Communication method and apparatus, storage medium, and electronic device

Abstract

The disclosure provides a communication method and device, a storage medium and an electronic device, and relates to the technical field of communication. The method is applied to a computing resource scheduling function, the computing resource scheduling function belongs to a wireless intelligent management and arrangement function layer, and the method comprises the following steps: receiving a service request forwarded by a first intelligent wireless access network node; the first intelligent wireless access network node is connected to a target device, and the service request is sent by the target device to the first intelligent wireless access network node; according to the service request, a target artificial intelligence model is deployed to a second intelligent wireless access network node, so that the second intelligent wireless access network node completes inference of the target artificial intelligence model and sends an inference result to the first intelligent wireless access network node; and the first intelligent wireless access network node is further used for sending the inference result to the target device. The problems of high cost, high power consumption and uneven utilization of computing resource are solved.

Description

Technical Field

[0001] This disclosure relates to the field of communication technology, and in particular to a communication method and apparatus, a storage medium and an electronic device. Background Technology

[0002] In the current technological field, the main intelligent functions of intelligent robots during operation, such as environmental recognition, path planning, and target tracking, are usually performed by the robot itself. These functions rely on high-performance embedded computing units (such as GPUs or TPUs).

[0003] Because intelligent robots require high-performance computing units, their manufacturing costs are significantly increased. These high-performance computing units and complex intelligent processing tasks greatly increase the robot's energy consumption, which not only shortens battery life but can also lead to overheating issues, further affecting hardware stability and lifespan. The robot's internal computing resources need to be reserved for the most complex scenarios, but during daily operation, this computing power may be idle, resulting in wasted resources. Furthermore, in complex task scenarios requiring even greater computing power, the robot's internal computing power may be insufficient, leading to task failure or performance degradation.

[0004] It should be noted that the information disclosed in the background section above is only used to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0005] This disclosure provides a communication method and apparatus, a storage medium and an electronic device, which at least to some extent overcome the problems of high cost, high power consumption and uneven utilization of computing resources in related technologies.

[0006] Other features and advantages of this disclosure will become apparent from the following detailed description, or may be learned in part from practice of this disclosure.

[0007] According to one aspect of this disclosure, a communication method is provided for use in a general computing resource scheduling function, wherein the general computing resource scheduling function belongs to the wireless intelligent management and orchestration function layer, the method comprising:

[0008] The system receives a service request forwarded by a first node of the intelligent wireless access network; the first node of the intelligent wireless access network is connected to the target device, and the service request is sent from the target device to the first node of the intelligent wireless access network.

[0009] According to the service request, the target artificial intelligence model is deployed to the second node of the intelligent wireless access network, so that the second node of the intelligent wireless access network completes the inference of the target artificial intelligence model and sends the inference result to the first node of the intelligent wireless access network; the first node of the intelligent wireless access network is also used to send the inference result to the target device.

[0010] In some embodiments, the target device is in a business scenario, and the business request is determined by the target device according to the business instructions in the business scenario. The business request includes: the network requirements and the artificial intelligence model requirements of the target device when executing the business instructions in the business scenario.

[0011] In some embodiments, before forwarding the service request, the first node of the intelligent wireless access network further includes:

[0012] The first node of the intelligent wireless access network determines that the current network condition meets the network requirements in the service request.

[0013] In some embodiments, deploying the target artificial intelligence model to a second node of the intelligent wireless access network according to the service request includes:

[0014] Based on the network requirements in the service request, determine the second node of the intelligent wireless access network registered with the general computing resource scheduling function;

[0015] Based on the requirements for artificial intelligence models in the business request, determine the target artificial intelligence model;

[0016] The target artificial intelligence model is deployed to the second node of the intelligent wireless access network.

[0017] In some embodiments, the target device is further configured to execute the business instruction in the business scenario based on the reasoning result.

[0018] In some embodiments, the first node of the smart wireless access network is a smart wireless access network node that is adjacent to the target device in the service scenario.

[0019] According to another aspect of this disclosure, a communication method is also provided, applied to a first node of an intelligent wireless access network, the method comprising:

[0020] Receive a service request sent by a target device; the target device is connected to the first node of the intelligent wireless access network;

[0021] The service request is forwarded to the general computing resource scheduling function, so that the general computing resource scheduling function deploys the target artificial intelligence model to the second node of the intelligent wireless access network according to the service request; the general computing resource scheduling function belongs to the wireless intelligent management and orchestration function layer; the second node of the intelligent wireless access network is used to complete the inference of the target artificial intelligence model and send the inference result to the first node of the intelligent wireless access network;

[0022] The inference result is received and forwarded to the target device.

