CN110597637A - System resource scheduling method, device and readable storage medium - Google Patents
System resource scheduling method, device and readable storage medium Download PDFInfo
- Publication number
- CN110597637A CN110597637A CN201910885587.1A CN201910885587A CN110597637A CN 110597637 A CN110597637 A CN 110597637A CN 201910885587 A CN201910885587 A CN 201910885587A CN 110597637 A CN110597637 A CN 110597637A
- Authority
- CN
- China
- Prior art keywords
- preset
- system resource
- verification
- data
- prediction result
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/50—Indexing scheme relating to G06F9/50
- G06F2209/5019—Workload prediction
Abstract
The invention discloses a system resource scheduling method, a device and a readable storage medium, wherein the system resource scheduling method comprises the following steps: and step S11: acquiring system resource data before the current time point; s12, inputting the system resource data into a predictor for predicting overload operation to obtain a first prediction result; and step S13: and when the first prediction result is overload operation, allocating preset system resources. The technical problems of blind system resource scheduling and unreasonable allocation are solved.
Description
Technical Field
The present invention relates to the field of game processing technologies, and in particular, to a method, device, and readable storage medium for scheduling system resources.
Background
With the development of network technology, games have become one of the essential entertainment modes in people's life, but in a game scene, a pause phenomenon often occurs, which affects user experience, in the prior art, system resources are generally scheduled by means of touch events to solve the pause phenomenon, but the method causes the system resources to be always in a high negative state, which causes great waste to the use of the system resources and brings pause risks to other applications, i.e., the method cannot perform accurate scheduling and reasonable allocation of the system resources, so that the game applications always occupy most of the system resources, further, game terminals are heated, the system power consumption is too high, and therefore, the technical problems of blind scheduling and unreasonable allocation of the system resources exist in the prior art.
Disclosure of Invention
The invention mainly aims to provide a system resource scheduling method, system resource scheduling equipment and a readable storage medium, and aims to solve the technical problems that system resource scheduling is blind and unreasonable in distribution in the prior art.
In order to achieve the above object, an embodiment of the present invention provides a system resource scheduling method, where the system resource scheduling method is applied to a system resource scheduling device, and the system resource scheduling method includes the following steps:
s11: acquiring system resource data before the current time point;
s12: inputting the system resource data into a preset predictor to obtain a first prediction result;
s13: and when the first prediction result is overload operation, allocating preset system resources.
Optionally, the step of S11 is preceded by:
acquiring a preset basic model and preset training data corresponding to the predictor;
and inputting the preset training data into the preset basic model, and training the preset basic model to obtain a verification model corresponding to the preset basic model.
Optionally, the preset training data comprises training input data and training result data, the preset base model comprises a plurality of initial weight ratios,
the step of inputting the preset training data into the preset basic model, training the preset basic model, and obtaining a verification model corresponding to the preset basic model includes:
inputting the training input data into the preset basic model to obtain initial prediction result data;
calculating the similarity of the initial prediction result data and the training result data, and setting the preset basic model as a verification model when the similarity is greater than or equal to a preset similarity;
and/or when the similarity is smaller than the preset similarity, adjusting the multiple initial weight ratios, and retraining the preset basic model to obtain the verification model.
Optionally, the training input data comprises a plurality of training data sets, wherein each of the training data sets comprises one or more of a Cpu resource proportion, an Io resource proportion, and a Memory resource proportion, the plurality of initial weight proportions comprises one or more of a Cpu weight proportion, an Io weight proportion, and a Memory weight proportion,
the step of inputting the training input data into the preset basic model to obtain initial prediction result data comprises:
inputting the training input data into the preset basic model to obtain a first stuck value corresponding to the Cpu resource ratio, a second stuck value corresponding to the Io resource ratio and a third stuck value corresponding to the Memory resource ratio;
calculating a composite stuck value based on the first stuck value, and/or the second stuck value, and/or the third stuck value and the Cpu weight ratio, and/or the Io weight ratio, and/or the Memory weight ratio, wherein one of the training data sets corresponds to one of the composite stuck values;
and comparing the comprehensive stuck value with a preset standard stuck value to obtain initial prediction result data.
Optionally, the step of inputting the preset training data into the preset basic model, training the preset basic model, and obtaining a verification model corresponding to the preset basic model includes:
acquiring preset verification data, wherein the preset verification data comprise verification input data and standard verification results, and each verification input data corresponds to one standard verification result;
inputting the verification input data into the verification model to obtain an actual verification result;
comparing the actual verification result with the standard verification result to obtain a verification error rate;
comparing the verification error rate with a preset error threshold value, and taking the verification model as the predictor when the verification error rate is smaller than or equal to the preset error threshold value;
and/or retraining the preset basic model when the verification error rate is larger than the preset error threshold value.
Optionally, the step S11 includes: the system resource data comprises system resource occupation ratios at a plurality of time points before the current time point, and each time point corresponds to a system resource occupation ratio,
the step of S12 includes:
inputting the system resource data into the predictor, and obtaining 1 or more comprehensive system resource ratios corresponding to the 1 or more time points;
comparing the 1 or more comprehensive system resource occupation ratios with a preset occupation ratio threshold value, and acquiring the time point quantity corresponding to a part of system resource occupation ratio when the part of system resource occupation ratio is larger than or equal to the preset occupation ratio threshold value in the 1 or more comprehensive system resource occupation ratios;
calculating the quantity ratio of the time point quantity relative to the 1 or more time point quantities, and when the quantity ratio is greater than a preset quantity ratio, the first prediction result is overload operation;
and/or when the number proportion is less than or equal to the preset number proportion, the first prediction result is normal.
Optionally, the step S13 is followed by:
acquiring a second prediction result of a next time point of the current time point, and comparing the first prediction result with the second prediction result;
when the second stuck degree of the second prediction result is larger than the first stuck degree of the first prediction result, scheduling the preset system resource;
and/or releasing the preset system resource when the second clamping degree of the second prediction result is less than or equal to the first clamping degree of the first prediction result.
Optionally, the step of S11 includes:
when a system resource scheduling request is received, extracting a current time point in the system resource scheduling request;
and acquiring system resource data in a preset time length before the current time point through a preset monitor.
Optionally, the system resource scheduling method further includes:
s21: acquiring a current running state;
s22: judging whether the current running state meets a preset condition or not;
s23: if yes, scheduling the system resources according to a preset strategy.
Optionally, the step of S21 includes:
obtaining system resource data, the system resource data comprising one or more of a Cpu resource, an Io resource, and a Memory resource.
