CN116467059A - Data processing system and method based on distributed computing - Google Patents
Data processing system and method based on distributed computing Download PDFInfo
- Publication number
- CN116467059A CN116467059A CN202310430673.XA CN202310430673A CN116467059A CN 116467059 A CN116467059 A CN 116467059A CN 202310430673 A CN202310430673 A CN 202310430673A CN 116467059 A CN116467059 A CN 116467059A
- Authority
- CN
- China
- Prior art keywords
- state
- execution
- execution unit
- task
- value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000012545 processing Methods 0.000 title claims abstract description 70
- 238000000034 method Methods 0.000 title claims abstract description 34
- 230000002159 abnormal effect Effects 0.000 claims abstract description 24
- 230000008569 process Effects 0.000 claims abstract description 10
- 238000006073 displacement reaction Methods 0.000 claims description 26
- 230000008859 change Effects 0.000 claims description 9
- 238000013500 data storage Methods 0.000 claims description 9
- 238000007726 management method Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 238000003672 processing method Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 3
- 241000699666 Mus <mouse, genus> Species 0.000 description 19
- 230000009471 action Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 241000699670 Mus sp. Species 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000630 rising effect Effects 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
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
-
- 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]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5066—Algorithms for mapping a plurality of inter-dependent sub-tasks onto a plurality of physical CPUs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/48—Indexing scheme relating to G06F9/48
- G06F2209/484—Precedence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/50—Indexing scheme relating to G06F9/50
- G06F2209/5021—Priority
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Debugging And Monitoring (AREA)
Abstract
The invention discloses a data processing system and method based on distributed computing, and belongs to the technical field of distributed task scheduling. The method can adjust the states of all execution units in the service range in real time, wherein the states comprise an offline state, an idle state, a busy state and an abnormal state; calculating a corresponding state value according to the efficiency of the execution unit to execute the task; during the business processing process: firstly, dividing a service into different types of subtasks including an active task and a passive task according to an execution mode; secondly, the active task is submitted to an execution unit with an offline state for execution; finally, dividing the passive tasks into sub-tasks with different priorities according to service requirements, and sequentially delivering the sub-tasks with idle states and higher state values to an execution unit for execution according to the high-low order of the priorities; the invention can more efficiently complete distributed task scheduling and processing by splitting the service and setting the state of the execution unit and matching with each other.
Description
Technical Field
The invention relates to the technical field of distributed task scheduling, in particular to a data processing system and method based on distributed computing.
Background
With the rapid development of technologies such as cloud computing, big data and artificial intelligence, the conventional single computer computing cannot meet the requirement of large-scale data processing. Distributed computing is a novel computing mode, and can effectively solve the problems faced by large-scale data processing. In distributed computing, a plurality of computers work cooperatively to finish complex data processing tasks together, so that the efficiency and speed of data processing are greatly improved.
In distributed computing, task scheduling is a very complex task that requires consideration of many factors, such as: splitting subtasks of a service, distributing subtasks with different priorities, executing modes, coordinating and matching among executing units and the like. How to split the service reasonably, distribute reasonably according to different conditions of the execution unit, schedule reasonably at the first time when the execution unit is in a state, improve the execution efficiency of the service to the maximum extent, and fully exert the performance of distributed computation is a very important topic, and a scheduling method with reasonable design is required to ensure the efficient execution of the service in practical application.
Disclosure of Invention
The present invention is directed to a data processing system and method based on distributed computing, so as to solve the problems set forth in the background art.
In order to solve the technical problems, the invention provides the following technical scheme: a distributed computing-based data processing system, the system comprising: the system comprises a data acquisition module, a data processing module, a function calling module and a data storage module.
The data acquisition module is used for acquiring weight information, image information and input information of all execution objects in the service range and sending the information to the data processing module. The data processing module sets the state of the corresponding execution unit according to the weight information, the image information and the input information of the execution object, calculates the state value of the corresponding execution unit according to the input information of the execution object, allocates different types of tasks to the execution units in different states, and allocates tasks with different priorities to the execution units in different state values. The function calling module is used for calling the weight sensor, the camera and the test software. The data storage module is used for carrying out backup storage on all the information.
The data acquisition module comprises a weight information acquisition unit, an image information acquisition unit and an input information acquisition unit.
The weight information acquisition unit is used for acquiring weight information of an execution object, weight information is collected through a weight sensor arranged in an area where the execution unit is located, and when the execution object leaves or enters the area where the corresponding execution unit is located, the weight information changes.
The image information acquisition unit is used for acquiring image information of an execution object, the image information is collected through a camera installed in an area where the execution unit is located, and when the execution object is located in the area where the corresponding execution unit is located, the camera can shoot the execution object.
The input information acquisition unit is used for acquiring input information of an execution object and detecting whether an execution unit corresponding to the execution object is allocated with a task or not, and the input information is collected through test software installed on a computer controlled by the execution object, wherein the input information comprises a mouse displacement speed, a keyboard input speed, a task processing speed and time from the last execution of the task.
When input information is collected, average values of continuous displacement speed of a plurality of mice and multi-keyboard knocking speed are collected in a period of time, and influence caused by instantaneous speed is reduced.
The data processing module comprises a state management unit, a state value calculation unit and a task allocation unit.
The state management unit is used for managing the states of all execution units in the service range, and changing the states of the corresponding execution units according to the weight information, the image information and the input information of different execution objects. The states of the execution unit include offline state, idle state, busy state, and abnormal state, and the state change includes: from offline to idle, from idle to busy, from busy to idle, from busy to abnormal, and from idle to offline.
The off-line state refers to a state that an execution object temporarily leaves an area where an execution unit is located, in the state, only a computer is working, an active task can be sent to the computer, the active task can be automatically executed and responded by the computer, and idle resources of the computer are fully utilized.
The idle state refers to a state that an execution object is in an area corresponding to an execution unit but is not allocated with tasks, in this state, both a person and a computer wait for task allocation, and a passive task with a proper priority can be allocated to a state value of the execution unit.
