An automated control system based on cloud printing platform

Abstract

The invention discloses an automatic control system based on a cloud printing platform, and relates to the technical field of workload regulation of the cloud printing platform. The method comprises the following steps: obtaining the input workload and the output workload of the cloud printing platform according to a set frequency, respectively, to obtain an input workload curve and an output workload curve; setting a normal workload interval of the input end and a normal workload interval of the output end; obtaining an abnormal workload curve of the input end based on the normal workload interval of the input end and the workload curve of the input end; the workload regulation method of the cloud printing platform and the cloud printing platform, by analyzing the probability of the workload automatically recovering within a specified time under the conditions of other electrical parameters and environmental data of each workload fluctuation characteristic and corresponding time, and setting a probability threshold, so that when the predicted probability is greater than the probability threshold, it is judged that the workload can be automatically recovered within the specified time without adjusting the workload of the cloud printing platform, thereby further improving the prediction accuracy.

Description

Technical Field

[0001] The present invention relates to the technical field of cloud printing platform workload regulation, and in particular to an automatic control system based on a cloud printing platform. Background Art

[0002] With the rapid economic development and technological advancement in various regions, cloud printing refers to the integration of printing service provider resources based on the Internet, building a shared printing platform, and providing quality standardized printing services anytime and anywhere to the whole society. The core content of cloud printing is the management platform. Through the role of the cloud printing management platform, the work efficiency of cloud printing can be improved.

[0003] However, at present, we only monitor and analyze the workload fluctuations of the printing platform to determine whether workload adjustment is needed. The reasons for the workload fluctuations of the cloud printing platform may come from the input end or the output end. At the same time, external factors such as printing tasks, frequency, environmental factors, equipment failures, etc. may affect the workload fluctuations. Therefore, only analyzing the workload fluctuations on the printing platform side may lead to certain deviations in the prediction, making the prediction accuracy relatively low. Summary of the invention

[0004] The object of the present invention is to provide an automated control system based on a cloud printing platform to solve at least one of the above-mentioned deficiencies in the prior art.

[0005] In order to achieve the above object, the present invention provides the following technical solution: an automatic control system based on a cloud printing platform, comprising the following steps:

[0006] S1. Obtain the input workload and output workload of the cloud printing platform according to the set frequency, and obtain the input workload curve and the output workload curve, wherein the input end refers to the end of the cloud printing platform connected to the power grid before the transformation, and the output end refers to the end of the cloud printing platform connected to the power grid after the transformation;

[0007] S2. Setting the normal working range of the input end and the normal working range of the output end;

[0008] S3, based on the normal workload interval of the input end and the workload curve of the input end, obtain the abnormal workload curve of the input end, based on the normal workload interval of the output end and the workload curve of the output end, obtain the abnormal workload curve of the output end, wherein the abnormal workload curve of the input end is the portion of the workload curve of the input end that exceeds the normal workload interval of the input end, and the abnormal workload curve of the output end is the portion of the workload curve of the output end that exceeds the normal workload interval of the output end;

[0009] S4, obtaining an abnormal workload curve of the input end and a curve thereof before the first set time length to obtain an input workload characteristic curve, obtaining an abnormal workload curve of the output end and a curve thereof before the first set time length to obtain an output workload characteristic curve;

[0010] S5, setting an input workload deviation threshold and an output workload deviation threshold for a historical input workload characteristic curve and a historical output workload characteristic curve respectively;

[0011] S6. Perform regression analysis based on the corresponding data of the historical input-end workload characteristic curve and the historical output-end workload characteristic curve, respectively, to obtain a plurality of input-end workload abnormality category curves whose errors are less than the input-end workload deviation threshold, and a plurality of output-end workload abnormality category curves whose errors are less than the output-end workload deviation threshold; that is, the error between each input-end workload abnormality category curve and the corresponding input-end workload characteristic curve is within the set deviation threshold, and the error between each output-end workload abnormality category curve and the corresponding output-end workload characteristic curve is within the set deviation threshold;

[0012] S7. Based on the monitoring needs, corresponding workload monitoring sensors are set to monitor the workload of the cloud printing platform and its input and output ends to obtain external influencing factors;

[0013] S8. Analyze the newly acquired input workload curve and output workload curve, the corresponding input workload abnormality category curve and output workload abnormality category curve, and analyze the probability of the input workload or the output workload returning to normal under the corresponding external influencing factors of the input workload abnormality category curve and the output workload abnormality category curve;

[0014] S9. Set a judgment threshold. If the probability that the input workload or the output workload returns to normal within the second set time period is greater than the judgment threshold, there is no need to adjust the workload of the cloud printing platform. Otherwise, adjust the workload of the cloud printing platform.

