CN109725989B - Task execution method and device - Google Patents
Task execution method and device Download PDFInfo
- Publication number
- CN109725989B CN109725989B CN201711049658.1A CN201711049658A CN109725989B CN 109725989 B CN109725989 B CN 109725989B CN 201711049658 A CN201711049658 A CN 201711049658A CN 109725989 B CN109725989 B CN 109725989B
- Authority
- CN
- China
- Prior art keywords
- task
- executed
- node
- nodes
- determining
- 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.)
- Active
Links
Images
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
Abstract
The application discloses a task execution method and a task execution device, when a task request is received, an initial DAG graph can be constructed firstly, namely leaf nodes of the DAG graph are generated, then the leaf nodes are used as nodes to be executed, corresponding tasks are executed and execution results are obtained, when the fact that the task corresponding to the task request is not executed completely is judged, downstream nodes are determined as the nodes to be executed according to the execution results, and the corresponding tasks are executed continuously until the task corresponding to the task request is executed completely.
Description
Technical Field
The present application relates to the field of information technologies, and in particular, to a method and an apparatus for task execution.
Background
Directed Acyclic Graph (DAG), an efficient way to describe the progress of a project, system, task flow, etc., is shown in fig. 1.
FIG. 1 is a schematic diagram of a DAG graph in which a plurality of nodes and arrows connecting the nodes are visible. Taking a DAG graph of the task flow as an example, the tasks corresponding to the nodes in fig. 1 are different steps in the task flow, and the arrows indicate which step needs to be executed next after the previous step is executed. The arrow starting node is an upstream node, and the arrow ending node is a downstream node.
In the prior art, a complex task flow can be simplified into a plurality of subtasks to be executed through a DAG graph. The existing DAG graph is preset before the task is executed, that is, what and how each step in the task needs to be executed are predetermined. Therefore, when a complex task needs to be executed, the execution of the task can be assisted through a predetermined DAG graph corresponding to the task (i.e., the complex task is simplified into a plurality of subtasks for execution).
However, in some task scenarios, only after the task corresponding to the upstream node is executed, the task corresponding to the downstream node can be determined according to the execution result, so that the DAG graph of the task cannot be predetermined. For example, if it is necessary to determine the data with the largest value among the plurality of data, each node in the DAG graph corresponding to the task may be generated according to the data required to execute the task. However, since the specific numerical value of the input data cannot be determined in advance, the execution result of the task corresponding to each node cannot be determined in advance. Therefore, the DAG graph corresponding to the task cannot be determined in advance, and the task cannot be executed in a mode of assisting in executing the task through the DAG graph.
Based on the prior art, the specification provides a new task execution method and device.
Disclosure of Invention
Embodiments of the present specification provide a method and an apparatus for task execution, which are used to solve the problem that when a downstream node needs to be generated according to a task execution result of an upstream node in a task scene, it is difficult to execute a task in a manner of splitting a complex task into simple subtasks through a DAG graph.
The embodiment of the specification adopts the following technical scheme:
a method of task execution, comprising:
receiving a task request;
generating leaf nodes of a directed acyclic graph DAG according to the task request, and determining the total number of the nodes of the DAG graph;
taking the leaf node as a node to be executed, determining and executing a task corresponding to the node to be executed, and obtaining an execution result;
judging whether the task corresponding to the task request is executed completely according to the number of the nodes which execute the corresponding task and the total number of the nodes;
if so, taking the execution result as a task result;
and if not, generating a downstream node according to the execution result, taking the downstream node as a node to be executed, and continuing to execute the task corresponding to the node to be executed until the task corresponding to the task request is determined to be executed completely.
An apparatus for task execution, comprising:
the receiving module receives a task request;
the determining module is used for generating leaf nodes of a directed acyclic graph DAG according to the task request and determining the total number of the nodes of the DAG graph;
the execution module is used for taking the leaf node as a node to be executed, determining and executing a task corresponding to the node to be executed and obtaining an execution result;
and the judging and generating module is used for judging whether the task corresponding to the task request is completely executed according to the number of the nodes which execute the corresponding task and the total number of the nodes, if so, taking the execution result as a task result, if not, generating a downstream node according to the execution result, taking the downstream node as a node to be executed by the executing module, and continuing to execute the task corresponding to the node to be executed until the task corresponding to the task request is determined to be completely executed.
A server, comprising: the method comprises the following steps: one or more memories and a processor, the memories storing programs and configured to perform, by the one or more processors:
receiving a task request;
generating leaf nodes of a directed acyclic graph DAG according to the task request, and determining the total number of the nodes of the DAG graph;
taking the leaf node as a node to be executed, determining and executing a task corresponding to the node to be executed, and obtaining an execution result;
judging whether the task corresponding to the task request is executed completely according to the number of the nodes which execute the corresponding task and the total number of the nodes;
if so, taking the execution result as a task result;
and if not, generating a downstream node according to the execution result, taking the downstream node as a node to be executed, and continuing to execute the task corresponding to the node to be executed until the task corresponding to the task request is determined to be executed completely.