The busy state refers to a state that an execution object is in an area corresponding to an execution unit and is allocated with a task, in the state, both a person and a computer are executing the task, test software can be called to collect working time efficiency information, and a state value of the execution unit is analyzed and calculated.
The abnormal state is a state that a value execution object is not in an area corresponding to an execution unit and is assigned with a task, in the state, no person operates a computer to execute the task, the state can seriously delay the whole service execution time, even cause irrecoverable results, the staff should be immediately warned to timely process, and the abnormal state can be restored to an offline state or an idle state after the processing is completed.
In general, when the acquired weight information is changed greatly, the camera is called to check, and whether the execution object is in the area where the execution unit is located is judged.
When the weight value rises greatly and the execution object is in the area where the execution unit is located, changing the state of the corresponding execution unit from an off-line state to an idle state; when the weight value is greatly reduced and the execution object is not in the area where the execution unit is located, the state of the corresponding execution unit is changed from an idle state to an offline state or from a busy state to an abnormal state.
When the state of the execution unit is an idle state, the test software changes the state of the corresponding execution unit from the idle state to a busy state when detecting the allocated task; when the state of the execution unit is busy, the test software detects that the task is submitted, and the state of the corresponding execution unit is changed from the busy state to the idle state.
The state value calculating unit is used for calculating the state value of the corresponding executing unit, the state value determines the timeliness of executing the task by the corresponding executing unit, and the higher the state value of the corresponding executing unit is, the higher the task executing efficiency is.
The state values of the execution units include a fixed state value and a floating state value. The fixed state value refers to a fixed state value of a corresponding execution unit calculated by substituting the mouse displacement speed, the keyboard input speed and the task processing speed of the execution object into a formula; the floating state value calculating unit needs to consider the time from the executing unit to the last executing task, and correspondingly increases along with the time from the last executing task, and the fixed state value is added with the floating state value to be the state value of the corresponding executing unit.
The task allocation unit is used for carrying out subtask division and scheduling on the service. The business to be processed is divided into different types of subtasks, wherein the subtask types comprise active tasks and passive tasks: the active task is a task which can be identified by a computer and automatically executed and responded, does not need to execute any operation of an object, and is transmitted to an execution unit in an off-line state to be executed; the passive tasks cannot be completely identified by a computer, tasks requiring the coordination operation of the execution object are divided into sub-tasks with different priorities according to different service requirements, the priorities comprise high and low, and the sub-tasks with different priorities in the passive tasks are transmitted to idle state execution units with different state values to be executed; all allocation operations are journaled.
The scheduling of the subtasks is flexibly adjusted according to the field condition, when the execution units in the offline state are insufficient to support all allocation of the active tasks, the execution units in the idle state or the busy state with lower resource utilization rate can be considered to be preferentially selected, the multithreading technology is adopted, and the maximum combination theory utilizes the existing resources under the condition that the normal execution of the tasks by the execution units is not influenced.
The function calling module is used for calling a weight sensor corresponding to the area where the execution unit is located and collecting weight information of an execution object; invoking a camera corresponding to the area where the execution unit is located, and collecting image information of an execution object; and calling test software on a computer for executing object control, and collecting input information of an executing object.
The data storage module is used for storing the acquired information, the state information and the distribution log information into a database for tracing operation.
A data processing method based on distributed computing, the method comprising the steps of:
s1, adjusting the states of all execution units in a service range in real time;
s2, splitting the service into N subtasks, and distributing the N subtasks to different execution units for execution;
s3, scoring the execution unit after the task is completed;
and S4, after the service is completed, returning to the step S1 to continue waiting for the next service.
In S1, the state adjustment procedure for the execution unit is as follows:
s101, acquiring weight information of the area where each execution unit is located through a weight sensor, calculating a difference value between a current acquired weight value and a weight value acquired at the previous moment in real time, judging whether the difference value is in a weight error interval or not, and if the difference value is in the weight error interval, directly entering the step S103 without processing. If the error interval is not found, the corresponding execution unit is marked, and the process goes to step S102.
The setting of the weight error section needs to be performed according to the weight change of the portable object, the weight of the portable object cannot influence the judgment of whether the object exists, and the weight difference between the area where the execution unit is located and the area where the execution unit is not located should not be within the weight error section.
S102, establishing a background image for each execution unit by using a mathematical modeling method, wherein no execution object exists in the background image, starting a corresponding camera to photograph the area where the marked execution unit is located, collecting a current image, subtracting gray values of corresponding pixel points of the two images, and obtaining a difference image after taking an absolute value, wherein the formula is as follows:
Z n (x,y)＝|d n (x,y)-B(x,y)|
wherein Z is n (x, y) is the gray value of the nth pixel point of the differential image, d n (x, y) is the gray value of the nth pixel point of the current image frame, and B (x, y) is the gray value of the corresponding pixel point of the background image。
Setting a threshold value X, and carrying out binarization processing on all pixel points of the differential image to obtain a binarized image, wherein the point with a gray value of 255 is a foreground point, and the point with a gray value of 0 is a background point; the formula is as follows:
in which Q n (X, y) is the gray value of the nth pixel point of the binarized image, X is the threshold value, Z n (x, y) is the gray value of the nth pixel point of the differential image.
For image Q n Performing connectivity analysis, detecting human body contours of the image by using OpenCV, and judging whether an execution object exists in the area where the corresponding execution unit is located: when an execution object exists and the weight difference value is a positive number, the state of an execution unit corresponding to the execution object is adjusted from an offline state to an idle state; when the execution object does not exist and the weight difference value is negative, the state of the execution unit corresponding to the execution object is adjusted from an idle state to an offline state or from a busy state to an abnormal state.
The camera needs to be started after a period of time is set, the minimum time of the camera cannot be lower than the time from the rising of an execution object to the leaving of the area where the corresponding execution unit is located, and the maximum time of the camera cannot be higher than the system task allocation withdrawal time.