[0023] According to another aspect of this disclosure, a communication device is also provided for use in a computing resource scheduling function, wherein the computing resource scheduling function belongs to the wireless intelligent management and orchestration function layer, and the device includes:

[0024] A service request receiving module is used to receive service requests forwarded by the first node of the intelligent wireless access network; the first node of the intelligent wireless access network is connected to the target device, and the service request is sent from the target device to the first node of the intelligent wireless access network.

[0025] The target AI model deployment module is used to deploy the target AI model to the second node of the intelligent wireless access network according to the service request, so that the second node of the intelligent wireless access network can complete the inference of the target AI model and send the inference result to the first node of the intelligent wireless access network; the first node of the intelligent wireless access network is also used to send the inference result to the target device.

[0026] According to another aspect of this disclosure, a communication device is also provided, applied to a first node of an intelligent wireless access network, the device comprising:

[0027] A service request receiving module is used to receive service requests sent by a target device; the target device is connected to the first node of the intelligent wireless access network.

[0028] A service request forwarding module is used to forward the service request to the general computing resource scheduling function, so that the general computing resource scheduling function can deploy the target artificial intelligence model to the second node of the intelligent wireless access network according to the service request; the general computing resource scheduling function belongs to the wireless intelligent management and orchestration function layer; the second node of the intelligent wireless access network is used to complete the inference of the target artificial intelligence model and send the inference result to the first node of the intelligent wireless access network;

[0029] The inference result forwarding module is used to receive the inference result and forward it to the target device.

[0030] According to another aspect of this disclosure, an electronic device is also provided, comprising: a processor; and a memory for storing executable instructions of the processor; wherein the processor is configured to perform the communication method described in any of the preceding claims by executing the executable instructions.

[0031] According to another aspect of this disclosure, a computer-readable storage medium is also provided, on which a computer program is stored, which, when executed by a processor, implements the communication method described in any of the preceding claims.

[0032] According to another aspect of this disclosure, a computer program product is also provided, including a computer program that, when executed by a processor, implements the communication method of any of the above.

[0033] The communication method, apparatus, storage medium, and electronic device provided in the embodiments of this disclosure are applied to a general computing resource scheduling function, which belongs to the wireless intelligent management and orchestration function layer. The method includes: receiving a service request forwarded by a first node of an intelligent wireless access network; the first node of the intelligent wireless access network connects to a target device, and the service request is sent from the target device to the first node of the intelligent wireless access network; according to the service request, deploying a target artificial intelligence model to a second node of the intelligent wireless access network, so that the second node of the intelligent wireless access network completes the inference of the target artificial intelligence model and sends the inference result to the first node of the intelligent wireless access network; the first node of the intelligent wireless access network is also used to send the inference result to the target device.

[0034] In this embodiment, the target device sends a service request to the first node of the intelligent wireless access network (WLAN). The first WLAN forwards the service request to the general computing resource scheduling function. Based on the service request, the general computing resource scheduling function deploys the target AI model to the second WLAN node. The second WLAN node completes the inference of the target AI model and sends the inference result back to the first WLAN node. The first WLAN node then sends the inference result back to the target device, completing the operation of the target device. Through the general computing resource scheduling function of the wireless intelligent management and orchestration function layer, fragmented computing resources in the wireless intelligent management and orchestration function layer are uniformly managed and dynamically scheduled. This eliminates the need to configure excessive computing power and high-performance computing units for the target device to cope with complex scenarios. Instead, on-demand allocation is achieved through networked collaboration, significantly improving resource utilization and reducing costs. Offloading intelligent processing functions requiring high-performance computing units from the target device to the intelligent wireless access network reduces the demand for local high-performance hardware by sharing computing resources, thereby reducing hardware costs. Offloading high-performance intelligent processing functions from the target device to the intelligent wireless access network reduces the load on the local computing unit, significantly lowering power consumption and extending the target device's battery life. Leveraging the low-latency communication capabilities of the intelligent wireless access network, combined with optimized deployment of latency-sensitive tasks by the wireless intelligent management and orchestration functional layer, the real-time performance and reliability of task execution in complex environments are ensured. Compared to edge computing solutions for intelligent processing tasks, this approach better meets real-time requirements, especially in high-reliability task scenarios in dynamic environments. The wireless intelligent management and orchestration functional layer enables efficient integration and scheduling of fragmented computing power, reducing wasted computing resources. It also enables dynamic updates and on-demand deployment of intelligent models without requiring hardware upgrades on the target device. Functional expansion is achieved through software updates and network scheduling, significantly improving system adaptability. Furthermore, the wireless intelligent management and orchestration functional layer facilitates computing power sharing and task allocation among multiple robots through scheduling and control. Compared to the traditional single-robot operation mode, this supports multi-robot collaborative work, improving overall efficiency and reducing the pressure on individual robots. Based on the dynamic deployment capabilities of the wireless intelligent management and orchestration function layer, it supports rapid iteration and expansion of new intelligent models and algorithms.

