A resource allocation method and device for marine emergency rescue

Abstract

The application discloses a resource allocation method and device for offshore emergency rescue, and the method comprises the following steps: acquiring a set of offshore emergency rescue demand information, a set of rescue resource description information and a set of rescue resource technical state parameter time series; the rescue resource description information comprises a rescue capability index value; each rescue demand index is one-to-one corresponding to the rescue capability index; pre-processing the set of offshore emergency rescue demand information, the set of rescue resource description information and the set of rescue resource technical state parameter time series to obtain a set of pre-processed information; performing resource allocation processing on the set of pre-processed information to obtain a set of resource allocation information; the set of resource allocation information comprises resource allocation information; the resource allocation information is used for describing the allocation information of resources for tasks.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of marine emergency rescue, in particular to a resource allocation method and device for marine emergency rescue. BACKGROUND

[0002] Marine safety incidents are usually sudden and disastrous, compared with general rescue operations, have the characteristics of variable search and rescue environment, difficulty in determining the search area, high time efficiency requirement for rescuing personnel, complex coordination of search and rescue forces, etc., so marine emergency rescue also presents the characteristics of technical intensity.

[0003] In the process of marine emergency rescue, reasonable allocation of various rescue resources is the key to successful rescue. However, the traditional marine emergency rescue resource allocation method usually relies on artificial experience and historical data, lacks systematic and data analysis tools, resulting in unreasonable resource allocation and affecting the efficiency of rescue.

[0004] In the resource allocation of the marine emergency rescue process, how to quickly respond to rescue demand and environmental changes, real-time adjustment of resource allocation, and improve the efficiency and accuracy of resource allocation are the current problems to be solved. SUMMARY

[0005] The present application mainly solves the problem of how to quickly respond to rescue demand and environmental changes, real-time adjustment of resource allocation, and improve the efficiency and accuracy of resource allocation in the resource allocation of the marine emergency rescue process, and discloses a resource allocation method and device for marine emergency rescue.

[0006] In a first aspect, the present application discloses a resource allocation method for marine emergency rescue, comprising:

[0007] S1, obtaining a set of marine emergency rescue demand information, a set of rescue resource description information and a set of rescue resource technical state parameter time series;

[0008] The set of marine emergency rescue demand information includes marine emergency rescue demand information; the set of rescue resource description information includes rescue resource description information; the marine emergency rescue demand information includes a lower limit value and a demand urgency value of each rescue demand index; each marine emergency rescue demand information corresponds to a marine emergency rescue task;

[0009] The rescue resource description information includes a rescue capability index value; each rescue demand index is one-to-one corresponding to a rescue capability index;

[0010] The set of rescue resource technical state parameter time series includes a performance parameter time series of each rescue resource;

[0011] S2, pre-process the offshore emergency rescue demand information set, rescue resource description information set and rescue resource technical state parameter time sequence set to obtain a pre-processed information set;

[0012] S3, perform resource allocation processing on the pre-processed information set to obtain a resource allocation information set; the resource allocation information set includes resource allocation information; the resource allocation information is used to describe the allocation information of resources for tasks.

[0013] The pre-processing of the offshore emergency rescue demand information set, the rescue resource description information set and the rescue resource technical state parameter time sequence set to obtain the pre-processed information set comprises:

[0014] S21, perform wild value elimination processing on each type of information set respectively to obtain a first information set;

[0015] S22, perform normalization processing on the first information set to obtain a normalized information set;

[0016] S23, perform category discrimination processing on the normalized information set to obtain the pre-processed information set.

[0017] The resource allocation processing on the pre-processed information set to obtain the resource allocation information set comprises:

[0018] S31, obtain a rescue resource standard state time sequence set; the rescue resource standard state time sequence set includes a rescue resource standard state time sequence of each rescue resource;

[0019] S32, perform state monitoring processing on the rescue resource state parameter sequence set in the pre-processed information set and the rescue resource standard state time sequence set to obtain a first rescue resource set;

[0020] S33, perform index lower limit discrimination processing on the first rescue resource set to obtain a second rescue resource set;

[0021] S34, perform allocation optimization processing on the second rescue resource set to obtain the resource allocation information set.

