QoS-based work chain orchestration method, apparatus, electronic device, and medium

Abstract

The present application provides a work chain orchestration method and apparatus based on quality of service (QoS), as well as an electronic device and a computer-readable medium. The work chain orchestration method is applied to a first network element and includes the steps of: acquiring QoS requirement parameters; generating a project-level QoS indicator for providing an overall quality of service guarantee for a service based on the acquired QoS requirement parameters; generating a domain-level QoS indicator for a second network element based on the project-level QoS indicator; querying a task list stored in the second network element to acquire tasks that satisfy the domain-level QoS indicator; and performing work chain orchestration on the acquired tasks based on the project-level QoS indicator, the domain-level QoS indicator, and the task list query results.

Description

[Technical Field]

[0001] The present disclosure relates to, but is not limited to, the computer and communications fields, and more particularly to a Quality of Service (QoS)-based workflow orchestration method and apparatus, and an electronic device and computer-readable medium. [Background technology]

[0002] As information and communications technology (ICT) technologies converge, future networks will no longer simply be bit-transmission pipelines; they will also be required to possess wireless sensing, computing power, intelligent service capabilities, network security, and reliable tradable capabilities. QoS is typically used to provide service guarantees in networks. Future networks will provide integrated services, and their scenario services may span multiple domains, including communications, sensing, computing, intelligent services, and secure, reliable, and tradable services. Because domains are spaces with a certain degree of specialization and independence, the corresponding QoS service guarantees must incorporate the characteristics of each domain. Traditional 5G QoS mechanisms use QoS profiles to describe the QoS characteristics and parameters of communication domains. However, due to the large differences between domain services in non-communication domains, QoS metrics cannot be shared. Because 5G QoS cannot be directly used to characterize services in other domains, each domain provides its own QoS metrics. Given the impossibility of unifying the QoS dimensions of each domain, numerous factors affect the overall QoS effect when multiple network domains cooperate to provide comprehensive services. Currently, there is no effective solution to guarantee the QoS of multi-domain integrated services. Summary of the Invention

[0003] To solve the problems in the related art that the QoS dimensions of each domain cannot be unified, the service capabilities and cooperation are weak, and the overall service guarantee effect for QoS is poor, the embodiments of the present application provide a QoS-based workflow orchestration method, apparatus, electronic device and medium.

[0004] In a first aspect, an embodiment of the present application provides a QoS-based work chain orchestration method, which is applied to a first network element and includes: acquiring QoS requirement parameters; generating a project-level QoS indicator for providing overall service quality guarantees for a service based on the acquired QoS requirement parameters; generating a domain-level QoS indicator for a second network element based on the project-level QoS indicator; querying a task list stored in the second network element to obtain tasks that satisfy the domain-level QoS indicator; and performing work chain orchestration on the obtained tasks based on the project-level QoS indicator, the domain-level QoS indicator, and the result of querying the task list.

[0005] In a second aspect, an embodiment of the present application provides a QoS-based work chain orchestration method that is applied to a second network element and includes the steps of receiving domain-level QoS indicators and task query information from a first network element, querying a task list of the second network element based on the domain-level QoS indicators and selecting a task that satisfies the domain-level QoS indicators based on task-level QoS information, feeding back the task list query result to the first network element, receiving a work chain orchestration result from the first network element, determining a task execution entity based on the work chain orchestration result and the domain-level QoS indicators, and notifying the task execution entity to execute a task according to the work chain orchestration result.

[0006] In a third aspect, an embodiment of the present application provides a QoS-based work chain orchestration device, which includes: a QoS management control unit disposed in a first network element, for generating a project-level QoS indicator and a domain-level QoS indicator, and for querying tasks and performing work chain orchestration of tasks based on the project-level QoS indicator and the domain-level QoS indicator, wherein the project-level QoS indicator is for providing overall service quality guarantee for a service, and the domain-level QoS indicator is generated based on the project-level QoS indicator.

[0007] In a fourth aspect, the present embodiment provides a QoS-based work chain orchestration device, including: a QoS task query unit, disposed in a second network element, for performing a task information query on a task list stored in the second network element, the task information query including at least one of a task name, task level QoS information, task description information, a task identifier, and a task execution entity; and a QoS task execution unit, for instructing a task entity to execute a task according to the QoS work chain orchestration result based on the task query result.

[0008] In a fifth aspect, an embodiment of the present application provides an electronic device including one or more processors and a memory in which one or more programs are stored, which is a first network element or is located within a first network element, and when the one or more programs are executed on the one or more processors, causes the one or more processors to perform the following operations: acquire QoS requirement parameters; generate a project-level QoS indicator for providing overall QoS guarantees for a service based on the acquired QoS requirement parameters; generate a domain-level service quality indicator for a second network element based on the project-level QoS indicator; query a task list stored in the second network element to acquire tasks that satisfy the domain-level QoS indicator; and perform work chain orchestration for the acquired tasks based on the project-level QoS indicator, the domain-level QoS indicator, and the result of querying the task list.

[0009] In a sixth aspect, an embodiment of the present application provides an electronic device including one or more processors and a memory in which one or more programs are stored, which is a second network element or is located within a second network element, and when the one or more programs are executed on the one or more processors, causes the one or more processors to perform the following operations: receive domain-level QoS indicators and task query information from a first network element; query a task list of the second network element based on the domain-level QoS indicators; select a task that satisfies the domain-level QoS indicators based on task-level QoS information; feed back the task list query result to the first network element; receive a work chain orchestration result from the first network element; determine a task execution entity based on the work chain orchestration result and the domain-level QoS indicators; and notify the task execution entity to execute a task according to the work chain orchestration result.

[0010] In a seventh aspect, the present embodiment provides a computer-readable medium having a computer program stored thereon, the computer program, when executed by a processor, implementing a method according to the first or second aspect above.

