Capability information exposure method and apparatus, storage medium, and computer program product

Abstract

Embodiments of the present disclosure provide a capability information exposure method, a capability information exposure apparatus, a communication device, a chip, a computer-readable storage medium, and a computer program product. The capability information exposure method comprises: generating capability information on the basis of first information, wherein the first information comprises air interface information and / or computing resource information of a communication node, the communication node is a communication node on a radio access network (RAN) side, and the capability information represents communication and computing capabilities of the communication node; and sending the capability information to a first device. By means of the capability information exposure method provided in the embodiments of the present disclosure, the capability information is exposed to the first device, thereby solving the problem of low resource allocation and collaborative computing efficiency caused by ignoring a resource competition relationship between communication and computing when only one type of information is considered.

Description

Capability information disclosure methods, devices, storage media, and computer program products

[0001] Cross-reference to related applications

[0002] This disclosure is based on and claims priority to Chinese Patent Application No. 202410986404.6, filed on July 22, 2024, the entire contents of which are incorporated herein by reference. Technical Field

[0003] This disclosure relates to the field of wireless technology, specifically to a capability information disclosure method, capability information disclosure device, communication equipment, chip, computer-readable storage medium, and computer program product. Background Technology

[0004] With the rapid development of 5G and future 6G technologies, services such as cloud gaming, extended reality (XR), and connected vehicles are increasingly demanding higher requirements for local data offloading, deterministic mobile connectivity, and millisecond-level latency, highlighting the crucial role of edge computing. Multi-access edge computing (MEC) pushes computing power down to the network edge, reducing service transmission latency and bandwidth requirements. It achieves unified physical deployment of communication and computing, while remaining logically independent. Deploying wireless computing power close to data sources and users at the edge not only reduces the cost of building additional computing systems but also minimizes network communication overhead with these systems. This deployment method balances data processing and response speeds between MEC and edge computing, providing users with more flexible and efficient services. Faced with the rapidly growing demand for computing power and the low utilization rate of ubiquitous computing power, optimizing the supply of computing power has become an urgent need. This means further opening up wireless capabilities and strengthening collaboration with services, edge clouds, and central clouds. However, there is still no unified technical system open to external access for wireless computing power and communication-related information. This not only limits the full utilization of computing and communication capabilities on the wireless side, but also hinders the realization of integrated communication and computing services on the Radio Access Network (RAN) side. Future networks are expected to provide integrated communication and computing services, where communication nodes possess both communication and computing capabilities. Computing resources in base stations are shared by communication processing and computing tasks, thus creating competition between the two. In this context, focusing solely on either communication or computing is likely to lead to inefficient resource allocation and collaborative computing, resulting in degraded system performance. Summary of the Invention

[0005] This disclosure provides a capability information disclosure method, a capability information disclosure device, a communication device, a chip, a computer-readable storage medium, and a computer program product.

[0006] The methods for opening up capability information disclosed herein include:

[0007] Based on the first information, capability information is generated; the first information includes: air interface information and / or computing resource information of the communication node; the communication node is a communication node on the RAN side of the radio access network, and the capability information characterizes the computing capability of the communication node;

[0008] The capability information is sent to the first device.

[0009] The capability information disclosure method provided in this disclosure, wherein the computing capability characterizes the degree to which the integrated computing service capability of the communication node meets business requirements; the capability information includes one or more of the following: comprehensive capability information of communication and computing resources, degree to which communication and computing resources meet business requirements, and system operation and maintenance and reliability information.

[0010] The capability information disclosure method provided in this disclosure includes the comprehensive capability information of communication and computing resources, which includes one or more of the following: network connectivity capability, computing resource capability, memory and storage capability, transmission performance, network stability and quality, and performance prediction; the degree to which the communication and computing resources meet service requirements includes one or more of the following: service experience quality (QoE) parameters and capability level; wherein different capability levels correspond to different QoE parameters; and the system operation and reliability information includes one or more of the following: security, scalability, and energy efficiency.

[0011] The capability information disclosure method provided in this disclosure includes one or more of the following devices: network management device, service server, mobile edge computing MEC manager, core network device, and wireless network device.

[0012] The capability information disclosure method provided in this disclosure includes the following air interface information: total uplink bandwidth, total downlink bandwidth, remaining bandwidth, number of physical resource blocks (PRBs), PRB utilization, terminal channel conditions, received signal strength index (RSSI), and communication link latency to adjacent communication nodes; the computing resource information includes the following one or more of the following: CPU utilization of communication nodes, CPU utilization of Pods, CPU utilization of service applications, CPU frequency, CPU core binding status, number of remaining CPU cores, floating-point operations per second (FLOPS) of CPU, FLOPS of graphics processing units (GPUs), FLOPS of neural network processing units (NPUs), GPU memory capacity, remaining GPU memory, number of CUDA cores in GPU computing unified device architecture, and number of remaining GPU CUDA cores.

[0013] The capability information opening method provided in this disclosure further includes, before generating capability information based on the first information: receiving a first request sent by the first device; the first request is used to request or subscribe to the capability information; the first request includes: parameter information required by the first device; generating capability information based on the first information includes: generating capability information according to a calculation method based on the air interface information and computing resource information of the communication node; the capability information includes: parameters required by the first device.

[0014] The capability information disclosure method provided in this disclosure includes a first request carrying the calculation method; and / or, the calculation method being configured and / or trained by the RAN side; and / or, the calculation method being configured and / or trained by the first device.

[0015] The capability information disclosure method provided in this disclosure includes the following calculation method: an identifier or address of a calculation model, input parameters of the calculation model, and output parameters of the calculation model; wherein the calculation model includes one or more of the following: mathematical formula model, artificial intelligence (AI) model, and machine learning (ML) model.

[0016] The capability information opening device provided in this disclosure includes:

[0017] Computation module: configured to generate capability information based on first information; the first information includes: air interface information and / or computing resource information of the communication node; the communication node is a communication node on the RAN side of the radio access network, and the capability information characterizes the computing capability of the communication node;

[0018] The computing module is further configured to send the capability information to the first device.

[0019] The communication device provided in this disclosure includes a processor and a memory, the memory being configured to store a computer program, and the processor being configured to call and run the computer program stored in the memory to execute any of the capability information disclosure methods provided in the embodiments of this disclosure.

[0020] The chip provided in this disclosure includes a processor configured to call and run a computer program from memory, causing a device on which the chip is installed to perform any of the capability information disclosure methods provided in the embodiments of this disclosure.

[0021] The computer-readable storage medium provided in this disclosure is configured to store a computer program that causes a computer to execute any of the capability information disclosure methods provided in the embodiments of this disclosure.

[0022] The computer program product provided in this disclosure includes a computer program that, when executed by a processor, implements any of the capability information disclosure methods provided in this disclosure.

[0023] The capability information opening method provided in this disclosure characterizes the communication node's computing capability based on its air interface information and / or computing resource information. Opening capability information to a first device integrates the air interface information and / or computing resource information on the RAN side to a third party, avoiding the problem of prior art neglecting the resource competition relationship between the two types of information due to considering only one type. The integrated computing information is data estimated or predicted through data analysis, and its generation method includes both RAN internal formation and third-party provision, avoiding the problem that third parties cannot directly use the original data in the RAN. It provides customized services, offering the first device the parameters it needs. This reduces the latency issues caused by the first device separately acquiring two types of information, the security risks of data opening within the RAN, and errors caused by equipment aging. Attached Figure Description

[0024] The accompanying drawings, which are included to provide a further understanding of this disclosure and form part of this disclosure, illustrate exemplary embodiments of the present disclosure and are used to explain the disclosure, but do not constitute an undue limitation of the disclosure. In the drawings:

[0025] Figure 1 is a schematic diagram of the implementation process of the capability information opening method provided in this embodiment of the present disclosure;

[0026] Figure 2 is a schematic diagram of the topology provided in an embodiment of this disclosure;

[0027] Figure 3 is a schematic diagram of the implementation process of capability information disclosure provided in the embodiments of this disclosure (II).

[0028] Figure 4 is a schematic diagram illustrating the implementation of capability information disclosure under the Open Radio Access Network (O-RAN) architecture provided in this embodiment of the present disclosure;

[0029] Figure 5 is a schematic diagram of the structural composition of the capability information opening device provided in an embodiment of this disclosure;

[0030] Figure 6 is a schematic structural diagram of a communication device provided in an embodiment of this disclosure;

[0031] Figure 7 is a schematic structural diagram of a chip according to an embodiment of this disclosure. Detailed Implementation

[0032] The technical solutions of the embodiments of this disclosure will now be described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this disclosure. All other embodiments obtained by those skilled in the art based on the embodiments of this disclosure without creative effort are within the scope of protection of this disclosure.

[0033] It should be noted that, in the embodiments of this disclosure, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, and B existing alone. Furthermore, in the embodiments of this disclosure, the character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0034] In the description of the embodiments of this disclosure, the term "correspondence" may indicate a direct or indirect correspondence between two things, or an association between two things, or a relationship of instruction and being instructed, configuration and being configured, etc.

[0035] To facilitate understanding of the technical solutions of the embodiments of this disclosure, the related technologies of the embodiments of this disclosure are described below. The following related technologies are optional solutions and can be combined with the technical solutions of the embodiments of this disclosure in any way, and they all fall within the protection scope of the embodiments of this disclosure.

[0036] Figure 1 is a schematic diagram of the implementation process of the capability information opening method provided in this embodiment of the present disclosure. As shown in Figure 1, the capability information opening method provided in this embodiment of the present disclosure includes the following steps:

[0037] Step 101: Generate capability information based on the first information; the first information includes: air interface information and / or computing resource information of the communication node; the communication node is a communication node on the RAN side of the radio access network, and the capability information characterizes the computing capability of the communication node.

[0038] In this embodiment of the disclosure, the computing capability represents the degree to which the integrated computing service capability of the communication node meets business requirements.

[0039] In this embodiment of the disclosure, the capability information includes one or more of the following: comprehensive capability information of communication and computing resources, the degree to which communication and computing resources meet business requirements, and system operation and maintenance reliability information.

[0040] In this embodiment of the disclosure, the comprehensive capability information of the communication and computing resources includes one or more of the following: network connectivity capability, computing resource capability, memory and storage capability, transmission performance, network stability and quality, and performance prediction;

[0041] The degree to which the communication and computing resources meet the business requirements includes one or more of the following information: the Quality of Experience (QoE) parameter and the capability level of the service; wherein, different capability levels correspond to different QoE parameters;

[0042] The system operation and reliability information includes one or more of the following: security, scalability, and energy efficiency;

[0043] In this embodiment of the disclosure, air interface information can be subscribed to or requested from the communication node through the interface, and computing resource information can be subscribed to or requested from the underlying computing resource manager on the RAN side through the interface.

[0044] In one optional embodiment of this disclosure, the air interface information includes one or more of the following: total uplink bandwidth, total downlink bandwidth, remaining bandwidth, number of physical resource blocks (PRBs), PRB utilization, terminal channel conditions, received signal strength indicator (RSSI), and communication link delay to adjacent communication nodes.

[0045] The computing resource information includes one or more of the following: CPU utilization of the communication node, CPU utilization of the Pod, CPU utilization of the business application, CPU frequency, CPU core binding status, number of remaining CPU cores, floating-point operations per second (FLOPS) of the CPU, FLOPS of the graphics processing unit (GPU), FLOPS of the neural network processing unit (NPU), GPU memory capacity, remaining GPU memory, number of GPU CUDA cores, and number of remaining GPU CUDA cores.

[0046] For example, taking a communication node as a base station, the air interface information includes one or more of the following: the base station's total uplink bandwidth, the base station's total downlink bandwidth, the base station's remaining bandwidth, the base station's physical resource blocks (PRBs), the base station's PRB utilization rate, the terminal's channel conditions, the received signal strength index (RSSI), and the communication link delay from this base station to neighboring stations.

[0047] The computing resource information includes one or more of the following: CPU utilization of the base station's central processing unit, CPU utilization of the Pod, CPU utilization of the service application, CPU frequency, CPU core binding status, number of remaining CPU cores, floating-point operations per second (FLOPS) of the CPU, FLOPS of the graphics processing unit (GPU), FLOPS of the neural network processing unit (NPU), GPU memory capacity, remaining GPU memory, number of CUDA cores in the GPU computing unified device architecture, and number of remaining CUDA cores in the GPU.

[0048] In this embodiment, the capability information is information estimated or predicted through data analysis. The capability information characterizes the degree to which the communication node's integrated computing service capability meets business requirements and can be understood and applied by external applications. It should be noted that in practical applications, capability information can be generated based on either the air interface information or the computing resource information of the communication node, or it can be generated based on a combination of air interface information and computing resource information. This disclosure does not limit this approach.

[0049] In this embodiment of the disclosure, the capability information includes one or more of the following: comprehensive capability information of communication and computing resources, the degree to which communication and computing resources meet business requirements, and system operation and reliability information; wherein,

[0050] The comprehensive capability information of the communication and computing resources includes one or more of the following: network connectivity capability, computing resource capability, memory and storage capability, transmission performance, network stability and quality, and performance prediction.

[0051] The degree to which the communication and computing resources meet the service requirements includes one or more of the following information: the service's Quality of Experience (QoE) parameter and capability level; wherein, different capability levels correspond to different QoE parameters.

[0052] The system operation and reliability information includes one or more of the following: security, scalability, and energy efficiency.

[0053] In this embodiment of the disclosure, the QoE parameter can be the end-to-end delay of the service, the frame rate of the video service, the frame rate of the artificial intelligence (AI) inference task, the accuracy of the AI ​​inference task, or other parameters. This disclosure does not limit the parameters. Different capability levels represent different QoE parameters. Taking the end-to-end delay as an example, the capability levels are Level 1, Level 2 and Level 3. The end-to-end delay corresponding to Level 1 is 10ms-15ms, the end-to-end delay corresponding to Level 2 is 16ms-20ms, and the end-to-end delay corresponding to Level 3 is 21ms-30ms.

[0054] In this embodiment of the disclosure, capability information can be generated according to the air interface information and computing resource information of the communication node, and the calculation method can be an AI model, a machine learning (ML) model, or a mathematical model that determines mathematical relationships. This disclosure does not limit the specific method.

[0055] For example, taking AI model training as an example, the AI ​​model can be trained and generated using machine learning algorithms (Q-learning, DQN, etc.). Historical data on air interface information and computing resource information within the system are used to train the computational method. For instance, to train an AI model that generates capability information for a specific video service: Preprocess the collected air interface information, computing resource information (bandwidth allocated to the video service, PRB count, CPU frequency, and floating-point operations per second), and service E2E latency data; select a Convolutional Neural Network (CNN); select a suitable cross-entropy loss function and a Stochastic Gradient Descent (SGD) optimizer; train the model using training data, adjusting the model parameters to minimize the loss function (minimizing the E2E latency of the video service in the system). Evaluate the model's performance on the validation and test sets, calculating metrics such as accuracy, precision, and recall. Finally, deploy the model.

[0056] For example, taking the training of a mathematical model as an example, the end-to-end latency calculation method for a certain service is as follows: t total =t comm +t comp , where t total For end-to-end delay, t comm It is the communication transmission delay, which is the ratio of the amount of data transmitted to the transmission rate. The amount of data transmitted is related to the service itself, while the transmission rate is related to the current air interface channel conditions; t comp It is the computation processing latency, which is the ratio of the computation task size to the computation capacity. Its processing capacity is the total current computing resources minus the computing resources occupied by the communication processing of this task. The size of the computation task being processed is the size of the computation task of the business itself.

[0057] Step 102: Send the capability information to the first device.

[0058] In this embodiment of the disclosure, the first device is a third-party device, including one or more of the following: network management device, service server, MEC manager, core network device, and wireless network device.

[0059] In this embodiment of the disclosure, the RAN side receives a first request sent by the first device. The first request is used to request or subscribe to the capability information. The first request may carry parameter information required by the first device. The RAN side can generate the capability information required by the first device according to the parameters required by the first device, based on the air interface information and computing resource information of the communication node, and according to the calculation method.

[0060] Based on this, in an optional embodiment of this disclosure, before generating capability information based on the first information, the method further includes:

[0061] Receive a first request sent by the first device; the first request is used to request or subscribe to the capability information; the first request includes: parameter information required by the first device;

[0062] The generation of capability information based on the first information includes:

[0063] Based on the air interface information and computing resource information of the communication node, capability information is generated according to the calculation method; the capability information includes: the parameters required by the first device.

[0064] When related technologies are opened to third parties (such as MEC orchestrators, 5G core networks, etc.), they lack the ability to customize for various types of services. The allocation of resources and service deployment cannot fully adapt to service requirements. In this disclosure, the RAN side can open up customized requirements and generate the parameters required by the third party according to the third party's needs, thus adapting to different service requirements.

[0065] In this embodiment of the disclosure, the calculation method may also be provided by the first device and carried in the first request. The RAN side performs data processing on the collected air interface information and computing resource information, and generates the first device requirement data or analysis results according to the calculation method provided by the first device.

[0066] Based on this, in an optional embodiment of this disclosure, the first request carries the calculation method; and / or, the calculation method is configured and / or trained by the RAN side; and / or, the calculation method is configured and / or trained by the first device.

[0067] In one optional embodiment of this disclosure, the calculation method includes: an identifier or address of the calculation model, input parameters of the calculation model, and output parameters of the calculation model; wherein, the calculation model includes one or more of the following: a mathematical formula model, an AI model, and an ML model.

[0068] In this embodiment of the disclosure, capability information is generated by a calculation method provided by a third party. Compared with related technologies, this avoids the problem that the RAN side data is opened to third parties but cannot be used by them.

[0069] For example, the identifier of the computational model can be a model ID, and the address can be a URL.

[0070] In this embodiment of the disclosure, air interface information and computing resource information are collected internally by the RAN side, and the capability information required by the first device is obtained by data analysis or prediction using a large amount of data. This information is the integrated computing service capability information that combines radio access network air interface information and computing resource information.

[0071] Understandably, if the first device does not have customized requirements, the RAN side can generate general capability information based on air interface information and computing resource information, and send it to the first device.

[0072] Referring to Figure 2, which is a schematic diagram of the topology provided in an embodiment of this disclosure, as shown in Figure 2, the capability information opening device obtains air interface information from the base station through interface A and obtains computing resource information from the underlying computing resource manager on the RAN side (which may be the unified cloud platform of the cloud base station or the resource manager of the macro base station) through interface B. Based on this information, the capability information opening device generates a RAN-side integrated computing service capability information table through data analysis, estimation, or prediction to represent the capability information, and opens the capability information to the first device through interface C.

[0073] Referring to Figure 3, Figure 3 is a schematic diagram of the implementation process of capability information disclosure provided in this embodiment of the present disclosure. As shown in Figure 3, the process includes the following steps:

[0074] Step 301: The capability information opening device subscribes to or requests air interface information from the base station through interface A.

[0075] Step 302: The capability information opening device subscribes to or requests computing resource information from the underlying computing resource manager on the RAN side through interface B.

[0076] Step 303: The first device requests or subscribes to the RAN-side integrated computing service capability information from the capability information opening device through interface C.

[0077] The first device's request or subscription message carries the parameters and calculation methods it requires.

[0078] Step 304: The capability information opening device generates a RAN-side integrated computing service capability information table based on the content requested or subscribed by the first device.

[0079] The capability information opening device generates a RAN-side integrated communication and computing service capability information table based on the parameters required by the first device, air interface information, and computing resource information, and according to the calculation method provided by the first device.

[0080] Step 305: The capability information opening device sends the RAN-side integrated computing service capability information table to the first device.

[0081] Example 1

[0082] Referring to Figure 4, which is a schematic diagram illustrating the implementation of capability information opening under the O-RAN architecture provided in this embodiment, the Near-RT RIC collects air interface information through the E2 interface and reports underlying computing resource information via the O-Cloud API. A capability information opening device can be deployed within the Near-RT RIC to process the collected air interface information and computing resource information to obtain RAN-side integrated computing service capability information. Third-party service providers can request or subscribe to RAN-side integrated computing service capability information from the Near-RT RIC through the Y1 interface. Furthermore, the Non-RT RIC can be used to train and distribute computing methods to the Near-RT RIC.

[0083] Example 2

[0084] A certain video service requires a QoE latency of 50ms / frame for its end-to-end (E2E) communication. Edge computing service providers need to select business applications that meet this requirement.

[0085] Assuming that the RAN side currently has base stations A and B, when the air interface information and computing resource information are respectively made available to third parties, the corresponding delays calculated based on the current information are shown in Table 1:

[0086] Table 1

[0087] From this perspective, both base stations can meet the E2E latency requirements. When the base stations provide integrated computing capabilities, actual system communication processing will consume some computing resources, such as intelligent AMC processing (e.g., 1.44 TFLOPS for a single user equipment). In addition, equipment aging and other issues can also lead to errors between the final E2E latency and the theoretically calculated value. Considering more internal information and conditions on the RAN side, the E2E latency can be derived using a model trained on RAN information by the capability information open device. Possible results are shown in Table 2:

[0088] Table 2

[0089] Therefore, to meet the QoE requirements of this video service, it is necessary to select a video service application near base station B or within base station B for rendering services.

[0090] Example 3

[0091] Taking an edge computing device as an example, which provides rendering services for an XR service deployed within the RAN, the QoE requirement for this XR service is a frame rate of 60 FPS and an E2E latency of 30 ms / frame. A possible form of the RAN-side integrated computing service capability information table is shown in Table 3.

[0092] Table 3

[0093] The QoE of this service is related to both computing and communication resources. When calculating the frame rate, the computing resources expected to be used by the communication function must be subtracted to obtain the frame rate that the remaining computing resources can handle. E2E latency includes the transmission latency of the air interface and the processing latency of the computation.

[0094] Example 4

[0095] The RAN-side integrated computing service capability information table can also present the current integrated computing service capabilities in a hierarchical manner. For example, in the field of industrial automation, robot control requires the server to perform complex calculations on robot path planning and generate efficient motion control commands. Therefore, this service has very high E2E latency requirements. When the first device selects a service application within the RAN side to provide computing services for this service, it is required to obtain the E2E latency level, corresponding to Level 1 (10ms-15ms), Level 2 (16ms-20ms), Level (21ms-30ms), ...

[0096] One possible form of the RAN-side integrated computing service capability information table is shown in Table 4:

[0097] Table 4

[0098] Example 5

[0099] A city's video surveillance and security application wants to select a node on the RAN side to perform local real-time video analysis and alarm services at a key intersection A. It needs to obtain the location and coverage information of the base station, the base station's video service processing capability information, and the computing power distribution information of terminals within its coverage area. In this way, it can determine which video analysis tasks can be processed at the base station and which can be processed on the terminal devices, thereby achieving more efficient real-time video analysis.

[0100] The information that may be included in the requests sent by urban video surveillance and security applications to the capability information opening device is shown in Table 5:

[0101] Table 5

[0102] The calculation method may be represented in the form of an ID or a URL. For example, the possible specific content is as follows:

[0103] model-1: This should include propagation model information, such as the Okumura model or the Hata model. The coverage radius of the base station is calculated based on the base station coordinates, transmit power, antenna gain, and propagation model.

[0104] Model-2: Video processing throughput = (base station computing resources * utilization efficiency) / video processing complexity. Here, the base station computing resource utilization efficiency is obtained through mathematical analysis such as machine learning based on historical data from the RAN side, and the video processing complexity is related to video encoding format, resolution, etc.

[0105] Model-3: Distance between terminal and base station = (PT - RSSI) / (propagation loss factor × propagation speed)

[0106] The possible forms of capability information generated by the capability information open device are shown in Table 6:

[0107] Table 6

[0108] To meet the local real-time video analysis, processing, and alarm service requirements of a key intersection A, the city's surveillance application selects base station 1 for local real-time video analysis and processing based on the RAN-side integrated computing service capability information. This is because, given that both base stations 1 and 2 can cover key intersection A, base station 1 can provide better video processing capabilities.

[0109] Example 6

[0110] In this embodiment of the disclosure, the comprehensive capability information of communication and computing resources includes, but is not limited to: network connectivity capability, computing resource capability, memory and storage capability, transmission performance, network stability and quality, and performance prediction.

[0111] Table 7 shows one possible form of the comprehensive capability information of the communication and computing resources provided in the embodiments of this disclosure:

[0112] Table 7

[0113] The possible representation methods for the aforementioned specific target entities include, but are not limited to: the ID of a single UE, the ID of a group of UEs, and the network slice ID.

[0114] In this embodiment of the disclosure, when the core network requests service information of a UE from the RAN, one possible form of the comprehensive capability information of communication and computing resources is shown in Table 8:

[0115] Table 8

[0116] Example 7

[0117] In this embodiment of the disclosure, the degree to which communication and computing resources meet service requirements includes, but is not limited to: the QoE parameters of the service, which represent capabilities in a graded manner; wherein, the QoE parameters of the service include, but are not limited to: latency performance, video service quality, extended reality service quality, and artificial intelligence service performance.

[0118] Table 9 shows the possible forms in which communication and computing resources meet business needs:

[0119] Table 9

[0120] Example 8

[0121] In this embodiment of the disclosure, system operation and reliability information includes, but is not limited to: security, scalability, and energy efficiency.

[0122] Table 10 shows the possible formats of system operation and reliability information:

[0123] Table 10

[0124] This disclosure also provides a capability information opening device. Referring to FIG5, the capability information opening device in this embodiment includes:

[0125] Computation module: configured to generate capability information based on first information; the first information includes: air interface information and / or computing resource information of the communication node; the communication node is a communication node on the RAN side of the radio access network, and the capability information characterizes the computing capability of the communication node;

[0126] The computing module is further configured to send the capability information to the first device.

[0127] In this embodiment of the disclosure, the computing capability represents the degree to which the integrated computing service capability of the communication node meets business requirements;

[0128] The capability information includes one or more of the following: comprehensive capability information of communication and computing resources, the degree to which communication and computing resources meet business requirements, and system operation and reliability information.

[0129] In this embodiment of the disclosure, the comprehensive capability information of the communication and computing resources includes one or more of the following: network connectivity, computing resource capability, memory and storage capability, transmission performance, network stability and quality, and performance prediction; the degree to which the communication and computing resources meet service requirements includes one or more of the following: service quality of experience (QoE) parameters and capability levels; wherein different capability levels correspond to different QoE parameters; the system operation and maintenance and reliability information includes one or more of the following: security, scalability, and energy efficiency.

[0130] In this embodiment of the disclosure, the first device includes one or more of the following: a network management device, a service server, a mobile edge computing (MEC) manager, a core network device, and a wireless network device.

[0131] In this embodiment of the disclosure, the air interface information includes one or more of the following: total uplink bandwidth, total downlink bandwidth, remaining bandwidth, number of physical resource blocks (PRBs), PRB utilization, channel conditions of the terminal, received signal strength index (RSSI), and communication link latency to adjacent communication nodes; the computing resource information includes one or more of the following: CPU utilization of the communication node's central processing unit (CPU), CPU utilization of the Pod, CPU utilization of the service application, CPU frequency, CPU core binding status, number of remaining CPU cores, floating-point operations per second (FLOPS) of the CPU, FLOPS of the graphics processing unit (GPU), FLOPS of the neural network processing unit (NPU), GPU memory capacity, remaining GPU memory, number of CUDA cores in the GPU computing unified device architecture, and number of remaining GPU CUDA cores.

[0132] In this embodiment of the disclosure, the computing module is configured to receive a first request sent by the first device; the first request is used to request or subscribe to the capability information; the first request includes: parameter information required by the first device; and capability information is generated according to a computing method based on the air interface information and computing resource information of the communication node; the capability information includes: parameters required by the first device.

[0133] In this embodiment of the disclosure, the first request carries the calculation method; and / or,

[0134] The calculation method is obtained by RAN-side configuration and / or training; and / or,

[0135] The calculation method is obtained by configuring and / or training the first device.

[0136] In this embodiment of the disclosure, the calculation method includes: an identifier or address of the calculation model, input parameters of the calculation model, and output parameters of the calculation model; wherein, the calculation model includes one or more of the following: mathematical formula model, artificial intelligence (AI) model, and machine learning (ML) model.

[0137] Those skilled in the art should understand that the functions of each unit in the capability information opening device shown in Figure 5 can be understood with reference to the relevant description of the aforementioned method. The functions of each unit in the capability information opening device shown in Figure 5 can be implemented by a program running on a processor, or by specific logic circuits.

[0138] Figure 6 is a schematic structural diagram of a communication device 600 provided in an embodiment of this disclosure. The communication device 600 shown in Figure 6 includes a processor 610, which can call and run computer programs from memory to implement the methods in the embodiments of this disclosure.

[0139] Optionally, as shown in FIG6, the communication device 600 may further include a memory 620. The processor 610 may retrieve and run computer programs from the memory 620 to implement the methods in the embodiments of this disclosure.

[0140] The memory 620 can be a separate device independent of the processor 610, or it can be integrated into the processor 610.

[0141] Optionally, as shown in FIG6, the communication device 600 may further include a transceiver 630, and the processor 610 may control the transceiver 630 to communicate with other devices. Specifically, it may send information or data to other devices or receive information or data sent by other devices.

[0142] The transceiver 630 may include a transmitter and a receiver. The transceiver 630 may further include antennas, and the number of antennas may be one or more.

[0143] The communication device 600 may specifically be a capability information opening device in the embodiments of this disclosure, and the communication device 600 may implement the corresponding processes implemented by the capability information opening device in the various methods of the embodiments of this disclosure. For the sake of brevity, it will not be described in detail here.

[0144] By way of example, this disclosure also provides a computer program product, including a computer program that can be executed by the processor 610 of the communication device 600 to perform the steps described in any of the foregoing methods.

[0145] Figure 7 is a schematic structural diagram of a chip according to an embodiment of the present disclosure. The chip 700 shown in Figure 7 includes a processor 710, which can call and run computer programs from memory to implement the methods in the embodiments of the present disclosure.

[0146] Optionally, as shown in FIG7, chip 700 may further include memory 720. Processor 710 may retrieve and run computer programs from memory 720 to implement the methods in the embodiments of this disclosure.

[0147] The memory 720 can be a separate device independent of the processor 710, or it can be integrated into the processor 710.

[0148] Optionally, the chip 700 may also include an input / output interface 730. The processor 710 can control the input / output interface 730 to communicate with other devices or chips; specifically, it can acquire information or data sent by other devices or chips.

[0149] Optionally, the chip 700 may also include an output interface 740. The processor 710 can control the output interface 740 to communicate with other devices or chips, specifically, to output information or data to other devices or chips.

[0150] The chip can be applied to the capability information opening device in the embodiments of this disclosure, and the chip can implement the corresponding processes implemented by the capability information opening device in the various methods of the embodiments of this disclosure. For the sake of brevity, it will not be described in detail here.

[0151] It should be understood that the chip mentioned in the embodiments of this disclosure may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0152] It should be understood that the processor in this disclosure embodiment may be an integrated circuit chip with signal processing capabilities. In implementation, the steps of the above method embodiments can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor described above can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in this disclosure embodiment. The general-purpose processor can be a microprocessor or any conventional processor, etc. The steps of the methods disclosed in the embodiments of this disclosure can be directly embodied as being executed by a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules can be located in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0153] It is understood that the memory in the embodiments of this disclosure can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDR SDRAM), Enhanced Synchronous DRAM (ESDRAM), Synchlink DRAM (SLDRAM), and Direct Rambus RAM (DR RAM). It should be noted that the memory used in the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0154] It should be understood that the above-described memory is exemplary but not limiting. For example, the memory in the embodiments of this disclosure may also be static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus RAM (DR RAM), etc. That is to say, the memory in the embodiments of this disclosure is intended to include, but is not limited to, these and any other suitable types of memory.

[0155] This disclosure also provides a computer-readable storage medium configured to store a computer program. This computer-readable storage medium can be applied to the capability information opening device in the embodiments of this disclosure, and the computer program causes a computer to execute the corresponding processes implemented by the capability information opening device in the various methods of the embodiments of this disclosure; for brevity, further details are omitted here.

[0156] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented 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 this disclosure.

[0157] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0158] In the several embodiments provided in this disclosure, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical network element division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual couplings, direct couplings, or communication connections may be through some output interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0159] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0160] In addition, the functional units in the various embodiments of this disclosure can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0161] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this disclosure, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, a server, or a capability information opening device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this disclosure. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0162] The above description is merely a specific embodiment of this disclosure, but the scope of protection of this disclosure is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this disclosure should be included within the scope of protection of this disclosure. Therefore, the scope of protection of this disclosure should be determined by the scope of the claims.

Claims

1. A method for exposing capability information, comprising: generating capability information based on first information; the first information comprises air interface information and / or computing resource information of a communication node; the communication node is a communication node at a radio access network (RAN) side, and the capability information represents a computing capability of the communication node; sending the capability information to a first device.

2. The method of claim 1, wherein: the computing capability represents a degree of satisfaction of a computing integrated service capability of the communication node to a service requirement; the capability information comprises one or more of the following information: comprehensive capability information of communication and computing resources, degree of satisfaction of communication and computing resources to a service requirement, system operation and reliability information.

3. The method of claim 2, wherein: the comprehensive capability information of communication and computing resources comprises one or more of the following information: network connection capability, computing resource capability, memory and storage capability, transmission performance, network stability and quality, performance prediction; the degree of satisfaction of communication and computing resources to a service requirement comprises one or more of the following information: quality of experience (QoE) parameters of a service, capability level; different capability levels correspond to different QoE parameters; the system operation and reliability information comprises one or more of the following information: security, scalability, energy efficiency.

4. The method of claim 1, wherein: the first device comprises one or more of the following: a network management device, a service server, a mobile edge computing (MEC) manager, a core network device, a wireless network device.

5. The method of claim 1, wherein: the air interface information comprises one or more of the following information: total uplink bandwidth, total downlink bandwidth, remaining bandwidth, number of physical resource blocks (PRBs), PRB utilization rate, channel condition of a terminal, received signal strength indication (RSSI), communication link delay to a neighboring communication node; the computing resource information comprises one or more of the following information: central processing unit (CPU) utilization rate of the communication node, CPU utilization rate of a Pod, CPU utilization rate of a service application, CPU frequency, CPU core binding state, number of remaining CPU cores, floating point operations per second (FLOPS) of the CPU, FLOPS of a graphics processing unit (GPU), FLOPS of a neural processing unit (NPU), GPU video memory capacity, GPU remaining video memory, number of GPU compute unified device architecture (CUDA) cores, number of GPU CUDA remaining cores.

6. The method of claim 1, wherein, Before generating the capability information based on the first information, the method further comprises: receiving a first request sent by the first device; the first request is used to request or subscribe to the capability information; the first request comprises parameter information required by the first device; the generating of the capability information based on the first information comprises: generating the capability information based on the air interface information and the computing resource information of the communication node; the capability information comprises the parameter required by the first device.

7. The method of claim 6, wherein, the capability information is obtained according to a capability information generation method; the first request carries the capability information generation method; and / or, The capability information generation method is obtained by configuration and / or training of the RAN side. And / or, The capability information generation method is obtained by configuration and / or training of the first device.

8. The method of claim 6, wherein, The calculation method comprises: an identifier or address of a calculation model, an input parameter of the calculation model, and an output parameter of the calculation model; wherein the calculation model comprises one or more of the following: a mathematical formula model, an artificial intelligence AI model, and a machine learning ML model.

9. A capability information exposure apparatus, comprising: a calculation module configured to generate capability information based on first information; The first information comprises air interface information and / or computing resource information of a communication node; The communication node is a communication node on the radio access network RAN side, and the capability information represents the computing capability of the communication node; The calculation module is further configured to send the capability information to a first device.

10. A communication device comprising: A processor and a memory, the memory is configured to store a computer program, and the processor is configured to call and run the computer program stored in the memory to execute the capability information exposure method in any one of claims 1 to 8.

11. A chip comprising: A processor configured to call and run a computer program from a memory, so that a device installed with the chip executes the capability information exposure method in any one of claims 1 to 8.

12. A computer readable storage medium configured to store a computer program, the computer program causing a computer to execute the capability information exposure method in any one of claims 1 to 8.

13. A computer program product comprising a computer program which, when executed by a processor, implements the capability information exposure method in any one of claims 1 to 8.

Images