[0022] The state monitoring processing on the rescue resource state parameter sequence set in the pre-processed information set and the rescue resource standard state time sequence set to obtain the first rescue resource set;

[0023] S321, perform feature fitting processing on the rescue resource standard state time sequence set to obtain a rescue resource state evaluation model;

[0024] S322, performing state analysis on each rescue resource state parameter time sequence of the rescue resource state parameter sequence set to obtain a set of evaluation serial number values;

[0025] S323, performing calculation processing on the set of evaluation serial number values by using the rescue resource state evaluation model to obtain a set of rescue resource technical state values;

[0026] S324, constructing a first rescue resource set by using all rescue resources with a rescue resource technical state value less than a preset risk threshold value.

[0027] The feature fitting processing on the set of rescue resource standard state time sequences to obtain a rescue resource state evaluation model comprises:

[0028] S3211, constructing a first capability matrix by using the set of rescue resource standard state time sequences; a row vector of the first capability matrix is a rescue resource standard state time sequence in the set of rescue resource standard state time sequences;

[0029] S3212, performing decomposition processing on the first capability matrix to obtain a left decomposition matrix, a feature matrix and a right decomposition matrix of the first capability matrix;

[0030] S3213, extracting diagonal elements of the feature matrix to obtain a feature vector;

[0031] S3214, performing linear fitting processing on elements and element serial number values of the feature vector to obtain a rescue resource state evaluation model.

[0032] The state analysis on each rescue resource state parameter time sequence of the rescue resource state parameter sequence set to obtain a set of evaluation serial number values comprises:

[0033] S3221, calculating an average value of each rescue resource state parameter time sequence of the set of rescue resource standard state time sequences;

[0034] S3222, calculating an absolute value of a difference between each element in each rescue resource state parameter time sequence and the average value; confirming the absolute value of the difference as a deviation of the element;

[0035] S3223, finding an element with a maximum deviation in the rescue resource state parameter time sequence to determine a serial number value of the element in the rescue resource state parameter time sequence as an evaluation serial number value of the rescue resource state parameter time sequence;

[0036] S3224, using the evaluation serial number value of all rescue resource state parameter time series of the rescue resource standard state time series set, a set of evaluation serial number values is constructed.

[0037] The allocation optimization processing of the second rescue resource set obtains a resource allocation information set, which includes:

[0038] The demand urgency value of the offshore emergency rescue demand information set is expressed as matrix A; the element A of the i-th row and the j-th column of the matrix A represents the demand urgency value of the i-th offshore emergency rescue demand information for the j-th rescue demand index; ij

[0039] All rescue capability index values of the second rescue resource set are expressed as matrix B; the i-th row vector of the matrix B represents all rescue capability index values of the i-th rescue resource;

[0040] Initialize a resource allocation vector; the i-th element Ti of the resource allocation vector T represents the number of participating offshore emergency rescue tasks of the i-th resource;

[0041] The resource allocation optimization model is established, and its expression is:

[0042]

[0043] Ti≠0, i=1, 2, …, N,

[0044] Wherein, N is the number of offshore emergency rescue tasks, B Ti,j represents the element of the Ti-th row and the j-th column of the matrix B, T0 is a preset allocation threshold, m is the number of rescue capability indexes, the resource allocation vector T is a to-be-solved vector, and C(T) is an objective function;

[0045] The resource allocation optimization model is solved to obtain a resource allocation information set; the resource allocation information set is the resource allocation vector T.

[0046] The second aspect of the application discloses a resource allocation device for offshore emergency rescue, which comprises:

[0047] A memory storing executable program codes;

[0048] A processor coupled with the memory;

[0049] The processor calls the executable program codes stored in the memory to execute the resource allocation method for offshore emergency rescue.

[0050] ​The third aspect of the present application discloses a computer storage medium, which stores computer instructions, and the computer instructions are used to execute the resource allocation method for maritime emergency rescue when called by a computer.

[0051] The fourth aspect of the present application discloses an information data processing terminal, which is used to implement the resource allocation method for maritime emergency rescue.

[0052] The present application has the following beneficial effects:

[0053] The present application discloses a resource allocation method and device for maritime emergency rescue, and mainly solves the problem of how to quickly respond to rescue demand and environmental changes, real-time adjust resource allocation, and improve the efficiency and accuracy of resource allocation in the process of resource allocation in maritime emergency rescue.

[0054] After obtaining the rescue demand information set and the resource description information, the present application first performs screening processing on the rescue demand information set and the resource description information set to obtain a candidate resource description information set, thereby reducing the number of materials to be matched and greatly reducing the complexity of the subsequent rescue matching process.

[0055] The present application establishes a rescue optimization model to match and solve the candidate resource description information set and the preprocessed rescue demand information set, thereby improving the matching accuracy and obtaining an effective and accurate rescue resource allocation information set. BRIEF DESCRIPTION OF DRAWINGS

[0056] Figure 1 The present application is a method for implementing the flowchart. DETAILED DESCRIPTION

[0057] In order to better understand the content of the present application, an embodiment is given.

[0058] Figure 1 The present application is a method for implementing the flowchart.

[0059] The first aspect of the embodiment of the present application discloses a resource allocation method for maritime emergency rescue, which comprises the following steps:

[0060] S1, obtaining a maritime emergency rescue demand information set, a rescue resource description information set and a rescue resource technical state parameter time sequence set;

[0061] The maritime emergency rescue demand information set comprises maritime emergency rescue demand information; the rescue resource description information set comprises rescue resource description information; the maritime emergency rescue demand information comprises a lower limit value and a demand urgency value of each rescue demand index; each maritime emergency rescue demand information corresponds to a maritime emergency rescue task;

[0062] The rescue resource description information comprises a rescue capability index value; each rescue demand index is in one-to-one correspondence with a rescue capability index;

[0063] The rescue resource technical state parameter time sequence set comprises a performance parameter time sequence of each rescue resource; the performance parameter time sequence of the rescue resource is a time sequence of rescue resource parameters;

[0064] S2, pre-process the maritime emergency rescue demand information set, the rescue resource description information set and the rescue resource technical state parameter time sequence set to obtain a pre-processed information set;

[0065] S3, perform resource allocation processing on the pre-processed information set to obtain a resource allocation information set; the resource allocation information set comprises resource allocation information; the resource allocation information is used for describing allocation information of resources for tasks;

[0066] The pre-processing of the maritime emergency rescue demand information set, the rescue resource description information set and the rescue resource technical state parameter time sequence set to obtain a pre-processed information set comprises:

[0067] S21, perform wild value elimination processing on each type of information set respectively to obtain a first information set;

[0068] S22, perform normalization processing on the first information set to obtain a normalized information set;

[0069] S23, perform category discrimination processing on the normalized information set to obtain a pre-processed information set.

[0070] The resource allocation processing on the pre-processed information set to obtain a resource allocation information set comprises:

[0071] S31, obtain a rescue resource standard state time sequence set; the rescue resource standard state time sequence set comprises a rescue resource standard state time sequence of each rescue resource;

[0072] S32, perform state monitoring processing on the rescue resource state parameter sequence set in the pre-processed information set and the rescue resource standard state time sequence set to obtain a first rescue resource set;

[0073] S33, performing lower limit discrimination processing on the first rescue resource set to obtain a second rescue resource set;

[0074] S34, performing allocation optimization processing on the second rescue resource set to obtain a resource allocation information set;

[0075] The lower limit discrimination processing on the first rescue resource set to obtain a second rescue resource set comprises:

[0076] For each rescue resource in the first rescue resource set, it is respectively judged whether all rescue capability index values are greater than the lower limit value of the corresponding rescue demand index, and the rescue resource with a rescue capability index value not greater than the lower limit value of the corresponding rescue demand index is deleted from the first rescue resource set to obtain a second rescue resource set.

[0077] The state monitoring processing on the rescue resource state parameter sequence set and the rescue resource standard state time sequence set in the preprocessed information set to obtain a first rescue resource set;

[0078] S321, performing feature fitting processing on the rescue resource standard state time sequence set to obtain a rescue resource state evaluation model;

[0079] S322, performing state analysis on each rescue resource state parameter time sequence of the rescue resource state parameter sequence set to obtain an evaluation serial number value set;

[0080] S323, using the rescue resource state evaluation model to perform calculation processing on the evaluation serial number value set to obtain a rescue resource technical state value set;

[0081] S324, using all rescue resources with a technical state value less than a preset risk threshold value to construct a first rescue resource set.

[0082] The feature fitting processing on the rescue resource standard state time sequence set to obtain a rescue resource state evaluation model comprises:

[0083] S3211, using the rescue resource standard state time sequence set to construct a first capability matrix; the row vector of the first capability matrix is a rescue resource standard state time sequence in the rescue resource standard state time sequence set;

[0084] S3212, performing decomposition processing on the first capability matrix to obtain a left decomposition matrix, a feature matrix and a right decomposition matrix of the first capability matrix;

[0085] S3213, extracting the diagonal elements of the feature matrix to obtain a feature vector;

[0086] S3214, linear fitting is performed on the element and element sequence number value of the feature vector to obtain a rescue resource state evaluation model;

[0087] The state analysis on each rescue resource state parameter time sequence of the rescue resource state parameter sequence set obtains an evaluation sequence number value set, which includes:

[0088] S3221, for each rescue resource state parameter time sequence of the rescue resource standard state time sequence set, the average value of the rescue resource state parameter time sequence is calculated;

[0089] S3222, for each element in each rescue resource state parameter time sequence, the absolute value of the difference between the element and the average value is calculated; the absolute value of the difference is confirmed as the offset of the element;

[0090] S3223, for the rescue resource state parameter time sequence, the element with the maximum offset is found, and the sequence number value of the element in the rescue resource state parameter time sequence is determined as the evaluation sequence number value of the rescue resource state parameter time sequence;

[0091] S3224, the evaluation sequence number value set is constructed by using the evaluation sequence number values of all rescue resource state parameter time sequences of the rescue resource standard state time sequence set;

[0092] The rescue resource state evaluation model is used to calculate and process the evaluation sequence number value set to obtain a rescue resource technology state value set. Each evaluation sequence number value in the evaluation sequence number value set is respectively brought into the rescue resource state evaluation model for calculation and processing to obtain a corresponding result value. All result values are used to construct a rescue resource technology state value set.

[0093] The rescue resource technology state value represents the probability of risk of rescue resource technology state. The greater the risk value, the more likely the rescue resource technology state is to occur.

[0094] The linear fitting process is to take the characteristic vector element sequence number value Ix as the known independent variable and the characteristic vector element value as the known dependent variable. The known independent variable and the known dependent variable are used to construct a to-be-approximated curve. The function approximation method is used to perform curve fitting on the to-be-approximated curve to obtain a rescue resource state evaluation model f(Ix).

[0095] The function approximation method can be used to perform curve fitting on the to-be-approximated curve.

[0096] The decomposition processing can adopt matrix eigenvalue decomposition processing.

[0097] The allocation optimization processing on the second rescue resource set obtains a resource allocation information set, which includes:

[0098] The demand urgency value of the offshore emergency rescue demand information set is expressed as matrix A; the element A ij of the ith row and jth column of the matrix A represents the demand urgency value of the ith offshore emergency rescue demand information for the jth rescue demand index;

[0099] All rescue capability index values of the second rescue resource set are expressed as matrix B; the ith row vector of the matrix B represents all rescue capability index values of the ith rescue resource;

[0100] A resource allocation vector is initialized; the ith element Ti of the resource allocation vector T represents the number of participating offshore emergency rescue tasks of the ith resource;

[0101] A resource allocation optimization model is established, and its expression is:

[0102]

[0103] Ti≠0, i = 1, 2, …, N

[0104] Wherein, N is the number of offshore emergency rescue tasks, B Ti,j represents the element of the Tith row and jth column of the matrix B, T0 is a preset allocation threshold, m is the number of rescue capability indexes, the resource allocation vector T is a to-be-solved vector, and C(T) is an objective function;

[0105] The resource allocation optimization model is solved to obtain a resource allocation information set. The resource allocation information set is the resource allocation vector T.

[0106] The objective function of the resource allocation optimization model directly associates the demand urgency and resource capability through matrix multiplication, ensuring that high-urgency demands are prioritized to obtain matching resources. The matrix operation form is simple and can efficiently process large-scale multi-task and multi-resource allocation problems. The resource allocation vector allows dynamic allocation of the same resource among different tasks, adapting to the suddenness and variability of offshore rescue tasks. The optimal allocation scheme is automatically determined through optimization solving, reducing human decision-making errors. The capability constraint ensures that resource use does not exceed the preset threshold, avoiding resource depletion caused by excessive allocation. The non-zero constraint ensures that each resource participates in at least one task, improving resource utilization. The allocation threshold can be dynamically adjusted according to actual rescue scenarios (such as material reserves and equipment wear and tear), enhancing the adaptability of the model.

[0107] The wild value elimination includes filling in missing values, smoothing noise data, smoothing or deleting wild value points; the smoothing noise data is to firstly determine noise data, and then to smooth the noise data according to the data before and after the noise data; the noise data is a value less than the detection sensitivity of a sensor of the observation data or greater than the measurement upper limit of the sensor. The determination of the wild value points can adopt the Kalman filtering method. For the determination of the filling value of the missing value, the measurement values in a certain sampling interval before and after the missing value are averaged.

[0108] The normalization processing is to map data with different value ranges into a specified value range;

[0109] The category determination processing is to determine whether the attribute of each data in each category information of the normalized information set is within the preset attribute range of the category information, and to eliminate the data not within the attribute range from the information.

[0110] The decomposition processing has a calculation expression as follows:

[0111] Y = UAV,

[0112] Wherein, U is a left decomposition matrix, Y is a first capability matrix, A is a characteristic matrix, V is a right decomposition matrix, U and V are both orthogonal matrices, and A is a diagonal matrix;

[0113] The second aspect of the present application discloses a resource allocation device for offshore emergency rescue, which comprises:

[0114] A memory storing executable program codes;

[0115] A processor coupled with the memory;

[0116] The processor calls the executable program codes stored in the memory to execute the resource allocation method for offshore emergency rescue.

[0117] The third aspect of the present application discloses a computer storage medium storing computer instructions, which are called by a computer to execute the resource allocation method for offshore emergency rescue.

[0118] The fourth aspect of the present application discloses an information data processing terminal for implementing the resource allocation method for offshore emergency rescue.

[0119] The above merely illustrates the embodiments of the present application but should not be taken as limitations. Various modifications and variations can be made to the present application based on the skilled in the art. Any modification, equivalent replacement, improvement, etc. within the spirit and principles of the present application shall be included in the scope of claims of the present application.

Claims

1. A method for resource allocation for maritime emergency rescue, characterized in that, The method comprises the following steps: S1, obtaining a set of maritime emergency rescue demand information, a set of rescue resource description information, and a set of rescue resource technical state parameter time series; The set of maritime emergency rescue demand information comprises maritime emergency rescue demand information; the set of rescue resource description information comprises rescue resource description information; the maritime emergency rescue demand information comprises a lower limit value and a demand urgency value of each rescue demand index; each maritime emergency rescue demand information corresponds to a maritime emergency rescue task; The rescue resource description information comprises a rescue capability index value; each rescue demand index is in one-to-one correspondence with the rescue capability index; The set of rescue resource technical state parameter time series comprises a performance parameter time series of each rescue resource; S2, preprocessing the set of maritime emergency rescue demand information, the set of rescue resource description information, and the set of rescue resource technical state parameter time series to obtain a set of preprocessed information; S3, performing resource allocation processing on the set of preprocessed information to obtain a set of resource allocation information; The set of resource allocation information comprises resource allocation information, which comprises: S31, obtaining a set of rescue resource standard state time series; the set of rescue resource standard state time series comprises a rescue resource standard state time series of each rescue resource; S32, performing state monitoring processing on the set of rescue resource state parameter time series and the set of rescue resource standard state time series in the set of preprocessed information to obtain a first rescue resource set; S33, performing index lower limit discrimination processing on the first rescue resource set to obtain a second rescue resource set; S34, performing allocation optimization processing on the second rescue resource set to obtain a set of resource allocation information, which comprises: The urgency value of the offshore emergency rescue demand information set is denoted as matrix A; the element of the i-th row and the j-th column of the matrix A denotes the urgency value of the i-th offshore emergency rescue demand information for the j-th rescue demand index; Expressing all rescue capability index values of the second rescue resource set as a matrix B; the ith row vector of the matrix B represents all rescue capability index values of the ith rescue resource; initializing a resource allocation vector; an i-th element of the resource allocation vector T Ti denotes the number of the i-th resource participating in the maritime emergency rescue task; Establishing a resource allocation optimization model, the expression of which is: ， Wherein, N is the number of offshore emergency rescue tasks, represents the element of the i-th row and the j-th column of the matrix B, T 0 is a preset allocation threshold, m is the number of rescue capacity indexes, the resource allocation vector T is a to-be-solved vector, and C( T ) is an objective function.​ Solving the resource allocation optimization model to obtain a set of resource allocation information; the set of resource allocation information is a resource allocation vector T; The resource allocation information is used for describing allocation information of resources for tasks.

2. The method for allocating resources for maritime emergency rescue according to claim 1, characterized in that, The preprocessing of the set of maritime emergency rescue demand information, the set of rescue resource description information, and the set of rescue resource technical state parameter time series to obtain a set of preprocessed information comprises the following steps: S21, performing wild value elimination processing on each type of information set respectively to obtain a first information set; S22, performing normalization processing on the first information set to obtain a normalized information set; S23, performing category discrimination processing on the normalized information set to obtain a set of preprocessed information.

3. The method for allocating resources for maritime emergency rescue according to claim 1, characterized in that, The state monitoring processing on the set of rescue resource state parameter time series and the set of rescue resource standard state time series in the set of preprocessed information to obtain a first rescue resource set comprises the following steps: S321, performing feature fitting processing on the set of rescue resource standard state time series to obtain a rescue resource state evaluation model; S322, performing state analysis on each rescue resource state parameter time sequence of the rescue resource state parameter sequence set to obtain a sequence number value set of evaluations; S323, using the rescue resource state evaluation model to perform calculation processing on the sequence number value set of evaluations to obtain a rescue resource technical state value set; S324, using all rescue resources with rescue resource technical state values less than a preset risk threshold value to construct a first rescue resource set.

4. The method for allocating resources for maritime emergency rescue according to claim 3, characterized in that, The feature fitting processing on the rescue resource standard state time sequence set includes: S3211, using the rescue resource standard state time sequence set to construct a first capability matrix; a row vector of the first capability matrix is a rescue resource standard state time sequence in the rescue resource standard state time sequence set; S3212, performing decomposition processing on the first capability matrix to obtain a left decomposition matrix, a feature matrix and a right decomposition matrix of the first capability matrix; S3213, extracting diagonal elements of the feature matrix to obtain a feature vector; S3214, performing linear fitting processing on elements and element sequence number values of the feature vector to obtain a rescue resource state evaluation model.

5. The method for allocating resources for maritime emergency rescue according to claim 3, wherein, The state analysis on each rescue resource state parameter time sequence of the rescue resource state parameter sequence set to obtain a sequence number value set of evaluations includes: S3221, calculating an average value of each rescue resource state parameter time sequence of the rescue resource standard state time sequence set; S3222, calculating an absolute value of a difference between each element in each rescue resource state parameter time sequence and the average value; confirming the absolute value of the difference as a deviation of the element; S3223, finding an element with a maximum deviation in the rescue resource state parameter time sequence to determine a sequence number value of the element in the rescue resource state parameter time sequence as an evaluation sequence number value of the rescue resource state parameter time sequence; S3224, using evaluation sequence number values of all rescue resource state parameter time sequences of the rescue resource standard state time sequence set to construct a sequence number value set of evaluations.

6. A resource allocation apparatus for maritime emergency rescue, characterized by, The device includes: a memory storing executable program codes; a processor coupled with the memory; the processor invokes the executable program codes stored in the memory to execute the resource allocation method for offshore emergency rescue according to any one of claims 1 to 5.

7. A computer storable medium, characterized by The computer storage medium stores computer instructions, which are invoked by a computer to execute the resource allocation method for offshore emergency rescue according to any one of claims 1 to 5.

8. An information data processing terminal, characterized by The information data processing terminal is used to implement the resource allocation method for offshore emergency rescue according to any one of claims 1 to 5.

Images