Remote order dispatching optimization method and device, equipment and medium

Abstract

The invention discloses a remote order dispatching optimization method and device, equipment and a medium, and relates to the field of computers, and the method comprises the steps: obtaining feature information of a plurality of target vehicles and a plurality of target maintenance personnel, carrying out the preprocessing of the feature information, and generating identifiers corresponding to the plurality of target vehicles and the plurality of target maintenance personnel; generating a plurality of initial order sending schemes according to the identifier, and calculating fitness corresponding to the plurality of initial order sending schemes according to a preset fitness function; and performing selection operation on the plurality of initial order sending schemes, performing interlace operation and mutation operation on the plurality of selected target initial order sending schemes to generate a plurality of processed order sending schemes, and performing iteration operation on the plurality of processed order sending schemes through a simulated annealing algorithm to obtain a plurality of target order sending schemes. Therefore, resource configuration can be optimized according to actual conditions, the diagnosis time of automobile faults is shortened, and the accuracy and efficiency of order dispatching are improved.

Description

Technical Field

[0001] The present invention relates to the field of computers, and in particular to a remote dispatch optimization method, device, equipment and medium. Background Art

[0002] With the rapid development of the automotive industry, the demand for remote automotive diagnostic services is growing. However, when dealing with a large number of diagnostic requests, existing remote automotive diagnostic dispatch systems often have problems such as low dispatch efficiency and unreasonable resource allocation. Traditional dispatch methods are usually based on simple rules or experience, and are simply pushed based on specific or evaluation pushes. They are difficult to adapt to complex and changing actual situations and cannot achieve the expected results, resulting in the quality and efficiency of diagnostic services being affected, affecting user experience.

[0003] From the above, it can be seen that how to optimize resource allocation according to actual conditions, shorten the diagnosis time of automobile failures, and improve the accuracy and efficiency of dispatching orders is an urgent problem to be solved. Summary of the invention

[0004] In view of this, the purpose of the present invention is to provide a remote dispatch optimization method, device, equipment and medium, which can optimize resource allocation according to actual conditions, shorten the diagnosis time of automobile faults, and improve the accuracy and efficiency of dispatch. The specific scheme is as follows:

[0005] In a first aspect, the present application provides a remote dispatch optimization method, comprising:

[0006] Acquire characteristic information of a plurality of target vehicles and a plurality of target maintenance personnel, and preprocess the characteristic information to generate a plurality of vehicle identifiers corresponding to the plurality of target vehicles and a plurality of personnel identifiers corresponding to the plurality of target maintenance personnel according to the obtained preprocessed characteristic information;

[0007] Generating a plurality of initial dispatching schemes according to the plurality of vehicle identifiers and the plurality of personnel identifiers, and calculating the fitness corresponding to the plurality of initial dispatching schemes according to a preset fitness function;

[0008] A selection operation is performed on the several initial order dispatching plans based on the fitness, and a crossover operation and a mutation operation are performed on the selected several target initial order dispatching plans to generate several processed order dispatching plans, and the several processed order dispatching plans are iterated through a simulated annealing algorithm to obtain several target order dispatching plans.

[0009] Optionally, the acquiring characteristic information of a plurality of target vehicles and a plurality of target maintenance personnel, and preprocessing the characteristic information to generate a plurality of vehicle identifiers corresponding to the plurality of target vehicles and a plurality of personnel identifiers corresponding to the plurality of target maintenance personnel according to the obtained preprocessed characteristic information, comprises:

[0010] Acquire characteristic information of a plurality of target vehicles and a plurality of target maintenance personnel, and perform standardization processing on the characteristic information to obtain first characteristic information corresponding to the plurality of target vehicles and second characteristic information corresponding to the plurality of target maintenance personnel;

[0011] A plurality of vehicle identifiers corresponding to the plurality of target vehicles are generated according to the first characteristic information, and a plurality of personnel identifiers corresponding to the plurality of target maintenance personnel are generated according to the second characteristic information.

[0012] Optionally, before generating a plurality of initial dispatching schemes according to the plurality of vehicle identifiers and the plurality of personnel identifiers and calculating the fitness corresponding to the plurality of initial dispatching schemes according to a preset fitness function, the method further includes:

[0013] Determining fitness function parameters of a preset fitness function based on a preset dispatch target, and constructing the preset fitness function according to the fitness function parameters;

[0014] The preset dispatch target is a combination of a preset time target, a preset accuracy target and a preset resource utilization target.

[0015] Optionally, generating a plurality of initial dispatching schemes according to the plurality of vehicle identifiers and the plurality of personnel identifiers, and calculating the fitness corresponding to the plurality of initial dispatching schemes according to a preset fitness function, includes:

[0016] matching the plurality of vehicle identifiers with the plurality of personnel identifiers to generate a plurality of identification pairs;

[0017] A number of initial dispatching plans are generated based on the number of identification pairs, and the first fitness corresponding to the number of initial dispatching plans is calculated according to the preset fitness function.

