Task processing method and device, equipment and medium

Abstract

The embodiment of the invention relates to a task processing method and device, equipment and a medium. The method includes, in response to expiration of a timer for execution of a task, measuring a voltage of a capacitor for powering the execution of the task. The method further includes updating the timer with a target duration in response to the voltage being within a predetermined range, the target duration being determined based on a compensation voltage provided by the energy conversion component to the capacitor; and performing a task using the voltage of the capacitor. According to the method disclosed by the embodiment of the invention, the voltage can be provided for the capacitor by the energy conversion part, self power supply is realized, additional wire arrangement is avoided, in addition, the execution period of task scheduling can be determined according to the magnitude of the voltage of the capacitor, reliable execution of tasks is realized, and the user experience is improved.

Description

Technical Field

[0001] Embodiments of the present disclosure generally relate to the field of task management, and more particularly to methods, apparatuses, devices, and media for processing tasks. Background Art

[0002] With the improvement of industrialization, large-scale industrial Internet of Things (IIoT) applications have been deployed. In these applications, various tasks can be implemented for manufacturing scenarios. For example, an anomaly detection task can be implemented, which is considered an important task in manufacturing scenarios. If potential faults are identified before they occur, enabling manufacturers to proactively intervene early, quality defects can be prevented and production delays can be avoided.

[0003] In addition, during the development of the industrial Internet of Things, various algorithms or models, including machine learning models, have been increasingly applied to the industrial Internet of Things. The combination of various models and the Internet of Things enables the use of algorithms or models such as machine learning models to process various problems in the Internet of Things. For example, the identification of potential faults described above. However, there are still many problems to be solved during the development of the industrial Internet of Things. Summary of the Invention

[0004] Embodiments of the present disclosure provide a method, apparatus, device, and medium for processing tasks.

[0005] According to a first aspect of the present disclosure, a method for processing tasks is provided. The method includes measuring a voltage of a capacitor that supplies power for the execution of a task in response to a timer expiration for the execution of the task. The method further includes updating the timer with a target duration in response to the voltage being within a predetermined range, where the target duration is determined based on a compensation voltage provided by an energy conversion component to the capacitor; and executing the task using the voltage of the capacitor.

[0006] According to a second aspect of the present disclosure, an apparatus for processing tasks is provided. The apparatus includes a voltage measurement unit configured to measure a voltage of a capacitor that supplies power for the execution of a task in response to a timer expiration for the execution of the task; a timer update and task execution unit configured to update the timer with a target duration in response to the voltage being within a predetermined range, where the target duration is determined based on a compensation voltage provided by an energy conversion component to the capacitor; and execute the task using the voltage of the capacitor.

[0007] According to a third aspect of the present disclosure, a controller is provided. The controller includes at least one processor; and a memory coupled to the at least one processor and having instructions stored thereon that, when executed by the at least one processor, cause the controller to perform the steps of the method in the first aspect of the present disclosure.

[0008] According to a fourth aspect of the present disclosure, an energy-based adaptive scheduling device is provided. The task processing device includes an energy conversion component; a capacitor; and a controller in the third aspect of the present disclosure.

[0009] According to a fifth aspect of the present disclosure, a computer-readable storage medium is provided. Computer-executable instructions are stored on the computer-readable storage medium, and when the computer-executable instructions are executed by a processor, the steps of the method in the first aspect of the present disclosure are implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] By describing the exemplary embodiments of the present disclosure in more detail in conjunction with the accompanying drawings, the above and other objects, features, and advantages of the present disclosure will become more apparent. Among them, in the exemplary embodiments of the present disclosure, the same reference numerals generally represent the same components.

[0011] Figure 1 A schematic diagram illustrating an example environment in which the device and / or method according to the embodiments of the present disclosure may be implemented;

[0012] Figure 2 A schematic diagram illustrating an example of the system structure of an energy-based adaptive scheduling device according to an embodiment of the present disclosure;

[0013] Figure 3 A schematic diagram illustrating an example of the circuit of a solar panel according to an embodiment of the present disclosure;

[0014] Figure 4 A schematic diagram illustrating an example of a voltage measurement circuit according to an embodiment of the present disclosure;

[0015] Figure 5 A schematic diagram illustrating an example of a specific design of the system structure according to an embodiment of the present disclosure;

[0016] Figure 6 A flowchart illustrating a method for processing tasks according to an embodiment of the present disclosure;

[0017] Figure 7 A schematic diagram illustrating an example process for processing tasks according to an embodiment of the present disclosure;

[0018] Figure 8 A schematic diagram illustrating another example process for processing tasks according to an embodiment of the present disclosure;

[0019] Figure 9 A schematic diagram illustrating examples of on-demand scheduling and periodic scheduling according to an embodiment of the present disclosure;

[0020] Figure 10The figure shows a schematic diagram of a device for processing tasks according to an embodiment of the present disclosure;

[0021] Figure 11 The figure shows a schematic block diagram of an example device suitable for implementing embodiments of the present disclosure.