The embodiment of the specification adopts at least one technical scheme which can achieve the following beneficial effects:
by the method and the device provided by the specification, when a task request is received, an initial DAG graph can be constructed, namely leaf nodes of the DAG graph are generated, and the total number of the nodes of the DAG graph is determined. And then taking the leaf node as a node to be executed, executing the corresponding task and obtaining an execution result, determining a downstream node as the node to be executed according to the execution result when judging that the task corresponding to the task request is not executed completely according to the total number of the nodes and the number of the nodes which have executed the corresponding task, and continuing to execute the corresponding task until the task corresponding to the task request is not executed completely. When the task is executed, only the structure and the leaf nodes of the DAG graph corresponding to the task are determined, and the downstream nodes are continuously generated according to the execution result along with the continuous execution of the task corresponding to the nodes, so that the complex task can be continuously split into a plurality of simple subtasks and executed according to the assistance of the DAG graph before the task is executed. That is, by dynamically determining a DAG graph for assisting task execution during task execution, the problem that it is difficult to assist task execution through a predetermined DAG graph in some business scenarios is solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the application and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the application and together with the description serve to explain the application and not to limit the application. In the drawings:
FIG. 1 is a schematic diagram of a DAG graph in the prior art;
FIG. 2 is a process of task execution provided by an embodiment of the present specification;
fig. 3 is a schematic diagram of a DAG graph leaf node provided in an embodiment of the present specification;
FIGS. 4a and 4b are diagrams of determining a total number of nodes of a DAG graph provided by an implementation of the present specification;
FIG. 5 is a diagram illustrating an execution queue and a preparation queue provided by an embodiment of the present description;
fig. 6a to fig. 6c are schematic diagrams of an execution queue and a preparation queue in a task execution process according to an embodiment of the present disclosure;
fig. 7 is a schematic diagram of a task execution system corresponding to a task execution method according to an embodiment of the present disclosure;
fig. 8 is a schematic structural diagram of a task execution device provided in an embodiment of the present disclosure;
fig. 9 is a schematic structural diagram of a server according to an embodiment of the present disclosure.
Detailed Description
In order to make the objects, technical solutions and advantages of the present disclosure more apparent, the technical solutions of the present disclosure will be clearly and completely described below with reference to the specific embodiments of the present disclosure and the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application, and not all of the embodiments. All other embodiments obtained by a person skilled in the art without making any inventive step based on the embodiments in the description belong to the protection scope of the present application.
The technical solutions provided by the embodiments of the present application are described in detail below with reference to the accompanying drawings.
Fig. 2 is a process for executing a task provided in an embodiment of the specification, which specifically includes the following steps:
s100: a task request is received.
In one or more embodiments of the present description, a task request may be received by a device of a service provider and a corresponding task may be performed according to the task request. The device provided by the service may be a terminal or a server, such as a mobile phone, a personal computer, a server, and the like, which is not limited in this specification. For convenience of description, the following description will take the server as an example of the execution subject of the task execution process.
In addition, the task request can carry data required for executing the task, so that the server can execute the task subsequently. The server may be a single device or a system of devices, such as a distributed server.
Further, in this specification embodiment, the task request may be a request to determine extremum data among a number of data. Specifically, the data may be data required for executing the task corresponding to the task request, and the extreme value data may be a maximum value or a minimum value of the required data.
It should be noted that, in this specification, the extreme value data may be directly the data itself required for executing the task (for example, data with the maximum or minimum value selected from several data), or may also be a result determined by the data required for executing the task.
For example, the task request is the user with the highest loan risk among the users a to D, the data required for executing the task may include the identity information of the users a to D, the transaction record, and the like, and when the loan risk results corresponding to the users a to D are determined further according to the data required for executing the task, the maximum value is determined from the loan risk results. Then the extreme value data is not the input data itself but the result calculated from the input data.
S102: and generating leaf nodes of the directed acyclic graph DAG according to the task request, and determining the total number of the nodes of the DAG graph.
In this specification, the server may generate each leaf node in the DAG graph corresponding to the task according to the task request, so as to split the task corresponding to the task request into a plurality of simple subtasks through each leaf node of the DAG graph, and execute the task corresponding to the task request. In addition, since the server has already determined the leaf nodes of the DAG graph, the server may further determine the total number of nodes of the DAG graph according to the task request, so that when a downstream node is subsequently generated by executing a task, it may be determined when the task is completely executed (e.g., when all the nodes of the DAG graph are generated).
Specifically, the server may determine, according to the task request, data that needs to be input to execute a task corresponding to the task request, and then generate each leaf node in the DAG graph according to the determined data. Or, when the task request already carries data required for executing the task, the server may also generate each leaf node in the DAG graph directly according to the data carried by the task request. Of course, the two methods for generating leaf nodes may be used alone or in combination, and this specification is not limited thereto.
For example, the server receives the task request to determine which of the banks a-d the user a has the most deposits. And banks a-d are all likely to be the most deposited banks by user a, the server may determine that the data that needs to be entered to perform the task is the user a's deposits in banks a-d.
First, the server may determine the deposits of the user a in the banks a to d, respectively, as data to be input for executing the task corresponding to the task request, by sending query requests to the banks a to d, respectively. Or, assuming that the task request is sent by the bank a, the task request carries a deposit value of the user a in the bank a, and then the server can determine data required to be input for executing a task corresponding to the task request by sending a query request to the banks b-d.
Then, the server can respectively generate leaf nodes of the DAG graph according to the deposits of the user A in the banks a-d, and the leaf nodes of the DAG graph are generated.
Suppose that the deposits of user A in banks a-d are as shown in Table 1.
TABLE 1
The server may establish DAG graph leaf nodes as shown in fig. 3. As can be seen in FIG. 3, each leaf node identifier has node identifiers 1-4, wherein each leaf node corresponds to an identifier of a bank. And for each leaf node, the server may take the deposit value of the user a in the bank corresponding to the leaf node as the value corresponding to the leaf node. Thus, it can be seen that each leaf node in fig. 3 corresponds to the identification of the bank and the deposit value of the user a in the bank.