[0018] Optionally, the selecting operation is performed on the several initial dispatching plans based on the fitness, and the crossover operation and mutation operation are performed on the several selected target initial dispatching plans to generate several processed dispatching plans, including:

[0019] Ranking the first fitness degrees based on the numerical values ​​of the first fitness degrees, and selecting a number of target initial dispatching plans corresponding to a preset quantity threshold from the number of initial dispatching plans according to the obtained first fitness rankings;

[0020] A crossover operation and a mutation operation are performed on the identification pairs corresponding to the several target initial dispatching plans to generate several processed identification pairs, and several processed dispatching plans are generated based on the several processed identification pairs.

[0021] Optionally, the iterative operation of the plurality of processed dispatching schemes by using a simulated annealing algorithm to obtain a plurality of target dispatching schemes includes:

[0022] Calculating the second fitness corresponding to the plurality of processed dispatching schemes according to the preset fitness function;

[0023] Determine whether the second fitness is greater than the first fitness; if the second fitness is greater than the first fitness, use the plurality of post-processing dispatching schemes as a plurality of target post-processing dispatching schemes; if the second fitness is not greater than the first fitness, determine the plurality of target post-processing dispatching schemes from the plurality of target initial dispatching schemes and the plurality of post-processing dispatching schemes based on the simulated annealing algorithm;

[0024] The plurality of target processed dispatching plans are processed based on preset target conditions to obtain the plurality of target dispatching plans.

[0025] Optionally, the processing of the plurality of target processed dispatching schemes based on preset target conditions to obtain the plurality of target dispatching schemes includes:

[0026] Determine whether the number of iterations of the several target-processing order dispatching schemes is less than a preset iteration number threshold; if the number of iterations of the several target-processing order dispatching schemes is not less than the preset iteration number threshold, use the several target-processing order dispatching schemes as target order dispatching schemes; if the number of iterations of the several target-processing order dispatching schemes is less than the preset iteration number threshold, calculate the third fitness corresponding to the several target-processing order dispatching schemes, and execute the next round of iteration operations for the several target-processing order dispatching schemes based on the third fitness until the number of iterations is not less than the preset iteration number threshold;

[0027] Or, determine whether the several target order dispatching schemes after processing meet the preset fitness conditions; if the several target order dispatching schemes after processing meet the preset fitness conditions, use the several target order dispatching schemes after processing as target order dispatching schemes; if the several target order dispatching schemes after processing do not meet the preset fitness conditions, calculate the third fitness corresponding to the several target order dispatching schemes after processing, and perform the next round of iterative operations on the several target order dispatching schemes after processing based on the third fitness, until the obtained several target order dispatching schemes after processing meet the preset fitness conditions;

[0028] Among them, the preset fitness condition is that the difference between the fitness of the dispatching scheme after processing several targets corresponding to the current iteration round and the fitness of the dispatching scheme after processing several targets corresponding to the previous iteration round is less than the preset fitness change threshold.

[0029] In a second aspect, the present application provides a remote dispatch optimization device, comprising:

[0030] A feature information acquisition module, used to acquire feature information of a plurality of target vehicles and a plurality of target maintenance personnel, and preprocess the feature information to generate a plurality of vehicle identifiers corresponding to the plurality of target vehicles and a plurality of personnel identifiers corresponding to the plurality of target maintenance personnel according to the obtained preprocessed feature information;

[0031] An initial scheme generating module, used to generate a plurality of initial dispatching schemes according to the plurality of vehicle identifiers and the plurality of personnel identifiers, and calculate the fitness corresponding to the plurality of initial dispatching schemes according to a preset fitness function;

[0032] The order dispatching plan iteration module is used to select the several initial order dispatching plans based on the fitness, and perform crossover and mutation operations on the several selected target initial order dispatching plans to generate several processed order dispatching plans, and iterate the several processed order dispatching plans through a simulated annealing algorithm to obtain several target order dispatching plans.

[0033] In a third aspect, the present application provides an electronic device, including:

[0034] Memory, used to store computer programs;

[0035] A processor is used to execute the computer program to implement the aforementioned remote dispatch optimization method.

[0036] In a fourth aspect, the present application provides a computer-readable storage medium for storing a computer program, wherein the computer program implements the aforementioned remote order dispatch optimization method when executed by a processor.

[0037] The present application obtains characteristic information of several target vehicles and several target maintenance personnel, and pre-processes the characteristic information to generate several vehicle identifiers corresponding to the several target vehicles and several personnel identifiers corresponding to the several target maintenance personnel according to the obtained pre-processed characteristic information; generates several initial dispatching plans according to the several vehicle identifiers and the several personnel identifiers, and calculates the fitness corresponding to the several initial dispatching plans according to a preset fitness function; selects the several initial dispatching plans based on the fitness, and performs crossover and mutation operations on the selected several target initial dispatching plans to generate several processed dispatching plans, and iterates the several processed dispatching plans through a simulated annealing algorithm to obtain several target dispatching plans.