[0011] The QoS-based workflow orchestration method and apparatus, electronic device, and computer-readable medium provided in this application adopt the flow of obtaining QoS requirements, generating project-level QoS indicators, generating domain-level QoS indicators, querying QoS tasks, and orchestrating QoS workflows, thereby providing comprehensive QoS guarantees across multiple domains, fully utilizing the capabilities of each domain, and achieving the effect of an excellent overall service experience. [Brief explanation of the drawings]

[0012] The drawings are intended to provide a further understanding of the present application, constitute a part of the specification, and are used to interpret the technical solution of the present application together with the following specific embodiments, but are not intended to limit the present application. [Figure 1] 1 is a flowchart of a QoS-based workflow orchestration method according to an embodiment of the present application; [Figure 2] 2 is a flowchart of an exemplary operation for performing work chain orchestration on an acquired task in the embodiment of FIG. 1. [Figure 3] 2 is a flowchart of an exemplary operation after work chain orchestration is performed on an acquired task in the embodiment of FIG. 1. [Figure 4] 2 is a schematic diagram of an exemplary association of first and second network elements according to an embodiment of the present invention; [Figure 5] 2 is a schematic diagram of an exemplary association of first, second and third network elements according to an embodiment of the present invention; [Figure 6] 1 is a flowchart of another QoS-based workflow orchestration method according to an embodiment of the present application; [Figure 7] FIG. 1 is a block diagram illustrating a configuration of a work chain orchestration device according to an embodiment of the present invention. [Figure 8] FIG. 10 is a configuration block diagram of another work chain orchestration device according to an embodiment of the present invention. [Figure 9] 1 is a block diagram illustrating a configuration of an electronic device according to an embodiment of the present invention. [Figure 10] FIG. 10 is a block diagram illustrating the configuration of another electronic device according to an embodiment of the present invention. [Figure 11] FIG. 1 is a block diagram of a computer-readable medium according to an embodiment of the present invention. [Figure 12] FIG. 1 is a schematic diagram of QoS-based work chain orchestration and task execution according to Example 1; DETAILED DESCRIPTION OF THE INVENTION

[0013] In order to allow those skilled in the art to better understand the technical solution of the present application, the following provides a more detailed description of exemplary embodiments with reference to the drawings. However, the exemplary embodiments may be embodied in different ways and should not be construed as being limited to the embodiments described herein. The purpose of providing these examples is to make the present application clear and complete, and to allow those skilled in the art to fully understand the scope of the present application.

[0014] As used herein, the term "and / or" includes any and all combinations of one or more of the associated listed items.

[0015] The terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the claimed subject matter. As used herein, the singular forms "a," "an," and "the" are intended to include the plural, unless the context clearly indicates otherwise. Also, when used herein, the terms "comprises" and / or "comprising..." indicate the presence of the stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or groups thereof.

[0016] Although terms such as "first" and "second" are used herein to describe elements, components, regions, layers, and / or portions, it should be understood that these elements, components, regions, layers, and / or portions are not limited by these terms. These terms are used only to distinguish one element, component, region, layer, or portion from another element, component, region, layer, or portion. Thus, without departing from the teachings disclosed herein, a first element, first component, first region, first node, or first portion discussed below may be referred to as a second element, second component, second region, second node, or second portion. Furthermore, a first element, first component, first region, first node, or first portion in one embodiment may be different from a first element, first component, first region, first node, or first portion in another embodiment.

[0017] Unless otherwise specified, all terms (including technical and scientific terms) and features used in this specification have the same meaning as those commonly understood by a person of ordinary skill in the art to which the subject matter disclosed in this specification belongs. Furthermore, terms defined in common dictionaries should be understood to have the same meaning as in the relevant art, and should not be interpreted as having an idealized meaning or an excessively formal meaning unless clearly limited in this specification.

[0018] It should be further understood that the description of a feature or aspect in each exemplary embodiment should generally be considered applicable to other similar features or aspects in other exemplary embodiments, unless otherwise clear from the context. Unless inconsistent, each embodiment and each feature in each embodiment and each feature in each embodiment can be combined with each other.

[0019] In a first aspect, an embodiment of the present application provides a workflow orchestration method based on QoS (Quality of Service), which is applied to a first network element and includes the following steps S11 to S15, as shown in FIG.

[0020] In step S11, the QoS requirement parameters are obtained.

[0021] In this embodiment, the first network element obtains QoS requirement parameters related to the service, and these requirement parameters are used as reference for formulating project-level QoS indicators.

[0022] In some alternative embodiments, the first network element may include one of a QoS management control entity, a QoS management control layer, a QoS management control network element, a QoS management control function, a QoS management control node, a core network, an access network, a cloud platform, an orchestrator, a control plane entity, a user plane entity, a management plane entity, a task management control entity, and a QoS management control agent. The QoS management control entity may be a functional entity for QoS management control in a network.

[0023] When the first network element is a QoS management control entity, for example, the QoS management control entity may be a functional entity dedicated to QoS management control in a network, such as a functional entity corresponding to a cloud platform function module, a functional entity in a CU (Centralized Unit), or a functional entity in a DU (Distributed Unit), and the QoS management control entity may be located in a certain control network element of the core network, such as a core network PCF (Policy Control function) or a core network SMF (Session Management function) network element, and the QoS management control entity may be located in an access network protocol layer, which is one of protocol layers such as an RRC (Radio Resource Control) layer, an SDAP (Service Data Adaptation Protocol) layer, a PDCP (Packet Data Convergence Protocol) layer, an RLC (Radio Link Control) layer, a MAC (Medium Access Control) layer, or a physical layer.

[0024] In some alternative embodiments, the first network element may obtain the QoS requirement parameters from other network elements via an interface, may obtain the QoS requirement parameters by its own sensing and analysis, or may use both.

[0025] 5, in some alternative embodiments, the step of the first network element obtaining the QoS requirement parameters may include the first network element obtaining the QoS requirement parameters from a third network element via a first interface, the first interface being an interface between the first network element and the third network element, the third network element being one or more network elements capable of interacting with the first network element and from which the QoS requirement parameters can be obtained.

[0026] In some alternative embodiments, the step of the first network element (or the third network element) obtaining the QoS request parameters may include at least one of generating the QoS request parameters by sensing network information, converting network intent into the QoS request parameters based on an intent network, generating the QoS request parameters by performing big data analysis and artificial intelligence (AI) inference on historical network data, generating the QoS request parameters by sensing capabilities of the second network element, and generating the QoS request parameters by sensing capabilities in domains such as communications, sensing, computing power, AI, and security.

[0027] The network information may include, but is not limited to, at least one of network state information, service request information, user request information, network scenario information, and network environment information. The second network element is one or more network elements that can interact with the first network element and store a task list themselves (described in detail below).

[0028] In some alternative embodiments, the QoS requirement parameters may include, but are not limited to, at least one of bandwidth, data rate, throughput, delay, jitter, priority, accuracy, resolution, computing power, storage capacity, intelligence level, reliability, and dependability.

[0029] In step S12, a project-level QoS index is generated based on the acquired QoS requirement parameters to provide an overall service quality guarantee for the service. In this embodiment, the first network element can generate one or more project-level QoS indicators based on the acquired QoS requirement parameters, which are used to provide overall service quality guarantee for the service, in other words, the project-level QoS indicators are comprehensive indicators for the entire service.

[0030] For example, if the QoS requirement parameters include reliability and the QoS reliability requirement parameters range from 1 to 10, indicating reliability from low to high, the first network element (e.g., QoS management control entity) can generate two project-level QoS indicators based on the reliability requirement parameter of 10: an ultra-low delay indicator "maximum delay=1 microsecond" and an ultra-high reliability indicator "reliability=99.99999%".

[0031] In some alternative embodiments, the first network element can map the obtained QoS requirement parameters to project-level QoS indicators through comprehensive analysis.

[0032] In step S13, a domain-level QoS indicator of the second network element is generated based on the project-level QoS indicator.

[0033] In this embodiment, the first network element generates one or more domain-level QoS indicators for the second network element based on the generated project-level QoS indicators.

[0034] In some alternative embodiments, according to a classification criterion, the "domain" in the present embodiment may include, but is not limited to, at least one of a communication domain, a sensing domain, a computational domain, an intelligent domain (AI domain), and a security domain. According to another classification criterion, the "domain" may include, but is not limited to, at least one of a core network domain, an access network domain, a transport network domain, a terminal domain, a wired domain, and a wireless domain. Furthermore, different classification criteria may be combined if they are not contradictory. For example, the generated domain-level QoS metric may include a security domain QoS metric and a wireless domain QoS metric.

[0035] In some alternative embodiments, the step of generating a domain-level QoS index for the second network element based on the project-level QoS index may include directly converting the project-level QoS index into a domain-level QoS index for a single domain, or decomposing the project-level QoS index into domain-level QoS indexes for multiple domains.

[0036] For example, if the project-level QoS indicator is a project-level data transmission rate, directly mapping the project-level data transmission rate to the data rate of the communication domain belongs to the scheme of directly mapping one project-level QoS indicator to a QoS indicator of a single domain. In another example, decomposing a project-level QoS certainty indicator into communication domain certainty indicators (e.g., delay, jitter, time window, etc.) and sensing domain certainty indicators (e.g., sensing accuracy, resolution, positioning accuracy) belongs to the scheme of decomposing one project-level QoS indicator into multiple domain-level QoS indicators.

[0037] In some alternative embodiments, the decomposition of the project-level QoS index into domain-level QoS indexes for multiple domains can be performed by at least one of the following methods: directly dividing the project-level QoS index according to the domain; decomposing the project-level QoS index for different domains using weighting factors; decomposing the project-level QoS index using an optimization method that cycles through multiple combinations; and decomposing the project-level QoS index using an optimization method that uses a theoretical formula.

[0038] For example, decomposing project-level QoS metrics using weighting factors for different domains can be used to generate domain-specific QoS priority indicators for each domain. For example, in a multi-domain integration scenario where communications is the primary focus, the communications domain QoS priority is high, while the other domains have low QoS priorities. When decomposing project-level QoS indicators into multiple domains, different weighting factors can be used to control the weighting and QoS priority of the QoS indicators for each domain. The weighting factors can be used to achieve a balance between domains. For example, in the AI ​​domain, longer model training time leads to higher accuracy, but increases AI latency. To ensure the total service latency, the communications domain latency must be reduced, which may limit the successful transmission of communications services. Controlling the latency weighting of the AI ​​domain, communications domain, and computing domain using weighting factors helps to provide an optimal solution for service latency. For example, if the project-level QoS indicator has a total service delay requirement of less than 25 ms (milliseconds) and a relatively high ratio of the AI ​​domain delay requirement indicator, the delay requirement can be decomposed into: calculation domain delay requirement: 5 ms, AI domain delay requirement: 10 ms, sensing domain delay requirement: 5 ms, and communication domain delay requirement: 5 ms. For example, if the project-level QoS indicator has a total service delay requirement of less than 25 ms and a relatively low ratio of the AI ​​domain delay requirement indicator, the delay requirement can be decomposed into: calculation domain delay requirement: 5 ms, AI domain delay requirement: 5 ms, sensing domain delay requirement: 5 ms, and communication domain delay requirement: 10 ms.

[0039] In step S14, query the task list stored in the second network element to obtain the tasks that satisfy the domain-level QoS indicators.

[0040] In this embodiment, the first network element can query the task list stored in the second network element to obtain intra-domain tasks that satisfy each domain-level QoS indicator.

[0041] In the present embodiment, the second network element may include at least one of a domain level entity, a domain level network element, a task execution node, a base station, a terminal, a core network, an integrated network element with multi-domain capabilities, an intelligent network element that combines communication and computing capabilities, and an intelligent sensing network element that combines communication and computing capabilities.

[0042] In some alternative embodiments, the results of the task list query may include, but are not limited to, at least one of task name, task level QoS information, task description information, task identifier, and task execution entity.

[0043] In some alternative embodiments, the first network element may query a suitable task from a task list stored in the second network element based on the domain-level QoS indicator and set a task-level QoS indicator for the queried task.

[0044] In step S15, work chain orchestration is performed on the acquired tasks based on the project-level QoS indicators, the domain-level QoS indicators, and the result of the task list query.

[0045] In some alternative embodiments, the step of performing work chain orchestration for the acquired tasks may include at least one of identifying a chronological relationship between each task, determining an integration form for each task, determining a conflict resolution priority for each task, determining trigger conditions for starting and ending each task, performing full life cycle management for each task, determining a pipeline for task execution, determining that each task is to be executed serially, determining that each task is to be executed in parallel, or determining that each task is to be executed in a mixed serial and parallel manner.

[0046] In some alternative embodiments, the step of performing work chain orchestration for the acquired task may include at least one of selecting task components from a component library, establishing a plurality of component association relationships, and performing component processing on the data stream based on the plurality of component association relationships.

[0047] For example, as shown in FIG. 2, the step of performing work chain orchestration on the acquired task may include sequentially executing the following steps S151 to S153.

[0048] In step S151, a task component is selected from the component library.

[0049] In step S152, a plurality of component association relationships are established.

[0050] In step S153, component processing is performed on the data stream based on a plurality of component association relationships.

[0051] In addition, the work chain orchestration performed on the above acquired tasks is applicable not only to multi-task orchestration collaboration under multi-domain comprehensive service guarantee, but also to multi-task orchestration collaboration of single-domain services.

[0052] In some alternative embodiments, if the result of the task list query includes task-level QoS information, performing work chain orchestration for the retrieved task may include selecting components required to perform the task based on the task-level QoS information, or selecting components required to perform the task based on the task-level QoS information and component-level QoS information associated with the components. In the latter case, for example, the first network element may select appropriate components based on the task-level QoS information, set component-level QoS metrics for the components, and perform work chain orchestration for the task components based on the component-level QoS metrics.

[0053] In some alternative embodiments, if a task-level QoS metric is set for the queried task, performing workchain orchestration for the retrieved task may include performing workchain orchestration of the task based on the task-level QoS metric.

[0054] The above task-level QoS index refers to selecting tasks based on domain-level QoS indexes, and is a QoS index corresponding to each task. The above component-level QoS index refers to completing task-level QoS in a domain and selecting appropriate components, and is a QoS index corresponding to each component.

[0055] Different services have different corresponding QoS indicators, which means that network resources must be provided to meet the QoS of the service. However, network resources are limited, and rational resource adjustment based on QoS indicators is necessary to fully utilize network resources and achieve energy savings and emission reductions. In some alternative embodiments, the ebb and flow phenomenon can be utilized during workflow orchestration to assign tasks with high real-time requirements to earlier timelines and higher priorities, and tasks with low real-time requirements to later timelines and lower priorities. For example, workflow orchestration can ensure that real-time tasks, such as voice, video, and real-time calculations, are executed first during daytime resources when resources are tight. At night, when resources are surplus, non-real-time tasks, such as automatic software updates and AI offline task training, can be executed.

[0056] In some alternative embodiments, to achieve a comprehensive QoS index, the workflow orchestration method may be a multi-task collaboration method. For example, when an AI task performs model training inference, collaboration with a computation task is required. For example, when a sensing task performs data collection, data processing and adjustment is required, which also requires a computation task to provide a guarantee.

[0057] In some alternative embodiments, to achieve a unified QoS index, the workflow orchestration method for tasks may be such that multiple network elements execute different tasks in a distributed manner, where the QoS management control entity sends tasks to different network elements, which then execute them regularly according to the requirements of the workflow.

[0058] The QoS-based workflow orchestration method provided in the embodiments of the present application adopts the steps of obtaining QoS requirements, generating project-level QoS indicators, generating domain-level QoS indicators, querying QoS tasks, and orchestrating QoS workflows, thereby providing comprehensive QoS guarantees across multiple domains, fully utilizing the capabilities of each domain, and achieving the effect of an excellent overall service experience.

[0059] In addition, in some optional embodiments, after the step of performing work chain orchestration on the acquired task, the first network element may further perform at least one of the following: sending a result of the work chain orchestration to a second network element; sending a task instruction to a task execution entity corresponding to each task in the work chain based on the result of the work chain orchestration; obtaining task execution results fed back from the execution entities; adjusting the project-level QoS indicators; adjusting the domain-level QoS indicators; and adjusting the result of the work chain orchestration.

[0060] The task execution entity may be a network element that executes a task, including but not limited to at least one of a communication control network element, a computational power control network element, a sensing control network element, an AI control network element, and a security control network element.

[0061] In addition, there may be an interface between the first network element (e.g., QoS management control entity) and the network element that executes the task. The information transmitted by the first network element to the interface of the network element that executes the task through the interface includes, but is not limited to, at least one of a task ID and a resource provided for the task. The information transmitted by the network element that executes the task to the first network element through the interface includes, but is not limited to, at least one of a task ID, a task execution status, a task execution result, and a resource occupied for the task execution.

[0062] For example, as shown in FIG. 3, after the first network element completes the work chain orchestration, it can perform the following steps S161 to S163. In step S161, based on the result of the work chain orchestration, a task instruction is sent to a task execution entity corresponding to each task in the work chain.

[0063] In step S162, the task execution result fed back from the execution entity is acquired.

[0064] In step S163, at least one of the project-level QoS indicator, the domain-level QoS indicator, and the result of the work chain orchestration is adjusted.

[0065] This allows the first network element to determine whether the result of the task execution reaches the projected QoS target and / or satisfies the actual QoS requirement. Based on the evaluation of the effect, the QoS management control entity adjusts the multi-domain QoS overall indicators, each domain indicator, the work chain orchestration method, and the task component orchestration method.

[0066] It should be noted that the above steps S161 to S163 may be repeatedly performed as necessary to obtain a suitable QoS mechanism scheme through iterative circulation.

[0067] In some alternative embodiments, after the step of performing work chain orchestration on the acquired task, the second network element may further perform at least one of the following operations: receiving a result of the work chain orchestration from the first network element; sending task instructions to task execution entities corresponding to each task in the work chain based on the result of the work chain orchestration; performing component orchestration on the tasks in the work chain based on the result of the work chain orchestration; determining a task execution entity based on the result of the work chain orchestration and the domain-level QoS indicator; notifying the task execution entity to execute a task according to the result of the work chain orchestration; obtaining the task execution result fed back from the execution entity; sending the task execution result fed back from the execution entity to the first network element; and receiving the adjusted work chain orchestration result from the first network element.

[0068] In other words, the task instruction may be sent to the task execution entity via the first network element or via the second network element as needed, and the task execution result may be fed back directly to the first network element by the task execution entity or fed back to the first network element via the second network element by the task execution entity.

[0069] In some alternative embodiments, as shown in Figures 4 and 5, the first network element exchanges information with the second network element via a second interface, the exchange including, but not limited to, at least one of: the first network element sending task query information to the second network element, the first network element obtaining a task query result fed back by the second network element, the first network element sending a task execution command to the second network element, the first network element sending a work chain orchestration result to the second network element, and the first network element obtaining a task execution result fed back by the second network element.

[0070] In a second aspect, the present embodiment provides a QoS-based workflow orchestration method, which is applied to a second network element, and includes the following steps S21 to S26, as shown in FIG. In step S21, receive domain level QoS indicators and task query information from a first network element.

[0071] In step S22, query the task list of the second network element based on the domain level QoS indicator, and select a task that satisfies the domain level QoS indicator based on task level QoS information.

[0072] In step S23, the task list query result is fed back to the first network element.

[0073] In step S24, receive a work chain orchestration result from the first network element.

[0074] In some alternative embodiments, the work chain orchestration results include, but are not limited to, at least one of task name, task number, task level QoS indicator, task execution entity, task execution rule, task priority, task collaboration relationship, and component orchestration instruction.

[0075] In step S25, a task execution entity is determined based on the work chain orchestration result and the domain level QoS indicator.

[0076] In step S26, the task execution entity is notified to execute a task according to the work chain orchestration result. In some alternative embodiments, between step S24 and step S26, the method may further include performing component orchestration on tasks in the work chain based on the work chain orchestration result.

[0077] In some alternative embodiments, when the work chain orchestration result includes the task-level QoS indicator, performing component orchestration for the tasks in the work chain may include selecting components to perform component orchestration based on the task-level QoS indicator, or selecting components to perform component orchestration based on the task-level QoS indicator and component-level QoS information associated with the components.

[0078] In a third aspect, as shown in FIG. 7 , the present embodiment provides a QoS-based work chain orchestration device 10, which includes a QoS management control unit 11 disposed in a first network element, for generating a project-level QoS indicator and a domain-level QoS indicator, and for querying tasks and performing work chain orchestration of tasks based on the project-level QoS indicator and the domain-level QoS indicator, wherein the project-level QoS indicator is for providing overall service quality guarantee for services, and the domain-level QoS indicator is generated based on the project-level QoS indicator.

[0079] In some alternative embodiments, the QoS management control unit 11 is further used to adjust the project-level QoS indicators, the domain-level QoS indicators and the results of the work chain orchestration based on task execution results.

[0080] In some alternative embodiments, the QoS management control unit 11 is further used to sense QoS requirements and generate the project-level QoS index based on the sensed QoS requirements.

[0081] In some alternative embodiments, the QoS management control unit 11 may be used to implement the first step or steps of the QoS-based work chain orchestration method provided in the first aspect above.

[0082] In a fourth aspect, as shown in FIG. 8 , the present embodiment provides a QoS-based work chain orchestration apparatus 20 disposed in a second network element, which includes a QoS task query unit 21 and a QoS task execution unit 22.

[0083] The QoS task query unit 21 is used to perform a task information query on the task list stored in the second network element, and the task information query includes, but is not limited to, at least one of task name, task-level QoS information, task description information, task identifier, and task execution entity.

[0084] The QoS task execution unit 22 is used to instruct a task entity to execute a task according to the QoS work chain orchestration result based on the task query result.

[0085] 9 , in a fifth aspect, an embodiment of the present application further provides an electronic device including one or more processors 101 and a memory 102 storing one or more computer programs. The electronic device is the above-mentioned first network element or is located within the above-mentioned first network element. When the one or more processors 101 execute the one or more programs, the one or more processors 101 perform the following operations: acquire QoS requirement parameters; generate a project-level QoS indicator based on the acquired QoS requirement parameters to provide an overall service quality guarantee for the service; generate a domain-level QoS indicator for a second network element based on the project-level QoS indicator; query a task list stored in the second network element to acquire tasks that satisfy the domain-level QoS indicator; and perform work chain orchestration for the acquired tasks based on the project-level QoS indicator, the domain-level QoS indicator, and a result of querying the task list.

[0086] The above operations and related concepts have already been specifically described in the first embodiment, and will not be described again here.

[0087] In some alternative embodiments, when the one or more processors 101 execute the one or more programs, the one or more processors 101 can implement the QoS-based work chain orchestration method described in the first aspect above.

[0088] The electronic device may further include one or more I / O interfaces 103 connected between the processor 101 and the memory 102 and arranged to enable information exchange between the processor 101 and the memory 102.

[0089] The processor 101 is a device having data processing capabilities, including but not limited to a central processing unit (CPU), the memory 102 is a device having data storage capabilities, including but not limited to random access memory (RAM, more specifically, SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), and flash memory (FLASH), and the I / O interface (read / write interface) 103 is connected between the processor 101 and the memory 102 to enable information exchange between the processor 101 and the memory 102, including but not limited to a data bus 104.

[0090] In some alternative embodiments, the electronic device is a QoS-based workflow orchestration apparatus according to the third aspect above.

[0091] In a sixth aspect, referring to FIG. 10 , an embodiment of the present application further provides another electronic device including one or more processors 101a and a memory 102a storing one or more computer programs. The electronic device is the above-mentioned second network element or is located within the second network element. When the one or more processors 101a execute the one or more programs, the one or more processors 101a perform the following operations: receiving domain-level QoS indicators and task query information from a first network element; querying a task list of the second network element based on the domain-level QoS indicators; selecting a task that satisfies the domain-level QoS indicators based on the task-level QoS information; feeding back a task list query result to the first network element; receiving a work chain orchestration result from the first network element; determining a task execution entity based on the work chain orchestration result and the domain-level QoS indicators; and notifying the task execution entity to execute a task according to the work chain orchestration result. The specific explanation of the above operation and related concepts has already been given in the second embodiment, so it will not be repeated here.

[0092] In some alternative embodiments, when the one or more processors 101a execute the one or more programs, the one or more processors 101a can implement the QoS-based work chain orchestration method described in the second aspect above.

[0093] The electronic device may further include one or more I / O interfaces 103a, which are connected between the processor 101a and the memory 102a and arranged to enable information exchange between the processor 101a and the memory 102a.

[0094] In some alternative embodiments, the electronic device is a QoS-based workflow orchestration apparatus according to the fourth aspect above. In a seventh aspect, referring to FIG. 11, an embodiment of the present application provides a computer-readable medium on which a computer program is stored, which, when executed by a processor, realizes any of the QoS-based workflow orchestration methods according to the embodiment of the present application.

[0095] In order to more intuitively express the specific implementation process of the data transmission method in the embodiments of the present application, some examples are listed below for explanation, which are not used to limit the scope of the claims of the embodiments of the present application.

[0096] Example 1 FIG. 12 is a schematic diagram of QoS-based workflow orchestration and task execution according to this example. In this example, a first network element is a QoS management control entity, and second network elements are domain-level entities for the sensing domain, communications domain, AI domain, computing domain, and security domain. Each second network element stores a task list. For example, the second network element in the sensing domain stores data collection tasks, data processing tasks, data reporting tasks, etc.; the second network element in the communications domain stores network access tasks, data forwarding tasks, routing address tasks, etc.; the second network element in the AI ​​domain stores machine learning tasks, model training tasks, knowledge base construction tasks, etc.; the second network element in the computing domain (also called the computation domain) stores free computing power allocation tasks, computing resource statistics tasks, computing resource guarantee tasks, etc.; and the second network element in the security domain stores fault detection tasks, anomaly analysis tasks, risk avoidance tasks, etc. In addition, there is an interface between the first network element and each second network element. The interface is for obtaining QoS requests, converting them into QoS indicators, and feeding back and negotiating the requests.

[0097] The QoS management control entity acquires the QoS requirement parameters, generates a project-level QoS index (also referred to as a multi-domain QoS comprehensive index) based on the acquired QoS requirement parameters, and then decomposes the project-level QoS index into domain-level QoS indexes for the sensing domain, the communication domain, the AI ​​domain, the computational power domain, and the security domain based on the capability information of each domain service or task. Optionally, the QoS management control entity arranges each domain capability information before decomposing the index. Optionally, each domain reports its domain capability information to the QoS management control entity before decomposing the index.

[0098] The QoS management control entity then selects appropriate tasks from each domain by querying the task list of each domain and orchestrates an executable work chain (in Figure 12, a work chain is orchestrated in which each task is executed in a mixed serial and parallel manner).

[0099] Example 2 This example illustrates the enhancement of QoS reliability in industrial Internet scenarios achieved by the QoS-based workflow orchestration method of the present application embodiment.

[0100] Industrial Internet services involve multiple domains, such as communications, sensing, computing power, and intelligence (AI), and the typical QoS indicators that correspond to their reliability are reflected in five aspects: delay, jitter, packet loss rate, bandwidth, and reliability. QoS-based workflow orchestration can integrate and consider the capabilities of each domain to achieve high reliability guarantees.

[0101] In this example, for example, the first network element is a QoS management control entity, and the second network element is an intelligent sensing network element that combines notification and calculation functions.

[0102] After a service request is raised in the factory Internet scenario, the first network element cooperates with the second network element to perform the following steps 1 to 4 of the QoS-based work chain orchestration:

[0103] Step 1: Obtain the QoS requirement parameters and convert the QoS requirements into a QoS certainty comprehensive (overall) index as a project-level QoS index.

[0104] Specifically, the QoS management and control entity forms a QoS reliability comprehensive index based on the requirements obtained from the industrial Internet physical network, for example, the QoS requirement parameters are to maintain high reliability within a certain period of time, and the QoS comprehensive index converted from the high reliability requirement is a traffic total delay requirement of less than 25 ms, a bandwidth of at least 10 MHz, and a packet loss rate of less than 0.1%.

[0105] Step 2: Decompose the QoS assurance comprehensive index into domain-level QoS indexes.

[0106] The QoS management control entity decomposes the overall QoS reliability index into a sensing domain reliability index, a communication domain reliability index, a computational domain reliability index, and an intelligent domain reliability index based on the capabilities of each domain. For example, to meet the overall index with a total delay requirement of 25 ms or more, the delay is decomposed into a computational domain delay of 5 ms, an AI domain delay of 10 ms, a sensing domain delay of 5 ms, and a communication domain delay of 5 ms, resulting in a total delay of 5 + 10 + 5 + 5 = 25 ms. For example, the packet loss rate is equivalent to the packet loss rate of communication domain data transmission, and the bandwidth index is equivalent to the communication domain spectrum resource bandwidth.

[0107] Step 3: Certainty task query.

[0108] Based on the reliability index of each domain, the QoS management control entity queries the reliability tasks within the domain. For example, sensing domain tasks use sensors to collect environmental data and wirelessly sense the location information of automated guided vehicles (AGVs). Communication domain tasks include network topology planning, data transmission quality assurance, information synchronization, and optimal routing selection. Security domain tasks include fault detection and anomaly detection analysis, anomaly modeling, and risk prevention. AI domain tasks include intelligent domain tasks such as mapping to big data analysis, AI model training inference, and knowledge graph management. Computation domain tasks include free computing power allocation, computing power storage, and computing power resource assurance. To ensure high reliability in the above time period and meet the latency requirements of each domain in step 2, the QoS management control entity queries each domain task to determine the communication domain routing optimization and data transmission tasks, the computing domain free computing power query scheduling tasks, the sensing domain sensor data collection tasks, and the AI ​​domain AI model training inference tasks. The communication domain routing optimization and data transmission tasks ensure low latency, low jitter, and extremely low packet loss rates for data transmission. The computational domain task of scheduling available computational power queries can find hardware devices that meet computation and storage requirements and ensure the provision of computational power within a specified time period. The sensing domain task of collecting sensor data can ensure that the network obtains sufficient data samples in a timely manner. The AI ​​domain task of training and inferencing AI models provides intelligent services that may be constrained to avoid a decrease in reliability due to excessive training times.

[0109] Step 4: Workchain orchestration.

[0110] After the QoS management control entity receives a query for a task that satisfies the domain-level indicators, it orchestrates the workflow for the query based on the QoS assurance comprehensive indicator. For example, it first executes the sensing task of collecting sensor data, then transmits communication data, and then performs AI model training. For example, it first executes the sensing task of collecting sensor data, then allocates computing resources, then transmits communication data, and then performs AI model training.

[0111] By decomposing the reliability index and selectively orchestrating each domain task, the QoS architecture mechanism can be made to perform at its full potential and the optimal reliability solution can be achieved.

[0112] Example 3 This example illustrates cooperative sensing, cooperative communication, and intelligent computing power allocation in a multi-hop scenario, which is realized by the QoS-based workflow orchestration method of the present application.

[0113] Multi-hop scenarios such as IAB (Integrated Access and Backhaul) and D2D (Device to Device) require cooperative sensing, cooperative communication, and intelligent allocation of computing power.

[0114] The QoS-based workflow orchestration method of the present embodiment employs a QoS management control entity as a first network element, which can obtain information such as network element topology relationships and QoS requirements based on physical network data and requirements. During workflow orchestration, the QoS management control entity can comprehensively consider the network element topology relationships, QoS requirements, and QoS indicators to perform routing selection, task execution network element selection, and task execution timing determination. For example, the QoS management control entity determines the sensor location for performing a sensing task, which communication node will transmit the sensing data, and when to provide computational power guarantees based on the network element topology relationships, QoS requirements, and QoS indicators, thereby formulating rational tasks and task relationships to form a workflow.

[0115] Those skilled in the art will understand that all or part of the functional modules / units in the above-disclosed steps, systems, and devices may be implemented as software, firmware, hardware, and any suitable combination thereof.

[0116] In hardware embodiments, the division between functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components, for example, one physical component may have multiple functions, or one function or step may be performed by several physical components in cooperation.

[0117] Some or all of the physical components may be implemented as software executed by a processor, such as, for example, a central processing unit (CPU), digital signal processor, or microprocessor, or may be implemented as hardware or as an integrated circuit, such as a dedicated integrated circuit. Such software may be located on a computer-readable medium, which may include computer storage media (or non-transitory media) and communication media (or transitory media). As is well known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information, such as computer-readable commands, data structures, program modules, or other data. A computer-readable storage medium may be any medium used to store desired information and accessible by a computer, including, but not limited to, random access memory (RAM, more specifically SDRAM, DDR, etc.), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory (FLASH) or other magnetic disk memory, read-only optical disks (CD-ROMs), digital versatile disks (DVDs) or other optical disk memory, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic memory. Those skilled in the art will also recognize that communication media typically include computer-readable commands, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0118] Although illustrative embodiments have been disclosed and specific terms have been used herein, they are used in a general descriptive manner only and should be construed as such and not for purposes of limitation. It will be apparent to those skilled in the art that, unless expressly indicated otherwise, in some embodiments, the features, characteristics, and / or elements described in connection with a particular embodiment can be used alone or in combination with features, characteristics, and / or elements described in connection with other embodiments. Accordingly, those skilled in the art will recognize that changes in form and detail may be made without departing from the scope of the present application, as defined by the appended claims.

Claims

1. applied to a first network element, obtaining quality of service requirement parameters; generating a project-level service quality indicator based on the acquired service quality requirement parameters to provide an overall service quality guarantee for the service; generating a domain-level service quality indicator of a second network element based on the project-level service quality indicator; querying a task list stored in the second network element to obtain a task that satisfies the domain-level service quality indicator; performing work chain orchestration on the acquired tasks based on the project-level service quality indicators, the domain-level service quality indicators, and the query results of the task list; A work chain orchestration method based on quality of service.

2. the domain includes at least one of a communications domain, a sensing domain, a computational domain, an intelligent domain, and a security domain; The method of claim 1.

3. The domain includes at least one of a core network domain, an access network domain, a transport network domain, a terminal domain, a wired domain, and a wireless domain; The method of claim 1.

4. The step of performing work chain orchestration on the acquired task includes: Identifying the chronological relationship of each task; Deciding the collaboration form for each task; determining a conflict resolution priority for each task; determining trigger conditions for the start and end of each task; Full lifecycle management for each task, Identifying a pipeline of task execution; determining that each task is to be executed serially; determining that each task is to be executed in parallel; determining that each task is to be executed in a mixture of serial and parallel execution; The method of claim 1.

5. the task list query result includes at least one of a task name, task-level service quality information, task description information, task identifier, and task execution entity; The method of claim 1.

6. If the task list query result includes the task-level service quality information, performing a workflow orchestration on the acquired task includes: selecting components required to perform the task based on the task-level quality of service information; or selecting components required to perform the task based on the task-level service quality information and component-level service quality information associated with the components; The method of claim 5.

7. After performing the work chain orchestration on the acquired task, the first network element: sending a result of the work chain orchestration to the second network element; sending task instructions to task execution entities corresponding to each task in the work chain based on a result of the work chain orchestration; Obtaining task execution results fed back from the execution entities; and adjusting the project-level service quality indicator; adjusting the domain-level quality of service metric; and coordinating the results of the work chain orchestration.

7. The method according to any one of claims 1 to 6.

8. The step of obtaining the quality of service requirement parameters comprises: generating the service quality requirement parameters through sensing network information, the network information including at least one of network status information, service requirement information, user requirement information, network scene information, and network environment information; converting a network intent into the quality of service requirement parameters based on an intent network; generating the quality of service requirement parameters by performing big data analysis and artificial intelligence inference on network history data; generating the quality of service requirement parameters based on sensing the capabilities of the second network element; 7. The method according to any one of claims 1 to 6.

9. generating a domain-level service quality indicator of the second network element based on the project-level service quality indicator, The project-level service quality indicators are directly used as domain-level service quality indicators for a single domain; or decomposing the project-level service quality indicators into domain-level service quality indicators for a plurality of domains; 7. The method according to any one of claims 1 to 6.

10. Decomposing the project-level service quality indicators into domain-level service quality indicators for a plurality of domains includes: A direct division of project-level service quality metrics according to domains is also possible. A method for decomposing project-level service quality indicators using weighting factors for different domains; A method of decomposing project-level service quality indicators using an optimization method that cycles through multiple combinations; and a method of decomposing project-level service quality indicators using an optimization method using a theoretical formula; 10. The method of claim 9.

11. The step of performing work chain orchestration for each acquired task includes: Selecting a task component from the component library; Building a plurality of component association relationships; performing component processing on the data stream based on a plurality of component association relationships; 7. The method according to any one of claims 1 to 6.

12. The first network element: at least one of a quality of service management control entity, a quality of service management control layer, a quality of service management control network element, a quality of service management control function, a quality of service management control node, a core network, an access network, a cloud platform, an orchestrator, a control plane entity, a user plane entity, a management plane entity, a task management control entity, and a quality of service management control agent; 7. The method according to any one of claims 1 to 6.

13. The second network element: The network includes at least one of a domain level entity, a domain level network element, a task execution node, a base station, a terminal, a core network, an integrated network element with multi-domain functionality, an intelligent network element with integrated communication and computation functionality, and an intelligent sensing network element with integrated communication and computation functionality; 7. The method according to any one of claims 1 to 6.

14. The first network element obtains the quality of service requirement parameters through a first interface, and the first interface is an interface between the first network element and a third network element; 7. The method according to any one of claims 1 to 6.

15. The first network element communicates with the second network element via a second interface, the communication including: The method includes at least one of: the first network element sending task query information to the second network element; the first network element obtaining the task query result fed back by the second network element; the first network element sending a task execution command to the second network element; the first network element sending a work chain orchestration result to the second network element; and the first network element obtaining the task execution result fed back by the second network element.

7. The method according to any one of claims 1 to 6.

16. applied to a second network element, receiving domain-level service quality indicators and task query information from a first network element; querying a task list of the second network element based on the domain-level service quality indicator, and selecting a task that satisfies the domain-level service quality indicator based on task-level service quality information; feeding back a task list query result to the first network element; receiving a work chain orchestration result from the first network element; determining a task execution entity based on the work chain orchestration result and the domain-level service quality indicator; notifying the task execution entity to execute a task according to the work chain orchestration result; A work chain orchestration method based on quality of service.

17. The workflow orchestration result is: at least one of a task name, a task number, a task-level service quality indicator, a task execution entity, a task execution rule, a task priority, a task collaboration relationship, and a component orchestration instruction; 17. The method of claim 16.

18. performing component orchestration on tasks in the work chain based on the work chain orchestration result; performing component orchestration on tasks in the work chain, Performing component orchestration based on the task-level service quality metric selection component; or selecting components for component orchestration based on the task-level service quality indicators and component-level service quality information associated with the components; 18. The method of claim 17.

19. disposed in a first network element; a service quality management control unit for generating a project level service quality indicator and a domain level service quality indicator, and querying a task based on the project level service quality indicator and the domain level service quality indicator to perform work chain orchestration of the task; The project-level service quality indicator is for providing an overall service quality guarantee for the service, and the domain-level service quality indicator is generated based on the project-level service quality indicator. A work chain orchestration device based on quality of service.

20. disposed in a second network element; a service quality task query unit for querying task information, including at least one of task name, task level service quality information, task description information, task identifier, and task execution entity, against the task list stored in the second network element; a quality of service task execution unit for instructing a task entity to execute a task according to the quality of service work chain orchestration result based on the task query result; A work chain orchestration device based on quality of service.

21. one or more processors; a memory in which one or more programs are stored; being a first network element or being located within the first network element; When the one or more programs are executed by the one or more processors, the one or more processors are Obtaining quality of service request parameters; Generate a project-level service quality indicator based on the acquired service quality requirement parameters to provide an overall service quality guarantee for the service; Generate a domain-level service quality indicator of the second network element based on the project-level service quality indicator; Querying a task list stored in the second network element to obtain a task that satisfies the domain-level service quality indicator; Performing a workflow orchestration on the acquired tasks based on the project-level service quality indicators, the domain-level service quality indicators, and the query results of the task list; Electronic devices.

22. When the one or more programs are executed by the one or more processors, the one or more processors are causing the second network element to transmit a result of the work chain orchestration; Sending task instructions to task execution entities corresponding to each task in the work chain based on the result of the work chain orchestration; obtaining task execution results fed back from the execution entities; adjusting the project-level service quality indicator; adjusting the domain-level quality of service indicator; Coordinating the result of the workflow orchestration; and further realizing the operation; 22. The electronic device of claim 21.

23. the domain includes at least one of a communications domain, a sensing domain, a computational domain, an intelligent domain, and a security domain; the first network element comprises one of a quality of service management control entity, a quality of service management control layer, a quality of service management control network element, a quality of service management control function, a quality of service management control node, a core network, an access network, a cloud platform, an orchestrator, a control plane entity, a user plane entity, a management plane entity, a task management control entity, and a quality of service management control agent; The second network element includes at least one of a domain level entity, a domain level network element, a task execution node, a base station, a terminal, a core network, an integrated network element with multi-domain functions, an intelligent network element with integrated communication and computing capabilities, and an intelligent sensing network element with integrated communication and computing capabilities; the task list query result includes at least one of a task name, task-level service quality information, task description information, task identifier, and task execution entity; 23. An electronic device according to claim 21 or 22.

24. one or more processors; a memory in which one or more programs are stored; being or located within the second network element; When the one or more programs are executed by the one or more processors, the one or more processors are receiving domain-level service quality indicators and task query information from the first network element; Querying a task list of the second network element based on the domain-level service quality indicator, and selecting a task that satisfies the domain-level service quality indicator based on task-level service quality information; Feedback a task list query result to the first network element; receiving a work chain orchestration result from the first network element; determining a task execution entity based on the work chain orchestration result and the domain-level service quality indicator; notifying the task execution entity to execute a task according to the work chain orchestration result; Electronic devices.

25. A computer program is stored, which, when executed by a processor, implements the method according to any one of claims 1 to 18. Computer-readable medium.

Images