Optionally, the step of S22 includes:
inputting the system resource data into a preset predictor to obtain a first prediction result;
and when the first prediction result is overload operation, judging that a preset condition is met.
The invention also provides a system resource scheduling device, which is applied to a system resource scheduling device, and comprises:
the first acquisition module is used for acquiring system resource data before the current time point;
the prediction module is used for inputting the system resource data into a preset predictor to obtain a first prediction result;
and the first scheduling module is used for allocating preset system resources when the first prediction result is overload operation.
Optionally, the system resource scheduling apparatus further includes:
the second acquisition module is used for acquiring a preset basic model and preset training data corresponding to the predictor;
and the training module is used for inputting the preset training data into the preset basic model, training the preset basic model and obtaining a verification model corresponding to the preset basic model.
Optionally, the training module comprises:
the first input unit is used for inputting the training input data into the preset basic model to obtain initial prediction result data;
the first calculation unit is used for calculating the similarity between the initial prediction result data and the training result data, and when the similarity is greater than or equal to a preset similarity, the preset basic model is set as a verification model;
and the adjusting unit is used for adjusting the plurality of initial weight ratios and retraining the preset basic model to obtain the verification model when the similarity is smaller than the preset similarity.
Optionally, the input unit includes:
an input subunit, configured to input the training input data into the preset base model, so as to obtain a plurality of first stuck values corresponding to the Cpu resource occupation ratio, a plurality of second stuck values corresponding to the Io resource occupation ratio, and a plurality of third stuck values corresponding to the Memory resource occupation ratio;
a calculating subunit, configured to calculate a composite stuck value based on the first stuck value, and/or the second stuck value, and/or the third stuck value and the Cpu weight ratio, and/or the Io weight ratio, and/or the Memory weight ratio, wherein a training data set corresponds to a composite stuck value;
and the comparison subunit is used for comparing the comprehensive stuck value with a preset standard stuck value to obtain initial prediction result data.
Optionally, the system resource scheduling apparatus further includes:
a third obtaining module, configured to obtain preset verification data, where the preset verification data includes verification input data and standard verification results, and each verification input data corresponds to one standard verification result;
the input module is used for inputting the verification input data into the verification model to obtain an actual verification result;
the first comparison module is used for comparing the actual verification result with the standard verification result to obtain a verification error rate;
the second comparison module is used for comparing the verification error rate with a preset error threshold value, and when the verification error rate is smaller than or equal to the preset error threshold value, the verification model is used as the predictor;
and the retraining module is used for retraining the preset basic model when the verification error rate is larger than the preset error threshold value and/or when the verification error rate is larger than the preset error threshold value.
Optionally, the prediction module comprises:
a second input unit, configured to input the system resource data into the predictor, and obtain 1 or more comprehensive system resource ratios corresponding to the 1 or more time points;
a comparing unit, configured to compare the 1 or more comprehensive system resource occupation ratios with a preset occupation ratio threshold, and when a part of the system resource occupation ratio in the 1 or more comprehensive system resource occupation ratios is greater than or equal to the preset occupation ratio threshold, obtain a number of time points corresponding to the part of the system resource occupation ratio;
a second calculating unit, configured to calculate a quantity ratio of the number of time points to the 1 or more number of time points, where when the quantity ratio is greater than a preset quantity ratio, the first prediction result is an operation overload;
a second comparison unit, configured to determine that the first prediction result is normal if the number ratio is smaller than or equal to the preset number ratio.
Optionally, the system resource scheduling apparatus further includes:
a third comparison module, configured to obtain a second prediction result at a time point next to the current time point, and compare the first prediction result with the second prediction result;
the scheduling module is used for scheduling the preset system resource when the second stuck degree of the second prediction result is greater than the first stuck degree of the first prediction result;
and the releasing module is used for releasing the preset system resource when the second clamping degree of the second prediction result is smaller than or equal to the first clamping degree of the first prediction result.
Optionally, the first input module comprises:
the extracting unit is used for extracting the current time point in the system resource scheduling request when the system resource scheduling request is received;
and the collecting unit is used for collecting the system resource data in the preset time length before the current time point through a preset monitor.
Optionally, the system resource scheduling apparatus further includes:
a fourth obtaining module, configured to obtain the current operating state;
the judging module is used for judging whether the current running state meets a preset condition or not;
and the second scheduling module is used for scheduling the system resources according to a preset strategy if the system resources are the same as the preset strategy.
Optionally, the fourth obtaining module includes:
an obtaining unit, configured to obtain system resource data, where the system resource data includes one or more of a Cpu resource, an Io resource, and a Memory resource.
Optionally, the determining module includes:
the prediction unit is used for inputting the system resource data into a preset predictor to obtain a first prediction result;
and the judging unit is used for judging that a preset condition is met when the first prediction result is running overload.
The invention also provides a system resource scheduling device, which comprises: a memory, a processor and a program of the system resource scheduling method stored on the memory and executable on the processor, the program of the system resource scheduling method when executed by the processor being capable of implementing the steps of the system resource scheduling method as described above.
The invention also provides a readable storage medium, which stores a program for implementing the system resource scheduling method, and when the program of the system resource scheduling method is executed by a processor, the steps of the system resource scheduling method are implemented.
The method comprises the steps of obtaining system resource data before the current time point, inputting the system resource data into a preset predictor to obtain a first prediction result, and distributing preset system resources when the first prediction result is overload operation. That is, this application is through in the system resource data input predictor that will acquire, and then based on first calorie dun prediction result, realize accurate dispatch and the rational distribution to predetermineeing system resource, also, this application has realized that the game terminal moves overloaded accurate prediction, and then has realized accurate dispatch and the rational distribution to system resource, has solved the blind and unreasonable technical problem of distribution of system resource dispatch among the prior art.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious for those skilled in the art that other drawings can be obtained according to these drawings without inventive exercise.
FIG. 1 is a flowchart illustrating a method for scheduling system resources according to a first embodiment of the present invention;
FIG. 2 is a flowchart illustrating a second embodiment of a method for scheduling system resources according to the present invention;
fig. 3 is a schematic device structure diagram of a hardware operating environment related to the method according to the embodiment of the present invention.