[0038] As can be seen from the above, the present application performs crossover operations and mutation operations on the several target initial dispatching plans to generate several processed dispatching plans, and iterates the several processed dispatching plans through a simulated annealing algorithm, which can improve the fitness of the dispatching plan to achieve the purpose of reasonable allocation of dispatching resources, and can adjust the parameters in the preset fitness function according to the actual application situation, so as to adapt to complex and changeable actual situations. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0040] Figure 1 A flow chart of a remote dispatch optimization method disclosed in this application;

[0041] Figure 2 A flowchart of a specific remote dispatch optimization method disclosed in this application;

[0042] Figure 3 A schematic diagram of a remote dispatch optimization device disclosed in this application;

[0043] Figure 4 This is a structural diagram of an electronic device disclosed in this application. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] With the rapid development of the automobile industry, the demand for remote automobile diagnostic services is growing. However, existing remote automobile diagnostic dispatch systems often have problems such as low dispatch efficiency and unreasonable resource allocation when processing a large number of diagnostic requests. Traditional dispatch methods are usually based on simple rules or experience, which are difficult to adapt to complex and changeable actual situations, resulting in the quality and efficiency of diagnostic services being affected. To this end, the present application provides a remote dispatch optimization solution, which generates several processed dispatch solutions by performing cross operations and mutation operations on the several target initial dispatch solutions, and iterates the several processed dispatch solutions, thereby improving the adaptability of the dispatch solution and improving the quality and efficiency of the diagnostic service.

[0046] See also Figure 1 As shown, the embodiment of the present application discloses a remote dispatch optimization method, including:

[0047] Step S11, acquiring characteristic information of a plurality of target vehicles and a plurality of target maintenance personnel, and preprocessing the characteristic information to generate a plurality of vehicle identifiers corresponding to the plurality of target vehicles and a plurality of personnel identifiers corresponding to the plurality of target maintenance personnel according to the obtained preprocessed characteristic information.

[0048] In this embodiment, the characteristic information of several target vehicles uploaded by the target user is obtained through the preset remote diagnosis client, and the characteristic information of several target maintenance personnel is obtained from the preset maintenance personnel information database, and the data is standardized. Among them, the characteristic information of several target vehicles includes but is not limited to the vehicle brand information, vehicle model information, production year information, mileage information, vehicle location information and vehicle fault information of the target vehicle; the characteristic information of several target maintenance personnel includes but is not limited to the identity authentication information, maintenance skill information, experience level information, maintenance type information, current location information and current workload information of the target maintenance personnel; the standardized processing is to analyze and process the characteristic information of the several target vehicles and several target maintenance personnel according to the preset standards. For example, the fault information and location information of the target vehicle and the professional skills and working status of the maintenance technician are collected, the brand and model of the target vehicle are standardized and coded, the fault symptoms are classified and coded, and the data are cleaned, integrated and normalized, and key features are extracted to make the data easier to process and analyze.

[0049] In this embodiment, a number of vehicle identifiers corresponding to the target vehicles and a number of personnel identifiers corresponding to the target maintenance personnel are generated according to the characteristic information after analysis and processing according to the preset standard. The vehicle identifiers and the personnel identifiers are identification information corresponding to the target vehicles and the target maintenance personnel, and the types of the identification information include but are not limited to vehicle codes and personnel codes corresponding to the target vehicles and the target maintenance personnel, which can be determined according to the actual application situation.

[0050] Specifically, the feature information of several target vehicles and several target maintenance personnel is obtained, and the feature information is preprocessed to generate several vehicle identifiers corresponding to the several target vehicles and several personnel identifiers corresponding to the several target maintenance personnel according to the obtained preprocessed feature information, including: obtaining vehicle brand information, vehicle model information, production year information, mileage information, vehicle location information and vehicle fault information of several target vehicles and identity authentication information, maintenance skill information, experience level information, maintenance type information, current location information and current workload information of several target maintenance personnel, and cleaning, integrating and normalizing the above feature information, extracting key features, so as to obtain first feature information corresponding to the several target vehicles and second feature information corresponding to the several target maintenance personnel; generating several vehicle codes corresponding to the several target vehicles by standardizing the brand and model of the vehicle according to the first feature information, and generating several personnel codes corresponding to the several target maintenance personnel according to the second feature information. By preprocessing the obtained feature information, the data can be made easier to process and analyze, so as to facilitate the subsequent steps to process the first feature information and the second feature information.

[0051] Step S12: generating a plurality of initial dispatching plans according to the plurality of vehicle identifiers and the plurality of personnel identifiers, and calculating the fitness corresponding to the plurality of initial dispatching plans according to a preset fitness function.

[0052] In this embodiment, the target vehicle and the target maintenance personnel are matched by the several vehicle identifiers and the several personnel identifiers, and the obtained several matching combinations are used as several initial dispatching schemes, and the fitness corresponding to the several initial dispatching schemes is calculated according to the preset fitness function. Among them, the preset fitness function is a fitness calculation function constructed according to the preset dispatching target, and the preset dispatching target includes any one or a combination of several of the preset time target, the preset accuracy target and the preset resource utilization target. The fitness function parameters of the preset fitness function are adjusted by changing the weight ratio of the preset time target, the preset accuracy target and the preset resource utilization target to construct the preset fitness function. Specifically, in a specific implementation, before generating several initial dispatching plans according to the several vehicle identifiers and the several personnel identifiers, and calculating the fitness corresponding to the several initial dispatching plans according to the preset fitness function, it also includes: determining the fitness function parameters of the preset fitness function based on the preset dispatching target, and constructing the preset fitness function according to the fitness function parameters; wherein the preset dispatching target is a preset time weight of 60%, a preset accuracy weight of 30%, and a preset resource utilization weight of 10%. That is, the parameters in the preset fitness function are adjusted according to the actual application situation to adjust the preset fitness function, so that the subsequent steps can use the preset fitness function to generate a target dispatching plan, which can adapt to the complex and changeable actual situation.