Of course, the above example is only one example provided by the embodiment of the present specification, and the present specification does not limit how the server generates each leaf node and how to determine the corresponding numerical value of each leaf node. For example, when the task request is to determine the most single deposits of user a in each bank, each leaf node generated may correspond to only the value of each single deposit of user a in each bank. Or, when the task request is a web page with the determined maximum browsing frequency of the user, leaf nodes may be generated according to the web pages browsed by the user, and the frequency of browsing the web pages by the user may be used as a numerical value corresponding to each leaf child node, respectively, and so on.
Further, in one or more embodiments of the present description, after determining the leaf nodes of the DAG graph, the server may also determine the total number of nodes of the DAG graph, i.e., determine how many nodes should exist in the DAG graph. So that whether the task corresponding to the task request is executed completely can be judged subsequently based on the total number of the nodes of the DAG graph.
Specifically, the DAG graph may be used to split the complex task into a plurality of simple subtasks, and what manner is used to determine the subtasks, that is, how to assemble the task corresponding to the node may be set as needed. Therefore, in this specification, the server may store the task assembly condition in advance. The server may determine the total number of nodes of the DAG graph based on the number of leaf nodes that have been generated and pre-stored task assembly conditions.
In this specification, when the task request is a task that determines extremum data from a plurality of data, the task assembly condition may be: a preset number of nodes that have not executed the corresponding task is selected, and the preset number may be set as needed, for example, 2, 3, and so on.
Continuing with the above example, assume that for a task request for determining the magnitude of a numerical value, the server is pre-configured with the following task assembly conditions: two nodes that have not performed the task are selected, i.e., the preset number is 2. And the server can select numerical values corresponding to the two nodes according to the task assembly condition, perform pairwise comparison, and take the comparison result as an execution result. The total number of nodes for the DAG graph may thus be according to the formula: m is determined as 2 n-1. Wherein m is the total number of nodes, and n is the number of leaf nodes. The server may then determine that for 4 leaf nodes, the total number of DAG graph nodes may be determined to be 7 based on the task assembly condition, as shown in fig. 4 a. Alternatively, assuming that the server generates 7 leaf nodes, the total number of nodes of the DAG graph may be determined to be 13 according to the same task assembly condition, as shown in fig. 4 b.
Fig. 4a and 4b are schematic diagrams for determining the total number of nodes of the DAG graph provided in the implementation of this specification, where leaf nodes are generated nodes and are represented by solid lines, while the rest nodes in the DAG graph are not generated yet and are represented by dotted lines, and dotted arrows in the graphs represent the trend of the DAG graph, that is, the upstream and downstream relationships of the nodes.
It should be noted that, of course, the dashed lines shown in fig. 4a to 4b are schematic, and since no task is assembled at this time, the arrows are all dashed lines to indicate a possible task assembly situation, and do not indicate that the DAG graph is necessarily generated in a node form indicated by the dashed lines in the following, and the dashed lines are only one possible form of the DAG graph corresponding to the task when finally determining.
S104: and taking the leaf node as a node to be executed, determining and executing a task corresponding to the node to be executed, and obtaining an execution result.
In this specification, the server as described in step S102 may assemble and execute tasks according to preset task assembly conditions. Therefore, the server can firstly use each leaf node as a node to be executed, and then determine the task corresponding to the node to be executed. And finally, assembling the tasks corresponding to the nodes meeting the task assembling conditions, and executing the assembled tasks to obtain an execution result.
For example, in the example of determining which bank among the banks a to d has the most deposits, assuming that the tasks corresponding to the nodes 1 and 2 in the DAG graph are of the comparative data size, after the tasks corresponding to the nodes 1 and 2 are assembled and executed, it is determined that the deposits in the bank b are more, and it is determined that the execution result is the bank b, and the corresponding value is 200 yuan. If the tasks corresponding to the nodes 3 and 4 are assembled and executed, the execution result can be determined to be the bank c, and the corresponding numerical value is 5000 yuan.
In addition, in the prior art, for convenience of using a computer language to execute tasks according to a DAG graph, the DAG graph is usually converted into a linked list form, and the subtasks to be executed are determined according to the linked list. Moreover, since there is no data index in the data structure of the linked list, each time it is determined what needs to be executed next (e.g., determining which node corresponds to a task to be executed subsequently), the server generally needs to traverse the linked list to determine which node corresponds to the task to be executed.
However, since the DAG map in this specification cannot be determined in advance, there is no corresponding linked list for assisting execution.
Therefore, in the embodiment of the present specification, after determining the leaf nodes of the DAG graph, the server may add or remove the nodes to or from the queues for executing the two auxiliary tasks through the queues for executing the two auxiliary tasks according to whether the nodes to be executed satisfy the task assembly condition, so as to assist in dynamically generating the nodes in the DAG graph, and further promote the execution of the tasks.
Specifically, the server can determine the nodes to be executed which meet the task assembly condition, add the nodes to the execution queue, determine the nodes to be executed which do not meet the task assembly condition, and add the nodes to the preparation queue. And then, according to the task assembly condition, assembling and executing the task corresponding to the to-be-executed node in the execution queue. And when the nodes in the preparation queue meet the task assembly condition, the nodes meeting the task assembly condition can be moved to the execution queue to assemble and execute the task. On one hand, execution of tasks is assisted, and on the other hand, the linked list is not adopted, so that the problem of low efficiency caused by the fact that a server needs to repeatedly traverse the linked list in the prior art is solved.
