Operation processing methods, nodes, system and storage medium

Abstract

Provided in the present disclosure are operation processing methods, nodes, a system, and a storage medium. A method comprises: if quality-of-service (QoS) information cannot be satisfied, sending a first request to a second node, wherein the first request is used for requesting the second node to perform QoS coordination. The present disclosure ensures the QoS of a first node, and ensures the performance of AI services by means of QoS coordination, improving the availability and reliability of the AI services.

Description

Operation processing methods, nodes, systems, and storage media Technical Field

[0001] This disclosure relates to the field of communications, and more particularly to operation processing methods, nodes, systems, and storage media. Background Technology

[0002] Currently, distributed, efficient, energy-saving, and secure artificial intelligence (AI) services and open ecosystems can be built by leveraging network resources and functions such as connectivity, computing, data, and models. Summary of the Invention

[0003] To improve the performance of AI services, embodiments of this disclosure provide an operation processing method, node, system, and storage medium.

[0004] According to a first aspect of the present disclosure, an operation processing method is provided, the method being executed by a first node, the method comprising:

[0005] If the QoS information cannot be met, a first request is sent to the second node; wherein, the first request is used to request the second node to perform QoS coordination.

[0006] According to a second aspect of the present disclosure, an operation processing method is provided, the method being executed by a second node, the method comprising:

[0007] Receive a first request sent by the first node; wherein the first request is used to request the second node to perform QoS coordination;

[0008] Based on the first request, QoS coordination is performed.

[0009] According to a third aspect of the present disclosure, an operation processing method is provided, the method being executed by a third node, the method comprising:

[0010] Send a first indication message to the first node; wherein the first indication message is used to indicate whether to perform QoS coordination.

[0011] According to a third aspect of the present disclosure, an operation processing method is provided, the method being executed by a fourth node, the method comprising:

[0012] Send a second indication message to the first node; wherein the second indication message is used to identify the second node.

[0013] According to a fifth aspect of the present disclosure, an operation processing method is provided, the method being executed by an associated node, the method comprising:

[0014] Update the Quality of Service (QoS) information of the associated node; wherein the associated node is a node associated with the QoS information of the first node.

[0015] According to a sixth aspect of the present disclosure, an operation processing method is provided, the method being executed by a fifth node, the method comprising:

[0016] Receive an update request sent by a second node; wherein the update request is used to request an update of the Quality of Service (QoS) information of an associated node, and the associated node is a node associated with the QoS information of the first node;

[0017] Based on the update request, a fourth indication message is sent to the associated node; wherein the fourth indication message is used to update the QoS information of the associated node.

[0018] According to a seventh aspect of the present disclosure, a first node is provided, the first node comprising:

[0019] The transceiver module is configured to send a first request to the second node when it is unable to meet the Quality of Service (QoS) information; wherein the first request is used to request the second node to perform QoS coordination.

[0020] According to an eighth aspect of the present disclosure, a second node is provided, the second node comprising:

[0021] The transceiver module is configured to receive a first request sent by the first node; wherein the first request is used to request the second node to perform QoS coordination;

[0022] The processing module is configured to determine the updated QoS of the second node based on the first request.

[0023] According to a ninth aspect of the present disclosure, a third node is provided, the third node comprising:

[0024] The transceiver module is configured to send first indication information to the first node; wherein the first indication information is used to indicate whether to perform QoS coordination.

[0025] According to a tenth aspect of the present disclosure, a fourth node is provided, the fourth node comprising:

[0026] The transceiver module is configured to send second indication information to the first node; wherein the second indication information is used to identify the second node.

[0027] According to an eleventh aspect of the present disclosure, an associated node is provided, the associated node comprising:

[0028] The processing module is configured to update the Quality of Service (QoS) information of the associated node; wherein the associated node is a node associated with the QoS information of the first node.

[0029] According to a twelfth aspect of the present disclosure, a fifth node is provided, the fifth node comprising:

[0030] The transceiver module is configured to receive an update request sent by a second node; wherein the update request is used to request an update of the Quality of Service (QoS) information of an associated node, and the associated node is a node associated with the QoS information of the first node.

[0031] The transceiver module is further configured to send a fourth indication information to the associated node based on the update request; wherein the fourth indication information is used to update the QoS information of the associated node.

[0032] According to a thirteenth aspect of the present disclosure, a first node is provided, comprising:

[0033] One or more processors;

[0034] The processor is used to execute the operation processing method described in any one of the first aspects.

[0035] According to a fourteenth aspect of the present disclosure, a second node is provided, comprising:

[0036] One or more processors;

[0037] The processor is used to execute the operation processing method described in any one of the second aspects.

[0038] According to a fifteenth aspect of the present disclosure, a third node is provided, comprising:

[0039] One or more processors;

[0040] The processor is used to execute the operation processing method described in any one of the third aspects.

[0041] According to a sixteenth aspect of the present disclosure, a fourth node is provided, comprising:

[0042] One or more processors;

[0043] The processor is used to execute the operation processing method described in any one of the fourth aspects.

[0044] According to a seventeenth aspect of the present disclosure, an associated node is provided, comprising:

[0045] One or more processors;

[0046] The processor is used to execute the operation processing method described in any one of the fifth aspects.

[0047] According to an eighteenth aspect of the present disclosure, a fifth node is provided, comprising:

[0048] One or more processors;

[0049] The processor is used to execute the operation processing method described in any one of the sixth aspects.

[0050] According to a nineteenth aspect of the present disclosure, a communication system is provided, comprising:

[0051] A first node, configured to perform the operation processing method described in any one of the first aspects;

[0052] The second node is configured to perform the operation processing method described in any one of the second aspects;

[0053] A third node, wherein the third node is configured to perform the operation processing method described in any one of the third aspects;

[0054] The fourth node is configured to perform the operation processing method described in any one of the fourth aspects;

[0055] An associated node, wherein the associated node is configured to perform the operation processing method described in any of the fifth aspects;

[0056] The fifth node is configured to perform the operation processing method described in any one of the sixth aspects.

[0057] According to a twentieth aspect of the present disclosure, a storage medium is provided that stores instructions that, when executed on a communication device, cause the communication device to perform an operation processing method as described in any one of the first, second, third, fourth, fifth, or sixth aspects.

[0058] According to a twenty-first aspect of the present disclosure, a computer program product is provided, including a computer program that, when executed by a processor, is used to implement the operation processing method described in any one of the first, second, third, fourth, fifth, or sixth aspects.

[0059] In this embodiment of the disclosure, the first node can request the second node to perform QoS coordination if the QoS information cannot be met. Through QoS coordination, the performance of AI services is ensured, thereby improving the availability and reliability of AI services.

[0060] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0061] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0062] Figure 1A is an exemplary schematic diagram of the architecture of a communication system provided according to an embodiment of the present disclosure.

[0063] Figure 1B is a schematic diagram of QoS profile parameters provided according to an embodiment of the present disclosure.

[0064] Figure 2 is an exemplary interactive schematic diagram of an operation processing method provided according to an embodiment of the present disclosure.

[0065] Figure 3A is one of the exemplary flowcharts of an operation processing method provided according to an embodiment of the present disclosure.

[0066] Figure 3B is a second exemplary flowchart of an operation processing method provided according to an embodiment of the present disclosure.

[0067] Figure 3C is a third exemplary flowchart of an operation processing method provided according to an embodiment of the present disclosure.

[0068] Figure 3D is a fourth exemplary flowchart of an operation processing method provided according to an embodiment of the present disclosure.

[0069] Figure 3E is a fifth exemplary flowchart of an operation processing method provided according to an embodiment of the present disclosure.

[0070] Figure 3F is a sixth exemplary flowchart of an operation processing method provided according to an embodiment of the present disclosure.

[0071] Figure 4A is an exemplary block diagram of a first node provided according to an embodiment of the present disclosure.

[0072] Figure 4B is an exemplary block diagram of a second node provided according to an embodiment of the present disclosure.

[0073] Figure 4C is an exemplary block diagram of a third node provided according to an embodiment of the present disclosure.

[0074] Figure 4D is an exemplary block diagram of a fourth node provided according to an embodiment of the present disclosure.

[0075] Figure 4E is an exemplary block diagram of an associated node provided according to an embodiment of the present disclosure.

[0076] Figure 4F is an exemplary block diagram of a fifth node provided according to an embodiment of the present disclosure.

[0077] Figure 5A is an exemplary block diagram of a communication device provided according to an embodiment of the present disclosure.

[0078] Figure 5B is an exemplary block diagram of a chip provided according to an embodiment of the present disclosure. Detailed Implementation

[0079] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.

[0080] This disclosure provides an operation processing method, node, system, and storage medium.

[0081] In a first aspect, embodiments of this disclosure propose an operation processing method, which is executed by a first node. The method includes: if the Quality of Service (QoS) information cannot be satisfied, sending a first request to a second node; wherein the first request is used to request the second node to perform QoS coordination.

[0082] In the above embodiments, the first node can request the second node to perform QoS coordination, which ensures the QoS of the first node. Through QoS coordination, the performance of AI services is ensured, and the availability and reliability of AI services are improved.

[0083] In conjunction with some embodiments of the first aspect, in some embodiments, the first request includes at least one of the following: information of the first node; QoS information of the first node; a first reason; wherein the first reason is used to indicate the reason for performing the first operation; information of a fourth node; wherein the fourth node is a node associated with the QoS information of the first node.

[0084] In the above embodiments, the first request may include at least one of the above-mentioned items to assist the second node in QoS coordination, thereby improving the availability and reliability of AI services.

[0085] In conjunction with some embodiments of the first aspect, in some embodiments, the QoS information of the first node includes at least one of the following: QoS information satisfied by the first node; QoS information that the first node cannot satisfy; and QoS information used by the first node.

[0086] In the above embodiments, the QoS of the first node includes at least one of the above-mentioned features to assist the second node in performing QoS updates, thereby improving the availability and reliability of AI services.

[0087] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes: performing a first operation; wherein the first operation includes determining whether to perform QoS coordination and / or determining the second node.

[0088] In the above embodiments, the first node can perform the first operation to request the second node to perform QoS coordination, thereby improving the availability and reliability of AI services.

[0089] In conjunction with some embodiments of the first aspect, in some embodiments, determining whether to perform QoS coordination includes at least one of the following: determining whether to perform QoS coordination based on a predefined method; determining whether to perform QoS coordination based on first indication information sent by a third node; wherein the first indication information is used to indicate whether to perform QoS coordination.

[0090] In the above embodiments, the first node can use at least one of the above methods to determine whether to perform QoS coordination, which is simple to implement and has high availability.

[0091] In conjunction with some embodiments of the first aspect, in some embodiments, the third node includes at least one of the following: a node that configures the QoS information of the first node; a node that controls QoS coordination.

[0092] In the above embodiments, the third node may include at least one of the above-mentioned features, which is simple to implement and highly usable.

[0093] In conjunction with some embodiments of the first aspect, in some embodiments, determining the second node includes at least one of the following: determining the second node based on a predefined method; determining the second node based on second indication information sent by the fourth node; wherein the second indication information is used to determine the second node.

[0094] In the above embodiments, the first node can determine the second node using at least one of the above methods, which is simple to implement and highly usable.

[0095] In conjunction with some embodiments of the first aspect, in some embodiments, the fourth node includes at least one of the following: a node that configures the QoS information of the first node; a node that controls QoS coordination.

[0096] In the above embodiments, the fourth node may include at least one of the above-mentioned features, which is simple to implement and highly usable.

[0097] In conjunction with some embodiments of the first aspect, in some embodiments, the second node includes at least one of the following: a node that configures the QoS information of the first node; a node that controls QoS coordination; and a node whose QoS information type is at the same level as the first node.

[0098] In the above embodiments, the second node can be at least one of the aforementioned nodes, which improves the reliability and availability of QoS coordination.

[0099] In conjunction with some embodiments of the first aspect, in some embodiments, the QoS information includes at least one of the following: QoS information of artificial intelligence (AI) services; QoS information of artificial intelligence (AI) tasks; and QoS information of artificial intelligence (AI) resources.

[0100] The above embodiments can implement a three-layer guarantee mechanism of AI services, AI tasks, and AI resources, resulting in high availability.

[0101] In conjunction with some embodiments of the first aspect, in some embodiments, QoS coordination includes at least one of the following: QoS coordination between the first node and an associated node; wherein, after coordination, the QoS information of the first node satisfies the QoS information of the AI ​​service and / or satisfies the QoS information of the first node, and the associated node is a node associated with the QoS information of the first node; QoS coordination between the first node and a second node; wherein, after coordination, the QoS information of the first node satisfies the QoS information of the AI ​​service and / or satisfies the QoS information of the first node.

[0102] In the above embodiments, the QoS information of AI services and / or the QoS information of the first node are ensured. The performance of AI services is ensured through QoS coordination, thereby improving the availability and reliability of AI services.

[0103] Secondly, embodiments of this disclosure propose an operation processing method, which is executed by a second node. The method includes: receiving a first request sent by a first node; wherein the first request is used to request the second node to perform QoS coordination; and performing QoS coordination based on the first request.

[0104] In conjunction with some embodiments of the second aspect, in some embodiments, the first request includes at least one of the following: information about the first node; QoS information about the first node; a first reason; wherein the first reason is used to indicate the reason for the first node to perform a first operation, the first operation including determining whether to perform QoS coordination and / or determining the second node; information about an associated node; wherein the associated node is a node associated with the QoS information of the first node.

[0105] In conjunction with some embodiments of the second aspect, in some embodiments, the QoS information of the first node includes at least one of the following: QoS information satisfied by the first node; QoS information that the first node cannot satisfy; and QoS information used by the first node.

[0106] In conjunction with some embodiments of the second aspect, in some embodiments, the second node includes at least one of the following: a node that configures the QoS information of the first node; a node that controls QoS coordination; and a node whose QoS information type is at the same level as the first node.

[0107] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes: receiving multiple first requests sent by multiple first nodes, and at least two of the multiple first requests conflicting, determining the priority of each first request; and performing QoS coordination in descending order of the priority of the first requests.

[0108] In conjunction with some embodiments of the second aspect, in some embodiments, the QoS coordination includes at least one of the following: QoS coordination between the first node and an associated node; wherein, after coordination, the QoS information of the first node satisfies the QoS information of the AI ​​service and / or satisfies the QoS information of the first node, and the associated node is a node associated with the QoS information of the first node; QoS coordination between the first node and the second node; wherein, after coordination, the QoS information of the first node satisfies the QoS information of the AI ​​service and / or satisfies the QoS information of the first node.

[0109] In conjunction with some embodiments of the second aspect, in some embodiments, the QoS coordination includes: determining the QoS information of the first node after coordination based on the QoS information of the AI ​​service and / or the QoS information of the first node; and determining the QoS information of the associated nodes after coordination based on the QoS information of the first node after coordination.

[0110] In conjunction with some embodiments of the second aspect, in some embodiments, the QoS coordination includes: determining the QoS information of the first node after coordination based on the QoS information of the AI ​​service and / or the QoS information of the first node; determining the QoS information of the second node after coordination based on the QoS information of the first node after coordination; and performing QoS update based on the QoS information of the second node after coordination.

[0111] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes: sending third indication information to the associated node; wherein the third indication information is used to update the QoS information of the associated node.

[0112] In conjunction with some embodiments of the second aspect, in some embodiments, the third indication information includes at least one of the following: QoS information of the first node; QoS information of the associated node after collaboration.

[0113] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes: sending an update request to a fifth node; wherein the update request is used to request the fifth node to update the QoS information of the fourth node.