[0053] In this embodiment, several identification pairs are generated by randomly matching the several vehicle identifiers and the several personnel identifiers, and several initial dispatching schemes are generated based on the several identification pairs. Among them, the identification pair is a combination of any target vehicle identifier and any target personnel identifier. Specifically, the several initial dispatching schemes are generated based on the several vehicle identifiers and the several personnel identifiers, and the fitness corresponding to the several initial dispatching schemes is calculated according to the preset fitness function, including: matching the several vehicle identifiers with the several personnel identifiers to generate several identification pairs; generating several initial dispatching schemes based on the several identification pairs, and calculating the first fitness corresponding to the several initial dispatching schemes according to the preset fitness function. It can be understood that the specific number of the several identification pairs can be determined according to the actual application situation. For example, there are currently 500 faulty vehicles that need to be repaired, and there are 200 online maintenance personnel. According to the actual situation, 500 vehicle identifiers and 200 personnel identifiers are generated by randomly matching to generate 500 identification pairs, and 500 initial dispatching schemes are generated based on the identification pairs.

[0054] Step S13: selecting the several initial dispatching plans based on the fitness, and performing crossover and mutation operations on the selected several target initial dispatching plans to generate several processed dispatching plans, and iterating the several processed dispatching plans through a simulated annealing algorithm to obtain several target dispatching plans.

[0055] In this embodiment, a preset number threshold is determined according to the number of the initial dispatching plans, and the initial dispatching plans are selected based on the fitness to obtain a number of target initial dispatching plans. For example, the fitness of 500 initial dispatching plans is calculated using a preset fitness function. The target initial dispatching plans ranked in the top 200 in terms of fitness are selected as the target initial dispatching plans.

[0056] The identification pairs corresponding to the selected 200 target initial dispatching schemes are cross-operated and mutated to generate several processed dispatching schemes. Specifically, the selection operation is performed on the several initial dispatching schemes based on the fitness, and the selected several target initial dispatching schemes are cross-operated and mutated to generate several processed dispatching schemes, including: determining a preset quantity threshold according to the quantity of the several initial dispatching schemes, ranking the first fitness based on the numerical value of the first fitness, and screening out several target initial dispatching schemes corresponding to the preset quantity threshold from the several initial dispatching schemes according to the obtained first fitness ranking; the identification pairs corresponding to the several target initial dispatching schemes are cross-operated and mutated to generate several processed identification pairs, and several processed dispatching schemes are generated based on the several processed identification pairs. That is, by performing cross-operation and mutation operations on the target initial dispatching scheme to generate a processed dispatching scheme different from the target initial dispatching scheme, the diversity of the schemes can be increased, so as to find a dispatching scheme that meets the dispatching purpose.

[0057] It should be noted that the cross-operation can randomly select two target initial dispatching plans, and exchange the vehicle identifiers in the identification pairs corresponding to the target initial dispatching plans, and repeat the above steps multiple times to achieve the purpose of cross-operating the several target initial dispatching plans; it can also randomly select half of the target initial dispatching plans, and exchange the vehicle identifiers in the identification pairs corresponding to the target initial dispatching plans with the vehicle identifiers in the identification pairs corresponding to the other half of the target initial dispatching plans, so as to achieve the purpose of cross-operating the several target initial dispatching plans.

[0058] Furthermore, the mutation operation is based on the above-mentioned cross operation on the target initial dispatching plan, randomly selects a target initial dispatching plan with a preset mutation probability, and randomly changes any identifier in the identification pair corresponding to the plan, so as to achieve the purpose of performing mutation operations on the several target initial dispatching plans. Among them, the preset mutation probability can be determined according to the actual application situation. For example, the mutation operation randomly changes the maintenance technician identifier corresponding to a car with a probability of 5% to introduce new possibilities. It should be noted that in order to ensure the reliability of the processed dispatching plan generated by the mutation operation, the preset mutation probability needs to be lower than the preset mutation probability threshold. The preset mutation probability threshold can be specifically determined according to the actual application situation.

[0059] In this embodiment, several processed dispatching schemes are generated by performing selection operations, crossover operations and mutation operations on the several initial dispatching schemes, and the dispatching schemes are iteratively optimized by comparing the dispatching scheme with the highest fitness among the several initial dispatching schemes and the dispatching scheme with the highest fitness among the several processed dispatching schemes, and the dispatching schemes are iteratively optimized by the annealing algorithm. Specifically, the second fitness corresponding to the several processed dispatching schemes is calculated according to the preset fitness function; it is determined whether the maximum value of the second fitness is greater than the maximum value of the first fitness; if the maximum value of the second fitness is greater than the maximum value of the first fitness, the several processed dispatching schemes are used as several target processed dispatching schemes; if the maximum value of the second fitness is not greater than the maximum value of the first fitness, the annealing probability of determining the several processed dispatching schemes as several target processed dispatching schemes under the current number of iterations is calculated by the preset simulated annealing function, and the several target processed dispatching schemes are randomly determined from the several target initial dispatching schemes and the several processed dispatching schemes based on the annealing probability. That is, the simulated annealing algorithm is used to perform multiple iterations of optimization on the initial dispatching plans to improve the adaptability of the dispatching plans, thereby optimizing resource allocation, improving the work efficiency and satisfaction of maintenance technicians, and improving the quality and competitiveness of remote vehicle diagnostic services. Among them, the preset simulated annealing function is:

