CN120276854A

CN120276854A - Resource scheduling method and system and electronic equipment

Info

Publication number: CN120276854A
Application number: CN202510388174.8A
Authority: CN
Inventors: 陈勇
Original assignee: Vivo Mobile Communication Co Ltd
Current assignee: Vivo Mobile Communication Co Ltd
Priority date: 2025-03-31
Filing date: 2025-03-31
Publication date: 2025-07-08

Abstract

The application discloses a resource scheduling method and system and electronic equipment, and belongs to the technical field of terminals. The resource scheduling method comprises the steps of determining load information of a working scene according to load characteristic information and service quality information of the working scene of the electronic equipment, transmitting the load information to a scheduler corresponding to the working scene for processing, and determining processor parameters corresponding to the working scene according to the processed load information.

Description

Resource scheduling method and system and electronic equipment

Technical Field

The application belongs to the technical field of terminals, and particularly relates to a resource scheduling method and system and electronic equipment.

Background

Currently, pheoda new series of chips are full-core central processing units (Central Processing Unit, CPU) with 1+3+4 architectures, namely 1 super-core, 3 super-cores and 4 super-cores, and Cell most-honour chips use self-developed Oryon CPU architecture 2+6, namely 2 super-cores and 6 performance cores. The architecture design of the processor has an evolution trend towards heavy load task application, but the change characteristics corresponding to the game scenes and the daily application scenes can not be distinguished, and the problems of excessive performance or power consumption of the game scenes with different loads or the application scenes with different loads still exist, so that the problem needs to be solved.

Aiming at the problems, the existing processing schemes schedule for different platforms and various scenes so as to exert the optimal performance and energy efficiency of the chip. Specifically, one class of processing schemes is to allocate multiple cores in a multi-core CPU according to priorities of different applications. For example, a majority of cores are preferentially allocated to foreground applications having a higher priority, and a minority of cores are allocated to background applications having a lower priority. Another type of processing scheme is to perform special processing for a specific priority or a heavy-load scene, such as a game scene, and schedule processing one by one for the type and scene characteristics of the game. Based on the method, a scheduling scheme of configuring and labeling game scenes and then corresponding to binding core frequency modulation and a scheduling scheme of setting specific strategies for fixed scenes of different games are gradually evolved. Meanwhile, the energy efficiency of the performance core is improved by adopting a mode of optimizing a kernel general scheduler, namely a full fairness scheduler (Completely Fair Scheduler, CFS) according to the application scene characteristics.

However, for the scheduling scheme of the processor, the scheduling scheme of the specific application task scene mostly depends on the specific debugging of the manual resource, is time-consuming and labor-consuming, is not intelligent enough, and only improves a small part of application scenes, while the scheduling scheme of the general scheduler optimized and improved can not accurately distinguish the key task scenes all the time, and has higher coupling degree in performance release matching.

Disclosure of Invention

The embodiment of the application aims to provide a resource scheduling method and system and electronic equipment, which can improve the intelligence, comprehensiveness and accuracy of processor scheduling.

In a first aspect, an embodiment of the present application provides a resource scheduling method, where the method includes determining load information of a working scenario according to load feature information and service quality information of the working scenario of an electronic device, transmitting the load information to a scheduler corresponding to the working scenario for processing, and determining processor parameters corresponding to the working scenario according to the processed load information.

In a second aspect, the embodiment of the application provides a resource scheduling system, which comprises a kernel layer, a load decision module and a hardware layer, wherein the kernel layer comprises the load decision module which is used for determining load information of a working scene of electronic equipment according to load characteristic information and service quality information of the working scene, the load decision module is also used for transmitting the load information to a scheduler corresponding to the working scene for processing, and the hardware layer is used for determining processor parameters corresponding to the working scene according to the processed load information.

In a third aspect, an embodiment of the present application provides an electronic device comprising a processor and a memory storing a program or instructions executable on the processor, the program or instructions implementing the steps of the resource scheduling method as in the first aspect when executed by the processor.

In a fourth aspect, embodiments of the present application provide a readable storage medium having stored thereon a program or instructions which, when executed by a processor, implement the steps of the resource scheduling method as in the first aspect.

In a fifth aspect, an embodiment of the present application provides a chip, the chip including a processor and a communication interface, the communication interface being coupled to the processor, the processor being configured to execute programs or instructions to implement the steps of the resource scheduling method as in the first aspect.

In a sixth aspect, embodiments of the present application provide a computer program product stored in a storage medium, the program product being executable by at least one processor to perform the steps of the resource scheduling method as in the first aspect.

In the resource scheduling method provided by the embodiment of the application, the load information of the working scene is determined according to the load characteristic information and the service quality information of the working scene of the electronic equipment, the load information is transmitted to the scheduler corresponding to the working scene for processing, and the processor parameters corresponding to the working scene are determined according to the processed load information. According to the resource scheduling method, the load information of the working scene is predicted based on the load characteristic information and the service quality information of the working scene of the electronic equipment, the corresponding scheduler is selected to process the load information, and then the processor parameters required by the working scene are scheduled based on the processed load information. Therefore, load information is predicted and resource scheduling is carried out based on relevant information of a working scene, manual debugging is not needed, and the intelligence, the comprehensiveness and the accuracy of processor scheduling are improved.

Drawings

Fig. 1 is a schematic flow chart of a resource scheduling method according to an embodiment of the present application;

FIG. 2 is a schematic diagram of a resource scheduling method according to an embodiment of the present application;

FIG. 3 is a second schematic diagram of a resource scheduling method according to an embodiment of the present application;

FIG. 4 is a third schematic diagram of a resource scheduling method according to an embodiment of the present application;

FIG. 5 is a schematic diagram of a resource scheduling method according to an embodiment of the present application;

FIG. 6 is a schematic diagram of an operation interface of a resource scheduling method according to an embodiment of the present application;

FIG. 7 is a schematic diagram of a resource scheduling method according to an embodiment of the present application;

FIG. 8 is a schematic diagram of a resource scheduling method according to an embodiment of the present application;

FIG. 9 is a schematic diagram of a resource scheduling method according to an embodiment of the present application;

FIG. 10 is a schematic diagram of a resource scheduling method according to an embodiment of the present application;

FIG. 11 is a diagram illustrating a resource scheduling method according to an embodiment of the present application;

FIG. 12 is a schematic diagram of a resource scheduling method according to an embodiment of the present application;

FIG. 13 is a block diagram illustrating a resource scheduling system according to an embodiment of the present application;

Fig. 14 is a block diagram of an electronic device according to an embodiment of the present application;

Fig. 15 is a schematic hardware structure of an electronic device according to an embodiment of the present application.