[0022] In the respective figures, the same or corresponding reference numerals denote the same or corresponding parts. Detailed implementation manners

[0023] Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although some embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. On the contrary, these embodiments are provided to more thoroughly and completely understand the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not used to limit the protection scope of the present disclosure.

[0024] In the description of the embodiments of the present disclosure, the term "including" and its like should be understood as an open inclusion, that is, "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "an embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc. may refer to different or the same objects. There may also be other explicit and implicit definitions hereinafter.

[0025] As mentioned above, there are still many problems to be solved in the development process of the industrial Internet of Things. For example, early identification of potential failures may be challenging. For existing production lines, in order to perform tasks such as detecting failures, new detection devices or detection components need to be added to complete the above tasks. For these added detection devices or detection components, power needs to be provided when they are working. However, it is very challenging to add additional power sources or form an industrial Internet of Things using the added devices, making it difficult to use wire-connected computing devices for fault monitoring. Devices powered by batteries need to have their batteries replaced frequently, which will also seriously affect the monitoring efficiency of the automated production line.

[0026] In addition, the use of energy harvesting technologies (such as solar panels) has enabled self-power supply in industrial environments. However, existing energy harvesting platforms are usually designed for intermittent computing. In industrial applications that emphasize reliability, continuous data collection and decision-making are crucial. When the energy is insufficient, it cannot support the execution of tasks designed for sustainable operation.

[0027] To address at least the above and other potential issues, embodiments of the present disclosure provide a method for processing tasks. In this method, when a timer set for the execution of a task expires, the controller can measure the voltage of a capacitor that supplies power for the execution of the task. Then, the controller determines whether the voltage of the capacitor is within a predetermined range. If the voltage of the capacitor is within the predetermined range, the timer can be updated using a target duration, where the target duration is determined based on the compensation voltage provided by the energy conversion component to the capacitor. At the same time, the controller can also use the voltage provided by the capacitor to execute the task. Through this method, the energy conversion component can supply voltage to the capacitor, avoiding the addition of extra power line arrangements in the detection environment. Additionally, the period for task scheduling and execution is determined based on the magnitude of the capacitor voltage, enabling reliable execution of tasks through self-power supply and improving the user experience.

[0028] Embodiments of the present disclosure will be described in further detail below in conjunction with the accompanying drawings, where Figure 1 illustrates an example environment in which the devices and / or methods of the embodiments of the present disclosure can be implemented.

[0029] As Figure 1 shown, the example environment 100 includes a controller 104. The controller 104 is used to control the execution of a task 102. For example, the controller 104 schedules the execution of the task 102 according to a timer 108.

[0030] In some embodiments, the controller 104 can be a microcontroller system-on-chip. In some embodiments, the controller 104 is any suitable computing device that can be powered by a capacitor. Alternatively or additionally, the controller 104 can also be powered by a battery or a power supply when the capacitor power supply is insufficient.

[0031] As Figure 1 shown, the task 102 is loaded into the controller 104 from the outside and then executed by the controller 104, which is only an example and not a specific limitation of the present disclosure. In some embodiments, the task 102 is stored locally in the controller 104.

[0032] In some embodiments, the task 102 is an inference and / or training task of a machine learning model. In one example, the machine learning model is a neural network model. In another example, the machine learning model is a decision tree. In yet another example, the machine learning model is a linear regression model. The above examples are only used to describe the present disclosure and are not specific limitations of the present disclosure. In some embodiments, the task 102 is an algorithm or model other than a machine learning model. For example, the task 102 is a sorting algorithm that performs a sorting operation on some data. The above examples are only used to describe the present disclosure and are not specific limitations of the present disclosure.

[0033] The controller 104 is connected to the capacitor 106. The capacitor 106 can supply energy to the controller. For example, the capacitor 106 can supply a voltage to the controller 104 for the controller to perform the task 102. The capacitor 106 can obtain energy from an energy conversion component. In some embodiments, the energy conversion component is a solar panel. The capacitor 106 is connected to the solar panel, and the solar panel supplies a voltage to the capacitor 106. In some embodiments, the energy conversion component is a wind or water energy conversion device. The capacitor 106 can be connected to a wind or hydroelectric power generation device to supply a voltage to the capacitor 106. Additionally, in addition to the capacitor 106 supplying a voltage to the controller 104, a battery can also supply a voltage to the controller 104.