[0060] P = exp((F2-F1) / T);

[0061] Wherein, P is the value of the annealing probability, F2 is the maximum value of the second fitness, F1 is the maximum value of the first fitness, and T is a temperature parameter, which is negatively correlated with the current number of iterations. In addition, in the formula, "exp()" represents an exponential function with the natural constant e as the base.

[0062] The annealing probability can be calculated through the preset simulated annealing function, and the several target post-processing dispatching plans are randomly determined from the several target initial dispatching plans and the several post-processing dispatching plans according to the annealing probability, until the preset number of iterations is reached or the termination condition is met, and the optimal dispatching plan is output.

[0063] As can be seen from the above, the embodiment of the present application performs crossover operations and mutation operations on the several target initial dispatching plans to generate several processed dispatching plans, and iterates the several processed dispatching plans through a simulated annealing algorithm. This can prevent the final plan from falling into a local optimal situation, improve the fitness of the dispatching plan, so as to achieve the purpose of reasonably allocating dispatching resources, and can adjust the parameters in the preset fitness function according to the actual application situation, so as to adapt to complex and changeable actual situations.

[0064] For further information, see Figure 2 As shown, in order to prevent the situation where multiple iterations are performed and computing resources are wasted, the present application provides a remote dispatch optimization method, including:

[0065] Step S21, acquiring characteristic information of a plurality of target vehicles and a plurality of target maintenance personnel, and preprocessing the characteristic information to generate a plurality of vehicle identifiers corresponding to the plurality of target vehicles and a plurality of personnel identifiers corresponding to the plurality of target maintenance personnel according to the obtained preprocessed characteristic information.

[0066] Step S22: generating a plurality of initial dispatching plans according to the plurality of vehicle identifiers and the plurality of personnel identifiers, and calculating the fitness corresponding to the plurality of initial dispatching plans according to a preset fitness function.

[0067] Step S23: selecting the several initial dispatching plans based on the fitness, and performing crossover and mutation operations on the selected several target initial dispatching plans to generate several processed dispatching plans, and iterating the several processed dispatching plans through a simulated annealing algorithm to obtain several target processed dispatching plans.

[0068] Step S24: determine whether the dispatching plans after the target processing meet the preset target conditions, and generate corresponding judgment results.

[0069] In this embodiment, by judging whether the several target-processing dispatching schemes meet the preset target conditions, it is determined whether the current target-processing dispatching scheme can be output as the target dispatching scheme. The preset target conditions include but are not limited to preset iteration number conditions or preset fitness conditions. For example, it is judged whether the current iteration number reaches 100 times or there is no obvious change between the fitness corresponding to the several target-processing dispatching schemes of the current iteration round and the fitness corresponding to the several target-processing dispatching schemes of the previous iteration round. It can be understood that if the target-processing dispatching scheme meets the above conditions, it means that the fitness of the target-processing dispatching scheme has reached the saturation state, and continuing the iterative operation will not significantly improve the scheme. The current target-processing dispatching scheme can be output to avoid unnecessary iterative operations and waste of resources.

[0070] Step S25: processing the plurality of target processed order dispatching plans based on the judgment result to obtain the plurality of target order dispatching plans.

[0071] In this embodiment, the several target-processing order dispatching schemes are processed by the judgment result. If the judgment result indicates that the several target-processing order dispatching schemes meet the preset target conditions, the scheme with the highest fitness among the several target-processing order dispatching schemes is output as the target order dispatching scheme. Specifically, the processing of the several target-processing order dispatching schemes based on the preset target conditions to obtain the several target order dispatching schemes includes: judging whether the number of iterations of the several target-processing order dispatching schemes is less than a preset iteration number threshold; if the number of iterations of the several target-processing order dispatching schemes is not less than the preset iteration number threshold, taking the scheme with the highest fitness among the several target-processing order dispatching schemes as the target order dispatching scheme; if the number of iterations of the several target-processing order dispatching schemes is less than the preset iteration number threshold, judging whether the several target-processing order dispatching schemes meet the preset fitness conditions; if the several target-processing order dispatching schemes meet the preset fitness conditions, The scheme with the highest fitness among the several target-processing dispatching schemes is used as the target dispatching scheme; if the several target-processing dispatching schemes do not meet the preset fitness condition, the third fitness corresponding to the several target-processing dispatching schemes is calculated, and the next round of iterative operations for the several target-processing dispatching schemes is performed based on the third fitness until the number of iterations is not less than the preset iteration number threshold or the obtained several target-processing dispatching schemes meet the preset fitness condition; wherein the preset fitness condition is that the difference between the fitness of the several target-processing dispatching schemes corresponding to the current iteration round and the fitness of the several target-processing dispatching schemes corresponding to the previous iteration round is less than the preset fitness change threshold. That is, when the preset number of iterations is reached or the termination condition is met, the optimal dispatching scheme is output. This avoids wasting resources caused by performing unnecessary iteration operations, and also shortens the scheme generation time.

