WO2021212657A1 - Procédé et dispositif de planification de tâches entre un terminal et un serveur, et planificateur - Google Patents

Procédé et dispositif de planification de tâches entre un terminal et un serveur, et planificateur Download PDF

Info

Publication number
WO2021212657A1
WO2021212657A1 PCT/CN2020/098913 CN2020098913W WO2021212657A1 WO 2021212657 A1 WO2021212657 A1 WO 2021212657A1 CN 2020098913 W CN2020098913 W CN 2020098913W WO 2021212657 A1 WO2021212657 A1 WO 2021212657A1
Authority
WO
WIPO (PCT)
Prior art keywords
task
server
allocated
tasks
time
Prior art date
Application number
PCT/CN2020/098913
Other languages
English (en)
Chinese (zh)
Inventor
程超楠
郭倜颖
刘伟超
陈远旭
刘明亮
Original Assignee
平安科技（深圳）有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 平安科技（深圳）有限公司 filed Critical 平安科技（深圳）有限公司
Publication of WO2021212657A1 publication Critical patent/WO2021212657A1/fr

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
    • G06F9/48—Program initiating; Program switching, e.g. by interrupt
    • G06F9/4806—Task transfer initiation or dispatching
    • G06F9/4843—Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
    • G06F9/4881—Scheduling strategies for dispatcher, e.g. round robin, multi-level priority queues
    • 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
    • G06F9/5038—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 considering the execution order of a plurality of tasks, e.g. taking priority or time dependency constraints into consideration