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The invention provides a system resource scheduling method, which is applied to system resource scheduling equipment, and in a first embodiment of the system resource scheduling method, referring to fig. 1, the system resource scheduling method comprises the following steps:
step S11, obtaining system resource data before the current time point;
in this embodiment, it should be noted that the current time point refers to a time point at which overload prediction of terminal operation needs to be performed, and the system resource data includes a Cpu resource usage duty ratio, an Io resource usage duty ratio, and a Memory resource usage duty ratio, where the Cpu resource usage duty ratio refers to a duty ratio of Cpu resources occupied by the game application to total Cpu resources of the game terminal, the Io resource usage duty ratio refers to a duty ratio of Io resources occupied by the game application to total Io resources of the game terminal, and the Memory resource usage duty ratio refers to a duty ratio of Memory resources occupied by the game application to total Memory resources of the game terminal.
The method includes the steps of obtaining system resource data before a current time point, specifically, obtaining system resource data within a preset time length before 9: 30, assuming that the current time point is 9: 30, wherein the preset time length can be determined by a user or a system default time length is used.
Wherein the step of acquiring the system resource data before the current time point comprises:
step S111, when a system resource scheduling request is received, extracting a current time point in the system resource scheduling request;
in this embodiment, it should be noted that the system resource scheduling request may be sent by a user or triggered when the user opens an application, and the system resource scheduling request includes a current time point, and the current time point may be sealed in a timestamp, and when the system resource scheduling request is received, the current time point in the system resource scheduling request is extracted, specifically, when the system resource scheduling request is received, the current time point in the timestamp of the system resource scheduling request is extracted by a time point extractor.
And step S112, acquiring and collecting system resource data in a preset time length before the current time point through a preset monitor.
In this embodiment, it should be noted that the preset monitor is a monitor preset in a system and capable of collecting system resource data, the preset duration is a duration preset by a user or a default duration of the system, and the preset duration includes a collection duration and a collection frequency, where the collection duration is a time interval for collecting the system resource data, and a time interval between the preset duration and the current time point may be set by the user, for example, the time interval may be set to 1s, 2s, or 3s, and the like.
Step S12, inputting the system resource data into a preset predictor to obtain a first prediction result;
in this embodiment, it should be noted that the predictor is an optimal model obtained by training a preset base model based on deep learning, the first prediction result includes a quantization result and a descriptive result, the quantization result includes specific quantities such as a stuck degree and a stuck value, for example, the stuck degree is 20%, the specific quantity is a specific quantity, and the descriptive result includes descriptive words such as overload operation and normal operation, where the overload operation means that the current idle system resource cannot meet the requirement for keeping the game application running, and the system resource data corresponds to the preset duration, that is, the system resource data is obtained within the preset duration.
Inputting the system resource data into a preset predictor to obtain a first prediction result, specifically, inputting the system resource data corresponding to the preset duration into the preset predictor to obtain the first prediction result, for example, assuming that the collection duration is 5s, if the collection times is 3, the system resource data is the system resource data collected in the first 15s of the time point to be predicted.
Wherein the step S11 includes: the current time point is preceded by 1 or more time points, the system resource data includes system resource proportions, and each of the time points corresponds to a system resource proportion,
the step of S12 includes:
step S121, inputting the system resource data into the predictor, and obtaining 1 or more comprehensive system resource ratios corresponding to the 1 or more time points;
in this embodiment, it should be noted that the system resource ratio includes one or more of a Cpu resource ratio, an Io resource ratio, and a Memory resource ratio, each time point corresponds to a system resource ratio, the Cpu resource ratio corresponds to a Cpu weight ratio, the Io resource ratio corresponds to an Io weight ratio, the Memory resource ratio corresponds to a Memory weight ratio, and the predictor includes the Cpu weight ratio, the Io resource ratio, and the Memory weight ratio.
Inputting the system resource data into the predictor, obtaining 1 or more comprehensive system resource occupation ratios corresponding to the 1 or more time points, specifically, inputting the Cpu resource occupation ratio, the Io resource occupation ratio and the Memory resource occupation ratio corresponding to each time point into a preset predictor, and calculating the comprehensive system resource occupation ratio at each time point through the preset predictor, that is, calculating the sum of the product of the Cpu resource occupation ratio and the Cpu weight occupation ratio, the product of the Io resource occupation ratio and the Io weight occupation ratio, and the sum of the product of the Memory resource occupation ratio and the Memory weight occupation ratio, for example, assuming that the Cpu resource occupation ratio, the Io resource occupation ratio and the Memory resource occupation ratio are A, B, C respectively, and the Cpu weight occupation ratio, the Io weight occupation ratio and the Memory weight occupation ratio are X, Y, Z respectively, the comprehensive system resource occupation ratio is (AX + BY + CZ).
Step S122, comparing the 1 or more comprehensive system resource occupation ratios with a preset occupation ratio threshold value, and when a part of the 1 or more comprehensive system resource occupation ratios is larger than or equal to the preset occupation ratio threshold value, acquiring the number of time points corresponding to the part of the system resource occupation ratios;
in this embodiment, it should be noted that the preset occupation ratio threshold is a measure for measuring whether the game terminal will be overloaded during operation, and when the comprehensive system resource occupation ratio is greater than the preset occupation ratio threshold, the game terminal will be overloaded during operation, and the time point quantity refers to the quantity of the time point quantities corresponding to the partial system resource occupation ratios.
Comparing the 1 or more comprehensive system resource occupation ratios with a preset occupation ratio threshold value, when a part of the system resource occupation ratio in the 1 or more comprehensive system resource occupation ratios is larger than or equal to the preset occupation ratio threshold value, acquiring the number of time points corresponding to the part of the system resource occupation ratio, specifically, comparing the comprehensive system resource occupation ratio at each time point with the preset occupation ratio threshold value, and counting the number of the part of the system resource occupation ratio larger than the preset occupation ratio threshold value in the plurality of comprehensive system resource occupation ratios, that is, counting the number of the time points corresponding to the part of the system resource occupation ratio.
Step S123, calculating the quantity ratio of the time point quantity relative to the 1 or more time point quantities, and when the quantity ratio is greater than the preset quantity ratio, the first prediction result is running overload;
in this embodiment, a number ratio of the number of time points to the 1 or more number of time points is calculated, and when the number ratio is greater than a preset number ratio, the first prediction result is an operation overload, specifically, a quantity ratio of the quantity of the time points corresponding to the partial system resource ratio in all the time points is calculated, when the quantity ratio is greater than a preset quantity ratio, the first prediction result is an overload operation, that is, when the number of time points in the time points reaches the preset number to the number of time points corresponding to the preset number, the first prediction result is an operation overload, for example, assuming that the preset number proportion is 70%, the number of time points is 8, the number of time points is 10, the number proportion is 80%, therefore, the number ratio is greater than a preset number ratio, and the first prediction result is an overload operation.