[0035] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0036] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this disclosure and, together with the description, serve to explain the principles of this disclosure. It is obvious that the drawings described below are merely some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0037] Figure 1 A schematic diagram of the system structure of a communication method according to an embodiment of this disclosure is shown.

[0038] Figure 2 A schematic diagram of a communication method according to an embodiment of this disclosure is shown.

[0039] Figure 3 This diagram illustrates a wireless intelligent management and orchestration functional layer of a communication method according to an embodiment of the present disclosure.

[0040] Figure 4 This diagram illustrates a first interaction of a communication method according to an embodiment of the present disclosure.

[0041] Figure 5 This diagram illustrates a second interaction of a communication method according to an embodiment of the present disclosure.

[0042] Figure 6 Another schematic diagram of a communication method according to an embodiment of this disclosure is shown.

[0043] Figure 7 A schematic diagram of a communication device according to an embodiment of this disclosure is shown.

[0044] Figure 8 Another schematic diagram of a communication device according to an embodiment of the present disclosure is shown.

[0045] Figure 9 A structural block diagram of a computer device for a communication method according to an embodiment of the present disclosure is shown. Detailed Implementation

[0046] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, they are provided so that this disclosure will be more comprehensive and complete, and will fully convey the concept of the exemplary embodiments to those skilled in the art. The described features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

[0047] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and therefore repeated descriptions of them will be omitted. Some block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0048] To facilitate understanding, before introducing the embodiments of this disclosure, the following explanations are provided for several terms involved in the embodiments of this disclosure:

[0049] Artificial Intelligence Radio Access Network (AI RAN) is a new architecture that integrates artificial intelligence (AI) technology into the radio access network (RAN). By leveraging AI and machine learning algorithms, AI RAN aims to optimize network performance, improve resource management efficiency, enhance user experience, and achieve more automated and intelligent network operation and maintenance. This architecture represents a significant trend in the development of traditional RAN towards greater efficiency, flexibility, and intelligence. AI RAN refers to a network architecture that introduces AI technology to improve network management and operation on the basis of existing radio access networks. It not only focuses on data transmission itself but also emphasizes analyzing the large amounts of data generated in the network to predict and resolve potential problems, thereby improving overall network performance and quality of service.

[0050] The Radio Intelligent Management and Orchestration Layer (RAN AI Layer) is a layer specifically designed within the Radio Access Network (RAN) to integrate and apply artificial intelligence (AI) technologies for more efficient network management and optimization. This layer focuses on leveraging AI capabilities to improve network performance, automate operations and maintenance, and provide personalized user experiences. The RAN AI Layer is a logical layer structure designed to intelligently manage and coordinate network resources and services by introducing advanced AI algorithms and technologies into the radio access network. This goes beyond simply optimizing existing network operations; it also includes predictive maintenance, automatic fault recovery, and other functions, thereby achieving a higher level of automation and intelligence.

[0051] The specific implementation methods of the embodiments of this disclosure will now be described in detail with reference to the accompanying drawings.

[0052] like Figure 1As shown, the system architecture includes a terminal device 101, a network 102, and a network-side device 103. The network 102 is used as a medium to provide a communication link between the terminal device 101 and the network-side device 103, and can be a wired network or a wireless network.

[0053] Optionally, the aforementioned wireless or wired networks use standard communication technologies and / or protocols. The network is typically the Internet, but can also be any network, including but not limited to Local Area Networks (LANs), Metropolitan Area Networks (MANs), Wide Area Networks (WANs), mobile, wired or wireless networks, private networks, or any combination of virtual private networks. In some embodiments, technologies and / or formats including Hyper Text Markup Language (HTML), Extensible Markup Language (XML), etc., are used to represent data exchanged over the network. Furthermore, conventional encryption technologies such as Secure Socket Layer (SSL), Transport Layer Security (TLS), Virtual Private Networks (VPNs), and Internet Protocol Security (IPSec) can be used to encrypt all or some links. In other embodiments, custom and / or dedicated data communication technologies can be used to replace or supplement the aforementioned data communication technologies.

[0054] Optionally, the terminal device in this embodiment may also be referred to as UE (User Equipment). In specific implementation, the terminal device may be a mobile phone, tablet personal computer, laptop computer, personal digital assistant (PDA), mobile internet device (MID), wearable device, or vehicle-mounted device, etc. It should be noted that the specific type of terminal device is not limited in the embodiments of the present invention.

[0055] Network-side equipment can be base stations, relays, or access points, etc. Base stations can be 5G and later versions of base stations (e.g., 5G NR NB), or base stations in other communication systems (e.g., eNB base stations). It should be noted that the specific type of network-side equipment is not limited in the embodiments disclosed herein.

[0056] Those skilled in the art will know that Figure 1 The number of terminals, networks, and network-side devices shown is merely illustrative; any number of terminals, networks, and network-side devices can be included as needed. This disclosure does not limit the scope of the embodiments.