Detailed Description

The technical solutions of the embodiments of the present application will be clearly described below with reference to the drawings in the embodiments of the present application, and it is apparent that the described embodiments are some embodiments of the present application, but not all embodiments. All other embodiments, which are obtained by a person skilled in the art based on the embodiments of the present application, fall within the scope of protection of the present application.

The terms first, second and the like in the description and in the claims, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the terms so used are interchangeable under appropriate circumstances such that the embodiments of the application are capable of operation in sequences other than those illustrated or otherwise described herein, and that the objects identified by "first," "second," etc. are generally of a type not limited to the number of objects, for example, the first object may be one or more. Furthermore, in the description and claims, "and/or" means at least one of the connected objects, and the character "/", generally means that the associated object is an "or" relationship.

The resource scheduling method, the resource scheduling system and the electronic equipment provided by the embodiment of the application are described in detail through specific embodiments and application scenes thereof by combining the attached drawings.

As shown in fig. 1, an embodiment of the present application provides a resource scheduling method, which may include the following steps S102 to S106:

s102, determining the load information of the working scene according to the load characteristic information and the service quality information of the working scene of the electronic equipment.

The resource scheduling method provided by the embodiment of the application is executed by the electronic equipment, and the electronic equipment can be specifically intelligent electronic equipment such as intelligent mobile phones, tablet computers, notebook computers, intelligent watches and the like, and is not particularly limited.

The working scene may be a game scene, a non-game scene or a combination of the two, which is not particularly limited herein.

Further, quality of service (Qiality of Service, qoS) information is used to indicate the behavior of the electronics during processing of the current operating scenario, such as response speed.

Further, the load information is an actual scene load of the predicted working scene.

Specifically, as shown in fig. 3, in the system frame of the resource scheduling method provided by the embodiment of the present application, a load decision module of a kernel layer may obtain load feature information of a working scenario. On this basis, as shown in fig. 10, the load decision module predicts the actual scene load of the working scene based on the load characteristic information of the working scene and in combination with the preset service quality information of the working scene, so as to obtain the load information of the working scene.

And S104, transmitting the load information to a scheduler corresponding to the working scene for processing.

Specifically, in the resource scheduling method provided by the embodiment of the present application, as shown in fig. 3, after the load decision module determines the load information of the working scenario, the load information is transmitted to the scheduler corresponding to the working scenario for processing according to the scenario type of the working scenario.

In practical applications, the scheduler may be a Real Time (RT) scheduler, a virtual network address (Virtual Internet Protocol, VIP) scheduler, a full-fair scheduler, an energy-aware scheduler (ENERGY AWARE Scheduling, EAS), or an extensible scheduler, which is not limited herein.

And S106, determining processor parameters corresponding to the working scene according to the processed load information.

Specifically, in the resource scheduling method provided by the embodiment of the present application, as shown in fig. 3, after processing load information of a working scenario by a scheduler, the kernel layer transmits the processed load information to the hardware layer. On this basis, as shown in fig. 8, the hardware layer selectively schedules processor parameters, such as processor cores and processor frequencies, corresponding to the working scene based on the processed load information, and updates the priority of rendering threads of the working scene.

The resource scheduling method provided by the embodiment of the application determines the load information of the working scene according to the load characteristic information and the service quality information of the working scene of the electronic equipment, transmits the load information to the scheduler corresponding to the working scene for processing, and determines the processor parameters corresponding to the working scene according to the processed load information. According to the resource scheduling method, the load information of the working scene is predicted based on the load characteristic information and the service quality information of the working scene of the electronic equipment, the corresponding scheduler is selected to process the load information, and then the processor parameters required by the working scene are scheduled based on the processed load information. Therefore, load information is predicted and resource scheduling is carried out based on relevant information of a working scene, manual debugging is not needed, and the intelligence, the comprehensiveness and the accuracy of processor scheduling are improved.

In the embodiment of the present application, before S102, the above method for scheduling resources may specifically further include S108 and S110 as follows:

s108, identifying the working scene of the electronic equipment according to the interface information and the operation information of the electronic equipment by utilizing the target model.

As shown in fig. 4, the target model is obtained after learning and training task loads and core configuration information of different types of task scenes of different applications, and the target model can record a current foreground task and a background task of the electronic device, identify a key task scene, and can distinguish a game scene from a non-game scene without distinguishing a fixed task load through a designated process.

Specifically, the object model has an Agent (ARTIFICIAL INTELLIGENCE AGENT, AI Agent), which is a phased key capability of the object model, with the ability to perceive, think, memorize, plan, screen identify, and execute, etc., to understand the content on the screen and to perform the user's tasks. In the resource scheduling method provided by the embodiment of the application, in order to accurately identify the load of a critical task scene, an Operating System (OS) end side model pertinently expands the capability of an intelligent agent for a scene layer, so that a target model of the intelligent agent end side performs local learning. In an actual application process, a training learning process of the target model for task scene perception may be specifically shown in fig. 12, so as to give the target model the task scene perception and recognition capability.

Further, the operation information may specifically include a current operation load of the electronic device and operation core information.

Specifically, in the resource scheduling method provided by the embodiment of the application, as shown in fig. 3, the scene perception engine module of the application layer identifies the working scene of the electronic device according to the interface information and the operation information of the electronic device by using the target model. The scene perception engine module is a key perception module of the intelligent agent and has the capability of operating a system end side model.

S110, acquiring load characteristic information of the working scene.

The load characteristic information is scene load in theory of a working scene, and the load characteristic information is determined by a target model based on task loads of different task scenes in the training and learning process.

Specifically, in the resource scheduling method provided by the embodiment of the application, as shown in fig. 3, after the working scene of the electronic device is identified, the scene perception engine module further obtains the load characteristic information of the working scene based on the identified working scene, and transmits the load characteristic information to the scene perception module of the framework layer, and the scene perception module further transmits the received load characteristic information to the load decision module of the kernel layer, so that the load decision module predicts the actual scene load of the working scene to obtain the load information of the working scene.

According to the embodiment of the application, the target model is utilized to identify the working scene of the electronic equipment according to the interface information and the operation information of the electronic equipment, and the load characteristic information of the working scene is obtained. Therefore, the target model is utilized to identify the working scene of the electronic equipment according to the related information of the electronic equipment, manual debugging is not needed, the intelligent performance of the processor scheduling is improved, the manpower and material resource consumed by the processor scheduling is reduced, most of task scenes and key task scenes can be identified based on the target model, and the comprehensiveness and accuracy of the processor scheduling are improved.

In the embodiment of the present application, the above S108 may specifically include the following S108a to S108c:

s108a, intercepting a display interface of the electronic equipment by utilizing the target model, and carrying out interface identification on the display interface to obtain an interface identification result.

