On-site supervision task scheduling method and system for digital intelligent integrated platform

Abstract

The present application provides a method and system for scheduling on-site supervision tasks for a digital intelligent integrated platform. The scheduling method includes: obtaining the basic information of all supervision tasks and the basic information of experts who can currently perform supervision tasks; performing a first encoding operation on the supervision tasks to obtain a first population composed of corresponding first chromosomes; performing a second encoding operation on the experts to obtain a second population composed of corresponding second chromosomes; performing matching calculations on the chromosomes in the first population and the second population one by one to obtain a fitness value; judging whether the difference between the current best fitness and the historical best fitness is less than a preset threshold; if it is judged that the difference between the current best fitness and the historical best fitness is less than the threshold, selecting the first chromosome and the second chromosome corresponding to the historical best fitness as the optimal scheduling scheme, and if it is greater than or equal to the threshold, performing selection, crossover and mutation operations on the first population or the second population.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment supervision, and in particular to a method and system for scheduling on-site supervision tasks for a digital intelligent integrated platform. Background Art

[0002] Currently, equipment supervision has yet to establish a scientific and standardized management system. Learning and strengthening are ongoing practices, leading to numerous problems that inevitably arise during the supervision process, seriously impacting the quality and performance of equipment production. Existing supervision task scheduling techniques lack efficient algorithms, hindering effective coordination of supervision tasks and the experts who carry them out. This results in chaotic scheduling and low overall completion and efficiency. Summary of the Invention

[0003] The purpose of the embodiments of the present invention is to provide a method and system for scheduling on-site supervision tasks for a digital intelligent integrated platform, which can improve the overall execution efficiency of supervision tasks.

[0004] To achieve the above objectives, an embodiment of the present invention provides a method for scheduling on-site supervision tasks for a digital intelligent integrated platform, comprising:

[0005] Obtain basic information of all supervision tasks and basic information of experts currently capable of performing supervision tasks;

[0006] Performing a first encoding operation on the supervision task to obtain a first population consisting of corresponding first chromosomes;

[0007] performing a second encoding operation on the experts to obtain a second population consisting of corresponding second chromosomes;

[0008] Perform matching calculation on the chromosomes in the first population and the second population one by one to obtain a fitness value;

[0009] Determine whether the difference between the current best fitness and the historical best fitness is less than a preset threshold;

[0010] When it is determined that the difference between the current best fitness and the historical best fitness is less than the threshold, the first chromosome and the second chromosome corresponding to the historical best fitness are selected as the optimal scheduling solution;

[0011] When it is determined that the difference between the current best fitness and the historical best fitness is greater than or equal to the threshold, selection, crossover and mutation operations are performed on the first population or the second population, and the step of performing matching calculations on the chromosomes in the first population and the second population one by one to obtain fitness values ​​is returned again, until it is determined that the difference between the current best fitness and the historical best fitness is less than the threshold.

[0012] Optionally, the basic information of the supervision task includes the duration, type attributes, and priority of the supervision task;

[0013] The expert's basic information includes the expert's professional type, supervision method and corresponding time window.

[0014] Optionally, the first encoding operation includes:

[0015] Randomly arrange the supervision tasks in chronological order based on the day;

[0016] Performing a second encoding operation on the experts to obtain a second population consisting of the corresponding second chromosomes includes:

[0017] Taking days as units and according to the minimum number of supervisors for the supervision task, the experts' time windows are arranged into multiple sequences in chronological order.

[0018] Optionally, performing matching calculation on the chromosomes in the first population and the second population one by one to obtain a fitness value includes:

[0019] randomly selecting an unselected first chromosome from the first population and randomly selecting an unselected second chromosome from the second population;

[0020] The fitness value is calculated according to formula (1),

[0021]

[0022] Among them, S pk is the fitness value corresponding to the pth first chromosome and the kth second chromosome, x ij is the matching degree between the expert’s patent capability and the supervision task requirements in the jth work unit time period, i is an integer number, N is the number of supervision task requirements, t ij is the matching degree x ij The weight of, S is the number of experts, x s is the average matching degree of the s-th expert, is the average matching degree of all experts, Y is the number of supervision tasks, x y is the average matching degree of the y-th supervision task, is the average value of the matching degree of all the supervision tasks.