For example, the server generates 7 leaf nodes. Continuing to assume that the task assembly conditions are: two nodes that have not performed the task are selected. The server may select 6 leaf nodes from the 7 leaf nodes, add to the execution queue as nodes satisfying the task assembly condition, and add the remaining one leaf node that does not satisfy the task assembly condition to the preparation queue, as shown in fig. 5.
Further, after the task corresponding to the to-be-executed node in the execution queue is assembled and executed, the server may also remove the to-be-executed node that has executed the corresponding task as an executed node from the execution queue, so as to avoid repeatedly assembling the node task.
Of course, the present specification does not limit when to move the node to be executed, which satisfies the task assembling condition, to the execution queue, as long as the node to be executed moves before the execution result is obtained. For example, when determining that there is a node to be executed in the preparation queue that satisfies the task assembly condition, the server may also assemble and execute a task corresponding to the node to be executed that satisfies the task assembly condition, and then move the node to be executed that satisfies the task assembly condition to the execution queue.
S106: and judging whether the task corresponding to the task request is executed completely or not according to the number of the nodes executing the corresponding task and the total number of the nodes, if so, executing the step S108, and otherwise, executing the step S110.
In one or more embodiments provided in this specification, after each task is assembled and executed, the server may determine whether the task corresponding to the task request is completely executed, and execute different subsequent operations according to the determination result.
Specifically, since the server has determined the total number of nodes of the DAG graph in step S102, the server may determine, according to the number of nodes that have executed the corresponding task (i.e., the number of nodes that have been generated), whether the number of nodes that have been generated and have executed the corresponding task in the DAG graph is consistent with the total number of nodes, if yes, it indicates that the task corresponding to the task request is requested, and if not, the server completes execution of each sub-task that has been split by the server according to the assistance of the DAG graph, then step S108 is performed, and if not, step S110 is performed.
In addition, since it is generally difficult for the server to determine the number of nodes that have executed the corresponding task during the execution of the task, in this specification, the server may determine whether the execution of the task corresponding to the task request is completed according to whether the number of nodes that have been generated matches the total number of nodes, and whether the execution queue and the preparation queue described in step S104 above are empty.
Specifically, since the server has determined the total number of nodes of the DAG graph in step S102, when the number of generated nodes is equal to the total number of nodes, it may be determined that all the nodes are generated. As an example, with FIG. 4a, when the lowest node is generated, it may be determined that all nodes of the DAG graph have been generated.
Further, in order to determine whether the task corresponding to the generated node has been executed, the server may also determine according to whether there are nodes in the execution queue and in the preparation queue. For the node to be executed, when the corresponding task is executed completely, the server may remove the node to be executed as the executed node from the execution queue, so when the execution queue is empty, it may be determined that all the nodes meeting the task assembly condition have executed the task. If there are nodes to be executed in the preparation queue, it is indicated that there are nodes that have not executed the corresponding task, so that it can be determined that the task corresponding to the task request has not been executed. And when the preparation queue and the execution queue are both empty, the generated nodes can be determined to have executed the tasks.
Therefore, when the server determines whether the number of generated nodes is equal to the total number of nodes and determines whether the preparation queue and the execution queue are empty, if yes, it is determined that the task corresponding to the task request is completely executed, and step S108 is executed, and if no, it is determined that the task corresponding to the task request is not completely executed, and step S110 is executed.
It should be noted that, continuing with fig. 4a as an example, there is only one node generated last, and the task corresponding to the node is "return execution result". The tasks corresponding to the node are different from the tasks corresponding to other nodes in the DAG graph, and the tasks corresponding to the node do not need to be assembled with other nodes. Therefore, in this specification, a node that has executed a corresponding task may be considered as a node that assembles and executes a task with other nodes according to a task assembly condition, and a node that executes a task of "returning an execution result".
S108: the execution result is taken as the task result.
In this embodiment, after determining that the task corresponding to the task request is completely executed, the server may use the execution result as the task result.
And, it should be noted that, at this time, the task result is already returned. The nodes that have executed the corresponding tasks are all the nodes that have been generated by the server, and the downstream nodes are generated according to the execution result, so that for each node, the server can determine the upstream and downstream relationship of the node with other nodes. When the task result is determined, the DAG graph corresponding to the task is also generated, that is, all nodes of the DAG graph are dynamically generated.
S110: and generating a downstream node according to the execution result, taking the downstream node as a node to be executed, and continuing to execute the task corresponding to the node to be executed until the task corresponding to the task request is determined to be executed completely.
In one or more embodiments provided in this specification, when it is determined that the task corresponding to the task request is not completely executed, the server may further generate a downstream node according to the execution result, so as to continue to use the downstream node as a node to be executed, and execute the task corresponding to the node to be executed until the task corresponding to the task request is not completely executed.
Specifically, after the downstream node is determined, the downstream node may be added to the preparation queue as a node to be executed, and step S104 and step S106 may be repeated.
For example, assume that the server has determined 7 leaf nodes and the task assembly condition is still: two nodes that have not performed the task are selected. Further assuming that the tasks corresponding to the nodes 3 and 4 have been executed, the downstream node is determined to be generated according to the execution result: node 8, and as a downstream node of nodes 3 and 4, as shown in fig. 6 a. The server may then remove node 3 and node 4 from the execution queue and add node 8 to the preparation queue, as shown in FIG. 6 b. Then there may be node 7 and node 8 in the preparation queue, and the server may determine that nodes 7 and 8 satisfy the task assembly condition, move nodes 7 and 8 to the execution queue, assemble the tasks corresponding to nodes 7 and 8, and execute them, as shown in fig. 6 c.