S103, judging whether the corresponding execution unit is allocated with tasks through test software installed on a computer controlled by an execution object, wherein the tasks comprise an active task and a passive task, and only the execution unit allocated to the passive task can carry out state change, and the allocation of the passive task only aims at the execution unit with an idle state, so that the state of the execution unit allocated to the passive task is changed from the idle state to a busy state; changing the state of an execution unit, which is detected by test software to be submitted by a task, from a busy state to an idle state; and changing the state of the execution unit, which is detected by the test software that the task is not submitted and no execution object exists in the area where the execution unit is located, from a busy state to an abnormal state.
In S2, the service is split into subtasks and the subtask allocation steps are as follows:
s201, splitting the service to be processed into an active task which can be independently executed and responded by a computer and a passive task which can be completed only by coordination of an executed object according to an execution mode.
S202, the active task is submitted to the execution unit with the offline state for execution.
S203, the passive tasks are continuously divided into sub-tasks with different priorities according to service requirements, and the execution units with idle states and high state values are sequentially handed to execute according to the high-low order of the priorities.
When the execution unit executes the passive task, the weight difference value is changed into a negative number, no execution object exists in the area where the corresponding execution unit is located, the execution object leaves the area where the corresponding execution unit is located, the state of the corresponding execution unit is changed from a busy state to an abnormal state, and workers are warned to process in time.
The splitting number of subtasks needs to be adaptively split according to the traffic and the traffic difficulty, the service splitting number with large traffic and high difficulty is large, the service splitting number with small traffic and low difficulty is small; meanwhile, subtask splitting also needs to refer to the number of execution units in the service range and the time efficiency of executing the tasks by the execution units.
In S3, scoring the execution unit means calculating a state value of the execution unit, where the state value includes a fixed state value and a floating state value; the method comprises the following steps:
s301, firstly, substituting a mouse displacement speed, a keyboard input speed and a task processing speed of an execution object into a formula to calculate a fixed state value of a corresponding execution unit; the formula is as follows:
in ZTZ G For the fixed state value of the execution unit, a is the mouse displacement speed influence factor, V s For recorded mouse displacement speed, R s Is a standard mouseThe displacement speed b is the keyboard input speed influence factor, V J R is the recorded keyboard input speed J Input speed of standard keyboard, c is task processing speed influencing factor, R c For standard task processing speed, V c Processing speed for recorded tasks.
The standard mouse displacement speed and the standard keyboard input speed need to be set by referring to the normal speed of each execution object, and the speeds of different execution objects are different; the standard task processing speed is set according to the task difficulty, and the higher the task difficulty is, the lower the standard task processing speed is set, and the higher the standard task processing speed is.
S302, calculating a floating state value according to the time from the execution unit to the last task execution, summing the fixed state value and the floating state value, and calculating the state value of the execution unit, wherein the formula is as follows:
where ZTZ is the state value of the execution unit, ZTZ G For a fixed state value of the execution unit, d is a floating state value influence coefficient, f t For the time from the last execution of the task, R t Is the standard idle time.
Compared with the prior art, the invention has the following beneficial effects:
1. the invention manages the state of each execution unit, and updates the state information of the execution unit in real time through various sensors and test software, thereby avoiding the situations of task scheduling delay and unreasonable allocation.
2. The invention regulates the state value of each execution unit, and performs task allocation with different priorities according to the working state of the execution object, thereby ensuring the overall timeliness of service execution and avoiding the situation of high-frequency task allocation to the same execution unit.
3. The invention divides the business into the active task and the passive task according to the execution mode, the active task is submitted to the computer to be independently completed, and the passive task is submitted to the person and the computer to be jointly completed, thereby reducing the workload of the person and improving the utilization efficiency of the spare resources of the computer.
4. According to the invention, the change amplitude of the weight information is used as a primary trigger unit, the image detection of the camera is used as a secondary trigger unit, and the camera is started to acquire the image information only when the primary trigger unit is triggered, so that the pressure of a system on image analysis and calculation is reduced, and the monitoring efficiency is improved.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention. In the drawings:
FIG. 1 is a schematic diagram of a distributed computing-based data processing system and method in accordance with the present invention;
FIG. 2 is a flow chart of a distributed computing based data processing system and method of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the present invention provides a data processing system based on distributed computing, the system includes: the system comprises a data acquisition module, a data processing module, a function calling module and a data storage module.
The data acquisition module is used for acquiring weight information, image information and input information of all execution objects in the service range and sending the information to the data processing module. The data processing module sets the state of the corresponding execution unit according to the weight information, the image information and the input information of the execution object, calculates the state value of the corresponding execution unit according to the input information of the execution object, allocates different types of tasks to the execution units in different states, and allocates tasks with different priorities to the execution units in different state values. The function calling module is used for calling the weight sensor, the camera and the test software. The data storage module is used for carrying out backup storage on all the information.
An execution object generally refers to a person operating a computer to perform a task, and an execution unit refers to a minimum unit for performing the task, and generally refers to the computer or the person and the computer; when executing an active task: the minimum unit of the execution task is a computer, and the execution task is independently executed; when executing a passive task: the minimum unit for executing the task is a person and a computer, and the person and the computer cooperate to execute the task.
The data acquisition module comprises a weight information acquisition unit, an image information acquisition unit and an input information acquisition unit.
The weight information acquisition unit is used for acquiring weight information of an execution object, the weight information is acquired through a weight sensor arranged in an area where the execution unit is located, the weight sensor can be arranged below a chair or on the ground where the execution object sits, and when the execution object leaves or enters the area where the corresponding execution unit is located, the weight information acquired by the weight sensor can be obviously changed.
The image information acquisition unit is used for acquiring image information of an execution object, the image information is collected through a camera installed in the area where the execution unit is located, and when the execution object is located in the area where the corresponding execution unit is located, the camera can shoot the execution object.