[0023] Optionally, performing selection, crossover, and mutation operations on the first population or the second population includes:

[0024] Read the types of objects selected, crossed, and mutated during the previous iteration;

[0025] According to formula (2), the fitness difference change rate under the current number of iterations is calculated.

[0026]

[0027] Among them, Δ a,a-1 is the fitness difference between the ath and a-1th iterations, S a-1pk -S a-2pk is the fitness difference between the a-1th and a-2th iterations, Δ a,a-1 is the fitness difference change rate of the ath time;

[0028] Determine whether the current fitness difference change rate is greater than 1;

[0029] When it is determined that the current fitness difference change rate is greater than 1, another type of object in the previous iteration process is selected as the object of selection, crossover and mutation operations in this iteration process.

[0030] Optionally, when the type of the objects of the selection, crossover, and mutation operations is the first population, the crossover operation includes:

[0031] Selecting the first chromosome whose current fitness value is less than the maximum fitness value as the first set to be operated;

[0032] Randomly select two first chromosomes from the first set to be operated;

[0033] exchanging a sequence on the two selected first chromosomes, wherein the sequence includes the complete supervision task;

[0034] Randomly swapping the duplicate supervision tasks on the two swapped first chromosomes to ensure that no duplicate supervision tasks exist on each of the first chromosomes;

[0035] Mutation operations include:

[0036] When the type of the object of the selection, crossover and mutation operation is the first population, selecting the first chromosome whose current fitness value is less than the maximum fitness value as the second set to be operated;

[0037] Randomly select a first chromosome from the second set to be operated;

[0038] Randomly intercepting a sequence on the selected first chromosome, where the sequence includes the complete supervision task;

[0039] Randomly sorting the supervision tasks on the selected sequence to obtain a new sequence;

[0040] The new sequence is replaced back into the first chromosome of choice.

[0041] Optionally, when the type of the objects of the selection, crossover, and mutation operations is the second population, the crossover operation includes:

[0042] Selecting the first chromosome whose current fitness value is less than the maximum fitness value as the second set to be operated;

[0043] Randomly select two second chromosomes from the second set to be operated;

[0044] Exchange a sequence on the two selected second chromosomes;

[0045] The time windows of the experts on the two second chromosomes after the exchange are randomly exchanged to determine that there is no repeated time window of the expert on each second chromosome;

[0046] Mutation operations include:

[0047] When the type of the object of the selection, crossover and mutation operations is the second population, selecting the second chromosome whose current fitness value is less than the maximum fitness value as the second set to be operated;

[0048] Randomly selecting a second chromosome from the second set to be operated;

[0049] Randomly intercepting a sequence on the selected second chromosome, wherein the sequence includes a complete supervision task;

[0050] Randomly sort the supervision tasks on the selected sequence to obtain a new sequence;

[0051] The new sequence is replaced back into the selected second chromosome.

[0052] Optionally, the scheduling method includes:

[0053] The first chromosome or the second chromosome with the smallest current fitness value is selected to perform a crossover operation with the first chromosome or the second chromosome with the smallest historical fitness value, and the chromosome after the crossover operation is added to the new first population or the second population.

[0054] Optionally, the scheduling method further includes:

[0055] Determine whether the current number of iterations is greater than a preset iteration threshold;

[0056] When it is determined that the current number of iterations is greater than the iteration threshold, selection, crossover and mutation operations are performed on the first population and the second population at the same time, and the step of performing matching calculations on the chromosomes in the first population and the second population one by one to obtain fitness values ​​is returned again, until it is determined that the difference between the current best fitness and the historical best fitness is less than the threshold.

[0057] On the other hand, the present invention also provides an on-site supervision task scheduling system for a digital intelligent integrated platform, wherein the scheduling system includes a processor configured to execute any of the scheduling methods described above.