And step S124, and/or when the number ratio is smaller than or equal to the preset number ratio, the first prediction result is normal.
In this embodiment, and/or when the number ratio is less than or equal to the preset number ratio, the first prediction result is normal, specifically, the number ratio of the number of the time points corresponding to the partial system resource ratio in the number of the time points is calculated, and when the number ratio is less than or equal to the preset number ratio, the first prediction result is normal.
And step S13, when the first prediction result is the running overload, allocating preset system resources.
In this embodiment, it should be noted that the system resources include idle resources and resources occupied by other applications, and when the idle resources cannot meet the system resources required by the game application, the game terminal is overloaded during operation. And when the first prediction result is that the running of the game application is overloaded, allocating preset system resources, specifically, when the idle resources cannot meet the system resources required by the running of the game application, and the running of the game terminal is overloaded at this time, scheduling the preset system resources to solve the problem of the running overload, that is, scheduling other applications to occupy resources to solve the problem of the running overload, wherein the other applications to occupy resources can be scheduled in a mode of closing the other applications or switching the other applications to background running and the like.
Wherein, when the first prediction result is overload operation, the step of allocating preset system resources comprises the following steps:
step S14, obtaining a second prediction result at a time point next to the current time point, and comparing the first prediction result with the second prediction result;
in this embodiment, a second prediction result of a next time point of the current time point is obtained, and the first prediction result is compared with the second prediction result, specifically, the second prediction result of the next time point of the current time point is obtained through a preset predictor, and the first prediction result is compared with the second prediction result, that is, a first stuck degree of the first prediction result is compared with a second stuck degree of the second prediction result, where the stuck degree can be represented by a system resource occupation ratio of the game application.
Step S15, when the second stuck degree of the second prediction result is greater than the first stuck degree of the first prediction result, scheduling the preset system resource;
in this embodiment, when the second stuck degree of the second prediction result is greater than the first stuck degree of the first prediction result, the preset system resource is scheduled, where the first stuck degree corresponds to a current time point, and the second stuck degree corresponds to a next time point, specifically, when the occupation ratio of the game application occupying the system resource corresponding to the next time point is greater than the occupation ratio of the game application occupying the system resource corresponding to the current time point, the preset system resource needs to be scheduled to support the game application to run, that is, other application occupying resources are scheduled to support the game application to run.
And step S16, and/or when the second stuck degree of the second prediction result is less than or equal to the first stuck degree of the first prediction result, releasing the preset system resource.
In this embodiment, when the second degree of the second prediction result is less than the first degree of the first prediction result, the preset system resource is released, specifically, when the proportion of the system resource occupied by the game application corresponding to the current time point is less than the proportion of the system resource occupied by the game application corresponding to the current time point, the excess proportion of the system resource is released, for example, if the proportion of the system resource corresponding to the second degree of the stuck is 50%, and the proportion of the system resource corresponding to the first degree of the stuck is 30%, 20% of the proportion of the system resource is released as the idle system resource.
In the embodiment, the system resource data before the current time point is obtained, and then the system resource data is input into the preset predictor to obtain a first prediction result, and when the first prediction result is operation overload, the preset system resource is allocated. That is, in the present embodiment, the acquired system resource data is input into the predictor, so as to acquire the first prediction result, and then, based on the first katton prediction result, the accurate scheduling and reasonable allocation of the preset system resource are realized, that is, the present embodiment realizes the accurate prediction of the overload of the game terminal, and further, the accurate scheduling and reasonable allocation of the system resource are realized, and the technical problems of blind scheduling and unreasonable allocation of the system resource in the prior art are solved.
Further, referring to fig. 2, in another embodiment of the method for providing system resource scheduling according to the first embodiment of the present application, the step S11 includes:
a10, acquiring a preset basic model and preset training data corresponding to the predictor;
in this embodiment, it should be noted that the preset basic model is an untrained model, and the preset basic model includes a plurality of initial weight ratios, where the initial weight ratios are randomly determined by a system, the preset training data is extracted from a local sample database, and the local sample database is pre-established, where the local sample database includes a large amount of preset training data, and the preset training data includes a plurality of training data sets.
Step A20, inputting the preset training data into the preset basic model, and training the preset basic model to obtain a verification model corresponding to the preset basic model.
In this embodiment, the preset training data is input into the preset basic model, the preset basic model is trained, a verification model corresponding to the preset basic model is obtained, specifically, the preset training data is input into the preset basic model, an output result is obtained, the output result is compared with training result data in the preset training data, an error rate is analyzed, when the error rate is greater than a preset threshold value, the initial weight ratios are adjusted, and the preset basic model is retrained until the error rate is less than or equal to the preset threshold value.
Wherein the preset training data comprises training input data and training result data, the preset base model comprises a plurality of initial weight ratios,
the step of inputting the preset training data into the preset basic model, training the preset basic model, and obtaining a verification model corresponding to the preset basic model includes:
step A21, inputting the training input data into the preset basic model to obtain initial prediction result data;
in this embodiment, it should be noted that the training input data includes a plurality of training data sets, the number of the training data sets can ensure that the training effect on the preset basic model is good, each of the training data sets corresponds to a preset time duration, each of the training data sets includes one training input data and one training result data, that is, assuming that the training result data is a prediction result obtained at a certain specific time point, the preset time duration is a time period before the specific time point, and the interval time between the specific time point and the time period can be set by itself. Further, the training input data is input into the preset basic model, so that initial prediction result data is obtained, wherein the initial prediction result data comprises a plurality of initial prediction results, and one preset duration corresponds to one initial prediction result.
Wherein the training input data comprises a plurality of training data sets, wherein each of the training data sets comprises one or more of a Cpu resource proportion, an Io resource proportion, and a Memory resource proportion, the plurality of initial weight proportions comprises one or more of a Cpu weight proportion, an Io weight proportion, and a Memory weight proportion,
the step of inputting the training input data into the preset basic model to obtain initial prediction result data comprises:
step A211, inputting the training input data into the preset basic model to obtain a first stuck value corresponding to the Cpu resource ratio, a second stuck value corresponding to the Io resource ratio, and a third stuck value corresponding to the Memory resource ratio;
in this embodiment, it should be noted that the stuck value is a value used to measure a stuck degree of a game terminal, and the larger the ratio of system resources to total system resources required by a game application is, the larger the stuck value is, the training input data is input into the preset base model to obtain a first stuck value corresponding to the ratio of the Cpu resource to the Cpu resource, and/or a second stuck value corresponding to the ratio of the Io resource to the Memory resource, and/or a third stuck value corresponding to the ratio of the Memory resource, specifically, the ratio of the Cpu resource to the Io resource to the Memory resource and the ratio of the Memory resource for each preset duration are input into the preset base model to obtain a first stuck value corresponding to the ratio of the Cpu resource, and/or a second stuck value corresponding to the ratio of the Io resource to the Memory resource, and/or a plurality of third stuck values corresponding to the Memory resource, where one or more time points are included before the current time point, and each time point corresponds to a Cpu resource ratio, an Io resource ratio and a Memory resource ratio, the Cpu resource ratio of the preset time length is the mean value of the Cpu resource ratios of the corresponding time points, the Io resource ratio of the preset time length is the mean value of the Io resource ratios of the corresponding time points, and the Memory resource ratio of the preset time length is the mean value of the Memory resource ratios of the corresponding time points.
Step a212, calculating a composite stuck value based on the first stuck value, and/or the second stuck value, and/or the third stuck value and the Cpu weight ratio, and/or the Io weight ratio, and/or the Memory weight ratio, wherein one training data set corresponds to one composite stuck value;
in this embodiment, a comprehensive stuck value is calculated based on the first stuck value, and/or the second stuck value, and/or the third stuck value and the Cpu weight ratio, and/or the Io weight ratio, and/or the Memory weight ratio, wherein one training data set corresponds to one comprehensive stuck value, and specifically, a sum of a product of the first stuck value and the Cpu weight ratio, a product of the second stuck value and the Io weight ratio, and a product of the third stuck value and the Memory weight ratio for each preset duration is calculated to obtain the comprehensive stuck value for each preset duration, that is, the comprehensive stuck value is obtained.
Step A213, comparing the comprehensive stuck value with a preset standard stuck value to obtain initial prediction result data.
In this embodiment, it should be noted that the preset standard stuck value is a stuck value used for measuring whether the game terminal is overloaded or not, when the integrated stuck value is greater than the preset standard stuck value, the game terminal is overloaded, and when the integrated stuck value is less than or equal to the preset standard stuck value, the game terminal is normally operated.
Comparing the comprehensive stuck value with a preset standard stuck value to obtain initial prediction result data, specifically, comparing the comprehensive stuck value with the preset standard stuck value, judging initial prediction results corresponding to all preset durations, combining the initial prediction results corresponding to all the preset durations into a set, wherein the set is the initial prediction result data, each initial prediction result corresponds to one preset duration, each preset duration corresponds to a timestamp, and each initial prediction result can be distinguished according to the timestamp.
Step A22, calculating the similarity between the initial prediction result data and the training result data, and setting the preset basic model as a verification model when the similarity is greater than or equal to a preset similarity;
in this embodiment, the similarity between the initial prediction result data and the training result data is calculated, when the similarity is greater than or equal to a preset similarity, the preset basic model is set as a verification model, specifically, the initial prediction results of each preset duration are compared with the training result data corresponding to each preset duration one by one, wherein the training result data includes the training prediction results corresponding to each preset duration, when the initial prediction results are the same as the training prediction results, the same result is recorded, the ratio of the number of the initial prediction results corresponding to the same result to the number of the initial prediction results of all the preset durations is counted, the ratio is the similarity, the similarity can be used to measure the prediction accuracy of the preset basic model, and the higher the similarity is, the higher the prediction accuracy is, and when the similarity is greater than or equal to a preset similarity, setting the preset basic model as a verification model, wherein the preset similarity is a value set by a user or default by a system and represents the prediction accuracy of the verification model, the verification model can be directly set as the predictor, and the verification model can be further verified in order to verify the prediction accuracy of the verification model.
And A23, and/or when the similarity is smaller than the preset similarity, adjusting the initial weight ratios, and retraining the preset basic model to obtain the verification model.
In this embodiment, and/or when the similarity is smaller than the preset similarity, adjusting the plurality of initial weight ratios, and retraining the preset basic model to obtain the verification model, specifically, when the similarity is smaller than the preset similarity, adjusting the Cpu weight ratio, the Io weight ratio, and the Memory weight ratio, retraining the preset basic model, where the similarity obtained by retraining should be greater than the similarity obtained by the previous training, and when the similarity is greater than or equal to the preset similarity, obtaining the verification model.
The step of inputting the preset training data into the preset basic model, training the preset basic model, and obtaining the verification model corresponding to the preset basic model includes:
step A30, acquiring preset verification data, wherein the preset verification data comprises verification input data and standard verification results, and each verification input data corresponds to one standard verification result;
in this embodiment, it should be noted that the verification data includes a plurality of verification data sets, each of the verification data sets includes a verification input data and a standard verification result, and the verification input data and the standard verification result correspond to each other one by one.
Step A40, inputting the verification input data into the verification model to obtain an actual verification result;
in this embodiment, it should be noted that, when each piece of the verification input data is input into the verification model, an actual verification result, that is, an actual verification result, may be output. Each verification input data corresponds to an actual verification result, and the quantity of the verification input data needs to ensure that the verification effect of the verification model is good.
Step A50, comparing the actual verification result with the standard verification result to obtain a verification error rate;
in this embodiment, the actual verification result is compared with the standard verification result to obtain a verification error rate, specifically, the actual verification result and the standard verification result corresponding to each verification input data are compared one by one, and the percentage of the actual verification results different from the standard verification result in all the actual verification results is calculated to obtain the verification error rate, for example, if there are 3 actual verification results different from the corresponding standard verification result in 100 actual verification results, the verification error rate is 3%.
Step A60, comparing the verification error rate with a preset error threshold value, and when the verification error rate is less than or equal to the preset error threshold value, using the verification model as the predictor;
in this embodiment, it should be noted that the preset error threshold is a measure for measuring the prediction accuracy of the predictor, and the smaller the preset error threshold is, the higher the prediction accuracy of the predictor is.
Comparing the verification error rate with a preset error threshold value, taking the verification model as the predictor when the verification error rate is smaller than or equal to the preset error threshold value, specifically, comparing the verification error rate with the preset error threshold value, and taking the verification model as the predictor when the verification error rate is smaller than or equal to the preset error threshold value, that is, when the prediction accuracy of the verification model reaches a specified accuracy.
Step a70, and/or retraining the preset base model when the verification error rate is larger than the preset error threshold.
In this embodiment, and/or when the verification error rate is greater than the preset error threshold, retraining the preset basic model, specifically, when the verification error rate is greater than the preset error threshold, it indicates that the prediction accuracy of the verification model does not reach the specified accuracy, at this time, setting the verification model as the preset basic model, performing retraining, and then performing re-verification until the verification error rate is less than or equal to the preset error threshold.
