237 results about "Task number" patented technology

The invention provides a distributed computing resource allocation system and a task processing method. The distributed computing resource allocation system comprises a central server and a plurality of node servers. The central server is used for receiving video image tasks sent by a user and allocating the video image tasks to corresponding node servers through central ends of computing units based on the types of the video image tasks as well as the current task number and load conditions of the node servers. The node servers are used for processing the video image tasks through node ends of the computing units corresponding to the video image tasks. According to the distributed computing resource allocation system and the task processing method provided by the invention, different types of video image tasks can be processed by using multiple servers of one server cluster, and the utilization rate of the server cluster can be increased.

The invention relates to a solution for multiple mobile robot path conflict based on dense storage regions. The technical scheme of the solution comprises steps of (1), establishing an initialized mesh path image by dispatching a server; (2), detecting a cargo access task and dividing the task into a plurality of sub-tasks; (3), outputting task paths of current sub-tasks by using an image search method; (4), determining whether target points of sub-tasks are released by a last task; (5), marking all task paths by using task numbers; (6), returning to the step (2) after marking all task paths; (7), seizing resource variables through all tasks in a task executing queue; (8), dividing conflict regions; (9) determining whether conflict regions are released completely; (10), sending a task execution command to a mobile robot; and (11) returning to the step (7) after releasing resource variables to the server. The solution has the advantages of being reasonable in design, capable of distributing tasks at any time, planning tasks at any time and avoiding conflict at any time, high in accuracy, simple in calculation and practical.

The invention discloses a task unloading method for a deep learning application in an edge computing environment, and the method comprises the steps: firstly dividing a deep neural network into a plurality of model blocks, collecting related data in a system, and analyzing corresponding features; taking the obtained characteristic data as an input parameter, establishing an M/M/n queuing model, and obtaining expectation of the average task number of a terminal device layer and an edge server layer, and expectation of task completion time when the task starts to be executed on the terminal device and the task is directly unloaded to the edge server to start to be executed; taking the two expected minimum and maximum values as a target function, and constructing an optimization model for minimizing task execution time; and solving the optimization model by using a heuristic algorithm to obtain an optimal unloading scheme. According to the method, a multi-mode and fine-grained personalized task unloading scheme can be provided for different deep learning applications, the task completion time is minimized, and the resource utilization rate of the terminal equipment is improved, so that the application requirements of high precision and low delay are met.

The invention discloses a task scheduling method and a task scheduling system, relates to the technical field of network communication, and is used for solving the problem of low task scheduling efficiency. The task scheduling method comprises the following steps of receiving a task completion message transmitted by an operating platform by a scheduling server through a message bus, updating the task states of a current task and a subsequent task of the current task; acquiring ready tasks, grouping the ready tasks according to task types, and sequencing the ready tasks in each group according to static priority; acquiring a maximum concurrency number, a ready task number and a task-in-operation number of each task type; adjusting the maximum concurrency number of each task type through the maximum concurrency number, the ready task number and the task-in-operation number of each task type, distributing the ready tasks of each task type to respective operating platform for operating according to the sequence of the ready tasks in each group until the task-in-operation number of each task type reaches the maximum concurrency number of the respective task type. The scheme provided by the invention is applicable to task scheduling.

The invention relates to a task scheduling method in a multi-core DSP system. A shared task pool is established in a shared memory in the multi-core DSP system, tasks are input into the task pool, the tasks are firstly classified into two categories of time-related and non-time-related, then each task is carried out the numbering, the time-related tasks have the same serial number, the non-time-related tasks are independently carried out the numbering, the initial states of the tasks with the different serial numbers are set as the non-locked states; and a task obtaining device of each idle slave core carries out the inquiry to the shared task pool and carries out the processing of the task after obtaining the task. The task scheduling method changes the technical proposal of using a main core for distributing tasks by the traditional multi-core DSP system and adopts the method of using the slave cores to actively obtain the tasks during the idle time, which can effectively reduce the requirements on the reliability of priori knowledge and reduce the load balance of the multi-core system.

The invention relates to an RDF data storage and query method combined with star figure coding. The RDF data storage and query method comprises the steps that S1, RDF data are preprocessed, and the RDF data are presented in an RDF data map mode; S2, an input SPARQL query statement is presented in an SPARQL query graph mode, and query decomposition is carried out; S3, the SPARQL query statement is preprocessed, and the task number of whole query, the connecting sequence of query star sub-nodes and relevant information of the query star sub-nodes are obtained; S4, the SPARQL query statement is executed, query connection planning is carried out, a Map Reduce parallel computation frame of Hadoop is adopted, and the number of times of starting a query task Job is decided according to the relevance of the SPARQL query statement; S5, subgraph query is carried out, and a Map function is adopted; S6, a result connecting algorithm is carried out, and a Reduce function is adopted. Due to the fact that a Hash coding index query strategy based on star configuration is adopted, stored data redundancy and the number of query tasks are reduced, and query efficiency is improved.

The invention relates to a task scheduling technology in a network downloading system. The technical problem that the invention aims to solve is to provide a network downloading method for a downloading system to automatically conduct downloading task scheduling. The network downloading method of the invention is added with technical measures of downloading task number limitation, downloading-speed detection, downloading task PRI, downloading mode mutex, error processing mechanism, and the like which ensure that the invention can more effectively use the network resource to more rapidly download content resource, and is applicable to various multi-mode multi-task network downloading systems.

The invention discloses a parallel recovery method of a main memory database, which comprises the following steps: a. logs are imported in a buffer memory by adopting a plurality of tasks and are read in parallel by a log system, and the tasks for reading the logs reorganize the logs by a certain protocols in a memory according to a sequence in the original log file; b. the log sequence is distributed to a plurality of queues by a distribution module by an equally loaded algorithm, and the distribution work abides by two rules of log synchronization; c. a plurality of tasks in parallel execute the log recovery, acquire logs from respective corresponding queues and then execute the log recovery, and a plurality of log recovery tasks abide by the two rules of the log synchronization. The method adopts a scheduling algorithm of importing tasks, a scheduling algorithm of in parallel recovering tasks, an equally loaded algorithm of recovering tasks and a balance algorithm of self-adaption of log file import task number and recovery task number, and can realize the quick recovery of the main memory database.

The invention discloses a RFID (Radio Frequency Identification)-based AGV (Automatic Guided Vehicle) multi-task positioning method. The method comprises the following steps: card writing: carrying out unique numbering on each guidepost radio frequency card; task association: according to an AGV task, planning a corresponding path, and writing a function code corresponding to each station on the path into the radio frequency card; task distribution: sending the function code in the step 2 and the corresponding ID of the function code to a controller, storing the function code into EEPOM (Electrically Erasable Programmable Read-Only Memory) space which is distributed in advance according to a corresponding task number by the controller, and recording and storing by utilizing an address variable; and task guidepost matching: copying a task list of the task number disclosed by the EEPOM space to a SRAM (Static Random Access Memory) temporary task buffer area, inquiring the guidepost number of the radio frequency card in fixed time when the AGV operates, uniting the guidepost number and the task number after the guidepost number is obtained, finding a unique function code matched with a set matching algorithm according to the set matching algorithm in the task buffer area, and finally finishing setting action according to the function code.

A microcomputer includes a bus, a CPU coupled to the bus, a trace data generating circuit coupled to the bus to output trace data of a process executed by the CPU at an output node, a memory coupled to the output node of the trace data generating circuit to store the trace data, a first register coupled to the bus to store a task number indicative of a task being executed by the CPU, and a control unit coupled to the first register to control on/off of outputting of the trace data from the trace data generating circuit in response to the task number.

The invention vigorously supports a process of allocating tasks numbering several thousand to units numbering several hundred and allows a streamlined task assignment to be obtained in a short time. The computer system of the invention comprises the following: Task list storing memory 2 stores, on a by-task basis, task times, and task location within a product. Unit list storing memory 4 stores, on a by-unit basis, tasks allocated to the unit and task order within the unit. Walking time calculation means 6 calculates walking time of a worker from the task order within the unit and task location within the product. Task assignment visual display screen displaying means 8 displays a visual display screens about task assignment in which task times and walking times are displayed along the Y-axis in accordance with the task order within a unit at a location corresponding to the unit on the screen in which the units are arranged along the X-axis. Sifting means 30 allows a planner to designate and shift a certain task in the task assignment visual display screen. Updating means 32 updates the contents stored in the unit list storing means 4 in accordance with the result of shift by the shifting means 30.

The invention relates to a client, a signaling tracking server, a protocol module and a signaling tracking method. The signaling tracking server comprises a task node establishing unit, a tracking request message sending unit and a response message processing unit, wherein the task node establishing unit is used for generating a task number corresponding to a tracking request message received fromthe client, filling in the task number, the protocol type, a client identifier and a tracking condition list in an idle task node, and setting the task node to be the use state, and the tracking condition list comprises a tracking condition and a protocol module identifier which are associated mutually; the tracking request message sending unit is used for sending the tracking request message with preset format to the protocol module, and the tracking request message with preset format comprises the task number, the protocol type and the tracking condition; and the response message processingunit is used for responding a tracking request response message received from the protocol module to the client, and the tracking request response message comprises the task number and the symbol ofthe tracking whether is successfully established or not. The invention can improve the reusage and the maintenance of codes.

The invention discloses a material tray warehousing method and system guaranteeing accurate material receiving by an automatic guided vehicle. The material tray warehousing method comprises the steps that when the automatic guided vehicle arrives at a material receiving platform and gets ready for fetching materials, a material receiving information verification request is sent to a warehouse dispatching platform; the warehouse dispatching platform acquires the current index number Index l of the automatic guided vehicle and searches for the corresponding predistribution transfer task number task 1 according to the index number Index l; the warehouse dispatching platform compares the task 1 and a current transfer task number task 2 provided by an electric control unit, wherein the task 2 is the transfer task number corresponding to a material container on the material receiving platform currently; if the task 1 is equal to the task 2, the warehouse dispatching platform sends a verification success instruction to the automatic navigation trolley; the automatic guided vehicle continues to receive the materials and transfer the material container to a target position. According to the material tray warehousing method and system guaranteeing accurate material receiving by the automatic guided vehicle, it is guaranteed that the AGV does not receive the material incorrectly in the material receiving process, an extra guarantee is provided for conformance between system record information and reality after the container is warehoused, and therefore production quality accidents caused by container warehousing dislocation can be avoided as far as possible.

The invention discloses a data center energy consumption management method and system based on dynamic frequency modulation. The method comprises frequency modulation energy conservation of a single server and task scheduling of energy awareness among servers, wherein the frequency modulation energy conservation of the single server comprises the steps of taking a time quantum of a constant task number as a frequency modulation unit, estimating dissipative energy of each unit according to an energy consumption model and task information, and utilizing a heuristic algorithm to select a frequency modulation mode which enables the sum of energy consumption of all units to be minimum so as to adjust the frequency of a processor; the task scheduling of energy awareness among the servers comprises the steps of selecting a candidate server according to the state of each server and the task information when a task reaches, utilizing a frequency modulation energy conservation method on the single server by each server according the task information to estimate the energy consumption change, selecting the server with the minimum energy consumption change by a controller to distribute a new task, and utilizing the frequency modulation energy conservation method on the single server by the selected server to modulate the frequency and operate the new task. According to the invention, the energy consumption of the servers in a data center is reduced by frequency modulation and task distribution, and energy saving and emission reduction effects are achieved.

The invention discloses a multi-core CPU video transcoding scheduling method, which belongs to the field of video transcoding. Before a scheduling scheme is implemented, a static pressure test is carried out for a transcoding server in order to measure the maximum concurrent transcoding task number of a single CPU core; the scheduling scheme is started; the number of currently executed tasks of all the CPU cores is initialized as 0; if a new transcoding task arrives, then scheduling is carried out according to an allocation and scheduling method for new tasks; if a transcoding task is stopped, then scheduling is carried out according to an allocation and scheduling method for existing tasks; if a message for stopping all transcoding tasks is received, then a program is closed, and otherwise, the method rejudges whether a new transcoding task arrives, and carries out circular processing. The invention ensures that the transcoding tasks can be operated in the same CPU core to the greatest extent, thus effectively increasing the hit rate of the CPU cache and the operation efficiency of the system, and moreover, the loads of all the CPU cores can be balanced to the greatest extent.

The invention discloses an automation equipment communication method based on a CAN bus. The communication method is based on a CAN bus protocol, and an application layer protocol employs a CAN data frame with an expansion frame format. An arbitration domain comprises a priority identification domain, a source address domain, a target address domain, a source task number domain and a target task number domain. The communication method comprises the following steps that the CAN data frame sent by a sender via the CAN bus is received; priority of the CAN data frame is acquired; whether the priority of the CAN data frame is the highest priority is judged; if the judgment result is yes, data interaction is performed between the CAN data frame and a CAN application communication layer via a high-speed communication mode; and if the judgment result is no, the CAN data frame is sent to a queue with the corresponding priority, and data interaction is performed between the CAN data frame and the CAN application communication layer via an information queue mode. According to the automation equipment communication method based on the CAN bus, real-time and multitask processing can be performed on a data message.

Systems and methods are disclosed for generating a program executed by a central processing apparatus for assigning instructions of the program. The systems and methods may include dividing the program into a plurality of instruction sequences, each instruction sequence comprising a plurality of instructions not executable in parallel because of data dependency. In addition, the systems and methods may include moving an instruction sequence speculatively executable forward an instruction sequence not speculatively executable in the program and aligning the plurality of instruction sequences in correspondence with each of the plurality of buffers. Moreover, the systems and methods may include assigning a task number representing the instruction sequence and a corresponding buffer to each instruction and replacing a condition instruction by a commit instruction, the commit instruction including a condition, task numbers to be accepted if the condition is not satisfied and task numbers to be rejected if the condition is satisfied.