[0015] Further, the S8 comprises the following steps:

[0016] Based on the error, the input workload curve and the output workload curve are matched with the input workload abnormality category curve and the output workload abnormality category curve;

[0017] Extracting an input-end workload characteristic curve of the input-end workload curve and an output-end workload characteristic curve of the output-end workload curve;

[0018] Calculating the average error between the input-end workload characteristic curve and each input-end workload abnormality category curve, and the average error between the output-end workload characteristic curve and each output-end workload abnormality category curve;

[0019] The input workload anomaly category curve with the smallest average error is matched with the input workload curve, and the output workload anomaly category curve with the smallest average error is matched with the output workload curve;

[0020] Extracting an input-end workload characteristic curve from the input-end workload curve, using the input-end workload curve after the extraction as the input-end workload judgment curve, and extracting an output-end workload curve after the output-end workload characteristic curve from the output-end workload curve to obtain an output-end workload judgment curve;

[0021] According to different input-end workload abnormality category curves, based on the input-end workload judgment curve and its corresponding external influencing factors, and the recovery of the input-end workload within the second set time period, a Bayesian time series analysis model is trained to obtain an input-end workload automatic recovery probability prediction sub-model, which is used to predict the probability of input-end workload recovery within the second set time period based on the input-end workload judgment curve and the external influencing factors;

[0022] According to different output end workload abnormality category curves, based on the output end workload judgment curve and its corresponding external influencing factors, and the recovery of the output end workload within the second set time period, a Bayesian time series analysis model is trained to obtain an output end workload automatic recovery probability prediction sub-model, which is used to predict the probability of output end workload recovery within the second set time period based on the input output end workload judgment curve and the external influencing factors;

[0023] All input-end workload automatic recovery probability prediction sub-models are combined to obtain an input-end workload automatic recovery probability prediction model, and all output-end workload automatic recovery probability prediction sub-models are combined to obtain an output-end workload automatic recovery probability prediction model.

[0024] Furthermore, the S8 further comprises the following steps:

[0025] Inputting the newly acquired input workload curve and output workload curve into the input workload automatic recovery probability prediction model and the output workload automatic recovery probability prediction model respectively;

[0026] The input end workload automatic recovery probability prediction model matches the corresponding input end workload abnormality category curve and the input end workload automatic recovery probability prediction sub-model, and obtains the corresponding input end workload judgment curve;

[0027] The obtained input-end workload judgment curve is input into the matching input-end workload automatic recovery probability prediction sub-model to obtain the probability of input-end workload recovery within the second set time length;

[0028] The output end workload automatic recovery probability prediction model matches the corresponding output end workload abnormality category curve and the output end workload automatic recovery probability prediction sub-model, and obtains the corresponding output end workload judgment curve;

[0029] The obtained output end workload judgment curve is input into the matching output end workload automatic recovery probability prediction sub-model to obtain the probability of output end workload recovery within the second set time length.

[0030] Furthermore, before step S8, the method further includes the following steps:

[0031] The input-end printing task and the output-end printing task of the cloud printing platform are obtained according to the set frequency respectively, and the input-end printing task curve and the output-end printing task curve are obtained;

[0032] Obtain an input-end printing task curve corresponding to the input-end workload characteristic curve time, obtain an input-end printing task characteristic curve, obtain an output-end printing task curve corresponding to the output-end workload characteristic curve time, obtain an output-end printing task characteristic curve, that is, obtain characteristic change curves of input-end printing tasks at the same time of each input-end workload characteristic curve, and characteristic change curves of output-end printing tasks at the same time of each output-end workload characteristic curve;

[0033] Set the input-end printing task deviation threshold and the output-end printing task deviation threshold for the historical input-end printing task characteristic curve and the historical output-end printing task characteristic curve respectively;

[0034] Regression analysis is performed based on the corresponding data of the historical input-end printing task characteristic curve and the historical output-end printing task characteristic curve, and multiple input-end printing task anomaly category curves with errors less than the input-end printing task deviation threshold and multiple output-end printing task anomaly category curves with errors less than the output-end printing task deviation threshold are obtained.