[0072] Among them, the specific implementation process of the above steps S21, S22 and S23 can refer to the corresponding content in the previous embodiment, and will not be repeated here.

[0073] As can be seen from the above, the embodiment of the present application performs crossover operations and mutation operations on the several target initial dispatching plans to generate several processed dispatching plans, and iterates the several processed dispatching plans through a simulated annealing algorithm, so as to prevent the final plan from falling into a local optimal situation. By judging whether the dispatching plan generated by the iterative operation meets the preset target conditions, the number of iterations is controlled to avoid wasting computing resources.

[0074] See also Figure 3 As shown, the present application provides a remote dispatch optimization device, comprising:

[0075] The characteristic information acquisition module 11 is used to acquire characteristic information of a plurality of target vehicles and a plurality of target maintenance personnel, and pre-process the characteristic information to generate a plurality of vehicle identifiers corresponding to the plurality of target vehicles and a plurality of personnel identifiers corresponding to the plurality of target maintenance personnel according to the obtained pre-processed characteristic information;

[0076] An initial plan generating module 12 is used to generate a plurality of initial dispatch plans according to the plurality of vehicle identifiers and the plurality of personnel identifiers, and calculate the fitness corresponding to the plurality of initial dispatch plans according to a preset fitness function;

[0077] The order dispatching plan iteration module 13 is used to select the several initial order dispatching plans based on the fitness, and perform crossover operations and mutation operations on the several selected target initial order dispatching plans to generate several processed order dispatching plans, and iterate the several processed order dispatching plans through a simulated annealing algorithm to obtain several target order dispatching plans.

[0078] As can be seen from the above, the present application performs crossover operations and mutation operations on the several target initial dispatching plans to generate several processed dispatching plans, and iterates the several processed dispatching plans through a simulated annealing algorithm, which can improve the fitness of the dispatching plan to achieve the purpose of reasonable allocation of dispatching resources, and can adjust the parameters in the preset fitness function according to the actual application situation, so as to adapt to complex and changeable actual situations.

[0079] In some specific implementations, the feature information acquisition module 11 may specifically include:

[0080] A characteristic information acquisition unit, used to acquire characteristic information of a plurality of target vehicles and a plurality of target maintenance personnel, and perform standardization processing on the characteristic information to obtain first characteristic information corresponding to the plurality of target vehicles and second characteristic information corresponding to the plurality of target maintenance personnel;

[0081] An identifier generating unit is used to generate a plurality of vehicle identifiers corresponding to the plurality of target vehicles according to the first characteristic information, and to generate a plurality of personnel identifiers corresponding to the plurality of target maintenance personnel according to the second characteristic information.

[0082] In some specific implementations, the initial solution generation module 12 may specifically include:

[0083] A fitness function generating unit, configured to determine fitness function parameters of a preset fitness function based on a preset dispatch target, and construct the preset fitness function according to the fitness function parameters; the preset dispatch target is a combination of a preset time target, a preset accuracy target, and a preset resource utilization rate target;

[0084] an identifier matching unit, configured to match the plurality of vehicle identifiers with the plurality of personnel identifiers to generate a plurality of identification pairs;

[0085] The dispatch plan generation unit is used to generate a number of initial dispatch plans based on the number of identification pairs, and calculate the first fitness corresponding to the number of initial dispatch plans according to the preset fitness function.

[0086] In some specific implementations, the dispatching plan iteration module 13 may specifically include:

[0087] A selection operation execution submodule is used to rank the first fitness based on the numerical value of the first fitness, and select a plurality of target initial dispatching plans corresponding to a preset quantity threshold from the plurality of initial dispatching plans according to the obtained first fitness ranking;

[0088] A cross-operation execution submodule, configured to perform a cross-operation on the identification pairs corresponding to the plurality of target initial dispatching schemes to generate a plurality of processed identification pairs, and generate a plurality of processed dispatching schemes based on the plurality of processed identification pairs;

[0089] a mutation operation execution submodule, configured to perform a mutation operation on the identification pairs corresponding to the plurality of target initial dispatching schemes to generate a plurality of processed identification pairs, and to generate a plurality of processed dispatching schemes based on the plurality of processed identification pairs;

[0090] The iterative operation execution submodule is used to iterate the several processed order dispatching schemes through a simulated annealing algorithm to obtain several target order dispatching schemes.

