Communication method and apparatus

Abstract

A communication method and apparatus. In the method, a mapping relationship between different measurement results of a first QoE and quality-of-service flows can be established, and the method comprises, for example: currently, on the basis of the first QoE, measuring a service corresponding to first data, so as to determine a first measurement result; then, on the basis of the "mapping relationship between different measurement results of the first QoE and the quality-of-service flows", inquiring for a quality-of-service flow (such as a first quality-of-service flow) corresponding to the first measurement result; and mapping the first data to the first quality-of-service flow for transmission. By using the method of the present application, quality-of-service requirements of the same service in different phases can be met, thereby improving the service transmission performance.

Description

Communication method and apparatus

[0001] Cross Reference to Related Applications

[0002] This application claims priority to the Chinese Patent Application No. 202510246266.2, filed on February 28, 2025, and entitled "A Communication Method and Apparatus", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0003] The present application relates to the field of communication technology, and in particular to a communication method and apparatus. BACKGROUND

[0004] In uplink transmission, the terminal can map the first data (at this time, referring to uplink data) to the corresponding quality of service flow; and transmit the first data to the receiving end (such as the user plane function (UPF) network element side, etc.) through the corresponding quality of service flow. The first quality of service flow can have independent quality of service parameters, such as the transmission speed and packet loss rate corresponding to the quality of service flow, etc., so as to meet the transmission requirements of the first data.

[0005] In downlink transmission, the UPF network element can map the first data (at this time, referring to downlink data) to the corresponding quality of service flow; and transmit the first data to the receiving end (such as the terminal side, etc.) through the corresponding quality of service flow.

[0006] How to map the quality of service flow to meet the transmission requirements of different data and improve the transmission performance of data is a research direction. SUMMARY

[0007] In a first aspect, a communication method is provided, which can be applied to a terminal side, such as a terminal or a communication module and / or a computing module in the terminal, or a circuit or a chip (such as a modem chip, also known as a baseband chip, or a system on chip (SoC) chip or a system in package (SIP) chip containing a modem core) in the terminal responsible for communication functions, or a circuit or a chip (such as a graphics processing unit (GPU), an artificial intelligence (AI) processor, or an application specific integrated circuit (ASIC)) in the terminal responsible for communication and / or computing functions, or a logic node, a logic module, or software capable of realizing all or part of the terminal functions. Alternatively, the method can be applied to a network side, such as a UPF network element on the network side, a module (such as a circuit, a chip, or a chip system, etc.) in the UPF network element, or a logic node, a logic module, or software capable of realizing all or part of the UPF network element functions, or a circuit or a chip (such as a GPU, an AI processor, or an ASIC) in the UPF network element responsible for communication and / or computing functions, etc.

[0008] Taking the case where the method is applied to a terminal, in the method: the terminal takes a first measurement result of a first quality of experience (QoE), the first QoE including at least one of the following: inference accuracy, inference latency, inference throughput, training latency, training power consumption, or training convergence speed; the terminal maps first data to a first quality of service (QoS) flow according to the first measurement result, the first measurement result and the first QoS flow having a mapping relationship; and the terminal transmits the first data through the first QoS flow.

[0009] Through the above design, a mapping relationship between different measurement results of the first QoE and the service quality flow can be established. For example, based on the first QoE, the service corresponding to the first data is measured to determine the first measurement result. Then, according to the above "mapping relationship between different measurement results of the first QoE and the service quality flow", the service quality flow corresponding to the first measurement result (such as the first service quality flow) is queried. The first data is mapped to the first service quality flow for transmission. In the example above, the corresponding measurement results are different at different training stages, therefore, the service quality flows with mapping relationships are different. For example, in the first half of the model training stage, measurement result 1 corresponds to service quality flow 1, and the service quality flow parameters corresponding to service quality flow 1 are faster transmission speed but lower transmission accuracy (such as higher packet loss rate). In the second half of the model training stage, measurement result 2 corresponds to service quality flow 2, and the service quality parameters corresponding to service quality flow 2 are slower transmission speed but higher transmission accuracy (such as lower packet loss rate). Using the method of this application, the service quality requirements of the same service at different stages can be met, improving the performance of service transmission.

[0010] In one possible design, the first measurement result is indicated at least by the type information of the first QoE and the measurement result information of the first QoE. Optionally, the first measurement result may also be indicated by the business information of the first data.

[0011] Through the above design, the first measurement result is specifically indicated by the type information of the first QoE and the measurement result information of the first QoE. Furthermore, it can also be indicated by its corresponding service information. With the above information, a measurement result (i.e., the first measurement result) can be uniquely indicated / represented. Furthermore, based on the uniquely indicated / represented first measurement result, the service quality flow with which it has a mapping relationship (i.e., the first service quality flow) can be accurately determined, thereby mapping the first data to the matching service quality flow and improving the transmission performance of the service.

[0012] In one possible design, obtaining the first measurement result includes: obtaining the first measurement result from the first data; or, measuring the inference task and / or training task corresponding to the first data according to the first QoE to obtain the first measurement result; or, receiving first indication information, the first indication information being used to indicate the first measurement result.

[0013] Through the above design, the terminal or UPF network element can obtain the first measurement result from the first data; or, the terminal or UPF network element can perform the measurement itself to obtain the first measurement result; or, other network elements can indicate the first measurement result to the terminal or UPF network element. In the first or third method described above, the terminal or UPF network element does not need to perform the measurement itself, which can reduce the power consumption overhead caused by the measurement of the terminal or UPF network element.

[0014] In one possible design, it further includes: receiving first configuration information, which is used to configure the mapping relationship between the first measurement result and the first quality of service flow.

[0015] In one possible design, when the method of the first aspect is applied to the network side (such as the UPF network element side), the mapping relationship between the first measurement result and the first quality of service flow is included in the first packet detection rule (PDR), which is associated with the first usage reporting rule (URR), and further includes: sending a first report to indicate the first data volume of the first data, which is determined according to the first URR, which is used to indicate the granularity of the statistics of the first data volume.

[0016] By modifying the granularity of the statistical data in the first URR through the above design, the UPF network element can report the corresponding data volume with finer granularity, thereby meeting the needs of different services.

[0017] In one possible design, the granularity of this first data volume is: business granularity; or a finer granularity than business granularity (such as the granularity of the first category under a business), without restriction.

[0018] Through the above design, UPF network elements can perform data volume statistics and report at the service granularity (e.g., the first data volume). For example, a UPF network element can statistically analyze and report the corresponding data volume for a specific service. Alternatively, UPF network elements can statistically analyze and report data volume at a finer granularity than the service granularity (e.g., the first data volume). For example, for a specific service, a UPF network element can statistically analyze and report the corresponding data volume (e.g., the first data volume) at the "data home node granularity." On one hand, the corresponding receiving end (e.g., SMF network element) can obtain more granular data statistics, thus providing richer information about the data volume. Optionally, further, the corresponding receiving end (e.g., SMF network element) can perform corresponding operations based on the finer-grained data statistics reported by the UPF network element, thereby improving data transmission performance. For example, if the data volume corresponding to a "data home node" is too large, the SMF network element at the receiving end can optimize the transmission parameters corresponding to that data, such as increasing the transmission rate of subsequent data.

[0019] In one possible design, after sending the first report, the method further includes: receiving first update information; and updating the first forwarding action rule FAR and / or the first quality of service flow execution rule QER associated with the first PDR based on the first update information.

[0020] Through the above design, the SMF network element can update the corresponding parameters based on the first data volume reported by the UPF network element, thereby meeting the needs of the corresponding services and improving data transmission performance.

[0021] Secondly, a communication method is provided, which is applied to the network side, such as a UPF network element on the network side, a module (e.g., a circuit, chip, or chip system) in the UPF network element, or a logical node, logical module, or software that can implement all or part of the functions of the UPF network element, or a circuit or chip (e.g., a GPU, AI processor, or ASIC) in the UPF network element responsible for communication and / or computing functions. Taking the application of this method to a UPF network element as an example, in this method: the UPF network element receives first information, which is used to indicate or configure a first mapping relationship, which matches a first measurement result of a first quality of experience (QoE) of the first data; the UPF network element sends the first data through a first quality of service stream corresponding to the first mapping relationship.

[0022] Through the above design, the SMF network element can instruct or configure the UPF network element to apply the corresponding mapping relationship according to the different first measurement results, and perform service quality flow mapping, thereby meeting the service quality flow requirements of the transmitted data under different stages or different measurement results, and satisfying the data needs.

[0023] In one possible design, the first information is used to indicate a first mapping relationship, which belongs to multiple mapping relationships, and any one of these multiple mapping relationships is associated with the measurement result of the first QoE.

[0024] Through the above design, the UPF network element can obtain multiple mapping relationships in advance. The SMF network element can then directly indicate to the UPF network element the identifier or index of the first mapping relationship that matches the current first measurement result. In other words, the first information can include the identifier or index of the first mapping relationship. Typically, the identifier or index occupies relatively little transmission resources, thus saving transmission resources.

[0025] In one possible design, the multiple mapping relationships are predefined or configured by the session management function network element, and also include: the UPF network element receiving first configuration information, which is used to configure the multiple mapping relationships.

[0026] Through the above design, multiple mapping relationships on the UPF network element side can be predefined. The terminal can then obtain these multiple mapping relationships according to the predefined method without additional configuration procedures, thus saving transmission resources for configuring multiple mapping relationships.

[0027] In one possible design, the first information is used to configure a first mapping relationship, and the method further includes: the UPF network element updates the current application mapping relationship to the first mapping relationship according to the configuration of the first information.

[0028] Through the above design, the UPF network element updates the current application mapping relationship to a first mapping relationship that matches the current first measurement result, which can map the current first data to be transmitted to the matching first quality of service stream, thereby improving the transmission performance of the service.

[0029] In one possible design, the first mapping relationship includes: a mapping relationship between a first parameter and a first quality of service flow, wherein the first parameter includes at least the address information and / or port information of the data.

[0030] In one possible design, sending the first data through the first quality of service flow corresponding to the first mapping relationship includes: the UPF network element obtaining a first parameter from the first data; the UPF network element determining the first quality of service flow corresponding to the first parameter based on the mapping relationship between the first parameter and the first quality of service flow contained in the first mapping relationship; and the UPF network element sending the first data through the first quality of service flow.

[0031] In one possible design, the first mapping relationship is included in the first packet detection rule (PDR), the first PDR is associated with the first usage report rule (URR), and further includes: the UPF network element determines the first data volume according to the first URR, the first URR includes granular information for statistical analysis of the first data volume; when the first data volume meets the first condition, the UPF network element sends a first report, the first report includes indication information of the first data volume.

[0032] By modifying the granularity of the statistical data in the first URR through the above design, the UPF network element can report the corresponding data volume with finer granularity, thereby meeting the needs of different services.

[0033] In one possible design, the first URR includes granular information for statistically analyzing the first data volume, specifically: business granularity.

[0034] In one possible design, the UPF network element further includes: receiving first update information, which is used to update the first forwarding action rule (FAR) and / or the first quality of service flow execution rule (QER) associated with the first PDR; and the UPF network element updating the first FAR and / or the first QER associated with the first PDR according to the first update information.

[0035] Through the above design, the SMF network element can update the corresponding parameters based on the first data volume reported by the UPF network element, thereby meeting the needs of the corresponding services and improving data transmission performance.

[0036] Thirdly, a communication method is provided, which is applied to the network side, such as an SMF network element on the network side, a module (e.g., a circuit, chip, or chip system) in the SMF network element, or a logical node, logical module, or software that can implement all or part of the functions of the SMF network element, or a circuit or chip (e.g., a GPU, AI processor, or ASIC) in the SMF network element responsible for communication and / or computing functions. Taking the application of this method to an SMF network element as an example, the method includes: the SMF network element receiving first request information, which is used to request an update of the mapping relationship of downlink data of the user plane function network element; the SMF network element sending first information, which is used to indicate or configure a first mapping relationship, which is associated with a first measurement result of a first quality of experience (QoE) of the first data.

[0037] In one possible design, the first request information comes from an artificial intelligence (AI) entity or a policy control function network element, which performs the measurement of the first QoE; or, the first request information comes from a terminal, which performs the measurement of the first QoE.

[0038] In one possible design, the first request information includes indication information of the first mapping relationship, and further includes: determining the first mapping relationship among multiple mapping relationships based on the indication information of the first mapping relationship.

[0039] In one possible design, the first request information includes indication information of the first measurement result of the first QoE of the first data, and further includes: the SMF network element determining a first mapping relationship that is associated with the first measurement result among multiple mapping relationships, wherein any one of the multiple mapping relationships is associated with the measurement result of the first QoE.

[0040] In one possible design, the multiple mapping relationships are predefined, or generated based on policy information provided by the policy function network element, and may also include: the SMF network element receiving policy information corresponding to the multiple mapping relationships; and the SMF network element generating the multiple mapping relationships based on the policy information.

[0041] In one possible design, when the first information is used to indicate the first mapping relationship, configuring the multiple mapping relationships to the user plane function network element further includes: the SMF network element sending first configuration information, which is used to configure the multiple mapping relationships.

[0042] In one possible design, the first request information includes policy information related to the first measurement result of the first QoE of the first data, and also includes: the SMF network element generating the first mapping relationship based on the policy information.

[0043] In one possible design, the first mapping relationship includes: a mapping relationship between a first parameter and a first quality of service flow, wherein the first parameter includes at least the address information and / or port information of the data.

[0044] In one possible design, the first mapping relationship is included in the first packet detection rule (PDR), and further includes: the SMF network element receiving a first report, the first report containing indication information of a first data volume, the first data volume being determined according to the first usage reporting rule (URR) associated with the first PDR, the first URR containing granular information for statistically analyzing the first data volume.

[0045] In one possible design, the first URR includes the granularity of the statistics of the first data volume, specifically: business granularity, or the granularity of the first category of a business.

[0046] In one possible design, the SMF network element also includes: when the first data volume meets the second condition, sending first update information, which is used to update the first forwarding action rule FAR and / or the first quality of service flow execution rule QER associated with the first PDR.

[0047] The third aspect and its potential beneficial effects can be found in the explanation of the second aspect, and will not be repeated here.

[0048] Fourthly, this application provides a communication device that has the functions of the first aspect described above. For example, the communication device includes modules, units, or means that perform the operations involved in the first aspect. These modules, units, or means can be implemented by software, hardware, or a combination of software and hardware.

[0049] Fifthly, this application provides a communication device that has the functions of the second aspect above. For example, the communication device includes modules, units, or means that perform the operations involved in the second aspect above. These modules, units, or means can be implemented by software, hardware, or a combination of software and hardware.

[0050] Sixthly, this application provides a communication device that has the functions of the third aspect above. For example, the communication device includes modules, units, or means that perform the operations involved in the third aspect above. These modules, units, or means can be implemented by software, hardware, or a combination of software and hardware.

[0051] In a seventh aspect, this application provides a communication device including an interface circuit and one or more processors. The one or more processors are coupled to a memory. The memory stores part or all of the necessary computer program or instructions for implementing the functions described in the first aspect. The one or more processors are executable to carry out the computer program or instructions, causing the communication device to implement the methods in any possible design or implementation of the first aspect. The interface circuit is used to implement the communication functions within the communication device and / or the communication functions between the communication device and other devices or components.

[0052] In one possible design, the processor is used to communicate with other devices or components through the interface circuit.

[0053] In one possible design, the communication device may also include the memory.

[0054] The aforementioned communication device may be a terminal, or a communication and / or computing module in a terminal, or a chip in a terminal responsible for communication functions such as a modem chip (also known as a baseband chip) or a SoC or SIP chip containing a modem module, or a circuit or chip in a terminal responsible for communication and / or computing functions (such as a GPU, AI processor, or ASIC), or a logical node or logical module capable of implementing all or part of the terminal functions.

[0055] Eighthly, this application provides a communication device including an interface circuit and one or more processors. The one or more processors are coupled to a memory. The memory stores part or all of the necessary computer program or instructions for implementing the functions described in the second aspect above. The one or more processors are executable to carry out the computer program or instructions, causing the communication device to implement the methods in any possible design or implementation of the second aspect above. The interface circuit is used to implement the communication functions within the communication device and / or the communication functions between the communication device and other devices or components.

[0056] In one possible design, the processor is used to communicate with other devices or components through the interface circuit.

[0057] In one possible design, the communication device may also include the memory.

[0058] The aforementioned communication device may be an access network device, or a module (e.g., a circuit, chip, or chip system) within an access network device, or a circuit or chip (e.g., a GPU, AI processor, or ASIC) within an access network device responsible for communication and / or computing functions, or a logical node or logical module capable of implementing all or part of the functions of the access network device.

[0059] Ninthly, this application provides a communication device including an interface circuit and one or more processors. The one or more processors are coupled to a memory. The memory stores part or all of the computer program or instructions necessary to implement the functions described in the third aspect above. The one or more processors are executable to carry out the computer program or instructions, causing the communication device to implement the methods in any possible design or implementation of the third aspect above. The interface circuit is used to implement the communication functions within the communication device and / or the communication functions between the communication device and other devices or components.

[0060] In one possible design, the processor is used to communicate with other devices or components through the interface circuit.

[0061] In one possible design, the communication device may also include the memory.

[0062] The aforementioned communication device may be an access network device, or a module (e.g., a circuit, chip, or chip system) within an access network device, or a circuit or chip (e.g., a GPU, AI processor, or ASIC) within an access network device responsible for communication and / or computing functions, or a logical node or logical module capable of implementing all or part of the functions of the access network device.

[0063] In a tenth aspect, this application provides a computer-readable storage medium storing computer-readable instructions that, when read and executed by a computer, cause the computer to perform any of the possible designs in the first to third aspects described above.

[0064] In one aspect, this application provides a computer program product that, when read and executed by a computer, causes the computer to perform any of the possible designs in the first to third aspects described above.

[0065] In a twelfth aspect, this application provides a communication system, comprising: a first communication device and a second communication device; wherein the first communication device is used to implement any possible design method in the second aspect; and the second communication device is used to implement any possible design method in the third aspect. Attached Figure Description

[0066] Figure 1 is a schematic diagram of the communication system provided in an embodiment of this application;

[0067] Figure 2 is a schematic diagram of the network architecture based on the AI ​​module provided in an embodiment of this application;

[0068] Figure 3 is a schematic diagram of the access network node provided in an embodiment of this application;

[0069] Figure 4 is a schematic diagram of the application architecture of the AI ​​model provided in the embodiments of this application;

[0070] Figures 5, 7, 9, 10 and 12 are schematic flowcharts provided in the embodiments of this application;

[0071] Figure 6 is a schematic diagram of the service quality flow rules provided in an embodiment of this application;

[0072] Figures 8a and 8b are schematic diagrams of the air interface mapping rules provided in the embodiments of this application;

[0073] Figure 11 is a schematic diagram of the first data processing provided in an embodiment of this application;

[0074] Figure 13 is a structural schematic diagram of the device provided in an embodiment of this application;

[0075] Figure 14 is a schematic diagram of the structure of the terminal device provided in the embodiment of this application. Detailed Implementation

[0076] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings. The specific operating methods and functional descriptions in the method embodiments can also be applied to the device embodiments or system embodiments.

[0077] I. In the description of this application, unless otherwise specified, the number of nouns refers to "singular nouns or plural nouns," that is, "one or more." "At least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, or B exists alone, where A and B can be singular or plural. In the textual description of this application, the character " / " generally indicates that the related objects before and after are in an "or" relationship; in the formulas of this application, the character " / " indicates that the related objects before and after are in a "division" relationship. "Including at least one of A, B, or C" or similar expressions can mean: including A; including B; including C; including A and B; including A and C; including B and C; including A, B, and C, where A, B, and C can be singular or plural.

[0078] II. In the description of this application, the various numerical designations are for ease of description and are not intended to limit the scope of the embodiments of this application. The order of the process numbers does not imply the order of execution; the execution order of each process should be determined by its function and internal logic. The ordinal numbers such as "first" and "second" used in the embodiments of this application are used to distinguish multiple objects and do not limit the size, order, timing, priority, or importance of the multiple objects. In the description of this application,

Embodiment 1

Embodiment 2

Embodiment 3

Embodiment 1

Embodiment 3

Embodiment 2

Embodiment 4

[0079] III. In the description of this application, the numbering of steps in the various flowcharts is only for distinguishing different steps and is not intended to limit the order of steps. Furthermore, there is no limitation on the number of steps included in each flowchart; each flowchart may contain more or fewer steps than shown in the diagram, and multiple steps may be combined into one step, or one step may be broken down into multiple steps, etc. Related descriptions in different flowcharts can be referred to cross-referenced. The dashed arrows or boxes in the flowcharts indicate optional steps or optional modules.

[0080] IV. In this application, "sending information" can be understood as one device sending information to another device, or it can also be understood as one logical module within a device sending information to another logical module. For example, "access network device sending information" can be understood as the access network device sending information to another device (such as a terminal), or it can be understood as logical module 1 in the access network device sending information to logical module 2 in the access network device.

[0081] In this application, "receiving information" can be understood as one device receiving information from another device, or it can also be understood as a logical module within a device receiving information from another logical module. For example, "access network device receiving information" can be understood as the access network device receiving information from another device (such as a terminal), or it can be understood as logical module 1 in the access network device receiving information from logical module 2 in the access network device.

[0082] In this application, phrases such as "sending information to... (e.g., a terminal)" or related illustrations in the accompanying drawings can be understood as indicating that the destination of the information is a terminal. This can include sending information directly or indirectly to a terminal. Similarly, phrases such as "receiving information from... (e.g., a terminal)," "receiving information from... (e.g., a terminal)," or "receiving information sent by (e.g., a terminal)," or related illustrations in the accompanying drawings, can be understood as indicating that the source of the information is a terminal. This can include receiving information directly or indirectly from a terminal. Information may undergo necessary processing between the source and destination, such as format changes, but the destination can understand the valid information from the source. Similar expressions in this application can be interpreted similarly and will not be elaborated further here.

[0083] V. In the description of this application, "for indicating" can include both direct indication (or explicit indication) and indirect indication (or implicit indication). For example, when describing a certain indication information for indicating information I, it can include whether the indication information directly indicates I or indirectly indicates I, but does not necessarily mean that the indication information carries I.

[0084] VI. In the description of this application, "when," "if," and "if" all refer to the fact that the device will take corresponding actions under certain objective circumstances, and are not limited to a specific time, nor do they require the device to perform a judgment action, nor do they imply any other limitations. Unless otherwise specified, "if" and "if" are interchangeable, "when" is interchangeable with "in the case of," and "when" can also be replaced with "when," or "after," etc., and "when" can also be replaced with "if" / "if," etc. The words "exemplary" or "for example" are used to indicate that they are examples, illustrations, or explanations. Any embodiment or design that is described as "exemplary" or "for example" in this application should not be construed as being more preferred or advantageous than other embodiments or design solutions. Specifically, the use of the words "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0085] VII. In the description of this application: the terms “system” and “network” are used interchangeably, and “according to” and “based on” are used interchangeably. The terms “comprising,” “including,” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are expressly listed, but may include other steps or units that are not expressly listed or that are inherent to such process, method, product, or device.

[0086] 8. In the description of this application, words such as "exemplarily," "for example," and "e.g." are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as an "example" in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word "example" is intended to present concepts in a concrete manner. In the embodiments of this application, "of," "corresponding, relevant," and "corresponding" may sometimes be used interchangeably, and it should be noted that their intended meanings are consistent unless their distinction is emphasized.

[0087] IX. The embodiments of this application will be presented in the context of a system including multiple devices, components, modules, etc. It should be understood that the system may include other unmentioned devices, components, modules, etc., or may only include some of the devices, components, or modules mentioned in the embodiments. Optionally, the terms "component" and "part" in this application can be used interchangeably.

[0088] 10. In the description of this application, the terms "storage" or "preservation" may refer to storage in one or more memory devices. These memory devices may be separately configured or integrated into a processor or communication device. Alternatively, some memory devices may be separately configured, while others may be integrated into the processor or communication device. The type of memory may be any form of storage medium, and this is not limited.

[0089] XI. The network architecture and business scenarios described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0090] 12. The technical solutions of the embodiments of this application can be applied to various communication systems, such as integrated sensing and communication (ISAC), wireless local area network (WLAN), extended reality (XR) communication systems, short-range wireless communication systems (such as sidelink, wireless fidelity (Wi-Fi), Bluetooth, etc.), wired networks, vehicle to everything (V2X) communication systems, device-to-device (D2D) communication systems, vehicle-to-everything (V2X) communication systems, 4th generation (4G) mobile communication systems (such as Long Term Evolution (LTE) systems), LTE frequency division duplex (FDD) systems, LTE time division duplex (TDD) systems, worldwide interoperability for microwave access (WiMAX) communication systems, and 5th generation (5G) mobile communication systems (such as New Radio (NR) systems). No restrictions are imposed on radio (NR) systems, future communication systems, or other similar communication systems.

[0091] Figure 1 illustrates a possible, non-limiting system diagram. As shown in Figure 1, the communication system 10 includes a radio access network (RAN) 100 and a core network (CN) 200. RAN 100 includes at least one RAN node (110a and 110b in Figure 1, collectively referred to as 110) and at least one terminal (120a-120j in Figure 1, collectively referred to as 120). RAN 100 may also include other RAN nodes, such as wireless relay devices and / or wireless backhaul devices (not shown in Figure 1). Terminal 120 is wirelessly connected to RAN node 110. RAN node 110 is wirelessly or wired connected to core network 200. The core network equipment in core network 200 and RAN node 110 in RAN 100 can be different physical devices, or they can be the same physical device integrating core network logical functions and radio access network logical functions.

[0092] RAN 100 can be a cellular system related to the 3rd Generation Partnership Project (3GPP), such as 4G, 5G mobile communication systems, or future-oriented evolution systems. RAN 100 can also be an open RAN (O-RAN or ORAN), cloud RAN (CRAN), virtualized RAN (vRAN), artificial intelligence radio access network (AI RAN), or wireless fidelity (WiFi) system. RAN 100 can also be a communication system that integrates two or more of the above systems.

[0093] RAN node 110, sometimes referred to as access network equipment, RAN entity, or access node, constitutes part of the communication system and assists terminals in achieving wireless access. Multiple RAN nodes 110 in communication system 10 can be of the same type or different types. In some scenarios, the roles of RAN node 110 and terminal 120 are relative. For example, network element 120i in Figure 1 can be a helicopter or drone, which can be configured as a mobile base station. For terminals 120j accessing RAN 100 through network element 120i, network element 120i is a base station; however, for base station 110a, network element 120i is a terminal. RAN node 110 and terminal 120 are sometimes both referred to as communication devices. For example, network elements 110a and 110b in Figure 1 can be understood as communication devices with base station functions, and network elements 120a-120j can be understood as communication devices with terminal functions.

[0094] In one possible scenario, a RAN node can be a base station, an evolved NodeB (eNodeB), an access point (AP), a transmission reception point (TRP), a next-generation NodeB (gNB), a base station in a future mobile communication system, or an access node in a WiFi system. A RAN node can be a macro base station (as shown in Figure 1, 110a), a micro base station or indoor station (as shown in Figure 1, 110b), a relay node or donor node, a radio controller in a CRAN scenario, or a device that performs base station functions in device-to-device (D2D) and / or machine-to-machine (M2M) transmissions. Optionally, a RAN node can also be a server, wearable device, vehicle, or in-vehicle equipment. For example, the access network equipment in vehicle-to-everything (V2X) technology can be a roadside unit (RSU). All or part of the functions of the RAN node in this application can also be implemented through software functions running on hardware, or through virtualization functions instantiated on a platform (e.g., a cloud platform). The RAN node may also include communication modules, circuits, or chips that perform corresponding communication functions. The RAN node may also be configured with program instructions for performing corresponding communication functions and corresponding program instructions. The RAN node in this application can also be a logical node, logical module, or software capable of implementing all or part of the access node functions, or a circuit or chip (such as a graphics processing unit (GPU), artificial intelligence (AI) processor, or application-specific integrated circuit (ASIC)) responsible for communication and / or computing functions in the access node.

[0095] In another possible scenario, multiple RAN nodes collaborate to assist terminals in achieving wireless access, with different RAN nodes implementing some of the base station's functions. For example, RAN nodes can be central units (CUs), distributed units (DUs), CU-control plane (CPs), CU-user plane (UPs), or radio units (RUs). CUs and DUs can be separate entities or included in the same network element, such as a baseband unit (BBU). RUs can be included in radio frequency equipment or radio frequency units, such as remote radio units (RRUs), active antenna units (AAUs), or remote radio heads (RRHs). Furthermore, RAN nodes can also be computing units, providing computational power for tasks such as model inference and / or model training, and can also be used to implement one or more of the following: task partitioning, scheduling, and orchestration. The functionality of a computing unit can be implemented by a separate module independent of other units (e.g., CU, DU, RU), or by one or more other units (e.g., one or more of CU, DU, RU).

[0096] In different systems, CU (or CU-CP and CU-UP), DU, computing unit, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an ORAN system, CU can also be called O-CU (open CU), DU can also be called O-DU, CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. For ease of description, this application uses CU, CU-CP, CU-UP, DU, computing unit, and RU as examples. Any of the units among CU (or CU-CP, CU-UP), DU, computing unit, and RU in this application can be implemented through software modules, hardware modules, or a combination of software modules and hardware modules.

[0097] A terminal can be a device or module that accesses the aforementioned communication system and has corresponding communication functions. A terminal can also be called a terminal device, user equipment (UE), mobile station, mobile terminal, etc. Terminals can be widely used in various scenarios, such as D2D, vehicle-to-everything (V2X) communication, machine-type communication (MTC), Internet of Things (IoT), virtual reality, augmented reality, industrial control, autonomous driving, telemedicine, smart grids, smart furniture, smart offices, smart wearables, smart transportation, smart cities, etc. Terminals can be mobile phones, tablets, computers with wireless transceiver capabilities, wearable devices, vehicles, drones, helicopters, airplanes, ships, robots, robotic arms, smart home devices, transportation vehicles with wireless communication capabilities, communication modules, etc. The embodiments of this application do not limit the device form of the terminal. Terminals typically contain communication modules, circuits, or chips that perform corresponding communication functions; furthermore, they can also contain modules, circuits, or chips (such as GPUs, AI processors, or ASICs) that perform corresponding communication and / or computing functions. The terminal can also be configured with program instructions for performing corresponding communication and / or computing functions.

[0098] It is understood that RAN nodes are used to help terminals achieve wireless access, and they can also be referred to in other different ways, such as RAN entity, ORAN device, access node, access network device, etc. In the following description of the embodiments of this application, unless otherwise specified, the node or device that helps the terminal achieve wireless access will be described as "access network device".

[0099] The core network 200 includes one or more network elements. For example, in the control plane, the core network 200 includes session management function (SMF) network elements and policy control function (PCF) network elements. In the user plane, the core network 200 includes user plane function (UPF) network elements. The SMF network element is primarily responsible for session management in the mobile network, such as session establishment, modification, or release. The PCF network element mainly supports providing a unified policy framework to control network behavior, providing policy rules to the control layer network functions, and is also responsible for obtaining user subscription information related to policy decisions. The UPF network element is mainly responsible for forwarding and receiving user data. For example, in downlink transmission, the UPF network element can receive user data from the data network (DN) and transmit it to the terminal through the access network equipment; in uplink transmission, the UPF network element can receive user data from the terminal through the access network equipment and forward the user data to the DN. In this application, the names of network elements such as SMF, PCF, and PCF are not limited. For example, as networks develop and evolve, the aforementioned network elements may be referred to by other names. In the description of this application, the names of the various network elements are mainly described using a 5G communication system as an example.

[0100] It is understood that terminals, access network equipment, and core network elements are sometimes referred to as communication devices. For example, a terminal can be understood as a communication device with terminal functions, an access network device can be understood as a communication device with access network equipment functions, and a core network element (such as an SMF or PCF element) can be understood as a communication device with core network functions. In the method of this application, the functions of the access network equipment can also be performed by modules, units, or components (such as chips) within the access network equipment, or by a control subsystem containing access network equipment functions. This control subsystem containing access network equipment functions can be a control center in the aforementioned application scenarios such as smart grids, industrial control, intelligent transportation, and smart cities. The functions of the terminal can also be performed by modules, units, or components (such as chips or modems) within the terminal, or by a device containing terminal functions. The functions of the core network element can also be performed by modules, units, or parts within the core network element.

[0101] To support artificial intelligence (AI) technology in wireless networks, AI nodes may be introduced into the network. AI nodes can be AI network elements or AI modules.

[0102] AI nodes can be deployed in one or more of the following locations within the communication system: access network nodes (RAN nodes), terminals, or core network equipment, etc. Alternatively, AI nodes can be deployed independently, for example, in a location other than any of the above-mentioned devices, such as in the host or cloud server of an over-the-top (OTT) system. AI nodes can communicate with other devices in the communication system, which can be one or more of the following: network equipment, terminals, or core network elements, etc.

[0103] It is understood that this application does not limit the number of AI nodes. For example, when there are multiple AI nodes, they can be divided based on function, such as different AI nodes being responsible for different functions.

[0104] It can also be understood that AI nodes can be independent devices, or they can be integrated into the same device to achieve different functions. Alternatively, they can be network elements in hardware devices, software functions running on dedicated hardware, or virtualization functions instantiated on a platform (e.g., a cloud platform). This application does not limit the specific form of the aforementioned AI nodes.

[0105] Figure 2 illustrates a possible application framework in a communication system. As shown in Figure 2, network elements in the communication system are connected via interfaces (e.g., NG, Xn) or air interfaces. These network element nodes, such as core network equipment, access network nodes (RAN nodes), terminals, or one or more devices in operations administration and maintenance (OAM), are equipped with one or more AI modules (only one is shown in Figure 2 for clarity). An access network node can be a single RAN node or can comprise multiple RAN nodes, for example, including CU and DU. The CU and / or DU can also be equipped with one or more AI modules. A CU can also be split into CU-CP and CU-UP, with one or more AI modules configured in the CU-CP and / or CU-UP.

[0106] AI modules are used to implement corresponding AI functions. AI modules deployed in different network elements can be the same or different. The models of AI modules can achieve different functions depending on the parameter configurations. The models of AI modules can be configured based on one or more of the following parameters: structural parameters (e.g., at least one of the following: number of neural network layers, neural network width, inter-layer connections, neuron weights, neuron activation function, or biases in the activation function), input parameters (e.g., the type and / or dimension of the input parameters), or output parameters (e.g., the type and / or dimension of the output parameters). The biases in the activation function can also be referred to as the biases of the neural network.

[0107] In one example, the neural network mentioned above can be a deep neural network (DNN), a convolutional neural network (CNN), a recurrent neural network (RNN), or a generative adversarial network (GAN).

[0108] Deep Neural Networks (DNNs) are artificial neural network architectures with multiple layers of nonlinear transformation units stacked in a hierarchical structure to form deep computational models. Compared to shallow neural networks, deep neural networks have more hidden layers, allowing the network model to capture more complex data structures and higher-level abstract features.

[0109] A CNN is a deep neural network with a convolutional structure. A CNN contains a feature extractor consisting of convolutional layers and subsampling layers. This feature extractor can be viewed as a filter, and the convolution process can be seen as performing convolution between a trainable filter and an input image or a convolutional feature map.

[0110] RNN is a type of recursive neural network that takes sequence data as input, recursively moves along the direction of sequence evolution, and connects all nodes (recurrent units) in a chain-like manner.

[0111] GAN is a deep learning model. It consists of a generator and a discriminator, and is trained through adversarial learning. Its purpose is to estimate the potential distribution of data samples and generate new data samples.

[0112] An AI module can have one or more models. A model can infer an output, which includes one or more parameters. The learning, training, or inference processes of different models can be deployed on different nodes or devices, or they can be deployed on the same node or device.

[0113] Figure 3 illustrates a possible application framework in a communication system. As shown in Figure 3, the communication system includes a RAN intelligent controller (RIC). For example, the RIC is used to implement AI-related functions. RICs include near-real-time RICs (near-RT RICs) and non-real-time RICs (non-RT RICs). Non-real-time RICs primarily process non-real-time information, such as data that is not sensitive to latency, with latency in the order of seconds. Real-time RICs primarily process near-real-time information, such as data that is relatively sensitive to latency, with latency in the order of tens of milliseconds.

[0114] Near real-time (NRT) RICs are used for model training and inference. For example, they are used to train AI models and then use those models for inference. NRT RICs can obtain network-side and / or terminal-side information from RAN nodes (e.g., CUs, CU-CPs, CU-UPs, DUs, compute nodes, and / or RUs) and / or terminals. This information can be used as training data or inference data. NRT RICs can deliver inference results to RAN nodes and / or terminals. Inference results can be exchanged between CUs and DUs, and / or between DUs and RUs. For example, a NRT RIC delivers an inference result to a DU, which then forwards it to an RU.

[0115] Non-real-time RICs are also used for model training and inference. For example, they are used to train AI models and then use those models for inference. Non-real-time RICs can obtain network-side and / or terminal-side information from RAN nodes (e.g., CUs, CU-CPs, CU-UPs, DUs, compute nodes, and / or RUs) and / or terminals. This information can be used as training data or inference data, and the inference results can be delivered to RAN nodes and / or terminals. Inference results can be exchanged between CUs and DUs, and / or between DUs and RUs; for example, a non-real-time RIC delivers inference results to a DU, which then forwards them to an RU.

[0116] Near real-time RICs and non-real-time RICs can also be configured as separate network elements. Near real-time RICs and non-real-time RICs can also be part of other devices. For example, near real-time RICs can be set in RAN nodes (e.g., CU, DU, compute nodes), while non-real-time RICs can be set in OAM, cloud servers, core network devices, or other network devices.

[0117] For ease of description, some communication terms or terminology used in this application are explained. It is understood that these explanations are for understanding the method of this application and are not intended to limit this application.

[0118] 1. Quality of experience (QoE)

[0119] QoE can be considered a user's subjective feeling or satisfaction evaluation of the service and / or application experience. Unlike Quality of Service (QoS), which measures network performance from a technical perspective (such as bandwidth, latency, packet loss rate), QoE focuses more on the user's actual experience and feelings. In one understanding, the relationship between QoE and QoS is as follows: QoS is a technical performance indicator and the foundation affecting QoE; while QoE is a user-facing experience indicator and the target of QoS.

[0120] QoE has important applications in many fields, especially in services requiring a high-quality user experience: such as video streaming, where QoE is used to evaluate video clarity, buffering time, and stuttering frequency; online gaming, where QoE is used to evaluate latency, frame rate, and interaction response speed; voice and video calls, where QoE is used to evaluate voice clarity, video smoothness, and latency; and web browsing, where QoE evaluates page load speed and response time.

[0121] In the International Telecommunication Union (ITU) standards, QoE is defined as: a user's subjective perception of the quality and performance of equipment, networks and systems, applications, or services. The 3rd Generation Partnership Project (3GPP) standardized QoE-related protocols (such as: QoE measurement for different services, QoE activation and deactivation procedures, and RAN-side visible QoE measurement interaction protocols, etc.).

[0122] In this application, a first QoE is referenced for evaluating or measuring the performance of a service corresponding to first data. For example, the service corresponding to the first data can be measured based on the first QoE to obtain a first measurement result. This first measurement result can be specifically used to evaluate or measure the performance of the service corresponding to the first data. For instance, if the first QoE is inference accuracy: then by measuring the service corresponding to the first data based on the inference accuracy, a measurement result corresponding to the inference accuracy (i.e., the first measurement result) can be obtained. For example, the measured inference accuracy result could be that the inference accuracy of the service corresponding to the first data (such as the current inference service) ranges from 95% to 98%, etc.

[0123] 2. Quality of Service (QOS) Flow

[0124] A Quality of Service (QoS) flow is used to provide a corresponding Quality of Service (QoS) for a given business flow. A QoS flow can be identified by a QoS flow identifier (QFI). Each QoS flow has corresponding QoS parameters, for example:

[0125] 5G QoS identifier (5QI): used for predefined QoS feature templates; Allocation and retention priority (ARP): used for resource allocation and retention priority; Guaranteed bit rate (GBR): applicable to services requiring fixed bandwidth; Maximum flow bit rate (MFBR); Averaging window: the time window used to calculate GBR and MFBR.

[0126] Establishment of Quality of Service (QoS) flow: This is achieved by SMF network elements based on policies and / or service requirements, such as when a Protocol Data Unit (PDU) session is established or modified. In one interpretation, a PDU session can be considered to contain one or more QoS flows.

[0127] QoS flow modification: SMF network elements can dynamically adjust the QoS parameters of the QoS flow based on network conditions and / or service requirements.

[0128] Deletion of QoS flow: When a PDU session terminates and / or the service is no longer needed, the SMF network element can delete the corresponding QoS flow.

[0129] 3. AI Model

[0130] AI models are used to implement AI functions. An AI model represents the mapping relationship between the model's input and output. AI models can be neural networks, linear regression models, decision tree models, clustering SVD models, or other machine learning models. The term AI model can be abbreviated as intelligent model, model, or other names without restriction. AI-related operations can include at least one of the following: data collection, model training, model information publication, model testing (or model validation), model inference (or model reasoning, inference, or prediction, etc.), or publication of inference results, etc.

[0131] Figure 4 illustrates an example of the first application framework of AI in a communication system. In Figure 4, the data source stores training and inference data. The model training host analyzes or trains the AI ​​model using the training data provided by the data source and deploys the AI ​​model in the model inference host. The AI ​​model represents the mapping relationship between the model's input and output. Learning the AI ​​model through the model training host is equivalent to the model training host learning the mapping relationship between the model's input and output using the training data. The model inference host uses the AI ​​model to perform inference based on the inference data provided by the data source, obtaining the inference result. This method can also be described as follows: the model inference host inputs inference data into the AI ​​model, obtains the output through the AI ​​model, and this output is the inference result. This inference result can indicate the configuration parameters used (executed) by the execution object, and / or the operations performed by the execution object. The inference result can be uniformly planned by the actor entity and sent to one or more execution objects (e.g., network elements) for execution. Optionally, the model inference node can feed its inference results back to the model training node. This process can be called model feedback. The fed-back parameters are used by the model training node to update the AI ​​model, and the updated AI model is deployed in the model inference node. Optionally, the execution object can feed back the network parameters it collects to the data source. This process can be called performance feedback. The fed-back parameters can be used as training data or inference data.

[0132] In this application, the example application framework shown in Figure 4 can be deployed on the network elements shown in Figure 1. For example, the application framework in Figure 4 can be deployed on at least one of the terminals, access network devices, core network devices, or independently deployed AI network elements (not shown) in Figure 1. For example, the AI ​​network element (which can be considered a model training node) can analyze or train the training data provided by the terminal and / or access network device to obtain a model. At least one of the terminals, access network devices, or core network devices (which can be considered a model inference node) can use the model and inference data to perform inference and obtain the model's output. The inference data can be provided by the terminal and / or access network device. The input of the model includes the inference data, and the output of the model is the inference result corresponding to the model. At least one of the terminals, access network devices, or core network devices (which can be considered an execution object) can perform corresponding operations based on the inference data and / or inference result. The model inference node and the execution object can be the same or different, without limitation.

[0133] 4. Mapping of Quality of Service Flow

[0134] During uplink transmission, the SMF network element can configure a Quality of Service (QoS) flow rule for the terminal. This QoS flow rule includes at least one mapping relationship, which can be specifically described in [Example 1], such as the mapping relationship between the first measurement result and the QoS flow. Alternatively, this mapping relationship can be specifically described in [Example 2], such as the mapping relationship between the first parameter and the QoS flow. The terminal can map uplink data (such as the first data) to the corresponding QoS flow for transmission according to the above mapping relationship. In one interpretation, the QoS flow rule includes a packet filter, and the packet filter includes the above mapping relationship.

[0135] During downlink transmission, the SMF network element can configure a packet detection rule (PDR) for the UPF network element, such as the first PDR. The first PDR contains at least one mapping relationship, which can be referred to in the description of [Example 1] or [Example 2]. The UPF network element can map downlink data (such as the first data) to the corresponding Quality of Service (QoS) stream for transmission according to the above mapping relationship. In one interpretation, the first PDR includes a packet filter, and the packet filter contains the above mapping relationship.

[0136] 5. The relationship between the first PDR, the first FAR, and the first QER.

[0137] Among them, PDR, FAR, and QER are all rules applied to the UPF side. In the description of this application, PDR, FAR, and QER are referred to as the first PDR, the first FAR, and the first QER, respectively. FRA stands for forwarding action rule. QER stands for QoS enforcement rule.

[0138] The first PDR is used to map data to the corresponding Quality of Service (QoS) flow transmission. For example, the first PDR contains at least one mapping relationship. As in [Example 1], the mapping relationship includes a mapping between a first measurement result and a QoS flow. Alternatively, as in [Example 2], the mapping relationship includes a mapping between at least one item of the IP 5-tuple and the QoS flow.

[0139] The first PDR and the first FAR are associated (or bound) to each other. The first FAR defines the forwarding behavior of data packets, such as forwarding, dropping, or buffering. Forwarding can specifically refer to transferring data to a specified interface, such as forwarding to the corresponding DN via the N6 interface, or forwarding to other UPF network elements via the N9 interface.

[0140] There is a relationship between the first PDR and the first QER. For example, the first QER is used to specify the QoS parameters of the service quality traffic, such as bandwidth, priority, or latency, for the mapping relationship included in the first PDR. If the first PDR contains a first mapping relationship, and the first data can be mapped to a first service quality flow using the first mapping relationship, then the first QER can specify the QoS parameters of the first service quality flow.

[0141] During the establishment or modification of a PDU session, the SMF network element configures QoS rules for the terminal via non-access stratum (NAS) messages. These QoS rules may include packet filters that map packets to corresponding Quality of Service (QoS) flows. They may also include mappings between address information (such as IP addresses) and QoS flows. When mapping QoS flows, the terminal obtains the first data to be sent, extracts the source and / or destination addresses from it, and determines the QoS flow corresponding to the first data based on the mapping between address information and QoS flows contained in the QoS rules. The terminal then maps the first data to the corresponding QoS flow for transmission. This process of mapping QoS flows based on address information can also be understood as mapping QoS flows based on the type of service. For example, mapping all data of a certain type of service to the same QoS flow.

[0142] However, research on AI-related services reveals that even within the same AI-related service, the requirements for Quality of Service (QoS) flow differ. Take training services as an example: the terminal trains a model and sends the corresponding training data to the access network equipment. In the early stages of training, the model's accuracy is not high, therefore the requirements for QoS flow are not high. For instance, in the early stages of training, due to the low accuracy of the trained model, the accuracy requirements for data transmission are not high, and a relatively high packet loss rate can be tolerated. As model training progresses, the model's accuracy increases, and the model tends to converge, leading to increasingly higher requirements for QoS flow, such as the accuracy requirements for data transmission.

[0143] It can be seen that the demand for service quality flow varies at different stages for AI-related businesses. Furthermore, research reveals that QoE (such as the first QoE) can be used to measure the service quality flow demand of AI-related businesses.

[0144] For example, if the first QoE is the model training accuracy, then by measuring the model accuracy of the aforementioned training process, the corresponding measurement result can be determined. For instance, in the first half of the training phase, based on the "model training accuracy," the training process is measured, resulting in measurement result 1, with a value range of 80% to 90%. That is, in the first half of the training phase, the model accuracy corresponding to the training process is 80% to 90%. In the second half of the training phase, based on the "model training accuracy," the training process is measured, resulting in measurement result 2, with a value range of 95% to 98%. That is, in the second half of the training phase, the model accuracy corresponding to the training process is 95% to 98%.

[0145] In view of the above, this application provides a communication method and apparatus, in which a mapping relationship between different measurement results of a first QoE and a quality of service flow can be established. For example, currently, based on the first QoE, the service corresponding to the first data is measured to determine the first measurement result. Then, based on the above-mentioned "mapping relationship between different measurement results of the first QoE and the quality of service flow", the quality of service flow corresponding to the first measurement result (such as the first quality of service flow) is queried. The first data is mapped to the first quality of service flow for transmission. In the example above, the corresponding measurement results are different at different training stages, therefore, the quality of service flows with mapping relationships are different. For example, in the first half of the above model training, measurement result 1 corresponds to quality of service flow 1, and the quality of service flow parameters corresponding to quality of service flow 1 are that the transmission speed is relatively fast, but the transmission accuracy is relatively low (such as a high packet loss rate). In the second half of the model training, measurement result 2 corresponds to quality of service flow 2, and the quality of service parameters corresponding to quality of service flow 2 are that the transmission speed is relatively slow, but the transmission accuracy is relatively high (such as a low packet loss rate). The method described in this application can meet the service quality requirements of the same service at different stages and improve the performance of service transmission.

[0146] The communication method and apparatus of this application will be further described below with reference to the accompanying drawings. It is understood that this application primarily uses access network equipment and terminals as examples of the execution entities in the interactive illustration, but this application does not limit the execution entities in the interactive illustration. For example, the method executed by the access network equipment in this application can also be implemented by modules (e.g., circuits, chips, or chip systems) in the access network equipment, or by logical nodes, logical modules, or software that can implement all or part of the functions of the access network equipment, or by circuits or chips (e.g., GPUs, AI processors, or ASICs) in the access network equipment responsible for communication and / or computing functions. Similarly, the method executed by the terminal in this application can also be implemented by communication and / or computing modules in the terminal, or by circuits or chips (e.g., modem chips (also known as baseband chips), or SoC chips / SIP chips containing modem cores, or GPUs / AI processors / ASICs) in the terminal responsible for communication and / or computing functions, or by logical nodes, logical modules, or software that can implement all or part of the terminal functions. Similarly, the methods shown in Figures 7, 9, 10, or 12 of this application may also involve UPF network elements, SMF network elements, PCF network elements, or AI entities. The methods in the above-described schematic diagrams can be executed by the aforementioned network elements or entities, or they can be implemented by modules, logical nodes, logical modules, or software within the corresponding network elements or entities.

[0147] Example 1

[0148] Figure 5 provides a flowchart of a communication method, which includes:

[0149] Step 510: The terminal acquires the first measurement result of the first QoE.

[0150] In this application, "first QoE" can refer to a single type of QoE, and "first measurement result" refers to the measurement result corresponding to that type of QoE. Alternatively, "first QoE" can refer to multiple types of QoE, and "first measurement result" can contain multiple measurement results, each corresponding one-to-one with a different type of QoE; that is, one type of QoE corresponds to one measurement result. For example, "first QoE" may include at least one of the following: inference accuracy, inference latency, inference throughput, training latency, training power consumption, or training convergence speed. Training convergence speed can also be referred to as model convergence speed. It is understood that the type included in "first QoE" is not limited in this application; the above is merely an example. For instance, the above-mentioned "first QoE" may also include: the accuracy of the trained model, etc. Furthermore, with the evolution and / or development of technology, other types of QoE measurements can be performed on the services corresponding to the first data, and corresponding measurement results can be obtained. Then, using the method of this application, the first data is mapped to the service quality stream corresponding to the above measurement results for transmission, which is also within the scope of protection of this application.

[0151] The process by which the terminal obtains the first measurement result is not limited. For example, if the first measurement result is encapsulated in the first data to be sent, the terminal can obtain the first measurement result from the first data. Alternatively, the first measurement result can be encapsulated in the header of the first data, allowing the terminal to obtain the first measurement result from the header. Furthermore, the terminal can perform a measurement of the first QoE to determine the first measurement result. Or, the terminal can measure the task corresponding to the first data based on the first QoE to obtain the first measurement result. In the description of this application, "measurement" can also be replaced with terms such as "detection" or "metric," without limitation. Correspondingly, the measurement result (such as the first measurement result) can also be replaced with terms such as "first detection result" or "first metric result."

[0152] For example, if the task corresponding to the first data is an inference task, measuring the inference task yields a first measurement result, which may include at least one of the following: a measurement result corresponding to inference accuracy, a measurement result corresponding to inference latency, a measurement result corresponding to inference throughput, etc. Similarly, if the task corresponding to the first data is a training task, measuring the training task yields a first measurement result, which may include at least one of the following: a measurement result corresponding to training latency, a measurement result corresponding to training power consumption, or a measurement result corresponding to training convergence speed, etc. Furthermore, the network side can measure the service corresponding to the first data based on the first QoE to obtain the first measurement result. The network side then indicates the first measurement result to the terminal. For example, the network side sends first indication information to the terminal, which indicates the first measurement result. The terminal determines the first measurement result based on the indication of the first indication information. There are no restrictions on the device or entity performing the first QoE measurement on the network side. For example, the device or entity performing the first QoE measurement on the network side can be an access network device, a core network element, an OAM network element, or a new entity can be added on the network side to perform the first QoE measurement. When a network-side device or entity uses AI (AI-based) methods to perform the first QoE measurement, that device or entity can be referred to as an AI entity. It is understood that the functionality of an AI entity can be implemented by hardware, software, or a combination of both. The functionality of an AI entity can be implemented by a single network element or by multiple network elements; these network elements can be hardware-implemented, software-implemented, or a combination of both, without limitation.

[0153] Step 520: The terminal maps the first data to the first quality of service stream based on the first measurement result, and there is a mapping relationship between the first measurement result and the first quality of service stream.

[0154] It is understood that the first data can be data to be sent by the terminal, specifically uplink data. For example, the terminal can obtain the mapping relationship between measurement results and service quality flows. The terminal can query the service quality flow corresponding to the first measurement result (e.g., referred to as the first service quality flow) from the above mapping relationship. The terminal can map the first data to the first service quality flow and send the first data through the first service quality flow. It is understood that the mapping relationship between measurement results and service quality flows obtained by the terminal includes at least the mapping relationship between the first measurement result and the first service quality flow. Optionally, the mapping relationship between measurement results and service quality flows obtained by the terminal may also include other mapping relationships, such as the mapping relationship between the second measurement result and the second service quality flow; or, for example, the mapping relationship between the third measurement result and the third service quality flow, etc.

[0155] Optionally, the mapping relationship between the above measurement results and the Quality of Service (QoS) flow (or the mapping relationship between the first measurement result and the first QoS flow) can be predefined or configured by the network device for the terminal. For example, the SMF network element can configure the mapping relationship between the above measurement results and the QoS flow (or the mapping relationship between the first measurement result and the first QoS flow) for the terminal. For example, the SMF network element sends first configuration information, and correspondingly, the terminal receives the first configuration information, which is used to configure the mapping relationship between the measurement results and the QoS flow (or the mapping relationship between the first measurement result and the first QoS flow). In one possible implementation, the SMF network element sends a NAS message, which contains the above first configuration information. Furthermore, during the establishment or modification of a PDU session, the SMF network element can configure QoS rules for the terminal via a NAS message, and the QoS rules contain the mapping relationship between the above measurement results and the QoS flow (or the mapping relationship between the first measurement result and the first QoS flow). It is understood that the mapping relationship between the above measurement results and the QoS flow (or the mapping relationship between the first measurement result and the first QoS flow) can be included in the QoS rules. The function of the first configuration information mentioned above can also be replaced by: the first configuration information is used to configure QoS rules, and the QoS rules contain the mapping relationship between measurement results and service quality flow (or the mapping relationship between the first measurement result and the first service quality flow).

[0156] It is understandable that the first measurement result may contain one measurement result or multiple measurement results. When the first measurement result contains one measurement result, as mentioned above, the terminal queries the service quality corresponding to that measurement result (i.e., the first service quality flow) in the mapping relationship between measurement results and service quality flows. Alternatively, when the first measurement result contains multiple measurement results, there is no restriction on the process by which the terminal determines the first service quality flow. For example, multiple measurement results may be processed, including averaging or assigning different weight coefficients to different measurement results, to determine a final measurement result; the service quality flow corresponding to the final measurement result (i.e., the first service quality flow) is then queried in the mapping relationship between measurement results and service quality flows. Furthermore, the mapping relationship between measurement results and service quality flows can be one-to-one, meaning one measurement result corresponds to one service quality flow. When the first measurement result contains multiple measurement results, the terminal queries the service quality flows corresponding to each of the multiple measurement results in the mapping relationship between measurement results and service quality flows. Thus, multiple service quality flows can be retrieved from the multiple measurement results. Finally, among the multiple Quality of Service (QoS) flows, one QoS flow (i.e., the first QoS flow) is selected for mapping the first data. There are no restrictions on the method used to select the first QoS flow from among the multiple QoS flows.

[0157] Optionally, the above "mapping relationship between measurement results and quality of service flows is one-to-one", that is, one measurement result corresponds to one quality of service flow.

[0158] Alternatively, the mapping between measurement results and quality of service (QoS) flows can be many-to-one, meaning multiple measurement results correspond to one QoS flow. For example, when the first measurement result contains multiple measurement results, the mapping between these results and QoS flows can be many-to-one. The terminal can query the QoS flows corresponding to the multiple measurement results contained in the first measurement result within the mapping relationship; the queried QoS flow is the first QoS flow.

[0159] For example, the first QoE includes inference accuracy and inference latency, and the first measurement result includes range 1 and range 2. For example, the measurement result corresponding to inference accuracy is range 1, such as range 1 being 95% to 98%. The measurement result corresponding to inference latency is range 2, such as range 2 being 0 to 0.1. Specifically, the "mapping relationship between the first measurement result and the first quality of service flow" can be: the mapping relationship between (range 1 of inference accuracy and range 2 of inference latency) and quality of service flow X. Based on the above mapping relationship, the terminal can determine that the current first measurement result (range 1 and range 2) corresponds to quality of service flow X. The terminal sends the first data through quality of service flow X. It can be understood that, at this time, quality of service flow X is an example implementation of the first quality of service flow.

[0160] Step 530: The terminal sends the first data through the first Quality of Service (QoS) flow. Correspondingly, the access network device receives the first data through the first QoS flow.

[0161] If the receiving end of the first data is an access network device, then the access network device can process the received first data. If the receiving end of the first data is another network element or device, then the access network device can forward the first data to the corresponding network element or device. For example, the access network device can forward the first data to a UPF network element through a first quality of service flow. Further, optionally, the UPF network element can send the first data to the corresponding DN, or other UPF network elements, etc.

[0162] This application does not limit the business type of the first data and / or the type of the first QoE. For example, the business type of the first data can be AI-related business, such as inference business, training business, data acquisition business (such as acquiring training data for AI model training, and / or acquiring inference data for AI model inference, etc.).

[0163] For example, the data to be sent on the terminal side is called the first data, and there are no restrictions on the service type of the first data. For example, the service type of the first data can be AI-related, such as training, inference, or data acquisition.

[0164] Taking training as an example, the terminal and the network can perform bilateral / multi-sided model training, such as at least joint model training by the terminal and the network. For instance, the terminal trains the AI ​​model and obtains the training results. The terminal sends the data related to the training results to the network. Based on the terminal's training results, the network continues to train the model to obtain the final AI model that meets the requirements. The "data related to the training results" sent by the terminal to the network can be considered an example implementation of the first type of data.

[0165] Taking inference services as an example, this could involve bilateral / multi-sided model inference between the terminal and the network, or at least joint model inference between the terminal and the network. For instance, the terminal deploys AI model 1, which performs model inference to obtain inference data 1. The terminal then sends inference data 1 to the network. The network deploys AI model 2, which, based on the inference data 1 sent by the terminal, continues model inference using AI model 2 to obtain the final inference result. Alternatively, the network can use the inference data 1 sent by the terminal as input to AI model 2, and consider the output of AI model 2 as the final inference result. The aforementioned inference data 1 sent by the terminal to the network can be considered another example of the first data implementation.

[0166] For example, the terminal performs model training, while the network performs model inference. The terminal trains the model to obtain the corresponding AI model and sends the AI ​​model to the network, which can then use the AI ​​model indicated by the terminal for model inference. The AI ​​model instruction information sent by the terminal to the network can be considered another example of the implementation of the first data. Optionally, the service type corresponding to the first data in this case can be considered as a training service.

[0167] Taking data acquisition as an example, a terminal collects data and sends it to the network side. The network side then uses the data sent by the terminal for model training or inference. The data sent by the terminal to the network side can be considered another example of the first type of data acquisition.

[0168] As explained earlier, the first QoE measurement can be performed on the terminal side or the network side to obtain the first measurement result. There are no restrictions on the specific measurement methods used on the terminal side or the network side. The following examples illustrate the measurement methods on the terminal side or the network side, based on the service type corresponding to the first data.

[0169] For example, before sending the first data, the terminal can use a test set (which contains at least one test data item) to measure the first QoE and obtain the first measurement result. Of course, the test set mentioned above should be consistent with the service type corresponding to the first data.

[0170] For example, the business type corresponding to the first data is model inference, and the first QoE includes at least one of the following: inference accuracy, inference latency, inference throughput, etc.

[0171] The process of determining the measurement result corresponding to the inference accuracy using a test set involves the test set containing test data and corresponding data. For example, an AI model is deployed on the terminal side. The test data is input into the AI ​​model, and the output of this AI model can be considered as the data obtained through inference by the AI ​​model, referred to as inference data. The terminal side can compare the inference data obtained through the AI ​​model with the corresponding data of the test data to obtain the inference accuracy. Of course, the above describes the process by which the terminal side uses the test set to obtain the measurement result corresponding to the inference accuracy. The execution process on the network side is similar to that on the terminal side, and will not be described further on the network side.

[0172] The process of determining the measurement result corresponding to inference latency using a test set involves: deploying an AI model on the terminal or network side; inputting the test data contained in the test set into the AI ​​model; and considering the output of the AI ​​model as the inference data, referred to as inference data. The time interval from inputting the test data to obtaining the inference data is then calculated; this time interval can be called inference latency.

[0173] The process of determining the measurement results corresponding to inference throughput using a test set involves several definitions. Inference throughput can be defined in different ways, such as the number of inferences per unit time or the amount of data that can be processed in one inference. If an AI model is deployed on the terminal or network side, test data is input into the AI ​​model for measurement to obtain the inference throughput.

[0174] For example, the business type corresponding to the first data is model training, and the first QoE includes at least one of the following: training latency, training power consumption, training convergence speed, etc.

[0175] By using a test set, the measurement result corresponding to training latency can be determined: for example, on the terminal side used to train an AI model. The test set can be used to test the time taken for the terminal to train an AI model, and this time can be considered as the measurement result corresponding to training latency.

[0176] By using a test set, the measurement results corresponding to training power consumption can be determined: if the terminal is used to train an AI model, the test set can be used to test the energy consumed by the terminal to train an AI model, and this energy can be considered as the measurement result corresponding to training power consumption.

[0177] Using a test set, the measurement results corresponding to the training convergence speed can be determined. During the training of an AI model, a loss function is defined. The loss function describes the difference between the output value of the AI ​​model and the ideal target value; this application does not limit the specific form of the loss function. The training process of an AI model is the process of adjusting some or all of the parameters of the AI ​​model so that the value of the loss function is less than a threshold or meets the target requirement. If the AI ​​model is a neural network, one or more of the following parameters can be adjusted during training: the number of layers in the neural network, the width of the neural network, the connection relationship between layers, the weight value of the neuron, the activation function of the neuron, or the bias in the activation function, so that the difference between the output of the neural network and the ideal target value is minimized. When the loss function corresponding to the AI ​​model is less than the threshold or meets the target requirement, the training of the AI ​​model is considered complete, and the AI ​​model is considered converged. The model convergence function refers to the speed at which the loss function of the AI ​​model gradually decreases and tends to stabilize during training. Using a test set, the training convergence speed of the terminal during the training of the AI ​​model can be tested.

[0178] Alternatively, other methods can be used to determine the measurement result corresponding to the first QoE. For example, an AI model can be deployed on the terminal or network side to determine the first measurement result. If the input to the AI ​​model is the first data and the first QoE, the output of the AI ​​model is the first measurement result. Alternatively, the first measurement result can be determined based on the output of the AI ​​model. For instance, if the first QoE is inference precision, then the first data and the type of inference precision are input into the AI ​​model, and the output of the AI ​​model is the measurement result corresponding to the inference precision.

[0179] Optionally, the first measurement result is indicated by at least the type information of the first QoE and the measurement result information of the first QoE. Alternatively, the type information of the first QoE and the measurement result information of the first QoE can be used to indicate the first measurement result. As mentioned above, the first QoE includes at least one of the following: inference accuracy, inference latency, inference throughput, training latency, training power consumption, or training convergence speed. Different identifiers can be set for the above eight types of QoE; for example, 8 bits can be used to identify any one of the above types of QoE. Specific examples:

[0180] The identifier corresponding to inference precision is: 00000001; the identifier corresponding to inference latency is: 00000010;

[0181] The identifier for inference throughput is 00000011; the identifier for training latency is 00000100.

[0182] The identifier corresponding to training power consumption is: 00000101; the identifier corresponding to training convergence speed is: 00000110.

[0183] At this point, the "type information of the first QoE" can specifically refer to the type identifier corresponding to the first QoE. For example, when the first QoE is the inference precision, the type information of the first QoE can be specifically: 00000001.

[0184] It is understandable that the measurement result information of the first QoE (such as the first measurement result information) can be a specific value or a range of values, without restriction. For example, if the first QoE is the inference precision, the measurement result corresponding to the first QoE can be a specific value (such as 98%) or a range / interval of values ​​(such as 95% to 98%). Of course, the specific measurement result can be indicated using corresponding binary bits. Alternatively, to reduce indication overhead, a mapping relationship can be established between the measurement result corresponding to the first QoE and the identifier. For example, the above (95% to 98%) corresponds to identifier 1. In this case, the above "measurement result information of the first QoE" can specifically refer to: the identifier that has a mapping relationship with the measurement result information of the first QoE.

[0185] Furthermore, optionally, the first measurement result is also indicated by the business information of the first data. The business of the first data may refer to the business corresponding to the first data. "Business" can also be described as "service," such as the business corresponding to the first data being replaced with: the service corresponding to the first data. It is understood that different types of businesses may have different corresponding business identifiers; for example, the business identifier corresponding to inference business may be 00, the business identifier corresponding to training business may be 01, the business identifier corresponding to data acquisition business may be 10, and so on. The aforementioned "business information of the first data" may specifically refer to: the business identifier of the first data, or be described as: the business identifier of the business corresponding to the first data.

[0186] In one possible implementation, the type information of the first QoE, the measurement result information of the first QoE, and the service information of the first data are used to represent the first measurement result. Specifically, the "mapping relationship between the first measurement result and the first quality of service flow" is the mapping relationship between (the type information of the first QoE + the measurement result information of the first QoE + the service information of the first data) and the first quality of service flow. There is no limitation on the number of parameters representing the "first measurement result." For example, in addition to the above three parameters, other parameters can be added / introduced to represent the first measurement result.

[0187] In a specific example, during the establishment or modification of a PDU session, the SMF network element can configure a Quality of Service (QoS) flow rule to the terminal via NAS messages. This QoS flow rule includes at least a mapping relationship between a first measurement result and a first QoS flow. This can also be understood as modifying the mapping relationship contained in the QoS flow rule during the establishment or modification of the PDU session. For example, in one method, the QoS flow rule includes a mapping relationship between at least one item in the IP 5-tuple and the QoS flow. In this application, QoE is introduced, modifying the mapping relationship in the QoS flow rule to a mapping relationship between the first measurement result corresponding to the first QoE and the first QoS flow. Since the QoS flows with different mapping relationships differ depending on the value (or range) of the first measurement result, the requirements for QoS flows are met. Subsequently, when the terminal obtains the first data to be transmitted, it uses the method shown in Figure 5 to obtain the first measurement result. This first measurement result is related to the first data, such as being obtained by measuring the service corresponding to the first data. Based on the mapping relationship between the first measurement result and the first quality of service flow configured above, the first quality of service flow corresponding to the first measurement result is determined; the first data is mapped to the first quality of service flow for transmission, that is, the first data is sent through the first quality of service flow.

[0188] In one interpretation, before step 510 of the method shown in Figure 5, the method further includes: the SMF network element sending first configuration information to the terminal. Accordingly, the terminal receives the first configuration information from the SMF network element. This first configuration information is used to configure the "mapping relationship between the first measurement result and the first quality of service flow," or, as described, the first configuration information is used to configure the "mapping relationship between the measurement result and the quality of service flow." The mapping relationship between the measurement result and the quality of service flow configured by the first configuration information at least includes the mapping relationship between the first measurement result and the first quality of service flow. For example, the SMF network element may send the first configuration information to the terminal during the creation or modification of a PDU session. When this first configuration information is carried in a NAS message, the access network device may transparently transmit the NAS message to the terminal. Accordingly, the terminal receives the NAS message transparently transmitted by the access network device, obtains the first configuration information from the NAS message, and further obtains the mapping relationship between the first measurement result and the first quality of service flow.

[0189] As shown in Figure 6, in one possible implementation, the Quality of Service (QoS) flow rule includes N packet filters. Each packet filter corresponds to the following: packet filter direction, packet filter identifier, length of packet filter contents, and packet filter contents. Referring to Figure 6, taking packet filter content 1 as an example, packet filter content 1 includes: a service identifier and a QoE description. This QoE description includes: a QoE filter identifier. For example, when the type of the first QoE is inference precision, its corresponding QoE filter identifier is 00000001. Similarly, when the type of the first QoE is inference latency, its corresponding QoE filter identifier is 00000010, etc. It can be understood that the above QoE filter identifier is an example implementation of the identifier of the first QoE, the type identifier of the first QoE, or the index of the first QoE in this application. Furthermore, the packet filter contents also include: the corresponding measurement results (not shown in Figure 6).

[0190] Furthermore, the packet filter also includes: the identifier of the Quality of Service (QoS) flow corresponding to / mapped with the packet filter content (not shown in Figure 6). In the example of Figure 6, it can be assumed that there is a mapping relationship between the packet filter content and the QoS flow, or described as: there is a mapping relationship between the (service identifier + QoE description) contained in the packet filter content and the QoS flow, or described as: there is a mapping relationship between the (service identifier + QoE filter identifier + measurement result) contained in the packet filter content and the QoS flow. In this case, it can be assumed that the above three components, "service identifier + QoE filter identifier + measurement result," are used to uniquely indicate a measurement result (i.e., the first measurement result). The English name of the service identifier can be (service ID).

[0191] Optionally, as shown in Figure 6, the Quality of Service (QoS) flow rule contains N packet filters, each packet filter occupying multiple bytes. For example, packet filter 1 occupies bytes 8 to m. Specifically, packet filter identifier 1 and packet filter indication 1 occupy bytes 8. Optionally, 2 bits are reserved in bytes 8, such as bits 7 and 8 in bytes 8. Packet filter length 1 occupies bytes 9, and packet filter content 1 occupies bytes 10 to m. Similarly, packet filter 2 occupies bytes (m+1) to n. The content of packet filter N occupies bytes (y+1) to Z, etc. A byte can be represented as an Octet. It can be understood that 1 Octet = 8 bits. An Octet can be understood as a data unit composed of 8 binary bits, which can represent 256 (2^8) different values, ranging from 0 to 255.

[0192] Figure 7 provides a flowchart of a communication method. The difference between this method and the one shown in Figure 5 is that in the method of Figure 5, the terminal maps the first data to the first Quality of Service (QoS) stream, and the first data is uplink data. In the method of Figure 7, the UPF network element maps the first data to the first QoS stream, and the first data is downlink data. The method shown in Figure 7 includes:

[0193] Step 710: The UPF network element acquires the first measurement result of the first QoE.

[0194] For example, a UPF network element can obtain a first measurement result from the first data. If the first measurement result is carried in the packet header of the first data, the UPF network element can obtain the first measurement result from the packet header of the first data. Alternatively, the UPF network element can measure the service corresponding to the first data (such as inference service and / or training service) according to the first QoE to obtain the first measurement result. Alternatively, other network elements or nodes can perform corresponding measurements according to the first QoE to obtain the first measurement result. Further, the other network element or entity indicates the first measurement result to the UPF network element. For example, the other network element or entity sends first indication information to the UPF network element, the first indication information being used to indicate the first measurement result. Accordingly, the UPF network element receives the first indication information from the other network element or entity; the UPF network element obtains the first measurement result according to the indication of the first indication information. Optionally, the other network element or entity performing the first QoE measurement is specifically another network element or entity besides the UPF network element. For example, the other network element or entity can be a network element or entity originally existing in the core network. Alternatively, a new network element or entity can be added to the core network to perform the first QoE measurement. The aforementioned other network elements or entities can implement AI functions, such as using AI to infer the first measurement result. This other network element or entity can be called an AI entity. An entity can also be described as a node; for example, an AI entity can also be called an AI node. Even the network element or entity performing the first QoE measurement can be a terminal; for example, the terminal measures the service corresponding to the first data based on the first QoE to obtain the first measurement result. The terminal sends a first indication message to the UPF network element to indicate the first measurement result.

[0195] Step 720: The UPF network element maps the first data to the first quality of service flow based on the first measurement result, and there is a mapping relationship between the first measurement result and the first quality of service flow.

[0196] For example, the mapping relationship between the first measurement result and the first quality of service flow can be predefined or configured by other network devices for the UPF network element. For instance, the SMF network element can configure the mapping relationship between the first measurement result and the first quality of service flow to the UPF network element. If the SMF network element sends first configuration information to the UPF network element, the UPF network element receives the first configuration information from the SMF network element. This first configuration information is used to configure the mapping relationship between the first measurement result and the first quality of service flow, or, in other words, the first configuration information is used to configure the mapping relationship between the measurement result and the quality of service flow, and this mapping relationship at least includes the mapping relationship between the first measurement result and the first quality of service flow.

[0197] In one possible implementation, during the creation or modification of a PDU session, the SMF network element can configure the "mapping relationship between the first measurement result and the first quality of service flow" to the UPF network element. For example, during the creation or modification of the PDU session, the SMF network element sends the aforementioned first configuration information to the UPF network element.

[0198] Optionally, as in Example 1: During the creation or modification of a PDU session, the SMF network element can also instruct the UPF network element to perform QoE measurement. For instance, the SMF network element sends a second instruction message to the UPF network element, which instructs the UPF network element to perform QoE measurement. For example, the UPF network element receives first data from the DN, which is downlink data. This first data at least contains a type identifier for the first QoE. Optionally, the first data also contains a service identifier corresponding to the first data. The UPF network element performs the first QoE measurement according to the instruction of the second instruction message sent by the SMF network element during the PDU session creation or modification process: for example, measuring the service corresponding to the first data based on the first QoE, and determining the first measurement result, etc.

[0199] Optionally, Example 2: During the creation or modification of a PDU session, the SMF network element can also instruct the UPF network element to map the Quality of Service (QoS) flow according to the QoE measurement results. For example, the SMF network element sends a third indication message to the UPF network element, which instructs the UPF network element to map the QoS flow according to the QoE measurement results. For instance, the UPF network element receives first data from the DN, which is downlink data. When the UPF network element receives the first data, it maps the QoS flow according to the QoE measurement results based on the third indication message sent by the SMF network element during the PDU session creation or modification process. For example, the UPF network element can measure the service corresponding to the first data based on the first QoE to determine the first measurement result; the UPF network element determines the first QoS flow corresponding to the first measurement result based on the configured mapping relationship between the measurement result and the QoS flow; and the UPF network element maps the first data onto the first QoS flow for transmission. At this point, the UPF network element can obtain the QoE type it needs to measure (i.e., the first QoE) from the first data, such as the first data containing a type identifier for the first QoE. Optionally, the first data may also contain an identifier for the service corresponding to the first data. Alternatively, the UPF network element may not perform the measurement of the first QoE. The UPF network element obtains the first measurement result through other means, such as the UPF network element obtaining the first measurement result from the first data.

[0200] For example, in a specific implementation, during the creation or modification of a PDU session, the SMF network element can send a second indication message (refer to the description in Example 1 above) or a third indication message (refer to the description in Example 2 above) to the UPF network element. The UPF network element receives the first data from the DN. The first data can be application layer data. In the description of this application, the first data can also be referred to as application layer traffic, or data corresponding to application layer traffic. The first data contains information associated with the first QoE, such as: 1) the first measurement result, which can also be described as: the measurement result (QoE metric) of the current QoE (i.e., the first QoE). 2) parameters related to the first QoE corresponding to the first measurement result. For example, the above parameters can be the application identifier corresponding to the current first QoE, etc. For example, a service can have multiple application identifiers, and one application identifier corresponds to one QoE index. When the type of the first QoE (such as the QoE index) is different, the application identifiers contained in the first data are also different. For example, a service includes multiple application identifiers, namely ID1, ID2, etc. When the types of the first QoE are different, for example, when the indexes of the QoE are different, the corresponding application identifier can be carried in the first data.

[0201] Furthermore, in the method shown in Figure 7: the "mapping relationship between the first measurement result and the first quality of service flow" or "mapping relationship between the measurement result and the quality of service flow" is included in the first PDR. For example, the SMF network element sends first configuration information to the UPF network element. This first configuration information is used to configure the first PDR, and the first PDR includes the aforementioned "mapping relationship between the first measurement result and the first quality of service flow," or it can be described as the first PDR including the aforementioned "mapping relationship between the measurement result and the quality of service flow," etc.

[0202] Step 730: The UPF network element sends the first data through the first quality of service flow.

[0203] Accordingly, the access network device receives the first data through the first quality of service flow. Optionally, if the receiving end of the first data is another device, the access network device can forward the first data through the first quality of service flow. For example, the access network device can forward the first data to other access network devices or to a terminal, etc.

[0204] As can be understood, the method shown in Figure 5 illustrates the process of the terminal mapping first data to a first Quality of Service (QoS) stream. Optionally, as shown in Figure 8a, after mapping the first data to the first QoS stream, the method further includes: the terminal determining the radio bearer (RB) corresponding to the first QoS stream (e.g., referred to as the first RB) according to air interface mapping rules. The number of first RBs can be one or more, without limitation. For example, the air interface mapping rules include: the mapping relationship between QoS streams and radio bearers. This mapping relationship can be many-to-one, that is, multiple QoS streams correspond to one radio bearer. Or, the mapping relationship between QoS streams and radio bearers. This mapping relationship can be one-to-one, that is, one QoS stream corresponds to one radio bearer. The terminal sends the first data through the first RB.

[0205] Accordingly, the access network device receives the first data through the first RB; based on the air interface mapping rules, it then determines the first quality of service flow corresponding to the first RB. The access network device then sends the first data to the UPF network element through the first quality of service flow.

[0206] As can be understood, the method shown in Figure 7 illustrates the process by which the UPF network element maps the first data to the first Quality of Service (QoS) stream. Optionally, as shown in Figure 8b, the UPF network element can map the first data to the first QoS stream according to the first PDR; and send the first data to the access network device through the first QoS stream. Correspondingly, the access network device receives the first data through the first QoS stream. Based on the air interface mapping rules, the first RB corresponding to the first QoS stream is determined. The access network device then sends the first data to the terminal through the first RB.

[0207] Through the above design, the default UPF network element can identify the first measurement result. Therefore, the UPF network element can map the quality of service flow based on the first measurement result, meeting the quality of service flow requirements of data at different stages or with different measurement results, and improving the transmission performance of data or services.

[0208]

Example 2

[0209] Example 2 provides a method that differs from the method shown in Example 1 in that the mapping relationships included in the PDR can remain unchanged. For example, this mapping relationship can be a mapping relationship between at least one item in the IP 5-tuple and the Quality of Service (QoS) flow. When the value of the first measurement result of the first QoE is different, the mapping relationship associated with the current first measurement result is indicated to the UPF network element (see Example 2 below). Alternatively, the mapping relationship associated with the current first measurement result is reconfigured for the UPF network element (see Example 1 below). For example, the first measurement result may be specifically measurement result 1, measurement result 2, or measurement result 3. Mapping relationship 1 is associated with measurement result 1. Mapping relationship 2 is associated with measurement result 2. Mapping relationship 3 is associated with measurement result 3. When the specific value of the first measurement result is measurement result 1, mapping relationship 1 can be indicated or reconfigured to the UPF network element; similarly, when the specific value of the first measurement result is measurement result 2, mapping relationship 2 can be indicated or reconfigured to the UPF network element; when the specific value of the first measurement result is measurement result 3, mapping relationship 3 can be indicated or reconfigured to the UPF network element, and so on.

[0210] Figure 9 provides a flowchart of a communication method, which includes at least:

[0211] Optionally, in step 910: other devices send first request information; correspondingly, the SMF network element receives the first request information.

[0212] Other devices can be AI entities, PCF network elements, or terminals, etc., without restriction. The first request information is used to request an update to the downlink data mapping relationship on the UPF network element side. For the content of the first request information, please refer to the explanation in [Example 1] or [Example 2] below. It is understood that the aforementioned other devices can be AI entities, PCF network elements, or terminals, etc. The AI ​​entity can directly send the first request information to the SMF network element, or the AI ​​entity can send the first request information to the SMF network element through the PCF network element, without restriction.

[0213] Example 1

[0214] The first request information includes indication information for the first mapping relationship. Based on this indication information, the SMF network element determines the first mapping relationship from among multiple mapping relationships. Then, the SMF network element can indicate the first mapping relationship to the UPF network element, such as by sending first information indicating the first mapping relationship to the UPF network element. Alternatively, the SMF network element can generate configuration information for the first mapping relationship and configure it to the UPF network element. For example, the SMF network element can send configuration information for configuring the first mapping relationship to the UPF network element. Optionally, the first mapping relationship can be included in the first PDR. The above process can be described as follows: the SMF network element resets the PDR to the UPF network element and configures the first PDR to the UPF network element.

[0215] The aforementioned mapping relationships can be predefined or configured by other network devices for the SMF network element. Alternatively, they can be generated by the SMF network element, such as based on policy information provided by the PCF network element. For example, the PCF network element can send policy information corresponding to multiple mapping relationships to the SMF network element. The SMF network element then generates the aforementioned multiple mapping relationships based on this policy information.

[0216] Example 2

[0217] The first request information contains indication information of the first measurement result. The SMF network element determines a first mapping relationship among multiple mapping relationships that is associated with the current first measurement result. Then, the SMF network element can send first information indicating the first mapping relationship to the UPF network element. Alternatively, the SMF network element generates configuration information for the first mapping relationship. The SMF network element then sends configuration information for configuring the first mapping relationship to the UPF network element.

[0218] It is understandable that any one of the above mapping relationships is correlated with the measurement result of the first QoE. These mapping relationships can be predefined, configured by other network devices for the SMF network element, or generated by the SMF network element; there are no restrictions.

[0219] Example 3

[0220] The first request information contains policy information related to the first measurement result. The SMF network element generates a first mapping relationship based on this policy information. At this point, the first request information can be considered to originate from the PCF network element. Subsequently, the SMF network element sends first information indicating the first mapping relationship to the UPF network element.

[0221] Alternatively, the SMF network element can generate configuration information for the first mapping relationship based on the aforementioned policy information (such as the first policy). The SMF network element sends first information for configuring the first mapping relationship to the UPF network element. For example, the SMF network element sends a session modification request to the UPF network element, which includes the configuration information for the first mapping relationship. It can be understood that the first mapping relationship can be included in the first PDR. The above process can also be described as follows: The SMF network element generates configuration information for the first PDR based on the policy information (such as the first policy) provided by the PCF network element. The SMF sends the configuration information of the first PDR to the UPF network element, reconfiguring the PDR currently applied or stored by the UPF network element to the first PDR. As mentioned above, the configuration information of the first PDR can be carried in the session modification request.

[0222] In any of Examples 1 to 3 above, the SMF network element can obtain the first mapping relationship (or configuration information of the first mapping relationship). Then, the SMF network element can send first information to the UPF network element, the first information being used to indicate or configure the first mapping relationship. The UPF network element determines the first mapping relationship based on the configuration or indication of the SMF network element. Based on the first mapping relationship, the UPF network element maps the first data to the corresponding Quality of Service (QoS) flow.

[0223] Step 920: The SMF network element sends the first information; correspondingly, the UPF network element receives the first information.

[0224]

Example 1

[0225] For example, the first information includes indication information of the first mapping relationship. An SMF network element can determine the first mapping relationship from among multiple mapping relationships based on the indication of the first information. It can be understood that the first mapping relationship can be considered to belong to the aforementioned multiple mapping relationships, and any one of these multiple mapping relationships is correlated with the measurement result of the first QoE.

[0226] These multiple mapping relationships can be predefined or configured by other network devices for the UPF network element. For example, the SMF network element can configure these multiple mapping relationships for the UPF network element. Specifically, during the creation or modification of a PDU session, the SMF network element can configure multiple mapping relationships for the UPF network element. Specifically, the SMF network element can send first configuration information to the UPF network element, which is used to configure the aforementioned multiple mapping relationships.

[0227] It is understandable that the first measurement result corresponding to different mapping relationships may be different. For example, the above mapping relationships include mapping relationship 1, mapping relationship 2, and mapping relationship 3. The first measurement result includes measurement result 1, measurement result 2, and measurement result 3. Mapping relationship 1 is associated with measurement result 1. Mapping relationship 2 is associated with measurement result 2. Mapping relationship 3 is associated with measurement result 3.

[0228] For example, an AI entity can measure the service corresponding to the first data based on the first QoE to obtain a first measurement result. If the first measurement result is specifically measurement result 1, the AI ​​entity can directly initiate a request to the SMF network element, such as a session modification request. For example, this request may contain indication information of measurement result 1. The SMF network element determines mapping relationship 1, which is associated with measurement result 1, among multiple mapping relationships. The SMF network element sends first information to the UPF network element, which indicates the aforementioned mapping relationship 1, such as including an identifier for mapping relationship 1. In this case, mapping relationship 1 is one possible implementation of the first mapping relationship.

[0229]

Example 2

[0230] When a UPF network element receives the first information, it can update (or reset) the mapping relationship of the current application to the first mapping relationship according to the configuration of the first information. For example, an AI entity can measure the service corresponding to the first data according to the first QoE to obtain the first measurement result. For example, the first measurement result can be specifically measurement result 1, measurement result 2, or measurement result 3. If the first measurement result meets the first condition, such as the first measurement result obtained by the current measurement is different from the first measurement result obtained by the previous measurement, such as the first measurement result obtained by the current measurement being specifically measurement result 1, while the first measurement result obtained by the previous measurement was specifically measurement result 2, then the first condition can be considered to be met. The AI ​​entity can send a request to the PCF network element, such as a policy update request, which includes the first measurement result obtained by the current measurement, such as measurement result 1. The PCF network element can generate policy information related to the mapping relationship (such as called mapping relationship 1) corresponding to measurement result 1 based on measurement result 1. The PCF network element sends a request to the SMF network element, such as a user plane policy update request, which includes policy information related to mapping relationship 1. The SMF network element generates configuration information for mapping relationship 1 based on the policy information related to mapping relationship 1. The SMF network element sends a request, such as a session modification request, to the UPF network element. This request contains the configuration information for mapping relationship 1, or in other words, it contains the first configuration information, which is used to configure mapping relationship 1.

[0231] It is understandable that the "first mapping relationship" can be included in the first PDR. The first information is used to configure the first mapping relationship, which can be replaced with: the first information is used to configure (or reconfigure) the first PDR, and the first PDR contains at least the first mapping relationship. Alternatively, the above first configuration information is used to configure multiple mapping relationships, which can be replaced with: the first configuration information is used to configure multiple PDRs, and one PDR contains one mapping relationship.

[0232] For example, the first mapping relationship includes: a mapping relationship between a first parameter and a first quality of service flow, wherein the first parameter includes at least the address information and / or port information of the data. For example, the address information of the data includes the source address and destination address, and the port information includes the source port and destination port, etc. Furthermore, the first parameter may also include: protocol type information, etc. For example, the mapping relationship between the first parameter and the first quality of service flow can specifically be: a mapping relationship between (source IP address + destination IP address) and the quality of service flow, or a mapping relationship between (source MAC address + destination MAC address) and the quality of service flow, etc.

[0233] For example, the first PDR contains a packet filter, which contains a first mapping relationship. The function of the packet filter is to map the data to be sent to the corresponding quality of service stream. The above "mapping" process can be regarded as filtering the data, hence the name packet filter.

[0234] For example, this packet filter could be an Internet Protocol (IP) packet filter. The classification of IP packet filters primarily includes the IP 5-tuple, such as the IP address / port of the sender and receiver, and the protocol type (IPv4, IPv6). The IP packet filter contains the aforementioned first mapping relationship. Specifically, the first mapping relationship is a mapping between (source IP address + destination IP address) and the Quality of Service (QoS) flow. When a UPF network element receives data (such as the first data), it can query the corresponding QoS flow from the first mapping relationship based on the source and destination IP addresses contained in the first data, and map the first data to the first QoS flow for transmission. It can be understood that the IP 5-tuple includes: source IP address, destination IP address, source port number, destination port number, and transport layer protocol, such as TCP, UDP, etc.

[0235] For example, this packet filter could be an Ethernet packet filter. Ethernet packet filters are primarily classified based on information such as the MAC addresses of the sending and receiving ends. For instance, an Ethernet packet filter might include the aforementioned first mapping relationship. Specifically, the first mapping relationship is a mapping between (source MAC address + destination MAC address) and a Quality of Service (QoS) flow. When a UPF network element receives data (such as the first data), it can query the corresponding QoS flow from the first mapping relationship based on the source and destination MAC addresses contained in the first data, and map the first data to the first QoS flow for transmission.

[0236] Step 930: The UPF network element sends the first data through the first quality of service flow corresponding to the first mapping relationship.

[0237] For example, the UPF network element obtains the first parameter from the first data. For example, it obtains the first parameter from the packet header of the first data. For example, the first parameter could be the source IP address and destination IP address of the first data, or it could be the source MAC address and destination MAC address of the first data, etc. The UPF network element determines the first quality of service (QoS) flow corresponding to the first parameter based on the mapping relationship between the first parameter and the first QoS flow contained in the first mapping relationship. For example, the first mapping relationship could be a mapping relationship between (source IP address + destination IP address) and the first QoS flow, or a mapping relationship between (source MAC address + destination MAC address) and the first QoS flow, etc. The UPF network element maps the first data to the first QoS flow for transmission.

[0238] [Example 1]: The SMF network element configures (e.g., reconfigures) the first PDR for the UPF network element. For example, the SMF network element sends first information to the UPF network element, and this first information is used to configure the first PDR. If the first measurement result of the first QoE meets the first condition (e.g., the trigger condition), the SMF network element is triggered to configure the first PDR for the UPF network element. The first PDR contains a first mapping relationship that matches the current first measurement result.

[0239]

Example 1.1

[0240] For example, a service corresponding to the first data is continuously transmitted between the terminal and the UPF network element. This service can be an ongoing service. During this process, the UPF network element can send the first data to the terminal. The AI ​​entity can perform QoE detection / monitoring on the service of the first data. For instance, the AI ​​entity can measure the service corresponding to the first data based on the first QoE and determine the first measurement result. The first QoE can be understood as a certain type of QoE, containing one type of QoE. Alternatively, the first QoE can be understood as multiple types of QoE, containing multiple types of QoE.

[0241] When the first measurement result meets the first condition, the AI ​​entity sends the information of the current first measurement result to the PCF network element (if it is carried in the policy update request). The PCF network element provides the SMF network element with the policy corresponding to the current first measurement result, which can be referred to as the first policy (if it is carried in the user plane policy update request). The SMF network element generates information for reconfiguring the first PDR according to the first policy and sends the configuration information of the first PDR to the UPF network element (if the configuration information of the first PDR is carried in the session modification request). The UPF network element updates the current application or stored PDR to the first PDR based on the configuration information of the first PDR. Afterwards, the UPF network element maps the first data to the quality of service flow based on the first mapping relationship contained in the first PDR.

[0242] As shown in Figure 10, the method includes:

[0243] Step 1010: The AI ​​entity measures the business corresponding to the first data based on the first QoE and determines the first measurement result.

[0244] Step 1020: When the first measurement result meets the first condition, the AI ​​entity and the PCF network element perform a policy update.

[0245] The English name for policy update is "policy update". During the policy update process, the AI ​​entity sends a policy update request to the PCF network element; in response to the policy update request, the PCF network element sends a policy update response to the AI ​​entity.

[0246] For example, the first condition can be predefined or configured by other devices for the AI ​​entity, without restriction. The first condition can also be called a trigger condition or trigger event. For example, if the first measurement result meets the first condition, the AI ​​entity is triggered to send a policy update request to the PCF network element. The specific content of the first condition is not limited. For example, the first condition can be that the current first measurement result is different from the adjacent previous measurement result. Or, the first condition can be that the difference between the current first measurement result and the adjacent previous measurement result is greater than a threshold, etc., without restriction.

[0247] Optionally, unlike other applications, in this application, the policy update request includes indication information of the current first measurement result. For example, the first QoE is the inference accuracy, and the current first measurement result is 95% to 98% (i.e., the inference accuracy range is 95% to 98%). For instance, the range of the aforementioned inference accuracy can have a corresponding index, which is used to indicate the range of the aforementioned inference accuracy. For example, the indication information of the current first measurement result included in the policy update request can specifically be: the index corresponding to the range of the aforementioned inference accuracy, etc. The PCF network element can determine a first policy based on the current first measurement result. For example, the first policy can be the policy corresponding to the first PDR, and the first PDR contains a first mapping relationship corresponding to the current first measurement result.

[0248] Step 1030: The PCF network element and the SMF network element perform a user plane policy update (UP policy update).

[0249] For example, the process of updating user plane policies includes: the PCF network element sending a user plane policy update request to the SMF network element; and in response to the above request, the SMF network element sending a user plane policy update response to the PCF network element.

[0250] Optionally, the user plane policy update request includes information about the first policy. The SMF network element determines the configuration information of the first PDR based on the first policy information.

[0251] Step 1040: SMF network element performs session modification with UPF network element.

[0252] The process of session modification includes: the SMF network element sending a session modification request to the UPF network element. In response to the request, the UPF network element sends a session modification response to the SMF network element. "Session modification" can also be described as: session update.

[0253] For example, a session modification request may contain configuration information for a first PDR. This first PDR can be considered as a PDR reconfigured for the UPF network element based on the current first measurement result. The UPF network element resets the PDR for the current application or storage according to the configuration information of the aforementioned first PDR. For example, the UPF network element updates the PDR for the current application or storage to the first PDR.

[0254] Through the above process, the PDR stored or applied between UPF network elements is updated to the first PDR. The first PDR contains at least a first mapping relationship. UPF network elements can map the first data corresponding to the first service to the corresponding quality of service flow (such as the first quality of service flow) according to the first PDR or the first mapping relationship.

[0255] Optionally, in step 1050: the UPF network element performs a user plane update with the access network device.

[0256] For example, the user plane update process includes: the UPF network element sending a user plane update request to the access network device; and in response to the above request, the access network device sending a user plane update response to the UPF network element.

[0257] For example, the access network device can obtain air interface mapping rules, which are used to map Quality of Service (QoS) flows to Resource Blocks (RBs). There are no restrictions on the content of the user plane updates described above. For example, the user plane update process may include updating the RB corresponding to the first QoS flow in the first mapping relationship included in the first PDR.

[0258] Through the above process, the UPF-side storage or application PDR is reconfigured or updated to the first PDR. The UPF network element can map or filter the data (such as the first data) of the continuously running service based on the first PDR. For example, the UPF network element receives the first data. The first data can also be described as data corresponding to application layer traffic, which can be simply referred to as application layer traffic. Based on the reset first PDR, the UPF network element maps the first data to a first quality of service (QoS) flow and transmits the first data through the first QoS. For example, the first PDR contains a first mapping relationship. The first mapping relationship is specifically a mapping relationship between (source IP address + destination IP address) and the first QoS flow. The UPF network element obtains the source IP address and destination address from the first data. Based on the above (source IP address + destination IP address) and the first mapping relationship, the first QoS flow is determined. Afterwards, the UPF network element maps the first data to the first QoS flow and transmits the first data through the first QoS flow.

[0259] [Example 1.2]: The terminal measures the service corresponding to the first data based on the first QoE and determines the first measurement result. When the first measurement result meets the first condition, the terminal directly sends a request to the SMF network element, such as a session update (modification) request. This request contains the first measurement result or the first mapping relationship corresponding to the first measurement result. The SMF network element configures the first PDR for the UPF network element based on the first measurement result or the first mapping relationship. For example, the SMF network element can determine the configuration information of the first PDR based on the first measurement result or the first mapping relationship. The SMF network element reconfigures the first PDR for the UPF network element. If the SMF network element sends a request to the UPF network element, such as a session update request, this request contains the configuration information of the first PDR.

[0260] [Example 1.3]: The SMF side can obtain multiple mapping relationships, each corresponding to different measurement results of the first QoE. For example, during the creation or modification of a PDU session, the PCF network element provides the SMF network element with the strategies corresponding to the aforementioned multiple mapping relationships. The SMF network element generates multiple mapping relationships based on these strategies. When the AI ​​entity or terminal determines that the first measurement result obtained from the measurement meets the first condition, it directly sends a request to the SMF network element, such as a session update request, if the request contains the first measurement result. The SMF determines the first mapping relationship corresponding to the first measurement result. The SMF network element determines the configuration information of the first PDR containing the first mapping relationship and reconfigures the first PDR to the UPF network element.

[0261]

Example 2

[0262] For example, when an AI entity or terminal detects and obtains a first measurement result that meets a first condition, it can feed back the first measurement result, or the first PDR corresponding to the first measurement result, to the SMF network element. The SMF network element triggers the UPF network element to apply the first PDR, such as by the SMF network element sending an indication message for the first PDR to the UPF network element. The aforementioned first PDR can be one of the predefined PDRs. For example, the UPF side can obtain multiple predefined PDRs. The SMF can directly trigger the UPF network element to apply any one of the aforementioned multiple PDRs.

[0263] In one possible implementation, the UPF network element can acquire first data. The first data can be downlink data, such as data received from the DN side. In one description, the first data can also be described as a first data packet or a downlink data packet. Similarly, in uplink transmission, the first data can also be described as a first data packet or an uplink data packet. As shown in Figure 11: The UPF network element can determine or discover a PFCP session based on the first data. Further, within this PFCP session, it discovers or determines a PDR (PFCP session's PDR lookup), such as determining the highest priority PDR in the PFCP session, referred to as the successfully matched PDR, i.e., the first PDR. This first PDR is at least associated with the FAR; optionally, the first PDR is also associated with the MAR, QER, and URR. The UPF network element at least utilizes or applies the rules contained in the matching PDR to map the first data to a first quality of service flow.

[0264] Through the above design, the SMF network element can instruct or configure the UPF network element to apply the corresponding mapping relationship according to the different first measurement results, and perform service quality flow mapping, thereby meeting the service quality flow requirements of the transmitted data under different stages or different measurement results, and satisfying the data needs.

[0265]

Example 3

[0266] This third embodiment can be implemented alone, or it can be implemented in combination with the first or second embodiment, etc., without limitation. It is understood that in the description of the first or second embodiment above, the UPF network element can obtain a first PDR, and the UPF network element maps the first data to a first quality of service flow according to the first PDR, and transmits the first data through the first quality of service flow.

[0267] The first PDR is associated with the first URR. For example, in one method, the UPF network element calculates the amount of data transmitted by the UPF based on the first URR, which may include the amount of uplink and / or downlink data. When a triggering condition is met, such as the calculated data amount being greater than or equal to a threshold, the UPF network element sends a report to the SMF network element to report the amount of data transmitted by the UPF network element. In one understanding,

[0268] In the method of this application: the granularity of the first URR statistical data is modified. For example, the granularity of the first URR statistical data is modified to the business granularity, or a finer granularity, such as the granularity of a certain category under a certain business. Furthermore, in one method, after the UPF network element reports its statistical granularity to the SMF network element, the SMF network element does not update accordingly based on the data volume information reported by the UPF network element. In this application, the SMF network element can update based on the data volume information reported by the UPF network element. For example, updating the first FAR and / or the first QER associated with the first PDR, etc.

[0269] Figure 12 provides a flowchart of a communication method, including:

[0270] Optionally, in step 1210: the terminal and the UPF network element continuously transmit data corresponding to the first service, which may be an ongoing service, or simply an ongoing service.

[0271] Step 1220: The UPF network element determines the first data volume based on the first URR;

[0272] For example, the first URR is predefined, or configured by other network devices for the UPF network element. For instance, the SMF network element configures the first URR for the UPF network element during the creation or modification of a PDU session. In this application, the first URR at least contains granularity information for calculating the first data volume. The UPF network element calculates the corresponding data volume and determines the first data volume based on the granularity information indicated by the first URR. For example, the granularity information for calculating the first data volume contained in the first URR may specifically be: service granularity, or the granularity of the first category of a service.

[0273] For example, the first URR instructs the UPF network element to count data volume at the "service granularity," such as the first URR containing the granularity of counting the first data volume specifically being the "service granularity." The UPF network element can identify the data of a service; furthermore, the UPF network element counts the data volume of a service (e.g., referred to as the first data volume).

[0274] For example, when a UPF network element receives data, it can determine the service corresponding to the data based on the service identifier contained in the data. Furthermore, the UPF network element counts the amount of data transmitted for that service. For instance, the UPF network element can separately count the amount of data corresponding to any one of the following tasks: training tasks, data acquisition tasks, inference tasks, etc. (It can be understood that the amount of data corresponding to any one service can be referred to as the first data amount). When the first data amount meets a first condition, the UPF network element reports the data amount of at least one task to the SMF network element. It can be understood that the aforementioned first condition can be considered as the condition that triggers the UPF network element to report the data amount (such as the first data amount) to the SMF network element.

[0275] For example, the first URR instructs the UPF network element to collect data at the "granularity of the first category," such as the granularity of the first URR for collecting the first data volume being the "granularity of the first category." For instance, the granularity of the first category could be: the geographical location information corresponding to the data, or the node information to which the data belongs, etc. Alternatively, the granularity of the first category could be the amount of data consumed during training, the training time, etc.

[0276] For example, taking data acquisition services as an example, when a UPF network element identifies data as belonging to a data acquisition service: the UPF network element can use "the geographic location information corresponding to the data" as the granularity to count the amount of data corresponding to any geographic location. For example, a UPF network element can receive or send data, which is acquired data, and this data contains the geographic location information corresponding to the data, i.e., the geographic location information of the acquired data, etc. The UPF network element can use geographic location information as the granularity to count the amount of data corresponding to any geographic location. For example, the geographic locations corresponding to the acquired data in a data acquisition service include: geographic location A, geographic location B, geographic location C, etc. The UPF network element can use address location as the granularity to count the amount of data transmitted by the UPF network element in geographic location A, geographic location B, and geographic location C, respectively. It can be understood that "data transmitted by the UPF network element" includes: data sent and / or received by the UPF network element. For example, data sent and / or received by the UPF network element in geographic location A, etc. Alternatively, the UPF network element can use the data's home node as the granularity to count the amount of data corresponding to any home node. It can be understood that the data's home node refers to the destination receiving end of the data. Similarly, a UPF network element can be used to count: the amount of data transmitted by the UPF network element corresponding to the home node A, the amount of data transmitted by the UPF network element corresponding to the home node B, and the amount of data transmitted by the UPF network element corresponding to the home node C, etc.

[0277] For example, taking inference tasks as an example, when a UPF network element identifies that the data belongs to an inference task, the UPF network element can count the corresponding data volume at the granularity of the data's geographical location information or data classification information.

[0278] Step 1230: When the first data volume meets the first condition, the UPF network element sends the first report. Correspondingly, the SMF network element receives the first report.

[0279] The first report contains indication information about the first data volume. For example, the first condition can be predefined or configured by other network devices for the UPF network element. The first condition can also be called a trigger condition; for instance, if the first data volume counted by the UPF network element meets the first condition, the UPF network element is triggered to send the first report. In one interpretation, the UPF network element can count the corresponding data volume (e.g., the first data volume) at different granularities. Different granularities of data volume have corresponding first conditions. The first conditions corresponding to the above different granularities can be the same or different.

[0280] For example, a UPF network element can count the data volume of any service transmitted by the UPF network element at the service granularity. For instance, the UPF network element can separately count the data volume corresponding to a training task, the data volume corresponding to a data acquisition service, or the data volume corresponding to an inference task. The first condition for the training task can be: the data volume corresponding to the training task is greater than or equal to threshold 1; the first condition for the data acquisition task can be: the data volume corresponding to the data acquisition service is greater than or equal to threshold 2; and the first condition for the inference task can be: the data volume corresponding to the inference task is greater than or equal to threshold 3. It is understood that the values ​​of threshold 1, threshold 2, or threshold 3 can be the same or different. Optionally, threshold 1, threshold 2, or threshold 3 can be predefined or configured by other network devices for the UPF network element, without restriction.

[0281] Optionally, in step 1240: In response to the first report, the SMF network element sends the first update information. Accordingly, the UPF network element receives the first update information.

[0282] For example, the first update information can be included in the updated user plane configuration. In one understanding, when the first data volume counted by the UPF network element meets a first condition, the UPF network element is triggered to send a first report to the SMF network element. Upon receiving the first report, the SMF network element can send the first update information to the UPF network element. The first update information can be considered as being sent by the SMF network element triggered by the first report. For example, upon receiving the first report, the SMF network element, triggered by the first report, updates the user plane configuration. If the SMF network element sends an updated user plane configuration to the UPF network element, this updated user plane configuration includes the aforementioned first update information.

[0283] Alternatively, upon receiving the first report, the SMF network element can send the first report to the PCF network element. Alternatively, the UPF network element can directly send the first report to the PCF network element. Upon receiving the first report, the PCF network element can update the user plane policy. For example, the PCF network element sends an updated user plane policy to the UPF network element, and this updated user plane policy includes the aforementioned first update information. Alternatively, the PCF network element sends the aforementioned first update information to the SMF network element, which then forwards it to the UPF network element. For example, the PCF network element updates the user plane policy to the SMF network element, and this updated user plane policy includes the first update information. The SMF network element sends an updated user plane configuration to the UPF network element, and this updated user plane configuration includes the first update information, etc. In other words, besides the method illustrated in Figure 13, the following methods may also exist: Upon receiving the first report, the SMF network element forwards the first report to the PCF network element. The PCF network element can send the first update information to the UPF network element. Alternatively, the PCF network element can send the first update information to the SMF network element, and the SMF network element can forward the first update information to the UPF network element.

[0284] In one possible implementation, the first update information is used to update the first FAR and / or first QER associated with the first PDR. The UPF network element can update the first FAR and / or first QER associated with the first PDR based on the first update information.

[0285] For example, the UPF network element performs a first data volume count based on the first URR, using the entity / node receiving the data as the granularity. When the first data volume meets the first condition, it reports the first report. When the SMF network element receives the first report, it can determine that the amount of data received by the current node is too large, for example, exceeding a threshold. At this time, the SMF network element can send the first update information to update the first FAR. The first FAR can specify new forwarding rules, such as forwarding subsequent data or traffic data to new service entities or nodes. Alternatively, when the SMF network element receives the first report, it determines that the current service data volume is too large. The SMF network element can update the first QER. For example, the SMF network element can allocate new QoS traffic for the current service data or traffic data (such as allocating a higher QoS flow), or configure new QoS parameters for the current application's QoS flow (such as configuring a higher transmission rate for the current QoS flow), thereby meeting the current service's requirements for QoS flow.

[0286] Optionally, step 1250: The UPF network element and the access network equipment perform a user plane update.

[0287] This can be understood as follows: when the FAR or QER associated with the first PDR is updated, the access network equipment needs to be updated accordingly.

[0288] By modifying the granularity of the statistical data in the first URR through the above design, the UPF network element can report the corresponding data volume with finer granularity, thereby meeting the needs of different services. Furthermore, the SMF network element can update the corresponding parameters based on the data volume reported by the UPF network element, thereby meeting the needs of the corresponding services and improving data transmission performance.

[0289] The embodiments provided in this application primarily describe the methods from the perspective of interaction between the terminal and network-side devices (such as access network devices, UPF network elements, or SMF network elements). To implement the functions of the methods provided in this application, the terminal and network devices may include hardware structures and / or software modules, implementing the aforementioned functions in the form of hardware structures, software modules, or a combination of hardware structures and software modules. Whether a particular function is executed in the form of hardware structures, software modules, or a combination of hardware structures and software modules depends on the design constraints of the specific application of the technical solution.

[0290] Based on the same design concept as the above-described method embodiments, Figure 13 is a schematic diagram of the structure of a possible communication device provided in the embodiments of this application. These communication devices can realize the functions implemented by terminals or network devices in the above-described method embodiments, and therefore may achieve the beneficial effects possessed by the above-described method embodiments. In the embodiments of this application, the communication device may be a terminal or network device, or a unit, module, or component (such as a chip, chip system, circuit, processor, or others) applied in a terminal or network device. In the following description, the term "unit" will be used as an example. For example, in the following description, the communication device will be described as including a processing unit and a communication unit. The processing unit in the following description may also be replaced by: a processing module or a processing component, etc. The communication unit may also be replaced by: a communication unit or a transceiver component. For example, a transceiver component may refer to a communication module.

[0291] Figure 13 illustrates a possible exemplary block diagram of the communication device involved in the embodiments of this application. As shown in Figure 13, the communication device 1300 may include modules or units for implementing the method embodiments described above. In one possible design, the communication device 1300 includes a processing unit 1302 and a communication unit 1303. Optionally, the communication device 1300 may further include a storage unit 1301 for storing device program code and / or data.

[0292] The communication device 1300 can be a terminal-side device in the above embodiments, such as a terminal or a communication module in a terminal, or a circuit or chip in a terminal that is responsible for communication functions.

[0293] For example, in one embodiment, the communication device 1300 is used to implement the terminal-side functions in the method shown in FIG5 of the above method embodiment. For instance, the processing unit 1302 is used to obtain a first measurement result of the first Quality of Experience (QoE), which includes at least one of the following: inference accuracy, inference latency, inference throughput, training latency, training power consumption, or training convergence speed; the processing unit 1302 is also used to map the first data to a first Quality of Service (QoS) stream based on the first measurement result, wherein there is a mapping relationship between the first measurement result and the first QoS stream; the communication unit 1303 is used to send the first data through the first QoS stream.

[0294] In one possible design, the first measurement result is indicated at least by the type information of the first QoE and the measurement result information of the first QoE.

[0295] In one possible design, the first measurement result is also indicated by the business information of the first data.

[0296] In one possible design, when the processing unit 1302 acquires the first measurement result, it is specifically configured to: acquire the first measurement result from the first data; or, measure the inference task and / or training task corresponding to the first data according to the first QoE to acquire the first measurement result; or, receive first indication information, which is used to indicate the first measurement result.

[0297] In one possible design, the communication unit 1303 is further configured to: receive first configuration information, the first configuration information being used to configure the mapping relationship between the first measurement result and the first quality of service flow.

[0298] In one possible design, the mapping relationship between the first measurement result and the first quality of service flow is included in the first packet detection rule (PDR), which is associated with the first usage report rule (URR). The communication unit 1303 is further configured to: send a first report indicating the first data volume of the first data, which is determined according to the first URR, which indicates the granularity of the statistics of the first data volume.

[0299] In one possible design, the granularity of this first data volume is: business granularity.

[0300] In one possible design, the communication unit 1303 is further configured to: receive first update information; and update the first forwarding action rule FAR and / or the first quality of service flow execution rule QER associated with the first PDR according to the first update information.

[0301] In one possible design, when the communication device 1300 is a terminal or a communication module within a terminal, the function of the processing unit 1302 can be implemented by one or more processors. Specifically, the processor may include a modem chip, or a system-on-a-chip (SoC) chip or a SIP chip containing a modem core. The function of the communication unit 1303 can be implemented by transceiver circuitry.

[0302] In one possible design, when the communication device 1300 is a circuit or chip in a terminal responsible for communication functions, such as a modem chip or a system-on-a-chip (SoC) or SIP chip containing a modem core, the function of the processing unit 1302 can be implemented by a circuit system in the aforementioned chip that includes one or more processors or processor cores. The function of the communication unit 1303 can be implemented by an interface circuit or data transceiver circuit on the aforementioned chip.

[0303] In one possible design, when the communication device 1300 is a terminal or a communication and / or computing module within a terminal, the functionality of the processing unit 1302 can be implemented by one or more processors. Specifically, the processor may include a GPU, or a system-on-a-chip (SoC) or SIP chip containing a GPU. Alternatively, the processor may include an AI processor, or a SoC or SIP chip containing an AI processor. Or, the processor may include an ASIC, or a SoC or SIP chip containing an ASIC. The functionality of the communication unit 1303 can be implemented by transceiver circuitry.

[0304] In one possible design, when the communication device 1300 is a circuit or chip in a terminal responsible for communication and / or computing functions, such as a GPU or a system-on-a-chip (SoC) or SIP chip containing a GPU, an AI processor or a SoC or SIP chip containing an AI processor, or an ASIC or a SoC or SIP chip containing an ASIC, the function of the processing unit 1302 can be implemented by a circuit system in the aforementioned chip that includes one or more processors or processor cores. The function of the communication unit 1303 can be implemented by interface circuits or data transceiver circuits on the aforementioned chip.

[0305] The communication device 1300 can be a network-side device in the above embodiments, such as a UPF network element or a communication module in a UPF network element, or a circuit or chip in a UPF network element that is responsible for communication functions.

[0306] For example, in one embodiment, the communication device 1300 is used to implement the functions of the UPF network element side in the method shown in FIG7 of the above method embodiment. For example, the processing unit 1302 is used to obtain a first measurement result of the first quality of experience (QoE), which includes at least one of the following: inference accuracy, inference latency, inference throughput, training latency, training power consumption, or training convergence speed; the processing unit 1302 is also used to map the first data to a first quality of service stream according to the first measurement result, and there is a mapping relationship between the first measurement result and the first quality of service stream; the communication unit 1303 is used to send the first data through the first quality of service stream.

[0307] In one possible design, the first measurement result is indicated at least by the type information of the first QoE and the measurement result information of the first QoE.

[0308] In one possible design, the first measurement result is also indicated by the business information of the first data.

[0309] In one possible design, when the processing unit 1302 acquires the first measurement result, it is specifically configured to: acquire the first measurement result from the first data; or, measure the inference task and / or training task corresponding to the first data according to the first QoE to acquire the first measurement result; or, receive first indication information, which is used to indicate the first measurement result.

[0310] In one possible design, the communication unit 1303 is further configured to: receive first configuration information, the first configuration information being used to configure the mapping relationship between the first measurement result and the first quality of service flow.

[0311] In one possible design, the mapping relationship between the first measurement result and the first quality of service flow is included in the first packet detection rule (PDR), which is associated with the first usage report rule (URR). The communication unit 1303 is further configured to: send a first report indicating the first data volume of the first data, which is determined according to the first URR, which indicates the granularity of the statistics of the first data volume.

[0312] In one possible design, the granularity of this first data volume is: business granularity.

[0313] In one possible design, the communication unit 1303 is further configured to: receive first update information; and update the first forwarding action rule FAR and / or the first quality of service flow execution rule QER associated with the first PDR according to the first update information.

[0314] The communication device 1300 can be a network-side device in the above embodiments, such as a UPF network element or a communication module in a UPF network element, or a circuit or chip in a UPF network element that is responsible for communication functions.

[0315] For example, in one embodiment, the communication device 1300 is used to implement the functions of the UPF network element side in the method shown in FIG9 of the above method embodiment. The communication unit 1303 is used to receive first information, which is used to indicate or configure a first mapping relationship, and the first mapping relationship matches a first measurement result of the first quality of experience (QoE) of the first data; the communication unit 1303 is also used to send the first data through the first quality of service stream corresponding to the first mapping relationship. Optionally, the processing unit 1302 is used to determine the first quality of service stream corresponding to the first mapping relationship.

[0316] In one possible design, the first information is used to indicate a first mapping relationship, which belongs to multiple mapping relationships, and any one of these multiple mapping relationships is associated with the measurement result of the first QoE.

[0317] In one possible design, the multiple mapping relationships are predefined or configured by the session management function network element. The communication unit 1303 is also used to receive first configuration information, which is used to configure the multiple mapping relationships.

[0318] In one possible design, the first information is used to configure a first mapping relationship, and the processing unit 1302 is further used to update the mapping relationship of the current application to the first mapping relationship according to the configuration of the first information.

[0319] In one possible design, the first mapping relationship includes: a mapping relationship between a first parameter and a first quality of service flow, wherein the first parameter includes at least the address information and / or port information of the data.

[0320] In one possible design, when the communication unit 1303 sends the first data through the first quality of service stream corresponding to the first mapping relationship, it is specifically used to: obtain a first parameter in the first data; determine the first quality of service stream corresponding to the first parameter according to the mapping relationship between the first parameter and the first quality of service stream contained in the first mapping relationship; and send the first data through the first quality of service stream.

[0321] In one possible design, the first mapping relationship is included in a first packet detection rule (PDR), which is associated with a first usage report rule (URR). The processing unit 1302 is further configured to determine the first data volume based on the first URR, which includes granular information for statistical analysis of the first data volume. The communication unit 1303 is further configured to send a first report when the first data volume meets a first condition, which includes indication information for the first data volume.

[0322] In one possible design, the first URR includes granular information for statistically analyzing the first data volume, specifically: business granularity, or the granularity of a first category of a business.

[0323] In one possible design, the communication unit 1303 is further configured to receive first update information, which is used to update the first forwarding action rule (FAR) and / or the first quality of service flow execution rule (QER) associated with the first PDR; the processing unit 1302 is further configured to update the first FAR and / or the first QER associated with the first PDR according to the first update information.

[0324] The communication device 1300 can be a network-side device in the above embodiments, such as an SMF network element or a communication module in an SMF network element, or a circuit or chip in an SMF network element that is responsible for communication functions.

[0325] For example, in one embodiment, the communication device 1300 is used to implement the SMF network element side function in the method shown in FIG9 of the above method embodiment. The communication unit 1303 is used to receive first request information, which requests an update to the downlink data mapping relationship of the user plane function network element; the communication unit 1303 is also used to send first information, which indicates or configures a first mapping relationship, which is associated with a first measurement result of the first quality of experience (QoE) of the first data. Optionally, the processing unit 1302 is used to generate the first information and / or process the received first request information.

[0326] In one possible design, the first request information comes from an artificial intelligence (AI) entity or a policy control function network element, which performs the measurement of the first QoE; or, the first request information comes from a terminal, which performs the measurement of the first QoE.

[0327] In one possible design, the first request information includes indication information of the first mapping relationship, and the processing unit 1302 is further configured to determine the first mapping relationship among multiple mapping relationships based on the indication information of the first mapping relationship.

[0328] In one possible design, the first request information includes indication information of the first measurement result of the first QoE of the first data. The processing unit 1302 is further configured to determine, among multiple mapping relationships, a first mapping relationship that is associated with the first measurement result, wherein any one of the multiple mapping relationships is associated with the measurement result of the first QoE.

[0329] In one possible design, the multiple mapping relationships are predefined, or generated based on policy information provided by the policy function network element. The communication unit 1303 is also used to receive the policy information corresponding to the multiple mapping relationships; the processing unit 1302 is also used to generate the multiple mapping relationships based on the policy information.

[0330] In one possible design, when the first information is used to indicate the first mapping relationship, the multiple mapping relationships are configured to the user plane function network element. The communication unit 1303 is also used to send the first configuration information, which is used to configure the multiple mapping relationships.

[0331] In one possible design, the first request information includes policy information related to the first measurement result of the first QoE of the first data, and the processing unit 1302 is further configured to generate the first mapping relationship based on the policy information.

[0332] In one possible design, the first mapping relationship includes: a mapping relationship between a first parameter and a first quality of service flow, wherein the first parameter includes at least the address information and / or port information of the data.

[0333] In one possible design, the first mapping relationship is included in the first packet detection rule (PDR), and the communication unit 1303 is also used to receive a first report, which includes indication information of a first data volume. The first data volume is determined according to the first usage reporting rule (URR) associated with the first PDR, and the first URR includes granular information for statistically analyzing the first data volume.

[0334] In one possible design, the first URR includes the granularity of the statistics of the first data volume, specifically: business granularity, or the granularity of the first category of a business.

[0335] In one possible design, the communication unit 1303 is further configured to send first update information when the first data volume meets the second condition. The first update information is used to update the first forwarding action rule FAR and / or the first quality of service flow execution rule QER associated with the first PDR.

[0336] It is understood that the division of units in the above-described device is merely a logical functional division. One function can correspond to one functional unit, or two or more functions can be integrated into one functional unit. In actual implementation, all or some units can be integrated onto a single physical entity, or distributed across different physical entities. Furthermore, the aforementioned functional units can be implemented in hardware, software, or a combination of both. Whether a function is executed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for specific applications, but such implementations should not be considered beyond the scope of this application.

[0337] In one example, the functional unit in any of the above devices may be one or more integrated circuits configured to implement the above methods, such as: one or more application-specific integrated circuits (ASICs), or one or more central processing units (CPUs), one or more microcontroller units (MCUs), one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0338] In one example, storage unit 1301 may include random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory and / or registers, etc.

[0339] Referring to Figure 14, which is a structural schematic diagram of a terminal 1400 provided in an embodiment of this application, the terminal 1400 corresponds to the terminal shown in Figure 1 and is used to implement the operation of the terminal in the above embodiments. As shown in Figure 14, the terminal includes: one or more antennas 1410, a radio frequency processing system 1420, and a processor system 1430.

[0340] In the downlink or sidelink direction, the RF processing system 1420 receives RF signals through the antenna 1410 and sends the RF-processed signals to the processor system 1430 for further processing. In the uplink or sidelink direction, the processor system 1430 processes the terminal-side information and sends it to the RF processing system 1420, which then processes the signal and transmits it through the antenna 1410.

[0341] In one example, the RF processing system 1420 serves as the communication interface for external communication of the terminal and may include an RF front end (RFFE) 1421 and an RF transceiver 1422. The RFFE 1421 is primarily used for one or more processing operations, such as shaping, passband selection, or gain adjustment, on the RF signals received by the antenna or those to be transmitted through the antenna. It may include one or more components such as RF switches, duplexers, filters, power amplifiers, antenna tuners, and low-noise amplifiers. The RFFE 1421 can be a circuit system composed of multiple discrete components or integrated into one or more chips. The RF transceiver 1422 processes the RF signals received by the RFFE into baseband / IF signals for further processing by the processor system 1430, and processes the baseband / IF signals provided by the processor system 1430 into RF signals for transmission to the RFFE 1421. The baseband / IF signals transmitted between the RF transceiver 1422 and the processor system 1430 can be digital or analog signals. The radio frequency transceiver 1422 can be implemented by one or more chips, which are commonly referred to as radio frequency chips (RFICs).

[0342] In one example, processor system 1430 may include one or more processors for processing signals and executing one or more communication protocols. Optionally, processor system 1430 may also include memory 1436. In one example, the one or more processors include at least one baseband processor 1431 (also known as a modem processor). Memory 1436 is used to store data and / or computer program instructions. Optionally, processor system 1430 may also include one or more application processors 1432 for implementing processing of the terminal operating system and application layer. Application processor 1432 may include, for example, a GPU, AI processor, or ASIC. Optionally, processor system 1430 may also include one or more of a voice subsystem 1433, a multimedia subsystem 1434, or an interface circuit 1435. The voice subsystem 1433 is used to process voice signals, the multimedia subsystem 1434 is used to handle multimedia-related operations, such as video encoding / decoding, image processing, etc., and the interface circuit 1435 is used to implement communication with other terminal components, such as a display 1440, an input device 1450, memory 1460, etc. The aforementioned components in the processor system 1430 can communicate with each other via a bus or communication interface circuit.

[0343] In one example, the processor system 1430 can be packaged as a single processor chip, such as a SoC chip or a SIP chip. In another example, the processor system 1430 can be a system composed of multiple chips; for example, the baseband processor 1431 can be packaged as a single chip, or packaged with part or all of the circuitry of the radio frequency processing system into a single chip.

[0344] In one example, memory 1436 can be on-chip memory, i.e., located on the processor system 1430 chip. In another example, memory 1460 can be off-chip memory, i.e. located outside the processor system 1430 chip.

[0345] In one example, the baseband processor 1431 may include one or more processor cores 14311 and interface circuitry 14314. The one or more processor cores 14311 are used to process signals and execute one or more communication protocols. Optionally, the baseband processor 1431 may also include a memory 14312 for storing at least a portion of the corresponding computer program instructions and / or data. In one example, the one or more processor cores 14311 execute the computer program instructions stored in the memory 14312 to implement the relevant operations in the above method embodiments (the terminal-side functions in the method shown in FIG. 5). In this disclosure, memory 14312 is used to store corresponding computer program instructions and / or data. This can mean that memory 14312 stores all corresponding computer program instructions and / or data for execution by processor core 14311; or it can mean that memory 14312 stores a portion of corresponding computer program instructions and / or data, including the computer program instructions and / or data currently required to be executed by processor core 14311. Memory 14312 can store different portions of computer program instructions and / or data multiple times for execution by processor core 14311 to implement the relevant operations in the above method embodiments. Interface circuit 14314 serves as a communication interface for communication with other components, such as transmitting signals with radio frequency processing system 1420, communicating with other subsystems and related components of processor system 1430 via bus, such as transmitting data control signals with application processor 1432, and transmitting data or computer program instructions with memory 1436 or memory 1460. Optionally, in order to reduce the load on the processor core, a baseband signal processing circuit 14313 can be set to perform at least some baseband signal processing, including one or more of signal demodulation, modulation, encoding or decoding.

[0346] In one example, the communication device provided in this application may be a terminal 1400, a communication module including a processor system 1430 and a radio frequency system 1420, or a baseband processor 1431.

[0347] The processor, processor system, application processor, baseband processor, processor circuit, or processor core mentioned above can be collectively referred to as a processor. The processor may include one or more of the following: central processing unit (CPU), digital signal processor (DSP), microprocessor unit (MPU), microcontroller unit (MCU), graphics processing unit (GPU), field programmable gate array (FPGA), application specific integrated circuit (ASIC), artificial intelligence processor (AI processor), or neural processing unit (NPU).

[0348] The aforementioned memory may include one or more of the following storage media: random access memory (RAM), static random access memory (SRAM), dynamic random access memory (DRAM), phase-change memory (PCM), resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), cache, register, read-only memory (ROM), flash memory, erasable programmable read-only memory (EPROM), hard disk, etc. In one example, computer program instructions for executing the above embodiments may be stored on non-volatile memory, such as at least a portion of the aforementioned memory 1460 (e.g., one or more of ROM, flash memory, EPROM, or hard disk). When the terminal is running, the corresponding computer program instructions may be partially or wholly loaded onto a memory with a faster transfer speed than the processor, such as at least a portion of memory 1436 and / or memory 14312 (e.g., one or more of RAM, SRAM, DRAM, PCM, RERAM, MRAM, FRAM, cache, or register), for the processor to execute in order to implement the steps in the above method embodiments.

[0349] In one example, the RF transceiver 1422 and the RF front-end 1421 can also be packaged in a single chip. In another example, the RF transceiver 1422, the RF front-end 1421, and the baseband processor 1431 can also be packaged in a single chip.

[0350] This application embodiment also provides a communication device, which includes a processor for implementing the functions of the terminal or network device (such as a UPF network element or an SMF network element) in the methods shown in Figures 5, 7, 9, 10, or 12. Optionally, the communication device further includes a memory, with the processor coupled to the memory. The processor is used to execute computer programs or instructions stored in the memory to implement the functions of the terminal or network device (such as a UPF network element or an SMF network element) in the methods shown in Figures 5, 7, 9, 10, or 12. Optionally, the communication device may be a chip or a chip system.

[0351] This application embodiment also provides a communication device, including a processor and an interface circuit. The interface circuit is used to receive signals from other devices outside the device and transmit them to the processor, or to send signals from the processor to other devices outside the device. The processor is used to implement the functions of the terminal or network device (such as UPF network element or SMF network element) in the methods shown in Figures 5, 7, 9, 10 or 12 through logic circuits or execution code instructions.

[0352] This application also provides a computer-readable storage medium storing instructions, which may also be referred to as computer programs, computer program code, etc. These instructions, when executed on a computer, cause the computer to perform the functions of the terminal or network device (such as a UPF network element or an SMF network element) in the methods shown in Figures 5, 7, 9, 10, or 12.

[0353] This application also provides a computer program product, including a computer program or instructions, which, when run on a computer, implement the functions of the terminal or network device (such as a UPF network element or an SMF network element) in the methods shown in Figures 5, 7, 9, 10 or 12.

[0354] It is understood that the processor in the embodiments of this application can be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof. A general-purpose processor can be a microprocessor or any conventional processor.

[0355] The memory in the embodiments of this application may be random access memory (RAM), flash memory, read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), register, hard disk, portable hard disk, CD-ROM, or any other form of storage medium known in the art.

[0356] The method steps in the embodiments of this application can be implemented in hardware or in software instructions executable by a processor. The software instructions can consist of corresponding software modules, which can be stored in random access memory, flash memory, read-only memory, programmable read-only memory, erasable programmable read-only memory, electrically erasable programmable read-only memory, registers, hard disks, portable hard disks, CD-ROMs, or any other form of storage medium well known in the art. An exemplary storage medium is coupled to a processor, enabling the processor to read information from and write information to the storage medium. The storage medium can also be a component of the processor. The processor and the storage medium can reside in an ASIC.

[0357] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any combination thereof. When implemented using software, it can be implemented entirely or partially in the form of a computer program product. This computer program product includes one or more computer programs or instructions. When the computer program or instructions are loaded and executed on a computer, the processes or functions of the embodiments of this application are performed, in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, an access network device, a user equipment, or other programmable device. The computer program or instructions can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer program or instructions can be transferred from one website, computer, server, or data center to another website, computer, server, or data center via wired or wireless means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center integrating one or more available media. The available medium can be a magnetic medium, such as a floppy disk, hard disk, or magnetic tape; it can also be an optical medium, such as a digital video optical disc; or it can be a semiconductor medium, such as a solid-state drive. The computer-readable storage medium may be a volatile or non-volatile storage medium, or may include both types of storage media.

[0358] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, etc.) containing computer-usable program code.

[0359] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in one or more blocks of the flowchart illustrations and / or one or more blocks of the block diagrams.

[0360] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and / or one or more block diagrams.

[0361] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide steps for implementing the functions specified in one or more flowcharts and / or one or more block diagrams.

[0362] In the various embodiments of this application, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of different embodiments are consistent and can be referenced by each other. The technical features of different embodiments can be combined to form new embodiments according to their inherent logical relationship.

Claims

1. A communication method, characterized in that, include: Obtain a first measurement result of the first experience quality (QoE), wherein the first QoE includes at least one of the following: inference accuracy, inference latency, inference throughput, training latency, training power consumption, or training convergence speed; Based on the first measurement result, the first data is mapped to the first quality of service stream, and there is a mapping relationship between the first measurement result and the first quality of service stream; The first data is sent via the first quality of service stream.

2. The method as described in claim 1, characterized in that, The first measurement result is indicated at least by the type information of the first QoE and the measurement result information of the first QoE.

3. The method as described in claim 2, characterized in that, The first measurement result is also indicated by the business information of the first data.

4. The method according to any one of claims 1 to 3, characterized in that, The acquisition of the first measurement result includes: Obtain the first measurement result from the first data; or, Based on the first QoE, the inference task and / or training task corresponding to the first data are measured to obtain the first measurement result; or... Receive first indication information, which is used to indicate the first measurement result.

5. The method according to any one of claims 1 to 4, characterized in that, Also includes: Receive first configuration information, which is used to configure the mapping relationship between the first measurement result and the first quality of service flow.

6. The method according to any one of claims 1 to 5, characterized in that, The mapping relationship between the first measurement result and the first quality of service flow is included in the first packet detection rule (PDR). The first PDR is associated with the first usage reporting rule (URR) and also includes: Send a first report indicating a first data volume of the first data, the first data volume being determined based on the first URR, the first URR being used to indicate the granularity of the statistical calculation of the first data volume.

7. The method as described in claim 6, characterized in that, The granularity of the first data volume is: business granularity.

8. The method as described in claim 6 or 7, characterized in that, After sending the first report, the following is also included: Receive the first update information; Based on the first update information, update the first forwarding action rule FAR and / or the first quality of service flow execution rule QER associated with the first PDR.

9. A communication device, characterized in that, Includes units for implementing the method as described in any one of claims 1 to 8.

10. A communication device, characterized in that, Includes a processor configured to cause the communication device to perform the method as described in any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores instructions that, when executed, perform the method as described in any one of claims 1 to 8.

12. A computer program product, characterized in that, The computer program product includes instructions that, when executed, perform the method as described in any one of claims 1 to 8.

Images