Network architecture and method for providing quality of service assurance

Abstract

The present application provides a network architecture and a method for providing quality of service (QoS) assurance, and facilitates ensuring the task-level quality of service of agents. The network architecture comprises: a task function network element, which is used for splitting a task of an agent into a plurality of subtasks, and splitting data carrying the subtasks to form one or more data packets, and is further used for providing QoS assurance for the one or more data packets carrying the subtasks.

Description

Network architecture and method for providing quality of service guarantee

[0001] The present application claims priority to the Chinese patent application No. 202410856090.8, filed on June 27, 2024, and entitled "Network architecture and method for providing quality of service guarantee", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the field of communication, and in particular to a network architecture and a method for providing quality of service guarantee. BACKGROUND

[0003] With the continuous development of communication technology, various types of intelligent agents are emerging, such as robots, autonomous vehicles, intelligent devices, artificial intelligence (AI) phones, AI assistant devices, software agents, etc. Intelligent agent services have higher requirements for rate, latency and reliability, and future communication networks need to support lower transmission latency, more reliable communication transmission and higher throughput.

[0004] In the application scenario of intelligent agents, the services of intelligent agents are task-level, or in other words, are task-granularity. Intelligent agents can perform single tasks or complex multi-step tasks, for example, the tasks of an autonomous vehicle can include environment perception, path planning, vehicle control, etc.

[0005] For intelligent agent scenarios, how to guarantee the quality of service (QoS) of task-level is a problem that needs to be solved. SUMMARY

[0006] The present application provides a network architecture and a method for providing quality of service guarantee, which is beneficial to guarantee the quality of service of task-level of intelligent agents.

[0007] In a first aspect, a network architecture is provided, which includes a task function unit configured to split a task of an intelligent agent into a plurality of sub-tasks, and split data carrying the sub-tasks into one or more data packets; the task function unit is further configured to provide QoS guarantee for one or more data packets of the sub-tasks.

[0008] The present application defines a task function unit for task-level services of intelligent agents on the basis of existing network protocol architecture, which can provide QoS guarantee for data packet transmission carrying tasks with task granularity, and support end-to-end implementation for task-level services of intelligent agents.

[0009] In some implementations of the first aspect, the task function unit includes a first function unit and a second function unit. The first function unit is configured to split the task of the agent into a plurality of sub-tasks, and split data carrying the sub-tasks into one or more data packets. The second function unit is configured to provide QoS guarantee for the one or more data packets of the sub-tasks.

[0010] The first function unit can be deployed in a control plane of the core network, and the second function unit can be deployed in a user plane of the core network.

[0011] In some implementations of the first aspect, the first function unit is further configured to maintain and control an execution accuracy and / or a task response time of the sub-tasks.

[0012] In some implementations of the first aspect, the QoS parameter of the data packet carrying the sub-tasks includes one or more of a delay, a jitter, a reliability, an execution accuracy, or a task response time.

[0013] In some implementations of the first aspect, the QoS parameter further includes a label of the sub-tasks and a label of the data packet carrying the sub-tasks.

[0014] In some implementations of the first aspect, the network architecture further includes a centralized unit (CU) configured to interact the QoS parameter with the task function unit.

[0015] In some implementations of the first aspect, the CU includes a third function unit configured to interact the QoS parameter with the task function unit and a distributed unit (DU).

[0016] In some implementations of the first aspect, the CU includes a CU-control plane (CU-CP) and a CU-user plane (CU-UP). The CU-CP is configured to interact the QoS parameter with the first function unit, and the CU-UP is configured to interact the QoS parameter with the second function unit.

[0017] In a second aspect, a method for providing quality of service guarantee is provided. The method can be performed by a communication device, which can be a task function unit, a component (e.g., a processor, a chip, or a chip system) configured in the task function unit, or a logic module or software capable of implementing all or part of the functions of the task function unit, without limitation. The method is described below with the task function unit as an example.

[0018] The method comprises: splitting a task of an agent into a plurality of sub-tasks; splitting data carrying the sub-tasks into one or more data packets; and providing QoS guarantee for the one or more data packets of the sub-tasks.

[0019] With reference to the second aspect, in some implementations of the second aspect, the QoS parameter of the data packet carrying the sub-task comprises one or more of: a time delay, a jitter, a reliability, an execution accuracy, or a task response time.

[0020] With reference to the second aspect, in some implementations of the second aspect, the QoS parameter further comprises: a label of the sub-task and a label of the data packet carrying the sub-task.

[0021] It should be understood that the second aspect of the present application corresponds to the technical solution of the first aspect of the present application, and the beneficial effects achieved by each aspect and the corresponding feasible implementation manners are similar, which will not be repeated.

[0022] In a third aspect, a communication apparatus is provided, which comprises: means for performing the method in any possible implementation manner of the second aspect. Specifically, the apparatus comprises means for performing the method in any possible implementation manner of the second aspect.

[0023] In one design, the apparatus can comprise a module corresponding to each of the methods / operations / steps / actions described in the second aspect, which can be a hardware circuit, or software, or a combination of hardware circuit and software.

[0024] In another design, the apparatus is a communication chip, which can comprise an input circuit or interface for sending information or data, and an output circuit or interface for receiving information or data.

[0025] In another design, the apparatus is a task function unit, which can comprise a transmitter for sending information or data, and a receiver for receiving information or data.

[0026] In another design, the apparatus is configured to perform the method in any possible implementation manner of the second aspect, and the apparatus can be configured in a task function unit.

[0027] In a fourth aspect, a communication apparatus is provided, which comprises: at least one processor configured to invoke and run a computer program from a memory, so that the apparatus performs the method in any possible implementation manner of the second aspect.

[0028] Optionally, the apparatus further includes a memory that can be used to store instructions and data. The memory is coupled to the processor, and the processor implements the method described in the second aspect above when executing the instructions stored in the memory.

[0029] Optionally, the apparatus further includes a transmitter (transmitter) and a receiver (receiver), which can be separate or integrated together, referred to as a transceiver (transceiver).

[0030] In a fifth aspect, a computer program product is provided, which includes a computer program (also referred to as code or instructions), which, when executed, causes a computer to execute the method in any possible implementation manner of the second aspect above.

[0031] In a sixth aspect, a computer-readable storage medium is provided, which stores a computer program (also referred to as code or instructions), which, when executed on a computer, causes the computer to execute the method in any possible implementation manner of the second aspect above.

[0032] In a seventh aspect, the present application provides a chip system, which includes at least one processor for supporting the implementation of the functions involved in any possible implementation manner of the second aspect above, such as receiving or processing the data involved in the above method, etc.

[0033] In a possible design, the chip system further includes a memory for saving program instructions and data, which is located in or outside the processor.

[0034] Optionally, the chip system can be composed of a chip, or include a chip and other discrete devices. BRIEF DESCRIPTION OF DRAWINGS

[0035] FIG. 1 is a schematic diagram of a communication system suitable for embodiments of the present application;

[0036] FIG. 2 is a schematic diagram of a network architecture of a 5G system;

[0037] FIG. 3 is a schematic diagram of a network architecture of a voice VMOS;

[0038] FIG. 4 is a schematic diagram of a C-V2X;

[0039] FIG. 5 is a schematic diagram of uploading data by an AI mobile phone;

[0040] FIG. 6 is a schematic diagram of a business process of an AI intelligent assistant;

[0041] FIG. 7 is a schematic diagram of a network architecture provided by embodiments of the present application;

[0042] FIG. 8 is a schematic diagram of another network architecture according to an embodiment of the present application;

[0043] FIG. 9 is a schematic diagram of still another network architecture according to an embodiment of the present application;

[0044] FIG. 10 is a schematic diagram of yet another network architecture according to an embodiment of the present application;

[0045] FIG. 11 is a schematic diagram of the functional division of network elements and protocol layers of an O-RAN system according to an embodiment of the present application;

[0046] FIG. 12 is a schematic diagram of the functional division of network elements and protocol layers of another O-RAN system according to an embodiment of the present application;

[0047] FIG. 13 is a schematic flowchart of a method for providing quality of service assurance according to an embodiment of the present application;

[0048] FIGS. 14 and 15 are schematic block diagrams of a communication device according to an embodiment of the present application. DETAILED DESCRIPTION

[0049] The technical solutions in the present application will be described below with reference to the accompanying drawings.

[0050] Before introducing the network architecture and the method for providing quality of service assurance according to the embodiments of the present application, the following points will be explained first.

[0051] First, in the embodiments shown below, the terms and English abbreviations, such as TFU, TCFU, task function unit, QoS parameter, etc., are all exemplary examples given for the convenience of description, and should not constitute any limitation on the present application. The present application does not exclude the possibility of defining other terms capable of achieving the same or similar functions in the existing or future protocols.

[0052] Second, in the embodiments shown below, the first, second and various numerical numbers are only used for the convenience of description, and do not limit the scope of the embodiments of the present application.

[0053] Third, "at least one" means one or more, "multiple" means two or more. "And / or" describes the association relationship of associated objects, which means that there can be three relationships, for example, A and / or B can represent: A exists alone, A and B exist together, and B exists alone, where A and B can be singular or plural. The character " / " generally represents that the associated objects before and after are in an "or" relationship. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b and c can represent: a, or b, or c, or a and b, or a and c, or b and c, or a, b and c, where a, b and c can be single or multiple.

[0054] Figure 1 is a schematic diagram of a communication system suitable for embodiments of the present application. The communication system 1000 shown in Figure 1 includes a radio access network (RAN) 100 and a core network (CN) 200. Optionally, the communication system 1000 also includes the Internet 300. The radio access network 100 can include at least one RAN node (e.g., 110a and 110b in Figure 1), and can also include at least one terminal (e.g., 120a-120j in Figure 1). The terminal is connected to the RAN node in a wireless manner, and the RAN node is connected to the core network 200 in a wireless or wired manner. The core network device and the RAN node can be independent and different physical devices, or the functions of the core network device and the logical functions of the RAN node can be integrated on the same physical device, or a physical device can integrate part of the functions of the core network device and part of the functions of the RAN node. The terminal and the terminal, and the RAN node and the RAN node can be connected to each other in a wired or wireless manner. Figure 1 is only a schematic diagram, and the communication system can also include other RAN nodes, such as wireless relay devices and wireless backhaul devices, which are not shown in Figure 1.

[0055] The wireless access network 100 can be a 3rd generation partnership project (3GPP) related cellular system, for example, a 4th generation mobile communication technology (4G) system (also referred to as a long term evolution (LTE) system), a 5th generation mobile communication technology (5G) system (also referred to as a new radio (NR) system), or can also be applied to future communication systems or other similar communication systems, which are not limited in the present application.

[0056] The wireless access network 100 can also be an open-RAN (O-RAN or ORAN), a cloud radio access network (CRAN). The wireless access network 100 can also be a non-terrestrial network (NTN), a satellite communication network, a high altitude platform station (HAPS) communication network, an integrated access and backhaul (IAB) communication network, a reconfigurable intelligent surface (RIS) communication network, etc. The wireless access network 100 can also be a communication system that combines two or more of the above systems.

[0057] The RAN node can also be referred to as a RAN device or an access network device. The RAN node is used to help the terminal to realize wireless access. The plurality of RAN nodes in the communication system 1000 can be nodes of the same type or nodes of different types.

[0058] The RAN node provided by the embodiments of the present application can be a base station, a Node B, an evolved Node B (eNodeB or eNB), a transmission reception point (TRP), a next generation Node B (gNB) in 5G or NR, a RAN node in open radio access network (O-RAN or open RAN), a next generation base station in the 6th generation mobile communication technology (6G). Alternatively, the RAN node can also be a satellite base station in a non-terrestrial network (NTN) communication network, or a base station in a future mobile communication system, or an access node in a wireless fidelity (Wi-Fi) system, etc. Alternatively, the RAN node can also be a module or unit that completes part of the function of the base station, for example, can be a CU, a DU, the function of the CU can be implemented by one entity, or can be implemented by different entities. For example, the function of the CU can be further divided, for example, the control plane and the user plane are separated, that is, the control plane of the CU (CU-CP) and the user plane of the CU (CU-UP). The RAN node can be a macro base station, the RAN node can also be a micro base station or an indoor station, can also be a relay node or a host node, etc. The specific technology and specific equipment form of the RAN node are not limited in the present application.

[0059] A terminal is a device with wireless transceiver function, which can send signals to a RAN node or receive signals from a RAN node. A terminal can also be referred to as a terminal device, a terminal equipment, a user equipment (UE), a mobile station, a mobile terminal, etc. A terminal can be widely applied in various scenarios, such as enhanced mobile broadband (eMBB), ultra-reliable low-latency communication (URLLC), massive machine-type communications (mMTC), device-to-device (D2D), vehicle to everything (V2X) communication, machine-type communication (MTC), internet of things (IOT), virtual reality, augmented reality, industrial control, automatic driving, remote medical treatment, smart grid, smart furniture, smart office, smart wear, smart transportation, smart city, etc. A terminal can be specifically a mobile phone, a tablet computer, a computer with wireless transceiver function, a wearable device, a vehicle, an airplane, a ship, a robot, a mechanical arm, a smart home device, etc. Embodiments of the present application do not limit specific technologies and specific device forms adopted by a terminal.

[0060] A RAN node and a terminal can be fixed in position or movable. A RAN node and a terminal can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; can be deployed on water surface; can also be deployed on an airplane, a balloon and a man-made satellite. Embodiments of the present application do not limit application scenarios of a RAN node and a terminal.

[0061] The roles of a RAN node and a terminal can be relative. For example, the helicopter or the drone 120i in FIG. 1 can be configured to move a RAN node, which is a RAN node for those terminals 120j accessing to the wireless access network 100 through 120i; but for the RAN node 110a, 120i is a terminal, i.e. 110a communicates with 120i through a wireless air interface protocol. Of course, 110a and 120i can also communicate through an interface protocol between RAN nodes, in which case, 120i is also a RAN node relative to 110a. Therefore, a RAN node and a terminal can be collectively referred to as a communication device, 110a and 110b in FIG. 1 can be referred to as a communication device with RAN node function, and 120a-120j in FIG. 1 can be referred to as a communication device with terminal function.

[0062] The communication between the RAN node and the terminal, between the RAN nodes, between the terminals can be through the licensed spectrum, or through the unlicensed spectrum, or through the licensed spectrum and the unlicensed spectrum at the same time; the communication can be through the spectrum below 6 gigahertz (GHz), or through the spectrum above 6 GHz, or through the spectrum below 6 GHz and the spectrum above 6 GHz at the same time. The embodiments of the present application do not limit the spectrum resources used by the wireless communication.

[0063] In the embodiments of the present application, the functions of the RAN node can also be performed by a module (such as a chip) in the RAN node, or by a control subsystem containing RAN node functions. The control subsystem containing RAN node functions herein can be a control center in the above-mentioned application scenarios such as smart grid, industrial control, intelligent transportation, and smart city. The functions of the terminal can also be performed by a module (such as a chip or a modem) in the terminal, or by a device containing terminal functions.

[0064] The core network device refers to a device in the core network that provides service support for the terminal. At present, some examples of the core network device are: access and mobility management function (AMF) network element, session management function (SMF) network element, user plane function (UPF) network element, and the like, which are not listed one by one here.

[0065] The related technologies and concepts involved in the present application are introduced as follows.

[0066] 1, Core network (CN) network protocol architecture of the 5G system

[0067] To cope with the challenge of wireless broadband technology, keep the leading advantage of 3GPP network, the 3GPP standard group formulates the next generation mobile communication network architecture (Next Generation System) at the end of 2016, called 5G network architecture. This architecture not only supports the wireless technology (such as LTE, NR, etc.) defined by the 3GPP standard group to access the core network side, but also supports non-3GPP (non-3GPP) access technology to access the core network side through non-3GPP interworking function (N3IWF) or next generation packet data gateway (ngPDG). Among them, the core network function is divided into user plane network element function (such as UPF) and control plane network element function. The user plane network element function is mainly responsible for the forwarding of packet data, QoS control, charging information statistics, etc. The control plane network element function is mainly responsible for user registration and authentication, mobility management, and issuing data packet forwarding strategy and QoS control strategy to the user plane.

[0068] Referring to the 5G network architecture shown in FIG. 2, the network functions and entities shown include: UE, RAN, UPF, AMF, SMF, data network (DN). It should be noted that in some embodiments, more or less network functions and entities than those shown in FIG. 2 can also be included, which are not limited herein. For example, the network architecture optionally includes unified data management (UDM), network exposure function (NEF), policy control function (PCF), network repository function (NRF), network slice selection function (NSSF), authentication server function (AUSF), network data analysis function (NWDAF).

[0069] The names of the network functions and entities shown in this application are all exemplary examples given for convenience of description, and should not constitute any limitation on this application. This application does not exclude the possibility of defining other terms that can achieve the same or similar functions in existing or future protocols.

[0070] The UE, RAN, UPF and DN in FIG. 2 are generally referred to as user plane (or data plane) network functions and entities, through which user data traffic can be transmitted between the UE and the DN via a protocol data unit (PDU) session established between the UE and the DN, and the transmission can pass through the RAN node and the UPF, which can be considered as a user plane network element of the core network. Other network elements are referred to as control plane network functions and entities (or control plane network elements), which are mainly responsible for functions such as authentication and authorization, registration management, session management, mobility management and policy control, so as to realize reliable and stable transmission of user layer traffic. Among them, the user plane is used to carry service data, and the control plane is used to carry signaling messages.

[0071] The interaction relationship between the network functions and entities and the corresponding interfaces are shown in FIG. 2. For example, the UE and the AMF can interact through the N1 interface, and the interaction message is referred to as an N1 message. Some interfaces are implemented in the form of a service interface.

[0072] The AMF is a network element, module or component that provides access management functions, and is mainly responsible for signaling processing, such as access control, mobility management, attachment and detachment, gateway selection and the like. When the AMF network element provides services for a session in the terminal, it provides storage resources for the control plane of the session to store the identifier of the session, the identifier of the SMF associated with the identifier of the session and the like.

[0073] The SMF is a network element, module or component responsible for processing user traffic, such as user plane function selection, user plane function redirection, internet protocol (IP) address allocation, establishment, modification and release of bearers for QoS control.

[0074] The UPF is responsible for forwarding and receiving user data in the terminal. The UPF can receive user data from the DN and transmit it to the UE through the RAN node; the UPF can also receive user data from the UE through the RAN node and forward it to the DN. The transmission resources and scheduling functions provided by the UPF for the UE are managed and controlled by the SMF network element.

[0075] The AUSF is responsible for authenticating user equipment and determining the legitimacy of the user equipment.

[0076] The UDM is used to store the subscription data of the user equipment.

[0077] The PCF is used to issue service-related policies to the AMF or the SMF.

[0078] The AF is used to send application-related requirements to the PCF, so that the PCF generates corresponding policies.

[0079] The DN is used to provide services for the user, such as providing mobile operator services, Internet services, or third-party services.

[0080] 2. Voice over LTE (VoLTE) network protocol architecture

[0081] Referring to the VoLTE network protocol architecture shown in FIG. 3, the core network is divided into two parts, including an evolved packet core (EPC) and an IP multimedia subsystem (IMS). The EPC is used to process data services in 4G mobile voice services, and provides a channel between a terminal and a packet data network gateway (PGW) for voice service-related signaling and media.

[0082] The EPC side network elements include, but are not limited to, a mobility management entity (MME), a serving gateway (SGW) or a PGW, and a policy and charging rules function (PCRF).

[0083] The SGW and the PGW are usually the same physical entity, and are similar to a media gateway (MGW) in function. The SGW is used to converge traffic transmitted from a base station. The PGW is used to interface with the IMS (for example, with an application server of the IMS). After the terminal sends voice-related information to the PGW, the PGW sends the voice-related information to the IMS. The SGW is an interface of the EPC connecting the IMS (signaling / media to the IMS must pass through the PGW).

[0084] The PCRF is used to cooperate with the SGW / PGW to establish a channel between the terminal and the PGW. As described above, the network elements of the EPC are used to process data services, and the voice service also passes through the channel of the data service. The PCRF is used to ensure that the channel meets the requirements of the voice service, and controls parameters such as jitter, delay, and packet loss rate of the channel from the terminal to the PGW.

[0085] The network elements on the IMS side include, but are not limited to, a home subscriber server (HSS), an application server (AS), a call session control function (CSCF), and a session border controller (SBC).

[0086] The HSS functions similarly to a home location register (HLR) and is used to store user information and find a called party. The AS is responsible for providing voice services such as caller ID, call forwarding, and other services. The CSCF functions similarly to a mobile switching center-server (MSC-server) and is also responsible for triggering voice services to the AS and finding a called party to the HSS. The SBC is used to isolate the network elements of the access network and the IMS core network (both signaling and media need to pass through the SBC) and is an entrance for the PGW to the IMS.

[0087] 3. Cellular vehicle to everything (C-V2X)

[0088] C-V2X is a V2X communication technology developed based on a cellular system, which utilizes and enhances the current cellular network functions and elements to achieve low-latency and high-reliability communication between various nodes in a vehicle network. As shown in FIG. 4, C-V2X includes vehicle to vehicle (V2V) communication, vehicle to pedestrian (V2P) communication, vehicle to infrastructure (V2I) communication, and vehicle to network (V2N) communication.

[0089] As the cellular system evolves from a 4G system (also referred to as an LTE system) to a 5G system (also referred to as an NR system), C-V2X evolves from LTE-V2X to NR-V2X. NR-V2X can support lower transmission latency, more reliable communication transmission, higher throughput, better user experience, and meet the needs of a wider range of application scenarios. Further, the vehicle-to-vehicle communication technology supported by V2X can be extended to D2D in a task system.

[0090] At present, mobile phones configured with an end-side large model (for example, an AI mobile phone) are increasingly favored by the market. Many terminal manufacturers have launched mobile phones featuring AI large models, which can support functions such as an AI generated content (AIGC) picture assistant, generative editing, real-time translation during a call, a health assistant, and a snapshot function.

[0091] FIG. 5 is a schematic diagram of uploading data by an AI mobile phone. Referring to FIG. 5, the AI mobile phone uploads training data of 1 gigabyte (GB) per month to the cloud, and the training data includes but is not limited to state information, system data, picture data, and video data. The cloud can perform inference according to the training data uploaded by the AI mobile phone and send relevant feedback to the AI mobile phone, for example, rendered pictures and videos.

[0092] FIG. 6 is a schematic diagram of a business process of an AI intelligent assistant. Referring to FIG. 6, a terminal (for example, an AI mobile phone) has a microphone and / or a camera, which can collect voice data, image data, and video data, and interact with the cloud in text, language, image, and video. The cloud includes an AI large model platform, which can identify and process text, language, image, and video.

[0093] It can be seen that future intelligent agent (for example, a robot, an autonomous vehicle, a smart device, an AI mobile phone, an AI assistant device, and a software agent) services, for example, vehicle networking services, vehicle entertainment services, and AI mobile phone uploading services, have higher requirements for rate, latency, and reliability, and future communication networks need to support lower transmission latency, more reliable communication transmission, and higher throughput.

[0094] In the application scenario of an intelligent agent, the service of the intelligent agent is task-level or task-granularity, which can be referred to as task-level service. The intelligent agent can perform a single task or a complex multi-step task. For example, a task of an autonomous vehicle can include environment perception, path planning, and vehicle control.

[0095] The network architecture described above is for packet data and voice services, and the definition of the network architecture does not support service guarantee for task-level packets of intelligent agents. Therefore, how to guarantee the task-level QoS of intelligent agents is a problem that needs to be solved.

[0096] Therefore, an embodiment of the present application provides a network architecture, which can be regarded as an improvement on the existing 5G network architecture. Specifically, a task function unit (TFU) is added to the existing 5G network architecture, which can guarantee the QoS of the task-level service of the intelligent agent and support end-to-end implementation of the task-level service of the intelligent agent.

[0097] FIG. 7 is a schematic diagram of a network architecture according to an embodiment of the present application. Referring to FIG. 7, the network architecture includes a TFU, which is located in the control plane of the core network. The TFU is configured to split a task of an agent into a plurality of sub-tasks, and split data of a bearing sub-task into one or more data packets. The TFU is further configured to provide QoS guarantee for the one or more data packets of the sub-task. If the task does not need to be split, the TFU is configured to provide QoS guarantee for the one or more data packets of the task of the agent.

[0098] It should be understood that the traffic of the agent is in the granularity of a task, which is referred to as task-level traffic.

[0099] The task performed by the agent can be a specific task or a series of tasks performed by the agent. The task can be a simple single task or a complex multi-step task. For a single task, the TFU does not need to split it. The agent performing the task usually needs the support of network resources, including data transmission resource allocation, computing resources, etc.

[0100] Exemplarily, the task of the agent can include, but is not limited to, the following types:

[0101] 1. Data processing task: for example, image recognition, speech recognition, natural language processing, etc.

[0102] 2. Control task: for example, robot control, automatic driving control, unmanned aerial vehicle flight control, etc.

[0103] 3. Communication task: for example, data packet transmission, information exchange, real-time communication, etc.

[0104] 4. Decision-making task: for example, path planning, strategy selection, dynamic adjustment, etc.

[0105] Among them, the robot control is, for example, controlling the robot to perform public service tasks such as traffic management, environmental monitoring, and rescue tasks, or controlling the robot to perform service tasks such as meal delivery, luggage transportation, and room cleaning. The robot can also perform more other tasks, which are not listed here.

[0106] The following illustrates the splitting of a complex task.

[0107] In an example, the agent is a robot, and the task of the agent is a rescue task, which can be split into:

[0108] Sub-task 1: environmental perception, for example, obtaining data of the surrounding environment through a camera and a sensor.

[0109] Sub-task 2: personnel search and rescue, for example, performing real-time processing on the environmental data to identify personnel.

[0110] Subtask 3: Mark the location, for example, mark and record the location of the discovered personnel and dangerous areas.

[0111] Further, the TFU can split the data of a subtask into one or more data packets. Each subtask can be a single task consisting of a single data packet or a single task consisting of multiple data packets, depending on the size of the data of the subtask.

[0112] For example, subtask 1 is a single task consisting of a single data packet, and subtask 2 is a single task consisting of multiple data packets.

[0113] Alternatively, for a simple task, the single task can be a single task consisting of a single data packet or a single task consisting of multiple data packets.

[0114] Each data packet carrying a subtask has its corresponding label. For example, for a single task, its label is "0", and one or more data packets of the task carry the label of the task, which can identify that the one or more data packets belong to the same task, and the TFU can provide the same QoS guarantee for the one or more data packets. When the agent executes the next task, its label flips to "1", and when the agent executes the next task, its label flips to "0" again.

[0115] For example, for a complex task split into two subtasks, the label of the complex task is "0", the label of subtask 1 is "0", and the label of subtask 2 is "1", and one or more data packets of each subtask carry the label of the complex task and the label of the subtask, for example, the data packets of subtask 1 carry the task label "00", and the data packets of subtask 2 carry the label "01". The TFU can provide the same QoS guarantee for different subtasks, or the QoS guarantees for different subtasks are different, which is not limited by the embodiments of the application.

[0116] Optionally, the data packet carrying a task or a subtask can also carry label information such as the serial number of the data packet, the total number of data packets, etc.

[0117] Optionally, the network architecture shown in FIG. 7 further includes an AF corresponding to the TFU, which is used for the TFU to connect the application service on the network side.

[0118] In combination with the above FIG. 7, the application adds a TFU on the basis of the existing network architecture, provides QoS guarantee for the data packet transmission of the task-level service of the agent through the IP bearer network, and supports end-to-end implementation of the task-level service of the agent.

[0119] In another embodiment, the above TFU can be split into two different functional units, responsible for different functions.

[0120] FIG. 8 is a schematic diagram of another network architecture according to an embodiment of the present application. Referring to FIG. 8, the task function unit includes a first functional unit and a second functional unit. The first functional unit is configured to split a task of an intelligent agent into a plurality of sub-tasks, and split data carrying the sub-tasks into one or more data packets. The second functional unit is configured to provide QoS guarantee for the one or more data packets of the sub-tasks.

[0121] The first functional unit can be referred to as a task control function unit (TCFU), and the second functional unit can be referred to as a TFU. It should be understood that the TFU shown in FIG. 8 is different from the TFU shown in FIG. 7, and the TFU shown in FIG. 8 has part of the functions of the TFU shown in FIG. 7.

[0122] The TCFU and the TFU in FIG. 8 will be described below.

[0123] The TCFU can be arranged at the control plane of the core network, for example, the TCFU is a logical functional unit of the AMF. The TFU can be arranged at the user plane of the core network, for example, the TFU is a logical functional unit of the UPF.

[0124] Optionally, the TCFU further includes a new definition of a management function for execution of the task of the intelligent agent, for example, the TCFU is further configured to maintain and control the execution accuracy and / or response time of the sub-tasks of the intelligent agent.

[0125] The TFU is configured to provide QoS guarantee for the one or more data packets of the task or the sub-task, wherein the QoS parameters of the data packets carrying the task or the sub-task include one or more of the following: latency, jitter, reliability, execution accuracy, or task response time.

[0126] For example, the TFU specifies that the latency from the intelligent agent to the cloud is 100 ms, that is, the maximum transmission latency from the intelligent agent to the cloud for a task or a sub-task of the intelligent agent is 100 ms.

[0127] Optionally, the QoS parameters further include a label of the task or the sub-task and a label of the data packets carrying the task or the sub-task. For example, the TFU interacts with the CU of the RAN to exchange the labels of the plurality of data packets of the sub-task, indicating that the same QoS guarantee is required for the plurality of data packets.

[0128] It should be understood that the QoS parameters described in the embodiments of the present application are task-level QoS parameters, which are used to guarantee the service quality of transmission of the data packets carrying the task or the sub-task.

[0129] As an implementation, the RAN in the network architecture shown in FIG. 7 or FIG. 8 can be a centralized RAN, including a CU, and the TFU can interact with the CU for the QoS parameters.

[0130] Optionally, the CU includes a third functional unit, for example, referred to as CU-t. Referring to FIG. 9, the TFU interacts with the CU for the QoS parameters, including that the TFU interacts with the CU-t for the QoS parameters. It should be understood that the CU-t is an optional functional unit in the CU, and the embodiments of the present application do not limit whether the CU includes the CU-t.

[0131] As another implementation, the RAN in the network architecture shown in FIG. 7 or FIG. 8 can be an O-RAN, including a CU and a DU, and the CU is configured to interact with the TFU and the DU for the QoS parameters. The CU includes a CU-UP and a CU-CP. Referring to FIG. 10, the CU-CP interacts with the CU-UP for the QoS parameters. Optionally, the CU further includes a CU-t, and the CU-t is configured to interact with the TFU for the QoS parameters.

[0132] The CU and the DU are deployed with different protocol layers. Referring to FIG. 11, as an implementation, the CU is deployed with a radio resource control (RRC) layer, a packet data convergence protocol (PDCP) layer, and a service data adaptation protocol (SDAP) layer in a protocol stack. The DU is deployed with a radio link control (RLC) layer, a media access control (MAC) layer, and a physical layer (PHY) in a protocol stack, and the physical layer can further include a high layer of the physical layer (PHY-high) and a low layer of the physical layer (PHY-low). Thus, the CU has processing capabilities of the RRC, the PDCP, and the SDAP, and the DU has processing capabilities of the RLC, the MAC, and the PHY.

[0133] As can be seen from FIG. 11, the CU and the DU are deployed with different protocol layers, and in order to maintain data transmission between layers, the TFU can interact with the CU for the QoS parameters of the task-level service of the agent, and the CU can interact with the DU for the QoS parameters of the task-level service of the agent.

[0134] In the case of CU separation (i.e., split into CU-CP and CU-UP), referring to FIG. 12, as an implementation manner, the CU-CP is deployed with the control plane part of the RRC layer and the PDCP layer (referred to as PDCP-C), the CU-UP is deployed with the user plane part of the SDAP layer and the PDCP layer (referred to as PDCP-U), and the DU is deployed with the RLC layer, the MAC layer, and the PHY layer. The CU-CP can interact with a network element in the core network for implementing control plane functions. The network element in the core network for implementing control plane functions can be an access and mobility function network element, such as an AMF network element in the 5G system. The CU-UP can interact with a network element in the core network for implementing user plane functions. The network element in the core network for implementing user plane functions is, for example, a UPF network element in the 5G system.

[0135] As can be seen from FIG. 12, the CU-CP, the CU-UP, and the DU are deployed with different protocol layers, in order to maintain data transmission between layers, the functions of the CU-CP and the CU-UP are designed to indicate the QoS parameters of the task-level service of the CU-CP and the CU-UP interacting with each other. The TFU can interact with the CU to obtain the QoS parameters of the task-level service of the intelligent agent, and the CU can interact with the DU to obtain the QoS parameters of the task-level service of the intelligent agent.

[0136] The above-mentioned interaction QoS parameters include, for example, the label of the task or the label of the subtask, the label of the data packet carrying the subtask, the QoS flow requirement (including delay, jitter, reliability, etc.) of a single data packet constituting a single task, the QoS requirement of a plurality of data packets constituting a single task, and the like.

[0137] In summary, the embodiment of the present application provides a method for guaranteeing service quality. FIG. 13 is a schematic diagram of a method 1300 for providing service quality guarantee provided by the embodiment of the present application. The method can be performed by a task function unit (for example, the TFU shown in FIG. 7). The method 1300 includes S1301 and S1302, and the specific steps are as follows:

[0138] S1301, splitting a task of an intelligent agent into a plurality of subtasks, and splitting data carrying the subtasks into one or more data packets.

[0139] For example, the intelligent agent initiates a request for a task-level service, for example, a request for an image recognition task, a request for an intelligent driving control task, etc.

[0140] After receiving the request, the task function unit can split the task to obtain a plurality of subtasks, which is beneficial to split a complex task into simple subtasks and is beneficial to task implementation.

[0141] The target end of the request can be a cloud (server). After receiving the request, the cloud (server) generates response data for the request and sends the response data to the task function unit. The task function unit divides the response data according to subtasks to obtain one or more data packets corresponding to each subtask.

[0142] S1302, providing QoS guarantee for one or more data packets of the subtask.

[0143] The task function unit provides QoS guarantee for one or more data packets of each subtask to meet the QoS requirement of data packet transmission of the subtask. For example, appropriate wireless resources are allocated for the task-level service of the agent, and corresponding QoS level, priority, bandwidth, etc. are configured.

[0144] During the process of the task-level service of the agent, the task function unit can dynamically adjust the QoS parameter according to the real-time network condition and service requirement. For example, when the network is congested, the QoS level of some low-priority service can be appropriately reduced, and the QoS level of the task-level service of the agent is increased to guarantee the QoS of the task-level service of the agent.

[0145] It can be understood that, in order to implement the functions in the above embodiments, the task function unit includes hardware structures and / or software modules corresponding to the functions. Those skilled in the art should easily realize that, in combination with the units and method steps of the examples described in the embodiments disclosed in the present application, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function is implemented in hardware or computer software driven hardware depends on the specific application scenario and design constraints of the technical solution.

[0146] FIG. 14 and FIG. 15 are schematic block diagrams of communication devices provided by the embodiments of the present application. These communication devices can be used to implement the functions of the task function unit in the above method embodiments, and thus can also achieve the beneficial effects possessed by the above method embodiments.

[0147] As shown in FIG. 14, the device 1400 includes a processing module 1410. Optionally, the device 1400 further includes a transceiver module 1420. The transceiver module 1420 can also be referred to as a communication interface or a communication module.

[0148] The device 1400 can be used to execute the actions performed by the task function unit in the above method embodiments. Alternatively, the device 1400 is a component (for example, a chip) configured in the task function unit. The processing module 1410 is used to execute the processing-related operations of the task function unit in the above method embodiments. The transceiver module 1420 is used to execute the receiving and sending-related operations of the task function unit in the above method embodiments.

[0149] Optionally, the transceiver module 1420 can include a sending module and a receiving module. The sending module is configured to perform the sending operations in the above method embodiments. The receiving module is configured to perform the receiving operations in the above method embodiments.

[0150] It should be noted that the apparatus 1400 can include the sending module, but not the receiving module. Alternatively, the apparatus 1400 can include the receiving module, but not the sending module. Specifically, whether the sending module and the receiving module are included in the apparatus 1400 can depend on whether the above scheme executed by the apparatus 1400 includes the sending action and the receiving action.

[0151] Optionally, the apparatus 1400 is configured to perform the actions performed by the task function units in the above embodiments shown in FIG. 13. For example, the processing module 1410 is configured to: split the task of the intelligent agent into a plurality of sub-tasks, and split data carrying the sub-tasks into one or more data packets. For example, the transceiver module 1420 is configured to: send the QoS parameter to the CU. Details can be referred to the above related description, and will not be repeated here.

[0152] Optionally, the apparatus 1400 can further include a storage module, which can be configured to store data, and / or store computer programs or instructions. The processing module 1410 can read the computer programs / instructions and / or data in the storage module, so that the apparatus 1400 implements the above method embodiments.

[0153] FIG. 15 is a schematic block diagram of another communication apparatus 1500 according to an embodiment of the present application. As shown in FIG. 15, the apparatus 1500 includes one or more processors 1510 and interface circuitry 1520. The one or more processors 1510 and the interface circuitry 1520 are coupled to each other. It can be understood that the interface circuitry 1520 can be a transceiver or an input / output interface. Optionally, the apparatus 1500 can further include a memory 1530, which is configured to store instructions executed by the processor 1510, or to store input data required by the processor 1510 to execute instructions, or to store data generated by the processor 1510 after executing instructions. Sometimes, the interface circuitry 1520 can also be understood as a part of the one or more processors 1510. In this case, the apparatus 1500 includes the one or more processors 1510.

[0154] The one or more processors 1510 and the memory 1530 can be separately arranged or integrally arranged, which is not limited in the present application.

[0155] When the apparatus 1500 is configured to implement the method shown in FIG. 13, the one or more processors 1510 are configured to implement the functions of the above processing module 1410, and the interface circuitry 1520 is configured to implement the functions of the above transceiver module 1420.

[0156] When the apparatus 1500 is a chip applied to a task function unit, the chip of the task function unit implements functions of the task function unit in the method embodiments. The chip of the task function unit receives information from the agent, which can be understood as that the information is received by other modules (such as a radio frequency module or an antenna) in the task function unit first, and then the information is transmitted to the chip of the task function unit by the modules. The chip of the terminal transmits information to the agent, which can be understood as that the information is transmitted to other modules (such as a radio frequency module or an antenna) in the task function unit first, and then the information is transmitted to the agent by the modules.

[0157] The embodiments of the present application further provide a computer readable storage medium for storing a computer program, when the computer program is run on a computer, the computer program can make the computer execute the method in the above embodiments. In other words, the computer program includes instructions for implementing the method in the above embodiments.

[0158] The embodiments of the present application further provide a computer program product, including a computer program or instructions, when the computer program or instructions are run on a computer, the computer program or instructions make the computer execute the method in the above embodiments.

[0159] The embodiments of the present application further provide a chip, including at least one processor, for supporting implementation of the method in the above embodiments, for example, receiving or processing data involved in the method in the above embodiments.

[0160] It should be understood that, in the embodiments of the present application, the processor can be a central processing unit (CPU), and the processor can also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0161] In the implementation process, each step of the above method can be completed by integrated logic circuits of hardware in the processor or instructions in the form of software. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as hardware processor execution completion, or executed by a combination of hardware and software modules in the processor. The software module can be located in a mature storage medium in the art such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, register, etc. The storage medium is located in the memory, and the processor executes the instructions in the memory to complete the steps of the above method in combination with its hardware. To avoid repetition, it will not be described in detail here.

[0162] Those of ordinary skill in the art can realize that the modules and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are 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 each specific application, but such implementation should not be considered beyond the scope of the present application.

[0163] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device and module can refer to the corresponding processes in the foregoing method embodiments, which will not be described here.

[0164] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the modules is only a logical function division. In actual implementation, another division mode can be used, for example, a plurality of modules or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the shown or discussed modules can be indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0165] The modules described as separate components can or can not be physically separated, and the components shown as modules can or can not be physical modules, i.e. they can be located in one place or distributed on a plurality of network modules. Some or all of the modules can be selected according to actual needs to achieve the purpose of the embodiment.

[0166] In addition, each functional module in each embodiment of the present application can be integrated into one processing module, or each module can exist physically alone, or two or more modules can be integrated into one module.

[0167] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application or the parts that essentially contribute to the prior art or the parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0168] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A network architecture, characterized in that, Includes task function units; The task function unit is used to split the agent's task into multiple sub-tasks, and to split the data carrying the sub-tasks into one or more data packets; The task function unit is also used to provide Quality of Service (QoS) guarantees for one or more data packets carrying the subtask.

2. The network architecture according to claim 1, characterized in that, The task function unit includes a first function unit and a second function unit; The first functional unit is configured to split the task of the intelligent agent into the plurality of sub-tasks, and to split the data carrying the sub-tasks into one or more data packets; The second functional unit is used to provide QoS guarantees for one or more data packets of the subtask.

3. The network architecture according to claim 2, characterized in that, The first functional unit is also used for: Maintain and control the execution accuracy and / or task response time of the subtasks.

4. The network architecture according to claim 3, characterized in that, The QoS parameters of the data packets carrying the subtask include one or more of the following: Latency, jitter, reliability, execution accuracy, or task response time.

5. The network architecture according to claim 4, characterized in that, The QoS parameters also include: The label of the subtask and the label of the data packet carrying the subtask.

6. The network architecture according to claim 5, characterized in that, The network architecture also includes a centralized unit (CU); The CU is used to interact with the task function unit to obtain the QoS parameters.

7. The network architecture according to claim 6, characterized in that, The CU includes a third functional unit; The third functional unit is used to interact with the task functional unit and the distributed unit DU to obtain the QoS parameters.

8. The network architecture according to claim 7, characterized in that, The CU includes the CU-control plane CP and the CU-user plane UP; The CU-CP is used to interact with the first functional unit to obtain the QoS parameters; The CU-UP is used to interact with the second functional unit regarding the QoS parameters.

9. A method for providing quality of service assurance, characterized in that, Applied to a network architecture including task functional units, the method includes: The agent's task is divided into multiple subtasks, and the data carrying the subtasks is divided into one or more data packets; Provide Quality of Service (QoS) guarantees for one or more data packets carrying the subtask.

10. A communication device, characterized in that, Includes modules for implementing the method as described in claim 9.

11. A communication device, characterized in that, It includes at least one processor coupled to a memory for storing a program or instructions that, when executed by the at least one processor, cause the method of claim 9 to be executed.

12. A computer-readable storage medium, characterized in that, Used to store a computer program that, when run on a computer, causes the method of claim 9 to be executed.

13. A computer program product, characterized in that, include: A computer program or instruction that, when run, causes the method of claim 9 to be performed.

Images