[0034] The controller 104 further includes a timer 108. The controller 104 can control the execution of the task 106 through the timer 108. The controller 104 is used to execute the task 106 when the timer 108 expires. At this time, the controller 104 also needs to determine whether to use the capacitor to supply power to the microcontroller to execute the task. During this process, the controller 104 detects the voltage 110 of the capacitor 106 and determines whether the voltage 110 of the capacitor 106 is within a predetermined range. For example, the maximum voltage of the capacitor is 5.5V, and its predetermined range is 3 - 5.5V. If the voltage 110 of the capacitor 106 is within this predetermined range at this time, it indicates that the voltage 110 of the capacitor 106 can be used to execute the task 102. At this time, the voltage provided by the capacitor is used to execute the task 102. If the voltage 110 of the capacitor 106 is not within the predetermined range, for example, lower than 3V, it indicates that the voltage of the capacitor is insufficient to support the execution of the task 102. At this time, a battery or a power supply can be used to supply a voltage to the controller 104 to execute the task 102. In addition, in addition to executing the task 102, the controller 104 also updates the timer 108 to determine the time for the next execution of the task.

[0035] Through this method, it is possible to supply a voltage to the capacitor by the energy conversion component, avoiding the addition of extra power line arrangements in the detection environment. Additionally, the execution period of the task scheduling is determined based on the magnitude of the voltage of the capacitor, enabling the reliable execution of the task through self - power supply and improving the user experience.

[0036] The above combination Figure 1 describes an example environment in which the devices and / or methods of the embodiments of the present disclosure can be implemented. The following combination Figure 2 describes a schematic diagram of an example of the system structure according to an embodiment of the present disclosure.

[0037] Figure 2 Illustrates the implementation of Figure 1An example of an energy-based adaptive scheduling device 200 is provided. The system structure of the energy-based adaptive scheduling device includes a light sensor 202 for measuring light illuminance. In one example, light sensor 202 is a light sensor. In another example, light sensor 202 is an illuminance sensor. The above examples are merely illustrative of the present disclosure and are not intended to limit the present disclosure.

[0038] The light sensor 202 transmits the detected illuminance to the microcontroller unit 204, which corresponds to Figure 1 Controller 104 in FIG. Microcontroller unit 204 can determine the voltage applied to the capacitor by the solar panel based on the illumination obtained from light sensor 202. Furthermore, microcontroller unit 204 can obtain data measured by measurement unit 208, such as vibration or sound signals from the machine. This data measured by measurement unit 208 is used to execute tasks within the microcontroller, such as predicting machine failures based on the data measured by measurement unit 208. Furthermore, microcontroller unit 204 is connected to memory card 206, which stores the results calculated by the microcontroller unit in memory card 206. Furthermore, the microcontroller unit can also store received data, such as data from light sensor 202 and measurement unit 208, on memory card 206.

[0039] Combined with the above Figure 2 A schematic diagram of an example of the system structure of an embodiment of the present disclosure is described below. Figure 3 A schematic diagram depicting an example of a circuit for a solar panel according to an embodiment of the present disclosure.

[0040] like Figure 3 As shown, in Figure 1 In the circuit example 300 of a solar panel powered by capacitor 308, contacts 312 and 314 are connected to the input and output terminals of the solar panel, respectively, to charge capacitor 308. For example, the solar panel charges a 0.1F capacitor. When the solar panel receives more energy, the voltage of capacitor 308 increases as the energy received by the solar panel increases. Capacitor 308 is connected to the circuit's supply voltage 310 via diode 306. In addition, example 300 also includes a battery 302, which is also connected to the circuit's supply voltage 310 via diode 304. Battery 302 can provide voltage to the circuit when the voltage of capacitor 308 is lower than a threshold voltage.

[0041] Combined with the above Figure 3 The following is a schematic diagram of an example of a circuit of a solar panel according to an embodiment of the present disclosure. Figure 4 A schematic diagram depicting an example of a voltage measurement circuit according to an embodiment of the present disclosure.

[0042] The energy generated by the solar panel for charging the capacitor generally follows a pattern of increasing first and then decreasing during the charging process and requires maximum power point tracking (MPPT). Therefore, Figure 4 Example 400 of the circuit shown captures the real-time voltage of the solar panel as a voltage acquisition device to estimate its power output. Therefore, Figure 4 The example 400 shown can be used to measure Figure 3 the voltage in capacitor 308. In Figure 4 , contact 414 is connected to the input interface 414 that can be connected to the solar panel, and contact 412 is connected to the microcontroller unit to obtain the voltage value of resistor 404, so that the voltage provided by the solar panel can be determined based on the resistance values of resistor 402 and resistor 404, and thus the voltage of the capacitor can be determined. As Figure 4 shown, the voltage measurement circuit also has contact 416, which is used to provide a test signal managed by the controller, and the start and stop of voltage acquisition can be adjusted through the on / off operation of the MOS transistor. In addition, the voltage measurement circuit also includes resistors 408 and 410 and transistor 406, where transistor 406 is used to ensure that a voltage can be detected at contact 412.

[0043] The above has been described in conjunction with Figure 4 a schematic diagram of an example of a voltage measurement circuit according to an embodiment of the present disclosure. The following will be described in conjunction with Figure 5 an example of a specific design of the system structure according to an embodiment of the present disclosure.

