Device Cooperative Scheduling Method, Device, Equipment and Medium Based on Industrial Internet of Things

Abstract

The present invention discloses a device collaborative scheduling method, device, equipment and medium based on industrial Internet of Things, which relates to the technical field of Internet of Things. Among them, the method includes: obtaining various types of working data sequences of each device; determining a number of target sequences based on the working data sequences of the same category of each device and interpolating each target sequence, where the target sequence is a working data sequence lacking a number of data; determining the working state of each device based on the interpolated working data sequences of each device; and performing task scheduling on each device based on the working state of each device. The present invention solves the problem that the existing data interpolation algorithms only interpolate single devices and do not consider the collaborative relationship between devices, so that when using the interpolated working data sequences of each device to perform task scheduling on each device, the resource utilization rate can be optimized and the production efficiency can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial Internet of Things, and particularly to a device collaborative scheduling method, device, equipment and medium based on industrial Internet of Things. Background Art

[0002] In the industrial Internet of Things, device collaboration and scheduling are often intertwined. Device collaboration refers to enabling multiple devices to cooperate and work together to complete specific production tasks through network connection and intelligent control systems in an industrial production environment. Device scheduling refers to reasonably arranging the use of devices, personnel and materials and optimizing the production process through efficient scheduling algorithms and intelligent decision-making systems during the production process, so as to maximize production efficiency, reduce costs and meet production requirements.

[0003] When performing collaborative scheduling on devices, due to reasons such as device failures, communication delays or sensor malfunctions, data may be missing or incomplete, and the missing data needs to be filled. In the same manufacturing workshop, there may be close collaboration relationships between devices. If the data of a certain device is missing, it may affect the scheduling efficiency of the entire production line. Existing data interpolation algorithms only perform interpolation on a single device and do not consider the collaborative relationship between devices.

[0004] The above content is only used to assist in understanding the technical solution of the present invention and does not represent an admission that the above content is prior art. Summary of the Invention

[0005] The main purpose of the present invention is to provide a device collaborative scheduling method, device, equipment and medium based on industrial Internet of Things, aiming to solve the technical problem that existing data interpolation algorithms only perform interpolation on a single device and do not consider the collaborative relationship between devices.

[0006] To achieve the above purpose, the present invention provides a device collaborative scheduling method based on industrial Internet of Things, including: obtaining various types of working data sequences of each device; determining a number of target sequences based on the working data sequences of the same type of each device and performing interpolation on each target sequence, where the target sequence is a working data sequence missing several data; determining the working state of each device based on the interpolated working data sequences of each device; and performing task scheduling on each device based on the working state of each device.

[0007] Optionally, determining a plurality of target sequences based on the working data sequences of the same category of each device and interpolating each target sequence includes: determining a plurality of target sequences from the working data sequences of the same category of each device, where each target sequence is a data sequence including missing data bits; for any missing data bit of any target sequence, determining a supplementary sequence of the missing data bit from the other working data sequences except the target sequence, and supplementing the missing data bit based on the supplementary sequence, where the supplementary sequence corresponds to the position of the missing data bit and has data; interpolating each target sequence based on the supplemented working data sequences of each device according to a preset algorithm.

[0008] Optionally, supplementing the missing data bit based on the supplementary sequence includes: calculating a difference factor between each supplementary sequence and the missing data bit; using the supplementary sequence with the smallest difference factor as the matching sequence for the missing data bit; using the data corresponding to the position of the missing data bit in the matching sequence as the supplementary data for the missing data bit.

[0009] Optionally, calculating the difference factor between each supplementary sequence and the missing data bit includes: setting a preset window centered on the missing data bit; respectively calculating the difference factor between each supplementary sequence and the target sequence where the missing data bit is located within the preset window.

[0010] Optionally, respectively calculating the difference factor between each supplementary sequence and the target sequence where the missing data bit is located within the preset window includes: respectively calculating the difference factor between each supplementary sequence and the target sequence where the missing data bit is located within the preset window using the following formula (1):

[0011]

[0012] In the formula, represents the difference factor between the th target sequence where the th missing data bit is located and the th supplementary sequence of the th missing data bit within the preset window, represents the number of data commonly possessed by the th target sequence where the th missing data bit is located and the th supplementary sequence of the th missing data bit within the preset window, represents the th data of the [[ID=tmp41]]th target sequence where the th missing data bit is located within the preset window, represents the The supplementary sequence of the missing data bits within the preset window represents taking the absolute value, represents the hyperbolic tangent function, represents the preset adjustment factor.