The input information acquisition unit is used for acquiring input information of an execution object and detecting whether an execution unit corresponding to the execution object is allocated with a task or not, and the input information is collected through test software installed on a computer controlled by the execution object, wherein the input information comprises a mouse displacement speed, a keyboard input speed, a task processing speed and time from the last execution of the task.
When input information is collected, average values of continuous displacement speed of a plurality of mice and multi-keyboard knocking speed are collected in a period of time, and influence caused by instantaneous speed is reduced.
The data processing module comprises a state management unit, a state value calculation unit and a task allocation unit.
The state management unit is used for managing the states of all execution units in the service range, and changing the states of the corresponding execution units according to the weight information, the image information and the input information of different execution objects. The states of the execution unit include offline state, idle state, busy state, and abnormal state, and the state change includes: from offline to idle, from idle to busy, from busy to idle, from busy to abnormal, and from idle to offline.
The off-line state refers to a state that an execution object temporarily leaves an area where an execution unit is located, in the state, only a computer is working, an active task can be sent to the computer, the active task can be automatically executed and responded by the computer, and idle resources of the computer are fully utilized.
The idle state refers to a state that an execution object is in an area corresponding to an execution unit but is not allocated with tasks, in this state, both a person and a computer wait for task allocation, and a passive task with a proper priority can be allocated to a state value of the execution unit.
The busy state refers to a state that an execution object is in an area corresponding to an execution unit and is allocated with a task, in the state, both a person and a computer are executing the task, test software can be called to collect working time efficiency information, and a state value of the execution unit is analyzed and calculated.
The abnormal state is a state that a value execution object is not in an area corresponding to an execution unit and is assigned with a task, in the state, no person operates a computer to execute the task, the state can seriously delay the whole service execution time, even cause irrecoverable results, the staff should be immediately warned to timely process, and the abnormal state can be restored to an offline state or an idle state after the processing is completed.
In general, when the acquired weight information is changed greatly, the camera is called to check, and whether the execution object is in the area where the execution unit is located is judged.
When the weight value rises greatly and the execution object is in the area where the execution unit is located, changing the state of the corresponding execution unit from an off-line state to an idle state; when the weight value is greatly reduced and the execution object is not in the area where the execution unit is located, the state of the corresponding execution unit is changed from an idle state to an offline state or from a busy state to an abnormal state.
When the state of the execution unit is an idle state, the test software changes the state of the corresponding execution unit from the idle state to a busy state when detecting the allocated task; when the state of the execution unit is busy, the test software detects that the task is submitted, and the state of the corresponding execution unit is changed from the busy state to the idle state.
The state value calculating unit is used for calculating the state value of the corresponding executing unit, the state value determines the timeliness of executing the task of the corresponding executing unit, and the higher the state value of the corresponding executing unit is, the higher the task executing efficiency is.
The state values of the execution units include a fixed state value and a floating state value. The fixed state value refers to a fixed state value of a corresponding execution unit calculated by substituting the mouse displacement speed, the keyboard input speed and the task processing speed of the execution object into a formula; the floating state value calculating unit needs to consider the time from the executing unit to the last executing task, and correspondingly increases along with the time from the last executing task, and the fixed state value is added with the floating state value to be the state value of the corresponding executing unit.
The task allocation unit is used for carrying out subtask division and scheduling on the service. The business to be processed is divided into different types of subtasks, wherein the subtask types comprise active tasks and passive tasks: the active task is a task which can be identified by a computer and automatically executed and responded, does not need to execute any operation of an object, and is transmitted to an execution unit in an off-line state to be executed; the passive tasks cannot be completely identified by a computer, tasks requiring the coordination operation of the execution object are divided into sub-tasks with different priorities according to different service requirements, the priorities comprise high and low, and the sub-tasks with different priorities in the passive tasks are transmitted to idle state execution units with different state values to be executed; all allocation operations are journaled.
The scheduling of the subtasks is flexibly adjusted according to the field condition, when the execution units in the offline state are insufficient to support all allocation of the active tasks, the execution units in the idle state or the busy state with lower resource utilization rate can be considered to be preferentially selected, the multithreading technology is adopted, and the maximum combination theory utilizes the existing resources under the condition that the normal execution of the tasks by the execution units is not influenced.
The function calling module is used for calling a weight sensor corresponding to the area where the execution unit is located and collecting weight information of an execution object; invoking a camera corresponding to the area where the execution unit is located, and collecting image information of an execution object; and calling test software on a computer for executing object control, and collecting input information of an executing object.
The data storage module is used for storing the acquired information, the state information and the distribution log information into a database for tracing operation.
Referring to fig. 2, the present invention provides a data processing method based on distributed computing, the method includes the following steps:
s1, adjusting the states of all execution units in a service range in real time;
s2, splitting the service into N subtasks, and distributing the N subtasks to different execution units for execution;
s3, scoring the execution unit after the task is completed;
And S4, after the service is completed, returning to the step S1 to continue waiting for the next service.
In S1, the state adjustment procedure for the execution unit is as follows:
s101, acquiring weight information of the area where each execution unit is located through a weight sensor, calculating a difference value between a current acquired weight value and a weight value acquired at the previous moment in real time, judging whether the difference value is in a weight error interval or not, and if the difference value is in the weight error interval, directly entering the step S103 without processing. If the error interval is not found, the corresponding execution unit is marked, and the process goes to step S102.
The setting of the weight error section needs to be performed according to the weight change of the portable object, the weight of the portable object cannot influence the judgment of whether the object exists, and the weight difference between the area where the execution unit is located and the area where the execution unit is not located should not be within the weight error section.
S102, establishing a background image for each execution unit by using a mathematical modeling method, wherein no execution object exists in the background image, starting a corresponding camera to photograph the area where the marked execution unit is located, collecting a current image, subtracting gray values of corresponding pixel points of the two images, and obtaining a difference image after taking an absolute value, wherein the formula is as follows:
Z n (x,y)＝|d n (x,y)-B(x,y)|
Wherein Z is n (x, y) is the gray value of the nth pixel point of the differential image, d n (x, y) is the gray value of the nth pixel point of the current image frame, and B (x, y) is the gray value of the corresponding pixel point of the background image.