[0091] In some specific implementations, the iterative operation execution submodule may specifically include:

[0092] a fitness judgment unit, used for calculating the second fitness corresponding to the plurality of post-processing dispatching schemes according to the preset fitness function, and judging whether the second fitness is greater than the first fitness; if the second fitness is greater than the first fitness, taking the plurality of post-processing dispatching schemes as the plurality of target post-processing dispatching schemes; if the second fitness is not greater than the first fitness, determining the plurality of target post-processing dispatching schemes from the plurality of target initial dispatching schemes and the plurality of post-processing dispatching schemes based on the simulated annealing algorithm;

[0093] A target solution output unit, configured to process the plurality of target processed dispatch solutions based on preset target conditions to obtain the plurality of target dispatch solutions;

[0094] A first preset target condition judgment unit is used to judge whether the number of iterations of the several target processing order dispatching schemes is less than a preset iteration number threshold; if the number of iterations of the several target processing order dispatching schemes is not less than the preset iteration number threshold, the several target processing order dispatching schemes are used as target order dispatching schemes; if the number of iterations of the several target processing order dispatching schemes is less than the preset iteration number threshold, the third fitness corresponding to the several target processing order dispatching schemes is calculated, and the next round of iteration operations for the several target processing order dispatching schemes is performed based on the third fitness until the number of iterations is not less than the preset iteration number threshold;

[0095] A second preset target condition judgment unit is used to judge whether the several target processing order dispatching schemes meet the preset fitness conditions; if the several target processing order dispatching schemes meet the preset fitness conditions, the several target processing order dispatching schemes are used as target order dispatching schemes; if the several target processing order dispatching schemes do not meet the preset fitness conditions, the third fitness corresponding to the several target processing order dispatching schemes is calculated, and the next round of iterative operations for the several target processing order dispatching schemes are performed based on the third fitness until the obtained several target processing order dispatching schemes meet the preset fitness conditions;

[0096] Among them, the preset fitness condition is that the difference between the fitness of the dispatching scheme after processing several targets corresponding to the current iteration round and the fitness of the dispatching scheme after processing several targets corresponding to the previous iteration round is less than the preset fitness change threshold.

[0097] Furthermore, the present application also discloses an electronic device. Figure 4 It is a structural diagram of an electronic device 20 shown according to an exemplary embodiment, and the content in the figure cannot be regarded as any limitation on the scope of use of this application. The electronic device 20 may specifically include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input-output interface 25 and a communication bus 26. Among them, the memory 22 is used to store a computer program, and the computer program is loaded and executed by the processor 21 to implement the relevant steps in the remote dispatch optimization method disclosed in any of the aforementioned embodiments. In addition, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0098] In this embodiment, the power supply 23 is used to provide working voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and the external device, and the communication protocol it follows is any communication protocol that can be applied to the technical solution of the present application, and is not specifically limited here; the input and output interface 25 is used to obtain external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs and is not specifically limited here.

[0099] In addition, the memory 22 as a carrier for storing resources may be a read-only memory, a random access memory, a disk or an optical disk, etc. The resources stored thereon may include an operating system 221, a computer program 222, etc., and the storage method may be temporary storage or permanent storage.

[0100] The operating system 221 is used to manage and control the hardware devices and computer program 222 on the electronic device 20, which can be Windows Server, Netware, Unix, Linux, etc. In addition to including a computer program that can be used to complete the remote dispatch optimization method performed by the electronic device 20 disclosed in any of the aforementioned embodiments, the computer program 222 can further include a computer program that can be used to complete other specific tasks.

[0101] Furthermore, the present application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, the remote dispatch optimization method disclosed above is implemented. For the specific steps of the method, reference may be made to the corresponding contents disclosed in the above embodiments, and no further description will be given here.

[0102] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0103] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0104] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0105] Finally, it should be noted that, in this article, relational terms such as first and second, etc. 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 "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including 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, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0106] The technical solution provided by the present application is introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for general technicians in this field, according to the idea of ​​the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A remote dispatch optimization method, characterized in that: include: Acquire characteristic information of a plurality of target vehicles and a plurality of target maintenance personnel, and preprocess the characteristic information to generate a plurality of vehicle identifiers corresponding to the plurality of target vehicles and a plurality of personnel identifiers corresponding to the plurality of target maintenance personnel according to the obtained preprocessed characteristic information; Generating a plurality of initial dispatching schemes according to the plurality of vehicle identifiers and the plurality of personnel identifiers, and calculating the fitness corresponding to the plurality of initial dispatching schemes according to a preset fitness function; A selection operation is performed on the several initial order dispatching plans based on the fitness, and a crossover operation and a mutation operation are performed on the selected several target initial order dispatching plans to generate several processed order dispatching plans, and the several processed order dispatching plans are iterated through a simulated annealing algorithm to obtain several target order dispatching plans.

2. The remote dispatch optimization method according to claim 1, characterized in that: The step of acquiring characteristic information of a plurality of target vehicles and a plurality of target maintenance personnel, and preprocessing the characteristic information to generate a plurality of vehicle identifiers corresponding to the plurality of target vehicles and a plurality of personnel identifiers corresponding to the plurality of target maintenance personnel according to the obtained preprocessed characteristic information includes: Acquire characteristic information of a plurality of target vehicles and a plurality of target maintenance personnel, and perform standardization processing on the characteristic information to obtain first characteristic information corresponding to the plurality of target vehicles and second characteristic information corresponding to the plurality of target maintenance personnel; A plurality of vehicle identifiers corresponding to the plurality of target vehicles are generated according to the first characteristic information, and a plurality of personnel identifiers corresponding to the plurality of target maintenance personnel are generated according to the second characteristic information.

3. The remote dispatch optimization method according to claim 1, characterized in that: Before generating a plurality of initial dispatching schemes according to the plurality of vehicle identifiers and the plurality of personnel identifiers and calculating the fitness corresponding to the plurality of initial dispatching schemes according to a preset fitness function, the method further includes: Determining fitness function parameters of a preset fitness function based on a preset dispatch target, and constructing the preset fitness function according to the fitness function parameters; The preset dispatch target is a combination of a preset time target, a preset accuracy target and a preset resource utilization target.

4. The remote dispatch optimization method according to any one of claims 1 to 3, characterized in that: The generating a plurality of initial dispatching schemes according to the plurality of vehicle identifiers and the plurality of personnel identifiers, and calculating the fitness corresponding to the plurality of initial dispatching schemes according to a preset fitness function, includes: matching the plurality of vehicle identifiers with the plurality of personnel identifiers to generate a plurality of identification pairs; A number of initial dispatching plans are generated based on the number of identification pairs, and the first fitness corresponding to the number of initial dispatching plans is calculated according to the preset fitness function.

5. The remote dispatch optimization method according to claim 4, characterized in that: The selecting operation on the several initial dispatching plans based on the fitness, and performing a crossover operation and a mutation operation on the several selected target initial dispatching plans to generate several processed dispatching plans, including: Ranking the first fitness degrees based on the numerical values ​​of the first fitness degrees, and selecting a number of target initial dispatching plans corresponding to a preset quantity threshold from the number of initial dispatching plans according to the obtained first fitness rankings; A crossover operation and a mutation operation are performed on the identification pairs corresponding to the several target initial dispatching plans to generate several processed identification pairs, and several processed dispatching plans are generated based on the several processed identification pairs.

6. The remote dispatch optimization method according to claim 5, characterized in that: The simulated annealing algorithm is used to iterate the plurality of processed dispatching schemes to obtain a plurality of target dispatching schemes, including: Calculating the second fitness corresponding to the plurality of processed dispatching schemes according to the preset fitness function; Determine whether the second fitness is greater than the first fitness; if the second fitness is greater than the first fitness, use the plurality of post-processing dispatching schemes as a plurality of target post-processing dispatching schemes; if the second fitness is not greater than the first fitness, determine the plurality of target post-processing dispatching schemes from the plurality of target initial dispatching schemes and the plurality of post-processing dispatching schemes based on the simulated annealing algorithm; The plurality of target processed dispatching plans are processed based on preset target conditions to obtain the plurality of target dispatching plans.

7. The remote dispatch optimization method according to claim 6, characterized in that: The step of processing the plurality of target processed dispatching schemes based on the preset target conditions to obtain the plurality of target dispatching schemes includes: Determine whether the number of iterations of the several target-processing order dispatching schemes is less than a preset iteration number threshold; if the number of iterations of the several target-processing order dispatching schemes is not less than the preset iteration number threshold, use the several target-processing order dispatching schemes as target order dispatching schemes; if the number of iterations of the several target-processing order dispatching schemes is less than the preset iteration number threshold, calculate the third fitness corresponding to the several target-processing order dispatching schemes, and execute the next round of iteration operations for the several target-processing order dispatching schemes based on the third fitness until the number of iterations is not less than the preset iteration number threshold; Or, determine whether the several target order dispatching schemes after processing meet the preset fitness conditions; if the several target order dispatching schemes after processing meet the preset fitness conditions, use the several target order dispatching schemes after processing as target order dispatching schemes; if the several target order dispatching schemes after processing do not meet the preset fitness conditions, calculate the third fitness corresponding to the several target order dispatching schemes after processing, and perform the next round of iterative operations on the several target order dispatching schemes after processing based on the third fitness, until the obtained several target order dispatching schemes after processing meet the preset fitness conditions; Among them, the preset fitness condition is that the difference between the fitness of the dispatching scheme after processing several targets corresponding to the current iteration round and the fitness of the dispatching scheme after processing several targets corresponding to the previous iteration round is less than the preset fitness change threshold.

8. A remote dispatch optimization device, characterized in that: include: A feature information acquisition module, used to acquire feature information of a plurality of target vehicles and a plurality of target maintenance personnel, and preprocess the feature information to generate a plurality of vehicle identifiers corresponding to the plurality of target vehicles and a plurality of personnel identifiers corresponding to the plurality of target maintenance personnel according to the obtained preprocessed feature information; An initial scheme generating module, used to generate a plurality of initial dispatching schemes according to the plurality of vehicle identifiers and the plurality of personnel identifiers, and calculate the fitness corresponding to the plurality of initial dispatching schemes according to a preset fitness function; The order dispatching plan iteration module is used to select the several initial order dispatching plans based on the fitness, and perform crossover and mutation operations on the several selected target initial order dispatching plans to generate several processed order dispatching plans, and iterate the several processed order dispatching plans through a simulated annealing algorithm to obtain several target order dispatching plans.

9. An electronic device, characterized in that: include: Memory, used to store computer programs; A processor, used to execute the computer program to implement the remote dispatch optimization method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Used to store a computer program, wherein when the computer program is executed by a processor, the remote dispatch optimization method according to any one of claims 1 to 7 is implemented.

Images