[0013] Optionally, the interpolation of each target sequence based on the working data sequences supplemented by each device according to the preset algorithm includes: calculating the KNN distance matrix based on the working data sequences supplemented by each device, and determining the K nearest neighbor devices of each missing data bit based on the KNN distance matrix; interpolating each missing data bit based on the working data sequences supplemented by the K nearest neighbor devices of each missing data bit.

[0014] Optionally, the task scheduling of each device based on the working states of each device includes: presetting a scheduling model, where the input of the scheduling model is the working states of each device, and the output of the scheduling model is the scheduling strategy of each device; performing task scheduling on each device based on the scheduling model.

[0015] In addition, to achieve the above object, the present invention also provides a device collaborative scheduling device based on the industrial Internet of Things, including a management platform, a sensing network platform, and an object platform that are sequentially communicatively connected. The object platform is used to collect and store various types of working data of each device. The sensing network platform is used to transmit various types of working data of each device to the management platform. The management platform includes: a data acquisition module for obtaining various types of working data sequences of each device; a data interpolation module for determining several target sequences based on the working data sequences of the same type of each device and interpolating each target sequence, where the target sequence is a working data sequence missing several data; a working state determination module for determining the working states of each device based on the interpolated working data sequences of each device; a task scheduling module for performing task scheduling on each device based on the working states of each device.

[0016] The present invention also provides a device collaborative scheduling device based on the industrial Internet of Things, including: at least one processor; and a memory communicatively connected to the at least one processor; wherein, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above-mentioned device collaborative scheduling method based on the industrial Internet of Things.

[0017] The present invention also provides a computer-readable storage medium, including: storing a computer program, and when the computer program is executed by a processor, the above-mentioned device collaborative scheduling method based on the industrial Internet of Things is implemented.

[0018] A device collaborative scheduling method, device, equipment and medium based on industrial Internet of Things proposed by the present invention first obtains various types of working data sequences of each device; then determines several target sequences based on the working data sequences of each device and interpolates each target sequence; finally determines the working status of each device based on the interpolated working data sequences of each device and schedules tasks for each device based on the working status of each device; thus, using the same working data sequences of multiple devices to interpolate the working data sequences of each device, solves the problem that the existing data interpolation algorithms only interpolate a single device and do not consider the collaborative relationship between devices, resulting in poor interpolation accuracy. Furthermore, when scheduling tasks for each device using the interpolated working data sequences of each device, the resource utilization rate can be optimized and the production efficiency can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 FIG. is a flowchart of a device collaborative scheduling method based on industrial Internet of Things according to an embodiment of the present invention;

[0020] Figure 2 FIG. is a structural block diagram of a device collaborative scheduling device based on industrial Internet of Things according to an embodiment of the present invention;

[0021] Figure 3 FIG. is a structural schematic diagram of a device collaborative scheduling equipment based on industrial Internet of Things according to an embodiment of the present invention.

[0022] The realization, functional features and advantages of the object of the present invention will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0023] It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0024] Existing data interpolation algorithms only interpolate a single device and do not consider the collaborative relationship between devices. The KNN (K-Nearest Neighbor) interpolation algorithm can perform data interpolation based on the similarity of data and has a certain ability to capture the collaborative effect between devices.

[0025] When using the KNN algorithm for data interpolation, since the original data, that is, some working data of the device, is missing and the distance between samples cannot be directly calculated, the KNN distance matrix cannot be formed. Therefore, it is necessary to first temporarily fill the missing data. For time series data such as the working data of the device, usually only the previous or next data of the missing data is used to fill the missing data to form a complete data set.

[0026] However, when calculating the distance between samples, it is affected by the temporarily filled data. Using the previous or next data of the missing data to fill the missing item only considers the working data of a single device and does not consider the collaborative similarity between devices. For example, if the missing data of a certain device is abnormal current data and other devices have collected this abnormal current data, if it is filled only according to the previous or next data of this device, a large error will be obtained when calculating the distance matrix using the filled working data, and thus there will also be a large error in the final interpolation result.

[0027] To solve the above problems, the present invention provides a device collaborative scheduling method, device, equipment and medium based on the industrial Internet of Things. The following is a detailed introduction to the solution of the present invention.