In this embodiment, a preset basic model and preset training data corresponding to the predictor are obtained, and further, the preset training data is input into the preset basic model, and the preset basic model is trained to obtain a verification model corresponding to the preset basic model. That is, in the present embodiment, the preset basic model and the preset training data are obtained, and then the preset basic model is trained to obtain the verification model, and further, the verification model may be set as a predictor or further verified to obtain a predictor, that is, the predictor is obtained.
Further, based on the first embodiment and the second embodiment in the present application, in another embodiment of providing a system resource scheduling method, the system resource scheduling method includes:
step S21, acquiring the current running state;
in this embodiment, it should be noted that the current operating state is a real-time operating state of the user terminal, and whether the user terminal is stuck and a degree of the user terminal being stuck can be determined by obtaining the current operating state.
The method comprises the steps of obtaining a current operation state, namely obtaining the use conditions of various system resources of a user terminal, and obtaining the current operation state by analyzing the use conditions of various system resources, wherein if the user terminal is in normal operation, namely not in an operation overload state, the larger the demand on the various system resources is, the higher the probability of the user terminal being blocked is, and if the user terminal is in the operation overload state, the larger the demand on the various system resources is, the higher the blocking degree of the user terminal is.
Wherein the step S21 includes:
step S211, obtaining system resource data, where the system resource data includes one or more of a Cpu resource, an Io resource, and a Memory resource.
In this embodiment, it should be noted that the current operating state is obtained by analyzing the usage of the system resource data, and the system resource data can be obtained by a preset system resource monitor, where the preset system resource monitor can monitor the usage of various system resources of the user terminal in real time.
Step S22, judging whether the current running state meets the preset condition;
in this embodiment, it should be noted that the preset condition includes a system resource usage ratio standard, where the system resource usage ratio includes one or more of a Cpu resource usage ratio, an Io resource usage ratio, and a Memory resource usage ratio.
And judging whether the current operation state meets a preset condition, specifically, judging whether the system resource usage proportion corresponding to the current operation state is greater than a system resource usage proportion standard, if so, the current operation state meets the preset condition, and if not, the current operation state does not meet the preset condition.
Wherein the step S22 includes:
step S221, inputting the system resource data into a preset predictor to obtain a first prediction result;
in this embodiment, it should be noted that the preset predictor is a trained prediction model, and the system resource data is input into the preset predictor, so as to obtain a first prediction result, where the first prediction result is a determination result of the current operation state, and the first prediction result is an operation overload or no operation overload.
And step S222, judging that a preset condition is met when the first prediction result is overload operation.
In this embodiment, when the first prediction result is an overload operation, it is determined that a preset condition is satisfied, that is, when the current operation state is an overload operation, the usage percentage of the system resource corresponding to the current operation state is greater than the usage percentage standard of the system resource, so that the current operation state satisfies the preset condition.
And step S23, if yes, scheduling the system resource according to the preset strategy.
In this embodiment, it should be noted that the preset policy refers to a method for scheduling system resources, that is, when an operation overload occurs, scheduling system resources in a corresponding proportion according to the preset policy to solve the operation overload problem.
If so, scheduling system resources according to a preset strategy, specifically, if the current operating state meets a preset condition, determining a system resource demand proportion and a current system resource proportion corresponding to the current operating state, where the system resource demand proportion refers to a system resource proportion required by the current operating state in a non-operating overload state, and further obtaining a system resource proportion difference, and further, scheduling system resources to fill up the system resource proportion difference, for example, if the current system resource proportion is 60% and the system resource demand proportion is 70%, then scheduling 10% of the system resources.
In this embodiment, the current operating state is obtained, and whether the current operating state meets the preset condition is further determined, and if yes, the system resources are scheduled according to a preset strategy. That is, in this embodiment, by obtaining the current operating state and determining whether the current operating state meets the preset condition, it is determined whether the user terminal needs to schedule the system resource, and if so, the corresponding system resource is reasonably scheduled according to the preset policy to solve the problem of overload operation, so that the technical problems of blind scheduling and unreasonable allocation of the system resource in the prior art are solved
Referring to fig. 3, fig. 3 is a schematic device structure diagram of a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 3, the system resource scheduling apparatus may include: a processor 1001, such as a CPU, a memory 1005, and a communication bus 1002. The communication bus 1002 is used for realizing connection communication between the processor 1001 and the memory 1005. The memory 1005 may be a high-speed RAM memory or a non-volatile memory (e.g., a magnetic disk memory). The memory 1005 may alternatively be a memory device separate from the processor 1001 described above.
Optionally, the system resource scheduling device may further include a target user interface, a network interface, a camera, a Radio Frequency (RF) circuit, a sensor, an audio circuit, a WiFi module, and the like. The target user interface may comprise a Display screen (Display), an input unit such as a Keyboard (Keyboard), and the optional target user interface may also comprise a standard wired interface, a wireless interface. The network interface may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface).
Those skilled in the art will appreciate that the system resource scheduling device architecture shown in fig. 3 does not constitute a limitation of the system resource scheduling device and may include more or fewer components than shown, or some components may be combined, or a different arrangement of components.
As shown in fig. 3, a memory 1005, which is a kind of computer storage readable storage medium, may include an operating system, a network communication module, and a system resource scheduler therein. The operating system is a program that manages and controls the system resource scheduler hardware and software resources, supporting the operation of the system resource scheduler as well as other software and/or programs. The network communication module is used for communication among the components in the memory 1005 and with other hardware and software in the system resource scheduling system.
In the system resource scheduling apparatus shown in fig. 3, the processor 1001 is configured to execute a system resource scheduler stored in the memory 1005, so as to implement the steps of the system resource scheduling method described in any one of the above.
The specific implementation of the system resource scheduling device of the present invention is basically the same as the embodiments of the system resource scheduling method described above, and is not described herein again.
The invention also provides a system resource scheduling device, which comprises:
the first acquisition module is used for acquiring system resource data before the current time point;
the prediction module is used for inputting the system resource data into a preset predictor to obtain a first prediction result;
and the first scheduling module is used for allocating preset system resources when the first prediction result is overload operation.
Optionally, the system resource scheduling apparatus further includes:
the second acquisition module is used for acquiring a preset basic model and preset training data corresponding to the predictor;
and the training module is used for inputting the preset training data into the preset basic model, training the preset basic model and obtaining a verification model corresponding to the preset basic model.