[0114] In conjunction with some embodiments of the second aspect, in some embodiments, the fifth node includes at least one of the following: a node that configures the QoS of the associated node; a node that controls QoS coordination.

[0115] In conjunction with some embodiments of the second aspect, in some embodiments, the QoS information includes at least one of the following: QoS information of artificial intelligence (AI) services; QoS information of artificial intelligence (AI) tasks; and QoS information of artificial intelligence (AI) resources.

[0116] Thirdly, this disclosure provides an operation processing method, which is executed by a third node. The method includes: sending first indication information to a first node; wherein the first indication information is used to indicate whether to perform QoS coordination.

[0117] In conjunction with some embodiments of the third aspect, in some embodiments, the third node includes at least one of the following: a node that configures the QoS information of the first node; a node that controls QoS coordination.

[0118] In conjunction with some embodiments of the third aspect, the QoS information types include at least one of the following categories in some embodiments: QoS information for artificial intelligence (AI) services; QoS information for artificial intelligence (AI) tasks; and QoS information for artificial intelligence (AI) resources.

[0119] In conjunction with some embodiments of the third aspect, in some embodiments, QoS coordination includes at least one of the following: QoS coordination between the first node and an associated node; wherein, after coordination, the QoS information of the first node satisfies the QoS information of the AI ​​service and / or satisfies the QoS information of the first node, and the associated node is a node associated with the QoS information of the first node; QoS coordination between the first node and the second node; wherein, after coordination, the QoS information of the first node satisfies the QoS information of the AI ​​service and / or satisfies the QoS information of the first node.

[0120] Fourthly, this disclosure provides an operation processing method, which is executed by a fourth node. The method includes: sending second indication information to a first node; wherein the second indication information is used to determine a second node.

[0121] In conjunction with some embodiments of the fourth aspect, in some embodiments, the second node includes at least one of the following: a node that configures the QoS information of the first node; a node that controls QoS coordination; and a node whose QoS information type is at the same level as the first node.

[0122] In conjunction with some embodiments of the fourth aspect, in some embodiments, QoS coordination includes at least one of the following: QoS coordination between the first node and an associated node; wherein, after coordination, the QoS information of the first node satisfies the QoS information of the AI ​​service and / or satisfies the QoS information of the first node, and the associated node is a node associated with the QoS information of the first node; QoS coordination between the first node and the second node; wherein, after coordination, the QoS information of the first node satisfies the QoS information of the AI ​​service and / or satisfies the QoS information of the first node.

[0123] In conjunction with some embodiments of the fourth aspect, in some embodiments, the QoS information includes at least one of the following: QoS information of artificial intelligence (AI) services; QoS information of artificial intelligence (AI) tasks; and QoS information of artificial intelligence (AI) resources.

[0124] In conjunction with some embodiments of the fourth aspect, in some embodiments, QoS coordination includes at least one of the following: QoS coordination between the first node and an associated node; wherein, after coordination, the QoS information of the first node satisfies the QoS information of the AI ​​service and / or satisfies the QoS information of the first node, and the associated node is a node associated with the QoS information of the first node; QoS coordination between the first node and the second node; wherein, after coordination, the QoS information of the first node satisfies the QoS information of the AI ​​service and / or satisfies the QoS information of the first node.

[0125] Fifthly, embodiments of this disclosure propose an operation processing method, the method being executed by a fourth node, the method comprising: sending second indication information to a first node; wherein the second indication information is used to determine a second node.

[0126] In conjunction with some embodiments of the fifth aspect, in some embodiments, the second node includes at least one of the following: a node that configures the QoS information of the first node; a node that controls QoS coordination; and a node whose QoS information type is at the same level as the first node.

[0127] In conjunction with some embodiments of the fifth aspect, in some embodiments, the QoS coordination includes at least one of the following: QoS coordination between the first node and an associated node; wherein, after coordination, the QoS information of the first node satisfies the QoS information of the AI ​​service and / or satisfies the QoS information of the first node, and the associated node is a node associated with the QoS information of the first node; QoS coordination between the first node and the second node; wherein, after coordination, the QoS information of the first node satisfies the QoS information of the AI ​​service and / or satisfies the QoS information of the first node.

[0128] In conjunction with some embodiments of the fifth aspect, in some embodiments, the fourth node includes at least one of the following: a node that configures the QoS information of the first node; a node that controls QoS coordination.

[0129] In a sixth aspect, embodiments of this disclosure propose an operation processing method, which is executed by a fifth node. The method includes: receiving an update request sent by a second node; wherein the update request is used to request an update of the Quality of Service (QoS) information of an associated node, the associated node being a node associated with the QoS information of a first node; and sending fourth indication information to the associated node based on the update request; wherein the fourth indication information is used to update the QoS information of the associated node.

[0130] In conjunction with some embodiments of the sixth aspect, in some embodiments, the fifth node includes at least one of the following: a node that configures the QoS information of the associated node; a node that controls QoS coordination.

[0131] In conjunction with some embodiments of the sixth aspect, in some embodiments, the QoS coordination includes at least one of the following: QoS coordination between the first node and an associated node; wherein, after coordination, the QoS information of the first node satisfies the QoS information of the AI ​​service and / or satisfies the QoS information of the first node, and the associated node is a node associated with the QoS information of the first node; QoS coordination between the first node and a second node; wherein, after coordination, the QoS information of the first node satisfies the QoS information of the AI ​​service and / or satisfies the QoS information of the first node.

[0132] In conjunction with some embodiments of the sixth aspect, in some embodiments, the QoS information includes at least one of the following: QoS information of artificial intelligence (AI) services; QoS information of artificial intelligence (AI) tasks; and QoS information of artificial intelligence (AI) resources.

[0133] In a seventh aspect, embodiments of this disclosure propose a first node, the first node comprising: a transceiver module configured to send a first request to a second node when QoS information cannot be satisfied; wherein the first request is used to request the second node to perform QoS coordination.

[0134] Eighthly, this disclosure provides a second node, the second node comprising: a transceiver module configured to receive a first request sent by a first node; wherein the first request is used to request the second node to perform QoS coordination; and a processing module configured to perform QoS coordination based on the first request.

[0135] In a ninth aspect, embodiments of this disclosure propose a third node, the third node comprising: a transceiver module configured to send first indication information to a first node; wherein the first indication information is used to indicate whether QoS coordination is performed.

[0136] In a tenth aspect, embodiments of this disclosure provide a fourth node, the fourth node comprising: a transceiver module configured to send second indication information to a first node; wherein the second indication information is used to determine a second node.

[0137] Eleventhly, embodiments of this disclosure propose an associated node, the associated node comprising: a processing module configured to update the Quality of Service (QoS) information of the associated node; wherein the associated node is a node associated with the QoS information of a first node.

[0138] In a twelfth aspect, embodiments of this disclosure propose a fifth node, the fifth node comprising: a transceiver module configured to receive an update request sent by a second node; wherein the update request is used to request an update of the Quality of Service (QoS) information of an associated node, the associated node being a node associated with the QoS information of a first node; the transceiver module is further configured to send fourth indication information to the associated node based on the update request; wherein the fourth indication information is used to update the QoS information of the associated node.

[0139] In a thirteenth aspect, embodiments of this disclosure provide a first node comprising: one or more processors; wherein the processors are configured to perform the operation processing method described in any one aspect.

[0140] In a fourteenth aspect, embodiments of this disclosure provide a second node comprising: one or more processors; wherein the processors are configured to perform the operation processing method described in any one aspect.

[0141] In a fifteenth aspect, embodiments of this disclosure provide a third node comprising: one or more processors; wherein the processors are configured to perform the operation processing method described in any one aspect.

[0142] In a sixteenth aspect, embodiments of this disclosure provide a fourth node comprising: one or more processors; wherein the processors are configured to perform the operation processing method described in any one aspect of the fourth aspect.

[0143] In a seventeenth aspect, embodiments of this disclosure provide an associated node comprising: one or more processors; wherein the processors are configured to perform the operation processing method described in any one of the fifth aspects.

[0144] In an eighteenth aspect, embodiments of this disclosure provide a fifth node comprising: one or more processors; wherein the processors are configured to perform the operation processing method described in any of the sixth aspects.

[0145] In a nineteenth aspect, embodiments of this disclosure provide a communication system comprising: a first node configured to perform an operation processing method as described in any one aspect; a second node configured to perform an operation processing method as described in any one aspect; a third node configured to perform an operation processing method as described in any one aspect; a fourth node configured to perform an operation processing method as described in any one aspect; an associated node configured to perform an operation processing method as described in any one aspect; and a fifth node configured to perform an operation processing method as described in any one aspect.

[0146] In a twentieth aspect, embodiments of this disclosure provide a storage medium storing instructions that, when executed on a communication device, cause the communication device to perform an operation processing method as described in any one of the first, second, third, fourth, fifth, or sixth aspects.

[0147] In a twentieth aspect, embodiments of this disclosure provide a computer program product, including a computer program that, when executed by a processor, is used to implement the operation processing method described in any one of the first, second, third, fourth, fifth, or sixth aspects.

[0148] Understandably, the aforementioned nodes, communication systems, and storage media are all used to execute the methods proposed in the embodiments of this disclosure. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.

[0149] This disclosure provides embodiments of an operation processing method, node, system, and storage medium. In some embodiments, the terms "operation processing method" and "communication method," "information processing method," etc., can be used interchangeably; the terms "operation processing apparatus" and "communication apparatus," "information processing apparatus," etc., can be used interchangeably; and the terms "operation processing system," "information processing system," "communication system," etc., can be used interchangeably.

[0150] This disclosure is not exhaustive, but merely illustrative of some embodiments, and is not intended to limit the scope of protection of this disclosure. Unless otherwise specified, each step in a particular embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a particular embodiment can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment can be arbitrarily interchanged. Furthermore, the optional implementation methods in a particular embodiment can be arbitrarily combined; moreover, the embodiments can be arbitrarily combined, for example, some or all steps of different embodiments can be arbitrarily combined, and a particular embodiment can be arbitrarily combined with the optional implementation methods of other embodiments.

[0151] In each of the disclosed embodiments, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of the embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0152] The terminology used in the embodiments of this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the scope of this disclosure.

[0153] In this embodiment of the disclosure, unless otherwise stated, elements expressed in the singular form, such as "a," "an," "the," "the aforementioned," "the," "this," etc., can mean "one and only one," or "one or more," "at least one," etc. For example, when using articles such as "a," "an," "the," etc. in translation, the noun following the article can be understood as either a singular expression or a plural expression.

[0154] In the embodiments disclosed herein, "multiple" refers to two or more.

[0155] In some embodiments, the terms “at least one of”, “one or more”, “a plurality of”, “multiple”, etc., may be used interchangeably.

[0156] In some embodiments, the notation "at least one of A and B", "A and / or B", "A in one case, B in another", "in response to one case A, in response to another case B", etc., may include the following technical solutions depending on the situation: in some embodiments, A (execute A regardless of B); in some embodiments, B (execute B regardless of A); in some embodiments, execution is selected from A and B (A and B are selectively executed); in some embodiments, A and B (both A and B are executed). The same applies when there are more branches such as A, B, C, etc.

[0157] In some embodiments, the notation "A or B" may include the following technical solutions, depending on the situation: in some embodiments, A (execution of A regardless of B); in some embodiments, B (execution of B regardless of A); in some embodiments, execution is selected from A and B (A and B are selectively executed). The same applies when there are more branches such as A, B, C, etc.

[0158] The prefixes "first," "second," etc., used in the embodiments of this disclosure are merely for distinguishing different descriptive objects and do not impose restrictions on the position, order, priority, quantity, or content of the descriptive objects. The description of the descriptive objects is found in the claims or the context of the embodiments, and the use of prefixes should not constitute unnecessary restrictions. For example, if the descriptive object is a "field," the ordinal numbers preceding "field" in "first field" and "second field" do not restrict the position or order of the "fields." "First" and "second" do not restrict whether the "fields" they modify are in the same message, nor do they restrict the order of "first field" and "second field." Similarly, if the descriptive object is a "level," the ordinal numbers preceding "level" in "first level" and "second level" do not restrict the priority between "levels." Furthermore, the number of descriptive objects is not limited by ordinal numbers and can be one or more. For example, in "first device," the number of "devices" can be one or more. Furthermore, the objects modified by different prefixes can be the same or different. For example, if the object being described is "device", then "first device" and "second device" can be the same device or different devices, and their types can be the same or different. Similarly, if the object being described is "information", then "first information" and "second information" can be the same information or different information, and their content can be the same or different.

[0159] In some embodiments, “including A,” “containing A,” “for indicating A,” and “carrying A” can be interpreted as directly carrying A or indirectly indicating A.

[0160] In some embodiments, the apparatus and device may be interpreted as physical or virtual, and their names are not limited to those described in the embodiments. In some cases, they may also be understood as "equipment", "device", "circuit", "network element", "node", "function", "unit", "section", "system", "network", "entity", "body", etc.

[0161] In some embodiments, the acquisition of data, information, etc., may comply with the laws and regulations of the country where the location is situated.

[0162] In some embodiments, data, information, etc., may be obtained with the user's consent.

[0163] Furthermore, each element, each row, or each column in the table of this disclosure can be implemented as an independent embodiment, and any combination of any element, any row, or any column can also be implemented as an independent embodiment.

[0164] Figure 1A is a schematic diagram of the architecture of a communication system according to an embodiment of the present disclosure.

[0165] As shown in Figure 1A, the communication system 100 includes at least one of the following: a first node 101, a second node 102, a third node 103, a fourth node 104, an associated node 105, and a fifth node 1066.

[0166] In some embodiments, the first node 101 may refer to initiating a QoS coordination request when the Quality of Service (QoS) information cannot be met, thereby ensuring that the QoS information of the entire service will not be compromised due to its own QoS information not being met.

[0167] In some embodiments, the second node 102 may refer to performing QoS coordination after receiving the QoS coordination request sent by the first node 101, which includes at least updating the QoS information of the first node 101, thereby ensuring that the QoS information of the entire service will not be compromised due to the QoS information of the first node 101 not being satisfied.

[0168] In some embodiments, the third node 103 may refer to the node that configures the QoS information of the first node 101, and / or the node that controls QoS coordination.

[0169] In some embodiments, the fourth node 104 may refer to the node that configures the QoS information of the first node 101, and / or the node that controls QoS coordination.

[0170] In some embodiments, controlling QoS coordination includes, but is not limited to, controlling the QoS coordination process between nodes.

[0171] In some embodiments, associated node 105 may refer to a node associated with the QoS information of the first node 101. It is understood that being associated with the QoS information of the first node 101 can refer to a node capable of influencing the QoS information of the first node 101, and / or a node whose QoS information changes will affect its own QoS information. For example, a change in the QoS information of associated node 105 can improve or decrease the QoS information of the first node 101. Furthermore, a change in the QoS information of the first node 101 will change the QoS information of associated node 105.

[0172] In some embodiments, the fifth node 106 may refer to the node that configures the QoS information of the associated node 105, and / or the node that controls the first node 101 to perform the first operation, wherein the first operation includes, but is not limited to, determining whether to perform QoS coordination and / or determining the second node 102.

[0173] In some embodiments, the second node 102 and the third node 103 can be the same node. For example, the second node 102 and the third node 103 are the same node that configures the QoS information of the first node 101. Another example is that the second node 102 and the third node 103 are the same QoS coordination control node.

[0174] In some embodiments, the second node 102 and the associated node 104 can be the same node. For example, the second node 102 is a sibling node associated with the QoS information of the first node 101.

[0175] In some embodiments, the third node 103 and the associated node 105 can be the same node. For example, the third node 103 and the associated node 105 are the same node that configures the QoS information of the first node 101.

[0176] In some embodiments, the third node 103 and the fourth node 104 may be the same node, for example, the third node 103 and the fourth node 104 are the same node that configures the QoS information of the first node 101.

[0177] In some embodiments, the third node 103 and the fifth node 106 may be the same node. For example, the third node 103 and the fifth node 106 may be QoS configuration nodes, which may configure the QoS information of the first node 101 and the QoS information of the associated node 105.

[0178] The above is merely an illustrative example, and this disclosure does not limit whether the above nodes are the same node.

[0179] In some embodiments, the nodes described above can be ordinary terminals, such as mobile phones, wearable devices, automobiles with communication functions, smart cars, tablets, computers with wireless transceiver functions, virtual reality (VR) terminal devices, augmented reality (AR) terminal devices, wireless terminal devices in industrial control, wireless terminal devices in self-driving, wireless terminal devices in remote medical surgery, wireless terminal devices in smart grids, wireless terminal devices in transportation safety, wireless terminal devices in smart cities, and wireless terminal devices in smart homes, but not limited to these.

[0180] In some embodiments, at least one of the above nodes may be at least one of an access network device and a core network device.

[0181] The access network equipment includes, for example, nodes or devices that connect ordinary terminals or intermediate nodes to the wireless network. The access network equipment may include, but is not limited to, at least one of the following in a 5G communication system: evolved Node B (eNB), next-generation evolved Node B (ng-eNB), next-generation Node B (gNB), node B (NB), home node B (HNB), home evolved node B (HeNB), radio backhaul equipment, radio network controller (RNC), base station controller (BSC), base transceiver station (BTS), base band unit (BBU), mobile switching center, base station in a 6G communication system, open RAN, cloud RAN, base station in other communication systems, and access node in a Wi-Fi system.

[0182] The access network equipment can be composed of a central unit (CU) and a distributed unit (DU). The CU can also be called a control unit. The CU-DU structure can separate the protocol layer of the access network equipment. Some of the protocol layer functions are centrally controlled by the CU, while the remaining part or all of the protocol layer functions are distributed in the DU, which is centrally controlled by the CU. However, this is not the only option.

[0183] The core network equipment can be a single device, including one or more network elements, or multiple devices or a group of devices. Network elements can be virtual or physical. The core network includes, for example, at least one of the Evolved Packet Core (EPC), 5G Core Network (5GCN), and Next Generation Core (NGC).

[0184] In some embodiments, the technical solutions of this disclosure can be applied to the Open RAN architecture. In this case, the interfaces between or within access network devices involved in the embodiments of this disclosure can be transformed into internal interfaces of Open RAN. The processes and information interactions between these internal interfaces can be implemented by software or programs.

[0185] It is understood that the communication system described in this disclosure is for the purpose of more clearly illustrating the technical solutions of this disclosure, and does not constitute a limitation on the technical solutions proposed in this disclosure. As those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical solutions proposed in this disclosure are also applicable to similar technical problems.

[0186] The following embodiments of this disclosure can be applied to the communication system 100 shown in FIG1A, or to some of the main bodies, but are not limited thereto. The main bodies shown in FIG1A are illustrative. The communication system may include all or some of the main bodies in FIG1A, or it may include other main bodies outside of FIG1A. The number and form of each main body are arbitrary. Each main body may be physical or virtual. The connection relationship between the main bodies is illustrative. The main bodies may not be connected or may be connected. The connection can be in any way, it can be a direct connection or an indirect connection, it can be a wired connection or a wireless connection.

[0187] In some embodiments, the concepts involved in this disclosure are described as follows:

[0188] 1. 6G AI:

[0189] Communication networks, such as future 6G networks, will provide efficient end-to-end support for AI-related services and applications, intelligently connecting distributed intelligent agents to enable large-scale AI deployment across various industries. AI services and applications include both intelligent capabilities provided for the performance optimization of the 6G network itself, i.e., AI for Network (AI4NET), such as using end-to-end AI to achieve customized optimization and automated operation and maintenance of the air interface and network, providing the best solutions to meet diverse needs, and intelligent capabilities provided to third-party services, i.e., Network for AI (NET4AI), such as accelerating the evolution from centralized cloud intelligence to deep edge ubiquitous intelligence by leveraging the native integrated communication, computing, and sensing capabilities of 6G network elements, providing a distributed learning infrastructure for AI.

[0190] 6G AI services primarily address demands for high real-time performance, high security and privacy, and low overall energy consumption. They enable AI training and inference within the network, providing intelligent capabilities adaptable to various application scenarios. As a native intelligent architecture, the 6G network, through its resources and functions such as communication, computing, datasets, and basic models, possesses efficient training and inference capabilities for large-scale distributed AI. This provides users with ubiquitous, high-performance AI services while reducing the communication and computing overhead associated with training and deploying ultra-large-scale AI models, thus offering a low-carbon, energy-efficient, and open ecosystem.

[0191] 6G AI services primarily address demands for high real-time performance, high security and privacy, and low overall energy consumption. They enable AI training and inference within the network, providing intelligent capabilities adaptable to various application scenarios. As a native intelligent architecture, the 6G network, through its resources and functions such as communication, computing, datasets, and basic models, possesses efficient training and inference capabilities for large-scale distributed AI. This provides users with ubiquitous, high-performance AI services while reducing the communication and computing overhead associated with training and deploying ultra-large-scale AI models, thus offering a low-carbon, energy-efficient, and open ecosystem.

[0192] 2. QoS:

[0193] Quality of Service (QoS) refers to the performance characteristics of a network or service experienced by the user. Taking 5G networks as an example, QoS encompasses a range of factors, including but not limited to reliability, availability, latency, throughput, and traffic prioritization. These aspects play a crucial role in providing the best user experience and meeting the needs of various applications.

[0194] In a 5G core network, QoS is determined by QoS flows, which include at least one of Guaranteed Bit Rate (GBR), Non-Guaranteed Bit Rate (Non-GBR), and reflection flows for dynamic configuration. These QoS flows define specific quality parameters that can be applied to user plane traffic.

[0195] 2-1, GBR:

[0196] GBR can refer to the minimum bit rate that a network must guarantee to provide for a specific service or application at any given point in time. It is a quality of service guarantee that ensures critical applications or services have sufficient bandwidth and transmission rates within the network.

[0197] GBR can be applied in at least one of the following scenarios:

[0198] Real-time services: such as video conferencing, online games, telemedicine, and other applications that require stable bandwidth and low latency;

[0199] Mission-critical applications, such as industrial automation and intelligent transportation systems, have stringent requirements for the continuity and reliability of data transmission.

[0200] High-priority data streams: Certain data streams that require priority processing, such as urgent communications or the transmission of high-value content.

[0201] 2-2, non-GBR:

[0202] non-GBR refers to data streams or services that do not offer bandwidth guarantees. These services may be throttled or slowed down during network congestion, but can achieve better service quality when network resources are plentiful.

[0203] Non-GBR can be applied in at least one of the following scenarios:

[0204] Non-real-time services: such as email, file downloads, video on demand, etc., which do not require real-time transmission;

[0205] Background tasks: such as data backup and software updates, which can run in the background;

[0206] Low-priority traffic: For less important data streams, non-GBR services can be used to save bandwidth resources.

[0207] In some embodiments, each QoS flow in the 5G core network can be identified by a Quality of Service Flow ID (QFI). The QFI is a unique identifier for a specific QoS flow, allowing for precise management and control of traffic based on its specific quality requirements.

[0208] A, QoS traffic characteristics:

[0209] A key aspect of QoS in 5G core networks is the characterization of QoS parameters. These parameters define the specific requirements and guarantees for a given QoS profile. QoS profile parameters can be, for example, as shown in Figure 1B, and include, but are not limited to, at least one of the following: 5G QoS Identifier (5G QoS ID, 5QI), Allocation / Retention Priority (ARP), Reflective QoS Attributes (RQA), Guaranteed Flow Bit Rate (GFBR), Maximum Flow Bit Rate (MFBR), Notification Control, and Maximum Packet Loss Rate (MPLR).

[0210] The Session Management Function (SMF) provides QoS profiles to the Radio Access Network (RAN) through the Access and Mobility Management Function (AMF) at the N2 reference point, or pre-configures them directly in the RAN.

[0211] The QoS configuration file defines one or more QoS rules, along with options to associate QoS flow-level QoS parameters with these rules. QoS rules are responsible for specifying the specific behavior and processing of user plane traffic based on their respective QoS requirements. By associating QoS flow-level QoS parameters with these rules, further granularity and customization can be achieved to ensure optimal quality and performance for every flow within the network.

[0212] To implement and enforce defined QoS rules and parameters, the SMF provides the User Plane Function (UPF) with one or more Uplink (UL) and Downlink (DL) Packet Detection Rules (PDRs). These PDRs serve as guidelines for the UPF to properly process and handle user plane traffic, ensuring that required QoS guarantees are met. UL and DL PDRs play a crucial role in ensuring efficient traffic management across the entire network.

[0213] B, QoS configuration file:

[0214] The QoS profiles in the 5G core network contain specific QoS parameters for each QoS flow. These parameters ensure that the network can provide the necessary service levels and meet the QoS requirements of different flows.

[0215] Each QoS flow's QoS profile contains two basic QoS parameters: Allocation / Retention Priority (ARP) and a 5G QoS Identifier (5G QoS ID, 5QI). ARP determines the priority assigned to the QoS flow, enabling the network to allocate resources accordingly. 5QI represents the specific QoS class assigned to the flow, defining its associated quality characteristics and service level protocol.

[0216] For non-GBR QoS flows, the QoS profile may include an additional QoS parameter called Reflective QoS Attributes (RQA). RQA provides more information about the dynamic configuration requirements of non-GBR flows, allowing the network to adjust its behavior accordingly.

[0217] For GBR QoS flows, the QoS profile must include specific QoS parameters. These parameters include the Guaranteed Flow Bit Rate (GFBR) for both UL and DL, ensuring the minimum guaranteed bit rate for the flow. Additionally, the Maximum Flow Bit Rate (MFBR) for both UL and DL defines the upper limit of the flow bit rate. Optional parameters, such as {notification control, maximum packet loss rate (UL and DL)}, can be included to provide additional control for GBR flows and define acceptable levels of packet loss.

[0218] C, ARP:

[0219] In 5G core networks, ARP parameters included in QoS profiles serve multiple purposes. First, they allow the network to decide whether to accept or reject QoS flow establishment, modification, or switching requests, especially when resource constraints exist. By considering the ARP level of the requested flow, the network can determine whether its resource requirements can be met or whether it should be rejected due to resource limitations. Furthermore, ARP can be used to determine the priority of which QoS flows should be released and to free up resources during resource-constrained periods, thereby effectively managing resource allocation dynamically.

[0220] The ARP priority assigned to a QoS flow defines its relative importance in the network. ARP priorities range from 1 to 15, with 1 being the highest priority. This allows for fine-grained prioritization, enabling the network to differentiate between flows and allocate resources accordingly based on their assigned priorities. By assigning specific ARP priorities to QoS flows, the network can ensure that higher-priority flows receive preferential processing and resource allocation.

[0221] ARP preemption capability is another aspect determined by ARP parameters. It defines whether a QoS flow can obtain resources previously allocated to another QoS flow with a lower ARP priority. When resources become scarce, a higher-priority QoS flow may need to preempt resources from a lower-priority flow to meet its needs. ARP preemption capability allows the network to make informed decisions about resource reallocation and ensures that higher-priority flows can obtain the necessary resources, even if they were initially allocated to lower-priority flows.

[0222] On the other hand, ARP preemption vulnerability refers to the possibility that a QoS flow may lose its allocated resources in exchange for a QoS flow with a higher ARP priority. A higher preemption vulnerability means that a QoS flow may more easily lose its allocated resources when it needs to accommodate a higher-priority flow. This vulnerability ensures that the network can adjust and effectively allocate resources based on changing priorities and resource availability.

[0223] D, 5QI:

[0224] 5QI is a scalar value used as a reference for the standardized combination of 5G QoS features. It represents a set of access node-specific parameters used to control the QoS forwarding processing of specific QoS flows. The standardized nature of 5QI enables interoperability and consistency between different access nodes within the network. It ensures that QoS flows with the same 5QI value receive similar processing and follow the same set of QoS features. 5QI values ​​are shown in Table 1, for example.

[0225] Table 1

[0226] E, 5QI parameters:

[0227] Resource Type: GBR QoS flows can use either GBR resource types or delay-critical GBR resource types. These resource types have different definitions for parameters such as Packet Delay Budget (PDB) and Packet Error Budget (PER). Furthermore, the Maximum Data Burst Volume (MDBV) parameter is only applicable to delay-critical GBR resource types. The choice of resource type determines the specific characteristics and requirements associated with the QoS flow.

[0228] Priority: The priority assigned to a QoS flow indicates its relative importance in network resource scheduling. Priorities are defined such that the lowest level corresponds to the highest priority. This parameter is used to distinguish between QoS flows from the same terminal and QoS flows from different UEs. By assigning priorities, the network can effectively manage and prioritize resource allocation based on the specific needs and requirements of each flow.

[0229] Packet delay budget: The packet delay budget specifies the upper limit of the delay that a packet can experience between the terminal and the UPF endpoint on the N6 interface. This parameter ensures that packet transmission delay remains within acceptable limits. The same value for the packet delay budget applies to both UL and DL directions, thus ensuring consistent delay performance.

[0230] Maximum Data Burst Value (MDBV): The MDBV parameter represents the maximum amount of data that a 5G access network must process within a given time period, consistent with the PDB of the 5G access network. It indicates the data burst size that the 5G access network can provide without exceeding a specified limit. The MDBV parameter is used for resource allocation of QoS flows and ensures effective resource management and allocation according to defined burst requirements.

[0231] Packet Error Rate (PER): The packet error rate parameter defines the upper limit on the rate at which Internet Protocol (IP) packets, processed by a link-layer protocol such as Radio Link Control (RLC) but not successfully transmitted to an upper layer such as Packet Data Convergence Protocol (PDCP), are lost. It sets a threshold for the acceptable level of packet loss during transmission to ensure reliable data transmission between network entities.

[0232] Average Window: Each GBR QoS flow is associated with an average window. The average window represents the duration for which GBR and Maximum Bit Rate (MBR) parameters are calculated. This calculation occurs across various network elements, including the RAN, RAN User Plane Functions (UPRs), and terminals. The average window determines the time period for measuring GBR and MBR values ​​and provides a basis for accurate resource allocation and management.

[0233] 3. 6GAI Quality of AI Service (QoAIS) Tiered Architecture

[0234] With the introduction of new services such as AI as a Service (AIaaS) into 6G networks, the paradigm of providing a single connection service is shifting to X as a Service (XaaS), transforming from a purely connectivity resource to a multi-element resource encompassing connectivity, computing, data, and algorithms. Therefore, the existing session-centric network architecture is no longer adequate for the needs of these new services and necessitates an evolution towards a task-centric network architecture.

[0235] In a task-centric architecture, the implementation of a service comprises three layers: service, task, and resources. When a user makes a service request to the network, the request may involve one or more AI services, such as, but not limited to, AI training, AI inference, AI data, and AI verification services. AI tasks are decomposed and orchestrated from AI services, representing the coordination and allocation of connectivity, computation, data, and algorithm resources among multiple network nodes; they are a lightweight subset of AI services. AI resources are the four essential resources required to ensure the implementation of AI tasks, including but not limited to at least one of computation, algorithm, data, and connectivity. These resources include not only physical resources such as the computing power of a central processing unit (CPU) or air interface time-frequency domain resources, but also the implementation methods.

[0236] Therefore, from this perspective, the existing 5G QoS architecture is incompatible with the new task-centric network architecture, and 6G requires a new task-oriented QoS architecture. Considering the characteristics of a task-centric architecture, the new QoS architecture should possess the following features: layered mapping of service, task, and resource QoS; and a three-layer closed-loop guarantee of service, task, and resource QoS.

[0237] To improve the performance of AI services, this disclosure provides the following operation processing methods, nodes, systems, and storage media.

[0238] Figure 2 is an interactive schematic diagram of an operation processing method according to an embodiment of the present disclosure. As shown in Figure 2, the embodiments of the present disclosure relate to an operation processing method, which includes:

[0239] In step S2101a, the third node 103 sends the first instruction information to the first node 101.

[0240] In some embodiments, the first node 101 receives first instruction information.

[0241] In some embodiments, the third node 103 may include, but is not limited to, at least one of the following: a node that configures the QoS information of the first node 101; a node that controls QoS coordination.

[0242] In one example, QoS information may also be referred to as "QoS description information," which can be used to determine or describe a set of QoS parameters or at least some of the QoS parameters in a set of QoS parameters. QoS parameters include, but are not limited to, QoS priority parameters, resource type parameters, transmission reliability parameters, etc., which are not limited in this disclosure. For example, QoS information can be a bit value "01," corresponding to a QoS priority parameter, such as a QoS priority value of 1.

[0243] In one example, the node controlling QoS coordination can be an independently configured or deployed node, which can be used to control QoS coordination. For instance, the node controlling QoS coordination can control the first node 101 to send a first request to the second node 102 if the QoS information cannot be satisfied.

[0244] For example, the node that controls QoS coordination can control the first node 101 to determine whether to perform QoS coordination if the QoS information cannot be satisfied.

[0245] For example, the node that controls QoS coordination can control the first node 101 to determine the second node 102 if the QoS information cannot be satisfied.

[0246] For example, the node that controls QoS coordination can control the first node 101 to determine the second node 102 and whether to perform QoS coordination if the QoS information cannot be satisfied.

[0247] For example, the node controlling QoS coordination can control the first node 101 to determine the second node 102 and whether to perform QoS coordination if the QoS information cannot be satisfied. If it is determined that QoS coordination should be performed, the first node 101 can control the first node 101 to send a first request to the determined second node 102.

[0248] For example, the node that controls QoS coordination can control the QoS coordination between the second node 102 and the first node 101, thereby ensuring the QoS information of AI services and / or the QoS information of the first node 101.

[0249] For example, the node that controls QoS coordination can control the QoS coordination between the associated node 105 and the first node 101, thereby ensuring the QoS information of AI services and / or the QoS information of the first node 101.

[0250] This disclosure does not limit the content of node control for QoS coordination.

[0251] In one example, the third node 103 may include, but is not limited to, at least one of the following: core network function node; application function (AF); network exposure function (NEF); operation administration and maintenance (OAM); next generation radio access network (NG-RAN); terminal (or user equipment UE).

[0252] For example, the first operation may include, but is not limited to, determining whether to perform QoS coordination and / or determining the second node 102.

[0253] In some embodiments, the first node 101 may request other nodes, such as the second node 102, to perform QoS coordination when it is unable to meet the QoS requirements, thereby ensuring that the QoS of the entire service is not compromised due to its own failure to meet the QoS requirements.

[0254] In one example, the first node 101 can be at least one of the following: an AI service execution node; an AI task execution node; an AI resource QoS execution node, including but not limited to a Next Generation Radio Access Network (NG-RAN), a terminal, or other independent AI entity.

[0255] For example, AI services may include, but are not limited to, at least one of the following: AI training services; AI inference services; AI data services; and AI verification services.

[0256] AI training services may include, but are not limited to, services for training AI models.

[0257] AI reasoning services may include, but are not limited to, services that use AI models for reasoning.

[0258] AI data services may include, but are not limited to, data that is organized, statistically analyzed, and / or categorized using AI.

[0259] AI verification services may include, but are not limited to, identity verification and payment verification using AI.

[0260] For example, AI tasks may include, but are not limited to, at least one of the following: data preprocessing tasks; feature extraction tasks; model training tasks; inference tasks; evaluation tasks; and transmission tasks.

[0261] Among them, data preprocessing tasks may include, but are not limited to, at least one of data cleaning, data formatting, and data normalization.

[0262] Feature extraction tasks may include, but are not limited to, extracting useful features from raw data for model training.

[0263] The model training task may include, but is not limited to, training the model using a specific algorithm and / or a specific dataset.

[0264] The reasoning task may include, but is not limited to, using a trained model to predict or classify data.

[0265] The evaluation task may include, but is not limited to, evaluating and testing the model's performance.

[0266] The transmission task may include, but is not limited to, the transmission of AI data and / or AI models.

[0267] For example, AI resources may include, but are not limited to, at least one of the following: computing power resources; algorithm resources; connectivity resources; and data resources.

[0268] Among them, computing power resources can ensure that AI services can obtain sufficient computing resources, which can be provided by CPU, graphics processing unit (GPU) and / or other dedicated hardware.

[0269] Algorithm resources can refer to the resources that provide the necessary algorithm or model support for AI services and determine the operation of AI services.

[0270] Among them, connectivity resources can be used to ensure the stability and speed of AI model and / or AI data transmission, and to ensure that AI services can acquire and process AI data in a timely manner.

[0271] Among them, data resources can refer to high-quality data resources provided by computing power resources, which can ensure that AI services can make decisions and analyses based on accurate data.

[0272] The above is merely an illustrative example, and this disclosure does not limit the specific content of AI services, AI tasks, and AI resources.

[0273] In some embodiments, the second node 102 may refer to a node that controls QoS coordination. For example, if the first node 101 fails to meet the QoS requirements, the second node may update the QoS information of the first node 101, thereby ensuring that the QoS of the entire service is not compromised due to the failure of the first node 101 to meet the QoS requirements.

[0274] In some embodiments, the second node 102 may include, but is not limited to, at least one of the following: a node that configures the QoS information of the first node 101; a node that controls QoS coordination; or a node whose QoS information type is at the same level as the first node.

[0275] For example, the QoS information type of the first node 101 is QoS information for AI services, and the QoS information type of the peer nodes is also QoS information for AI services.

[0276] For example, the QoS information type of the first node 101 is the QoS information of the AI ​​task, and the QoS information type of the peer nodes is also the QoS information of the AI ​​task.

[0277] For example, the QoS information type of the first node 101 is QoS information of AI resources, and the QoS information type of the peer nodes is also QoS information of AI resources.

[0278] In addition, the parent node of the first node 101 can refer to a node with a QoS information type higher than that of the first node 101. For example, the parent node of the AI ​​resource node is the AI ​​task node, and the parent node of the AI ​​task node is the AI ​​service node.

[0279] In some embodiments, "performing QoS coordination" in this disclosure can refer to the following: when the QoS information of one node, such as node #1, cannot be satisfied, other nodes, such as node #2, can perform QoS coordination to at least adjust the QoS information of node #1, thereby ensuring that the QoS information of the entire service is not compromised due to the unsatisfactory QoS information of node #1. It is understood that when performing QoS coordination, other nodes, such as node #2, can also adjust their own QoS information and / or adjust the QoS information of nodes associated with the QoS information of node #1, such as nodes #3 and #4, thereby ensuring the QoS information of the entire service.

[0280] In one example, "performing QoS coordination" can mean that when the QoS information of one node, such as node #1, cannot be satisfied, other nodes, such as node #2, can coordinate QoS to adjust the QoS information of node #1 (thereby adjusting the QoS parameters of node #1) to satisfy or ensure the QoS information of node #1. For example, node #2 can lower the priority value of node #1, at which point node #1 can preempt QoS flow resources, thereby ensuring the QoS information of node #1 and thus guaranteeing the QoS information of the entire service.

[0281] In one example, "performing QoS coordination" can mean that when the QoS of one node, such as node #1, cannot be satisfied, other nodes, such as node #2, can adjust their own QoS information to satisfy or ensure the QoS of node #1. For example, node #2 can increase its own priority value, for instance, to be higher than the priority value of node #1. This is equivalent to lowering the priority value of node #1. The lower the priority value, the higher the priority of the corresponding QoS flow. At this time, node #1 can preempt the QoS flow resources allocated to node #2, thereby prioritizing the satisfaction of node #1's QoS information, and thus ensuring the QoS information of the entire service.

[0282] In one example, "performing QoS coordination" can mean that when the QoS information of one node, such as node #1, cannot be satisfied, other nodes, such as node #2, can adjust the QoS information of associated nodes. These associated nodes can be nodes linked to the QoS information of node #1. For example, node #2 can adjust the QoS information of node #3 to ensure the QoS information of the entire service. For instance, node #2 can increase the priority value of node #3, for example, to be higher than the priority value of node #1. This is equivalent to lowering the priority value of node #1. The lower the priority value, the higher the priority of the corresponding QoS flow. In this case, node #1 can preempt the QoS flow resources allocated to node #3, thereby prioritizing the satisfaction of node #1's QoS information and thus ensuring the QoS information of the entire service.

[0283] In this embodiment of the disclosure, QoS coordination is performed to ensure the QoS information of this service.

[0284] In some embodiments, the name of the first node 101 is not limited and can be interchanged with "cooperation request initiating node", "QoS cooperation request node", etc.

[0285] In some embodiments, the name of the second node 102 is not limited and can be interchanged with "cooperation request receiving node", "QoS cooperation node", etc.

[0286] In some embodiments, the name of the third node 103 is not limited and can be interchanged with "QoS configuration node", "QoS coordination control node", etc.

[0287] In some embodiments, QoS coordination may also be referred to as "QoS coordination" or "QoS negotiation," and this disclosure does not limit it.

[0288] In some embodiments, the first indication information may be used to indicate whether QoS coordination is to be performed.

[0289] In one example, the third node 103 can indicate whether QoS coordination is to be performed by using at least one bit occupied by the first indication information.

[0290] For example, the first indication information occupies 1 bit. If the bit value is the first value, it can indicate that QoS coordination is performed. If the bit value is the second value, it can indicate that QoS coordination is not performed. The first value can be "1" and the second value can be "0", or the first value can be "0" and the second value can be "1".

[0291] In one example, the third node 103 can indicate whether to perform QoS coordination by whether it carries the information unit containing the first indication information.

[0292] For example, if the third node 103 carries the aforementioned information element in the signaling sent to the first node 101, it can instruct QoS coordination to be performed; if the first node 101 does not carry the aforementioned information element in its signaling, it can instruct that QoS coordination not be performed.

[0293] The above is merely an illustrative example, and this disclosure does not limit the method of indicating whether to perform QoS coordination through the first indication information.

[0294] In some embodiments, the third node 103 may send a first indication message to the first node 101 if it determines that the QoS information of the first node 101 cannot be satisfied.

[0295] In some embodiments, the third node 103 may send first indication information to the first node 101 based on a request from the first node 101.

[0296] In some embodiments, the third node 103 may send first indication information to the first node 101 when configuring the QoS information of the first node 101.

[0297] In some embodiments, the third node 103 may send first instruction information to the first node 101 when it is necessary to control the first node 101 to perform a first operation.

[0298] In some embodiments, the third node 103 may send first indication information to the first node 101 based on its own implementation.

[0299] The above is merely an illustrative example, and this disclosure does not limit the timing or triggering conditions for the third node 103 to send the first instruction information.

[0300] In some embodiments, the first node 101 may determine whether to perform QoS coordination based on the first indication information.

[0301] In some embodiments, step S2101a is an optional execution step. For example, if the first node 101 determines whether to perform QoS coordination based on other methods or if the first node 101 can meet the QoS requirements, step S2101a may not be executed.

[0302] In step S2101b, the fourth node 104 sends the second instruction information to the first node 101.

[0303] In some embodiments, the first node 101 receives second instruction information.

[0304] In some embodiments, the second indication information may be used to determine the second node 102.

[0305] In one example, the fourth node 104 can indicate the identifier of the second node 102 through the second indication information.

[0306] In one example, the fourth node 104 can indicate the index of the second node 102 in a pre-configured list of nodes. For instance, the first node 101 has a pre-acquired list of candidate nodes, and the fourth node 104 can indicate the index of the second node 102 in that list through second indication information, based on which the first node 101 determines the second node 102.

[0307] In some embodiments, the fourth node 104 may send a second indication message to the first node 101 if it determines that the QoS of the first node 101 cannot be satisfied.

[0308] In some embodiments, the fourth node 104 may send a second instruction message to the first node 101 based on a request from the first node 101.

[0309] In some embodiments, the fourth node 104 may send a second indication message to the first node 101 if the QoS of the first node 101 is configured.

[0310] In some embodiments, the fourth node 104 may send a second instruction message to the first node 101 when it is necessary to control the first node 101 to perform a first operation.

[0311] In some embodiments, the fourth node 104 may, based on its own implementation, send a second instruction message to the first node 101.

[0312] The above is merely an illustrative example, and this disclosure does not limit the timing or triggering conditions for the fourth node 104 to send the second instruction information.

[0313] In some embodiments, the first node 101 may determine the second node 102 based on the second indication information.

[0314] In some embodiments, the fourth node 104 may include, but is not limited to, at least one of the following: a node that configures the QoS of the first node 101; a node that controls QoS coordination.

[0315] In some embodiments, the fourth node 104 may be the same node as the third node 103, in which case the second indication information and the first indication information may be sent to the first node 101 through the same or different signaling. Alternatively, the fourth node 104 may be a different node from the third node 103, and this disclosure does not limit this.

[0316] In some embodiments, step S2101b is an optional execution step. For example, if the first node 101 determines whether the second node or the first node 101 can meet the QoS requirements based on other methods, step S2101b may not be executed.

[0317] Step S2102: The first node 101 performs the first operation.

[0318] In some embodiments, the first node 101 performs a first operation if the QoS information cannot be satisfied.

[0319] In one example, the first node 101 can determine that QoS cannot be met after inspecting uplink and downlink packets based on packet detection rules (PDR).

[0320] In one example, the first node 101 can detect the QoS parameters of uplink and downlink data packets to determine whether the QoS information is satisfied. For example, if the resource type is type 2, resulting in the inability to preempt resources, or if the QoS parameters used to measure data transmission reliability are below the threshold, the first node 101 will determine that the QoS information cannot be satisfied.

[0321] The above is merely an illustrative example, and this disclosure does not limit the scheme in which the first node 101 determines that the QoS information cannot be satisfied.

[0322] In some embodiments, the first operation includes, but is not limited to: determining whether to perform QoS coordination and / or determining the second node 102.

[0323] In some embodiments, if the first node 101 cannot satisfy the QoS information, it can determine whether to perform QoS coordination. Further, if it is determined that QoS coordination should be performed, a second node 102 can be identified so that a first request can be subsequently sent to the second node 102, the first request being used to request the second node 102 to perform QoS coordination.

[0324] In some embodiments, if the first node 101 cannot meet the QoS information, it may default to needing to perform QoS coordination. In this case, the first node 101 may directly determine the second node 102 so that it can subsequently send a first request to the second node 102. The first request is used to request the second node 102 to perform QoS coordination.

[0325] In some embodiments, if the first node 101 cannot satisfy the QoS information, it can determine whether to perform QoS coordination and identify the second node 102. Subsequently, it can send a first request to the second node 102, which requests the second node 102 to perform QoS coordination. The order in which the first node determines whether to perform QoS coordination and identifies the second node 102 is not limited. For example, the first node 101 can first determine whether to perform QoS coordination and then identify the second node 102, or the first node 101 can first identify the second node 102 and then determine whether to perform QoS coordination.

[0326] In some embodiments, the QoS information of this disclosure may include, but is not limited to, at least one of the following: QoS information of AI services; QoS information of AI tasks; QoS information of AI resources.

[0327] The specific details of AI services, AI tasks, and AI resources have been described in the aforementioned embodiments and will not be repeated here.

[0328] In some embodiments, the first node 101 may determine whether to perform QoS coordination using, but is not limited to, one of the following:

[0329] Method 1-1 determines whether to perform QoS coordination based on a predefined method.

[0330] In one example, the protocol can stipulate that QoS coordination will be performed when QoS information cannot be met. In this case, the first node 101 can determine to perform QoS coordination based on the protocol.

[0331] In one example, the protocol can stipulate that QoS coordination will not be performed if QoS information cannot be met. In this case, the first node 101 can determine not to perform QoS coordination based on the protocol.

[0332] Methods 1-2 determine whether to perform QoS coordination based on the first indication information.

[0333] In one example, the first node 101 can determine whether to perform QoS coordination based on the first indication information sent by the third node 103.

[0334] For example, if the first indication information occupies 1 bit and its bit value is a first value, then the first node 101 determines to perform QoS coordination. If the bit value is a second value, then the first node 101 determines not to perform QoS coordination. The first value can be "1" and the second value can be "0", or the first value can be "0" and the second value can be "1".

[0335] For example, if the first node 101 determines that the signaling sent by the third node 103 carries the information element containing the first indication information, then the first node 101 determines to perform QoS coordination. If the first node 101 determines that the signaling sent by the third node 103 does not carry the information element containing the first indication information, then the first node 101 determines not to perform QoS coordination.

[0336] The above is merely an illustrative example, and this disclosure does not limit the scheme by which the first node 101 determines whether to perform QoS coordination based on the first indication information.

[0337] Methods 1-3 determine whether to perform QoS coordination based on predefined methods and first indication information.

[0338] In one example, the protocol can stipulate whether to perform QoS coordination based on the first indication information if the QoS information cannot be met. In this case, the first node 101 can determine whether to perform QoS coordination based on the indication of the first indication information.

[0339] In one example, the protocol can stipulate a waiting period in case QoS information cannot be met. If the first indication information is received within the waiting period, the first node 101 can determine to perform QoS coordination; if the first indication information is not received within the waiting period, the first node 101 can determine not to perform QoS coordination.

[0340] The above is merely an illustrative example, and this disclosure does not limit the scheme by which the first node 101 determines whether to perform QoS coordination.

[0341] In some embodiments, QoS coordination includes, but is not limited to, at least one of the following: QoS coordination between the first node 101 and the associated node 105; QoS coordination between the first node 101 and the second node 102.

[0342] In one example, associated node 105 is a node associated with the QoS information of the first node 101.

[0343] It is understandable that the QoS of the first node after collaboration can satisfy the QoS information of the AI ​​service and / or satisfy the QoS information of the first node.

[0344] In some embodiments, the first node 101 may determine the second node 102 by, but is not limited to, one of the following:

[0345] Method 2-1: Determine the second node 102 based on a predefined method.

[0346] In one example, the identifier of the second node 102 can be determined by the protocol, and the first node 101 can determine the second node 102 based on the protocol.

[0347] In one example, the method for determining the second node 102 can be agreed upon by the protocol, so the first node 101 can determine the second node 102 based on the protocol. For example, the protocol stipulates that if QoS information cannot be satisfied, a request message is sent to the network device, and the network device provides the identifier of the second node 102.

[0348] Method 2-2: Based on the second instruction information, determine the second node 102.

[0349] In one example, the first node 101 can determine the second node 102 based on the second indication information sent by the third node 103.

[0350] In one example, the first node 101 can determine the index of the second node 102 in the node list based on the second indication information sent by the third node 103, and thus determine the second node 102.

[0351] The above is merely an illustrative example, and this disclosure does not limit the scheme by which the first node 101 determines the second node 102 based on the second indication information.

[0352] Method 2-3: Based on the predefined method and the second instruction information, determine the second node 102.

[0353] In one example, the node list can be agreed upon by the protocol, and the first node 101 can determine the second node 102 in the node list based on the index indicated by the second indication information.

[0354] In one example, the set of available nodes can be agreed upon by the protocol, and the first node 101 can then determine the second node 102 from the set of nodes based on the indication of the second indication information.

[0355] The above is merely an illustrative example, and this disclosure does not limit the scheme by which the first node 101 determines the second node 102.

[0356] In some embodiments, in the above methods 1-1, 1-2, 1-3, 2-1, 2-2, and 2-3, the granularity of the predefined methods and / or indication information (including the first indication information and / or the second indication information) can be per node, per AI service, per AI task, per AI resource, or per QoS information.

[0357] For example, the granularity of the predefined method is each node. If any first node 101 cannot meet the QoS information, it can be determined whether to perform QoS coordination and / or determine the second node 102 based on the predefined method.

[0358] For example, the granularity of the predefined method is each QoS information. If the first node 101 cannot satisfy the specific QoS information and / or use the specific QoS information, it can determine whether to perform QoS coordination and / or determine the second node 102 based on the predefined method.

[0359] For example, the granularity of the predefined method is for each AI service, each AI task, or each AI resource. If the first node 101 cannot meet the QoS information related to a specific AI service, a specific AI task, or a specific AI resource, it can determine whether to perform QoS coordination and / or determine the second node 102 based on the predefined method.

[0360] For example, the granularity of the first indication information is each node. If any first node 101 cannot meet the QoS information, it can be determined whether to perform QoS coordination based on the first indication information.

[0361] For example, the granularity of the second indication information is per node. If any first node 101 cannot meet the QoS information, the second node 102 can be determined based on the second indication information.

[0362] For example, the granularity of the first indication information is each QoS information. If the first node 101 cannot satisfy a specific QoS information and / or use a specific QoS information, it can determine whether to perform QoS coordination based on the first indication information.

[0363] For example, the granularity of the second indication information is each QoS information. If the first node 101 cannot satisfy a specific QoS information and / or uses a specific QoS information, it can determine the second node 102 based on the second indication information.

[0364] For example, the granularity of the first indication information is for each AI service, each AI task, or each AI resource. If the first node 101 cannot meet the QoS information related to a specific AI service, a specific AI task, or a specific AI resource, it can determine whether to perform QoS coordination based on the first indication information.

[0365] For example, the granularity of the second indication information is for each AI service, each AI task, or each AI resource. If the first node 101 cannot meet the QoS information related to a specific AI service, a specific AI task, or a specific AI resource, it can determine the second node 102 based on the second indication information.

[0366] In step S2103, the first node 101 sends a first request to the second node 102.

[0367] In some embodiments, the second node 102 receives the first request.

[0368] In some embodiments, after determining to perform QoS coordination, the first node 101 determines the second node 102 and then sends a first request to the second node 102.

[0369] In some embodiments, after the first node 101 has identified the second node 102, it sends a first request to the second node 102.

[0370] In some embodiments, after determining to perform QoS coordination and identifying the second node 102, the first node 101 sends a first request to the second node 102.

[0371] In some embodiments, the first request is used to request the second node to perform QoS coordination. The meaning of performing QoS coordination has already been described in the foregoing embodiments and will not be repeated here.

[0372] In some embodiments, the second node 102 may update its own QoS information based on the first request in order to ensure the QoS information of the first node 101.

[0373] In some embodiments, the first request may include, but is not limited to, at least one of the following: information of the first node 101; QoS information of the first node 101; a first reason; and information of the associated node 105.

[0374] In one example, the information of the first node 101 may include, but is not limited to, the identification information of the first node 101 and / or the location information of the first node 101, and the location information may be the information of the cell it is located in and / or the geographical location information.

[0375] In one example, the information from the first node 101 can be used by the second node 102 to identify the first node 101 that cannot meet the QoS information, i.e., to identify the problem node.

[0376] In one example, the QoS information of the first node 101 may include, but is not limited to, at least one of the following: QoS information satisfied by the first node; QoS information that the first node cannot satisfy; QoS information used by the first node.

[0377] For example, the QoS information of the first node 101 may indicate a set of QoS parameters of the first node 101, or it may be a part of the set of QoS parameters of the first node 101. This disclosure does not limit it in this way.

[0378] The QoS information satisfied by the first node 101 can refer to the QoS-related information that the first node 101 can satisfy, such as a set of QoS parameters that the first node 101 can satisfy, or a portion of the parameters in a set of QoS parameters.

[0379] The QoS information that the first node 101 cannot satisfy can refer to the relevant information of the QoS that the first node 101 cannot satisfy at present. At this time, the first node 101 cannot satisfy a set of QoS parameters, or cannot satisfy some parameters in a set of QoS parameters.

[0380] The QoS information used by the first node 101 can refer to the QoS information currently being used by the first node 101, which may include, but is not limited to, old and unmet QoS information, or updated alternative QoS information (or new QoS information).

[0381] For example, if the first node 101 cannot satisfy the QoS information, it determines that QoS parameter #1 cannot be satisfied. At this time, the first node 101 is still using the QoS information corresponding to QoS parameter #1.

[0382] For example, if the first node 101 is unable to satisfy the QoS information, it determines that the QoS information cannot be satisfied. The first node 101 replaces the QoS parameter #1 with the QoS parameter #2. At this time, the first node 101 is using the QoS information corresponding to the QoS parameter #2.

[0383] For example, the QoS information of the first node 101 can be used to assist the second node 102 in QoS coordination.

[0384] For example, the first reason can be used to indicate why the first node 101 performs the first operation. The first reason may include, but is not limited to, congestion and / or insufficient resources.

[0385] For example, the first reason can be used by the second node 102 to determine the QoS problem of the first node, thereby selecting an appropriate cooperation strategy.

[0386] For example, the associated node 105 may be a node associated with the QoS information of the first node 101. It is understood that being associated with the QoS information of the first node 101 may refer to being able to influence the QoS information of the first node 101 and / or the QoS information of the first node 101 influencing its own QoS information.

[0387] For example, the information of the associated node 105 may include, but is not limited to, the identification information of the associated node 105 and / or the location information of the associated node 105.

[0388] For example, the information from associated node 105 can be used by second node 102 to perform QoS coordination or forward the first request. It is understood that second node 102 can forward the first request to at least one of associated node 105 and fifth node 106. Associated node 105 can update its own QoS information based on the first request to ensure the QoS information of first node 101, or fifth node 106 can determine the updated QoS information of the fourth node to ensure the QoS information of first node 101.

[0389] The fifth node 106 may include, but is not limited to, at least one of the following: a node used to configure QoS information of associated node 105; or a node for QoS coordination.

[0390] This disclosure does not limit the function or role of the fifth node 106.

[0391] The first node 101 can determine the associated node 105 based on the indication of the second node 102 or other nodes. For example, the second node 102 is the node that configures the QoS information of the first node. While configuring the QoS information for the first node 101, the information of the associated node 105 can be indicated to the first node 101.

[0392] In step S2104, the second node 102 performs QoS coordination.

[0393] In some embodiments, the second node 102 may perform QoS coordination based on the first request.

[0394] In some embodiments, the QoS coordination of the second node 102 may include, but is not limited to, determining the QoS information of the first node after coordination based on the QoS information of the AI ​​service and / or the QoS information of the first node, and further, determining the QoS information of the associated nodes after coordination based on the QoS information of the first node after coordination.

[0395] In some embodiments, the second node 102 may perform QoS coordination in a manner that includes, but is not limited to, determining the QoS information of the first node after coordination based on the QoS information of the AI ​​service and / or the QoS information of the first node, and further determining the QoS information of the second node after coordination based on the QoS information of the first node after coordination, thereby updating its own QoS information.

[0396] In some embodiments, the first request includes information about the first node 101, and the second node 102 can determine the first node that needs to perform QoS coordination based on the information about the first node 101.

[0397] In some embodiments, the first request includes QoS information of the first node 101. The second node 102 can determine at least one of the following based on the QoS information of the first node 101: QoS information that the first node 101 satisfies, QoS information that cannot be satisfied, and QoS information that is used. Further, the QoS parameters corresponding to the QoS information satisfied by the first node 101 are determined. For these QoS parameters, the second node 102 may not need to coordinate.

[0398] The QoS parameters corresponding to the QoS information that the first node 101 cannot satisfy are determined. For these QoS parameters, the second node 102 can coordinate to satisfy the QoS information of the first node 101 and / or satisfy the QoS information of the AI ​​service.

[0399] Regarding the QoS information currently being used by the first node 101, if it is old and unsatisfactory QoS information, the second node 102 can coordinate. If the first node 101 is using updated replacement QoS information, the second node 102 can coordinate to satisfy the QoS information of the first node 101 and / or the QoS information of the AI ​​service. Alternatively, if the second node 102 determines that the updated replacement QoS information of the first node 101 satisfies the QoS information of the first node 101 and / or the QoS information of the AI ​​service, it may not need to coordinate. Optionally, the second node 102 can send an acknowledgment message to the first node 101 to confirm the QoS information currently being used by the first node 101.

[0400] The second node 102 can determine the QoS information of the first node 101 after collaboration in the following way:

[0401] For example, the second node 102 can determine that the currently unmet QoS parameter is a priority parameter in a set of QoS parameters based on the QoS information that cannot be met. Then, the second node 102 can increase the priority of the QoS flow of the first node 101 based on the QoS information of the AI ​​service and / or the QoS information of the first node.

[0402] For example, the second node 102 can determine that the currently unmet QoS parameter is a resource type parameter in a set of QoS parameters based on the QoS information that cannot be met. The second node 102 can adjust the resource type of the first node 101 based on the QoS information of the AI ​​service and / or the QoS information of the first node. For example, the resource type of the first node 101 can be adjusted from the second type to the first type, wherein the first type can preempt resources first compared to the second type.

[0403] For example, the second node 102 can determine, based on the unmet QoS information, that the currently unmet QoS parameter is another QoS parameter in a set of QoS parameters. The second node 102 can adjust other QoS parameters of the first node 101 based on the QoS information of the AI ​​service and / or the QoS information of the first node, thereby ensuring that the QoS of the entire service will not be compromised due to the unmet QoS of the first node 101.

[0404] For example, the second node 102 can determine, based on the unmet QoS information, that the currently unmet QoS parameters are a set of QoS parameters, including resource type, priority, transmission reliability parameters, etc. The second node 102 can adjust the set of QoS parameters of the first node 101 based on the QoS information of the AI ​​service and / or the QoS information of the first node, thereby ensuring that the QoS information of the entire service will not be compromised due to the unmet QoS information of the first node 101.

[0405] The above is merely an illustrative example. This disclosure does not limit the method by which the second node 102 coordinates the QoS of the first node 101 based on the QoS information of the first node.

[0406] In some embodiments, the first request includes a first reason, and the second node 102 may adopt a corresponding QoS coordination strategy based on a first principle.

[0407] For example, if the first reason is insufficient resources, the second node 102 can determine the QoS coordination strategy to increase the priority of the QoS flow of the first node, so that the QoS flow of the first node can preempt more resources in order to meet the QoS of the first node 101.

[0408] For example, if the first reason is congestion, the second node 102 can determine that the QoS coordination strategy is to reduce specific QoS parameters, such as reducing the QoS parameters used to measure the reliability of data transmission, in order to meet the QoS of the first node 101.

[0409] The above is merely an illustrative example, and this disclosure does not limit the method by which the second node 102 determines the QoS coordination strategy based on the first reason.

[0410] In some embodiments, the first request includes information about the associated node 105. The second node 102 can perform QoS coordination based on the information about the associated node 105, or it can forward the first request to the associated node 105 or the fifth node 106, and the associated node 105 or the fifth node 106 can perform QoS coordination.

[0411] In some embodiments, after the second node 102 determines the QoS information of the first node 101 after collaboration, it can send update indication information to the first node 101 to inform the first node of the QoS information of the first node 101 after collaboration, so that the first node can update its own QoS information to meet the QoS information of AI services and / or meet the QoS information of the first node.

[0412] In some embodiments, the second node 102 can determine its own QoS information after collaboration based on the QoS information of the first node after collaboration. For example, if the second node 102 is a peer node of the first node 101 and the first node 101 has adjusted the resource type parameter in a set of QoS parameters, the second node 102 can determine its own QoS information after collaboration and update its own QoS information. For example, it can also adjust the resource type parameter in the set of QoS parameters it uses to meet the QoS information of the first node 101.

[0413] For example, both the second node 102 and the first node 101 are AI service nodes. The second node 102 can increase its own priority value. Suppose it increases its own priority value to exceed the priority value of the first node 101. Since the higher the priority value, the higher the priority, the first node 101 can take the lead in seizing resources.

[0414] For example, both the second node 102 and the first node 101 are AI task nodes. The second node 102 adjusts its own resource type from the first type to the second type. The first type can preempt resources first compared to the second type. In this way, the QoS information of the first node 101 can also be satisfied first.

[0415] In some embodiments, the second node 102 may determine the QoS information of the associated node 105 after collaboration based on the QoS information of the first node after collaboration. For example, the second node 102 may be a node that configures the QoS of the first node or a node that controls QoS collaboration. In this case, the second node 102 may update the QoS information of the first node 101 and determine the QoS information of the associated node associated with the QoS information of the first node based on the QoS information of the first node after collaboration, and update the QoS information of the associated node to meet the QoS information of AI services and / or the QoS information of the first node.

[0416] For example, the second node 102 can determine the priority value of the associated node after collaboration based on the priority value of the first node after collaboration. For example, it can increase the priority value of the associated node 105. Suppose that the priority value of the associated node 105 is increased to exceed the priority value of the first node 101, so that the first node 101 can preempt resources first.

[0417] For example, the second node 102 determines the resource type of the associated node after collaboration based on the resource type of the first node after collaboration. For example, the resource type of the associated node after collaboration is the second type. The first type can preempt resources first compared to the second type, thereby prioritizing the QoS information of the first node 101.

[0418] For example, the second node 102 determines a set of QoS parameters for the associated nodes after collaboration based on a set of QoS parameters of the first node after collaboration, thereby prioritizing the QoS information of the first node 101.

[0419] In some embodiments, the second node 102 may be the same node as the associated node 104. In this case, in addition to determining its own QoS information based on the QoS information of the first node after collaboration, the second node 102 may also determine the QoS information of other associated nodes after collaboration. Of course, the second node 102 may also only determine its own QoS information after collaboration, and this disclosure does not limit this.

[0420] In some embodiments, the second node 102 receives multiple first requests sent by multiple first nodes 101, and at least two of the first requests conflict. The second node 102 can determine the priority of each first request. Further, QoS coordination can be performed according to the order of priority of the first requests from high to low.

[0421] For example, if node 101-1 sends a first request #1 and node 101-2 also sends a first request, and the two requests conflict, assuming that both need to satisfy their own QoS at time point t, node 102 can determine the priority order of the two first requests. For example, if the priority of first request #1 is higher than the priority of first request #2, then node 102 will update the QoS of node 101-1 first, and after satisfying the QoS of node 101-1, update the QoS of node 101-2.

[0422] The above is merely an illustrative example, and this disclosure does not limit the specific scheme for QoS coordination of the second node 102.

[0423] In step S2105, the second node 102 sends a third instruction message to the associated node 105.

[0424] In some embodiments, the associated node 105 receives third instruction information.

[0425] In some embodiments, the third indication information may be used to update the QoS of the associated node 105.

[0426] In one example, the third indication information includes at least one of the following: the QoS information of the first node; and the QoS information of the associated node after collaboration.

[0427] The QoS information of the first node 101 has been described in the previous embodiments and will not be repeated here.

[0428] Among them, the QoS information of the associated node 105 after collaboration can be determined by the second node 102 and sent to the associated node 105 through the third indication information.

[0429] In some embodiments, the second node 102 may send a third indication message to the associated node 105 if it supports updating the QoS of the associated node 105.

[0430] In some embodiments, the second node 102 may send third indication information to the associated node 105 after determining the QoS information of the associated node after collaboration.

[0431] In step S2106, the second node 102 sends an update request to the fifth node 106.

[0432] In some embodiments, the fifth node 106 receives the update request.

[0433] In some embodiments, if the second node 102 cannot determine the QoS information of the associated node 105 after collaboration, it may send an update request to the fifth node 106.

[0434] In some embodiments, if the second node 102 does not support updating the QoS information of the associated node 105, it may send an update request to the fifth node 106.

[0435] In some embodiments, the update request is used to request the fifth node to update the QoS information of the fourth node.

[0436] In some embodiments, the fifth node 106 may include, but is not limited to, at least one of the following: a node that configures the QoS information of the associated node 105; a node that controls QoS coordination.

[0437] In step S2107, the fifth node 106 sends the fourth instruction information to the associated node 105.

[0438] In some embodiments, the associated node 105 receives fourth instruction information.

[0439] In some embodiments, the fourth indication information is used to update the QoS information of the associated node.

[0440] In some embodiments, the fourth indication information may include QoS information of the associated nodes behind the system.

[0441] In some embodiments, the fifth node 106 may determine the QoS information of the associated node 105 after collaboration based on the update request, and send the fourth indication information to the associated node 105.

[0442] In some embodiments, this disclosure does not limit the scheme by which the fifth node determines the QoS information of the four nodes 104 after collaboration.

[0443] In some embodiments, steps S2105 and S2106 to S2107 can be executed selectively. For example, if the second node 102 can determine the QoS information of the associated node 105 after collaboration, then step S2105 can be executed, in which case the second node 102 sends the second indication information to the associated node 105, and steps S2106 to S2107 do not need to be executed. As another example, if the second node 102 cannot determine the QoS information of the associated node 105 after collaboration, then steps S2106 to S2107 can be executed, in which case the fifth node 106 sends the fourth indication information to the associated node 105, and step S2105 does not need to be executed.

[0444] Step S2108: Associated node 105 updates the QoS information of associated node 105.

[0445] In some embodiments, the associated node 105 may update its own QoS information based on the QoS information of the associated node 105 after collaboration in the third indication information.

[0446] In some embodiments, the associated node 105 may update its own QoS information based on the fourth indication information.

[0447] In some embodiments, this disclosure does not limit the manner in which the associated node 105 updates its own QoS information.

[0448] In some embodiments, the names of information, etc., are not limited to the names described in the embodiments. Terms such as "information", "message", "signal", "signaling", "report", "configuration", "indication", "instruction", "command", "channel", "parameter", "domain", "field", "symbol", "symbol", "codebook", "codeword", "codepoint", "bit", "data", "program", and "chip" can be used interchangeably.

[0449] In some embodiments, "acquire," "get," "obtain," "receive," "transmit," "bidirectional transmission," and "send and / or receive" can be used interchangeably and can be interpreted as receiving from other entities, acquiring from protocols, acquiring from higher layers, obtaining through self-processing, or autonomous implementation. Protocols include, for example, at least one of the 3GPP protocol, Wi-Fi protocol, and audio and / or video protocols.

[0450] In some embodiments, terms such as “send,” “transmit,” “report,” “distribute,” “transfer,” “bidirectional transmission,” “send and / or receive” can be used interchangeably.

[0451] In some embodiments, terms such as "certain," "preset," "default," "set," "indicated," "a certain," "any," and "first" can be used interchangeably. "Certain A," "preset A," "default A," "set A," "indicated A," "a certain A," "any A," and "first A" can be interpreted as A pre-defined in a protocol or the like, or as A obtained through setting, configuration, or instruction, or as specific A, a certain A, any A, or first A, but are not limited thereto.

[0452] In some embodiments, the path selection method involved in this disclosure may include at least one of steps S2101a to S2108. For example, step S2101a can be implemented as a standalone embodiment, step S2101b can be implemented as a standalone embodiment, step S2101a+S2101b can be implemented as a standalone embodiment, step S2102 can be implemented as a standalone embodiment, step S2101a+S2102 can be implemented as a standalone embodiment, step S2101b+S2102 can be implemented as a standalone embodiment, and step S2101a+S2101b+S2102 can be implemented as a standalone embodiment. The implementation can be carried out using an independent embodiment. Step S2103 can be implemented as an independent embodiment, step S2104 can be implemented as an independent embodiment, step S2103+S2104 can be implemented as an independent embodiment, step S2105 can be implemented as an independent embodiment, step S2106+S2107 can be implemented as an independent embodiment, step S2108 can be implemented as an independent embodiment, and steps S2101a to S2108 can be implemented as independent embodiments, but are not limited thereto.

[0453] In some embodiments, steps S2101a to S2108 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0454] In some embodiments, the execution order of steps S2101a to S2108 is not limited.

[0455] In the above embodiments, the first node can request the second node to perform QoS coordination when the QoS information cannot be met, thereby ensuring the QoS information of the first node. Through QoS coordination, the performance of AI services is ensured, and the availability and reliability of AI services are improved.

[0456] Figure 3A is a flowchart illustrating an operation processing method according to an embodiment of the present disclosure. As shown in Figure 3A, the present disclosure relates to an operation processing method, which can be executed by the first node 101, and includes the following steps:

[0457] Step S3101: Send the first request.

[0458] In some embodiments, the first request is used to request the second node 102 to perform QoS coordination.

[0459] In some embodiments, the first node 101 sends a first request to the second node 102.

[0460] In some embodiments, the second node 102 receives the first request.

[0461] In some embodiments, step S3101 may refer to steps in other embodiments described before or after this embodiment, such as step S2103 in FIG2 and its optional implementation, and other related parts in the specification, which will not be repeated here.

[0462] In the above embodiments, the first node can request the second node to perform QoS coordination when the QoS information cannot be met, thus ensuring the QoS information of the first node. Through QoS coordination, the performance of AI services is ensured, and the availability and reliability of AI services are improved.

[0463] Figure 3B is a flowchart illustrating an operation processing method according to an embodiment of the present disclosure. As shown in Figure 3B, the present disclosure relates to an operation processing method, which can be executed by the second node 102, and includes the following steps:

[0464] Step S3201: Obtain the first request.

[0465] In some embodiments, the first request is used to request the second node 102 to perform QoS coordination.

[0466] In some embodiments, the second node 102 receives a first request sent by the first node 101, but is not limited thereto; it may also receive a first request sent by other entities.

[0467] In some embodiments, the second node 102 obtains a first request as defined by the protocol.

[0468] In some embodiments, the second node 102 obtains the first request from the upper layer(s).

[0469] In some embodiments, the second node 102 processes the request to obtain the first request.

[0470] In some embodiments, step S3201 is omitted, and the second node 102 autonomously implements the function indicated by the first request, or the above function is defaulted or set to default.

[0471] In some embodiments, optional implementations of step S3201 can be found in optional implementations of step S2103 in FIG2 and other related parts in the embodiments involved in FIG2, which will not be repeated here.

[0472] Step S3202: Perform QoS coordination.

[0473] In some embodiments, optional implementations of step S3202 can be found in optional implementations of step S2104 in FIG2 and other related parts in the embodiments involved in FIG2, which will not be repeated here.

[0474] In some embodiments, steps S3201 to S3202 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0475] In some embodiments, the execution order of steps S3201 to S3202 is not limited.

[0476] In the above embodiments, the second node can update the QoS information of the first node, and ensure the performance of AI services through QoS coordination, thereby improving the availability and reliability of AI services.

[0477] Figure 3C is a flowchart illustrating an operation processing method according to an embodiment of the present disclosure. As shown in Figure 3C, the embodiment of the present disclosure relates to an operation processing method, which can be executed by the third node 103, and includes the following steps:

[0478] Step S3301: Send the first instruction information.

[0479] In some embodiments, the first indication information is used to indicate whether QoS coordination is performed.

[0480] In some embodiments, the second indication information is used to determine the second node 102.

[0481] In some embodiments, the third node 103 sends a first instruction message to the first node 101.

[0482] In some embodiments, the first node 101 receives first instruction information.

[0483] In some embodiments, optional implementations of step S3301 can be found in optional implementations of step S2101a in FIG2 and other related parts in the embodiments involved in FIG2, which will not be repeated here.

[0484] In the above embodiments, the third node can assist the first node in performing the first operation, ensuring the QoS information of the first node. Through QoS collaboration, the performance of AI services is ensured, and the availability and reliability of AI services are improved.

[0485] Figure 3D is a flowchart illustrating an operation processing method according to an embodiment of the present disclosure. As shown in Figure 3D, the embodiment of the present disclosure relates to an operation processing method, which can be executed by the fourth node 104, and includes the following steps:

[0486] Step S3301: Send the second instruction information.

[0487] In some embodiments, the second indication information is used to determine the second node 102.

[0488] In some embodiments, the fourth node 104 sends a second instruction message to the first node 101.

[0489] In some embodiments, the first node 101 receives second instruction information.

[0490] In some embodiments, optional implementations of step S3401 can be found in optional implementations of step S2101b in FIG2 and other related parts in the embodiments involved in FIG2, which will not be repeated here.

[0491] In the above embodiments, the fourth node can assist the first node in performing the first operation, ensuring the QoS information of the first node. Through QoS collaboration, the performance of AI services is ensured, and the availability and reliability of AI services are improved.

[0492] Figure 3E is a flowchart illustrating an operation processing method according to an embodiment of the present disclosure. As shown in Figure 3E, this embodiment of the present disclosure relates to an operation processing method, which can be executed by associated node 105, and includes the following steps:

[0493] Step S3501: Update the Quality of Service (QoS) information of the associated node 105.

[0494] In some embodiments, optional implementations of step S3501 can be found in optional implementations of step S2108 in FIG2 and other related parts in the embodiments involved in FIG2, which will not be repeated here.

[0495] In the above embodiments, the associated node can update its own QoS information, which also achieves the purpose of satisfying the QoS information of the first node. Through QoS coordination, the performance of AI services is ensured, and the availability and reliability of AI services are improved.

[0496] Figure 3F is a flowchart illustrating an operation processing method according to an embodiment of the present disclosure. As shown in Figure 3F, this embodiment of the disclosure relates to an operation processing method, which can be executed by the fifth node 106, and includes the following steps:

[0497] Step S3501: Obtain the update request.

[0498] In some embodiments, the update request is used to request an update to the Quality of Service (QoS) information of the associated node 105.

[0499] In some embodiments, the fifth node 106 receives an update request sent by the second node 102, but is not limited thereto; it may also receive update requests sent by other entities.

[0500] In some embodiments, the fifth node 106 obtains an update request as specified in the protocol.

[0501] In some embodiments, the fifth node 106 obtains an update request from the upper layer(s).

[0502] In some embodiments, the fifth node 106 processes the request to obtain an update request.

[0503] In some embodiments, step S3501 is omitted, and the fifth node 106 autonomously implements the function indicated by the update request, or the above function is defaulted or set to default.

[0504] In some embodiments, optional implementations of step S3501 can be found in optional implementations of step S2106 in FIG2 and other related parts in the embodiments involved in FIG2, which will not be repeated here.

[0505] Step S3502: Send the fourth instruction information to the associated node 105.

[0506] In some embodiments, the fourth indication information is used to update the QoS information of the associated node 105.

[0507] In some embodiments, the fifth node 106 sends a fourth indication message to the associated node 105.

[0508] In some embodiments, the associated node 105 receives fourth instruction information.

[0509] In some embodiments, optional implementations of step S3502 can be found in optional implementations of step S2107 in FIG2 and other related parts in the embodiments involved in FIG2, which will not be repeated here.

[0510] In some embodiments, steps S3501 to S3502 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0511] In some embodiments, the execution order of steps S3501 to S3502 is not limited.

[0512] In the above embodiments, the fifth node can determine the QoS information of the associated nodes after collaboration, thus achieving the goal of satisfying the QoS information of the first node. By ensuring the performance of AI services through QoS collaboration, the availability and reliability of AI services are improved.

[0513] The above process is further illustrated with examples below.

[0514] In this embodiment of the disclosure, when the QoS of the AI ​​task node is not satisfied, the parent node or AI service node is notified so that the parent node or AI service node can reallocate the QoS of the AI ​​task node, or other peer nodes of the AI ​​task node are notified so that the QoS of the AI ​​service can be kept unchanged by adjusting the QoS of other peer nodes.

[0515] 1. If the current QoS cannot be satisfied, the first node determines whether to perform QoS coordination and / or determines the coordinating node.

[0516] 2. Based on 1, the determination of whether to perform QoS coordination and / or determine the coordination node is based on the default protocol and / or the signaling indication of the third node.

[0517] In possible implementations, the granularity of the protocol agreement and / or signaling indication can be per node, per AI service, per AI task, per AI resource, or per QoS. For example, it could be a per node indication, where if a node's QoS cannot be satisfied, the protocol agreement and / or signaling indication must determine whether to perform QoS coordination and / or coordinate with other nodes. Alternatively, it could be a per QoS indication, where QoS coordination and / or coordination with other nodes must be determined only when a specific QoS is used and / or a specific QoS cannot be satisfied. Furthermore, it could be a per service, per task, or per resource indication, where QoS coordination and / or coordination with other nodes must be determined based on the protocol agreement and / or signaling indication when the QoS related to a specific service / task / resource cannot be satisfied.

[0518] 3. Based on 2, the third node can be the QoS configuration node or an independent QoS coordination control node (e.g., core network function node, AF, NEF, OAM, etc.).

[0519] 4. Based on 1, the method further includes, in response to determining to perform QoS coordination, the first node sends a coordination request to the second node, wherein the second node may be the QoS configuration node, an independent QoS coordination control node, or a peer node.

[0520] 5. Based on 4, the collaboration request includes at least one of the following:

[0521] The first node information includes first node identification information, geographical location information, etc., and the first node information is used by the second node to determine the problem node.

[0522] QoS information, including at least one of the following: currently achievable QoS, unachievable QoS, and alternative QoS, is used to determine the QoS corresponding to the first node, thereby assisting the cooperating node in QoS adjustment. Where a QoS cannot be met, the first node updates it according to the previously configured alternative QoS. In this case, the first node can indicate the alternative QoS, i.e., the QoS currently used for updating, in the cooperation request.

[0523] The reasons why QoS cannot be met are used by the second node to determine the QoS problem and select an appropriate cooperation strategy.

[0524] The fourth node information is used by the second node to perform inter-node QoS coordination or forward QoS coordination requests. The fourth node can be determined based on indication information from a QoS configuration node or other nodes. For example, when a QoS configuration node configures QoS for the first node, it indicates the node information associated with the QoS information.

[0525] 6. Based on 4, in response to the second node receiving the cooperation request, determine the updated QoS, and optionally send indication information to the fourth node, the fourth node being at least one node associated with the QoS information, the indication information including at least one of the first node's related QoS (unmet QoS and / or alternative QoS) and the fourth node's updated QoS, the indication information being used to update the associated QoS accordingly.

[0526] 7. Based on 6, the method further includes, if the second node cannot determine the updated QoS, sending a request to the fourth node's associated QoS configuration node or independent QoS collaborative control node (i.e., the fifth node), for the QoS configuration node or independent QoS collaborative control node to determine the updated QoS and send it to the fourth node.

[0527] 8. Based on 4, the method further includes, if the second node receives multiple collaboration requests and they conflict, determining which collaboration request to prioritize for processing based on a predefined or configured priority.

[0528] 9. Based on the above, the QoS can be AI service QoS, AI task QoS, or AI resource QoS.

[0529] 10. Based on the above, the AI ​​resources include at least one of the following:

[0530] Computing resources: The computing resources guarantee service can obtain sufficient computing resources, which are provided by CPUs, GPUs and other dedicated hardware.

[0531] Algorithm resources: The algorithm resources provide the necessary algorithm or model support for AI services to ensure the operation of AI services.

[0532] Connection resources: The connection resources ensure the stability and speed of AI model or data transmission, ensuring that AI services can acquire and process data in a timely manner.

[0533] Data Resources: The computing power resources provide high-quality data resources to ensure that AI services can make decisions and analyses based on accurate data.

[0534] 11. Based on the above, the AI ​​services include, but are not limited to, at least one of AI training, AI inference, AI data, and AI verification services.

[0535] 12. Based on the above, the AI ​​task includes, but is not limited to, at least one of the following:

[0536] Data preprocessing tasks include data cleaning, formatting, and normalization;

[0537] Feature extraction tasks include extracting useful features from raw data for model training;

[0538] Model training tasks include training models using specific algorithms and datasets;

[0539] Reasoning tasks include using a trained model to predict or classify new data;

[0540] Evaluation tasks include evaluating and testing the model's performance;

[0541] The transmission task includes transmitting AI data or models.

[0542] 13. Based on the above, the first node is an AI service, AI task, or AI resource QoS execution node, such as NG-RAN, UE, or other independent AI entity.

[0543] This disclosure also proposes an apparatus for implementing any of the above methods. For example, an apparatus is proposed that includes units or modules for implementing the steps performed by each node (e.g., a first device, a network device) in any of the above methods.

[0544] It should be understood that the division of units or modules in the above device is only a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, the units or modules in the device can be implemented by a processor calling software: for example, the device includes a processor connected to a memory containing instructions. The processor calls the instructions stored in the memory to implement any of the above methods or to implement the functions of the units or modules in the above device. The processor can be, for example, a general-purpose processor, such as a Central Processing Unit (CPU) or a microprocessor, and the memory can be internal or external to the device. Alternatively, the units or modules in the device can be implemented in the form of hardware circuits. The functionality of some or all of the units or modules can be achieved through the design of these hardware circuits, which can be understood as one or more processors. For example, in one implementation, the hardware circuit is an application-specific integrated circuit (ASIC). The functionality of some or all of the units or modules is achieved through the design of the logical relationships between the components within the circuit. In another implementation, the hardware circuit can be implemented using a programmable logic device (PLD). Taking a field-programmable gate array (FPGA) as an example, it can include a large number of logic gates. The connection relationships between the logic gates are configured through configuration files, thereby achieving the functionality of some or all of the units or modules. All units or modules of the above device can be implemented entirely through processor-called software, entirely through hardware circuits, or partially through processor-called software with the remaining parts implemented through hardware circuits.

[0545] In this embodiment, the processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction read and execute capabilities, such as a Central Processing Unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), or a digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. The logical relationships of the aforementioned hardware circuits are fixed or reconfigurable. For example, the processor is a hardware circuit implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units or modules. Furthermore, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a Neural Network Processing Unit (NPU), a Tensor Processing Unit (TPU), or a Deep Learning Processing Unit (DPU).

[0546] Figure 4A is a schematic diagram of the structure of the first node proposed in an embodiment of this disclosure. As shown in Figure 4A, the first node 4100 may include a transceiver module 4101.

[0547] In some embodiments, the transceiver module 4101 is configured to send a first request to the second node when the Quality of Service (QoS) information cannot be satisfied; wherein the first request is used to request the second node to perform QoS coordination.

[0548] In some embodiments, the transceiver module 4101 is used to perform at least one of the communication steps such as sending and / or receiving performed by the first node 4100 in any of the above methods (e.g., steps S2101a, S2101b, and S2103, but not limited thereto), which will not be described in detail here.

[0549] Figure 4B is a schematic diagram of the structure of the second node proposed in an embodiment of this disclosure. As shown in Figure 4B, the second node 4200 may include at least one of a transceiver module 4201 and a processing module 4202.

[0550] In some embodiments, the transceiver module 4201 is used to receive a first request sent by the first node; wherein the first request is used to request the second node to perform QoS coordination.

[0551] In some embodiments, the processing module 4202 is used to perform QoS coordination based on the first request.

[0552] In some embodiments, the transceiver module 4201 is used to perform at least one of the communication steps (such as step S2103, step S2104, step S2106, but not limited thereto) performed by the second node 4200 in any of the above methods, which will not be described in detail here.

[0553] In some embodiments, the processing module 4202 described above is used to perform at least one of the other steps (such as step S2104, but not limited thereto) executed by the second node 4200 in any of the above methods, which will not be described in detail here.

[0554] Figure 4C is a structural schematic diagram of the third node proposed in an embodiment of this disclosure. As shown in Figure 4C, the third node 4300 may include: a transceiver module 4301.

[0555] In some embodiments, the transceiver module 4301 is configured to send first indication information to the first node; wherein the first indication information is used to indicate whether QoS coordination should be performed. And / or send second indication information to the first node; wherein the second indication information is used to determine the second node.

[0556] In some embodiments, the transceiver module 4301 is used to perform at least one of the communication steps (such as step S2101a, but not limited thereto) performed by the third node 4300 in any of the above methods, which will not be described in detail here.

[0557] Figure 4D is a structural schematic diagram of the fourth node proposed in an embodiment of this disclosure. As shown in Figure 4D, the fourth node 4400 may include a transceiver module 4401.

[0558] In some embodiments, the transceiver module 4401 is used to send second indication information to the first node; wherein the second indication information is used to determine the second node.

[0559] In some embodiments, the transceiver module 4401 is used to perform at least one of the communication steps (such as step S2101b, but not limited thereto) performed by the third node 4300 in any of the above methods, which will not be described in detail here.

[0560] Figure 4E is a structural schematic diagram of the fourth node proposed in an embodiment of this disclosure. As shown in Figure 4E, the associated node 4500 may include a processing module 4501.

[0561] In some embodiments, the processing module 4501 is used to update the Quality of Service (QoS) information of the associated node; wherein the associated node is a node associated with the QoS information of the first node.

[0562] In some embodiments, the processing module 4501 described above is used to perform at least one of the other steps (such as step S2108, but not limited thereto) performed by the associated node 4500 in any of the above methods, which will not be described in detail here.

[0563] Figure 4F is a structural schematic diagram of the fifth node proposed in an embodiment of this disclosure. As shown in Figure 4F, the fifth node 4600 may include a transceiver module 4601.

[0564] In some embodiments, the transceiver module 4601 is configured to receive an update request sent by a second node; wherein the update request is used to request an update of the Quality of Service (QoS) information of an associated node, the associated node being a node associated with the QoS information of the first node; based on the update request, a fourth indication information is sent to the associated node; wherein the fourth indication information is used to update the QoS information of the associated node.

[0565] In some embodiments, the transceiver module 4601 is used to perform at least one of the communication steps (e.g., steps S2106, S2107, but not limited thereto) performed by the fifth node 4600 in any of the above methods, which will not be elaborated further here. In some embodiments, the processing module may be a single module or may include multiple sub-modules. Optionally, the multiple sub-modules may each perform all or part of the steps required by the processing module. Optionally, the processing module may be interchangeable with the processor.

[0566] In some embodiments, the transceiver module may include a transmitting module and / or a receiving module, which may be separate or integrated. Optionally, the transceiver module may be interchangeable with a transceiver.

[0567] Figure 5A is a schematic diagram of the structure of the communication device 5100 proposed in an embodiment of this disclosure. The communication device 5100 can be a node (e.g., a first node, a second node, a third node, a fourth node, an associated node, or a fifth node), or a chip, chip system, or processor that supports the node in implementing any of the above methods. The communication device 5100 can be used to implement the methods described in the above method embodiments, and for details, please refer to the description in the above method embodiments.

[0568] As shown in Figure 5A, the communication device 5100 includes one or more processors 5101. The processor 5101 can be a general-purpose processor or a dedicated processor, such as a baseband processor or a central processing unit (CPU). The baseband processor can be used to process communication protocols and communication data, while the CPU can be used to control communication devices (e.g., base stations, baseband chips, terminal devices, terminal device chips, DUs or CUs, etc.), execute programs, and process program data. Optionally, the communication device 5100 can be used to execute any of the above methods. Optionally, one or more processors 5101 can be used to invoke instructions to cause the communication device 5100 to execute any of the above methods.

[0569] In some embodiments, the communication device 5100 further includes one or more transceivers 5102. When the communication device 5100 includes one or more transceivers 5102, the transceiver 5102 performs at least one of the communication steps such as sending and / or receiving in the above method (e.g., steps S2101a, S2101b, S2103, S2105, S2106, S2107, but not limited thereto), and the processor 5101 performs at least one of other steps (e.g., steps S2102, S2104, S2108, but not limited thereto). In optional embodiments, the transceiver may include a receiver and / or a transmitter, which may be separate or integrated. Optionally, the terms transceiver, transceiver unit, transceiver, transceiver circuit, interface circuit, interface, etc., can be used interchangeably; the terms transmitter, transmitting unit, transmitter, transmitting circuit, etc., can be used interchangeably; and the terms receiver, receiving unit, receiver, receiving circuit, etc., can be used interchangeably.

[0570] In some embodiments, the communication device 5100 further includes one or more memories 5103 for storing data. Optionally, all or part of the memories 5103 may be located outside the communication device 5100. In optional embodiments, the communication device 5100 may include one or more interface circuits 5104. Optionally, the interface circuits 5104 are connected to the memories 5103 and can be used to receive data from the memories 5103 or other devices, and to send data to the memories 5103 or other devices. For example, the interface circuits 5104 can read data stored in the memories 5103 and send the data to the processor 5101.

[0571] The communication device 5100 described in the above embodiments may be a network device, but the scope of the communication device 5100 described in this disclosure is not limited thereto, and the structure of the communication device 5100 may not be limited by FIG. 5A. The communication device may be a standalone device or a part of a larger device. For example, the communication device may be: (1) a standalone integrated circuit IC, or chip, or chip system or subsystem; (2) a collection of one or more ICs, optionally, the IC collection may also include storage components for storing data and programs; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (5) a receiver, terminal device, smart terminal device, cellular phone, wireless device, handheld device, mobile unit, vehicle device, network device, cloud device, artificial intelligence device, etc.; (6) others, etc.

[0572] Figure 5B is a schematic diagram of the structure of the chip 5200 proposed in an embodiment of this disclosure. For cases where the communication device 5100 can be a chip or a chip system, the schematic diagram of the chip 5200 shown in Figure 5B can be referred to, but is not limited thereto.

[0573] Chip 5200 includes one or more processors 5201. Chip 5200 is used to perform any of the methods described above.

[0574] In some embodiments, chip 5200 further includes one or more interface circuits 5202. Optionally, terms such as interface circuit, interface, and transceiver pin can be used interchangeably. In some embodiments, chip 5200 further includes one or more memories 5203 for storing data. Optionally, all or part of the memories 5203 may be located outside of chip 5200. Optionally, interface circuit 5202 is connected to memory 5203, and interface circuit 5202 can be used to receive data from memory 5203 or other devices, and interface circuit 5202 can be used to send data to memory 5203 or other devices. For example, interface circuit 5202 can read data stored in memory 5203 and send the data to processor 5201.

[0575] In some embodiments, the interface circuit 5202 performs at least one of the communication steps such as sending and / or receiving in the above method (e.g., steps S2101a, S2101b, S2103, S2105, S2106, S2107, but not limited thereto). The interface circuit 5202 performing the communication steps such as sending and / or receiving in the above method refers, for example, to the interface circuit 5202 performing data interaction between the processor 5201, the chip 5200, the memory 5203, or the transceiver device. In some embodiments, the processor 5201 performs at least one of other steps (e.g., steps S2102, S2104, S2108, but not limited thereto).

[0576] The modules and / or devices described in the various embodiments, such as virtual devices, physical devices, and chips, can be combined or separated arbitrarily as needed. Optionally, some or all steps can also be performed collaboratively by multiple modules and / or devices, which is not limited here.

[0577] This disclosure also proposes a storage medium storing instructions that, when executed on the communication device 5100, cause the communication device 5100 to perform any of the above methods. Optionally, the storage medium is an electronic storage medium. Optionally, the storage medium is a computer-readable storage medium, but not limited thereto; it may also be a storage medium readable by other devices. Optionally, the storage medium may be a non-transitory storage medium, but not limited thereto; it may also be a temporary storage medium.

[0578] This disclosure also provides a program product that, when executed by the communication device 5100, causes the communication device 5100 to perform any of the above methods. Optionally, the program product is a computer program product.

[0579] This disclosure also proposes a computer program that, when run on a computer, causes the computer to perform any of the above methods.

[0580] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0581] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. An operation processing method, characterized in that, The method is executed by the first node, and the method includes: If the QoS information cannot be met, a first request is sent to the second node; wherein, the first request is used to request the second node to perform QoS coordination.

2. The method according to claim 1, characterized in that, The first request includes at least one of the following: Information about the first node; QoS information of the first node; First reason; wherein, the first reason is used to indicate the reason for performing the first operation; Information about associated nodes; wherein the associated nodes are nodes associated with the QoS information of the first node.

3. The method according to claim 2, characterized in that, The QoS information of the first node includes at least one of the following: The QoS information satisfied by the first node; QoS information that the first node cannot satisfy; The QoS information used by the first node.

4. The method according to any one of claims 1-3, characterized in that, The method further includes: Perform a first operation; wherein the first operation includes determining whether to perform QoS coordination and / or determining the second node.

5. The method according to claim 4, characterized in that, The determination of whether to perform QoS coordination includes at least one of the following: Based on a predefined method, determine whether to perform QoS coordination; Based on the first indication information sent by the third node, it is determined whether to perform QoS coordination; wherein, the first indication information is used to indicate whether to perform QoS coordination.

6. The method according to claim 5, characterized in that, The third node includes at least one of the following: The node that configures the QoS information of the first node; Nodes that control QoS coordination.

7. The method according to any one of claims 4-6, characterized in that, Determining the second node includes at least one of the following: The second node is determined based on a predefined method; The second node is determined based on the second indication information sent by the fourth node; wherein the second indication information is used to determine the second node.

8. The method according to claim 7, characterized in that, The fourth node includes at least one of the following: The node that configures the QoS information of the first node; Nodes that control QoS coordination.

9. The method according to any one of claims 4-8, characterized in that, The second node includes at least one of the following: The node that configures the QoS information of the first node; Nodes that control QoS coordination; The QoS information type belongs to the same level as the first node.

10. The method according to any one of claims 1-9, characterized in that, The QoS information includes at least one of the following categories: QoS information for artificial intelligence (AI) services; QoS information for artificial intelligence (AI) tasks; QoS information for artificial intelligence (AI) resources.

11. The method according to any one of claims 1-10, characterized in that, The QoS coordination includes at least one of the following: QoS coordination between the first node and the associated node; wherein, after coordination, the QoS information of the first node satisfies the QoS information of the AI ​​service and / or satisfies the QoS information of the first node, and the associated node is a node associated with the QoS information of the first node; QoS coordination between the first node and the second node; wherein, after coordination, the QoS information of the first node satisfies the QoS information of the AI ​​service and / or satisfies the QoS information of the first node.

12. An operation processing method, characterized in that, The method is executed by the second node, and the method includes: Receive a first request sent by the first node; wherein the first request is used to request the second node to perform QoS coordination; Based on the first request, QoS coordination is performed.

13. The method according to claim 12, characterized in that, The first request includes at least one of the following: Information about the first node; QoS information of the first node; First reason; wherein the first reason is used to indicate the reason for the first node to perform the first operation, the first operation including determining whether to perform QoS coordination and / or determining the second node; Information about associated nodes; wherein the associated nodes are nodes associated with the QoS information of the first node.

14. The method according to claim 13, characterized in that, The QoS information of the first node includes at least one of the following: The QoS information satisfied by the first node; QoS information that the first node cannot satisfy; The QoS information used by the first node.

15. The method according to any one of claims 12-14, characterized in that, The second node includes at least one of the following: The node that configures the QoS information of the first node; Nodes that control QoS coordination; The QoS information type belongs to the same level as the first node.

16. The method according to any one of claims 12-15, characterized in that, The method further includes: Receive multiple first requests sent by multiple first nodes, and at least two of the multiple first requests conflict, and determine the priority of each first request; QoS coordination is performed in descending order of priority of the first request.

17. The method according to any one of claims 12-16, characterized in that, The QoS coordination includes at least one of the following: QoS coordination between the first node and the associated node; wherein, after coordination, the QoS information of the first node satisfies the QoS information of the AI ​​service and / or satisfies the QoS information of the first node, and the associated node is a node associated with the QoS information of the first node; QoS coordination between the first node and the second node; wherein, after coordination, the QoS information of the first node satisfies the QoS information of the AI ​​service and / or satisfies the QoS information of the first node.

18. The method according to claim 17, characterized in that, The QoS coordination includes: Based on the QoS information of the AI ​​service and / or the QoS information of the first node, determine the QoS information of the first node after collaboration; Based on the QoS information of the first node after collaboration, the QoS information of the associated nodes after collaboration is determined.

19. The method according to claim 17, characterized in that, The QoS coordination includes: Based on the QoS information of the AI ​​service and / or the QoS information of the first node, determine the QoS information of the first node after collaboration; Based on the QoS information of the first node after collaboration, determine the QoS information of the second node after collaboration; Based on the QoS information of the second node after collaboration, the QoS information is updated.

20. The method according to any one of claims 12-19, characterized in that, The method further includes: Send a third indication message to the associated node; wherein the third indication message is used to update the QoS information of the associated node.

21. The method according to claim 20, characterized in that, The third indication information includes at least one of the following: QoS information of the first node; QoS information of associated nodes after collaboration.

22. The method according to any one of claims 12-19, characterized in that, The method further includes: Send an update request to the fifth node; wherein the update request is used to request the fifth node to update the QoS information of the associated node.

23. The method according to claim 22, characterized in that, The fifth node includes at least one of the following: Nodes that configure the QoS of the associated nodes; Nodes that control QoS coordination.

24. The method according to any one of claims 13-23, characterized in that, QoS information includes at least one of the following: QoS information for artificial intelligence (AI) services; QoS information for artificial intelligence (AI) tasks; QoS information for artificial intelligence (AI) resources.

25. An operation processing method, characterized in that, The method is executed by a third node, and the method includes: Send a first indication message to the first node; wherein the first indication message is used to indicate whether to perform QoS coordination.

26. The method according to claim 25, characterized in that, The third node includes at least one of the following: The node that configures the QoS information of the first node; Nodes that control QoS coordination.

27. The method according to claim 26, characterized in that, QoS information includes at least one of the following: QoS information for artificial intelligence (AI) services; QoS information for artificial intelligence (AI) tasks; QoS information for artificial intelligence (AI) resources.

28. The method according to any one of claims 25-27, characterized in that, The QoS coordination includes at least one of the following: QoS coordination between the first node and the associated node; wherein, after coordination, the QoS information of the first node satisfies the QoS information of the AI ​​service and / or satisfies the QoS information of the first node, and the associated node is a node associated with the QoS information of the first node; QoS coordination between the first node and the second node; wherein, after coordination, the QoS information of the first node satisfies the QoS information of the AI ​​service and / or satisfies the QoS information of the first node.

29. An operation processing method, characterized in that, The method is executed by the fourth node, and the method includes: Send a second indication message to the first node; wherein the second indication message is used to identify the second node.

30. The method according to claim 29, characterized in that, The second node includes at least one of the following: The node that configures the QoS information of the first node; Nodes that control QoS coordination; The QoS information type belongs to the same level as the first node.

31. The method according to claim 30, characterized in that, The QoS coordination includes at least one of the following: QoS coordination between the first node and the associated node; wherein, after coordination, the QoS information of the first node satisfies the QoS information of the AI ​​service and / or satisfies the QoS information of the first node, and the associated node is a node associated with the QoS information of the first node; QoS coordination between the first node and the second node; wherein, after coordination, the QoS information of the first node satisfies the QoS information of the AI ​​service and / or satisfies the QoS information of the first node.

32. The method according to any one of claims 29-31, characterized in that, The fourth node includes at least one of the following: The node that configures the QoS information of the first node; Nodes that control QoS coordination.

33. The method according to any one of claims 30-32, characterized in that, QoS information includes at least one of the following: QoS information for artificial intelligence (AI) services; QoS information for artificial intelligence (AI) tasks; QoS information for artificial intelligence (AI) resources.

34. An operation processing method, characterized in that, The method is executed by the associated node, and the method includes: Update the Quality of Service (QoS) information of the associated node; wherein the associated node is a node associated with the QoS information of the first node.

35. The method according to claim 34, characterized in that, The updating of the Quality of Service (QoS) information of the associated node includes at least one of the following: The QoS of the fourth node is updated based on the third indication information sent by the second node; wherein the third indication information is used to update the QoS information of the fourth node. The QoS of the fourth node is updated based on the fourth indication information sent by the fifth node; wherein the fourth indication information is used to update the QoS information of the fourth node.

36. The method according to claim 35, characterized in that, The third indication information includes at least one of the following: QoS information of the first node; Nodes that control QoS coordination.

37. The method according to claim 35, characterized in that, The fifth node includes at least one of the following: The node that configures the QoS of the fourth node; Nodes that control QoS coordination.

38. The method according to any one of claims 34-37, characterized in that, QoS information includes at least one of the following: QoS information for artificial intelligence (AI) services; QoS information for artificial intelligence (AI) tasks; QoS information for artificial intelligence (AI) resources.

39. The method according to claim 37 or 38, characterized in that, The QoS coordination includes at least one of the following: QoS coordination between the first node and the associated node; wherein, after coordination, the QoS information of the first node satisfies the QoS information of the AI ​​service and / or satisfies the QoS information of the first node, and the associated node is a node associated with the QoS information of the first node; QoS coordination between the first node and the second node; wherein, after coordination, the QoS information of the first node satisfies the QoS information of the AI ​​service and / or satisfies the QoS information of the first node.

40. An operation processing method, characterized in that, The method is executed by the fifth node, and the method includes: Receive an update request sent by a second node; wherein the update request is used to request an update of the Quality of Service (QoS) information of an associated node, and the associated node is a node associated with the QoS information of the first node; Based on the update request, a fourth indication message is sent to the associated node; wherein the fourth indication message is used to update the QoS information of the associated node.

41. The method according to claim 40, characterized in that, The fifth node includes at least one of the following: The node that configures the QoS information of the associated node; Nodes that control QoS coordination.

42. The method according to claim 41, characterized in that, The QoS coordination includes at least one of the following: QoS coordination between the first node and the associated node; wherein, after coordination, the QoS information of the first node satisfies the QoS information of the AI ​​service and / or satisfies the QoS information of the first node, and the associated node is a node associated with the QoS information of the first node; QoS coordination between the first node and the second node; wherein, after coordination, the QoS information of the first node satisfies the QoS information of the AI ​​service and / or satisfies the QoS information of the first node.

43. The method according to any one of claims 40-42, characterized in that, QoS information includes at least one of the following: QoS information for artificial intelligence (AI) services; QoS information for artificial intelligence (AI) tasks; QoS information for artificial intelligence (AI) resources.

44. A first node, characterized in that, The first node includes: The transceiver module is configured to send a first request to the second node when it is unable to meet the Quality of Service (QoS) information; wherein the first request is used to request the second node to perform QoS coordination.

45. A second node, characterized in that, The second node includes: The transceiver module is configured to receive a first request sent by the first node; wherein the first request is used to request the second node to perform QoS coordination; The processing module is configured to perform QoS coordination based on the first request.

46. ​​A third node, characterized in that, The third node includes: The transceiver module is configured to send first indication information to the first node; wherein the first indication information is used to indicate whether to perform QoS coordination.

47. A fourth node, characterized in that, The fourth node includes: The processing module is configured to send second indication information to the first node; wherein the second indication information is used to determine the second node.

48. An associated node, characterized in that, The associated nodes include: The processing module is configured to update the Quality of Service (QoS) information of the associated node; wherein the associated node is a node associated with the QoS information of the first node.

49. A fifth node, characterized in that, The fifth node includes: The transceiver module is configured to receive an update request sent by a second node; wherein the update request is used to request an update of the Quality of Service (QoS) information of an associated node, and the associated node is a node associated with the QoS information of the first node. The transceiver module is further configured to send a fourth indication information to the associated node based on the update request; wherein the fourth indication information is used to update the QoS information of the associated node.

50. A first node, characterized in that, include: One or more processors; The processor is used to execute the operation processing method according to any one of claims 1-11.

51. A second node, characterized in that, include: One or more processors; The processor is used to execute the operation processing method according to any one of claims 12-24.

52. A third node, characterized in that, include: One or more processors; The processor is used to execute the operation processing method according to any one of claims 25-28.

53. A fourth node, characterized in that, include: One or more processors; The processor is used to execute the operation processing method according to any one of claims 29-33.

54. An associated node, characterized in that, include: One or more processors; The processor is used to execute the operation processing method according to any one of claims 34-39.

55. A fifth node, characterized in that, include: One or more processors; The processor is used to execute the operation processing method according to any one of claims 40-43.

56. A communication system, characterized in that, include: A first node, configured to perform the operation processing method according to any one of claims 1-11; The second node is configured to perform the operation processing method according to any one of claims 12-24; A third node, configured to perform the operation processing method according to any one of claims 25-28; A fourth node, configured to perform the operation processing method according to any one of claims 29-33; An associated node, wherein the associated node is configured to perform the operation processing method according to any one of claims 34-39; The fifth node is configured to perform the operation processing method according to any one of claims 40-43.

57. A storage medium storing instructions, characterized in that, When the instruction is executed on the communication device, the communication device performs the operation processing method as described in any one of claims 1-11, 12-24, 25-28, 29-33, 34-39 or 40-43.

58. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program is used to implement the operation processing method according to any one of claims 1-11, 12-24, 25-28, 29-33, 34-39 or 40-43.

Images