Definitions

  • This application relates to the field of artificial intelligence, in particular to a task scheduling method, device and scheduler between a terminal and a server.
  • the task generated by the terminal exceeds the computing capacity of the terminal itself or/and the edge node, the task can be sent to the server for processing.
  • the server When there are multiple terminals and multiple servers, and various tasks generated by different terminals have different priority requirements, it is necessary to schedule multiple tasks and assign servers to execute for each task.
  • the inventor found that when new tasks are constantly being generated and network conditions and server computing resources are also changing in real time, if tasks are not scheduled in a timely and reasonable manner, server resources may not be used reasonably and tasks with higher priority may be caused. In the backlog of tasks, it cannot be processed in time.
  • the main purpose of this application is to provide a task scheduling method, device, and scheduler between the terminal and the server, which aims to solve the problem that the server resources are not reasonably used during the task processing between the terminal and the server, and the tasks with higher priority are in a backlog. Problems that cannot be dealt with in a timely manner in the task.
  • this application proposes a task scheduling method between a terminal and a server, which includes:
  • the task to be allocated is removed from the task linked list containing the task to be allocated.
  • This application also provides a task scheduling device between a terminal and a server, including:
  • a receiving unit configured to receive multiple tasks sent by the terminal
  • Establishing a sorting unit configured to establish a task linked list for each of the terminals, and sort the tasks sent by the terminal in real time in the task linked list according to a preset priority order;
  • An obtaining and sorting unit configured to obtain the foremost task in each of the task linked lists, and sort the foremost tasks according to a preset priority order, and obtain the task with the highest priority as the task to be assigned;
  • a computing allocation unit configured to allocate servers for the tasks to be allocated according to the computing capabilities, task transmission time, and currently available resources of each of the servers;
  • the removing unit is used to remove the task to be allocated from the task linked list containing the task to be allocated.
  • the present application also provides a scheduler, including a memory and a processor, the memory stores a computer program, and when the processor executes the computer program, a method for scheduling tasks between a terminal and a server is implemented.
  • the method includes the following step:
  • the task to be allocated is removed from the task linked list containing the task to be allocated.
  • the present application also provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, a method for scheduling tasks between a terminal and a server is implemented.
  • the method includes the following steps:
  • the task to be allocated is removed from the task linked list containing the task to be allocated.
  • FIG. 1 is a schematic flowchart of a task scheduling method between a terminal and a server according to an embodiment of the application;
  • FIG. 2 is a schematic block diagram of the structure of a task scheduling device between a terminal and a server according to an embodiment of the application;
  • FIG. 3 is a schematic block diagram of the structure of a scheduler according to an embodiment of the application.
  • an embodiment of the present application provides a task scheduling method between a terminal and a server, including the steps:
  • the execution subject of the above method can be a scheduler, which is a transit device with data processing capabilities, and generally includes a processor, a memory, a wireless receiver, a wireless transmitter, etc. Realize tasks such as receiving, processing, and sending functions.
  • the aforementioned scheduler predefines different task types, and presets different priority attributes for different types of tasks.
  • the terminal is a mobile terminal, more specifically, the terminal is an autonomous vehicle, the server is a cloud server, and the task types include, but are not limited to, human-vehicle recognition, voice interaction, Offline map downloading, etc., among them, the human-vehicle recognition task is set as the highest priority, the voice interaction task is set as the lower priority, and the offline map download task is set as the lower priority.
  • the scheduler receives tasks sent by multiple terminals and establishes a task linked list for each terminal. According to a preset priority order, tasks with high priority are located at the front end of the task linked list, and tasks with low priority are located at the back end of the task linked list.
  • the scheduler receives the task sent by the terminal in real time, and inserts the new task into the corresponding position in the task chain according to the above rules.
  • a scheduler can serve multiple terminals at the same time, so a task linked list corresponding to each terminal is established for each connected terminal, and the task linked list records the tasks uploaded by the corresponding terminal.
  • the above-mentioned front-end task refers to the task with the highest priority in the task chain.
  • the scheduler allocates tasks, it sorts the front-end tasks in all the task chains and selects the task with the highest priority. One task is to be assigned. In other words, the scheduler sends tasks one by one when sending tasks to the server. It first obtains the front-end tasks in all the task linked lists, and then selects the highest priority tasks among the front-end tasks and sends them to the server first.
  • the scheduler needs to select the most suitable server. So what kind of server is the right server? In a specific embodiment, it is determined after the comparison of each server. The content of the comparison is the computing power, task transmission time, and current available resources of each server. In theory, the computing power is the strongest, the task transmission time is the shortest, and the current The server with the most available resources is the most suitable.
  • the aforementioned preset priority order is: a task with a lower delay tolerance has a higher priority, and for multiple tasks with the same delay tolerance, a task with an earlier sending time has a higher priority.
  • the task with low delay tolerance is the task with higher urgency. Set it to the higher priority.
  • the scheduler places the task with the lowest delay tolerance at the end of the list in the task list, and then tolerates it according to the delay.
  • the other tasks are arranged in order of increasing degree. For multiple tasks with the same delay tolerance, the task with the earlier sending time is set as the higher priority, and the task is processed first.
  • step S4 of allocating servers for the tasks to be allocated according to the computing capabilities, task transmission time and currently available resources of each of the servers includes:
  • the transmission bandwidth and computing capacity of each server can be obtained in advance by the scheduler, the current available resources of each server can be reported to the scheduler in real time by the server, and the data volume of the task to be allocated is obtained when the scheduler receives the task .
  • the scheduler first performs the first round of screening: selecting the first server that can run the current task.
  • a second round of screening is performed on each first server: the first server with the smallest sum of the transmission time of the first task and the running time of the first task is selected, and the tasks to be allocated are assigned to this server.
  • the task data size of the task X to be allocated is Sx
  • the scheduler compares the task data amount Sx with the current available resources of each server, and filters out multiple first servers Ej that can run the current task.