[0058] Through the above-mentioned technical solution, the method and system for scheduling on-site supervision tasks provided by the present invention separately encodes the time windows of the supervision task and the expert who performs it, calculates it using a fitness function that combines attributes, and iterates through operations such as selection, crossover, and mutation to ultimately generate an efficient scheduling solution. Compared to existing technologies, this method replaces the existing methods that rely on manual scheduling, improving scheduling efficiency and the execution efficiency of supervision tasks.

[0059] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following detailed description, they are used to explain the embodiments of the present invention, but do not constitute a limitation of the embodiments of the present invention. In the accompanying drawings:

[0061] Figure 1 is a flow chart of a method for scheduling on-site supervision tasks according to one embodiment of the present invention;

[0062] Figure 2 is a flow chart of a method for scheduling on-site supervision tasks according to one embodiment of the present invention;

[0063] Figure 3 is a partial flow chart of a method for scheduling on-site supervision tasks according to one embodiment of the present invention;

[0064] Figure 4 is a partial flow chart of a method for scheduling on-site supervision tasks according to one embodiment of the present invention;

[0065] Figure 5 is a partial flow chart of a method for scheduling on-site supervision tasks according to one embodiment of the present invention;

[0066] Figure 6 is a partial flow chart of a method for scheduling on-site supervision tasks according to one embodiment of the present invention;

[0067] Figure 7 The figure is a block diagram of the internal structure of a scheduling system for on-site supervision tasks according to one embodiment of the present invention.

[0068] Figure 82 is a schematic diagram of the architecture of an intelligent integrated platform for implementing on-site supervision tasks according to an embodiment of the present invention. DETAILED DESCRIPTION

[0069] The following describes the specific embodiments of the present application in detail with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are only used to illustrate and explain the present application and are not intended to limit the present application.

[0070] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back, etc.), such directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0071] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of such features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the fact that they can be implemented by ordinary technicians in this field. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0072] Figure 8 FIG. 1 is a schematic diagram of the architecture of an intelligent integrated platform system for realizing on-site supervision tasks according to an embodiment of the present invention. Figure 8 As shown, in one embodiment of the present application, on-site supervision tasks are implemented by building an intelligent integrated platform. The intelligent integrated platform uses a multi-standard management system to centrally manage task management, intelligent visual monitoring, cloud workstations, and information centers.

[0073] The intelligent integrated platform system has the following functions and advantages:

[0074] Based on SOA concept, B / S application architecture, supports XML and WebService, and supports various mainstream operating systems and database platforms;

[0075] The various components in the intelligent integrated platform system complete most of the system function construction work in a configuration manner, with less secondary development. At the same time, it supports the integrated operation and data sharing of various functional modules of the system, and realizes unified query and centralized operation of important information, reducing the frequent switching of operation interfaces in the system for similar business operations;

[0076] Adopting the platform's standard functions to achieve integration between system modules (sub-modules) and provide standard interfaces for integration with other application systems;

[0077] Secondary development uses platform tools and standard development technologies, mainly used to supplement or expand standard functions, ensure integration with the original product system and have necessary configurable functions. Functional expansion and adjustment can be flexibly carried out according to changes in business needs. The secondary development code is concise, efficient, stable and reliable.

[0078] Single-point (one-time) entry of source data ensures the independence and sharing of source data, supports batch data import and has certain error correction functions;

[0079] Supports flexible setting of organizational structure levels to meet the requirements of the existing three-level management system. If there is a change in the organizational structure, the hierarchical relationship can be changed without affecting the use of the system. The positions, roles and permissions of system users can be flexibly defined, and authorization can be carried out according to business categories and forms, realizing hierarchical authorization management of the system.

[0080] Provide management and supervision tools that can configure the system's basic data, control module functions, and view system logs;

[0081] It can record user login and operation information and form log files, which can be used to query the current online status of users and the operation status of the system at any time;

[0082] It can count the activity status of each system transaction and provide data support for system administrators to understand the system operation status;

[0083] It can intelligently plan an efficient time arrangement plan for multiple supervision tasks and experts' time arrangements, and efficiently dispatch the experts' working time while meeting the time and professional requirements of the supervision tasks.