[0035] Furthermore, the S8 further comprises the following steps:

[0036] Matching the input-end printing task curve and the output-end printing task curve based on the error, the input-end printing task abnormality category curve and the output-end printing task abnormality category curve;

[0037] Extracting an input-end printing task characteristic curve of an input-end printing task curve and an output-end printing task characteristic curve of an output-end printing task curve;

[0038] Calculating the average error between the input-end print task characteristic curve and each input-end print task abnormality category curve, and the average error between the output-end print task characteristic curve and each output-end print task abnormality category curve;

[0039] The input-end printing task abnormality category curve with the smallest average error is selected to correspond to the input-end printing task curve, and the output-end printing task abnormality category curve with the smallest average error is selected to correspond to the output-end printing task curve;

[0040] The input-end printing task curve after the input-end printing task characteristic curve is extracted from the input-end printing task curve to obtain the input-end printing task judgment curve, and the output-end printing task curve after the output-end printing task characteristic curve is extracted from the output-end printing task curve to obtain the output-end printing task judgment curve.

[0041] Furthermore, the S8 further comprises the following steps:

[0042] According to the difference between the input-end workload abnormality category curve and the input-end printing task abnormality category curve, based on the input-end workload judgment curve and its corresponding external influencing factors, the input-end printing task judgment curve, and the recovery of the input-end workload within the second set time period, a Bayesian time series analysis model is trained to obtain an input-end workload automatic recovery probability prediction sub-model, which is used to output the probability of input-end workload recovery within the second set time period based on the input input-end workload judgment curve, the external influencing factor prediction, and the input-end printing task judgment curve;

[0043] According to the difference between the output end workload abnormality category curve and the output end printing task abnormality category curve, based on the output end workload judgment curve and its corresponding external influencing factors, the output end printing task judgment curve, and the recovery of the output end workload within the second set time period, a Bayesian time series analysis model is trained to obtain an output end workload automatic recovery probability prediction sub-model, which is used to output the probability of output end workload recovery within the second set time period based on the input output end workload judgment curve, the external influencing factors, and the output end printing task judgment curve;

[0044] All input-end workload automatic recovery probability prediction sub-models are combined to obtain an input-end workload automatic recovery probability prediction model, and all output-end workload automatic recovery probability prediction sub-models are combined to obtain an output-end workload automatic recovery probability prediction model.

[0045] Furthermore, the S8 further comprises the following steps:

[0046] Input the newly acquired input end workload curve and input end printing task curve into the input end workload automatic recovery probability prediction model;

[0047] The input-end workload automatic recovery probability prediction model matches the corresponding input-end workload abnormality category curve, the print task abnormality category curve and the input-end workload automatic recovery probability prediction sub-model, and obtains the corresponding input-end workload judgment curve and the input-end print task judgment curve;

[0048] The obtained input end workload judgment curve and input end printing task judgment curve are input into the matching input end workload automatic recovery probability prediction sub-model to obtain the probability of input end workload recovery within the second set time length;

[0049] The newly acquired output end workload curve and output end printing task curve are input into the output end workload automatic recovery probability prediction model;

[0050] The output end workload automatic recovery probability prediction model matches the corresponding output end workload abnormality category curve, print task abnormality category curve and output end workload automatic recovery probability prediction sub-model, and obtains the corresponding output end workload judgment curve and output end print task judgment curve;

[0051] The obtained output end workload judgment curve and the output end printing task judgment curve are output to the matching output end workload automatic recovery probability prediction sub-model to obtain the probability of output end workload recovery within the second set time length.

[0052] 1. Compared with the prior art, the present invention provides an automatic control system based on a cloud printing platform, which analyzes the fluctuation characteristics of the workload and judges the similarity between the newly acquired workload fluctuation characteristics and the historical workload fluctuation characteristics through errors, so as to facilitate judging whether the workload can be automatically restored within the specified time through the historical workload fluctuation characteristics, so as to judge whether the workload needs to be adjusted. At the same time, by separately analyzing the workload fluctuations at the input and output ends of the cloud printing platform, the accuracy of the analysis is improved.

[0053] 2. Compared with the prior art, the present invention provides an automatic control system based on a cloud printing platform. By analyzing the fluctuation characteristics of each workload and other electrical parameters and environmental data at the corresponding time, the probability of the workload automatically recovering within the specified time is analyzed, and a probability threshold is set. Only when the predicted probability is greater than the probability threshold, it is judged that the workload can be automatically recovered within the specified time without adjusting the workload of the cloud printing platform, thereby further improving the prediction accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0055] Figure 1 A diagram of the method steps provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0056] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings.