Optionally, the training module comprises:
the first input unit is used for inputting the training input data into the preset basic model to obtain initial prediction result data;
the first calculation unit is used for calculating the similarity between the initial prediction result data and the training result data, and when the similarity is greater than or equal to a preset similarity, the preset basic model is set as a verification model;
and the adjusting unit is used for adjusting the plurality of initial weight ratios and retraining the preset basic model to obtain the verification model when the similarity is smaller than the preset similarity.
Optionally, the input unit includes:
an input subunit, configured to input the training input data into the preset base model, so as to obtain a plurality of first stuck values corresponding to the Cpu resource occupation ratio, a plurality of second stuck values corresponding to the Io resource occupation ratio, and a plurality of third stuck values corresponding to the Memory resource occupation ratio;
a calculating subunit, configured to calculate a composite stuck value based on the first stuck value, and/or the second stuck value, and/or the third stuck value and the Cpu weight ratio, and/or the Io weight ratio, and/or the Memory weight ratio, wherein a training data set corresponds to a composite stuck value;
and the comparison subunit is used for comparing the comprehensive stuck value with a preset standard stuck value to obtain initial prediction result data.
Optionally, the system resource scheduling apparatus further includes:
a third obtaining module, configured to obtain preset verification data, where the preset verification data includes verification input data and standard verification results, and each verification input data corresponds to one standard verification result;
the input module is used for inputting the verification input data into the verification model to obtain an actual verification result;
the first comparison module is used for comparing the actual verification result with the standard verification result to obtain a verification error rate;
the second comparison module is used for comparing the verification error rate with a preset error threshold value, and when the verification error rate is smaller than or equal to the preset error threshold value, the verification model is used as the predictor;
and the retraining module is used for retraining the preset basic model when the verification error rate is larger than the preset error threshold value and/or when the verification error rate is larger than the preset error threshold value.
Optionally, the prediction module comprises:
a second input unit, configured to input the system resource data into the predictor, and obtain 1 or more comprehensive system resource ratios corresponding to the 1 or more time points;
a comparing unit, configured to compare the 1 or more comprehensive system resource occupation ratios with a preset occupation ratio threshold, and when a part of the system resource occupation ratio in the 1 or more comprehensive system resource occupation ratios is greater than or equal to the preset occupation ratio threshold, obtain a number of time points corresponding to the part of the system resource occupation ratio;
a second calculating unit, configured to calculate a quantity ratio of the number of time points to the 1 or more number of time points, where when the quantity ratio is greater than a preset quantity ratio, the first prediction result is an operation overload;
a second comparison unit, configured to determine that the first prediction result is normal if the number ratio is smaller than or equal to the preset number ratio.
Optionally, the system resource scheduling apparatus further includes:
a third comparison module, configured to obtain a second prediction result at a time point next to the current time point, and compare the first prediction result with the second prediction result;
the scheduling module is used for scheduling the preset system resource when the second stuck degree of the second prediction result is greater than the first stuck degree of the first prediction result;
and the releasing module is used for releasing the preset system resource when the second clamping degree of the second prediction result is smaller than or equal to the first clamping degree of the first prediction result.
Optionally, the first input module comprises:
the extracting unit is used for extracting the current time point in the system resource scheduling request when the system resource scheduling request is received;
and the collecting unit is used for collecting the system resource data in the preset time length before the current time point through a preset monitor.
Optionally, the system resource scheduling apparatus further includes:
a fourth obtaining module, configured to obtain the current operating state;
the judging module is used for judging whether the current running state meets a preset condition or not;
and the second scheduling module is used for scheduling the system resources according to a preset strategy if the system resources are the same as the preset strategy.
Optionally, the fourth obtaining module includes:
an obtaining unit, configured to obtain system resource data, where the system resource data includes one or more of a Cpu resource, an Io resource, and a Memory resource.
Optionally, the determining module includes:
the prediction unit is used for inputting the system resource data into a preset predictor to obtain a first prediction result;
and the judging unit is used for judging that a preset condition is met when the first prediction result is running overload.
The specific implementation of the system resource scheduling apparatus of the present invention is basically the same as the embodiments of the system resource scheduling method described above, and is not described herein again.
The present invention provides a readable storage medium storing one or more programs, the one or more programs being further executable by one or more processors for implementing the steps of the system resource scheduling method of any of the above.
The specific implementation of the readable storage medium of the present invention is substantially the same as the embodiments of the system resource scheduling method described above, and is not described herein again.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by the contents of the present specification and drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (13)
1. A system resource scheduling method, characterized in that the system resource scheduling method comprises the following steps:
s11: acquiring system resource data before the current time point;
s12: inputting the system resource data into a preset predictor to obtain a first prediction result;
s13: and when the first prediction result is overload operation, allocating preset system resources.
2. The method for scheduling system resources according to claim 1, wherein the step of S11 is preceded by:
acquiring a preset basic model and preset training data corresponding to the predictor;
and inputting the preset training data into the preset basic model, and training the preset basic model to obtain a verification model corresponding to the preset basic model.
3. The system resource scheduling method of claim 2, wherein the predetermined training data comprises training input data and training result data, the predetermined base model comprises a plurality of initial weight ratios,
the step of inputting the preset training data into the preset basic model, training the preset basic model, and obtaining a verification model corresponding to the preset basic model includes:
inputting the training input data into the preset basic model to obtain initial prediction result data;
calculating the similarity of the initial prediction result data and the training result data, and setting the preset basic model as a verification model when the similarity is greater than or equal to a preset similarity;
and/or when the similarity is smaller than the preset similarity, adjusting the multiple initial weight ratios, and retraining the preset basic model to obtain the verification model.
4. The method of claim 3, wherein the training input data comprises a plurality of training data sets, wherein each of the training data sets comprises one or more of a Cpu resource ratio, an Io resource ratio, and a Memory resource ratio, wherein the plurality of initial weight ratios comprises one or more of a Cpu weight ratio, an Io weight ratio, and a Memory weight ratio,
the step of inputting the training input data into the preset basic model to obtain initial prediction result data comprises:
inputting the training input data into the preset basic model to obtain a first stuck value corresponding to the Cpu resource ratio, a second stuck value corresponding to the Io resource ratio and a third stuck value corresponding to the Memory resource ratio;
calculating a composite stuck value based on the first stuck value, and/or the second stuck value, and/or the third stuck value, and the Cpu weight ratio, and/or the Io weight ratio, and/or the Memory weight ratio, wherein a training data set corresponds to a composite stuck value;
and comparing the comprehensive stuck value with a preset standard stuck value to obtain initial prediction result data.