[0044] As Figure 5 shown, in an example 500 of a specific design of the system structure, it includes external hardware 502 and a microcontroller system-on-chip 504. The external hardware 502 includes a solar panel 512, which is used to obtain the light energy in the environment. The solar panel 512 can provide energy for the capacitor 510, so that the capacitor can continuously obtain energy through the solar panel 512. Additionally, the external hardware 5502 also includes a battery 506. Both the battery 5o6 and the capacitor 510 can be used to provide energy, such as voltage, for the microcontroller system-on-chip 504. The battery 506 and the capacitor 510 are both connected to a dual power selector 508, which is used to select which one of the battery 506 and the capacitor 510 provides voltage for the microcontroller system-on-chip 504. Additionally, the external hardware 502 also has a light sensor 526, which is used to measure the illuminance 522 of the light for the solar panel. Additionally, a control button 528 is also included in the external hardware 502, which can be used for the user to transmit a signal to the task coordinator 524 to control the execution of tasks, such as starting a task or restarting a task.

[0045] The system - on - a - chip microcontroller 504 has a task scheduler 514 that schedules the execution of tasks according to a timer. The task scheduler 514 includes an energy estimator 516. When the timer expires, the energy estimator 516 can calculate the voltage that can be provided to the capacitor by the solar panel based on the illuminance 522 of the light measured by the light sensor 526, so as to further determine the duration of the timer for scheduling the next execution of the task. The energy estimator 516 can also obtain the capacitor voltage 520 of the capacitor. In addition, the energy estimator 516 also includes collector characteristics 518, such as the magnitude of the internal resistance of the capacitor, the recovery efficiency of the solar panel, etc. The task coordinator 524 in the task scheduler 514 can start or restart the execution of the task according to the signal input by the control button 530. It can also control the scheduling of the task according to the magnitude of the capacitor voltage and whether the timer has expired. For example, when the task is a task of a machine - learning model, the task coordinator can start the training task of the machine - learning model according to the control button. After the training task is completed, the inference task of the machine - learning model is then controlled according to the magnitude of the capacitor voltage and the timer.

[0046] The above combines Figure 5 an example of the specific design of the system structure according to an embodiment of the present disclosure is described. The following combines Figure 6 a flowchart of a method for processing tasks according to an embodiment of the present disclosure is described. This method can be executed on the controller 104 or any suitable computing device

[0047] In Figure 6 the example 600 shown, at block 602, the controller 104 determines whether the timer for the execution of the task has expired. If the timer has not expired, the controller waits and does not execute the task. If the timer has expired, then at block 604, the controller 104 measures the voltage of the capacitor that provides power for the execution of the task. In some embodiments, as Figure 4 shown, the voltage of the resistor 404 can be obtained first through the contact point 412, and then the voltage of the input contact point 414 connected to the solar panel can be determined according to the ratio of the resistor 402 and the resistor 404, so as to determine the voltage of the capacitor.

[0048] Next, at block 606, the controller determines whether the voltage is within a predetermined range. If the voltage is within the predetermined range, then at block 608, the controller 104 updates the timer with a target duration, where the target duration is determined based on the compensation voltage provided to the capacitor by the energy conversion component.

[0049] In some embodiments, the scheduling of task execution is on-demand scheduling. At this time, the number of executions is determined according to the efficiency of capacitor charging. If more solar energy is obtained and the capacitor charges faster, the number of task scheduling can be increased. If less solar energy is obtained and the capacitor charges slower, the number of task scheduling can be reduced. In the on-demand scheduling scheme, when using the target duration to update the timer, a light sensor can be used to measure the illuminance. For example Figure 5 As shown, a light sensor 526 is used to measure the illuminance for the energy conversion component. Then the measured illuminance is transmitted to the controller. The controller can then determine the target duration available for updating the timer based on the detected illuminance, thereby determining the time for the next task execution.

[0050] In some embodiments, when determining the target duration according to the illuminance, the controller needs to determine the amount of voltage consumed for each task execution, that is, the controller will determine how much voltage the capacitor loses for one task execution. Since the tasks executed are fixed, the voltage consumed for each task execution is also fixed. Therefore, when compensating for this consumed voltage through the energy conversion component, the illuminance can be used to determine the compensation duration for compensating this consumed voltage. In addition, the controller can also determine the execution duration of the task. In one example, the task execution duration is preset to a predetermined value. In another example, the duration of the previous task execution is used as the execution duration of the current task. Then, the controller determines the target duration based on the compensation duration and the execution duration. For example, the sum of the compensation duration and the execution duration is used as the target duration, thereby determining how long to wait for the next task execution.

[0051] In some embodiments, the task execution is evenly scheduled. At this time, the time interval of the timer is uniform. This uniform interval or timer duration is determined based on the light data collected in the previous working cycle of the machine targeted by the task. For example, if the task is to detect a fault in the machine, the duration of the timer for scheduling the task in the subsequent working cycle can be determined based on the light data collected in one working cycle of the machine.

[0052] During this process, the controller 104 first obtains a set of illuminance values for the energy conversion component measured during the previous duty cycle of the machine related to the task. For example, a set of illuminance values measured by a light sensor during the previous duty cycle are collected by the light sensor and recorded and saved in a storage device. Then the controller uses this set of illuminance values to determine the total voltage that can be obtained during the target duty cycle of the machine. In some embodiments, a pre-trained machine learning model is used to calculate the total voltage that can be obtained from the solar panels during the target duty cycle using a set of illuminance values during the previous duty cycle. In some embodiments, a mathematical function can be used to calculate the total voltage that can be obtained from the solar panels during the target duty cycle based on a set of illuminance values. Additionally, the controller can also obtain the consumption voltage for each execution of the task. For example, the voltage consumed for each execution of the task is known. Therefore, the controller can determine the number of executions of the task based on the total voltage and the consumption voltage. For example, dividing the total voltage by the consumption voltage can determine how many times the total voltage provided by the solar panels can be used. Then the controller can use the duration of the target duty cycle and the number of executions to calculate the time interval for executing the task during the target duty cycle. For example, by dividing the duration of the target duty cycle by the number of executions to determine the duration of each execution interval. Then this time interval is used to update the timer.

[0053] In some embodiments, the compensation voltage provided by the energy conversion component to the capacitor is provided by wind energy or water energy, and its target duration can be determined based on the duration of the compensation voltage provided by wind energy or water energy. The above examples are only for describing the present disclosure and are not specific limitations of the present disclosure.

[0054] At block 610, the controller 104 uses the voltage of the capacitor to execute the task. When the voltage is within a predetermined range, it indicates that the voltage provided by the capacitor can complete the execution of the task, and at this time, the voltage of the capacitor is used to execute the task once.

[0055] In some embodiments, if the voltage is outside the predetermined range, in the on-demand scheduling scenario and in the uniform scheduling scenario of the task, the voltage provided by the battery can be used to execute the task. At this time, the controller obtains a preset predetermined duration, and then uses this predetermined duration to update the timer.

[0056] In some embodiments, the task scheduled and executed by the controller is an inference task of a machine learning model. Before executing this inference task, the controller can also load this inference task. For example, load the data required to execute the inference task. Additionally, the training task of this machine learning model can also be executed on the controller.

[0057] With this method, the energy conversion component can supply voltage to the capacitor, avoiding the addition of extra power line arrangements in the detection environment. Additionally, the period of task scheduling execution is determined based on the magnitude of the voltage of the capacitor, enabling reliable execution of tasks through self-power supply and improving the user experience.

[0058] The above has been combined with Figure 6 to describe the flowchart of the method for processing tasks according to an embodiment of the present disclosure. The following will be combined with Figure 7 to describe the schematic diagram of an example process for processing tasks according to an embodiment of the present disclosure.

[0059] As Figure 7 shown, the example process 700 is an example process for on-demand scheduling of the inference task of the machine learning model. This example process starts at block 702. Then, an external event for training or retraining the machine learning model is received at block 704. For example, the machine learning model is trained or retrained by triggering Figure 5 the control button 528 in

[0060] At block 706, the machine learning model starts to be trained. For example, the controller trains the machine learning model for fault detection of the machine. After the training task is completed, at block 708, the inference task of the machine learning model is loaded.

[0061] At block 710, the controller is in the idle stage. There is a timer in the controller. When the timer has not expired, the controller remains in the idle state and does not execute the inference task of the machine learning model. After the timer expires, at block 712, the voltage of the capacitor for supplying power to the controller is measured, and the controller obtains the voltage of this capacitor. Then, at block 714, it is determined whether the voltage of the capacitor is within the operating range. If the voltage of the capacitor is within the operating range, at block 716, the controller estimates the energy budget using the illuminance obtained from the optical sensor.

[0062]

[0063] where U c (0) represents the initial capacitor voltage, τ = RC is the time constant, where R is the internal resistance and C is the capacitor. Additionally, U Rrepresents the charging voltage of the capacitor, corresponding to the open-circuit voltage of the solar panel. Under appropriate conditions, U R can be considered a linear transformation of the measured illuminance η, expressed as U R = a×η + b, where a and b are constants.

[0064] Based on the relationship of U c ~t, given the current capacitor voltage as U c (t0), the voltage increment δU c (δt) at the time point after a time interval δt is calculated by the following formula (2):

[0065]

[0066] Therefore, considering that executing a single task takes Δt exe seconds and causes a voltage drop of ΔU, the time required to replenish the consumed energy is calculated by the following formula (3):

[0067]

[0068] where represents an approximation of U R -U c (t0). When performing on-demand scheduling, the energy budget is Δt exe +Δt charge , which can be set as the cycle timer period.