[0057] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0058] In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined. In addition, the terms "installed", "connected" and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal connection of two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0059] Example embodiments will be described more fully below with reference to the accompanying drawings, but the example embodiments may be embodied in different forms and should not be construed as limited to the embodiments set forth herein. On the contrary, the purpose of providing these embodiments is to make the present disclosure thorough and complete and to enable those skilled in the art to fully understand the scope of the present disclosure.

[0060] In the absence of conflict, the various embodiments of the present disclosure and the various features therein may be combined with each other.

[0061] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0062] The terms used herein are only used to describe specific embodiments and are not intended to limit the present disclosure. As used herein, the singular forms "a", "an" and "the" are also intended to include the plural forms, unless the context clearly indicates otherwise. It will also be understood that when the terms "comprising" and / or "made of" are used in this specification, the presence of the features, wholes, steps, operations, elements and / or components is specified, but the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or groups thereof is not excluded.

[0063] The embodiments described herein may be described with reference to plan views and / or cross-sectional views by means of idealized schematic diagrams of the present disclosure. Therefore, the example illustrations may be modified according to manufacturing techniques and / or tolerances. Therefore, the embodiments are not limited to the embodiments shown in the accompanying drawings, but include modifications of the configurations formed based on the manufacturing process. Therefore, the regions illustrated in the accompanying drawings have schematic properties, and the shapes of the regions shown in the figures illustrate the specific shapes of the regions of the elements, but are not intended to be limiting.

[0064] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by those of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and the present disclosure, and will not be interpreted as having an idealized or overly formal meaning unless explicitly defined as such herein.

[0065] See also Figure 1 , an automated control system based on a cloud printing platform, comprising the following steps:

[0066] S1. Obtain the input workload and output workload of the cloud printing platform according to the set frequency, and obtain the input workload curve and the output workload curve, wherein the input end refers to the end of the cloud printing platform connected to the power grid before the transformation, and the output end refers to the end of the cloud printing platform connected to the power grid after the transformation;

[0067] S2. Setting the normal working range of the input end and the normal working range of the output end;

[0068] S3, based on the normal workload interval of the input end and the workload curve of the input end, obtain the abnormal workload curve of the input end, based on the normal workload interval of the output end and the workload curve of the output end, obtain the abnormal workload curve of the output end, wherein the abnormal workload curve of the input end is the portion of the workload curve of the input end that exceeds the normal workload interval of the input end, and the abnormal workload curve of the output end is the portion of the workload curve of the output end that exceeds the normal workload interval of the output end;

[0069] S4, obtaining an abnormal workload curve of the input end and a curve thereof before the first set time length to obtain an input workload characteristic curve, obtaining an abnormal workload curve of the output end and a curve thereof before the first set time length to obtain an output workload characteristic curve;

[0070] S5, setting an input workload deviation threshold and an output workload deviation threshold for a historical input workload characteristic curve and a historical output workload characteristic curve respectively;

[0071] S6. Perform regression analysis based on the corresponding data of the historical input-end workload characteristic curve and the historical output-end workload characteristic curve, respectively, to obtain a plurality of input-end workload abnormality category curves whose errors are less than the input-end workload deviation threshold, and a plurality of output-end workload abnormality category curves whose errors are less than the output-end workload deviation threshold; that is, the error between each input-end workload abnormality category curve and the corresponding input-end workload characteristic curve is within the set deviation threshold, and the error between each output-end workload abnormality category curve and the corresponding output-end workload characteristic curve is within the set deviation threshold;

[0072] S7. Based on the monitoring needs, corresponding workload monitoring sensors are set to monitor the workload of the cloud printing platform and its input and output ends to obtain external influencing factors;

[0073] S8, analyzing the newly acquired input workload curve and output workload curve, the corresponding input workload abnormality category curve and output workload abnormality category curve, and analyzing the probability of the input workload or the output workload returning to normal under the corresponding external influencing factors of the input workload abnormality category curve and the output workload abnormality category curve, including the following steps:

[0074] S8.1a, matching the input workload abnormality category curve and the output workload abnormality category curve based on the error, specifically including the following steps:

[0075] S8.1a.1, extracting an input-end workload characteristic curve of the input-end workload curve and an output-end workload characteristic curve of the output-end workload curve;