Through the task execution process shown in fig. 2, it can be seen that when the DAG graph cannot be predetermined to assist the task execution, leaf nodes of the DAG graph may be generated first, and in the task execution process, the DAG graph is completed step by step to continue the execution of the auxiliary task, thereby avoiding a defect that it is difficult to execute the task in a mode of assisting the task execution by the DAG graph when the DAG graph cannot be generated in advance for a certain service scene in the prior art.
It should be noted that all execution subjects of the steps of the method provided in the embodiments of the present application may be the same apparatus, or different apparatuses may also be used as execution subjects of the method. For example, the execution subject of step S100 may be device 1, and the execution subject of step S102 may be device 2. The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
In this specification, the server may be a distributed server including a plurality of managers and a plurality of executives. And executing the task corresponding to the task request by all the management parties together, and maintaining a DAG graph corresponding to the task. And receiving and executing the task corresponding to the node to be executed by the executing party, and returning a determined execution result to any managing party, as shown in fig. 7.
Fig. 7 is a schematic diagram of a task execution system for executing the task execution method shown in fig. 2 according to an embodiment of the present disclosure. The system is divided into a manager and an executor, and a plurality of managers exist, and the task execution process commonly maintained by the managers is indicated in a dotted line box.
After receiving the task request, any manager may perform the operation corresponding to step S102 and the part of step S104 that determines the task corresponding to the node to be executed. Then, the task can be sent to any executive party, the executive party receiving the task executes the task, and an execution result is returned to any management party. The manager receiving the execution result executes the determination operation of step S106, and when the manager determines to execute step S110, the above process is repeated until the manager determines to finish executing step S106.
It can be seen that since the task corresponding to the task request is maintained by multiple managers, the task flow can continue to be executed no matter which manager the executive party returns the execution result to. Also, the manager may be executing asynchronously when assigning tasks. That is, when determining the tasks corresponding to the multiple nodes to be executed, the determined tasks may be sent to different executing parties respectively. Therefore, for each executing party, after the executing party determines the execution result, the execution result can be returned to any one of the managing parties, so that the managing party continues the operation of the subsequent steps.
Of course, the specification does not limit how the manager device maintains data synchronization, and the same method as that in the distributed system in the prior art may be specifically adopted.
Based on the data evidence storing method shown in fig. 1, an embodiment of the present specification further provides a task execution device, as shown in fig. 8.
Fig. 8 is a schematic structural diagram of a data certification device provided in an embodiment of the present specification, including:
a receiving module 200 for receiving a task request;
a determining module 202, configured to generate leaf nodes of a directed acyclic graph DAG according to the task request, and determine a total number of nodes of the DAG graph;
the execution module 204 is configured to use the leaf node as a node to be executed, determine and execute a task corresponding to the node to be executed, and obtain an execution result;
the determining and generating module 206 determines whether the task corresponding to the task request is completely executed according to the number of nodes on which the corresponding task has been executed and the total number of nodes, if so, the executing result is used as a task result, if not, a downstream node is generated according to the executing result, and the executing module 204 uses the downstream node as a node to be executed to continue executing the task corresponding to the node to be executed until it is determined that the task corresponding to the task request is completely executed.
The determining module 202 determines, according to the task request, data that needs to be input to execute a task corresponding to the task request, and generates each leaf node in the DAG graph according to the determined data.
The determining module 202 determines the total number of nodes of the DAG graph according to preset task assembly conditions and the number of the leaf nodes.
The execution module 204 determines the nodes to be executed that meet the task assembly condition, adds the nodes to the execution queue, determines the nodes to be executed that do not meet the task assembly condition, adds the nodes to be executed to the preparation queue, and assembles and executes the tasks corresponding to the nodes to be executed in the execution queue according to the task assembly condition.
The executing module 204, after obtaining the execution result, removes the node to be executed as the executed node from the execution queue.
The executing module 204 adds the downstream node as a node to be executed to the preparation queue, determines whether there is a node to be executed meeting the task assembling condition in the preparation queue, if so, moves the node to be executed meeting the task assembling condition to the execution queue, so as to assemble and execute a task corresponding to the node to be executed in the execution queue according to the task assembling condition, and if not, waits for other nodes to be executed to be added to the preparation queue.
The judgment generation module 206 is configured to judge whether the number of generated nodes is equal to the total number of nodes, judge whether the preparation queue and the execution queue are empty, determine that the task corresponding to the task request is executed completely if both the judgment results are yes, and determine that the task corresponding to the task request is not executed completely if any judgment result is no.
The task request is as follows: a request for extremum data is determined from the plurality of data.
The execution module 204 determines a task corresponding to the node to be executed, and sends the task to be executed to an execution party, so that the execution party executes the task and returns an execution result.
Based on the task execution method shown in fig. 1, the present specification correspondingly provides a server, as shown in fig. 9, including: one or more processors and memory, the memory storing a program and configured to perform, by the one or more processors:
receiving a task request;
generating leaf nodes of a directed acyclic graph DAG according to the task request, and determining the total number of the nodes of the DAG graph;
taking the leaf node as a node to be executed, determining and executing a task corresponding to the node to be executed, and obtaining an execution result;
judging whether the task corresponding to the task request is executed completely according to the number of the nodes which execute the corresponding task and the total number of the nodes;
if so, taking the execution result as a task result;
and if not, generating a downstream node according to the execution result, taking the downstream node as a node to be executed, and continuing to execute the task corresponding to the node to be executed until the task corresponding to the task request is determined to be executed completely.
It should be noted that, in the present specification, all the embodiments are described in a progressive manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. Particularly, for the mobile terminal and the server provided by the embodiment of the present application, since they are substantially similar to the method embodiment, the description is relatively simple, and for relevant points, reference may be made to part of the description of the method embodiment.
In the 90 th generation of 20 th century, it is obvious that improvements in Hardware (for example, improvements in Circuit structures such as diodes, transistors and switches) or software (for improvement in method flow) can be distinguished for a technical improvement, however, as technology develops, many of the improvements in method flow today can be regarded as direct improvements in Hardware Circuit structures, designers almost all obtain corresponding Hardware Circuit structures by Programming the improved method flow into Hardware circuits, and therefore, it cannot be said that an improvement in method flow cannot be realized by Hardware entity modules, for example, Programmable logic devices (Programmable logic devices L organic devices, P L D) (for example, Field Programmable Gate Arrays (FPGAs) are integrated circuits whose logic functions are determined by user Programming of devices), and a digital system is "integrated" on a P L D "by self Programming of designers without requiring many kinds of integrated circuits manufactured and manufactured by special chip manufacturers to design and manufacture, and only a Hardware software is written in Hardware programs such as Hardware programs, software programs, such as Hardware programs, software, Hardware programs, software, Hardware programs, software, Hardware programs, Hardware programs, software, Hardware, software, Hardware, software, Hardware, software, Hardware, software, Hardware, software, Hardware, software, Hardware, software, Hardware, software, Hardware, software, Hardware, software, Hardware, software, Hardware, software.
A controller may be implemented in any suitable manner, e.g., in the form of, for example, a microprocessor or processor and a computer readable medium storing computer readable program code (e.g., software or firmware) executable by the (micro) processor, logic gates, switches, Application Specific Integrated Circuits (ASICs), programmable logic controllers (PLC's) and embedded microcontrollers, examples of which include, but are not limited to, microcontrollers 625D, Atmel AT91SAM, Microchip PIC18F26K20 and Silicone L abs C8051F320, which may also be implemented as part of the control logic of a memory.
The systems, devices, modules or units illustrated in the above embodiments may be implemented by a computer chip or an entity, or by a product with certain functions. One typical implementation device is a computer. In particular, the computer may be, for example, a personal computer, a laptop computer, a cellular telephone, a camera phone, a smartphone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
For convenience of description, the above devices are described as being divided into various units by function, and are described separately. Of course, the functionality of the units may be implemented in one or more software and/or hardware when implementing the present application.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
In a typical configuration, a computing device includes one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
The memory may include forms of volatile memory in a computer readable medium, Random Access Memory (RAM) and/or non-volatile memory, such as Read Only Memory (ROM) or flash memory (flash RAM). Memory is an example of a computer-readable medium.
Computer-readable media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device. As defined herein, a computer readable medium does not include a transitory computer readable medium such as a modulated data signal and a carrier wave.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The application may be described in the general context of computer-executable instructions, such as program modules, being executed by a computer. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform particular tasks or implement particular abstract data types. The application may also be practiced in distributed computing environments where tasks are performed by remote processing devices that are linked through a communications network. In a distributed computing environment, program modules may be located in both local and remote computer storage media including memory storage devices.
The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the system embodiment, since it is substantially similar to the method embodiment, the description is simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
The above description is only an example of the present application and is not intended to limit the present application. Various modifications and changes may occur to those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.
Claims (8)
1. A method of task execution, comprising:
receiving a task request;
generating leaf nodes of a Directed Acyclic Graph (DAG) according to the task request, and determining the total number of the nodes of the DAG, wherein each leaf node of the DAG is used for splitting a task corresponding to the task request into a plurality of subtasks;
taking the leaf node as a node to be executed, determining and executing a task corresponding to the node to be executed, and obtaining an execution result;
judging whether the task corresponding to the task request is executed completely according to the number of the nodes which execute the corresponding task and the total number of the nodes;
if so, taking the execution result as a task result;
if not, generating a downstream node according to the execution result, taking the downstream node as a node to be executed, and continuing to execute the task corresponding to the node to be executed until the task corresponding to the task request is determined to be executed completely;
determining the total number of nodes of the DAG specifically comprises:
determining the total number of nodes of the DAG according to preset task assembly conditions and the number of the leaf nodes;
taking the leaf node as a node to be executed, determining and executing a task corresponding to the node to be executed, and specifically comprising:
determining nodes to be executed which meet the task assembly condition, adding the nodes to be executed to an execution queue, determining nodes to be executed which do not meet the task assembly condition, and adding the nodes to be executed to a preparation queue;
according to the task assembly condition, assembling and executing the task corresponding to the node to be executed in the execution queue;
taking the downstream node as a node to be executed, determining and executing a task corresponding to the node to be executed, and specifically comprising:
adding the downstream node as a node to be executed to the preparation queue;
judging whether a node to be executed meeting the task assembly condition exists in the preparation queue;
if so, moving the nodes to be executed meeting the task assembling condition to the execution queue, and assembling and executing the tasks corresponding to the nodes to be executed in the execution queue according to the task assembling condition;
and if not, waiting for other nodes to be executed to be added to the preparation queue.
2. The method of claim 1, wherein generating leaf nodes of the directed acyclic graph DAG according to the task request specifically comprises:
determining data required to be input for executing a task corresponding to the task request according to the task request;
and generating each leaf node in the DAG according to the determined data.
3. The method of claim 1, wherein after determining and executing the task corresponding to the node to be executed and obtaining the execution result, the method further comprises:
and taking the node to be executed as an executed node to be moved out of the execution queue.
4. The method according to claim 1, wherein the step of determining whether the task corresponding to the task request is completely executed according to the number of nodes on which the corresponding task has been executed and the total number of nodes includes:
judging whether the number of the generated nodes is equal to the total number of the nodes or not, and judging whether the preparation queue and the execution queue are empty or not;
if the judgment results are both yes, determining that the task corresponding to the task request is executed completely;
and if any judgment result is negative, determining that the task corresponding to the task request is not completely executed.
5. The method of claim 1, the task request being: a request for extremum data is determined from the plurality of data.
6. The method according to claim 1, wherein determining and executing the task corresponding to the node to be executed to obtain an execution result, specifically comprises:
and determining a task corresponding to the node to be executed, sending the task to be executed to an executing party so that the executing party executes the task, and returning an execution result.
7. An apparatus for task execution, comprising:
the receiving module receives a task request;
the determining module is used for generating leaf nodes of a directed acyclic graph DAG according to the task request and determining the total number of the nodes of the DAG, wherein each leaf node of the DAG is used for splitting a task corresponding to the task request into a plurality of subtasks;
the execution module is used for taking the leaf node as a node to be executed, determining and executing a task corresponding to the node to be executed and obtaining an execution result;
the judging and generating module is used for judging whether the task corresponding to the task request is executed completely according to the number of nodes which execute the corresponding task and the total number of the nodes, if so, the executing result is used as a task result, if not, a downstream node is generated according to the executing result, the executing module takes the downstream node as a node to be executed, and the task corresponding to the node to be executed is continuously executed until the task corresponding to the task request is determined to be executed completely;
wherein the determining module is further configured to:
determining the total number of nodes of the DAG according to preset task assembly conditions and the number of the leaf nodes;
the execution module is specifically configured to:
determining nodes to be executed which meet the task assembly condition, adding the nodes to be executed to an execution queue, determining nodes to be executed which do not meet the task assembly condition, and adding the nodes to be executed to a preparation queue;
according to the task assembly condition, assembling and executing the task corresponding to the node to be executed in the execution queue;
the judgment generation module is further configured to:
adding the downstream node as a node to be executed to the preparation queue;
judging whether a node to be executed meeting the task assembly condition exists in the preparation queue;
if so, moving the nodes to be executed meeting the task assembling condition to the execution queue, and assembling and executing the tasks corresponding to the nodes to be executed in the execution queue according to the task assembling condition;
and if not, waiting for other nodes to be executed to be added to the preparation queue.
8. A server, comprising: one or more memories and processors, the memories storing programs and configured to perform, by the one or more processors, the steps of:
receiving a task request;
generating leaf nodes of a Directed Acyclic Graph (DAG) according to the task request, and determining the total number of the nodes of the DAG, wherein each leaf node of the DAG is used for splitting a task corresponding to the task request into a plurality of subtasks;
taking the leaf node as a node to be executed, determining and executing a task corresponding to the node to be executed, and obtaining an execution result;
judging whether the task corresponding to the task request is executed completely according to the number of the nodes which execute the corresponding task and the total number of the nodes;
if so, taking the execution result as a task result;
if not, generating a downstream node according to the execution result, taking the downstream node as a node to be executed, and continuing to execute the task corresponding to the node to be executed until the task corresponding to the task request is determined to be executed completely;
determining the total number of nodes of the DAG specifically comprises:
determining the total number of nodes of the DAG according to preset task assembly conditions and the number of the leaf nodes;
taking the leaf node as a node to be executed, determining and executing a task corresponding to the node to be executed, and specifically comprising:
determining nodes to be executed which meet the task assembly condition, adding the nodes to be executed to an execution queue, determining nodes to be executed which do not meet the task assembly condition, and adding the nodes to be executed to a preparation queue;
according to the task assembly condition, assembling and executing the task corresponding to the node to be executed in the execution queue;
taking the downstream node as a node to be executed, determining and executing a task corresponding to the node to be executed, and specifically comprising:
adding the downstream node as a node to be executed to the preparation queue;
judging whether a node to be executed meeting the task assembly condition exists in the preparation queue;
if so, moving the nodes to be executed meeting the task assembling condition to the execution queue, and assembling and executing the tasks corresponding to the nodes to be executed in the execution queue according to the task assembling condition;
and if not, waiting for other nodes to be executed to be added to the preparation queue.
Priority Applications (3)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711049658.1A CN109725989B (en) | 2017-10-31 | 2017-10-31 | Task execution method and device |
| PCT/CN2018/101567 WO2019085601A1 (en) | 2017-10-31 | 2018-08-21 | Task execution method and apparatus |
| TW107130566A TWI679581B (en) | 2017-10-31 | 2018-08-31 | Method and device for task execution |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711049658.1A CN109725989B (en) | 2017-10-31 | 2017-10-31 | Task execution method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109725989A CN109725989A (en) | 2019-05-07 |
| CN109725989B true CN109725989B (en) | 2020-07-31 |
Family
ID=66294248
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711049658.1A Active CN109725989B (en) | 2017-10-31 | 2017-10-31 | Task execution method and device |
Country Status (3)
| Country | Link |
|---|---|
| CN (1) | CN109725989B (en) |
| TW (1) | TWI679581B (en) |
| WO (1) | WO2019085601A1 (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112214289A (en) * | 2019-07-11 | 2021-01-12 | 腾讯科技（深圳）有限公司 | Task scheduling method and device, server and storage medium |
| CN112799797B (en) * | 2019-11-14 | 2024-04-16 | 北京沃东天骏信息技术有限公司 | Task management method and device |
| CN111581449B (en) * | 2020-05-18 | 2023-04-28 | 网易（杭州）网络有限公司 | Task node execution method and device, computer equipment and medium |
| CN112131297A (en) * | 2020-09-28 | 2020-12-25 | 广州亚信技术有限公司 | Data processing method, device, equipment and storage medium |
| CN112346842B (en) * | 2020-11-19 | 2024-03-26 | 广州嘉为科技有限公司 | Workflow task scheduling method based on directed acyclic graph |
| CN114035968B (en) * | 2022-01-10 | 2022-03-18 | 北京一流科技有限公司 | Conflict processing system and method for multi-stream parallelism |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103336723A (en) * | 2013-07-21 | 2013-10-02 | 哈尔滨理工大学 | Scheduling method for adapting to shortage of processor cores and based on critical paths |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI313437B (en) * | 2006-09-20 | 2009-08-11 | Nat Chiao Tung Universit | Matching method for interdependent scheduling |
| US8301755B2 (en) * | 2007-12-14 | 2012-10-30 | Bmc Software, Inc. | Impact propagation in a directed acyclic graph |
| TW201211509A (en) * | 2010-09-15 | 2012-03-16 | Tomtom Int Bv | Navigation devices |
| US9170843B2 (en) * | 2011-09-24 | 2015-10-27 | Elwha Llc | Data handling apparatus adapted for scheduling operations according to resource allocation based on entitlement |
| CN102945295B (en) * | 2012-10-15 | 2015-09-02 | 浪潮(北京)电子信息产业有限公司 | A kind of parallel acceleration method of Lattice Boltzmann Method and system |
| WO2016040666A1 (en) * | 2014-09-10 | 2016-03-17 | Amazon Technologies, Inc. | Scalable log-based transaction management |
| TWI537817B (en) * | 2014-09-18 | 2016-06-11 | 國立清華大學 | Method of finding a minimum and minimum finder utilizing the same |
| CN104536814B (en) * | 2015-01-16 | 2019-01-22 | 北京京东尚科信息技术有限公司 | A kind of method and system handling workflow |
| US10235337B2 (en) * | 2015-06-24 | 2019-03-19 | EMC IP Holding Company LLC | Distributed work flow using database replication |
| CN106339252B (en) * | 2015-07-08 | 2020-06-23 | 阿里巴巴集团控股有限公司 | Self-adaptive optimization method and device for distributed DAG system |
| CN107239468B (en) * | 2016-03-29 | 2020-11-10 | 创新先进技术有限公司 | Task node management method and device |
| CN106155791B (en) * | 2016-06-30 | 2019-05-07 | 电子科技大学 | A kind of workflow task dispatching method under distributed environment |
-
2017
- 2017-10-31 CN CN201711049658.1A patent/CN109725989B/en active Active
-
2018
- 2018-08-21 WO PCT/CN2018/101567 patent/WO2019085601A1/en active Application Filing
- 2018-08-31 TW TW107130566A patent/TWI679581B/en active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103336723A (en) * | 2013-07-21 | 2013-10-02 | 哈尔滨理工大学 | Scheduling method for adapting to shortage of processor cores and based on critical paths |
Non-Patent Citations (1)
| Title |
|---|
| "软件实现.Netflow流量处理的关键技术和算法";王华;《计算机工程》;20041230;第30卷(第S1期);第232-234页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2019085601A1 (en) | 2019-05-09 |
| TWI679581B (en) | 2019-12-11 |
| TW201918878A (en) | 2019-05-16 |
| CN109725989A (en) | 2019-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109725989B (en) | Task execution method and device | |
| CA3048739C (en) | Blockchain-based data processing method and equipment | |
| CN105183735B (en) | The querying method and inquiry unit of data | |
| CN110020542B (en) | Data reading and writing method and device and electronic equipment | |
| CN106899666B (en) | Data processing method and device for service identification | |
| CN108418851B (en) | Policy issuing system, method, device and equipment | |
| CN108173706B (en) | Service marking method, device and equipment under multi-service system | |
| CN110134668B (en) | Data migration method, device and equipment applied to blockchain | |
| CN108599973B (en) | Log association method, device and equipment | |
| CN110008018A (en) | A kind of batch tasks processing method, device and equipment | |
| CN107578338B (en) | Service publishing method, device and equipment | |
| CN108683692A (en) | A kind of service request processing method and device | |
| CN107451204B (en) | Data query method, device and equipment | |
| CN110633959A (en) | Method, device, equipment and medium for creating approval task based on graph structure | |
| CN114529417A (en) | Method for executing transaction, block chain, main node and slave node | |
| CN111144132A (en) | Semantic recognition method and device | |
| CN110020004B (en) | Data calculation method and engine | |
| CN109376988B (en) | Service data processing method and device | |
| CN112181378B (en) | Method and device for realizing business process | |
| CN108769152B (en) | Service refresh policy registration method, service refresh request method, device and equipment | |
| CN107392408B (en) | Credit score prompt information output method and device | |
| CN114968422A (en) | Method and device for automatically executing contracts based on variable state | |
| CN110032433B (en) | Task execution method, device, equipment and medium | |
| CN109636324B (en) | Electronic service contract processing method and device | |
| CN117041980B (en) | Network element management method and device, storage medium and electronic equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20201019 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Patentee after: Innovative advanced technology Co.,Ltd. Address before: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Patentee before: Advanced innovation technology Co.,Ltd. Effective date of registration: 20201019 Address after: Cayman Enterprise Centre, 27 Hospital Road, George Town, Grand Cayman Islands Patentee after: Advanced innovation technology Co.,Ltd. Address before: A four-storey 847 mailbox in Grand Cayman Capital Building, British Cayman Islands Patentee before: Alibaba Group Holding Ltd. |