[0084] The on-site supervision task scheduling method for a digital intelligent integrated platform disclosed in this application is intended to realize the function of "intelligently planning an efficient time scheduling plan based on the time scheduling of multiple supervision tasks and experts" in the above-mentioned intelligent integrated platform system.

[0085] In one embodiment of this application, a big data center for construction supervision is established to provide decision support for the intelligent integrated platform system, forming a global data repository for construction supervision tasks. Multi-dimensional and multi-angle data mining supports management decisions. This big data center includes an expert database, a shared data center, and a central system display for centralized information sharing.

[0086] In one embodiment of the present application, the intelligent integrated platform system displays, analyzes, and summarizes key indicator data through a smart data dashboard, showcasing the operational status of each key indicator, including a hierarchical display of indicators for each company, site, task, and equipment scenario. This enables intelligent monitoring, real-time alarms, security management, task scheduling and command, and intelligent data analysis.

[0087] In one embodiment of the present application, the above-mentioned intelligent integrated platform system can be configured on a mobile terminal to build an intelligent mobile Internet platform.

[0088] In one embodiment of the present application, the above-mentioned intelligent integrated platform system solves the problem of incomplete knowledge of equipment manufacturing processes by on-site supervisors by establishing a remote diagnosis intervention program for the intelligent cloud supervision platform, overcomes geographical and time limitations, realizes the value of equipment supervision data services, and provides high-value supervision data resource services for the supervision industry.

[0089] In one embodiment of the present application, in order to standardize the on-site operation links of the supervision task and make the process transparent, QR code scanning technology is used to realize mobile scanning information sharing, so as to meet the data management needs of multiple users for each operation link of equipment supervision. First, a QR code identification is given to the supervision equipment, and one code covers the entire life cycle management of the equipment. Then, a QR code identification is given to the supervision task to view the progress of the task in real time. At the same time, the task QR code is generated in the task establishment business, and the corresponding equipment QR code is generated in the equipment information maintenance business program. The static information of the QR code that can be obtained by scanning the equipment and task QR code includes relevant basic information such as the task name, task number, and manufacturing unit. The dynamic information that can be obtained includes witness task situation analysis, quality problem defect processing, equipment, briefings and other related information. The QR code can support scanning by multiple applications.

[0090] In one embodiment of this application, the intelligent integrated platform system can be configured with an intelligent inspection function in conjunction with the aforementioned QR code scanning technology. Supervisors and manufacturers can use mobile devices to scan the project's mobile QR code to display basic project information and progress. During offline inspections, inspectors identify the object and code, and their mobile devices scan the device's QR code to display basic equipment information and progress. If hidden dangers or defects are discovered, feedback can be uploaded promptly, preventing accidents and improving work efficiency.

[0091] The algorithm for scheduling and directing tasks in the above-mentioned intelligent integrated platform system is an improved method based on the genetic algorithm in the field of data mining. Figure 1 This is a flow chart of a method for scheduling on-site supervision tasks according to one embodiment of the present invention. Figure 1 In the example, the scheduling method may include:

[0092] In step S10, basic information of all supervision tasks and basic information of experts who can currently perform supervision tasks are obtained, wherein the basic information of the supervision tasks may include the duration, type attributes and priority of the supervision tasks; the basic information of the experts may include the professional type of the experts, the supervision method and the corresponding time window.

[0093] In step S11, a first encoding operation is performed on the supervision tasks to obtain a first population consisting of corresponding first chromosomes. Specifically, the first encoding operation can be to randomly arrange the supervision tasks in chronological order based on days. The first chromosome can represent a sequence of time windows of the supervision tasks. In this embodiment, the first chromosome can be represented as, for example, T=t 11 ,t 12 ,t 13 ,…,t mn ,…,t MN Among them, t mn It represents the duration of the nth day of the mth supervision task, M represents the number of supervision tasks, and N represents the number of days of the corresponding duration;