[0076] S8.1a.2. Calculate the average error between the input workload characteristic curve and each input workload abnormality category curve, and the average error between the output workload characteristic curve and each output workload abnormality category curve;

[0077] S8.1a.3. Take the input workload anomaly category curve with the smallest average error and match it with the input workload curve, and take the output workload anomaly category curve with the smallest average error and match it with the output workload curve;

[0078] S8.2a, extracting the input workload characteristic curve from the input workload curve, using the input workload curve after the extraction as the input workload judgment curve, and extracting the output workload curve after the output workload characteristic curve from the output workload curve to obtain the output workload judgment curve;

[0079] S8.3a. According to the different abnormal category curves of the input workload, based on the input workload judgment curve and its corresponding external influencing factors, and the recovery of the input workload within the second set time period, the Bayesian time series analysis model is trained to obtain the input workload automatic recovery probability prediction sub-model, which is used to predict the probability of input workload recovery within the second set time period based on the input workload judgment curve and the external influencing factors; wherein the Bayesian time series analysis model training process needs to be based on historical data and newly acquired data, using prior probability, observation probability, transfer probability and posterior probability for analysis, calculation and update to improve the accuracy of probability prediction.

[0080] S8.4a. According to the different output end workload abnormality category curves, based on the output end workload judgment curve and its corresponding external influencing factors, and the recovery of the output end workload within the second set time period, the Bayesian time series analysis model is trained to obtain the output end workload automatic recovery probability prediction sub-model, which is used to predict the probability of output end workload recovery within the second set time period based on the input output end workload judgment curve and external influencing factors.

[0081] S8.5a. Combine all input-end workload automatic recovery probability prediction sub-models to obtain an input-end workload automatic recovery probability prediction model, and combine all output-end workload automatic recovery probability prediction sub-models to obtain an output-end workload automatic recovery probability prediction model.

[0082] S8.6a, inputting the newly acquired input workload curve and output workload curve into the input workload automatic recovery probability prediction model and the output workload automatic recovery probability prediction model respectively;

[0083] S8.7a, the input end workload automatic recovery probability prediction model matches the corresponding input end workload abnormality category curve and the input end workload automatic recovery probability prediction sub-model through S8.1a, and obtains the corresponding input end workload judgment curve;

[0084] S8.8a, input the obtained input end workload judgment curve into the matching input end workload automatic recovery probability prediction sub-model, and obtain the probability of input end workload recovery within the second set time length;

[0085] S8.9a, the output end workload automatic recovery probability prediction model matches the corresponding output end workload abnormality category curve and the output end workload automatic recovery probability prediction sub-model, and obtains the corresponding output end workload judgment curve;

[0086] S8.10a. Input the obtained output end workload judgment curve into the matching output end workload automatic recovery probability prediction sub-model to obtain the probability of output end workload recovery within the second set time length.

[0087] S9. Set a judgment threshold. If the probability that the input workload or the output workload returns to normal within the second set time period is greater than the judgment threshold, there is no need to adjust the workload of the cloud printing platform. Otherwise, adjust the workload of the cloud printing platform.

[0088] In one embodiment, before step S8, the following steps are also included:

[0089] A1. Obtain the input-end printing task and the output-end printing task of the cloud printing platform according to the set frequency, and obtain the input-end printing task curve and the output-end printing task curve.

[0090] A2. Obtain the input-end printing task curve corresponding to the input-end workload characteristic curve time, obtain the input-end printing task characteristic curve, obtain the output-end printing task curve corresponding to the output-end workload characteristic curve time, obtain the output-end printing task characteristic curve, that is, obtain the characteristic change curve of the input-end printing task at the same time of each input-end workload characteristic curve, and obtain the characteristic change curve of the output-end printing task at the same time of each output-end workload characteristic curve.

[0091] A3. Set an input-end printing task deviation threshold and an output-end printing task deviation threshold for the historical input-end printing task characteristic curve and the historical output-end printing task characteristic curve, respectively.

[0092] A4. Based on the corresponding data of the historical input-end printing task characteristic curve and the historical output-end printing task characteristic curve, regression analysis is performed to obtain multiple input-end printing task abnormality category curves whose errors are less than the input-end printing task deviation threshold, and multiple output-end printing task abnormality category curves whose errors are less than the output-end printing task deviation threshold.

[0093] In this embodiment, S8 further includes the following steps:

[0094] S8.1b, based on the error as the input workload curve and the output workload curve, matching the input workload abnormality category curve and the output workload abnormality category curve, and based on the error as the input print task curve and the output print task curve, matching the input print task abnormality category curve and the output print task abnormality category curve, specifically including the following steps:

[0095] S8.1b.1. Extract the input-end workload characteristic curve of the input-end workload curve, and the output-end workload characteristic curve of the output-end workload curve; calculate the average error between the input-end workload characteristic curve and each input-end workload abnormality category curve, and the average error between the output-end workload characteristic curve and each output-end workload abnormality category curve; extract the input-end printing task characteristic curve of the input-end printing task curve, and the output-end printing task characteristic curve of the output-end printing task curve.

[0096] S8.1b.2. Calculate the average error between the input-end print task characteristic curve and each input-end print task abnormality category curve, and the average error between the output-end print task characteristic curve and each output-end print task abnormality category curve;

[0097] S8.1b.3. Take the input-end workload anomaly category curve with the smallest average error to match the input-end workload curve, and take the output-end workload anomaly category curve with the smallest average error to match the output-end workload curve; take the input-end printing task anomaly category curve with the smallest average error to match the input-end printing task curve, and take the output-end printing task anomaly category curve with the smallest average error to match the output-end printing task curve.

[0098] S8.2b. Extract the input workload characteristic curve from the input workload curve, and use the input workload curve after the extraction as the input workload judgment curve, wherein the input workload judgment curve extracts the change of the input workload characteristics from the input workload characteristic curve as the judgment standard, i.e., as the curve independent variable, thereby obtaining the input workload judgment curve; extract the output workload curve after the output workload characteristic curve from the output workload curve to obtain the output workload judgment curve, wherein the output workload judgment curve uses the change of the adjacent output workload characteristics in the output workload characteristic curve as the judgment standard, i.e., as the curve independent variable, thereby obtaining the output workload judgment curve; extract the input printing task curve after the input printing task characteristic curve from the input printing task curve to obtain the input printing task judgment curve; extract the output printing task curve after the output printing task characteristic curve from the output printing task curve to obtain the output printing task judgment curve.

[0099] S8.3b, according to the difference between the input-end workload abnormality category curve and the input-end printing task abnormality category curve, based on the input-end workload judgment curve and its corresponding external influencing factor, the input-end printing task judgment curve, and the recovery of the input-end workload within the second set time, train the Bayesian time series analysis model to obtain the input-end workload automatic recovery probability prediction sub-model, which is used to output the probability of input-end workload recovery within the second set time based on the input input-end workload judgment curve, the external influencing factor prediction, and the input-end printing task judgment curve;

[0100] S8.4b, according to the difference between the output end workload abnormality category curve and the output end printing task abnormality category curve, based on the output end workload judgment curve and its corresponding external influencing factors, the output end printing task judgment curve, and the recovery of the output end workload within the second set time, train the Bayesian time series analysis model to obtain the output end workload automatic recovery probability prediction sub-model, which is used to output the probability of output end workload recovery within the second set time based on the input output end workload judgment curve, external influencing factors, and output end printing task judgment curve;

[0101] S8.5b. Combine all input-end workload automatic recovery probability prediction sub-models to obtain an input-end workload automatic recovery probability prediction model, and combine all output-end workload automatic recovery probability prediction sub-models to obtain an output-end workload automatic recovery probability prediction model.

[0102] S8.6b. Input the newly acquired input end workload curve and input end printing task curve into the input end workload automatic recovery probability prediction model.

[0103] S8.7b, the input-end workload automatic recovery probability prediction model matches the corresponding input-end workload abnormality category curve, the print task abnormality category curve and the input-end workload automatic recovery probability prediction sub-model through S8.1b, and obtains the corresponding input-end workload judgment curve and the input-end print task judgment curve;

[0104] S8.8b, input the obtained input end workload judgment curve and input end printing task judgment curve into the matching input end workload automatic recovery probability prediction sub-model, and obtain the probability of input end workload recovery within the second set time length;

[0105] S8.9b, input the newly acquired output end workload curve and output end printing task curve into the output end workload automatic recovery probability prediction model;

[0106] S8.10b, the output end workload automatic recovery probability prediction model is matched with the corresponding output end workload abnormality category curve, the print task abnormality category curve and the output end workload automatic recovery probability prediction sub-model, and the corresponding output end workload judgment curve and the output end print task judgment curve are obtained;

[0107] S8.11b, output the obtained output end workload judgment curve and the output end printing task judgment curve to the matching output end workload automatic recovery probability prediction sub-model, and obtain the probability of output end workload recovery within the second set time length.