5. The method for scheduling system resources according to claim 2, wherein the step of inputting the preset training data into the preset base model, training the preset base model, and obtaining the verification model corresponding to the preset base model comprises:
acquiring preset verification data, wherein the preset verification data comprise verification input data and standard verification results, and each verification input data corresponds to one standard verification result;
inputting the verification input data into the verification model to obtain an actual verification result;
comparing the actual verification result with the standard verification result to obtain a verification error rate;
comparing the verification error rate with a preset error threshold value, and taking the verification model as the predictor when the verification error rate is smaller than or equal to the preset error threshold value;
and/or retraining the preset basic model when the verification error rate is larger than the preset error threshold value.
6. The method for scheduling system resources according to claim 1, wherein said step S11 includes: the current time point is preceded by 1 or more time points, the system resource data includes system resource proportions, and each of the time points corresponds to a system resource proportion,
the step of S12 includes:
inputting the system resource data into the predictor, and obtaining 1 or more comprehensive system resource ratios corresponding to the 1 or more time points;
comparing the 1 or more comprehensive system resource occupation ratios with a preset occupation ratio threshold value, and acquiring the time point quantity corresponding to a part of system resource occupation ratio when the part of system resource occupation ratio is larger than or equal to the preset occupation ratio threshold value in the 1 or more comprehensive system resource occupation ratios;
calculating the quantity ratio of the time point quantity relative to the 1 or more time point quantities, and when the quantity ratio is greater than a preset quantity ratio, the first prediction result is overload operation;
and/or when the number proportion is less than or equal to the preset number proportion, the first prediction result is normal.
7. The method for scheduling system resources according to claim 1, wherein the step S13 is followed by the steps of:
acquiring a second prediction result of a next time point of the current time point, and comparing the first prediction result with the second prediction result;
when the second stuck degree of the second prediction result is larger than the first stuck degree of the first prediction result, scheduling the preset system resource;
and/or releasing the preset system resource when the second clamping degree of the second prediction result is less than or equal to the first clamping degree of the first prediction result.
8. The method for scheduling system resources according to claim 1, wherein the step S11 includes:
when a system resource scheduling request is received, extracting a current time point in the system resource scheduling request;
and acquiring system resource data in a preset time length before the current time point through a preset monitor.
9. A system resource scheduling method, characterized in that the system resource scheduling method comprises the following steps:
s21: acquiring a current running state;
s22: judging whether the current running state meets a preset condition or not;
s23: if yes, scheduling the system resources according to a preset strategy.
10. The method for scheduling system resources according to claim 9, wherein the step S21 includes:
obtaining system resource data, the system resource data comprising one or more of a Cpu resource, an Io resource, and a Memory resource.
11. The method for scheduling system resources according to claim 10, wherein the step S22 includes:
inputting the system resource data into a preset predictor to obtain a first prediction result;
and when the first prediction result is overload operation, judging that a preset condition is met.
12. A system resource scheduling apparatus, comprising: a memory, a processor, and a program stored on the memory for implementing the system resource scheduling method,
the memory is used for storing a program for realizing the system resource scheduling method;
the processor is configured to execute a program implementing the system resource scheduling method to implement the steps of the system resource scheduling method according to any one of claims 1 to 8 or 9 to 11.
13. A readable storage medium, having stored thereon a program for implementing a method for scheduling system resources, the program being executed by a processor to implement the steps of the method for scheduling system resources according to any one of claims 1 to 8 or 9 to 11.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910885587.1A CN110597637A (en) | 2019-09-17 | 2019-09-17 | System resource scheduling method, device and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910885587.1A CN110597637A (en) | 2019-09-17 | 2019-09-17 | System resource scheduling method, device and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110597637A true CN110597637A (en) | 2019-12-20 |
Family
ID=68860974
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910885587.1A Pending CN110597637A (en) | 2019-09-17 | 2019-09-17 | System resource scheduling method, device and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110597637A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111325451A (en) * | 2020-02-02 | 2020-06-23 | 贾海芳 | Intelligent building multistage scheduling method, intelligent building scheduling center and system |
-
2019
- 2019-09-17 CN CN201910885587.1A patent/CN110597637A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111325451A (en) * | 2020-02-02 | 2020-06-23 | 贾海芳 | Intelligent building multistage scheduling method, intelligent building scheduling center and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wu et al. | Stochastic analysis of delayed mobile offloading in heterogeneous networks | |
| US9286568B2 (en) | Battery drain analysis and prediction for wireless devices | |
| CN107506240B (en) | Background application program control method and device, storage medium and electronic equipment | |
| CN109981744B (en) | Data distribution method and device, storage medium and electronic equipment | |
| WO2019062405A1 (en) | Application program processing method and apparatus, storage medium, and electronic device | |
| CN110362460A (en) | A kind of application program capacity data processing method, device and storage medium | |
| CN110796591B (en) | GPU card using method and related equipment | |
| WO2023077813A1 (en) | Method and apparatus for determining fake traffic in live broadcast room | |
| CN107704317B (en) | Intelligent device and application management method thereof and device with storage function | |
| CN110597637A (en) | System resource scheduling method, device and readable storage medium | |
| Cho et al. | A battery lifetime guarantee scheme for selective applications in smart mobile devices | |
| CN109800085B (en) | Resource configuration detection method and device, storage medium and electronic equipment | |
| CN113079045B (en) | Bandwidth allocation method, device, server and storage medium | |
| CN111756589A (en) | Cloud resource management method and device, cloud server and storage medium | |
| CN115756812A (en) | Resource adjusting method and device and storage medium | |
| CN113271360A (en) | Recommendation method and device of application program, electronic device and medium | |
| CN113055423A (en) | Policy pushing method, policy execution method, device, equipment and medium | |
| CN113271228B (en) | Bandwidth resource scheduling method, device, equipment and computer readable storage medium | |
| CN112422370B (en) | Method and device for determining voice call quality | |
| CN115858048A (en) | Hybrid key level task oriented dynamic edge arrival unloading method | |
| CN106612212B (en) | Service network resource utilization rate statistical method and device | |
| CN112003900B (en) | Method and system for realizing high service availability under high-load scene in distributed system | |
| CN113595814A (en) | Message delay detection method and device, electronic equipment and storage medium | |
| CN114416326A (en) | Big data control method, device, control system and readable storage medium | |
| CN112988417A (en) | Message processing method and device, electronic equipment and computer readable medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |