independent of the number of nodes in the job area.

[0086]

[0087] in, , and These are the original control values ​​for the concentration of revenue indicators, the threshold ratio of revenue indicators, and the mixed ratio of basic coverage, respectively. , and These are the parameters obtained by performing monotonic compression, interval scaling, and neutral value calibration on the low-dimensional control quantity, respectively.

[0088] In step S4, the parameterized allocation module uses the Sigmoid function to perform monotonic compression and interval scaling on the low-dimensional control quantity, the expression of which is:

[0089]

[0090]

[0091]

[0092] in, and , and , and They are respectively , and The parameter range boundaries. In this embodiment, the obtained revenue indicator concentration parameter after mapping is 1.5, the revenue indicator threshold ratio parameter is 0.4, and the basic coverage mixing ratio parameter is 0.2.

[0093] The threshold truncation is determined based on the threshold ratio parameter of the return metric:

[0094]

[0095] in, Indicates the threshold of the profitability indicator. This represents the threshold ratio parameter for the profitability indicator. This represents the maximum value of the revenue indicator vector within the current job resource allocation period; based on the node reachability mask. Profitability threshold and the concentration parameter of returns Generate a weighted vector for the revenue metrics:

[0096]

[0097] in, Indicates the first The focus weight of each work area node, This indicates non-negative normalization; the normalized denominator is less than the normalized denominator threshold. Furthermore, when there is a positive return indicator, the distribution is formed by the reachable node with the largest return indicator; when all return indicators are zero, the basic coverage distribution or the effective distribution of the previous period is adopted; the larger α is, the more the resource allocation weight is concentrated on the high-return reachable node.

[0098] Node reachability mask Determined by road traffic conditions, access road conditions, resource type compatibility, and safety restrictions; when reachable and executable. ,otherwise Basic coverage is as follows:

[0099]

[0100] in, For the first The minimum guarantee factor for each work area node; when there is no minimum guarantee requirement. .

[0101] Then, based on the basic coverage mixing ratio parameters Mix the yield metrics with the weight vector or backtracking distribution and the underlying coverage distribution:

[0102]

[0103] in, Indicates the first The regional configuration weight of each work area node This represents the weight of the basic coverage distribution.

[0104] Finally, the regional configuration weight vector is obtained. and satisfy And the sum of all weighted components is 1.

[0105] In step S5, the total amount of configurable job resources for the current period is determined based on the job resource constraint data, and the continuous resource allocation amount for each job region node is generated by combining the regional allocation weight vector:

[0106]

[0107] The constrained projection module projects the continuous resource allocation of all nodes in the work area in the following order: unreachable node masks are zeroed out, area allocation limits are truncated, resource type capacity is normalized, minimum guarantee for tasks is supplemented, and remaining resources are redistributed according to area allocation weights. The guarantee standard is: the guarantee gap of all feasible minimum guarantee nodes. All values ​​are 0, and the configuration result simultaneously satisfies the single-cycle total constraint, node reachability constraint, regional configuration upper limit constraint, resource type capacity constraint, and discrete work unit constraint. If there is a guarantee gap and there are still deductible or unallocated surplus resources, they are replenished and redistributed according to task priority, revenue indicators, or regional configuration weight. If replenishment is not possible due to insufficient total resources, unreachable nodes, regional upper limit, or resource type capacity limitation, a resource shortage flag, guarantee gap amount, and an anomaly confirmation record are output. When converting discrete work units, the continuous configuration quantity is rounded and quantized, and the remaining units are replenished and allocated in descending order of quantization loss until the single-cycle total constraint is met. The final configuration result is output, which includes the work area node identifier, resource type, resource quantity, execution priority, resource shortage flag, and guarantee gap amount.

[0108] Distribution and Feedback: The configuration distribution and periodic feedback module distributes the regional operation resource configuration results that have passed the guarantee verification to the operation terminals (such as emergency repair vehicle dispatch screens, maintenance personnel handheld terminals, and drone control stations) or equipment control terminals through the emergency support management platform. For configuration results that cannot fully meet the guarantee standards but have been feasiblely corrected, the module sends the resource shortage indicator, guarantee gap amount, and abnormal confirmation record to the management platform for review or triggers the preset emergency mode. This transforms the configuration results into on-site operation instructions such as emergency repair vehicle dispatch, maintenance personnel arrangement, emergency material delivery, drone inspection, or sensor deployment. The module also receives arrival status, task completion status, resource consumption, and regional status changes from the operation execution system.

[0109] Example 3

[0110] An electronic device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement any step of a multi-regional job resource parameterized constraint allocation method as described in Embodiment 2.

[0111] Furthermore, the multi-regional operational resource parameterized constraint allocation method described in Embodiment 2 can be implemented as a computer software program. For example, this embodiment includes a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the method. In such an embodiment, the computer program can be downloaded and installed from a network, and / or installed from a removable medium. When the computer program is executed by a processor, it performs the functions defined in the method of this application.

[0112] Example 4

[0113] A computer-readable storage medium storing a computer program, which, when executed by a processor, implements any step of the method for implementing a multi-regional job resource parameterized constraint allocation as described in Embodiment 2.

[0114] The computer-readable medium described in this application may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. In this application, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to: wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0115] Computer program code for performing the operations of this application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, and conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0116] In summary, this invention effectively overcomes the shortcomings of the prior art and has high industrial applicability. The above embodiments are intended to illustrate the substantive content of this invention, but are not intended to limit the scope of protection of this invention. Those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of this invention without departing from the essence and scope of protection of this invention.

[0117] The above embodiments are specific implementations of the present invention, but the implementation of the present invention is not limited to the above embodiments. Any other combination, change, modification, substitution, or simplification that does not exceed the design concept of the present invention shall fall within the protection scope of the present invention.

Claims

1. A method for parameterized constraint allocation of multi-regional operational resources, characterized in that, The application to a multi-regional operational resource allocation system includes the following steps: S1. In a multi-region operation scenario, obtain the region operation status data and operation resource constraint data of the set of regions to be configured, which contains multiple operation region nodes; S2. Generate regional status features or regional map coding features based on regional operation status data, and apply this to all operation region nodes in the set of regions to be configured. Unified calculation of non-negative return indicators To form a vector of revenue indicators ; S3. Construct a feasible domain for operation resource allocation based on operation resource constraint data and revenue index vector. Input the regional state characteristics, revenue index vector and feasible domain for operation resource allocation into the operation resource allocation strategy model and output a three-dimensional low-dimensional control quantity. S4. Map the three-dimensional low-dimensional control quantity to the revenue indicator concentration parameter, the revenue indicator threshold ratio parameter and the basic coverage mixing ratio parameter. Then, based on the three types of parameters, perform threshold truncation, focused weight transformation and basic coverage mixing processing on the revenue indicator vectors of all work area nodes in sequence to obtain the regional configuration weight vector. S5. Determine the total configurable resources for a single cycle based on the operational resource constraints. Combine the regional configuration weight vector to generate the resource configuration amount for each operational region node. Determine the configuration result through feasible domain constraints, minimum guarantee supplementation, and guarantee verification. When the guarantee verification passes, the data is sent to the corresponding operational control terminal and operational data is collected. If the guarantee verification fails but the resource can be supplemented, supplementation and reallocation are performed. If the resource cannot be supplemented due to total amount, upper limit, or reachability limitations, the resource shortage flag and gap amount are output to provide a basis for the next configuration cycle iteration update.

2. The allocation method according to claim 1, characterized in that, In step S2, the calculation of the non-negative return indicator includes: Regional revenue items are generated based on the task urgency, regional risk, resource gap, facility value, future demand pressure, and neighboring support capacity of each operational area node. Regional cost items are generated based on transportation costs, maintenance difficulty, resource distance, equipment capacity reduction, and operational risks. The calculation is performed according to the following formula. Non-negative revenue metrics for each work area node: in, Indicates the first Non-negative revenue indicators for each work area node Indicates the first Regional revenue items for each work area node Indicates the first Regional cost item for each work area node Indicates the zero-prevention threshold. .

3. The allocation method according to claim 1, characterized in that, In step 3, the job resource allocation strategy model is a rule model, a neural network model, or a reinforcement learning strategy model. When it contains trainable parameters, it is trained in the job resource allocation simulation environment with the goal of maximizing the cumulative task guarantee benefits and risk reduction benefits over multiple consecutive periods.

4. The allocation method according to claim 1, characterized in that, In step 3, the three-dimensional low-dimensional control quantity is a three-dimensional control quantity that is independent of the number of nodes in the work area: in, , and These are the original control values ​​for the concentration of revenue indicators, the threshold ratio of revenue indicators, and the mixed ratio of basic coverage, respectively. , and These are the parameters obtained by performing monotonic compression, interval scaling, and neutral value calibration on the low-dimensional control quantity, respectively.

5. The allocation method according to claim 1, characterized in that, In step S4, the threshold value for the revenue indicator is: in, Indicates the threshold of the profitability indicator. This represents the threshold ratio parameter for the profitability indicator. This represents the maximum value of the revenue indicator vector within the current job resource allocation period; based on the node reachability mask. Profitability threshold and the concentration parameter of returns Generate a weighted vector for the revenue metrics: in, Indicates the first The focus weight of each work area node, This indicates nonnegative normalization based on the normalized denominator threshold. The region configuration weight vector is as follows: in, Indicates the first The regional configuration weight of each work area node This represents the weight of the basic coverage distribution.

6. The allocation method according to claim 1, characterized in that, In step S5, the resource allocation for each work area node is as follows: in, Indicates the first The amount of continuous resource allocation for each work area node. This indicates the total amount of configurable job resources per cycle.

7. A multi-regional operational resource parameterized constraint allocation system, characterized in that, include: The data acquisition module is used to acquire regional operation status data and operation resource constraint data of all operation area nodes; The status feature generation module is used to generate regional status features or regional map coding features based on regional operation status data. The revenue indicator calculation module is used to generate revenue indicator vectors for all nodes in the work area. The feasible region constraint module is used to construct the feasible region for job resource configuration based on job resource constraint data and revenue indicator vector; The job resource allocation strategy model module is used to output low-dimensional control quantities that are independent of the number of nodes in the job area; The parameterized allocation module is used to generate the regional configuration weight vector of all work area nodes based on low-dimensional control variables. The constraint projection module is used to uniformly generate regional operation resource allocation results and perform minimum guarantee replenishment, guarantee gap calculation and result verification. The configuration distribution and periodic feedback module is used to distribute the regional operation resource configuration results that have passed the guarantee verification to the operation terminal or equipment control terminal; for results that cannot fully meet the minimum guarantee, it sends the resource shortage indicator, gap amount and abnormal confirmation record to the management platform for review, and receives execution feedback for the next operation resource configuration cycle update.

8. The system according to claim 7, characterized in that, The job resource allocation strategy model is one or more of the following: rule model, neural network model, and reinforcement learning strategy model. When it contains trainable parameters, it is trained in a job resource allocation simulation environment with the goal of maximizing the cumulative task guarantee benefits and risk reduction benefits over multiple consecutive periods.

9. An electronic device comprising a processor and a memory, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements any step in the multi-regional operation resource parameterization constraint allocation method as described in any one of claims 1-6.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed by a computer processor, implements any step in the multi-regional operation resource parameterized constraint allocation method as described in any one of claims 1-6.

Images