[0108] The above description is only by way of illustration of certain exemplary embodiments of the present invention. It is undoubted that those skilled in the art can modify the described embodiments in various ways without departing from the spirit and scope of the present invention. Therefore, the above drawings and descriptions are illustrative in nature and should not be construed as limiting the scope of protection of the claims of the present invention.

Claims

1. An automated control system based on a cloud printing platform, characterized in that: The following steps are involved: S1. Obtain the input workload and output workload of the cloud printing platform according to the set frequency, and obtain the input workload curve and the output workload curve; S2. Setting the normal working range of the input end and the normal working range of the output end; S3, obtaining an abnormal workload curve of the input end based on the normal workload interval of the input end and the workload curve of the input end, and obtaining an abnormal workload curve of the output end based on the normal workload interval of the output end and the workload curve of the output end; S4, obtaining an abnormal workload curve of the input end and a curve thereof before the first set time length to obtain an input workload characteristic curve, obtaining an abnormal workload curve of the output end and a curve thereof before the first set time length to obtain an output workload characteristic curve; S5, setting an input workload deviation threshold and an output workload deviation threshold for a historical input workload characteristic curve and a historical output workload characteristic curve respectively; S6. Perform regression analysis based on the corresponding data of the historical input workload characteristic curve and the historical output workload characteristic curve, and obtain a plurality of input workload abnormality category curves whose errors are less than the input workload deviation threshold, and a plurality of output workload abnormality category curves whose errors are less than the output workload deviation threshold; S7. Based on the monitoring needs, corresponding workload monitoring sensors are set to monitor the workload of the cloud printing platform and its input and output ends to obtain external influencing factors; S8. Analyze the newly acquired input workload curve and output workload curve, the corresponding input workload abnormality category curve and output workload abnormality category curve, and analyze the probability of the input workload or the output workload returning to normal under the corresponding external influencing factors of the input workload abnormality category curve and the output workload abnormality category curve; S9. Set a judgment threshold. If the probability that the input workload or the output workload returns to normal within the second set time period is greater than the judgment threshold, there is no need to adjust the workload of the cloud printing platform. Otherwise, adjust the workload of the cloud printing platform.

2. According to claim 1, an automatic control system based on a cloud printing platform is characterized in that: The S8 comprises the following steps: Based on the error, the input workload curve and the output workload curve are matched with the input workload abnormality category curve and the output workload abnormality category curve; Extracting an input-end workload characteristic curve from the input-end workload curve, using the input-end workload curve after the extraction as the input-end workload judgment curve, and extracting an output-end workload curve after the output-end workload characteristic curve from the output-end workload curve to obtain an output-end workload judgment curve; According to different input-end workload abnormality category curves, based on the input-end workload judgment curve and its corresponding external influencing factors, and the recovery of the input-end workload within the second set time period, a Bayesian time series analysis model is trained to obtain an input-end workload automatic recovery probability prediction sub-model, which is used to predict the probability of input-end workload recovery within the second set time period based on the input-end workload judgment curve and the external influencing factors; According to different output end workload abnormality category curves, based on the output end workload judgment curve and its corresponding external influencing factors, and the recovery of the output end workload within the second set time period, a Bayesian time series analysis model is trained to obtain an output end workload automatic recovery probability prediction sub-model, which is used to predict the probability of output end workload recovery within the second set time period based on the input output end workload judgment curve and the external influencing factors; All input-end workload automatic recovery probability prediction sub-models are combined to obtain an input-end workload automatic recovery probability prediction model, and all output-end workload automatic recovery probability prediction sub-models are combined to obtain an output-end workload automatic recovery probability prediction model.

3. According to claim 2, an automatic control system based on a cloud printing platform is characterized in that: The S8 further comprises the following steps: Inputting the newly acquired input workload curve and output workload curve into the input workload automatic recovery probability prediction model and the output workload automatic recovery probability prediction model respectively; The input end workload automatic recovery probability prediction model matches the corresponding input end workload abnormality category curve and the input end workload automatic recovery probability prediction sub-model, and obtains the corresponding input end workload judgment curve; The obtained input-end workload judgment curve is input into the matching input-end workload automatic recovery probability prediction sub-model to obtain the probability of input-end workload recovery within the second set time length; The output end workload automatic recovery probability prediction model matches the corresponding output end workload abnormality category curve and the output end workload automatic recovery probability prediction sub-model, and obtains the corresponding output end workload judgment curve; The obtained output end workload judgment curve is input into the matching output end workload automatic recovery probability prediction sub-model to obtain the probability of output end workload recovery within the second set time length.

4. The automatic control system based on the cloud printing platform according to claim 3 is characterized in that: Before the step S8, the following steps are also included: The input-end printing task and the output-end printing task of the cloud printing platform are obtained according to the set frequency respectively, and the input-end printing task curve and the output-end printing task curve are obtained; Obtaining an input-end printing task curve corresponding to the input-end workload characteristic curve time, obtaining an input-end printing task characteristic curve, obtaining an output-end printing task curve corresponding to the output-end workload characteristic curve time, obtaining an output-end printing task characteristic curve; Set the input-end printing task deviation threshold and the output-end printing task deviation threshold for the historical input-end printing task characteristic curve and the historical output-end printing task characteristic curve respectively; Regression analysis is performed based on the corresponding data of the historical input-end printing task characteristic curve and the historical output-end printing task characteristic curve, and multiple input-end printing task anomaly category curves with errors less than the input-end printing task deviation threshold and multiple output-end printing task anomaly category curves with errors less than the output-end printing task deviation threshold are obtained.

5. The automatic control system based on the cloud printing platform according to claim 4 is characterized in that: The S8 further comprises the following steps: Matching the input-end printing task curve and the output-end printing task curve based on the error, the input-end printing task abnormality category curve and the output-end printing task abnormality category curve; The input-end printing task curve after the input-end printing task characteristic curve is extracted from the input-end printing task curve to obtain the input-end printing task judgment curve, and the output-end printing task curve after the output-end printing task characteristic curve is extracted from the output-end printing task curve to obtain the output-end printing task judgment curve.

6. The automatic control system based on the cloud printing platform according to claim 5, characterized in that: The S8 further comprises the following steps: According to the difference between the input-end workload abnormality category curve and the input-end printing task abnormality category curve, based on the input-end workload judgment curve and its corresponding external influencing factors, the input-end printing task judgment curve, and the recovery of the input-end workload within the second set time period, a Bayesian time series analysis model is trained to obtain an input-end workload automatic recovery probability prediction sub-model, which is used to output the probability of input-end workload recovery within the second set time period based on the input input-end workload judgment curve, the external influencing factor prediction, and the input-end printing task judgment curve; According to the difference between the output end workload abnormality category curve and the output end printing task abnormality category curve, based on the output end workload judgment curve and its corresponding external influencing factors, the output end printing task judgment curve, and the recovery of the output end workload within the second set time period, a Bayesian time series analysis model is trained to obtain an output end workload automatic recovery probability prediction sub-model, which is used to output the probability of output end workload recovery within the second set time period based on the input output end workload judgment curve, the external influencing factors, and the output end printing task judgment curve; All input-end workload automatic recovery probability prediction sub-models are combined to obtain an input-end workload automatic recovery probability prediction model, and all output-end workload automatic recovery probability prediction sub-models are combined to obtain an output-end workload automatic recovery probability prediction model.

7. The automatic control system based on the cloud printing platform according to claim 6 is characterized in that: The S8 further comprises the following steps: Input the newly acquired input end workload curve and input end printing task curve into the input end workload automatic recovery probability prediction model; The input-end workload automatic recovery probability prediction model matches the corresponding input-end workload abnormality category curve, the print task abnormality category curve and the input-end workload automatic recovery probability prediction sub-model, and obtains the corresponding input-end workload judgment curve and the input-end print task judgment curve; The obtained input end workload judgment curve and input end printing task judgment curve are input into the matching input end workload automatic recovery probability prediction sub-model to obtain the probability of input end workload recovery within the second set time length; The newly acquired output end workload curve and output end printing task curve are input into the output end workload automatic recovery probability prediction model; The output end workload automatic recovery probability prediction model matches the corresponding output end workload abnormality category curve, print task abnormality category curve and output end workload automatic recovery probability prediction sub-model, and obtains the corresponding output end workload judgment curve and output end print task judgment curve; The obtained output end workload judgment curve and the output end printing task judgment curve are output to the matching output end workload automatic recovery probability prediction sub-model to obtain the probability of output end workload recovery within the second set time length.

Images