The target model has the screen capturing identification capability.

Specifically, in the resource scheduling method provided by the embodiment of the application, the scene perception engine module intercepts the display interface of the electronic equipment by utilizing the screen capturing recognition capability of the target model, and performs interface recognition on the display interface to obtain an interface recognition result.

S108b, acquiring the operation load and the operation core information of the electronic equipment.

The running load is used for indicating the load of the current running task of the electronic equipment, and the running core information is used for indicating the processor core and the processor frequency of the current running of the electronic equipment.

Specifically, in the resource scheduling method provided by the embodiment of the application, the scene-aware engine module also obtains the current operation information of the electronic device, namely the operation load and the operation core information.

S108c, determining the working scene of the electronic equipment according to the interface identification result, the operation load and the operation core information.

Specifically, in the resource scheduling method provided by the embodiment of the application, after the interface identification result, the operation load and the operation core information are obtained, the target model perceives and identifies the current working scene of the electronic equipment based on the result of learning and training for the task loads and the core configuration information of different applications and different types of task scenes.

According to the embodiment of the application, in the process of identifying the working scene of the electronic equipment according to the interface information and the operation information of the electronic equipment by utilizing the target model, the display interface of the electronic equipment is intercepted by utilizing the target model, the interface identification is carried out on the display interface to obtain the interface identification result, the operation load and the operation core information of the electronic equipment are obtained, and the working scene of the electronic equipment is determined according to the interface identification result, the operation load and the operation core information. Therefore, the screen capturing recognition capability of the target model is utilized, the working scene of the electronic equipment is recognized by combining the operation load and the operation core information of the electronic equipment, manual debugging is not needed, the intelligence of scene recognition is improved, most of task scenes and key task scenes can be recognized based on the target model, and the comprehensiveness and the accuracy of scene recognition are improved.

In the embodiment of the present application, the above S108a may specifically include the following S112 to S116:

s112, carrying out interface identification on the display interface through the target model, and determining interface elements in the display interface.

The Interface elements are User Interface (UI) elements in a display Interface, such as pictures, buttons, menus, and the like.

Specifically, in the resource scheduling method provided by the embodiment of the application, after the screen capturing is performed to obtain the display interface of the electronic equipment, the target model is used for carrying out interface identification on the display interface so as to accurately identify the interface elements in the display interface.

And S114, determining a target area or a target element in the display interface according to the position information and the semantic information of the interface element.

The position information is used for indicating the position and the change condition of each interface element, and can be determined through visual positioning of the interface elements.

Further, the semantic information can be determined through semantic connection of the interface elements, and the semantic information can specifically include information such as label information of the interface elements.

Specifically, in the resource scheduling method provided by the embodiment of the application, after the interface elements in the display interface are identified, the target area or the target elements in the display interface are determined according to the position information and the semantic information of the interface elements.

S116, determining an interface recognition result according to the target area or the target element.

Specifically, in the resource scheduling method provided by the embodiment of the application, after the target area or the target element in the display interface is identified, the interface identification result is determined according to the target area or the target element so as to identify the current scene type and window scene of the electronic equipment, support understanding and responding to complicated user intention, and the method is not limited to simple clicking operation, but also includes operations such as sliding pages and the like.

It can be understood that the task scene recognition scheme in the related art determines that the game application is determined according to the game progress or the tag code control, and then determines several fixed scenes, such as a loading scene, a hall scene, a single person alignment scene, a group battle scene and a transmission scene, for a specific game adaptation game interface, so that the scene recognition is not comprehensive enough and relies on manual debugging.

In the resource scheduling method provided by the embodiment of the application, the screen interface of the electronic equipment is perceptively identified by utilizing the screen capturing identification capability of the target model, namely, UI elements on screens with different resolutions are accurately identified through screen capturing, and key target areas or target elements are accurately identified through visual positioning such as operation of a user on pictures, buttons, menus and the like and semantic connection such as user marks, so that the current scene type and window scene of the electronic equipment are acquired, and the user intention with complex understanding and response is supported. Therefore, manual debugging is not needed, the intelligence of scene recognition is improved, most task scenes and key task scenes can be recognized, and the comprehensiveness and accuracy of scene recognition are improved.

According to the embodiment of the application, in the process of utilizing the target model to intercept the display interface of the electronic equipment and carrying out interface identification on the display interface to obtain the interface identification result, the target model is used for carrying out interface identification on the display interface to determine the interface element in the display interface, the target area or the target element in the display interface is determined according to the position information and the semantic information of the interface element, and the interface identification result is determined according to the target area or the target element. Therefore, the screen capturing recognition capability of the target model is utilized to recognize the working scene of the electronic equipment, manual debugging is not needed, the intelligence of scene recognition is improved, most of task scenes and key task scenes can be recognized, and the comprehensiveness and accuracy of scene recognition are improved.

In the embodiment of the present application, the above S104 may specifically include the following S104a and S104b:

and S104a, when the working scene comprises a game scene, transmitting load information of the game scene to the first scheduler for processing.

The first scheduler is an extensible scheduler sce_ext, and a scheduling policy of the first scheduler is determined according to load characteristic information of a game scene.

Specifically, in the resource scheduling method provided by the embodiment of the present application, as shown in fig. 3, after the load decision module determines the load information of the working scenario, for the game scenario, such as the running scenario, the battle scenario, the monster scenario, the hall scenario, the revival scenario and the like shown in fig. 5, the load decision module transmits the load information of the game scenario to the first scheduler, that is, the expandable scheduler sche_ext is processed.

And S104b, in the case that the working scene comprises a non-game scene, transmitting load information of the non-game scene to the second scheduler for processing.

The second scheduler may be a VIP scheduler, a CFS scheduler, an RT scheduler, an EAS scheduler, and the like, which are not particularly limited herein.

Specifically, in the resource scheduling method provided by the embodiment of the present application, as shown in fig. 3, after the load decision module determines the load information of the working scenario, for the non-game scenario, such as the video scenario, the live broadcast scenario, the payment scenario, the recording scenario, the ticket-robbing scenario and the like shown in fig. 7, the load decision module transmits the load information of the non-game scenario to the second scheduler for processing.

It can be appreciated that the scheduler scheme in the related art, or locally optimizes for a general scheduler such as CFS, or increases the VIP scheduling scheme for the load of a mission critical scenario, has a higher degree of coupling in performance release matching.

In the resource scheduling method provided by the embodiment of the application, the SCHE_EXT scheduler is customized for the game scene, so that a self-defined kernel driving scheme can be realized, and the performance of the processor can be better distributed according to the load of the actual task scene.

According to the embodiment of the application, in the process of transmitting the load information to the scheduler corresponding to the working scene for processing, the load information of the game scene is transmitted to the first scheduler for processing when the working scene comprises the game scene, and the load information of the non-game scene is transmitted to the second scheduler for processing when the working scene comprises the non-game scene, wherein the first scheduler is an extensible scheduler, and the scheduling strategy of the first scheduler is determined according to the load characteristic information of the game scene. In this way, the scheduler is customized for the game scenario, enabling better allocation of processor performance based on the load of the actual task scenario.

In the embodiment of the present application, the step of transferring the load information of the game scenario to the first scheduler for processing may specifically include the following steps S118 to S122:

and S118, determining core configuration information according to the game scene and the load information.

Specifically, in the resource scheduling method provided by the embodiment of the application, after load information of a game scene is transmitted to a first scheduler, the first scheduler determines corresponding core configuration information according to the specific game scene and the load information thereof.

And S120, determining the characteristic information of the processor according to the core configuration information.

Specifically, in the resource scheduling method provided by the embodiment of the application, after the first scheduler determines the core configuration information corresponding to the game scene, the processor characteristic information is determined according to the core configuration information, so that the core configuration information is bound to the related processor characteristic.

S122, determining interface driving information of the processor according to the processor characteristic information.

Specifically, in the resource scheduling method provided by the embodiment of the application, after the first scheduler determines the processor characteristic information, the interface driving information of the processor is determined according to the processor characteristic information, so that the processor characteristic information is set to each processor of the hardware layer through the related interfaces of the driving, and the processor performance is better distributed according to the load of the actual task scene.

Specifically, as shown in fig. 9, the scheduling policy of the first scheduler, namely the sche_ext scheduler, on the load information of the game scene is implemented by a Core in the custom sche_ext scheduler to implement a Berkeley packet filter scheduler (Berkeley PACKET FILTER scheduler, bpf scheduler) and a Core scheduler, and an extended scheduling class ext_ sched _class and entity corresponding to the Core scheduler are customized to implement the custom scheduling policy according to the load feature information of the game scene.

Specifically, as shown in fig. 9, the game expansion scheduling, namely sched_ext_gate, implements dynamic loading of the scheduling policy by expanding the berkeley packet filter scheduler eBPF scheduler program to support writing of berkeley packet filter codes, namely BPF codes, in a user state, and implements key logic, such as task selection cores, select_cpu, task distribution scx _bpf_dispatch, and the like, registered to the kernel through an interface of the struct SCHED _ext_ops structure. Further, the bpf_struct_ops structure mechanism is utilized to replace the function pointer of the kernel scheduling class, so that the switching of the scheduling strategy is realized. Further, the rendering threads of the game scene are distributed to a global dynamic task queue (Dynamic Sequence Queue, DSQ), and the scene load core corresponding to the perception module configures the active pulling task. Further, load scheduling of task scenes corresponding to the perception modules is achieved through priority configuration of the expansion scheduling class ext_ sched _class, and an existing scheduling strategy is executed in non-game scenes. Further, the task is distributed to the load information acquired by the load decision module in the task selection ops. Select_cpu logic callback, and the determination mode of the load information is shown in fig. 10. Further, the processor frequency to be set is supported to be acquired through a HOOK function, that is, a HOOK function, and updated to be the load information acquired by the load decision module, which corresponds to the entity in fig. 9, such as enqueue _entity, that is, adding entity, dequeue _entity, that is, removing entity, and entity_tick, that is, entity clock period, and the like.

According to the embodiment of the application, in the process of transmitting the load information of the game scene to the first dispatcher for processing, the core configuration information is determined according to the game scene and the load information, the characteristic information of the processor is determined according to the core configuration information, and the interface driving information of the processor is determined according to the characteristic information of the processor. In this way, the scheduler is customized for the game scenario, enabling better allocation of processor performance based on the actual load of the game scenario.

In the embodiment of the present application, the processor parameters include a processor core and a processor frequency, and the above S106 may specifically include the following S106a:

And S106a, determining the processor core of the target cluster and the processor frequency of each processor core of the target cluster by utilizing the target model according to the processed load information, the processor type, the scene type and the performance information of each cluster of processor cores.

The processor type is used for indicating the chip platform corresponding to the processor, such as Gao Tongxiao long processor chip platform Qcom and Pheoda processor chip platform MTK.

The method comprises the steps of enabling a Gao Tongxiao-long processor core to be 2 oversized cores and 6 performance cores, enabling other versions of cores to be 1 big core and 3 middle cores and 4 small cores, enabling the latest version of cores to be 1 super big core and 3 oversized cores and 4 big cores and enabling other versions of cores to be 1 big core and 3 middle cores and 4 small cores, wherein the latest version of cores are called 2 oversized cores and 6 performance cores for the Gao Tongxiao-long processor core, and enabling the latest version of cores to be 1 big core and 3 middle cores and 4 small cores for the Pheoda processor core.

Specifically, in the resource scheduling method provided by the embodiment of the present application, as shown in fig. 11, the target model determines the target cluster processor core based on the result of learning and training for task loads of different applications and different types of task scenes and core configuration information, according to the processed load information, the processor type, the scene type and the performance information of each cluster of processor cores, and determines the processor frequency of each processor core in the target cluster processor core. That is, the target model performs core selection frequency modulation processing according to the processed load information, the processor type, the scene type and the performance information of each cluster of processor cores.

For example, for Gao Tongxiao Dragon processor chip platform Qcom, the game scene selects the oversized core, the processor frequency is boosted to high frequency, the video scene selects the oversized core, and the processor frequency is selected to low frequency. For Pheoda processor chip platform MTK, the game scene selects super large core, the processor frequency is raised to, the video scene selects super large core, and the processor frequency selects intermediate frequency.

In the above embodiment of the present application, the processor parameters include processor cores and processor frequencies, and in determining the processor parameters corresponding to the working scenario according to the processed load information, the processor frequencies of the target cluster processor core and each processor core in the target cluster processor core are determined according to the processed load information, the processor type, the scenario type and the performance information of each cluster processor core by using the target model. Therefore, the task scene is subjected to processor scheduling by utilizing the target model, and the intelligence, the comprehensiveness and the accuracy of the processor scheduling are improved.

In the embodiment of the present application, before S108, the above method for scheduling resources may specifically further include S124 to S132 as follows:

S124, acquiring a first corresponding relation between the task scene of the first type, the task load and the core configuration information.

Wherein the first type is a game scene.

Specifically, in the resource scheduling method provided by the embodiment of the present application, for different task scenes of a first type, a first corresponding relationship between each task scene and task load and core configuration information is obtained, as shown in the following table 1.

TABLE 1 load and core configuration mapping table for game task scenarios

S126, acquiring a second corresponding relation between the task scene of the second type, the task load and the core configuration information.

Wherein the second type is a non-game scene.

Specifically, in the resource scheduling method provided by the embodiment of the present application, for different task scenarios of a second type, a second corresponding relationship between each task scenario and task load and core configuration information is obtained, as shown in table 2 below.

TABLE 2 load and core configuration mapping table for non-game task scenarios

S128, obtaining a third corresponding relation between a third type of task scene, task load and core configuration information.

Wherein the third type is a multi-tasking scenario in which a game scenario is combined with a non-game scenario.

Specifically, in the resource scheduling method provided by the embodiment of the present application, for different task scenarios of a third type, a third corresponding relationship between each group of task scenarios and task load and core configuration information is obtained, as shown in the following table 3.

TABLE 3 load and core configuration mapping table for multitasking scenarios

For example, as shown in fig. 6, the electronic device is currently a multitasking scenario for a game-voice call, i.e., a user plays a game through the electronic device while making a voice call. For a game scene, if the processor chip platform is Qcom, the processor core selects an oversized core, and the processor frequency selects high frequency, and if the processor chip platform is MTK, the processor core selects the oversized core, and the processor frequency selects high frequency. For a voice call scene, if the processor chip platform is Qcom, the processor core selects an oversized core, and the processor frequency selects a low frequency, and if the processor chip platform is MTK, the processor core selects an oversized core, and the processor frequency selects an intermediate frequency.

S130, training a target model according to the first corresponding relation, the second corresponding relation and the third corresponding relation.

Specifically, in the resource scheduling method provided by the embodiment of the application, learning and training are performed on the target model based on the acquired first corresponding relation, second corresponding relation and third corresponding relation, so as to obtain a trained target model. In this way, as shown in fig. 5, 7 and 12, for different game scenes, non-game scenes and multi-task scenes, the target model learns the task load and core configuration information of each task scene, and the target model can intelligently schedule the processor for each task scene while endowing the target model with task scene perception recognition capability.

And S132, updating the trained target model according to feedback information of the electronic equipment on each task scene.

As shown in fig. 12, the feedback information may be specifically determined by a stuck condition, a frame dropping condition, a heating condition, and a power consumption condition of the electronic device in the process of running the task scene.

Specifically, in the resource scheduling method provided by the embodiment of the application, in the process of scene sensing and processor scheduling based on the target model, the running condition of the electronic equipment is monitored, if the electronic equipment has the phenomena of clamping, heating, frame dropping or power consumption abnormality and the like, the feedback information of the electronic equipment on the task scene is obtained based on the running condition of the electronic equipment, and the learning and training are continuously carried out on the target model according to the feedback information. The target model is repeatedly updated, and the scheduling performance and the resource allocation performance of the target model for processors of different task scenes are improved.

Further, in the process of running the task scene by the electronic device, if the electronic device has the phenomenon of clamping and heating, the target model also performs corresponding frequency modulation processing and/or core modulation processing, specifically, the current processor core and processor frequency of the task scene can be adjusted based on the core modulation and frequency modulation strategy shown in the following table 4, and the configuration critical value can be adjusted.

TABLE 4 Nuclear frequency modulation policy table for the phenomenon of stuck and heating

For example, a heating phenomenon occurs in the process of running a game-video multitasking scene by the electronic device, and if the processor chip platform is MTK and the current processor core configuration condition of the electronic device is that for the game scene, the processor core selects a super large core, the processor frequency selects a high frequency, and for the video scene, the processor core selects a super large core, and the processor frequency selects a medium frequency. At this time, the strategy of tuning the core is that for a game scene, the processor core selects a super-large core and the processor frequency selects a low frequency, and for a video scene, the processor core selects a large core and the processor frequency selects a low frequency.

According to the embodiment of the application, the target model is utilized, a first corresponding relation between a first type of task scene and task load and core configuration information is acquired before the working scene of the electronic equipment is identified according to interface information and operation information of the electronic equipment, a second corresponding relation between a second type of task scene and task load and core configuration information is acquired, a third corresponding relation between a third type of task scene and task load and core configuration information is acquired, the target model is trained according to the first corresponding relation, the second corresponding relation and the third corresponding relation, and the trained target model is updated according to feedback information of the electronic equipment to each task scene. Therefore, the target model scene perception capability and the intelligent scheduling capability of the processor can be given, and the intelligence, the comprehensiveness and the accuracy of the processor scheduling are improved.

In the embodiment of the present application, after S106, the method for scheduling resources may specifically further include S134:

S134, according to feedback information of the electronic equipment processing working scene, updating load characteristic information of the working scene.

Specifically, in the resource scheduling method provided by the embodiment of the application, the running condition of the electronic equipment is also monitored in the process of processing the working scene by the electronic equipment. On the basis, as shown in fig. 2, if the electronic equipment has the phenomena of clamping and heating, based on the running condition of the electronic equipment, acquiring feedback information of the electronic equipment for processing the working scene, and updating the load characteristic information of the working scene according to the feedback information so as to improve the accuracy of the subsequent scheduling of the processor based on the load characteristic information.

According to the embodiment of the application, after the processor parameters corresponding to the working scene are determined according to the processed load information, the load characteristic information of the working scene is updated according to the feedback information of the electronic equipment processing the working scene. Thus, the accuracy of the subsequent processor scheduling based on the load characteristic information is improved.

In summary, the present application provides a resource scheduling optimization scheme integrating scene awareness identification and customized schedulers, as shown in fig. 2, the task scene is directly identified through the capability of an OS agent awareness module, a key task scene is identified based on user intention, load characteristic information of the identified task scene is obtained, load prediction is performed based on the load characteristic information, frequency modulation and core selection are performed on a game scene by combining a customized sche_ext scheduler, frequency modulation and core selection are performed on a non-game scene by combining a CFS scheduler or a VIP scheduler, scheduling capability with high degree of freedom is provided, performance and energy efficiency are both realized, both the game scene and the non-game scene can be released with better processor performance and energy efficiency, and a scheduling policy is decoupled from a traditional kernel scheduling policy.

That is, the resource scheduling optimization scheme provided by the application merges an agent-aware regularized scene load recognition mechanism and has the capability of a scheduler for customizing a game scene. Based on the resource scheduling optimization scheme, the task scene identification is more intelligent, flexible, efficient and extensive, the task scene identification is more intelligent, the code processing is not dependent on fixing a specific task scene any more, the current end-side model capacity is utilized to realize the perception identification of the task scene, the method is more efficient and practical, the capacity application is more flexible and wide, the method is not limited to identifying a small number of task scenes, and the time-consuming and labor-consuming manual specific processing is not relied on.

Further, compared with the CFS scheduling strategy, the method has the advantages that the performance and the energy efficiency of the chip are low and the coupling degree is high due to the defects that the game scene cannot be distinguished from the non-game scene and the intention of the user cannot be identified. The application is based on the scheduling strategy of the game scene customization scheduler, decouples the problem of CFS scheduling strategy, can better match the load of task scenes, and better solves the problems of excessive performance waste, high energy consumption and the like of the chip platform due to the capability of customizing the sinking drive to the chip platform.

According to the resource scheduling method provided by the embodiment of the application, the execution main body can be a resource scheduling system. In the embodiment of the application, the resource scheduling system executes the resource scheduling method by taking the resource scheduling system as an example, and the resource scheduling system provided by the embodiment of the application is described.

As shown in FIG. 13, an embodiment of the present application provides a resource scheduling system 500 that may include a kernel layer 506 and a hardware layer 510 described below. Wherein the kernel layer 506 includes a load decision module 508.

The kernel layer 506 comprises a load decision module 508, wherein the load decision module 508 is used for determining load information of a working scene of the electronic device according to load characteristic information and service quality information of the working scene;

The load decision module 508 is further configured to transmit load information to a scheduler corresponding to the working scenario for processing;

And the hardware layer 510 is configured to determine processor parameters corresponding to the working scenario according to the processed load information.

The resource scheduling system 500 provided by the embodiment of the application determines the load information of the working scene according to the load characteristic information and the service quality information of the working scene of the electronic equipment, transmits the load information to a scheduler corresponding to the working scene for processing, and determines the processor parameters corresponding to the working scene according to the processed load information. Through the resource scheduling system 500, the load information of the working scene is predicted based on the load characteristic information and the service quality information of the working scene of the electronic device, and the corresponding scheduler is selected to process the load information, and then the processor parameters required by the working scene are scheduled based on the processed load information. Therefore, load information is predicted and resource scheduling is carried out based on relevant information of a working scene, manual debugging is not needed, and the intelligence, the comprehensiveness and the accuracy of processor scheduling are improved.

In the embodiment of the present application, as shown in fig. 13, the resource scheduling system 500 further includes an application layer 502, including a scene awareness engine module 504, where the scene awareness engine module 504 is configured to identify a working scene of the electronic device according to interface information and operation information of the electronic device by using a target model, and the scene awareness engine module 504 is further configured to obtain load feature information of the working scene.

In the embodiment of the application, the scene perception engine module 504 is specifically configured to intercept a display interface of the electronic device by using the target model, and perform interface recognition on the display interface to obtain an interface recognition result, obtain an operation load and operation core information of the electronic device, and determine a working scene of the electronic device according to the interface recognition result, the operation load and the operation core information.

According to the embodiment of the application, in the process of identifying the working scene of the electronic equipment according to the interface information and the operation information of the electronic equipment by utilizing the target model, the display interface of the electronic equipment is intercepted by utilizing the target model, the interface identification is carried out on the display interface to obtain the interface identification result, the operation load and the operation core information of the electronic equipment are obtained, and the working scene of the electronic equipment is determined according to the interface identification result, the operation load and the operation core information. Therefore, based on the screen capturing recognition capability of the target model, the working scene of the electronic equipment is recognized by combining the operation load and the operation core information of the electronic equipment, without relying on manual debugging, the intelligence of scene recognition is improved, and based on the target model, most of task scenes and key task scenes can be recognized, and the comprehensiveness and the accuracy of scene recognition are improved.

In the embodiment of the present application, the scene perception engine module 504 is specifically configured to intercept a target model to identify an interface of a display interface, determine an interface element in the display interface, determine a target area or a target element in the display interface according to the position information and semantic information of the interface element, and determine an interface identification result according to the target area or the target element.

In the embodiment of the application, the load decision module 508 is specifically configured to transmit load information of a game scene to the first scheduler for processing when the work scene includes the game scene, and transmit load information of a non-game scene to the second scheduler for processing when the work scene includes the non-game scene, wherein the first scheduler is an expandable scheduler, and a scheduling policy of the first scheduler is determined according to load feature information of the game scene.

In the embodiment of the application, the load decision module 508 is specifically configured to determine core configuration information according to game scenario and load information, determine processor characteristic information according to the core configuration information, and determine interface driving information of the processor according to the processor characteristic information.

In the embodiment of the present application, the processor parameters include processor cores and processor frequencies, and the hardware layer 510 is specifically configured to determine, by using the target model, the target cluster processor core and the processor frequencies of each of the target cluster processor cores according to the processed load information, the processor type, the scene type, and the performance information of each cluster of the processor cores.

In the above embodiment of the present application, the processor parameters include processor cores and processor frequencies, and in determining the processor parameters corresponding to the working scenario according to the processed load information, the processor frequencies of the target cluster processor core and each processor core in the target cluster processor core are determined according to the processed load information, the processor type, the scenario type and the performance information of each cluster processor core by using the target model. Therefore, the task scene is subjected to processor scheduling based on the target model, and the intelligence, the comprehensiveness and the accuracy of the processor scheduling are improved.

In the embodiment of the application, the scene perception engine module 504 is further used for acquiring a first corresponding relation between a first type of task scene and task load and core configuration information, acquiring a second corresponding relation between a second type of task scene and task load and core configuration information, acquiring a third corresponding relation between a third type of task scene and task load and core configuration information, training the target model according to the first corresponding relation, the second corresponding relation and the third corresponding relation, and updating the trained target model according to feedback information of the electronic equipment to each task scene.

In the embodiment of the present application, after determining the processor parameters corresponding to the working scenario according to the processed load information, the scenario awareness engine module 504 is further configured to update the load feature information of the working scenario according to the feedback information of the electronic device processing the working scenario.

The resource scheduling system 500 in the embodiment of the present application may be an electronic device, or may be a component in an electronic device, such as an integrated circuit or a chip. The electronic device may be a terminal, or may be other devices than a terminal. The electronic device may be a Mobile phone, a tablet computer, a notebook computer, a palm computer, a vehicle-mounted electronic device, a Mobile internet appliance (Mobile INTERNET DEVICE, MID), an augmented reality (augmented reality, AR)/Virtual Reality (VR) device, a robot, a wearable device, an ultra-Mobile personal computer (UMPC), a netbook or a Personal Digital Assistant (PDA), etc., and may also be a server, a network attached storage (Network Attached Storage, NAS), a personal computer (personal computer, PC), a Television (TV), a teller machine, a self-service machine, etc., which are not particularly limited in the embodiments of the present application.

The resource scheduling system 500 in the embodiment of the present application may be a device having an operating system. The operating system may be an Android operating system, an iOS operating system, or other possible operating systems, and the embodiment of the present application is not limited specifically.

The resource scheduling system 500 provided in the embodiment of the present application can implement each process implemented by the method embodiment of fig. 1, and in order to avoid repetition, a description is omitted here.

Optionally, as shown in fig. 14, the embodiment of the present application further provides an electronic device 600, including a processor 602 and a memory 604, where the memory 604 stores a program or an instruction that can be executed on the processor 602, and the program or the instruction implements each step of the above-mentioned resource scheduling method embodiment when executed by the processor 602, and the steps achieve the same technical effects, so that repetition is avoided, and no further description is given here.

The electronic device in the embodiment of the application includes the mobile electronic device and the non-mobile electronic device.

Fig. 15 is a schematic hardware structure of an electronic device implementing an embodiment of the present application.

The electronic device 700 includes, but is not limited to, a radio frequency unit 701, a network module 702, an audio output unit 703, an input unit 704, a sensor 705, a display unit 706, a user input unit 707, an interface unit 708, a memory 709, and a processor 710.

Those skilled in the art will appreciate that the electronic device 700 may also include a power source (e.g., a battery) for powering the various components, which may be logically connected to the processor 710 via a power management system so as to perform functions such as managing charge, discharge, and power consumption via the power management system. The electronic device structure shown in fig. 15 does not constitute a limitation of the electronic device, and the electronic device may include more or less components than those shown in the drawings, or may combine some components, or may be arranged in different components, which will not be described in detail herein.

The processor 710 is configured to determine load information of a working scenario according to load feature information and service quality information of the working scenario of the electronic device.

The processor 710 is further configured to transmit the load information to a scheduler corresponding to the working scenario for processing.

The processor 710 is further configured to determine a processor parameter corresponding to the working scenario according to the processed load information.

In the embodiment of the application, the load information of the working scene is determined according to the load characteristic information and the service quality information of the working scene of the electronic equipment, the load information is transmitted to the dispatcher corresponding to the working scene for processing, and the processor parameters corresponding to the working scene are determined according to the processed load information. In the embodiment of the application, the load characteristic information and the service quality information of the working scene of the electronic equipment are based, the load information of the working scene is predicted, the corresponding dispatcher is selected to process the load information, and then the processor parameters required by the working scene are dispatched based on the processed load information. Therefore, load information is predicted and resource scheduling is carried out based on relevant information of a working scene, manual debugging is not needed, and the intelligence, the comprehensiveness and the accuracy of processor scheduling are improved.

Optionally, the processor 710 is further configured to identify a working scenario of the electronic device according to the interface information and the operation information of the electronic device by using the target model, and acquire load feature information of the working scenario.

Optionally, the processor 710 is specifically configured to intercept a display interface of the electronic device by using the target model, and perform interface recognition on the display interface to obtain an interface recognition result, obtain an operation load and operation core information of the electronic device, and determine a working scenario of the electronic device according to the interface recognition result, the operation load and the operation core information.

Optionally, the processor 710 is specifically configured to intercept, through a target model, an interface identification performed on the display interface, determine an interface element in the display interface, determine a target area or a target element in the display interface according to the position information and semantic information of the interface element, and determine an interface identification result according to the target area or the target element.

Optionally, the processor 710 is specifically configured to transmit load information of a game scenario to a first scheduler for processing if the work scenario includes the game scenario, and transmit load information of a non-game scenario to a second scheduler for processing if the work scenario includes the non-game scenario, where the first scheduler is an expandable scheduler, and a scheduling policy of the first scheduler is determined according to load feature information of the game scenario.

Optionally, the processor 710 is specifically configured to determine core configuration information according to the game scenario and the load information, determine processor characteristic information according to the core configuration information, and determine interface driving information of the processor according to the processor characteristic information.

Optionally, the processor 710 is specifically configured to determine, using the target model, a target cluster processor core and a processor frequency of each of the target cluster processor cores based on the processed load information, the processor type, the scene type, and the performance information of each cluster of processor cores.

In the above embodiment of the present application, in determining the processor parameters corresponding to the working scenario according to the processed load information, the target model is used to determine the processor core of the target cluster and the processor frequency of each processor core in the target cluster according to the processed load information, the processor type, the scenario type and the performance information of each cluster of processor cores. Therefore, the task scene is subjected to processor scheduling based on the target model, and the intelligence, the comprehensiveness and the accuracy of the processor scheduling are improved.

Optionally, before identifying the working scenario of the electronic device according to the interface information and the operation information of the electronic device by using the target model, the processor 710 is further configured to obtain a first corresponding relationship between the task scenario of the first type and the task load, and between the task scenario of the second type and the core configuration information, obtain a third corresponding relationship between the task scenario of the third type and the task load, and between the task scenario of the third type and the core configuration information, train the target model according to the first corresponding relationship, the second corresponding relationship, and the third corresponding relationship, and update the trained target model according to feedback information of the electronic device to each task scenario.

Optionally, after determining the processor parameters corresponding to the working scenario according to the processed load information, the processor 710 is further configured to update the load feature information of the working scenario according to feedback information of the electronic device processing the working scenario.

It should be appreciated that in embodiments of the present application, the input unit 704 may include a graphics processor (Graphics Processing Unit, GPU) 7041 and a microphone 7042, with the graphics processor 7041 processing image data of still pictures or video obtained by an image capturing device (e.g., a camera) in a video capturing mode or an image capturing mode. The display unit 706 may include a display panel 7061, and the display panel 7061 may be configured in the form of a liquid crystal display, an organic light emitting diode, or the like. The user input unit 707 includes at least one of a touch panel 7071 and other input devices 7072. The touch panel 7071 is also referred to as a touch screen. The touch panel 7071 may include two parts, a touch detection device and a touch controller. Other input devices 7072 may include, but are not limited to, a physical keyboard, function keys (e.g., volume control keys, switch keys, etc.), a trackball, a mouse, a joystick, and so forth, which are not described in detail herein.

The memory 709 may be used to store software programs as well as various data. The memory 709 may mainly include a first storage area storing programs or instructions and a second storage area storing data, wherein the first storage area may store an operating system, application programs or instructions (such as a sound playing function, an image playing function, etc.) required for at least one function, and the like. Further, the memory 709 may include volatile memory or nonvolatile memory, or the memory 709 may include both volatile and nonvolatile memory. The nonvolatile Memory may be a Read-Only Memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an Electrically Erasable EPROM (EEPROM), or a flash Memory. The volatile memory may be random access memory (Random Access Memory, RAM), static random access memory (STATIC RAM, SRAM), dynamic random access memory (DYNAMIC RAM, DRAM), synchronous Dynamic Random Access Memory (SDRAM), double data rate Synchronous dynamic random access memory (Double DATA RATE SDRAM, DDRSDRAM), enhanced Synchronous dynamic random access memory (ENHANCED SDRAM, ESDRAM), synchronous link dynamic random access memory (SYNCH LINK DRAM, SLDRAM), and Direct random access memory (DRRAM). Memory 709 in embodiments of the application includes, but is not limited to, these and any other suitable types of memory.

Processor 710 may include one or more processing units and, optionally, processor 710 integrates an application processor that primarily processes operations involving an operating system, user interface, application programs, etc., and a modem processor that primarily processes wireless communication signals, such as a baseband processor. It will be appreciated that the modem processor described above may not be integrated into the processor 710.

The embodiment of the application also provides a readable storage medium, and the readable storage medium stores a program or an instruction, which when executed by a processor, implements each process of the above-mentioned resource scheduling method embodiment, and can achieve the same technical effect, so that repetition is avoided, and no further description is provided here.

The processor is a processor in the electronic device in the above embodiment. Readable storage media include computer readable storage media such as computer readable memory ROM, random access memory RAM, magnetic or optical disks, and the like.

The embodiment of the application further provides a chip, the chip comprises a processor and a communication interface, the communication interface is coupled with the processor, the processor is used for running programs or instructions, the processes of the resource scheduling method embodiment can be realized, the same technical effects can be achieved, and the repetition is avoided, and the description is omitted here.

It should be understood that the chips referred to in the embodiments of the present application may also be referred to as system-on-chip chips, chip systems, or system-on-chip chips, etc.

Embodiments of the present application provide a computer program product stored in a storage medium, where the program product is executed by at least one processor to implement the respective processes of the above-described resource scheduling method embodiment, and achieve the same technical effects, and for avoiding repetition, a detailed description is omitted herein.

It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element. Furthermore, it should be noted that the scope of the methods and apparatus in the embodiments of the present application is not limited to performing the functions in the order shown or discussed, but may also include performing the functions in a substantially simultaneous manner or in an opposite order depending on the functions involved, e.g., the described methods may be performed in an order different from that described, and various steps may be added, omitted, or combined. Additionally, features described with reference to certain examples may be combined in other examples.

From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in part in the form of a computer software product stored on a storage medium (e.g. ROM/RAM, magnetic disk, optical disk) comprising instructions for causing a terminal (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method of the embodiments of the present application.

The embodiments of the present application have been described above with reference to the accompanying drawings, but the present application is not limited to the above-described embodiments, which are merely illustrative and not restrictive, and many forms may be made by those having ordinary skill in the art without departing from the spirit of the present application and the scope of the claims, which are to be protected by the present application.

Claims

1. A method for scheduling resources, comprising:

according to load characteristic information and service quality information of a working scene of the electronic equipment, determining load information of the working scene;

transmitting the load information to a scheduler corresponding to the working scene for processing;

And determining processor parameters corresponding to the working scene according to the processed load information.

2. The method for scheduling resources according to claim 1, wherein before determining the load information of the working scenario according to the load characteristic information and the service quality information of the working scenario of the electronic device, the method for scheduling resources further comprises:

Identifying a working scene of the electronic equipment according to interface information and operation information of the electronic equipment by utilizing a target model;

And acquiring the load characteristic information of the working scene.

3. The resource scheduling method according to claim 2, wherein the identifying, by using the target model, the operation scenario of the electronic device according to the interface information and the operation information of the electronic device includes:

intercepting a display interface of the electronic equipment by using the target model, and carrying out interface identification on the display interface to obtain an interface identification result;

Acquiring the operation load and the operation core information of the electronic equipment;

And determining the working scene of the electronic equipment according to the interface identification result, the operation load and the operation core information.

4. The resource scheduling method according to claim 1, wherein the delivering the load information to the scheduler corresponding to the working scenario for processing includes:

Transmitting load information of the game scene to a first scheduler for processing under the condition that the working scene comprises the game scene;

In the case that the working scene comprises a non-game scene, transmitting load information of the non-game scene to a second scheduler for processing;

The first scheduler is an extensible scheduler, and the scheduling strategy of the first scheduler is determined according to load characteristic information of a game scene.

5. The method for scheduling resources according to claim 4, wherein said transferring load information of said game scenario to a first scheduler for processing comprises:

Determining core configuration information according to the game scene and the load information;

determining processor characteristic information according to the core configuration information;

And determining interface driving information of the processor according to the processor characteristic information.

6. The resource scheduling method according to claim 2, wherein the processor parameters include a processor core and a processor frequency, and the determining the processor parameters corresponding to the operating scenario according to the processed load information includes:

And determining the processor core of the target cluster and the processor frequency of each processor core in the target cluster according to the processed load information, the processed processor type, the processed scene type and the processed performance information of each cluster of processor cores by utilizing the target model.

7. The resource scheduling method according to claim 2, wherein before the identifying the operating scenario of the electronic device according to the interface information and the operation information of the electronic device by using the target model, the resource scheduling method further comprises:

acquiring a first corresponding relation between a first type of task scene, a task load and core configuration information;

Acquiring a second corresponding relation between a second type of task scene, task load and core configuration information;

acquiring a third corresponding relation between a third type of task scene, task load and core configuration information;

Training the target model according to the first corresponding relation, the second corresponding relation and the third corresponding relation;

and updating the trained target model according to the feedback information of the electronic equipment on each task scene.

8. A resource scheduling system, comprising:

The kernel layer comprises a load decision module, wherein the load decision module is used for determining load information of a working scene of the electronic equipment according to load characteristic information and service quality information of the working scene;

the load decision module is further used for transmitting the load information to a scheduler corresponding to the working scene for processing;

and the hardware layer is used for determining the processor parameters corresponding to the working scene according to the processed load information.

9. The resource scheduling system of claim 8, further comprising:

the application layer comprises a scene perception engine module, wherein the scene perception engine module is used for identifying the working scene of the electronic equipment according to the interface information and the operation information of the electronic equipment by utilizing the target model;

The scene perception engine module is further used for acquiring the load characteristic information of the working scene.

10. The resource scheduling system of claim 9, wherein the context awareness engine module is specifically configured to:

11. The resource scheduling system of claim 8, wherein the load decision module is specifically configured to:

12. The resource scheduling system of claim 11, wherein the load decision module is specifically configured to:

13. The resource scheduling system of claim 9, wherein the processor parameters include a processor core and a processor frequency, the hardware layer being specifically configured to:

14. The resource scheduling system of claim 9, wherein the scene-aware engine module is further configured to:

15. An electronic device comprising a processor and a memory storing a program or instructions executable on the processor, which when executed by the processor, implement the steps of the resource scheduling method of any one of claims 1 to 7.