[0057] Under the above system architecture, this disclosure provides a communication method that can be executed by any electronic device with computing capabilities.

[0058] In some embodiments, the communication method provided in this disclosure can be executed by a terminal device in the above-described system architecture; in other embodiments, the communication method provided in this disclosure can be executed by a server in the above-described system architecture; in still other embodiments, the communication method provided in this disclosure can be implemented by the terminal device and the server in the above-described system architecture through interaction.

[0059] When intelligent robots are running, their main intelligent functions, such as environmental recognition, path planning, and target tracking, are typically performed by the robot itself. These functions rely on high-performance embedded computing units, such as GPUs (Graphics Processing Units), TPUs (Tensor Processing Units), or high-end CPUs. The main characteristics of this technical architecture are: computing power is concentrated on the robot itself: the robot is equipped with high-performance computing hardware, collecting environmental data through built-in sensors such as cameras and radar, and then processing and analyzing the data locally to complete environmental perception, decision-making, and motion control. Edge computing applications: some existing solutions attempt partial collaboration between the robot's local machine and edge servers, offloading some non-real-time tasks, such as historical data analysis or complex model training, to the edge server. However, tasks with high real-time requirements still need to be completed locally by the robot. Highly dependent hardware architecture: current intelligent robots must rely on expensive and high-power computing hardware to achieve high levels of intelligent functions. For example, some commercial intelligent service robots typically have a built-in high-performance computing platform with powerful AI computing capabilities, capable of running deep learning models in real time for image recognition and voice interaction. However, this approach requires the robot to be equipped with high-performance batteries to support the high power consumption demands of the computing modules.

[0060] In embodied intelligence scenarios, hardware devices are installed within the robot to process intelligent algorithms such as robot balance and visual recognition. However, due to limitations in terminal computing power, embodied intelligent robots can only handle small models. AI RAN (AI Random Access Array) can integrate intelligent modules for processing, reducing the cost of embodied intelligent robots while enabling them to handle intelligent applications with higher computing power requirements. Although the above technologies have achieved autonomous operation of intelligent robots to a certain extent, the following significant technical problems still exist:

[0061] High cost: The need for high-performance computing units (such as GPUs or TPUs) inside intelligent robots significantly increases the manufacturing cost of robots, resulting in a high market price and limiting their widespread adoption and commercial application.

[0062] Excessive power consumption: High-performance computing units and complex intelligent processing tasks will greatly increase the robot's energy consumption. This not only shortens the robot's battery life, but may also cause overheating problems, further affecting the stability and lifespan of the hardware.

[0063] Uneven utilization of computing resources: The robot's internal computing resources need to be reserved for the most complex scenarios, but during daily operation, these computing resources may be idle, resulting in resource waste. At the same time, in complex task scenarios that require greater computing power, the robot's internal computing power may be insufficient, leading to task execution failure or performance degradation.

[0064] Real-time and reliability challenges: Although existing edge computing solutions attempt to offload some tasks to edge servers, in scenarios with high real-time requirements, edge computing solutions cannot fully meet the needs of intelligent robots due to network transmission latency and instability.

[0065] Poor system scalability: Current intelligent robot architectures are highly dependent on local hardware. Upgrading or changing algorithms usually requires replacing or upgrading the entire computing module, which limits the system's flexibility and scalability.

[0066] Figure 2 This diagram illustrates a communication method according to an embodiment of the present disclosure, such as... Figure 2 As shown in the embodiments of this disclosure, the communication method is applied to the general computing resource scheduling function, which belongs to the wireless intelligent management and orchestration function layer. The method includes:

[0067] Step S202: Receive the service request forwarded by the first node of the intelligent wireless access network; the first node of the intelligent wireless access network is connected to the target device, and the service request is sent from the target device to the first node of the intelligent wireless access network;

[0068] Step S204: According to the service request, the target artificial intelligence model is deployed to the second node of the intelligent wireless access network, so that the second node of the intelligent wireless access network completes the inference of the target artificial intelligence model and sends the inference result to the first node of the intelligent wireless access network; the first node of the intelligent wireless access network is also used to send the inference result to the target device.