  • the scheduler and The transmission bandwidth between the first servers Ej is Vj
  • the computing power of the first server Ej is Pj
  • the sum of the transmission time and running time of task X Tx Txj+T'xj
  • the scheduler Calculate the Tx of each first server Ej, select the first server with the smallest Tx, and send task X to the server.
  • the method further includes:
  • the scheduler first performs the first round of screening: After each server is filtered out to run the task with the most recent end time, its available resources can run the second server to which the task is to be allocated.
  • the resources occupied by the task with the most recent end time in each server and the currently available resources of the server can be reported to the scheduler by the server in real time, or obtained from the server by the scheduler.
  • the task is acquired when it is received.
  • the scheduler can filter out the second server.
  • a second round of screening is performed on each second server: the second server with the smallest sum of the task waiting time, the second task transmission time, and the second task running time is selected.
  • the task waiting time is the time at which the task with the closest end time in each second server has finished running, and can be calculated by subtracting the current time from the end time of the task with the closest end time in each second server; the second task transmission time
  • the calculation method of the running time with the second task is as described in the previous embodiment.
  • the scheduler assigns the task to the second server with the smallest sum of the task waiting time, the second task transmission time, and the second task running time, and sends the task to the waiting list of the server.
  • the foregoing step S46 of allocating the task to be allocated to the waiting list of the second server with the smallest sum of the task waiting time, the second task transmission time, and the second task running time After that include:
  • the terminal is notified of the task waiting time after obtaining the task waiting time, so that the user of the terminal can take countermeasures according to specific conditions, such as continuing to wait or cancel the task.
  • the step of obtaining the front-most tasks in each of the task linked lists, and sorting the front-most tasks according to a preset priority order, and obtaining the task with the highest priority as the task to be assigned Before S3, including:
  • the task linked list is sent to the idle scheduler. After the processing by the processor, the processed task processing result is forwarded to the corresponding terminal.
  • the above-mentioned first preset quantity and the second preset quantity may be the same or different, and are mainly related to the hardware processing of the scheduler.
  • the neighboring scheduler when the number of tasks in a certain task list is greater than the third preset number, query whether the neighboring scheduler is in an idle state, where the idle state refers to the ability to process more tasks such as scheduling ; If yes, split the certain task list to make the number of tasks in the certain task list less than or equal to the third preset number, and at the same time send the other part to the neighboring scheduler in the idle state, and A corresponding task linked list is formed in the neighboring scheduler, and the neighboring scheduler performs scheduling processing.
  • the method includes:
  • the step of obtaining the front-most tasks in each of the task linked lists, and sorting the front-most tasks according to a preset priority order, and obtaining the task with the highest priority as the task to be assigned Before S3, including:
  • the task scheduling method between the terminal and the server of the present application allocates servers reasonably to provide computing services for the terminal. According to the priority of the tasks generated in real time by multiple terminals, the real-time status of the current network and server resources, the server is assigned to the task to ensure that the urgent tasks are processed to the greatest extent, so as to make full use of the computing resources of the server, reduce the waiting time of the task, and improve user experience.
  • this application also provides a task scheduling device between a terminal and a server, including:
  • the receiving unit 10 is configured to receive multiple tasks sent by the terminal;
  • the establishment ordering unit 20 is configured to establish a task linked list for each of the terminals, in which the tasks sent by the terminal are sorted in real time according to a preset priority order in the task linked list;
  • the obtaining and sorting unit 30 is configured to obtain the front-most tasks in each of the task linked lists, and sort the front-most tasks according to a preset priority order, and obtain the task with the highest priority as the task to be assigned;
  • the calculation allocation unit 40 is configured to allocate servers for the tasks to be allocated according to the calculation capabilities, task transmission time, and currently available resources of each of the servers;
  • the removing unit 50 is configured to remove the task to be allocated from the task linked list containing the task to be allocated.
  • the foregoing calculation and distribution unit 40 includes:
  • the first screening module is configured to screen the first server that can run the task to be assigned according to the currently available resources of each of the servers;
  • the first calculation module is configured to calculate the first task transmission time required for the task to be allocated to the first server according to the transmission bandwidth of the first server and the data volume of the task to be allocated, and according to the Computing capacity of the first server and the amount of data of the task to be allocated, calculating the running time of the first task of the task to be allocated on the first server;
  • the first allocation module is configured to allocate the task to be allocated to the first server with the smallest sum of the transmission time of the first task and the running time of the first task.
  • the foregoing calculation and distribution unit 40 further includes:
  • the second brush selection module is used to if the first server that can run the task to be assigned is not currently available, according to the resources occupied by the task with the closest end time among the tasks currently running on each server, and the current availability of each server Resources, filter the second server that can run the task to be assigned after the task with the most recent end time is completed;
  • the second calculation module is configured to calculate the task waiting time required by the second server according to the end time of the task with the closest end time; and according to the transmission bandwidth of the second server and the data of the task to be allocated Calculate the second task transmission time required by the task to be allocated to the second server, and calculate the task to be allocated in each of the Running time of the second task of the second server;
  • the second allocation module is configured to allocate the task to be allocated to the waiting list of the second server with the smallest sum of the task waiting time, the second task transmission time, and the second task running time.
  • calculation and distribution unit 40 further includes:
  • the sending reminder module is used to send the task waiting time information to the terminal corresponding to the task to be assigned.
  • the above-mentioned task scheduling device between the terminal and the server further includes:
  • the query unit is configured to query the number of task linked lists of the neighboring scheduler when the number of all the task linked lists exceeds the first preset number
  • a sending scheduling unit configured to send task linked lists exceeding the first preset number to the neighboring scheduler for scheduling processing if the number of task linked lists of the neighboring scheduler is lower than the second preset number;
  • the feedback forwarding unit is configured to receive the task processing result sent back by the neighboring scheduler, and send the task processing result to the corresponding terminal.
  • the above-mentioned task scheduling device between the terminal and the server further includes:
  • the viewing unit is used to check whether there are overtime tasks whose remaining waiting time exceeds a preset threshold in the task waiting list in each server when all tasks in the task chain list are processed;
  • the execution unit is configured to, if there is a timeout task whose remaining waiting time exceeds a preset threshold in the task waiting list, establish a timeout task linked list corresponding to the timeout task, and transfer the timeout task into the timeout task linked list.
  • the above-mentioned task scheduling device between the terminal and the server further includes:
  • the upgrading unit is configured to increase the priority of the delayed task when there is a delayed task that exceeds the preset time limit and has not been processed in the task linked list.
  • the units and modules in the foregoing embodiments are devices corresponding to the foregoing method embodiments, and are not described here.
  • an embodiment of the present application also provides a scheduler, and the internal structure of the scheduler may be as shown in FIG. 3.
  • the scheduler includes a processor, a memory, a network interface, and a database connected through a system bus.
  • the processor designed by the computer is used to provide calculation and control capabilities.
  • the memory of the scheduler includes a non-volatile storage medium and an internal memory.
  • the non-volatile storage medium stores an operating system, a computer program, and a database.
  • the memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium.
  • the scheduler's database is used to store data such as task linked lists.
  • the network interface of the scheduler is used to communicate with external terminals through a network connection.
  • the computer program is executed by the processor to realize a task scheduling method between the terminal and the server.
  • the processor executes the task scheduling method between the terminal and the server, including the steps of: receiving tasks sent by a plurality of the terminals; establishing a task linked list for each of the terminals, and in the task linked list according to a preset priority Sort the tasks sent by the terminal in real time in order of level; obtain the front-end tasks in each of the task linked lists, and sort the front-end tasks according to the preset priority order to obtain the task with the highest priority As a task to be assigned; assign a server for the task to be assigned according to the computing capacity, task transmission time and currently available resources of each server; remove the task to be assigned from the task link list containing the task to be assigned.
  • the step of allocating servers for the tasks to be allocated according to the computing capabilities, task transmission time, and currently available resources of each of the servers includes:
  • the task to be allocated is allocated to the first server with the smallest sum of the transmission time of the first task and the running time of the first task.
  • the method further includes:
  • the first server that can run the task to be assigned If the first server that can run the task to be assigned is not currently available, filter the most recent end time based on the resources occupied by the task with the closest end time among the tasks running on each server and the currently available resources of each server After the task is completed, the second server that can run the task to be assigned;
  • the second task transmission time required to the second server is calculated based on the computing capacity of the second server and the data volume of the task to be allocated to calculate the second task of the task to be allocated in each of the second servers operation hours;
  • the task to be allocated is allocated to the waiting list of the second server with the smallest sum of the task waiting time, the second task transmission time, and the second task running time.
  • the step of allocating the task to be allocated to the waiting list of the second server with the smallest sum of the task waiting time, the second task transmission time, and the second task running time After that include:
  • said acquiring the front-most tasks in each of the task linked lists, and sorting the front-most tasks according to a preset priority order, and acquiring the task with the highest priority as the task to be assigned Before the steps include:
  • the method includes:
  • said acquiring the front-most tasks in each of the task linked lists, and sorting the front-most tasks according to a preset priority order, and acquiring the task with the highest priority as the task to be assigned Before the steps include:
  • the priority of the delayed task is increased.
  • FIG. 3 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the scheduler to which the solution of the present application is applied.
  • the embodiments of the present application also provide a computer-readable storage medium.
  • the computer-readable storage medium may be non-volatile or volatile.
  • a computer program is stored thereon, and the computer program is executed by a processor.
  • a method for scheduling tasks between a terminal and a server described above includes receiving multiple tasks sent by the terminal;
  • the task to be allocated is removed from the task linked list containing the task to be allocated.
  • the step of allocating servers for the tasks to be allocated according to the computing capabilities, task transmission time, and currently available resources of each of the servers includes:
  • the task to be allocated is allocated to the first server with the smallest sum of the transmission time of the first task and the running time of the first task.
  • the method further includes:
  • the first server that can run the task to be assigned If the first server that can run the task to be assigned is not currently available, filter the most recent end time based on the resources occupied by the task with the closest end time among the tasks running on each server and the currently available resources of each server After the task is completed, the second server that can run the task to be assigned;
  • the second task transmission time required to the second server is calculated based on the computing capacity of the second server and the data volume of the task to be allocated to calculate the second task of the task to be allocated in each of the second servers operation hours;
  • the task to be allocated is allocated to the waiting list of the second server with the smallest sum of the task waiting time, the second task transmission time, and the second task running time.
  • the step of allocating the task to be allocated to the waiting list of the second server with the smallest sum of the task waiting time, the second task transmission time, and the second task running time After that include:
  • said acquiring the front-most tasks in each of the task linked lists, and sorting the front-most tasks according to a preset priority order, and acquiring the task with the highest priority as the task to be assigned Before the steps include:
  • the method includes:
  • said acquiring the front-most tasks in each of the task linked lists, and sorting the front-most tasks according to a preset priority order, and acquiring the task with the highest priority as the task to be assigned Before the steps include:
  • the priority of the delayed task is increased.
  • Non-volatile memory may include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory.
  • Volatile memory may include random access memory (RAM) or external cache memory.
  • RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual-rate data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Software Systems (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Computer And Data Communications (AREA)

Abstract

La présente invention se rapporte au domaine de l'intelligence artificielle, et concerne un procédé et un dispositif de planification de tâches entre un terminal et un serveur, et un planificateur. Le procédé consiste à : recevoir des tâches envoyées par une pluralité de terminaux ; établir une liste liée à une tâche pour chaque terminal, et trier, en temps réel dans la liste liée à une tâche selon une séquence de priorité prédéfinie, des tâches envoyées par le terminal ; obtenir des tâches aux extrémités les plus hautes dans les listes liées aux tâches, trier les tâches au niveau des extrémités supérieures selon une séquence de priorité prédéfinie, et obtenir une tâche ayant la priorité la plus élevée en tant que tâche à attribuer ; en fonction de la puissance de calcul, des temps de transmission des tâches et des ressources disponibles actuelles des serveurs, attribuer un serveur à la tâche à attribuer; et l'élimination, à partir de la liste liée à des tâches contenant la tâche à attribuer, de la tâche à attribuer. Dans la présente invention, des serveurs sont raisonnablement répartis pour fournir des services informatiques pour des terminaux, et une tâche d'urgence est traitée en priorité; ainsi, des ressources de calcul de serveurs sont pleinement utilisées, le temps d'attente de tâche est réduit, et l'expérience d'utilisateur est améliorée.
PCT/CN2020/098913 2020-04-24 2020-06-29 Procédé et dispositif de planification de tâches entre un terminal et un serveur, et planificateur WO2021212657A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202010334967.9A CN111651246A (zh) 2020-04-24 2020-04-24 终端和服务器之间的任务调度方法、装置和调度器
CN202010334967.9 2020-04-24

Publications (1)

Publication Number Publication Date
WO2021212657A1 true WO2021212657A1 (fr) 2021-10-28

Family

ID=72343957

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/098913 WO2021212657A1 (fr) 2020-04-24 2020-06-29 Procédé et dispositif de planification de tâches entre un terminal et un serveur, et planificateur

Country Status (2)

Country Link
CN (1) CN111651246A (fr)
WO (1) WO2021212657A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117093345A (zh) * 2023-09-05 2023-11-21 上海合芯数字科技有限公司 任务链表的执行方法、装置、终端设备及存储介质
WO2024000533A1 (fr) * 2022-06-30 2024-01-04 北京小米移动软件有限公司 Procédé et appareil de gestion d'application d'intelligence artificielle, et dispositif de communication

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112153138A (zh) * 2020-09-23 2020-12-29 杭州迪普科技股份有限公司 一种流量调度的方法及装置、电子设备、存储介质
CN112150029A (zh) * 2020-10-09 2020-12-29 浙江专线宝网阔物联科技有限公司 一种支持动态与分散任务分配的区块链弹性架构设计方法
CN112749012B (zh) * 2021-01-15 2024-05-28 北京智芯微电子科技有限公司 终端设备的数据处理方法、装置、系统及存储介质
CN114205160B (zh) * 2021-12-13 2024-05-28 深圳前海微众银行股份有限公司 基于区块链的数据处理方法、装置及电子设备
CN115344487A (zh) * 2022-08-12 2022-11-15 虹软科技股份有限公司 一种算法测试方法、装置和存储介质
CN117992208A (zh) * 2022-11-01 2024-05-07 华为技术有限公司 任务管理方法、装置、系统、通信设备及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104035818A (zh) * 2013-03-04 2014-09-10 腾讯科技（深圳）有限公司 多任务调度的方法及装置
US20150121387A1 (en) * 2013-10-30 2015-04-30 Mediatek Inc. Task scheduling method for dispatching tasks based on computing power of different processor cores in heterogeneous multi-core system and related non-transitory computer readable medium
CN105897837A (zh) * 2015-12-07 2016-08-24 乐视云计算有限公司 内容分发任务的提交方法及系统
CN107291545A (zh) * 2017-08-07 2017-10-24 星环信息科技（上海）有限公司 计算集群中多用户的任务调度方法及设备

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104035818A (zh) * 2013-03-04 2014-09-10 腾讯科技（深圳）有限公司 多任务调度的方法及装置
US20150121387A1 (en) * 2013-10-30 2015-04-30 Mediatek Inc. Task scheduling method for dispatching tasks based on computing power of different processor cores in heterogeneous multi-core system and related non-transitory computer readable medium
CN105897837A (zh) * 2015-12-07 2016-08-24 乐视云计算有限公司 内容分发任务的提交方法及系统
CN107291545A (zh) * 2017-08-07 2017-10-24 星环信息科技（上海）有限公司 计算集群中多用户的任务调度方法及设备

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024000533A1 (fr) * 2022-06-30 2024-01-04 北京小米移动软件有限公司 Procédé et appareil de gestion d'application d'intelligence artificielle, et dispositif de communication
CN117093345A (zh) * 2023-09-05 2023-11-21 上海合芯数字科技有限公司 任务链表的执行方法、装置、终端设备及存储介质
CN117093345B (zh) * 2023-09-05 2024-05-07 上海合芯数字科技有限公司 任务链表的执行方法、装置、终端设备及存储介质

Also Published As

Publication number Publication date
CN111651246A (zh) 2020-09-11

Similar Documents

Publication Publication Date Title
WO2021212657A1 (fr) Procédé et dispositif de planification de tâches entre un terminal et un serveur, et planificateur
CN109618002B (zh) 一种微服务网关优化方法、装置及存储介质
US8023637B2 (en) Method and system for hierarchy based contact routing
CN102131297B (zh) 上行资源分配方法和设备
WO2017041492A1 (fr) Procédé et dispositif d'attribution de ressource, et support de stockage lisible par ordinateur
CN110087324B (zh) 资源分配方法、装置、接入网设备和存储介质
CN112214319B (zh) 一种计算资源感知的任务调度方法
CN109802895B (zh) 数据处理系统、方法及令牌管理方法
CN111176840B (zh) 分布式任务的分配优化方法和装置、存储介质及电子装置
CN109743751B (zh) 无线接入网的资源分配方法及装置
CN114007225A (zh) Bwp的分配方法、装置、电子设备及计算机可读存储介质
CN104184514A (zh) 一种用于卫星网络的带宽分配方法
CN103346980A (zh) 一种业务调度方法、装置及网络设备
CN111030945A (zh) 容灾方法、容灾网关、存储介质、装置以及系统
CN111901881B (zh) 一种传输方法及装置
CN115103450A (zh) 一种多业务时隙分配方法和设备
EP1478133B1 (fr) Ordonnanceur à précédence préemptif pour liaisons de communications à large bande
CN113038401A (zh) 差异化资源调度方法、装置、计算设备及计算机存储介质
CN112188500A (zh) 一种频谱资源动态分配方法及装置
CN116074260A (zh) 一种电力网络中业务切片调度编排方法
EP3925243B1 (fr) Procédé de planification semi-persistante à contrainte de qos de communications de type machine dans des réseaux cellulaires
CN111586880A (zh) 适用于tdma的动态混合接入方法及系统
CN113381885B (zh) 一种用于动态调整业务带宽的方法及系统
G∤ ąbowski et al. Simulation studies of communication systems with mutual overflows and threshold mechanisms
CN113891392B (zh) 拥塞控制方法、装置、设备及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20932262

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 20932262

Country of ref document: EP

Kind code of ref document: A1