[0028] Figure 1 FIG. is a flowchart of a device collaborative scheduling method based on the industrial Internet of Things according to an embodiment of the present invention. The device collaborative scheduling method based on the industrial Internet of Things can be executed by a device collaborative scheduling device with data processing capabilities. The device collaborative scheduling device can be a device collaborative scheduling device based on the industrial Internet of Things. Referring to Figure 1 the device collaborative scheduling method based on the industrial Internet of Things may include the following steps:

[0029] Step S1, obtain the working data sequences of various categories of each device.

[0030] Among them, the working data sequence is a time series data sequence representing the working state of the device.

[0031] In a specific implementation process, the working data sequences of various categories of each device can be obtained from an object platform storing various data of the device. The working data sequences of various categories of each device can be the load data, current data, voltage data, energy consumption data, task execution time data, etc. of the device. It should be noted that the load data can be collected by sensors or device monitoring tools on the device; the current data and voltage data can be collected by sensors or smart meters on the device; the energy consumption data can be collected by energy consumption monitoring devices or smart meters on the device; the task execution time data can be obtained from the object platform.

[0032] Step S2, determine a plurality of target sequences based on the working data sequences of the same category of each device and perform interpolation on each target sequence, where the target sequence is a working data sequence missing several data.

[0033] It should be noted that when using common interpolation algorithms such as linear interpolation algorithm, spline interpolation algorithm, polynomial interpolation algorithm, etc. to interpolate the working data sequence of a device, only the working data sequence of a single device is considered, that is, the collaborative relationship between devices is not considered. The KNN (K-Nearest Neighbors) algorithm can perform data interpolation based on the similarity of data. Therefore, in this embodiment, the KNN algorithm is used to interpolate the device. However, when calculating the distance matrix using the KNN interpolation algorithm, the missing data needs to be filled first. In the existing algorithms, only the previous data or the next data of the missing data is used to fill the missing item, and the similarity and collaborative relationship between devices are not considered.

[0034] Based on this, in the embodiment of the present invention, based on the similarity and collaborative relationship between devices, the working data sequence of the device with missing data is interpolated using the working data sequences of the devices with non-missing data. Considering that in the same working workshop, multiple devices work simultaneously, and at this time, the environmental conditions and sensor configurations of multiple devices are similar. The working data sequences of the devices with non-missing data can often better reflect the working state of the device represented by the missing data. Therefore, the working data sequences of the devices with non-missing data can better provide interpolation references for the devices with missing data.

[0035] In this embodiment, an example of a working data sequence of any category is used for illustration. It can be understood that due to the collaborative relationship between devices, for different devices, there is a certain correlation in the working data sequences of the same category corresponding to them. For example, if there are some missing data in the current data sequence of a certain device, the data in the current data sequence of other devices can be used to temporarily fill the missing data of this device. Therefore, compared with only relying on other data in the current data sequence of this device for temporary filling, by introducing the current data sequences of other devices, the similarity and collaborative relationship between devices can be combined, and the accuracy of temporarily filling the missing data can be significantly improved.

[0036] In one embodiment, in step S2, determining a plurality of target sequences based on the working data sequences of the same category of each device and interpolating each target sequence may specifically include:

[0037] S21. Determine a plurality of target sequences from the working data sequences of the same category of each device, where each target sequence is a data sequence containing missing data bits;

[0038] S22. For any missing data bit of any target sequence, determine the supplementary sequence of the missing data bit from the other working data sequences except the target sequence, and supplement the missing data bit based on the supplementary sequence, where the supplementary sequence corresponds to the position of the missing data bit and has data;

[0039] S23. Interpolate each target sequence based on the supplemented working data sequence of each device according to a preset algorithm.

[0040] In the specific implementation process, several working data sequences with missing data are found in the working data sequence of each device as target sequences. It can be understood that each target sequence is a data sequence containing missing data bits, and the missing data bits are data bits that need to be interpolated.

[0041] In one embodiment, in step S22, supplementing the missing data bits based on the supplement sequence may specifically include:

[0042] S221. Calculate the difference factor between each of the supplementary sequences and the missing data bits;

[0043] S222. Using the supplementary sequence with the smallest difference factor as the matching sequence for the missing data bits;

[0044] S223: Use the data corresponding to the position of the missing data bit in the matching sequence as supplementary data for the missing data bit.

[0045] The difference factor may represent the data difference between each supplementary sequence and the target sequence corresponding to the missing data bit within a preset window size.

[0046] It should be noted that the specific steps for using the KNN algorithm to interpolate various types of working data sequences of various devices are: cleaning the data and removing abnormal data; calculating the KNN distance matrix; selecting K nearest neighbors; and filling in missing data bits based on the K nearest neighbors.

[0047] This embodiment improves the steps of calculating the KNN distance matrix. In the existing KNN algorithm, it is necessary to temporarily fill in the missing data before calculating the KNN distance matrix. The supplementary data in this embodiment is the data used to temporarily fill in the missing data.

[0048] In step S221, the device cooperative scheduling device may first set a preset window with the missing data bit as the center, and then respectively calculate the difference factors between each of the supplementary sequences and the target sequence where the missing data bit is located within the preset window.

[0049] Specifically, the The target sequence missing data bits and the first As an example of a supplementary sequence, the following formula (1) can be used to calculate the The target sequence The first of the missing data bits Supplementary sequence and The difference factor of the target sequence within the preset window :

[0050]

[0051] In the formula, represents the th target sequence where the th missing data bit is located and the th difference factor of the th supplementary sequence of the th missing data bit within the preset window, represents the th target sequence where the th missing data bit is located and the th number of data shared by the th supplementary sequence of the th missing data bit within the preset window, [[ID=3,3]]represents the th data of the th target sequence where the th missing data bit is located within the preset window, represents the th data of the th supplementary sequence of the th missing data bit within the preset window, represents taking the absolute value,

[0052] It should be noted that if, within the preset window, the th target sequence where the th missing data bit is located has 8 data, while the th supplementary sequence of the th missing data bit has only 5 data, then is 5. In formula (1), represents the average difference of the corresponding data values at the common time points of the two sequences within the preset window. Since the more data the two sequences share within the preset window, that is, is larger, the higher the confidence level of the calculated difference factor. And because the hyperbolic tangent function has a normalization effect, that is, normalizing the input value to between -1 and 1 (since in this embodiment is a non - negative number, so in this embodiment is to normalize to between 0 and 1).

[0053] When remains unchanged, if is larger, is close to 1, and thus is larger; while if is smaller, being smaller can be understood as having a punishing effect, ensuring that the difference factor will not increase excessively at low confidence levels.

[0054] It can be understood that in this embodiment, is used to make an adjustment to which can be understood as multiplying by a weight representing the confidence level. In addition, in this embodiment, adding the natural number 1 to is to avoid the influence on the calculation result when is 0.

[0055] In one embodiment, in step S23, interpolating each target sequence based on the supplemented working data sequences of each device according to a preset algorithm may specifically include:

[0056] S231. Calculate the KNN distance matrix based on the supplemented working data sequences of each device, and determine the K nearest neighbor devices of each missing data bit based on the KNN distance matrix;

[0057] S232. Interpolate each missing data bit based on the supplemented working data sequences of the K nearest neighbor devices of each missing data bit.

[0058] In the specific implementation process, first use the KNN algorithm and calculate the KNN distance matrix based on the supplemented working data sequences of each device, and then determine the K nearest neighbor devices of each missing data bit based on the KNN distance matrix.

[0059] Further, in step S232, each missing data bit can be interpolated using the weighted average method based on the supplemented working data sequences of the K nearest neighbor devices of each missing data bit.

[0060] It can be understood that the weighted average method can make the nearer (i.e., the higher the similarity) neighbor data contribute more to the interpolation.

[0061] In this exemplary embodiment, since the difference factor characterizes the data difference between each supplemented sequence and the target sequence where the missing data bit is located within the preset window size, on this basis, determine the matching sequence of each missing data bit based on the difference factor and perform temporary filling of the missing data bit based on the matching sequence. Then, when using the KNN algorithm to perform interpolation calculation on the temporarily filled working data sequence, the similarity and collaborative relationship between devices can be utilized and the accuracy of interpolation can be greatly improved.

[0062] Step S3. Determine the working state of each device based on the interpolated working data sequences of each device;

[0063] Step S4: Perform task scheduling for each device based on the working status of each device.

[0064] In a specific implementation process, the working status of the device can be determined by analyzing the change trend and fluctuation range of the data in the interpolated working data sequence of each device.

[0065] It can be understood that the interpolated working data sequence makes up for the data missing caused by device failures, communication delays, or sensor malfunctions, thus providing more continuous and smooth working data. By monitoring and comparing the interpolated working data in real time, it can be identified whether the device is in a normal operation, warning, failure, or shutdown state, etc., so as to provide support for the maintenance and scheduling of the device.

[0066] In one embodiment, in step S4, performing task scheduling for each device based on the working status of each device specifically may include:

[0067] S41: Preset a scheduling model, the input of the scheduling model is the working status of each device, and the output of the scheduling model is the scheduling strategy for each device;

[0068] S42: Perform task scheduling for each device based on the scheduling model.

[0069] In a specific implementation process, a scheduling model can be constructed and trained through a heuristic algorithm. The working status of each device is input into the scheduling model, and the scheduling model processes and makes decisions on the working status of each device, and outputs the corresponding scheduling strategy for each device. Among them, the scheduling strategy may include: the start-stop sequence of the device, the distribution of the workload, the maintenance arrangement, etc.

[0070] Furthermore, the task is assigned to the most suitable device according to the priority of the task and the corresponding scheduling strategy of each device, and then the running order and load balance of the device are adjusted, and it is ensured that each device executes the task smoothly and efficiently according to the scheduling strategy.

[0071] Furthermore, the execution situation of the device is monitored in real time, and the scheduling strategy is dynamically adjusted to cope with emergencies or changes in the device status, so as to ensure the optimized execution of different tasks.

[0072] It can be understood that performing task scheduling for each device based on the corresponding scheduling strategy of each device can optimize the resource utilization rate, improve the production efficiency, and reduce the failure shutdown time.

[0073] In this exemplary embodiment, by obtaining the working data sequences of various types of each device; then determining a number of target sequences based on the working data sequences of the same type of each device and interpolating each target sequence; finally, determining the working state of each device based on the interpolated working data sequences of each device and performing task scheduling on each device based on the working state of each device; thus, by using the working data sequences of the same type of multiple devices to interpolate the working data sequences of various types of each device, the problem that the existing data interpolation algorithm only interpolates a single device and does not consider the collaborative relationship between devices, resulting in poor interpolation accuracy, is solved. At the same time, task scheduling based on the interpolated working data sequences of each device can better optimize the resource utilization rate, thereby improving the production efficiency.

[0074] Based on the above embodiment, Figure 2 As shown in the structural block diagram of the device collaborative scheduling device based on the industrial Internet of Things according to an embodiment of the present invention, Figure 2 As shown, the device collaborative scheduling device 200 based on the industrial Internet of Things may include a management platform 201, a sensing network platform 202, and an object platform 203 that are communicatively connected in sequence. The object platform 203 is used to collect and store the working data of various types of each device. The sensing network platform 202 is used to transmit the working data of various types of each device to the management platform. The management platform 201 may include: a data acquisition module 210, a data interpolation module 220, a working state determination module 230, and a task scheduling module 240. Among them,

[0075] The data acquisition module 210 is used to obtain the working data sequences of various types of each device;

[0076] The data interpolation module 220 is used to determine a number of target sequences based on the working data sequences of the same type of each device and interpolate each target sequence, where the target sequence is a working data sequence lacking a number of data;

[0077] The working state determination module 230 is used to determine the working state of each device based on the interpolated working data sequences of each device;

[0078] The task scheduling module 240 is used to perform task scheduling on each device based on the working state of each device.

[0079] In an exemplary embodiment, the data interpolation module 220 can also be used to determine several target sequences from the working data sequences of the same category of each device, wherein each target sequence is a data sequence containing missing data bits; for any missing data bit of any target sequence, a supplementary sequence of the missing data bit is determined from other working data sequences other than the target sequence, and the missing data bit is supplemented based on the supplementary sequence, wherein the supplementary sequence corresponds to the position of the missing data bit and has data; and each target sequence is interpolated based on the supplemented working data sequence of each device according to a preset algorithm.

[0080] In an exemplary embodiment, the data interpolation module 220 can also be used to calculate the difference factor between each of the supplementary sequences and the missing data bit; use the supplementary sequence with the smallest difference factor as the matching sequence of the missing data bit; and use the data corresponding to the position of the missing data bit in the matching sequence as the supplementary data of the missing data bit.

[0081] In an exemplary embodiment, the data interpolation module 220 may also be configured to set a preset window centered on the missing data bit; and calculate the difference factors between each of the supplementary sequences and the target sequence where the missing data bit is located within the preset window.

[0082] In an exemplary embodiment, the data interpolation module 220 uses the following formula (1) to calculate the difference factor between each of the supplementary sequences and the target sequence where the missing data bits are located within a preset window:

[0083]

[0084] Where, Indicates the The missing data bit is located in target sequence and The first of the missing data bits The difference factor of the complementary sequences within the preset window, Indicates the The missing data bit is located in The target sequence and The first of the missing data bits The number of data that the supplementary sequences have in common within the preset window, Indicates the The missing data bit is located in The target sequence is within the preset window data, Indicates the The first of the missing data bits The first supplementary sequence in the preset window data, represents taking the absolute value, represents the hyperbolic tangent function, represents a preset adjustment factor.

[0085] In an exemplary embodiment, the data interpolation module 220 can also be used to calculate a KNN distance matrix based on the supplemented working data sequences of each device, and determine the K nearest neighbor devices of each missing data bit based on the KNN distance matrix; perform interpolation on each missing data bit based on the supplemented working data sequences of the K nearest neighbor devices of each missing data bit.

[0086] In an exemplary embodiment, the task scheduling module 240 can also be used to preset a scheduling model, where the input of the scheduling model is the working status of each device, and the output of the scheduling model is the scheduling strategy of each device; perform task scheduling on each device based on the scheduling model.

[0087] Those skilled in the art should understand that the division of each module in the embodiment is only a logical function division. In actual application, it can be fully or partially integrated into one or more actual carriers, and these modules can all be implemented in the form of software called by a processing unit, or all be implemented in the form of hardware, or be implemented in a combination of software and hardware. It should be noted that each module in an apparatus for device collaborative scheduling based on industrial Internet of Things in this embodiment corresponds one by one to each step in a method for device collaborative scheduling based on industrial Internet of Things in the foregoing embodiment. Therefore, the specific implementation manners of this embodiment can refer to the implementation manners of the foregoing method for device collaborative scheduling based on industrial Internet of Things, which will not be elaborated here.

[0088] Based on the above embodiments, Figure 3 is a structural schematic diagram of a device for device collaborative scheduling based on industrial Internet of Things according to an embodiment of the present invention. As Figure 3 shown, the device may include: a processor 310, a communication interface 320, a memory 330, and a communication bus 340. Among them, the processor 310, the communication interface 320, and the memory 330 complete mutual communication through the communication bus 340. The processor 310 can call the logical instructions in the memory 330 to execute a method for device collaborative scheduling based on industrial Internet of Things. The method includes: obtaining working data sequences of various types of each device; determining a plurality of target sequences based on the working data sequences of the same type of each device and performing interpolation on each target sequence, where the target sequence is a working data sequence missing several data; determining the working status of each device based on the interpolated working data sequences of each device; performing task scheduling on each device based on the working status of each device.

[0089] In addition, when the logical instructions in the above-mentioned memory 330 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program codes.

[0090] On the basis of the above-mentioned embodiments, on the other hand, the present invention further provides a computer program product. The computer program product includes a computer program that can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the device collaborative scheduling method based on the industrial Internet of Things provided by the above-mentioned various methods. The method includes: obtaining various types of working data sequences of each device; determining a plurality of target sequences based on the working data sequences of the same type of each device and performing interpolation on each target sequence, where the target sequence is a working data sequence lacking several data; determining the working states of each device based on the interpolated working data sequences of each device; and performing task scheduling on each device based on the working states of each device.

[0091] On the basis of the above-mentioned embodiments, on the other hand, the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it is implemented to execute the device collaborative scheduling method based on the industrial Internet of Things provided by the above-mentioned various methods. The method includes: obtaining various types of working data sequences of each device; determining a plurality of target sequences based on the working data sequences of the same type of each device and performing interpolation on each target sequence, where the target sequence is a working data sequence lacking several data; determining the working states of each device based on the interpolated working data sequences of each device; and performing task scheduling on each device based on the working states of each device.

[0092] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structure or equivalent process transformation made by using the content of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, shall be equally included in the patent protection scope of the present invention.