[0094] In step S12, a second encoding operation is performed on the experts to obtain a second population consisting of corresponding second chromosomes. Specifically, the second encoding operation can be to arrange the time windows of the experts into multiple sequences in chronological order based on the minimum number of supervisors for the supervision task, taking days as units. The second chromosome can be used to represent the time window sequence of the experts. In this embodiment, the second chromosome can be represented as, for example: P = p 11 ,p 12 ,p 21 ,…,p mn ,…,p MN Among them, p mn represents the time window of the mth expert on the nth day. It is important to note that, unlike the supervision tasks, the duration of each supervision task in the first chromosome corresponding to the supervision task is continuous, meaning that the next supervision task will not begin until a single supervision task is completed. However, the time window of the expert corresponding to the second chromosome serves the supervision task and can therefore be discontinuous.

[0095] In step S13, the chromosomes in the first population and the second population are matched one by one to obtain a fitness value. The fitness value calculation formula can be formula (1),

[0096]

[0097] Among them, S pkis the fitness value corresponding to the pth first chromosome and the kth second chromosome, x ij is the degree of matching between the expert's ability and the requirements of the supervision task in the jth work unit time period, i is an integer number, N is the number of requirements of the supervision task, t ij is the matching degree x ij The weight of S is the number of experts, x s is the average matching degree of the s-th expert, is the average matching degree of all experts, Y is the number of supervision tasks, x y is the average matching degree of the y-th supervision task, The calculation idea of ​​the fitness function is mainly based on the matching degree between experts and supervision tasks and the balance of matching degree, so as to ensure that each supervision task can be completed by a sufficiently strong team of experts.

[0098] In step S14, it is determined whether the difference between the current best fitness and the historical best fitness is less than a preset threshold. The determination of whether the difference is less than the threshold is primarily to confirm whether the current algorithm has converged. If convergence occurs, it indicates that the currently generated scheduling solution is the optimal solution. Otherwise, further iteration is required, i.e., subsequent selection, crossover, and mutation operations.

[0099] In step S15, when it is determined that the difference between the current best fitness and the historical best fitness is less than the threshold, the first chromosome and the second chromosome corresponding to the historical best fitness are selected as the optimal scheduling solution;

[0100] In step S16, when it is determined that the difference between the current best fitness and the historical best fitness is greater than or equal to the threshold, selection, crossover and mutation operations are performed on the first population or the second population, and the step of performing matching calculations on the chromosomes in the first population and the second population one by one to obtain fitness values ​​is returned again, until it is determined that the difference between the current best fitness and the historical best fitness is less than the threshold.

[0101] When it is determined that the difference between the current best fitness and the historical best fitness is greater than or equal to the threshold, it means that the current scheduling scheme needs to be further optimized, and therefore selection, crossover, and mutation operations need to be performed.

[0102] Since the scheduling method is generated by matching two chromosomes, the operations of selection, crossover and mutation need to be performed on the two chromosomes separately. In order to determine which chromosome to perform the selection, crossover and mutation operations, in this embodiment, the following can be used: Figure 2Specifically, Figure 2 In, the method may include:

[0103] In step S20, the types of objects selected, crossed, and mutated in the previous iteration are read;

[0104] In step S21, the fitness difference change rate under the current number of iterations is calculated according to formula (2):

[0105]

[0106] Among them, Δ a,a-1 is the fitness difference between the ath and a-1th iterations, S a-1pk -S a-2pk is the fitness difference between the a-1th and a-2th iterations, Δ a,a-1 is the fitness difference change rate of the ath time;

[0107] In step S22, it is determined whether the current fitness difference change rate is greater than 1;

[0108] In step S23 , when it is determined that the current fitness difference change rate is greater than 1, another type of object in the previous iteration is selected as the object of selection, crossover and mutation operations in this iteration.

[0109] Calculating and determining the fitness difference rate of change is primarily to determine whether the previous selection, crossover, or mutation operation iterated the overall scheduling solution in a more optimal direction. If the fitness difference rate of change is greater than 1, it indicates that the previous iteration was more optimal and should be continued. Otherwise, it indicates that the previous iteration was less optimal and the selection, crossover, or mutation operation should be performed in a different direction.

[0110] For selection, crossover and mutation operations, they can be performed separately according to the different characteristics of the supervision task and the expert's time window. Figures 3 to 6 The selection, crossover, and mutation operations are a chromosome update method in the genetic algorithm. They are mainly used to update the first and second chromosomes, that is, to update the duration of the supervision task and the arrangement order of the expert's time window. Then, through the calculation and screening of the fitness function, a better scheduling plan is generated in the process of continuous iteration.

[0111] Specifically, when the type of the object of selection, crossover and mutation operation is the first population, the crossover operation is as follows: Figure 3 As shown. Figure 3 In, the method may include:

[0112] In step S30, the first chromosome whose current fitness value is less than the maximum fitness value is selected as the first set to be operated;

[0113] In step S31, two first chromosomes are randomly selected from the first set to be operated;

[0114] In step S32, a sequence on the two selected first chromosomes is exchanged, and the sequence includes the complete supervision task;

[0115] In step S33, the repeated supervision tasks on the two swapped first chromosomes are randomly swapped to determine that there is no repeated supervision task on each of the first chromosomes.

[0116] When the type of objects of selection, crossover and mutation operations is the first population, the mutation operation is as follows Figure 4 As shown. Figure 4 In, the method may include:

[0117] In step S40, the first chromosome whose current fitness value is less than the maximum fitness value is selected as the second set to be operated;

[0118] In step S41, a first chromosome is randomly selected from the second set to be operated;

[0119] In step S42, a sequence is randomly intercepted on the selected first chromosome, and the sequence includes the complete supervision task;

[0120] In step S43, the supervision tasks on the selected sequence are randomly sorted to obtain a new sequence;

[0121] In step S44, the new sequence is replaced back into the selected first chromosome.

[0122] When the type of objects of selection, crossover and mutation operations is the second population, the crossover operation is as follows Figure 5 As shown. Figure 5 In, the method may include:

[0123] In step S50, the second chromosome whose current fitness value is less than the maximum fitness value is selected as the second set to be operated;

[0124] In step S51, two second chromosomes are randomly selected from the second set to be operated;

[0125] In step S52, a sequence on the two selected second chromosomes is exchanged;

[0126] In step S53, the time windows of the experts on the two exchanged second chromosomes are randomly exchanged to determine that there is no repeated time window of the expert on each of the first chromosomes.

[0127] When the type of objects of selection, crossover and mutation operations is the second population, the mutation operation is as follows Figure 6 As shown. Figure 6 In , the mutation operation may include:

[0128] In step S60, the second chromosome whose current fitness value is less than the maximum fitness value is selected as the second set to be operated;

[0129] In step S61, a second chromosome is randomly selected from the second set to be operated;

[0130] In step S62, a sequence is randomly intercepted on the selected second chromosome, and the sequence includes the complete supervision task;

[0131] In step S63, the supervision tasks on the selected sequence are randomly sorted to obtain a new sequence;

[0132] In step S64, the new sequence is replaced back into the selected first chromosome.

[0133] Furthermore, during the iteration process, to accelerate the process of obtaining the optimal scheduling solution, relatively optimal chromosomes may be selected for crossover and mutation during the crossover and mutation operations, thereby achieving faster iteration of the optimal solution. Specifically, the first chromosome with the lowest current fitness value may be selected to perform a crossover operation with the first chromosome with the lowest historical fitness value, and the chromosome after the crossover operation may be added to the new first population or second population.

[0134] In addition, if the number of iterations is too many and the convergence result cannot be obtained, it means that the algorithm has fallen into a local dead loop. An iteration threshold can also be set and a judgment is made, that is, whether the current number of iterations is greater than the preset iteration threshold; when it is judged that the current number of iterations is greater than the iteration threshold, selection, crossover and mutation operations are performed on the first population and the second population at the same time, and the step of matching the chromosomes in the first population and the second population one by one to obtain the fitness value is returned again, until it is judged that the difference between the current best fitness and the historical best fitness is less than the threshold, thereby avoiding the algorithm from entering a local dead loop.

[0135] On the other hand, Figure 7As shown, the present invention further provides a scheduling system 200 for on-site supervision tasks, the scheduling system comprising a processor 201, and the processor is configured to execute any of the scheduling methods described above.

[0136] Through the above-mentioned technical solution, the method and system for scheduling on-site supervision tasks provided by the present invention separately encodes the time windows of the supervision task and the expert who performs it, calculates it using a fitness function that combines attributes, and iterates through operations such as selection, crossover, and mutation to ultimately generate an efficient scheduling solution. Compared to existing technologies, this method replaces the existing methods that rely on manual scheduling, improving scheduling efficiency and the execution efficiency of supervision tasks.

[0137] The scheduling method for the above-mentioned on-site supervision tasks is implemented based on the intelligent integrated platform. The method of scheduling supervision tasks through the intelligent integrated platform is more efficient than the traditional method. The traditional method generally involves assigning professional supervision engineers to the production site for on-site supervision to conduct inspections of equipment production. This can also achieve equipment supervision and ensure the quality of the equipment production, procurement and installation process. However, this cloud supervision system uses video surveillance V points from different perspectives to monitor equipment on the production site, greatly reducing the workload and difficulty of supervision engineers.

[0138] The above describes in detail the optional implementation methods of the examples of the present invention in conjunction with the accompanying drawings. However, the implementation methods of the present invention are not limited to the specific details in the above implementation methods. Within the technical concept of the implementation methods of the present invention, various simple modifications can be made to the technical solutions of the implementation methods of the present invention, and these simple modifications all fall within the scope of protection of the implementation methods of the present invention.

[0139] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any appropriate manner without contradiction. To avoid unnecessary repetition, the embodiments of the present invention will not further describe various possible combinations.

[0140] Those skilled in the art will appreciate that all or part of the steps in the above-described embodiments can be implemented by instructing the relevant hardware through a program. The program is stored in a storage medium and includes a number of instructions for causing a device (such as a microcontroller or chip) or a processor to execute all or part of the steps in the various embodiments of the present application. The aforementioned storage medium includes various media capable of storing program code, such as a USB flash drive, a mobile hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0141] In addition, various different embodiments of the embodiments of the present invention may be arbitrarily combined, and as long as they do not violate the concept of the embodiments of the present invention, they should also be regarded as the contents disclosed in the embodiments of the present invention.

Claims

1. A method for scheduling on-site supervision tasks for a digital intelligent integrated platform, characterized in that: The scheduling method comprises: Obtaining basic information of all supervision tasks and basic information of experts who can currently perform supervision tasks, wherein the basic information of the supervision tasks includes the duration, type attributes and priority of the supervision tasks, and the basic information of the experts includes the professional type of the experts, supervision methods and corresponding time windows; Performing a first encoding operation on the supervision task to obtain a first population consisting of corresponding first chromosomes; Performing a second encoding operation on the expert to obtain a second population consisting of a corresponding second chromosome; Performing matching calculation on the chromosomes in the first population and the second population one by one to obtain a fitness value; Determine whether the difference between the current best fitness and the historical best fitness is less than a preset threshold; When it is determined that the difference between the current best fitness and the historical best fitness is less than the threshold, the first chromosome and the second chromosome corresponding to the historical best fitness are selected as the optimal scheduling solution; In the case that it is determined that the difference between the current best fitness and the historical best fitness is greater than or equal to the threshold, performing selection, crossover and mutation operations on the first population or the second population, and returning to perform the step of performing matching calculations on the chromosomes in the first population and the second population one by one to obtain fitness values, until it is determined that the difference between the current best fitness and the historical best fitness is less than the threshold; The first encoding operation and the second encoding operation include: The supervision tasks are randomly arranged in chronological order on a daily basis; Taking days as units, the time windows of the experts are arranged into multiple sequences in chronological order according to the minimum number of supervisors for the supervision task; The step of performing matching calculation on the chromosomes in the first population and the second population one by one to obtain a fitness value comprises: randomly selecting an unselected first chromosome from the first population and randomly selecting an unselected second chromosome from the second population; The fitness value is calculated according to formula (1): ，（1） in, For the The first chromosome and The fitness value corresponding to the second chromosome, For the The degree of match between the professional capabilities of the experts and the requirements of the supervision task during the work unit period, is an integer sequence number, The required quantity for the supervision task, For the matching degree The weight of is the number of experts, For the The average matching degree of experts, is the average matching degree of all experts, is the number of the supervision tasks, For the The average matching degree of the supervision tasks is It is the average value of the matching degree of all the supervision tasks.

2. The scheduling method according to claim 1, characterized in that: Performing selection, crossover, and mutation operations on the first population or the second population includes: Read the type of objects selected, crossed, and mutated during the previous iteration; According to formula (2), the fitness difference change rate under the current number of iterations is calculated. ，（2） in, For the Second and The fitness difference between the iterations, For the Second and The fitness difference between the iterations, For the The rate of change of fitness difference; Determine whether the current fitness difference change rate is greater than 1; When it is determined that the current fitness difference change rate is greater than 1, another type of the object in the previous iteration process is selected as the object of selection, crossover and mutation operations in this iteration process.

3. The scheduling method according to claim 2, characterized in that: When the type of the object of the selection, crossover and mutation operation is the first population, the crossover operation includes: Selecting the first chromosome whose current fitness value is less than the maximum fitness value as the first set to be operated; Randomly select two first chromosomes from the first set to be operated; Exchanging a sequence on the two selected first chromosomes, wherein the sequence includes the complete supervision task; Randomly exchange the repeated supervision tasks on the two first chromosomes after the exchange, so as to determine that there is no repeated supervision task on each of the first chromosomes; The mutation operation includes: When the type of the object of the selection, crossover and mutation operation is the first population, selecting the first chromosome whose current fitness value is less than the maximum fitness value as the second set to be operated; Randomly select a first chromosome from the second set to be operated; Randomly intercept a sequence on the selected first chromosome, and the sequence includes the complete supervision task; Randomly sorting the supervision tasks on the selected sequence to obtain a new sequence; The new sequence is replaced back into the first chromosome of choice.

4. The scheduling method according to claim 2, characterized in that: When the type of the object of the selection, crossover and mutation operation is the second population, the crossover operation includes: Selecting the second chromosome whose current fitness value is less than the maximum fitness value as the second set to be operated; Randomly selecting two second chromosomes from the second set to be operated; Exchange a sequence on the two selected second chromosomes; Randomly exchange the time windows of the experts on the two exchanged second chromosomes to determine that there is no repeated time window of the expert on each of the first chromosomes; The mutation operation includes: When the type of the object of the selection, crossover and mutation operation is the second population, selecting the second chromosome whose current fitness value is less than the maximum fitness value as the second set to be operated; Randomly selecting a second chromosome from the second set to be operated; Randomly intercept a sequence on the selected second chromosome, and the sequence includes the complete supervision task; Randomly sorting the supervision tasks on the selected sequence to obtain a new sequence; The new sequence is replaced back into the second chromosome of choice.

5. The scheduling method according to claim 3 or 4, characterized in that: The scheduling method comprises: A first chromosome or a second chromosome with the smallest current fitness value is selected to perform a crossover operation with a first chromosome or a second chromosome with the smallest historical fitness value, and the chromosome after the crossover operation is added to the new first population or the second population.

6. The scheduling method according to claim 1, characterized in that: The scheduling method further includes: Determine whether the current number of iterations is greater than a preset iteration threshold; When it is determined that the current number of iterations is greater than the iteration threshold, selection, crossover and mutation operations are performed on the first population and the second population at the same time, and the step of performing matching calculations on the chromosomes in the first population and the second population one by one to obtain fitness values ​​is returned again, until it is determined that the difference between the current best fitness and the historical best fitness is less than the threshold.

7. A resident supervision task scheduling system for a digital intelligent integrated platform, characterized in that: The scheduling system comprises a processor, and the processor is configured to execute the scheduling method according to any one of claims 1 to 6.

Images