[0069] If the voltage of the capacitor is not within the operating range, the energy budget is calculated based on battery charging at block 720. When using battery charging, the energy budget is set to a predetermined duration. Then at block 720, the cycle timer is updated based on the energy budget. Then at block 722, the inference task of the machine learning model is started. Then, the next inference task of the machine learning model is executed after the updated cycle timer expires, and so on.

[0070] Through this method, the voltage can be provided to the capacitor by the energy conversion component, avoiding the addition of extra power line arrangements in the detection environment. Additionally, the period of task scheduling execution is determined based on the magnitude of the capacitor voltage, enabling reliable execution of tasks through self-power supply and improving the user experience.

[0071] The above Figure 7 describes a schematic diagram of an example process for processing tasks in an embodiment of the present disclosure. The following Figure 8 describes a schematic diagram of another example process for processing tasks according to an embodiment of the present disclosure.

[0072] As Figure 8As shown, the example process 800 is an example process for periodically scheduling inference tasks of a machine learning model. The example process starts at block 802. Then, at block 804, an external event for training or retraining the machine learning model is received. For example, by triggering Figure 5 The controller can then train or retrain the machine learning model by pressing control button 528 in the control panel. At block 806 , training of the machine learning model begins. For example, a machine learning model for machine fault detection is used. After the training task is completed, at block 808 , the controller loads an inference task, such as data acquired for fault detection.

[0073] At block 810, the controller loads the energy budget learning task. Furthermore, at block 812, the controller records a set of illuminance or lumens collected by the light sensor for one operating cycle of the machine. Additionally, this set of illuminance or lumens is acquired within a timer period set by a data logging timer. The recorded set of illuminance or lumens can then be used to perform the energy budget learning task, and the calculated energy budget can be used to update the inference task cycle timer.

[0074] For example, a machine operates in a 24-hour working cycle. If the sequence of illuminance measured in one working cycle is η(t), the energy collected in the next working cycle can be predicted by the following formula (4):

[0075]

[0076] in represents the moving average of the illuminance measured in one working cycle. Thus, the energy in one working cycle can be calculated using the above formula (4). The number of times a task can be executed in one working cycle can then be determined based on the energy collected in one working cycle and the voltage consumed by each task execution. The time interval between each task execution can then be determined by dividing the duration of one working cycle by the number of task executions. This time interval is then used as the energy budget to update the task cycle timer.

[0077] Before the task loop timer expires, the controller remains idle at block 814. After the task loop timer expires, at block 816, the voltage of the capacitor that powers the controller is measured. Then at block 818, it is determined whether the voltage of the capacitor is within the operating range. If the voltage of the capacitor is within the operating range, at block 820, the task loop timer is updated using the energy budget calculated over the entire environmental repetition period. For example, the task loop timer is updated using the previously calculated time interval. If the voltage of the capacitor is not within the operating range, at block 822, the task loop timer is updated based on the energy budget from the battery. For example, the energy budget for the battery is set to a predetermined duration. Then at block 824, the inference task of the machine learning model is started. Next, the next inference task of the machine learning model is executed after the updated loop timer expires. Additionally, in Example 800, an energy calculation timer is also set. This timer can be set to a duration, and then after the energy calculation timer expires, at block 826, the energy budget learning task is recalculated, and the task loop timer is updated to the recalculated duration.

[0078] Through this method, the voltage of the capacitor can be provided by the energy conversion component, avoiding the addition of extra power line arrangements in the detection environment. Additionally, the execution period of the task scheduling is determined based on the magnitude of the voltage of the capacitor, enabling the reliable execution of tasks through self-power supply and improving the user experience.

[0079] The above combination Figure 8 describes a schematic diagram of another example process for processing tasks according to an embodiment of the present disclosure. The following combination Figure 9 describes a schematic diagram of examples of on-demand scheduling and periodic scheduling according to an embodiment of the present disclosure.

[0080] In Figure 9 the illustrated Example 900, the change in illuminance within two working cycles is shown in block 902. Block 904 shows the corresponding change in the system voltage or capacitor voltage. Curve 912 is the change curve of the system voltage or capacitor voltage corresponding to on-demand scheduling, and curve 910 corresponds to the change curve of the system voltage or capacitor voltage corresponding to uniform scheduling. Straight line 914 corresponds to the battery voltage. Additionally, block 906 corresponds to the number of task executions and the corresponding time intervals for on-demand scheduling, and block 908 corresponds to the number of task executions and the uniform time intervals for uniform scheduling.

[0081] Figure 10 Further shown is a schematic diagram of a device for processing tasks according to an embodiment of the present disclosure. Device 1000 can be applied to controller 104, which can include multiple modules for performing the corresponding steps in method 600 as Figure 6 discussed. As Figure 10As shown, the apparatus 1000 includes: a voltage measurement unit 1002 configured to measure the voltage of a capacitor that supplies power for the execution of a task in response to the expiration of a timer for the execution of the task; a timer update and task execution unit 1004 configured to update the timer with a target duration in response to the voltage being within a predetermined range, where the target duration is determined based on a compensation voltage provided by an energy conversion component to the capacitor; and execute the task using the voltage of the capacitor.

[0082] In some embodiments, the timer update and task execution unit 1004 includes: an illuminance acquisition unit configured to acquire the illuminance of the energy conversion component measured by a light sensor; and a first target duration determination unit configured to determine the target duration based on the illuminance.

[0083] In some embodiments, the first target duration determination unit includes: a consumption voltage determination unit configured to determine the consumption voltage for the execution of the task; a compensation duration determination unit configured to determine, based on the illuminance, a compensation duration during which the energy conversion component compensates the capacitor for the consumption voltage; an execution duration determination unit configured to determine the execution duration of the task; and a second target duration determination unit configured to determine the target duration based on the compensation duration and the execution duration.

[0084] In some embodiments, the apparatus 1000 further includes: a set of illuminance acquisition units configured to acquire a set of illuminances of the energy conversion component measured during a previous working cycle of a machine related to the task; a total voltage determination unit configured to determine, based on the set of illuminances, the total voltage that can be obtained during a target working cycle of the machine; an execution times determination unit configured to determine the number of executions of the task based on the total voltage and the consumption voltage for each execution of the task; a third target duration determination unit configured to determine the target duration based on the number of executions; and a second timer update unit configured to update the timer with the target duration.

[0085] In some embodiments, the third target duration determination unit includes: a time interval determination unit configured to determine, based on the duration of the target working cycle and the number of executions, a time interval for executing the task during the target working cycle; and a fourth target duration determination unit configured to determine the time interval as the target duration.

[0086] In some embodiments, the apparatus 1000 further includes: a data collection unit configured to collect, during a previous working cycle, a set of illuminances measured by a light sensor; and a recording unit configured to record the set of illuminances.

[0087] In some embodiments, the apparatus 1000 further includes: a task execution unit configured to execute the task using the voltage provided by a battery in response to the voltage being outside the predetermined range.

[0088] In some embodiments, the apparatus 1000 further includes: a predetermined duration determining unit configured to determine a predetermined duration related to the battery; and a second timer updating unit configured to update the timer using the predetermined duration.

[0089] In some embodiments, where the task is an inference task of a machine learning model or a training task of the machine learning model, the apparatus 1100 further includes: a task loading unit configured to load an inference task of a machine learning model or the training task of the machine learning model.

[0090] Figure 11 A schematic block diagram of an example device 1100 that can be used to implement embodiments of the present disclosure is shown. Figure 1 The controller 104 in can be implemented using the device 1100. As shown, the device 1100 includes a processor 1101, which can execute various appropriate actions and processes according to computer program instructions stored in a read-only memory (ROM) 1102 and loaded into a random access memory (RAM) 1103. In the RAM 1103, various programs and data required for the operation of the device 1100 can also be stored. The processor 1101, the ROM 1102, and the RAM 1103 are connected to each other via a bus 1104. An input / output (I / O) interface 1105 is also connected to the bus 1104.

[0091] The various processes and processes described above, such as method 600 and processes 700 and 800, can be executed by the processor 1101. For example, in some embodiments, method 600 and processes 700 and 800 can be implemented as a computer software program, which is tangibly contained in a machine-readable medium. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 1100 via the ROM1102. When the computer program is loaded into the RAM1103 and executed by the processor 1101, one or more actions of method 600 and processes 700 and 800 described above can be executed.

[0092] The present disclosure can be a method, an apparatus, a system, and / or a computer program product. The computer program product can include a computer-readable storage medium having computer-readable program instructions thereon for performing various aspects of the present disclosure.

[0093] A computer-readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer-readable storage medium include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disc (DVD), a memory stick, a floppy disk, a mechanically encoded device such as a punch card or raised structures in grooves having instructions stored thereon, and any suitable combination of the foregoing. The computer-readable storage medium as used herein is not construed to be a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., an optical pulse through an optical fiber cable), or an electrical signal transmitted through a wire.

[0094] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to respective computing / processing devices, or can be downloaded to an external computer or an external storage device through a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network may include a copper transmission cable, an optical fiber transmission, a wireless transmission, a router, a firewall, a switch, a gateway computer, and / or an edge server. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in each computing / processing device.

[0095] The computer program instructions for performing the operations of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine - related instructions, microcode, firmware instructions, state - setting data, or source code or object code written in any combination of one or more programming languages, including object - oriented programming languages such as Smalltalk, C++, etc., and conventional procedural programming languages such as the "C" language or similar programming languages. The computer - readable program instructions may be executed entirely on the user's computer, partially on the user's computer, executed as a stand - alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or it may be connected to an external computer (e.g., via an Internet service provider through the Internet). In some embodiments, by using the state information of the computer - readable program instructions to customize an electronic circuit, such as a programmable logic circuit, a field - programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit can execute the computer - readable program instructions to implement various aspects of the present disclosure.

[0096] Aspects of the present disclosure are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the disclosure. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer - readable program instructions.

[0097] These computer - readable program instructions can be provided to a processing unit of a general - purpose computer, a special - purpose computer, or other programmable data - processing apparatus to produce a machine such that the instructions, when executed by the processing unit of the computer or other programmable data - processing apparatus, create a means for implementing the functions / acts specified in one or more blocks of the flowchart and / or block diagram. These computer - readable program instructions can also be stored in a computer - readable storage medium, which causes a computer, a programmable data - processing apparatus, and / or other devices to operate in a particular manner, so that the computer - readable medium storing the instructions includes a manufacture that includes instructions for implementing various aspects of the functions / acts specified in one or more blocks of the flowchart and / or block diagram.

[0098] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device, causing a series of operational steps to be performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process such that the instructions executed on the computer, other programmable data processing apparatus, or other device implement the functions / acts specified in one or more boxes of the flowchart and / or block diagram.

[0099] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a segment of code, or a portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions noted in the blocks may occur out of the order noted in the figures. For example, two consecutive blocks may in fact be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending upon the functionality involved. It should also be noted that each block of the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented by special purpose hardware-based systems that perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.

[0100] The embodiments of the present disclosure have been described above. The above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The choice of terms used herein is intended to best explain the principles of the embodiments, the practical application, or the technical improvement of the technology in the market, or to enable other ordinary skilled persons in the art to understand the embodiments disclosed herein.

Claims

1. A method for processing a task, comprising: Measuring a voltage of a capacitor that supplies power for the execution of the task in response to expiration of a timer for the execution of the task; In response to the voltage being within a predetermined range, Updating the timer with a target duration, wherein the target duration is determined based on a compensation voltage provided by an energy conversion component to the capacitor; and Executing the task using the voltage of the capacitor.

2. The method according to claim 1, wherein updating the timer with a target duration comprises: Obtaining an illuminance for the energy conversion component measured by a light sensor; And Determining the target duration based on the illuminance.

3. The method according to claim 2, wherein determining the target duration based on the illuminance comprises: Determining a consumption voltage for the execution of the task; Determining a compensation duration for the energy conversion component to compensate the consumption voltage for the capacitor based on the illuminance; Determining an execution duration of the task; And Determining the target duration based on the compensation duration and the execution duration.

4. The method according to claim 1, further comprising: Obtaining a set of illuminances for the energy conversion component measured in a previous work cycle of a machine related to the task; Determining a total voltage that can be obtained in a target work cycle of the machine based on the set of illuminances; Determining an execution number of the task based on the total voltage and a consumption voltage for each execution of the task; Determining the target duration based on the execution number; And Updating the timer with the target duration.

5. The method according to claim 4, wherein determining the target duration based on the execution number comprises: Determining a time interval for executing the task in the target work cycle based on a duration of the target work cycle and the execution number; And Determining the time interval as the target duration.

6. The method according to claim 4, further comprising: Collecting the set of illuminances measured by the light sensor in the previous work cycle; And Recording the set of illuminances.

7. The method according to claim 1, further comprising: Executing the task using a voltage provided by a battery in response to the voltage being outside the predetermined range.

8. The method according to claim 7, further comprising: Determining a predetermined duration related to the battery; and Updating the timer with the predetermined duration.

9. The method according to claim 1, wherein the task is an inference task or a training task of a machine learning model, and the method further comprises: Loading the inference task or the training task of the machine learning model.

10. An apparatus for processing a task, comprising: A voltage measurement unit configured to measure a voltage of a capacitor that supplies power for the execution of the task in response to expiration of a timer for the execution of the task; A timer update and task execution unit configured to, in response to the voltage being within a predetermined range, Updating the timer using a target duration, where the target duration is determined based on a compensation voltage provided by an energy conversion component to the capacitor; and Performing the task using the voltage of the capacitor.

11. A controller, comprising: At least one processor; And A memory, coupled to the at least one processor and having instructions stored thereon, the instructions, when executed by the at least one processor, cause the controller to perform the method according to any one of claims 1-9.

12. An energy-based adaptive scheduling device, comprising: An energy conversion component; A capacitor; And The controller according to claim 11.

13. The adaptive scheduling device according to claim 12, wherein, The energy conversion component includes: a solar panel.

14. A computer-readable storage medium having computer-executable instructions stored thereon, wherein the computer-executable instructions are executed by a processor to implement the method according to any one of claims 1 to 9.

Images