Setting a threshold value X, and carrying out binarization processing on all pixel points of the differential image to obtain a binarized image, wherein the point with a gray value of 255 is a foreground point, and the point with a gray value of 0 is a background point; the formula is as follows:
in which Q n (X, y) is the gray value of the nth pixel point of the binarized image, X is the threshold value, Z n (x, y) is the gray value of the nth pixel point of the differential image.
For image Q n Performing connectivity analysis, detecting human body contours of the image by using OpenCV, and judging whether an execution object exists in the area where the corresponding execution unit is located: when an execution object exists and the weight difference value is a positive number, the state of an execution unit corresponding to the execution object is adjusted from an offline state to an idle state; when no execution object exists and the weight difference value is negative, the state of the execution unit corresponding to the execution object is adjusted from the idle stateIs offline or is adjusted to an abnormal state from a busy state.
The camera needs to be started after a period of time is set, the minimum time of the camera cannot be lower than the time from the rising of an execution object to the leaving of the area where the corresponding execution unit is located, and the maximum time of the camera cannot be higher than the system task allocation withdrawal time.
S103, judging whether the corresponding execution unit is allocated with tasks through test software installed on a computer controlled by an execution object, wherein the tasks comprise an active task and a passive task, and only the execution unit allocated to the passive task can carry out state change, and the allocation of the passive task only aims at the execution unit with an idle state, so that the state of the execution unit allocated to the passive task is changed from the idle state to a busy state; changing the state of an execution unit, which is detected by test software to be submitted by a task, from a busy state to an idle state; and changing the state of the execution unit, which is detected by the test software that the task is not submitted and no execution object exists in the area where the execution unit is located, from a busy state to an abnormal state.
In S2, the service is split into subtasks and the subtask allocation steps are as follows:
s201, splitting the service to be processed into an active task which can be independently executed and responded by a computer and a passive task which can be completed only by coordination of an executed object according to an execution mode.
S202, the active task is submitted to the execution unit with the offline state for execution.
S203, the passive tasks are continuously divided into sub-tasks with different priorities according to service requirements, and the execution units with idle states and high state values are sequentially handed to execute according to the high-low order of the priorities.
When the execution unit executes the passive task, the weight difference value is changed into a negative number, no execution object exists in the area where the corresponding execution unit is located, the execution object leaves the area where the corresponding execution unit is located, the state of the corresponding execution unit is changed from a busy state to an abnormal state, and workers are warned to process in time.
The splitting number of subtasks needs to be adaptively split according to the traffic and the traffic difficulty, the service splitting number with large traffic and high difficulty is large, the service splitting number with small traffic and low difficulty is small; meanwhile, subtask splitting also needs to refer to the number of execution units in the service range and the time efficiency of executing the tasks by the execution units.
In S3, scoring the execution unit means calculating a state value of the execution unit, where the state value includes a fixed state value and a floating state value; the method comprises the following steps:
s301, firstly, substituting a mouse displacement speed, a keyboard input speed and a task processing speed of an execution object into a formula to calculate a fixed state value of a corresponding execution unit; the formula is as follows:
in ZTZ G For the fixed state value of the execution unit, a is the mouse displacement speed influence factor, V s For recorded mouse displacement speed, R s The displacement speed of the standard mouse is b is a keyboard input speed influence factor, V J R is the recorded keyboard input speed J Input speed of standard keyboard, c is task processing speed influencing factor, R c For standard task processing speed, V c Processing speed for recorded tasks.
The standard mouse displacement speed and the standard keyboard input speed need to be set by referring to the normal speed of each execution object, and the speeds of different execution objects are different; the standard task processing speed is set according to the task difficulty, and the higher the task difficulty is, the lower the standard task processing speed is set, and the higher the standard task processing speed is.
S302, calculating a floating state value according to the time from the execution unit to the last task execution, summing the fixed state value and the floating state value, and calculating the state value of the execution unit, wherein the formula is as follows:
where ZTZ is the state value of the execution unit, ZTZ G For a fixed state value of the execution unit, d is a floating state value influence coefficient, f t For the time from the last execution of the task, R t Is the standard idle time.
Embodiment one:
assuming A, B and C total 3 execution units, their states are A: idle; b: busy; c: offline; in this case:
When the weight sensor detects that the weight values of A and B are greatly reduced and the camera detects that no execution object exists in the area where the execution unit is located:
the a state adjusts from idle to: offline;
the B state is adjusted from busy to: abnormal, and warn the staff to deal with in time;
when the weight sensor detects that the weight value of C is greatly increased and the camera detects that an execution object exists in the area where the execution unit is located:
the C state is adjusted from offline: idle;
when the test software detects that the B state is adjusted to be idle by the staff and the C is assigned a task:
the B state is adjusted from abnormal to: idle;
the C state adjusts from idle to: busy;
when the test software detects that the C task has been submitted:
the C state is adjusted from busy to: and (5) idling.
Embodiment two:
assuming X, Y and Z are a total of 3 execution units, the states are all busy; the mouse displacement speed influence factor is 0.1, the keyboard input speed influence factor is 0.3, and the task processing speed influence factor is 0.6; the standard mouse displacement speed of the corresponding execution object of each execution unit is 360 pixel points/second, and the standard keyboard input speed is 120 letters/minute; the task difficulty is the same, the standard task processing speed is 36 seconds/piece, and under the same condition of the mouse sensitivity:
The average speed of the mouse displacement of the X execution object is 720 pixel points/second, the average speed of the keyboard input is 60 letters/minute, and the task processing speed is 42 seconds/piece;
the average speed of the mouse displacement of the Y execution object is 180 pixel points/second, the average speed of the keyboard input is 180 letters/minute, and the task processing speed is 23 seconds/piece;
the average speed of the mouse displacement of the Z execution object is 240 pixel points/second, the average speed of the keyboard input is 120 letters/minute, and the task processing speed is 30 seconds/piece;
substituting formula to calculate:
x fixed state value:
y fixed state value:
z fixed state value:
assuming that at a certain moment, the time from the last execution of the task by the X, Y and Z execution units is 24 seconds, 35 seconds and 92 seconds respectively, the standard idle time is 72 seconds, the influence coefficient of the floating state value is 0.5, and the state value of each execution unit is calculated by substituting the floating state value into a formula:
x state value:
y state value:
z state value:
when the service is split, a plurality of high-priority tasks are preferentially transmitted to the Z execution unit for execution, then the Y execution unit is used, and finally the X execution unit is used.
It is noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, 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.
Finally, it should be noted that: the foregoing description is only a preferred embodiment of the present invention, and the present invention is not limited thereto, but it is to be understood that modifications and equivalents of some of the technical features described in the foregoing embodiments may be made by those skilled in the art, although the present invention has been described in detail with reference to the foregoing embodiments. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A data processing system based on distributed computing, the system comprising: the system comprises a data acquisition module, a data processing module, a function calling module and a data storage module;
the data acquisition module is used for acquiring weight information, image information and input information of all execution objects in a service range and sending the information to the data processing module; the data processing module sets the state of the corresponding execution unit according to the weight information, the image information and the input information of the execution object, calculates the state value of the corresponding execution unit according to the input information of the execution object, allocates different types of tasks to the execution units in different states, and allocates tasks with different priorities to the execution units in different state values; the function calling module is used for calling the weight sensor, the camera and the test software; the data storage module is used for carrying out backup storage on all the information.
2. A distributed computing-based data processing system as recited in claim 1, wherein: the data acquisition module comprises a weight information acquisition unit, an image information acquisition unit and an input information acquisition unit;
the weight information acquisition unit is used for acquiring weight information of an execution object, and collecting the weight information through the weight sensor, and when the execution object leaves or enters an area where the corresponding execution unit is located, the weight information changes;
the image information acquisition unit is used for acquiring image information of an execution object, and the image information is collected through a camera installed in the area where the execution unit is located, and when the execution object is located in the area where the corresponding execution unit is located, the camera can shoot the execution object;
the input information acquisition unit is used for acquiring input information of an execution object and detecting whether an execution unit corresponding to the execution object is allocated with a task or not, and the input information is collected through test software installed on a computer controlled by the execution object, wherein the input information comprises a mouse displacement speed, a keyboard input speed, a task processing speed and time from the last execution of the task.
3. A distributed computing-based data processing system as recited in claim 1, wherein: the data processing module comprises a state management unit, a state value calculation unit and a task allocation unit;
The state management unit is used for managing the states of all execution units in the service range, and changing the states of the corresponding execution units according to the weight information, the image information and the input information of different execution objects; the states of the execution unit include offline state, idle state, busy state, and abnormal state, and the state change includes: from offline to idle, from idle to busy, from busy to idle, from busy to abnormal, and from idle to offline;
the state value calculation unit is used for calculating the state value of the corresponding execution unit, the state value determines the timeliness of the corresponding execution unit to execute the task, and the higher the state value of the corresponding execution unit is, the higher the task execution efficiency is;
the task allocation unit is used for carrying out subtask division and scheduling on the service; the business to be processed is divided into different types of subtasks, wherein the subtask types comprise active tasks and passive tasks: the active task is a task which can be identified by a computer and automatically executed and responded, does not need to execute any operation of an object, and is transmitted to an execution unit in an off-line state to be executed; the passive tasks cannot be completely identified by a computer, tasks requiring the coordination operation of the execution object are divided into sub-tasks with different priorities according to different service requirements, the priorities comprise high and low, and the sub-tasks with different priorities in the passive tasks are transmitted to idle state execution units with different state values to be executed; all allocation operations are journaled.
4. A distributed computing-based data processing system as recited in claim 1, wherein: the function calling module is used for calling a weight sensor corresponding to the area where the execution unit is located and collecting weight information of an execution object; invoking a camera corresponding to the area where the execution unit is located, and collecting image information of an execution object; and calling test software on a computer for executing object control, and collecting input information of an executing object.
5. A distributed computing-based data processing system as recited in claim 1, wherein: the data storage module is used for storing the acquired information, the state information and the distribution log information into a database for tracing operation.
6. A data processing method based on distributed computing, the method comprising the steps of:
s1, adjusting the states of all execution units in a service range in real time;
s2, splitting the service into N subtasks, and distributing the N subtasks to different execution units for execution;
s3, scoring the execution unit after the task is completed;
and S4, after the service is completed, returning to the step S1 to continue waiting for the next service.
7. The method for data processing based on distributed computing according to claim 6, wherein in S1, the step of adjusting the state of the execution unit is as follows:
S101, acquiring weight information of an area where each execution unit is located through a weight sensor, calculating a difference value between a current acquired weight value and a weight value acquired at the previous moment in real time, judging whether the difference value is in a weight error interval or not, and if the difference value is in the weight error interval, directly entering the step S103 without processing; if the error interval is not found, marking a corresponding execution unit, and entering step S102;
s102, establishing a background image for each execution unit by using a mathematical modeling method, wherein no execution object exists in the background image, starting a corresponding camera to photograph the area where the marked execution unit is located, collecting a current image, subtracting gray values of corresponding pixel points of the two images, and obtaining a difference image after taking an absolute value, wherein the formula is as follows:
Z n (x,y)＝|d n (x,y)-B(x,y)|
wherein Z is n (x, y) is the gray value of the nth pixel point of the differential image, d n (x, y) is the gray value of the nth pixel point of the current image frame, and B (x, y) is the gray value of the corresponding pixel point of the background image;
setting a threshold value X, and carrying out binarization processing on all pixel points of the differential image to obtain a binarized image, wherein the point with a gray value of 255 is a foreground point, and the point with a gray value of 0 is a background point; the formula is as follows:
in which Q n (X, y) is the gray value of the nth pixel point of the binarized image, X is the threshold value, Z n (x, y) is the gray value of the nth pixel point of the differential image;
for image Q n Performing connectivity analysis, detecting human body contours of the image by using OpenCV, and judging whether an execution object exists in the area where the corresponding execution unit is located: when an execution object exists and the weight difference value is a positive number, the state of an execution unit corresponding to the execution object is adjusted from an offline state to an idle state; when no execution object exists and the weight difference value is negative, the state of an execution unit corresponding to the execution object is adjusted from an idle state to an offline state or from a busy state to an abnormal state;
s103, judging whether the corresponding execution unit is allocated with tasks through test software installed on a computer controlled by an execution object, wherein the tasks comprise an active task and a passive task, and only the execution unit allocated to the passive task can carry out state change, and the allocation of the passive task only aims at the execution unit with an idle state, so that the state of the execution unit allocated to the passive task is changed from the idle state to a busy state; changing the state of an execution unit, which is detected by test software to be submitted by a task, from a busy state to an idle state; and changing the state of the execution unit, which is detected by the test software that the task is not submitted and no execution object exists in the area where the execution unit is located, from a busy state to an abnormal state.
8. The method for data processing based on distributed computing according to claim 6, wherein in S2, the service is split into sub-tasks and the sub-tasks are allocated as follows:
s201, splitting a service to be processed into an active task which can be independently executed and responded by a computer and a passive task which can be completed only by coordination of an object to be executed according to an execution mode;
s202, executing an active task by an execution unit with an offline state;
s203, the passive tasks are continuously divided into sub-tasks with different priorities according to service requirements, and the execution units with idle states and high state values are sequentially handed to execute according to the high-low order of the priorities.
9. A data processing method based on distributed computing as defined in claim 8, wherein: when the execution unit executes the passive task, the weight difference value is changed into a negative number, no execution object exists in the area where the corresponding execution unit is located, the execution object leaves the area where the corresponding execution unit is located, the state of the corresponding execution unit is changed from a busy state to an abnormal state, and workers are warned to process in time.
10. The distributed computing-based data processing method of claim 6, wherein in S3, scoring an execution unit refers to computing a state value of the execution unit, the state value including a fixed state value and a floating state value; the method comprises the following steps:
S301, firstly, substituting a mouse displacement speed, a keyboard input speed and a task processing speed of an execution object into a formula to calculate a fixed state value of a corresponding execution unit; the formula is as follows:
in ZTZ G For the fixed state value of the execution unit, a is the mouse displacement speed influence factor, V s For recorded mouse displacement speed, R s The displacement speed of the standard mouse is b is a keyboard input speed influence factor, V J R is the recorded keyboard input speed J Input speed of standard keyboard, c is task processing speed influencing factor, R c For standard task processing speed, V c Processing speed for the recorded task;
s302, calculating a floating state value according to the time from the execution unit to the last task execution, summing the fixed state value and the floating state value, and calculating the state value of the execution unit, wherein the formula is as follows:
where ZTZ is the state value of the execution unit, ZTZ G For a fixed state value of the execution unit, d is a floating state value influence coefficient, f t For the time from the last execution of the task, R t Is the standard idle time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310430673.XA CN116467059A (en) | 2023-04-21 | 2023-04-21 | Data processing system and method based on distributed computing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310430673.XA CN116467059A (en) | 2023-04-21 | 2023-04-21 | Data processing system and method based on distributed computing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116467059A true CN116467059A (en) | 2023-07-21 |
Family
ID=87174909
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310430673.XA Pending CN116467059A (en) | 2023-04-21 | 2023-04-21 | Data processing system and method based on distributed computing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116467059A (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6298448B1 (en) * | 1998-12-21 | 2001-10-02 | Siemens Information And Communication Networks, Inc. | Apparatus and method for automatic CPU speed control based on application-specific criteria |
| US20070169125A1 (en) * | 2006-01-18 | 2007-07-19 | Xiaohan Qin | Task scheduling policy for limited memory systems |
| CN102655685A (en) * | 2012-05-29 | 2012-09-05 | 福州大学 | Task fault-tolerance allocation method for wireless sensor networks |
| US20150323388A1 (en) * | 2014-05-06 | 2015-11-12 | Stryker Corporation | Person support apparatus with position monitoring |
| CN106444791A (en) * | 2016-12-20 | 2017-02-22 | 南阳师范学院 | Design method of multiple AGV (Automatic Guided Vehicle) unified dispatching system by upper computer |
| WO2017112714A1 (en) * | 2015-12-20 | 2017-06-29 | Michael Farr | Combination computer keyboard and computer pointing device |
| CN106933954A (en) * | 2017-01-22 | 2017-07-07 | 四川用联信息技术有限公司 | Search engine optimization technology is realized based on Decision Tree Algorithm |
| US20180144283A1 (en) * | 2016-11-18 | 2018-05-24 | DefinedCrowd Corporation | Identifying workers in a crowdsourcing or microtasking platform who perform low-quality work and/or are really automated bots |
| CN110928676A (en) * | 2019-07-18 | 2020-03-27 | 国网浙江省电力有限公司衢州供电公司 | Power CPS load distribution method based on performance evaluation |
| CN111831406A (en) * | 2020-05-27 | 2020-10-27 | 深圳市合正汽车电子有限公司 | Multi-task scheduling method and device based on vehicle-mounted embedded system |
| CN112269826A (en) * | 2020-08-25 | 2021-01-26 | 帝杰曼科技股份有限公司 | Visual processing system and method based on big data |
| CN112506634A (en) * | 2020-12-08 | 2021-03-16 | 天津津航计算技术研究所 | Fairness operation scheduling method based on reservation mechanism |
| CN112732431A (en) * | 2021-01-26 | 2021-04-30 | 海南职业技术学院 | Artificial intelligence system based on cloud computing |
| CN115617532A (en) * | 2022-11-22 | 2023-01-17 | 浙江莲荷科技有限公司 | Target tracking processing method, system and related device |
| CN115829538A (en) * | 2022-10-31 | 2023-03-21 | 南方电网科学研究院有限责任公司 | Terminal operation and maintenance service management system |
-
2023
- 2023-04-21 CN CN202310430673.XA patent/CN116467059A/en active Pending
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6298448B1 (en) * | 1998-12-21 | 2001-10-02 | Siemens Information And Communication Networks, Inc. | Apparatus and method for automatic CPU speed control based on application-specific criteria |
| US20070169125A1 (en) * | 2006-01-18 | 2007-07-19 | Xiaohan Qin | Task scheduling policy for limited memory systems |
| CN102655685A (en) * | 2012-05-29 | 2012-09-05 | 福州大学 | Task fault-tolerance allocation method for wireless sensor networks |
| US20150323388A1 (en) * | 2014-05-06 | 2015-11-12 | Stryker Corporation | Person support apparatus with position monitoring |
| WO2017112714A1 (en) * | 2015-12-20 | 2017-06-29 | Michael Farr | Combination computer keyboard and computer pointing device |
| US20180144283A1 (en) * | 2016-11-18 | 2018-05-24 | DefinedCrowd Corporation | Identifying workers in a crowdsourcing or microtasking platform who perform low-quality work and/or are really automated bots |
| CN106444791A (en) * | 2016-12-20 | 2017-02-22 | 南阳师范学院 | Design method of multiple AGV (Automatic Guided Vehicle) unified dispatching system by upper computer |
| CN106933954A (en) * | 2017-01-22 | 2017-07-07 | 四川用联信息技术有限公司 | Search engine optimization technology is realized based on Decision Tree Algorithm |
| CN110928676A (en) * | 2019-07-18 | 2020-03-27 | 国网浙江省电力有限公司衢州供电公司 | Power CPS load distribution method based on performance evaluation |
| CN111831406A (en) * | 2020-05-27 | 2020-10-27 | 深圳市合正汽车电子有限公司 | Multi-task scheduling method and device based on vehicle-mounted embedded system |
| CN112269826A (en) * | 2020-08-25 | 2021-01-26 | 帝杰曼科技股份有限公司 | Visual processing system and method based on big data |
| CN112506634A (en) * | 2020-12-08 | 2021-03-16 | 天津津航计算技术研究所 | Fairness operation scheduling method based on reservation mechanism |
| CN112732431A (en) * | 2021-01-26 | 2021-04-30 | 海南职业技术学院 | Artificial intelligence system based on cloud computing |
| CN115829538A (en) * | 2022-10-31 | 2023-03-21 | 南方电网科学研究院有限责任公司 | Terminal operation and maintenance service management system |
| CN115617532A (en) * | 2022-11-22 | 2023-01-17 | 浙江莲荷科技有限公司 | Target tracking processing method, system and related device |
Non-Patent Citations (3)
| Title |
|---|
| D.FERNANDEZ-LANVIN等: "The dimension of age and gender as user model demographic factors for automatic personalization in e-commerce sites", 《COMPUTER STANDARDS & INTERFACES》, 3 February 2018 (2018-02-03), pages 1 - 9 * |
| 崔勇等: "移动云计算研究进展与趋势", 《计算机学报》, vol. 40, no. 02, 26 September 2016 (2016-09-26), pages 273 - 295 * |
| 程辉: "扰动状态下水果采摘机器人视觉空间定位", 《中国优秀硕士学位论文全文数据库 信息科技辑》, no. 02, 15 February 2015 (2015-02-15), pages 138 - 1354 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108829494B (en) | Container cloud platform intelligent resource optimization method based on load prediction | |
| CN103294533A (en) | Task flow control method and task flow control system | |
| CN103823714A (en) | Virtualization-based method and device for adjusting QoS (quality of service) of node memory of NUMA (non uniform memory access architecture) | |
| CN109104493A (en) | A kind of cloud resource pool service Load-aware with from processing unit and method | |
| CN109976911B (en) | Self-adaptive resource scheduling method | |
| CN112685153A (en) | Micro-service scheduling method and device and electronic equipment | |
| CN105868004A (en) | Cloud computing based business system scheduling method and apparatus | |
| Li et al. | A task allocation method for stream processing with recovery latency constraint | |
| CN116955455A (en) | Processing method and platform suitable for radiation monitoring system | |
| CN103442087B (en) | A kind of Web service system visit capacity based on response time trend analysis controls apparatus and method | |
| CN114327811A (en) | Task scheduling method, device and equipment and readable storage medium | |
| CN106802825A (en) | A kind of dynamic task scheduling method and system based on real-time system | |
| CN116467059A (en) | Data processing system and method based on distributed computing | |
| CN109491775A (en) | Task processing and dispatching method under a kind of environment for edge calculations | |
| CN110489221B (en) | Method and system for dynamically adjusting computing resources by automatic task number | |
| US20240004707A1 (en) | Methods and systems for energy-efficient scheduling of periodic tasks on a group of processing devices | |
| CN115951974B (en) | Management method, system, equipment and medium of GPU virtual machine | |
| CN110083434B (en) | Method and device for batch integration of cloud virtual machines and server | |
| CN111988412A (en) | Intelligent prediction system and method for multi-tenant service resource demand | |
| CN112346863B (en) | Method and system for processing dynamic adjustment data of computing resources | |
| CN115033389A (en) | Energy-saving task resource scheduling method and device for power grid information system | |
| CN108874517A (en) | The stand-by system availability of fixed priority divides energy consumption optimization method | |
| CN114401195A (en) | Server capacity adjustment method and device, storage medium and electronic device | |
| CN108183870A (en) | A kind of cloud data center scheduling of resource sharing method and system based on cloud maturity | |
| CN106371908A (en) | Optimization method for image/video filter task distribution based on PSO (Particle Swarm Optimization) |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |