Task scheduling method and apparatus, computing processing device, computer program and computer readable medium

Abstract

The present disclosure provides a task scheduling method, device, computing processing equipment, computer program and computer readable medium. The task scheduling method comprises: obtaining a plurality of inspection tasks to be scheduled and at least one inspection device responsible for processing the plurality of inspection tasks, wherein each inspection task has a different task identifier; generating a gene sequence according to the inspection tasks and the inspection device, the gene sequence comprising a correspondence between the inspection tasks and the inspection devices processing the inspection tasks, and the genes in the gene sequence being the task identifiers of the inspection tasks; iteratively updating the gene sequence until an iteration stop condition is met, and scheduling the inspection tasks according to the updated gene sequence. The technical solution of the present disclosure can shorten the longest working time of the inspection devices, make the running time of each inspection device more balanced, avoid the situation where some inspection devices are in high-load operation while other inspection devices are idle, and also improve the utilization rate of the devices.

Description

Technical Field

[0001] This disclosure relates to the field of computer technology, and in particular to a task scheduling method, apparatus, computing processing device, computer program, and computer-readable medium. Background Technology

[0002] The configuration level of large-scale medical equipment directly affects the diagnostic and treatment capabilities of medical and health institutions. Summary of the Invention

[0003] This disclosure provides a task scheduling method, apparatus, computing processing device, computer program, and computer-readable medium to shorten the maximum working time of inspection equipment.

[0004] This disclosure provides a task scheduling method, including: Obtain multiple inspection tasks to be scheduled and at least one inspection device responsible for processing the multiple inspection tasks, wherein each inspection task has a different task identifier. Gene sequences are generated based on the inspection task and the inspection equipment. The gene sequences include the correspondence between the inspection task and the inspection equipment that processes the inspection task, and the genes in the gene sequences are the task identifiers of the inspection task. The gene sequence is iteratively updated until the iteration stop condition is met, and the inspection task is scheduled according to the updated gene sequence. The iterative update step includes: The device working time and task switching parameters corresponding to the gene sequence before the update are determined. The device working time is the maximum value of the working time of at least one inspection device that completes the multiple inspection tasks according to the gene sequence before the update. The task switching parameters are used to characterize the time required for the first inspection device corresponding to the maximum value to switch to process the first inspection task. The first inspection task is the inspection task in the gene sequence before the update that has a corresponding relationship with the first inspection device. The fitness of the gene sequence before the update is determined based on the device working time and the task switching parameters. The device working time and the task switching parameters are negatively correlated with the fitness. Based on the fitness, a high-quality gene sequence is selected from multiple unupdated gene sequences, and an updated gene sequence is generated based on the high-quality gene sequence.

[0005] In one alternative implementation, the step of determining the device operating time corresponding to the gene sequence before the update includes: Obtain the first historical working time of the second inspection device, wherein the second inspection device is any one of the at least one inspection device, and the first historical working time is the duration during which the second inspection device started running before processing the inspection task; The examination duration of the second examination task is determined based on the pre-set examination duration of each examination type and the examination type of the second examination task. The second examination task is the examination task that corresponds to the second examination device in the gene sequence before the update. The estimated working time of the second inspection equipment is obtained by adding the first historical working time to the inspection time of each of the second inspection tasks. The maximum value among the estimated working times of the at least one inspection device is determined as the working time of the device.

[0006] In one alternative implementation, the step of determining the task transition parameters corresponding to the gene sequence before the update includes: Based on the similarity between any two pre-set check types and the check type of the first check task, determine the first similarity between any two adjacent first check tasks in the gene sequence before the update. The first similarity scores are averaged to obtain the similarity parameter; Calculate the reciprocal of the similarity parameter to obtain the task conversion parameter.

[0007] In one optional implementation, the step of determining the fitness of the gene sequence before the update based on the device operating time and the task switching parameters includes: Get reference working hours; Calculate the difference between the reference working time and the device working time, and then perform a weighted summation of the difference and the reciprocal of the task conversion parameter to obtain the fitness.

[0008] In one optional implementation, the step of obtaining the reference working time includes: Obtain the second historical working time of the third inspection device, wherein the third inspection device is any one of the at least one inspection device, and the second historical working time is the duration during which the third inspection device started running before processing the inspection task; Based on the pre-set inspection duration of each inspection type, the inspection type of each inspection task, and the acquisition order of each inspection task, the third inspection task that the third inspection device needs to process and the inspection duration of the third inspection task are determined. The inspection duration of each of the third inspection tasks is added together with the second historical running duration to obtain the sequential working duration of the third inspection device. The maximum value among the sequential working times of the at least one inspection device is determined as the reference working time.

[0009] In one optional implementation, the set of all unupdated gene sequences constitutes a population, and the step of selecting high-quality gene sequences from multiple unupdated gene sequences based on the fitness includes: The population fitness is obtained by summing the fitness of all gene sequences in the population. Calculate the ratio of the fitness of the first gene sequence to the fitness of the population, wherein the first gene sequence is any one of all gene sequences before the update; The roulette wheel selection method is used, with the ratio as the selection probability, to select gene sequences from the population. The selected gene sequences are the high-quality gene sequences.

[0010] In one alternative implementation, prior to the step of calculating the sum of fitness of all gene sequences in the population, the method further includes: If the fitness of the second gene sequence is less than the first preset threshold, the second gene sequence will be deleted from the population. If the fitness of the second gene sequence is equal to the first preset threshold, then the fitness of the second gene sequence is adjusted to the sum of the first preset threshold and a specified value. Wherein, the second gene sequence is any one of all gene sequences before the update; the first preset threshold is greater than or equal to 0; the specified value is greater than 0 and less than or equal to 0.1.

[0011] In one alternative implementation, the step of generating an updated gene sequence based on the high-quality gene sequence includes at least one of the following steps: According to the first probability, the high-quality gene sequence is copied to generate an updated gene sequence; According to the second probability, the two different high-quality gene sequences are cross-processed to generate an updated gene sequence; According to the third probability, the gene sequence after crossover is mutated to generate an updated gene sequence.

[0012] In one optional implementation, the step of generating a gene sequence based on the inspection task and the inspection device includes: The plurality of inspection tasks are randomly assigned to the at least one inspection device, and the gene sequence is determined according to the correspondence between the assigned inspection tasks and the inspection devices.

[0013] In one optional implementation, the number of updated gene sequences is multiple, and the step of scheduling the inspection task based on the updated gene sequences includes: Calculate the fitness of each updated gene sequence; Gene sequences with a fitness greater than or equal to a second preset threshold are selected from multiple updated gene sequences and used as target gene sequences. The inspection task is scheduled according to the target gene sequence.

[0014] In one optional implementation, the task identifier is an identifier determined according to the acquisition order of each of the inspection tasks, and before the step of determining the device operating time and task conversion parameters corresponding to the gene sequence before the update, the method further includes: Based on the inspection order of each inspection task in the third gene sequence, the inspection identifier of each inspection task is determined, wherein the third gene sequence is any one of all the gene sequences before the update; Calculate the difference between the inspection identifier and the task identifier; If the difference is less than a third preset threshold, then the third gene sequence is deleted.

[0015] This disclosure provides a task scheduling apparatus, including: The acquisition module is configured to acquire multiple inspection tasks to be scheduled and at least one inspection device responsible for processing the multiple inspection tasks, wherein each inspection task has a different task identifier. The generation module is configured to generate a gene sequence based on the inspection task and the inspection device, wherein the gene sequence includes the correspondence between the inspection task and the inspection device that processes the inspection task, and the gene in the gene sequence is the task identifier of the inspection task; The update module is configured to iteratively update the gene sequence until the iteration stop condition is met, and to schedule the inspection task according to the updated gene sequence. Specifically, the update module is configured as follows: The device working time and task switching parameters corresponding to the gene sequence before the update are determined. The device working time is the maximum value of the working time of at least one inspection device that completes the multiple inspection tasks according to the gene sequence before the update. The task switching parameters are used to characterize the time required for the first inspection device corresponding to the maximum value to switch to process the first inspection task. The first inspection task is the inspection task in the gene sequence before the update that has a corresponding relationship with the first inspection device. The fitness of the gene sequence before the update is determined based on the device working time and the task switching parameters. The device working time and the task switching parameters are negatively correlated with the fitness. Based on the fitness, a high-quality gene sequence is selected from multiple unupdated gene sequences, and an updated gene sequence is generated based on the high-quality gene sequence.

[0016] This disclosure provides a computing processing device, including: Memory containing computer-readable code; One or more processors, when the computer-readable code is executed by the one or more processors, the computing processing device performs the task scheduling method described in any embodiment.

[0017] This disclosure provides a computer program including computer-readable code that, when executed on a computing processing device, causes the computing processing device to perform the task scheduling method described in any embodiment.

[0018] This disclosure provides a computer-readable medium storing the task scheduling method described in any embodiment.

[0019] Compared with the prior art, this disclosure includes the following advantages: In the technical solution provided in this disclosure, since the device working time and task switching parameters of the gene sequence are negatively correlated with the fitness of the gene sequence, the gene sequence with smaller device working time and task switching parameters has a higher probability of being selected in each iteration update. Thus, by iteratively updating the gene sequence multiple times, the inspection order of the inspection task can be optimized and adjusted. On the one hand, this shortens the maximum working time of the device, making the running time of each inspection device more balanced and avoiding the situation where some inspection devices operate under high load while others are idle. On the other hand, it shortens the task switching time, thereby improving equipment utilization and inspection efficiency.

[0020] The above description is merely an overview of the technical solution disclosed herein. In order to better understand the technical means of this disclosure and to implement it in accordance with the contents of the specification, and to make the above and other objects, features and advantages of this disclosure more apparent and understandable, specific embodiments of this disclosure are described below. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments or related technologies of this disclosure, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. It should be noted that the scale in the drawings is for illustration only and does not represent the actual scale.

[0022] Figure 1 A flowchart illustrating a task scheduling method is shown schematically. Figure 2 A block diagram of a task scheduling device is shown schematically. Figure 3 A block diagram of a computing processing apparatus for performing the method according to the present disclosure is shown schematically.

[0023] Figure 4 A storage unit for holding or carrying program code that implements the method according to this disclosure is illustrated schematically. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of the embodiments of this disclosure clearer, the technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this disclosure.

[0025] Currently, hospitals generally allocate examination equipment to patients on a first-come, first-served basis. This allocation method results in some examination equipment running for too long, while others remain idle. Furthermore, the first-come, first-served allocation method does not consider the examination types of adjacent patients using the same examination equipment. If two adjacent patients using the same examination equipment have different examination types, the equipment may need to be adjusted and switched, leading to unnecessary waste of time.

[0026] Figure 1 This is a flowchart illustrating a task scheduling method according to an exemplary embodiment, such as... Figure 1 As shown, the method may include the following steps.

[0027] Step S11: Obtain multiple inspection tasks to be scheduled and at least one inspection device responsible for processing the multiple inspection tasks, wherein each inspection task has a different task identifier.

[0028] The execution entity in this embodiment can be a computer device, which has a task scheduling device to execute the task scheduling method provided in this embodiment. The computer device can be, for example, a smartphone, tablet computer, or personal computer; this embodiment does not limit the type of device.

[0029] The execution entity in this embodiment can acquire examination tasks in various ways. For example, the execution entity can connect to a scanning device to acquire the examination tasks collected by the scanning device. The scanning device can collect examination tasks by scanning the barcode on the patient's medical insurance card or examination form.

[0030] The task identifier for an inspection task can be determined, for example, based on the acquisition order of the inspection task; that is, the task identifier can be determined based on the scan time of the inspection task. This embodiment does not limit the method of determining the task identifier.

[0031] The executing entity in this embodiment can obtain the inspection equipment responsible for handling the inspection task in various ways. For example, the executing entity can obtain information about the inspection equipment responsible for handling the inspection task that has been pre-set by the management account; it can also connect to each inspection equipment and obtain information about each inspection equipment through the connection interface.

[0032] The examination equipment may be, for example, a magnetic resonance imaging (MRI) device, which can handle examination tasks including head MRI, thoracic spine MRI and abdominal MRI, etc. This embodiment does not limit this.

[0033] The inspection types of each inspection task can be the same or different, and this embodiment does not limit this.

[0034] In this embodiment, both the number of inspection tasks and the number of inspection devices are limited. It is assumed that at any given time, one inspection device can only process one inspection task, and the inspection device does not interrupt the process of processing inspection tasks.

[0035] Assume there are n patients (n≥2) waiting for examinations in the examination room, and each patient only needs to undergo one examination. Then, the number of examination tasks to be scheduled is n, and these n tasks are identified by their respective task identifiers: 1, 2, …, n. These n tasks constitute a set J = {H, A, H, T, …, H}, which includes n tasks involving three examination types: H, A, and T. Here, H represents head MRI, T represents thoracic spine MRI, and A represents abdominal MRI.

[0036] Assume the number of devices to be inspected is m (m≥1), and the device identifiers are 1, 2, …, m.

[0037] Step S12: Gene sequence is generated based on the inspection task and inspection equipment. The gene sequence includes the correspondence between the inspection task and the inspection equipment that processes the inspection task. The genes in the gene sequence are the task identifiers of the inspection task.

[0038] In this context, the gene sequence is a sequence of task identifiers for multiple examination tasks arranged in a specific order; the order of the examination tasks in the gene sequence constitutes the examination order. The correspondence between examination tasks and examination devices in the gene sequence can be represented by B... im To indicate, B im This indicates that the i-th inspection task (the inspection task with task identifier i) is processed by the m-th inspection device (the inspection device with device identifier m).

[0039] In this embodiment, a gene sequence corresponds to a scheduling scheme, which corresponds to a chromosome or an individual in the genetic algorithm.

[0040] In practical implementation, there are several ways to generate gene sequences depending on the inspection task and the inspection equipment. In one optional implementation, multiple inspection tasks can be randomly assigned to at least one inspection device, and gene sequences can be generated based on the correspondence between the assigned inspection tasks and the inspection devices.

[0041] In this implementation, the gene sequence is initialized before iterative updates by randomly generating gene sequences.

[0042] Step S13: Iteratively update the gene sequence until the iteration stop condition is met, and schedule the inspection task according to the updated gene sequence.

[0043] In this embodiment, the iteration stopping condition can include various implementation methods.

[0044] For example, in one implementation, the iteration stops when the number of iterations reaches a set number.

[0045] When the iteration stopping condition is met, if there are multiple updated gene sequences, one of them is selected as the target gene sequence, and each inspection task is scheduled according to the target gene sequence. The method for selecting the target gene sequence will be described in subsequent embodiments. If there is only one updated gene sequence, that updated gene sequence is used as the target gene sequence. In this implementation, the number of iterations can be set by those skilled in the art based on experience, and this disclosure does not limit it.

[0046] In another implementation, the iteration stops when the number of updated gene sequences is one.

[0047] Specifically, when an iteration is completed and the number of updated gene sequences obtained is one, the updated gene sequence can be used as the target gene sequence, and each inspection task can be scheduled according to the target gene sequence.

[0048] This embodiment can use any of the above methods as the iteration stopping condition. Of course, other iteration stopping conditions can also be used. This embodiment does not specifically limit the iteration stopping condition.

[0049] In step S13, the iterative update step includes: First, determine the device operating time and task switching parameters corresponding to the gene sequence before the update. The device operating time is the maximum operating time of at least one inspection device that completes multiple inspection tasks according to the gene sequence before the update. The task switching parameters characterize the time required for the first inspection device corresponding to the maximum value to switch to processing the first inspection task. The first inspection task is the inspection task in the gene sequence before the update that corresponds to the first inspection device. The inspection device corresponding to the maximum value is the first inspection device.

[0050] Then, based on the device operating time and task switching parameters, the fitness of the gene sequence before the update is determined. The device operating time and task switching parameters are negatively correlated with the fitness. Fitness is used to characterize the ability of the gene sequence before the update to handle inspection tasks during task scheduling.

[0051] Then, based on fitness, high-quality gene sequences are selected from multiple unupdated gene sequences, and updated gene sequences are generated based on these high-quality gene sequences.

[0052] In this embodiment, the device working time is the maximum value among the working times of at least one inspection device after completing multiple inspection tasks. After completing multiple inspection tasks, the working time of each inspection device may include the time required to complete the inspection task corresponding to that inspection device in the gene sequence before the update, and may also include the time that the inspection device has been running before processing these inspection tasks. Subsequent embodiments will describe in detail the specific method for determining the device working time.

[0053] The device operating time is the maximum value of the operating time of at least one inspection device. The inspection device corresponding to this maximum value or device operating time is the first inspection device. The inspection task in the gene sequence before the update that corresponds to the first inspection device is the first inspection task, and the first inspection task is processed by the first inspection device.

[0054] The task switching parameter characterizes the time required for the first inspection device to switch between first inspection tasks while processing all first inspection tasks. When two adjacent first inspection tasks have the same or similar inspection types, the switching operation on the first inspection device can be reduced, enabling rapid positioning and thus reducing the switching time. Therefore, the task switching parameter can be determined based on the similarity between any two adjacent first inspection tasks, and this determination method will be described in detail in subsequent embodiments.

[0055] In addition, the task switching parameter can determine the switching duration between any two adjacent first inspection tasks in the gene sequence before the update based on the pre-set switching duration between any two inspection types and the inspection type of each first inspection task, and add the switching durations together to determine the result.

[0056] This embodiment does not specifically limit the method for determining the task conversion parameters.

[0057] In genetic algorithms, gene sequences with higher fitness have a higher probability of being selected. Therefore, in order to minimize device downtime, device downtime is negatively correlated with fitness. That is, for each gene sequence before the update, the device downtime of that gene sequence is negatively correlated with the probability of that gene sequence being selected.

[0058] Since the device's operating time for a gene sequence is negatively correlated with the probability of that gene sequence being selected, gene sequences with shorter operating times have a higher probability of being selected in each iteration. Therefore, by iteratively updating the gene sequences multiple times, the inspection order of the inspection task can be optimized, thereby shortening the device's operating time (i.e., the device's maximum inspection time).

[0059] To further improve equipment utilization, minimize task switching parameters, and shorten the switching time for switching inspection tasks on the same inspection equipment, a negative correlation is found between task switching parameters and fitness. That is, for each gene sequence before the update, the task switching parameters of that gene sequence are negatively correlated with the probability of that gene sequence being selected.

[0060] Since the task switching parameter of a gene sequence is negatively correlated with the probability of that gene sequence being selected, gene sequences with lower task switching parameters have a higher probability of being selected in each iteration. Therefore, by iteratively updating the gene sequence multiple times, the inspection order of the inspection task can be optimized, thereby shortening the task switching time.

[0061] In this embodiment, the fitness function can be constructed with the goal of minimizing device operating time and task transition parameters. In specific implementations, the specific functional relationship between fitness, device operating time, and task transition parameters can be adjusted according to actual circumstances; this embodiment does not impose any limitations on this. Subsequent embodiments will describe in detail the specific method for determining fitness.

[0062] In practical implementations, there are several ways to select high-quality gene sequences from multiple unupdated gene sequences based on fitness. For example, the ratio of the fitness of each unupdated gene sequence to the total fitness of the population (the population fitness is the sum of the fitness of all unupdated gene sequences) can be used as the selection probability; alternatively, the fitness of the unupdated gene sequences can be sorted, and selection can be based on the sorting position; and so on. The former implementation method will be described in detail in subsequent embodiments.

[0063] In this embodiment, there are multiple ways to generate an updated gene sequence based on a high-quality gene sequence. For example, at least one of the following methods can be used to obtain an updated gene sequence: duplication, crossover, and mutation.

[0064] In a specific implementation, the step of generating an updated gene sequence based on a high-quality gene sequence may include at least one of the following steps: replicating the high-quality gene sequence according to a first probability to generate an updated gene sequence; performing cross-processing on two different high-quality gene sequences according to a second probability to generate an updated gene sequence; and performing mutation processing on the cross-processed gene sequence according to a third probability to generate an updated gene sequence.

[0065] In this implementation, by cross-processing two different high-quality gene sequences, we can avoid obtaining locally optimal gene sequences and help to obtain globally optimal gene sequences.

[0066] In a specific implementation, the values ​​of the first probability, the second probability, and the third probability can be adjusted according to actual needs, and this embodiment does not limit this.

[0067] The task scheduling method provided in this embodiment will be illustrated with examples below.

[0068] Assume m=2, n=10, meaning there are 2 inspection devices and 10 inspection tasks. These 10 tasks are identified by task identifiers 1, 2, ..., 10, and their inspection types are H, A, T, H, H, A, T, A, and T, respectively. During the initialization of gene sequence generation, these 10 inspection tasks can be randomly assigned to two inspection devices, such as device 1 and device 2. Specifically, the task identifiers 1 to 10 of these 10 inspection tasks can be randomly encoded to generate the following gene sequences: Equipment 1: ⑥②⑩⑦④ Equipment 2: ⑧⑨③①⑤ The 10 inspection tasks are inspected in the gene sequence in the order of ⑥⑧②⑨⑩③⑦①④⑤. Based on the inspection order of each inspection task in the gene sequence, the inspection identifier of each inspection task can be determined. For example, the inspection task with task identifier 6 has an inspection identifier of 1 in the gene sequence, the inspection task with task identifier 8 has an inspection identifier of 2 in the gene sequence, and so on.

[0069] After the two examination devices completed 10 examination tasks according to the above gene sequence, their working times were 30 minutes and 45 minutes respectively. Therefore, the working time of the device corresponding to the gene sequence is the maximum working time of the two examination devices, which is 45 minutes.

[0070] After selecting high-quality gene sequences, the process of cross-processing two different high-quality gene sequences can be carried out according to the following steps: Suppose two different high-quality gene sequences are parent 1 and parent 2: Equipment 1: ⑥ ②⑩ ⑦④ Equipment 1: ③⑧①⑦⑥ Equipment 2: ⑧ ⑨③ ①⑤ Equipment 2: ⑩②⑨⑤④ Parent generation 1 Parent generation 2 Then, randomly select several genes from parent generation 1 and parent generation 2 as fixed genes, indicated by bold italics. Crossover is performed on these two high-quality gene sequences from parent generation 1 and parent generation 2 to generate a new generation. The positions of the fixed genes in the parent generation remain unchanged in the new generation, as shown below: Equipment 1: ○ ②⑩ ○○ Equipment 2: ○ ⑨③ ○○ offspring Next, genes that differ from the fixed gene in parent generation 2 (indicated by underscores) are sequentially placed into the offspring according to their order in parent generation 2 and their correspondence with the testing equipment, resulting in the following offspring, which is the updated gene sequence: Equipment 1: ③ ⑧① ⑦ ⑥ Equipment 1: ⑧ ②⑩ ①⑥ Equipment 2: ⑩② ⑨⑤④ Equipment 2: ⑨ ⑦③ ⑤④ Parent generation 2 offspring generation The task scheduling method provided in this embodiment utilizes a gene sequence whose device working time and task transition parameters are negatively correlated with its fitness. Therefore, in each iteration, gene sequences with smaller device working times and task transition parameters are more likely to be selected. By iteratively updating the gene sequence multiple times, the inspection order of inspection tasks can be optimized. This achieves two goals: firstly, shortening the longest working time of the devices, making the runtime of each inspection device more balanced and avoiding situations where some inspection devices operate at high load while others are idle; and secondly, shortening the task transition time, thereby improving device utilization and inspection efficiency.

[0071] The execution entity in this embodiment can also be connected to a display. The display can be used to display information about the examination task currently being prepared for examination (such as the task identifier of the examination task or the corresponding patient name, etc.) and information about the examination equipment responsible for processing the examination task (such as the room number corresponding to the examination equipment, etc.). It can also be used to display information about the next examination task to be prepared for examination, etc.

[0072] The execution entity in this embodiment can also be connected to a player, which can be used to provide voice broadcasts of information about the inspection task currently being prepared for inspection and the inspection equipment responsible for handling the inspection task.

[0073] It should be noted that, assuming m inspection tasks have already been completed or are being processed before these n inspection tasks, and that the m inspection devices are idle before these m inspection tasks are processed, these m inspection tasks can be randomly assigned to the m inspection devices. This improves the utilization rate of the inspection devices, reduces their idle time, and increases scheduling efficiency. For the n inspection tasks acquired after these m inspection tasks, they can be scheduled according to the task scheduling method provided in this embodiment. Furthermore, to reduce the number of calculations, the task scheduling process for these n inspection tasks can be completed before any inspection device finishes processing its current inspection task. This not only reduces the number of calculations but also improves the utilization rate of the inspection devices, reduces their idle time, and increases scheduling efficiency.

[0074] Once the scheduling scheme for these n inspection tasks, i.e. the gene sequence, is determined, the inspection tasks can be scheduled according to the final determined gene sequence. After a specified number of inspection tasks have been processed according to the final determined gene sequence, or after a preset time has elapsed for processing the inspection tasks according to the final determined gene sequence, the inspection tasks that have not yet started processing among the n inspection tasks and the inspection tasks obtained after the n inspection tasks can be re-determined as inspection tasks to be scheduled, and then the task scheduling method provided in this embodiment can be used for scheduling.

[0075] In one optional implementation, step S13, determining the device operating time corresponding to the gene sequence before the update, may specifically include: First, the first historical working time of the second inspection device is obtained, wherein the second inspection device is any one of at least one inspection device, and the first historical working time is the duration during which the second inspection device started running before processing the inspection task.

[0076] Then, based on the pre-set inspection duration of each inspection type and the inspection type of the second inspection task, the inspection duration of the second inspection task is determined. The second inspection task is the inspection task that corresponds to the second inspection device in the gene sequence before the update.

[0077] Then, the first historical working time is added to the inspection time of each second inspection task to obtain the estimated working time of the second inspection equipment.

[0078] Then, the maximum value among the estimated working times of at least one inspection device is determined as the device working time.

[0079] The examination duration for a particular examination type can be the average of the time required for at least one examination device to process that type of examination. For example, the examination durations for head MRI (H), thoracic spine MRI (T), and abdominal MRI (A) are 10 minutes, 12 minutes, and 15 minutes, respectively.

[0080] Historical working time can be, for example, the time from when the second inspection equipment is turned on and running on the same day until it processes the second inspection task.

[0081] For example, if the first historical running time is 30 minutes, and there are three second inspection tasks with inspection types H, A, and T, then the inspection times for the three second inspection tasks can be determined to be 10 minutes, 15 minutes, and 12 minutes, respectively. Adding the first historical running time to the inspection times of each second inspection task, the estimated running time of the second inspection equipment is obtained as 10 minutes + 15 minutes + 12 minutes + 30 minutes = 67 minutes.

[0082] The estimated working time of each inspection device can be calculated according to the above process. When the number of inspection devices is 2, the estimated working time of the two inspection devices is 67 minutes and 72 minutes respectively. Therefore, the working time of the device can be determined to be the maximum of the two, which is 72 minutes.

[0083] In this implementation, since the equipment working time includes historical working time, it can ensure a more balanced total running time (e.g., throughout the day) among the various inspection devices.

[0084] In one optional implementation, step S13, which involves determining the task conversion parameters corresponding to the gene sequence before the update, includes: firstly, determining the first similarity between any two adjacent first inspection tasks in the gene sequence before the update based on the similarity between any two pre-set inspection types and the inspection type of the first inspection task; then, averaging each first similarity to obtain the similarity parameter; and finally, calculating the reciprocal of the similarity parameter to obtain the task conversion parameter.

[0085] In a practical implementation, the similarity between any two examination types can be preset as follows: the similarity between two identical examination types is 1, otherwise it is 0. In CT examinations, there are plain scans and enhanced scans of the same area; the similarity between these two examination types can be defined as 0.5. In a practical implementation, the similarity between any two examination types can be set according to the actual situation; this embodiment does not impose any limitations on this.

[0086] Assuming the gene sequence before the update includes five first inspection tasks with inspection types H, A, T, T, and A, and any two adjacent first inspection tasks are H and A, A and T, T and T, and T and A, the first similarity between any two adjacent first inspection tasks can be determined to be 0, 0, 1, and 0, respectively. The average value is calculated to obtain a similarity parameter of 0.25. Then, the reciprocal of the similarity parameter is taken to determine the task transformation parameter as 4.

[0087] In this implementation, the task conversion parameters are determined based on the similarity between two adjacent inspection tasks on the same inspection equipment, which can improve task scheduling efficiency and the accuracy of task conversion parameters.

[0088] In one optional implementation, step S13, which involves determining the fitness of the gene sequence before the update based on the device working time and the task conversion parameters, includes: first obtaining the reference working time; then calculating the difference between the reference working time and the device working time, and performing a weighted summation of the difference and the reciprocal of the task conversion parameters to obtain the fitness.

[0089] The reference working time can be the maximum working time of the inspection equipment determined according to the first-come, first-served scheduling method; or it can be determined based on the equipment working time of each gene sequence during the previous iteration update process, for example, it can be the average of the equipment working times of multiple gene sequences. This embodiment does not limit the method of determining the reference working time.

[0090] Specifically, fitness can be calculated using the following formula: f(x) = 0.6 * (C1 - C) + 0.4 * s Where f(x) represents the fitness of the gene sequence x before the update, C1 represents the reference working time, C represents the device working time, and s represents the reciprocal of the task conversion parameter. It should be noted that since the task conversion parameter and the similarity parameter are reciprocals, s can also represent the similarity parameter. The weighting coefficient of the difference can be greater than the weighting coefficient of the reciprocal of the task conversion parameter. In the above formula, the weighting coefficient of the difference is 0.6, and the weighting coefficient of the reciprocal of the task conversion parameter is 0.4. In specific implementations, the weighting coefficients can be adjusted according to the actual situation; this embodiment does not limit this.

[0091] When the reference working time is the maximum working time of the inspection equipment determined according to the first-come-first-served scheduling method, the steps to obtain the reference working time may specifically include: firstly, obtaining the second historical working time of the third inspection equipment, wherein the third inspection equipment is any one of at least one inspection equipment, and the second historical working time is the duration during which the third inspection equipment started running before processing the inspection task; then, determining the third inspection task that the third inspection equipment needs to process and the inspection time of the third inspection task based on the pre-set inspection time of each inspection type, the inspection type of each inspection task, and the acquisition order of each inspection task; then, adding the inspection time of each third inspection task to the second historical working time to obtain the sequential working time of the third inspection equipment; and finally, determining the maximum value among the sequential working times of at least one inspection equipment as the reference working time.

[0092] The second historical runtime is the duration during which the third inspection device has been running before it begins processing the third inspection task.

[0093] Assuming the second historical runtime is 45 minutes, and following the first-come, first-served scheduling method, the number of third inspection tasks assigned to the third inspection device is three, with inspection types H, A, and T respectively. The inspection durations of the three third inspection tasks can be determined to be 10 minutes, 15 minutes, and 12 minutes respectively. Adding the inspection durations of each third inspection task to the second historical runtime results in 10 minutes + 12 minutes + 15 minutes + 45 minutes = 82 minutes, meaning the sequential working time of the third inspection device is 82 minutes.

[0094] The sequential working time of each inspection device can be calculated according to the above process. When there are 2 inspection devices, the sequential working time of the two inspection devices is 82 minutes and 95 minutes respectively, so the reference working time can be determined to be 95 minutes.

[0095] In one optional implementation, step S13, where the set of all unupdated gene sequences constitutes a population, involves selecting a high-quality gene sequence from multiple unupdated gene sequences based on fitness. This step includes: first, calculating the sum of the fitness of all gene sequences in the population to obtain the population fitness; then, calculating the ratio of the fitness of the first gene sequence to the population fitness, where the first gene sequence is any one of all unupdated gene sequences; and finally, using a roulette wheel selection method, using the ratio as the selection probability, to select a gene sequence from the population, and the selected gene sequence is the high-quality gene sequence.

[0096] In specific implementation, it can be made Population fitness is the sum of the fitness of all gene sequences in a population. The fitness of any gene sequence x (i.e., the first gene sequence) in the population is represented by the ratio of the fitness of any gene sequence x to the fitness of the entire population. This can represent the ability of the first gene sequence x to produce offspring. Using a roulette wheel selection method, the ratio of the corresponding gene sequences in the population can be used as the selection probability to select gene sequences from the population, thus obtaining high-quality gene sequences.

[0097] In this implementation, before calculating the sum of the fitness of all gene sequences in the population, the following steps may be included: if the fitness of the second gene sequence is less than a first preset threshold, then the second gene sequence is deleted from the population; if the fitness of the second gene sequence is equal to the first preset threshold, then the fitness of the second gene sequence is adjusted to the sum of the first preset threshold and a specified value.

[0098] The second gene sequence can be any one of the gene sequences before the update. The first preset threshold is greater than or equal to 0. The specified value is greater than 0 and less than or equal to 0.1. For example, the first preset threshold can be 0. When the first preset threshold is 0, the specified value can be a very small positive number, such as 0.05.

[0099] By deleting the second gene sequence whose fitness is less than the first preset threshold, it can be ensured that the working time of the device corresponding to each gene sequence in the population is less than the reference working time.

[0100] By adjusting the fitness level, which is equal to the first preset threshold, to the sum of the first preset threshold and a specified value, errors can be prevented during the calculation process.

[0101] In one optional implementation, when there are multiple updated gene sequences, step S13, which involves scheduling the inspection task based on the updated gene sequences, includes: first, calculating the fitness of each updated gene sequence; then, selecting a gene sequence from the multiple updated gene sequences whose fitness is greater than or equal to a second preset threshold as the target gene sequence; and finally, scheduling the inspection task according to the target gene sequence.

[0102] In practice, the fitness of each updated gene sequence can be calculated in the same way as the fitness of the gene sequence before the update, which will not be elaborated here.

[0103] The second preset threshold can be the maximum fitness of multiple updated gene sequences, or it can be set according to actual needs. This embodiment does not limit this.

[0104] For example, when there are two updated gene sequences, and the fitness of these two updated gene sequences is 5 and 7 respectively, the gene sequence with fitness of 7 can be identified as the target gene sequence, and then each inspection task can be scheduled according to the target gene sequence.

[0105] In one optional implementation, the task identifier is an identifier determined according to the acquisition order of each inspection task. In step S13, before determining the device working time and task conversion parameters corresponding to the gene sequence before the update, the following may be included: first, determining the inspection identifier of each inspection task according to the inspection order of each inspection task in the third gene sequence, wherein the third gene sequence is any one of all gene sequences before the update; then calculating the difference between the inspection identifier and the task identifier; if the difference is less than a third preset threshold, then deleting the third gene sequence.

[0106] The third preset threshold can be, for example, -5, and can be determined according to actual needs. This embodiment does not limit this.

[0107] Specifically, the inspection identifier of each inspection task can be determined first according to the inspection order of each inspection task in the third gene sequence, and then the difference between the inspection identifier and the task identifier can be calculated. If there is a difference in the third gene sequence that is less than a third preset threshold, the third gene sequence can be deleted from the population composed of the gene sequence before the update.

[0108] This approach ensures that patients arriving early are not scheduled for examinations too late, optimizing equipment operating time while also considering the possibility of delayed examinations, thus making the task scheduling plan more rational and user-friendly.

[0109] Figure 2 This is a block diagram illustrating a task scheduling apparatus according to an exemplary embodiment. (Refer to...) Figure 2 It can include: The acquisition module 21 is configured to acquire multiple inspection tasks to be scheduled and at least one inspection device responsible for processing the multiple inspection tasks, wherein each inspection task has a different task identifier. The generation module 22 is configured to generate a gene sequence based on the inspection task and the inspection device, wherein the gene sequence includes the correspondence between the inspection task and the inspection device that processes the inspection task, and the gene in the gene sequence is the task identifier of the inspection task. The update module 23 is configured to iteratively update the gene sequence until the iteration stop condition is met, and to schedule the inspection task according to the updated gene sequence. Specifically, the update module 23 is configured as follows: The device working time and task switching parameters corresponding to the gene sequence before the update are determined. The device working time is the maximum value of the working time of at least one inspection device that completes the multiple inspection tasks according to the gene sequence before the update. The task switching parameters are used to characterize the time required for the first inspection device corresponding to the maximum value to switch to process the first inspection task. The first inspection task is the inspection task in the gene sequence before the update that has a corresponding relationship with the first inspection device. The fitness of the gene sequence before the update is determined based on the device working time and the task switching parameters. The device working time and the task switching parameters are negatively correlated with the fitness. Based on the fitness, a high-quality gene sequence is selected from multiple unupdated gene sequences, and an updated gene sequence is generated based on the high-quality gene sequence.

[0110] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operations has been described in detail in the embodiments related to the method, for example, by using software, hardware, firmware, etc., and will not be elaborated here.

[0111] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0112] The various component embodiments of this disclosure can be implemented in hardware, or as software modules running on one or more processors, or a combination thereof. Those skilled in the art will understand that microprocessors or digital signal processors (DSPs) can be used in practice to implement some or all of the functions of some or all of the components in the computing processing device according to embodiments of this disclosure. This disclosure can also be implemented as a device or apparatus program (e.g., a computer program and computer program product) for performing some or all of the methods described herein. Such an implementation of this disclosure can be stored on a computer-readable medium or can take the form of one or more signals. Such signals can be downloaded from an Internet website, provided on a carrier signal, or provided in any other form.

[0113] For example, Figure 3 A computing processing apparatus is shown that can implement the methods according to this disclosure. The computing processing apparatus conventionally includes a processor 1010 and a computer program product or computer-readable medium in the form of a memory 1020. The memory 1020 may be an electronic memory such as flash memory, EEPROM (Electrically Erasable Programmable Read-Only Memory), EPROM, hard disk, or ROM. The memory 1020 has a storage space 1030 for program code 1031 for performing any of the method steps described above. For example, the storage space 1030 for program code may include various program codes 1031 respectively for implementing the various steps in the methods described above. These program codes can be read from or written to one or more computer program products. These computer program products include program code carriers such as hard disks, CDs, memory cards, or floppy disks. Such computer program products are typically as described in the references. Figure 4 The portable or fixed storage unit is described above. This storage unit may have the same characteristics as... Figure 3 The memory 1020 in the computing processing device is arranged similarly to storage segments, storage spaces, etc. Program code can be compressed, for example, in an appropriate form. Typically, the storage unit includes computer-readable code 1031', that is, code that can be read by a processor such as 1010, which, when run by the computing processing device, causes the computing processing device to perform the various steps in the methods described above.

[0114] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0115] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0116] The foregoing has provided a detailed description of a task scheduling method, apparatus, computing device, computer program, and computer-readable medium provided by this disclosure. Specific examples have been used to illustrate the principles and implementation methods of this disclosure. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this disclosure. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this disclosure. Therefore, the content of this specification should not be construed as a limitation of this disclosure.

[0117] It should be understood that although the steps in the flowcharts of the accompanying figures are shown sequentially as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the accompanying figures may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily completed at the same time, but can be executed at different times, and their execution order is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the sub-steps or stages of other steps.

[0118] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0119] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

[0120] The terms "an embodiment," "embodiment," or "one or more embodiments" as used herein mean that a particular feature, structure, or characteristic described in connection with an embodiment is included in at least one embodiment of this disclosure. Furthermore, please note that the examples of the phrase "in one embodiment" do not necessarily all refer to the same embodiment.

[0121] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of this disclosure may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0122] In the claims, any reference signs placed between parentheses should not be construed as limiting the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. This disclosure can be implemented by means of hardware comprising a plurality of different elements and by means of a suitably programmed computer. In a unit claim enumerating a plurality of means, several of these means may be embodied by the same item of hardware. The use of the words first, second, and third, etc., does not indicate any order. These words may be interpreted as names.

[0123] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this disclosure, and are not intended to limit them. Although this disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this disclosure.

Claims

1. A task scheduling method, characterized in that, The task scheduling method includes: Obtain multiple inspection tasks to be scheduled and at least one inspection device responsible for processing the multiple inspection tasks, wherein each inspection task has a different task identifier. Gene sequences are generated based on the inspection task and the inspection equipment. The gene sequences include the correspondence between the inspection task and the inspection equipment that processes the inspection task, and the genes in the gene sequences are the task identifiers of the inspection task. The gene sequence is iteratively updated until the iteration stop condition is met, and the inspection task is scheduled according to the updated gene sequence. The iterative update step includes: The device working time and task switching parameters corresponding to the gene sequence before the update are determined. The device working time is the maximum value of the working time of at least one inspection device that completes the multiple inspection tasks according to the gene sequence before the update. The task switching parameters are used to characterize the time required for the first inspection device corresponding to the maximum value to switch to process the first inspection task. The first inspection task is the inspection task in the gene sequence before the update that has a corresponding relationship with the first inspection device. The fitness of the gene sequence before the update is determined based on the device working time and the task switching parameters. The device working time and the task switching parameters are negatively correlated with the fitness. Based on the fitness, a high-quality gene sequence is selected from multiple unupdated gene sequences, and an updated gene sequence is generated based on the high-quality gene sequence. The steps to determine the task transformation parameters corresponding to the gene sequence before the update include: Based on the similarity between any two pre-set check types and the check type of the first check task, determine the first similarity between any two adjacent first check tasks in the gene sequence before the update. The first similarity scores are averaged to obtain the similarity parameter; Calculate the reciprocal of the similarity parameter to obtain the task conversion parameter.

2. The task scheduling method according to claim 1, characterized in that, The steps to determine the device operating time corresponding to the gene sequence before the update include: Obtain the first historical working time of the second inspection device, wherein the second inspection device is any one of the at least one inspection device, and the first historical working time is the duration during which the second inspection device started running before processing the inspection task; The examination duration of the second examination task is determined based on the pre-set examination duration of each examination type and the examination type of the second examination task. The second examination task is the examination task that corresponds to the second examination device in the gene sequence before the update. The estimated working time of the second inspection equipment is obtained by adding the first historical working time to the inspection time of each of the second inspection tasks. The maximum value among the estimated working times of the at least one inspection device is determined as the working time of the device.

3. The task scheduling method according to claim 1, characterized in that, The step of determining the fitness of the gene sequence before the update based on the device's operating time and the task conversion parameters includes: Get reference working hours; Calculate the difference between the reference working time and the device working time, and then perform a weighted summation of the difference and the reciprocal of the task conversion parameter to obtain the fitness.

4. The task scheduling method according to claim 3, characterized in that, The step of obtaining the reference working time includes: Obtain the second historical working time of the third inspection device, wherein the third inspection device is any one of the at least one inspection device, and the second historical working time is the duration during which the third inspection device started running before processing the inspection task; Based on the pre-set inspection duration of each inspection type, the inspection type of each inspection task, and the acquisition order of each inspection task, the third inspection task that the third inspection device needs to process and the inspection duration of the third inspection task are determined. The inspection duration of each of the third inspection tasks is added together with the second historical running duration to obtain the sequential working duration of the third inspection device. The maximum value among the sequential working times of the at least one inspection device is determined as the reference working time.

5. The task scheduling method according to claim 1, characterized in that, The population is a collection of all unupdated gene sequences. The step of selecting high-quality gene sequences from the multiple unupdated gene sequences based on the fitness includes: The population fitness is obtained by summing the fitness of all gene sequences in the population. Calculate the ratio of the fitness of the first gene sequence to the fitness of the population, wherein the first gene sequence is any one of all gene sequences before the update; The roulette wheel selection method is used, with the ratio as the selection probability, to select gene sequences from the population. The selected gene sequences are the high-quality gene sequences.

6. The task scheduling method according to claim 5, characterized in that, Before the step of calculating the sum of fitness of all gene sequences in the population, the method further includes: If the fitness of the second gene sequence is less than the first preset threshold, the second gene sequence will be deleted from the population. If the fitness of the second gene sequence is equal to the first preset threshold, then the fitness of the second gene sequence is adjusted to the sum of the first preset threshold and a specified value. Wherein, the second gene sequence is any one of all gene sequences before the update; the first preset threshold is greater than or equal to 0; the specified value is greater than 0 and less than or equal to 0.

1.

7. The task scheduling method according to claim 1, characterized in that, The step of generating an updated gene sequence based on the high-quality gene sequence includes at least one of the following steps: According to the first probability, the high-quality gene sequence is copied to generate an updated gene sequence; According to the second probability, the two different high-quality gene sequences are cross-processed to generate an updated gene sequence; According to the third probability, the gene sequence after crossover is mutated to generate an updated gene sequence.

8. The task scheduling method according to claim 1, characterized in that, The step of generating a gene sequence based on the inspection task and the inspection equipment includes: The plurality of inspection tasks are randomly assigned to the at least one inspection device, and the gene sequence is determined according to the correspondence between the assigned inspection tasks and the inspection devices.

9. The task scheduling method according to claim 1, characterized in that, The number of updated gene sequences is multiple. The step of scheduling the inspection task based on the updated gene sequences includes: Calculate the fitness of each updated gene sequence; Gene sequences with a fitness greater than or equal to a second preset threshold are selected from multiple updated gene sequences and used as target gene sequences. The inspection task is scheduled according to the target gene sequence.

10. The task scheduling method according to any one of claims 1 to 9, characterized in that, The task identifier is determined according to the acquisition order of each inspection task. Prior to the step of determining the device operating time and task conversion parameters corresponding to the gene sequence before the update, the method further includes: Based on the inspection order of each inspection task in the third gene sequence, the inspection identifier of each inspection task is determined, wherein the third gene sequence is any one of all the gene sequences before the update; Calculate the difference between the inspection identifier and the task identifier; If the difference is less than a third preset threshold, then the third gene sequence is deleted.

11. A task scheduling device, characterized in that, The task scheduling device includes: The acquisition module is configured to acquire multiple inspection tasks to be scheduled and at least one inspection device responsible for processing the multiple inspection tasks, wherein each inspection task has a different task identifier. The generation module is configured to generate a gene sequence based on the inspection task and the inspection device, wherein the gene sequence includes the correspondence between the inspection task and the inspection device that processes the inspection task, and the gene in the gene sequence is the task identifier of the inspection task; The update module is configured to iteratively update the gene sequence until the iteration stop condition is met, and to schedule the inspection task according to the updated gene sequence. Specifically, the update module is configured as follows: The device working time and task switching parameters corresponding to the gene sequence before the update are determined. The device working time is the maximum value of the working time of at least one inspection device that completes the multiple inspection tasks according to the gene sequence before the update. The task switching parameters are used to characterize the time required for the first inspection device corresponding to the maximum value to switch to process the first inspection task. The first inspection task is the inspection task in the gene sequence before the update that has a corresponding relationship with the first inspection device. The fitness of the gene sequence before the update is determined based on the device working time and the task switching parameters. The device working time and the task switching parameters are negatively correlated with the fitness. Based on the fitness, a high-quality gene sequence is selected from multiple unupdated gene sequences, and an updated gene sequence is generated based on the high-quality gene sequence. The device is also used for: Based on the similarity between any two pre-set check types and the check type of the first check task, determine the first similarity between any two adjacent first check tasks in the gene sequence before the update. The first similarity scores are averaged to obtain the similarity parameter; Calculate the reciprocal of the similarity parameter to obtain the task conversion parameter.

12. A computing processing device, characterized in that, include: Memory containing computer-readable code; One or more processors, wherein when the computer-readable code is executed by the one or more processors, the computing processing device performs the task scheduling method as described in any one of claims 1 to 10.

13. A computer program, characterized in that, Includes computer-readable code that, when executed on a computing processing device, causes the computing processing device to perform a task scheduling method according to any one of claims 1 to 10.

14. A computer-readable medium, characterized in that, It stores the task scheduling method as described in any one of claims 1 to 10.

Images