Claims

1. A device collaborative scheduling method based on the industrial Internet of Things, characterized in that Including: Obtain the working data sequences of various types of each device; Determine a number of target sequences based on the working data sequences of the same type of each device and interpolate each target sequence, where the target sequence is a working data sequence lacking several data; Determine the working states of each device based on the interpolated working data sequences of each device; Perform task scheduling on each device based on the working states of each device; Among them, the determining a number of target sequences based on the working data sequences of the same type of each device and interpolating each target sequence includes: Determine a number of target sequences from the working data sequences of the same type of each device, where each target sequence is a data sequence containing missing data bits; For any missing data bit of any target sequence, determine the supplementary sequence of the missing data bit from the other working data sequences except the target sequence, and supplement the missing data bit based on the supplementary sequence, where the supplementary sequence corresponds to the position of the missing data bit and has data; Interpolate each target sequence based on the supplemented working data sequences of each device according to a preset algorithm; The supplementing the missing data bit based on the supplementary sequence includes: Calculate the difference factor between each supplementary sequence and the missing data bit; Take the supplementary sequence with the smallest difference factor as the matching sequence of the missing data bit; Take the data corresponding to the position of the missing data bit in the matching sequence as the supplementary data of the missing data bit.

2. The device collaborative scheduling method based on industrial Internet of Things according to claim 1, wherein, The calculating the difference factor between each supplementary sequence and the missing data bit includes: Set a preset window with the missing data bit as the center; Calculate the difference factors of each supplementary sequence and the target sequence where the missing data bit is located within the preset window respectively.

3. The device collaborative scheduling method based on industrial Internet of Things according to claim 2, characterized in that The calculating the difference factors of each supplementary sequence and the target sequence where the missing data bit is located within the preset window respectively includes: Use the following formula (1) to calculate the difference factors of each supplementary sequence and the target sequence where the missing data bit is located within the preset window respectively: In the formula, represents the th difference factor of the th target sequence where the th missing data bit is located and the th supplementary sequence within a preset window, represents the th number of data shared in common by the th target sequence where the th missing data bit is located and the th supplementary sequence within a preset window, represents the th data of the th target sequence within a preset window where the th missing data bit is located, represents the th data of the th supplementary sequence within a preset window where the th missing data bit is located, represents taking the absolute value, represents the hyperbolic tangent function, represents a preset adjustment factor.

4. The device collaborative scheduling method based on industrial Internet of Things according to claim 1, characterized in that The interpolating each target sequence based on the supplemented working data sequences of each device according to a preset algorithm includes: Calculate the KNN distance matrix based on the supplemented working data sequences of each device, and determine the K nearest neighbor devices of each missing data bit based on the KNN distance matrix; Interpolate each missing data bit based on the supplemented working data sequences of the K nearest neighbor devices of each missing data bit.

5. The device collaborative scheduling method based on industrial Internet of Things according to claim 1, wherein The performing task scheduling on each device based on the working states of each device includes: Preset a scheduling model, the input of the scheduling model is the working states of each device, and the output of the scheduling model is the scheduling strategy of each device; Perform task scheduling on each device based on the scheduling model.

6. An equipment collaborative scheduling device based on the industrial Internet of Things, characterized in that, Including a management platform, a sensing network platform, and an object platform that are communicatively connected in sequence. The object platform is used to collect and store the working data sequences of various types of each device. The sensing network platform is used to transmit the working data sequences of various types of each device to the management platform. The management platform includes: A data acquisition module, which is used to obtain the working data sequences of various types of each device; A data interpolation module, configured to determine a plurality of target sequences based on the working data sequences of the same category of each device and perform interpolation on each target sequence, where the target sequence is a working data sequence lacking a plurality of data; A working state determination module, configured to determine the working state of each device based on the interpolated working data sequences of each device; A task scheduling module, configured to perform task scheduling on each device based on the working state of each device; The data interpolation module is further configured to determine a plurality of target sequences from the working data sequences of the same category of each device, where each target sequence is a data sequence including missing data bits; for any missing data bit of any target sequence, determine a supplementary sequence of the missing data bit from the other working data sequences except the target sequence, and supplement the missing data bit based on the supplementary sequence, where the supplementary sequence corresponds to the position of the missing data bit and has data; perform interpolation on each target sequence based on the supplemented working data sequences of each device according to a preset algorithm; The data interpolation module is further configured to calculate a difference factor between each supplementary sequence and the missing data bit; use the supplementary sequence with the smallest difference factor as the matching sequence of the missing data bit; and use the data corresponding to the position of the missing data bit in the matching sequence as the supplementary data of the missing data bit.

7. An equipment collaborative scheduling device based on industrial Internet of Things, characterized in that, Comprising: At least one processor; And a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the device collaborative scheduling method based on industrial Internet of Things according to any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the device collaborative scheduling method based on industrial Internet of Things according to any one of claims 1 to 5.

Images