[0069] In this embodiment, the target device sends a service request to the first node of the intelligent wireless access network (WLAN). The first WLAN forwards the service request to the general computing resource scheduling function. Based on the service request, the general computing resource scheduling function deploys the target AI model to the second WLAN node. The second WLAN node completes the inference of the target AI model and sends the inference result back to the first WLAN node. The first WLAN node then sends the inference result back to the target device, completing the operation of the target device. Through the general computing resource scheduling function of the wireless intelligent management and orchestration function layer, fragmented computing resources in the wireless intelligent management and orchestration function layer are uniformly managed and dynamically scheduled. This eliminates the need to configure excessive computing power and high-performance computing units for the target device to cope with complex scenarios. Instead, on-demand allocation is achieved through networked collaboration, significantly improving resource utilization and reducing costs. Offloading intelligent processing functions requiring high-performance computing units from the target device to the intelligent wireless access network reduces the demand for local high-performance hardware by sharing computing resources, thereby reducing hardware costs. Offloading high-performance intelligent processing functions from the target device to the intelligent wireless access network reduces the load on the local computing unit, significantly lowering power consumption and extending the target device's battery life. Leveraging the low-latency communication capabilities of the intelligent wireless access network, combined with optimized deployment of latency-sensitive tasks by the wireless intelligent management and orchestration functional layer, the real-time performance and reliability of task execution in complex environments are ensured. Compared to edge computing solutions for intelligent processing tasks, this approach better meets real-time requirements, especially in high-reliability task scenarios in dynamic environments. The wireless intelligent management and orchestration functional layer enables efficient integration and scheduling of fragmented computing power, reducing wasted computing resources. It also enables dynamic updates and on-demand deployment of intelligent models without requiring hardware upgrades on the target device. Functional expansion is achieved through software updates and network scheduling, significantly improving system adaptability. Furthermore, the wireless intelligent management and orchestration functional layer facilitates computing power sharing and task allocation among multiple robots through scheduling and control. Compared to the traditional single-robot operation mode, this supports multi-robot collaborative work, improving overall efficiency and reducing the pressure on individual robots. Based on the dynamic deployment capabilities of the wireless intelligent management and orchestration function layer, it supports rapid iteration and expansion of new intelligent models and algorithms.

[0070] Figure 3 This diagram illustrates a wireless intelligent management and orchestration functional layer of a communication method according to an embodiment of the present disclosure, such as... Figure 3 As shown, the Wireless Intelligent Management and Orchestration Functional Layer includes at least: model management functions, data management services, service management and orchestration, and general computing resource scheduling functions. This layer connects to various types of radio access networks, including at least: Intelligent Radio Access Network (AI RAN), 3GPP RAN, and other RANs. Through general computing resource scheduling, the Wireless Intelligent Management and Orchestration Functional Layer achieves cross-domain coordination of computing power between different RANs, improving computing power utilization efficiency and optimizing the overall performance of the target terminal.

[0071] In this embodiment, the target device can be an intelligent robot, which is a device integrating advanced artificial intelligence (AI), machine learning, sensor technology, and mechanical engineering, designed to perform a variety of tasks, from simple repetitive work to complex decision-making and interactions. Intelligent robots can perceive their environment, understand instructions, make decisions, and execute actions to accomplish specific goals or tasks. They possess a degree of autonomous decision-making ability and can perform tasks without direct human intervention. By integrating multiple sensors (such as cameras, LiDAR, microphones, etc.), intelligent robots can "perceive" their surroundings, collecting information for navigation, object and person recognition, obstacle avoidance, and more. Utilizing machine learning algorithms, intelligent robots can learn from experience, improve their performance, and adapt to new situations and environmental changes. Intelligent robots can communicate with humans, including understanding natural language, speech recognition, facial expression recognition, and responding to human commands and questions. They can adjust their behavior patterns according to different scenarios, making them suitable for diverse applications such as home assistants, healthcare, and industrial manufacturing.

[0072] Figure 4 This diagram illustrates a first interaction of a communication method according to an embodiment of the present disclosure, such as... Figure 4 As shown in the embodiment, the target device is in a business scenario, and the business request is determined by the target device according to the business instructions in the business scenario. The business request includes: the network requirements and the artificial intelligence model requirements of the target device when executing the business instructions in the business scenario.

[0073] The target device operates within a business scenario, which can be an embodied intelligence scenario. Embodied intelligence scenarios refer to application scenarios where intelligent behavior and interaction are achieved through physical entities (such as robots or other types of automated equipment). These entities can not only perceive their surroundings but also make decisions and execute corresponding actions based on the information they receive, thereby effectively interacting with the environment and other entities. For example, home assistant robots can automatically perform various tasks at home, such as cleaning and managing daily reminders. In hospitals or nursing homes, medical care robots can assist medical staff in providing intelligent companionship, reducing their burden. Robots in industrial manufacturing are typically used for repetitive tasks on production lines to improve production efficiency and product quality. Agricultural robots are designed to perform various field operations, such as sowing, weeding, and harvesting, aiming to improve agricultural production efficiency. Educational and entertainment robots can serve as teaching tools or playmates, helping children learn new knowledge or providing entertainment experiences. Within the business scenario, the target device determines business requests based on specific business instructions. Taking intelligent companionship with an embodied intelligence scenario as an example, the business instruction is for the medical care robot to measure the patient's body temperature. The business request is to determine the corresponding network requirements and artificial intelligence model requirements based on the network and artificial intelligence model needed for the medical care robot to measure the patient's body temperature in the business instruction, and then obtain the corresponding business request.

[0074] The target device sends a service request to the first node of the intelligent wireless access network. In this embodiment, the first node of the intelligent wireless access network is the node closest to the target device in the service scenario. In the service scenario, the target device selects and establishes a communication connection with the nearest intelligent wireless access network node to achieve communication with the network side. Since the intelligent wireless access network node is the closest node in the service scenario, it establishes a communication connection with the target device.

[0075] In this embodiment, before forwarding a service request, the first node of the intelligent wireless access network further includes: determining whether the current network conditions meet the network requirements in the service request. After receiving a service request, the first node of the intelligent wireless access network needs to analyze and determine whether the current network conditions can meet the network requirements in the service request. The network requirements in the service request include: the computing performance of the intelligent wireless access network needs to meet the computing requirements of the service request; the latency of the intelligent wireless access network needs to meet the latency requirements of the service request; and the communication bandwidth of the intelligent wireless access network needs to meet the service bandwidth requirements of the service request.

[0076] If the first node of the intelligent wireless access network determines that the current network conditions cannot meet the network requirements of the service, it will reject the current service request and send a service rejection response to the target device. The target device will then stop executing the service instruction.

[0077] If the first node of the intelligent wireless access network determines that the current network conditions meet the network requirements in the service needs, then it forwards the service needs to the general computing resource scheduling function of the wireless intelligent management and orchestration function layer.

[0078] In this embodiment, deploying the target artificial intelligence model to the second node of the intelligent wireless access network according to a service request includes:

[0079] Based on the network requirements in the business request, determine the second node of the intelligent wireless access network registered with the computing resource scheduling function;

[0080] Based on the requirements for artificial intelligence models in the business request, determine the target artificial intelligence model;

[0081] Deploy the target AI model to the second node of the intelligent wireless access network.

[0082] The general computing resource scheduling function receives service requests forwarded by the first node of the intelligent radio access network. The second node of the intelligent radio access network registers with the general computing resource scheduling function. The second node of the intelligent radio access network can be a single node or multiple nodes.

[0083] When a single node can meet the network requirements of a service request, then one intelligent radio access network (IRN) second node is used. When multiple nodes are required to meet the network requirements of a service request, then multiple IRN second nodes need to be used in conjunction.

[0084] Based on the network requirements in the service request, a second intelligent wireless access network node is determined from among multiple intelligent wireless access network nodes registered with the general computing resource scheduling function; wherein the second intelligent wireless access network node can meet the network requirements in the service request.

[0085] Furthermore, based on the requirements for artificial intelligence models in the business request, the corresponding target artificial intelligence model is determined; for example, if the business request requires an artificial intelligence model for environment recognition and action decision-making, then the corresponding target artificial intelligence models are an environment recognition artificial intelligence model and an intelligent decision-making artificial intelligence model. The target artificial intelligence model is then deployed to the second node of the intelligent wireless access network. The specific deployment process includes:

[0086] The general computing resource scheduling function sends a model deployment instruction to the second node of the intelligent wireless access network. The second node of the intelligent wireless access network receives the model deployment instruction, obtains the corresponding target artificial intelligence model from the model management function of the wireless intelligent management and orchestration function layer according to the model deployment instruction, and deploys the target artificial intelligence model in the second node of the intelligent wireless access network.

[0087] After the target artificial intelligence model is deployed in the second node of the intelligent wireless access network, the model inference task is executed in the second node of the intelligent wireless access network to complete the inference of the target artificial intelligence model and generate the inference result.

[0088] The second node of the intelligent wireless access network sends the inference result to the first node of the intelligent wireless access network. After receiving the inference result, the first node of the intelligent wireless access network sends the inference result to the target device.

[0089] In the embodiment, the target device is also used to execute business instructions in a business scenario based on the reasoning results.

[0090] After receiving the inference results, the target device executes business instructions in the business scenario based on the inference results.

[0091] The communication method provided in this disclosure enables dynamic computing power scheduling for efficient resource utilization, reduces robot manufacturing costs, improves robot endurance, ensures real-time performance and reliability, enhances system flexibility and scalability, and supports multi-robot collaborative operations. Specifically, dynamic computing power scheduling achieves efficient resource utilization by uniformly managing and dynamically scheduling fragmented computing resources in the AI ​​RAN through the RAN AILayer. It eliminates the need to configure excessive computing power for robots to cope with complex scenarios; instead, it achieves on-demand allocation through networked collaboration, significantly improving resource utilization and reducing costs. Reducing robot manufacturing costs involves offloading intelligent processing functions from the robot body to the AI ​​RAN, thereby reducing the need for local high-performance hardware through shared computing resources. Traditional solutions require expensive embedded computing units; this embodiment adopts a shared computing power model, which reduces hardware costs. Improving robot endurance involves offloading high-power tasks to the AI ​​RAN, reducing the load on local computing modules. Compared to traditional solutions that require continuous operation of high-performance computing units, this embodiment significantly reduces power consumption, thereby extending robot endurance by more than 30%. Ensuring real-time performance and reliability is achieved through the low-latency communication capabilities of AI RAN, combined with optimized deployment of the RAN AI Layer for latency-sensitive tasks. Compared to existing edge computing solutions, this embodiment better meets real-time requirements, especially in high-reliability task scenarios in dynamic environments. Enhancing system flexibility and scalability is achieved through the RAN AI Layer, enabling dynamic updates and on-demand deployment of intelligent models. Existing technologies typically require hardware upgrades to adapt to new task requirements, while this embodiment achieves functional expansion through software updates and network scheduling, significantly improving system adaptability. Supporting multi-robot collaborative operation is achieved through RAN AI Layer scheduling and control, enabling computing power sharing and task allocation among multiple robots. Compared to the traditional mode of single-robot operation, this embodiment supports multi-robot collaborative operation, improving overall efficiency and reducing the pressure on individual robots.

[0092] Figure 5 This illustration shows a second interaction diagram of a communication method according to an embodiment of the present disclosure, such as... Figure 5 As shown, in this embodiment, the second node of the intelligent wireless access network includes two nodes: intelligent wireless access network second node-1 and intelligent wireless access network second node-2; the specific process includes:

[0093] In a business scenario, the target device determines the business request based on the specific business instructions.

[0094] The target device sends a service request to the first node of the intelligent wireless access network.

[0095] The first node of the intelligent wireless access network determines whether the current network conditions meet the network requirements in the service request. If not, the service request is rejected; if it is met, the service request is forwarded to the general computing resource scheduling function of the wireless intelligent management and orchestration function layer.

[0096] The general computing resource scheduling function receives service requests forwarded by the first node of the intelligent wireless access network. Based on the network requirements in the service request, it identifies the second node-1 and the second node-2 of the intelligent wireless access network registered with the general computing resource scheduling function; based on the requirements for artificial intelligence models in the service request, it identifies the target artificial intelligence model-1 and the target artificial intelligence model-2; it deploys the target artificial intelligence model-1 to the second node-1 of the intelligent wireless access network and the target artificial intelligence model-2 to the second node-2 of the intelligent wireless access network.

[0097] The model inference task is performed in the second node-1 of the intelligent radio access network to complete the inference of the target artificial intelligence model-1 and generate inference result-1. The second node-1 of the intelligent radio access network sends the inference result-1 to the first node of the intelligent radio access network.

[0098] The model inference task is performed in the second node-2 of the intelligent radio access network to complete the inference of the target artificial intelligence model-2 and generate inference result-2. The second node-2 of the intelligent radio access network sends the inference result-2 to the first node of the intelligent radio access network.

[0099] The first node of the intelligent wireless access network receives inference result-1 and inference result-2, and sends inference result-1 and inference result-2 to the target device.

[0100] After receiving inference result-1 and inference result-2, the target device executes business instructions in the business scenario based on the inference results.

[0101] This disclosure achieves cost reduction by decreasing the robot's reliance on high-performance hardware and significantly reducing manufacturing costs through shared computing resources via AIRAN. It also reduces power consumption by offloading energy-intensive intelligent processing tasks to the AIRAN side, thereby significantly reducing the robot's power consumption and improving endurance. Furthermore, it improves computing power utilization by efficiently integrating and scheduling fragmented computing power through the RAN AI Layer, reducing wasted computing resources. Finally, it ensures real-time performance and reliability by leveraging the low-latency communication capabilities of AI RAN to ensure the robot's real-time performance and reliability in complex environments. Finally, it enhances system flexibility and scalability by supporting rapid iteration and expansion of new intelligent models and algorithms based on the dynamic deployment capabilities of the RAN AI Layer.

[0102] Figure 6Another schematic diagram of a communication method according to an embodiment of this disclosure is shown, such as... Figure 6 As shown in the embodiments of this disclosure, a communication method is also provided, applied to a first node of an intelligent wireless access network, the method comprising:

[0103] Step S602: Receive the service request sent by the target device; the target device connects to the first node of the intelligent wireless access network;

[0104] Step S604: Forward the service request to the general computing resource scheduling function, so that the general computing resource scheduling function can deploy the target artificial intelligence model to the second node of the intelligent wireless access network according to the service request; the general computing resource scheduling function belongs to the wireless intelligent management and orchestration function layer; the second node of the intelligent wireless access network is used to complete the inference of the target artificial intelligence model and send the inference result to the first node of the intelligent wireless access network;

[0105] Step S606: Receive the inference result and forward it to the target device.

[0106] It should be noted that the acquisition, storage, use, and processing of data in this disclosed technical solution comply with the relevant provisions of national laws and regulations. The various types of data, such as personal identity data, operational data, and behavioral data related to individuals, customers, and groups, obtained in the embodiments of this disclosure have all been authorized.

[0107] Based on the same inventive concept, this disclosure also provides a communication device, as described in the following embodiments. Since the principle by which this device embodiment solves the problem is similar to that of the above-described method embodiments, the implementation of this device embodiment can refer to the implementation of the above-described method embodiments, and repeated details will not be elaborated further.

[0108] Figure 7 This diagram illustrates a communication device according to an embodiment of the present disclosure, such as... Figure 7 As shown, the device includes:

[0109] The service request receiving module 701 is used to receive service requests forwarded by the first node of the intelligent wireless access network; the first node of the intelligent wireless access network is connected to the target device, and the service request is sent from the target device to the first node of the intelligent wireless access network.

[0110] The target artificial intelligence model deployment module 702 is used to deploy the target artificial intelligence model to the second node of the intelligent wireless access network according to the service request, so that the second node of the intelligent wireless access network completes the inference of the target artificial intelligence model and sends the inference result to the first node of the intelligent wireless access network; the first node of the intelligent wireless access network is also used to send the inference result to the target device.

[0111] It should be noted that the aforementioned business request receiving module 701 and target artificial intelligence model deployment module 702 correspond to S202 to S204 in the method embodiment. The examples and application scenarios implemented by the above modules and corresponding steps are the same, but are not limited to the content disclosed in the above method embodiment. It should be noted that the above modules, as part of the apparatus, can be executed in a computer system such as a set of computer-executable instructions.

[0112] Based on the same inventive concept, this disclosure also provides a communication device, as described in the following embodiments. Since the principle by which this device embodiment solves the problem is similar to that of the above-described method embodiments, the implementation of this device embodiment can refer to the implementation of the above-described method embodiments, and repeated details will not be elaborated further.

[0113] Figure 8 Another schematic diagram of a communication device according to an embodiment of this disclosure is shown, such as... Figure 8 As shown, the device includes:

[0114] The service request receiving module 801 is used to receive service requests sent by the target device; the target device is connected to the first node of the intelligent wireless access network.

[0115] The service request forwarding module 802 is used to forward the service request to the general computing resource scheduling function, so that the general computing resource scheduling function can deploy the target artificial intelligence model to the second node of the intelligent wireless access network according to the service request; the general computing resource scheduling function belongs to the wireless intelligent management and orchestration function layer; the second node of the intelligent wireless access network is used to complete the inference of the target artificial intelligence model and send the inference result to the first node of the intelligent wireless access network;

[0116] The inference result forwarding module 803 is used to receive the inference result and forward it to the target device.

[0117] It should be noted that the aforementioned service request receiving module 801, service request forwarding module 802, and inference result forwarding module 803 correspond to S602 to S606 in the method embodiment. The examples and application scenarios implemented by these modules and their corresponding steps are the same, but they are not limited to the content disclosed in the above method embodiment. It should also be noted that these modules, as part of the apparatus, can be executed in a computer system, such as a set of computer-executable instructions.

[0118] Those skilled in the art will understand that various aspects of this disclosure can be implemented as a system, method, or program product. Therefore, various aspects of this disclosure can be specifically implemented in the following forms: a completely hardware implementation, a completely software implementation (including firmware, microcode, etc.), or a combination of hardware and software aspects, collectively referred to herein as a "circuit," "module," or "system."

[0119] The following reference Figure 9 To describe an electronic device 900 according to such an embodiment of the present disclosure. Figure 9 The electronic device 900 shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments disclosed herein.

[0120] like Figure 9 As shown, the electronic device 900 is manifested in the form of a general-purpose computing device. The components of the electronic device 900 may include, but are not limited to: at least one processing unit 910, at least one storage unit 920, and a bus 930 connecting different system components (including the storage unit 920 and the processing unit 910).

[0121] The storage unit stores program code that can be executed by the processing unit 910, causing the processing unit 910 to perform the steps described in the "Exemplary Methods" section of this specification according to various exemplary embodiments of this disclosure. For example, the processing unit 910 can perform the following steps of the above method embodiment: applied to a general computing resource scheduling function, the general computing resource scheduling function belonging to the wireless intelligent management and orchestration function layer, the method includes: receiving a service request forwarded by a first node of an intelligent wireless access network; the first node of the intelligent wireless access network connects to a target device, the service request being sent from the target device to the first node of the intelligent wireless access network; according to the service request, deploying a target artificial intelligence model to a second node of the intelligent wireless access network, so that the second node of the intelligent wireless access network completes the inference of the target artificial intelligence model and sends the inference result to the first node of the intelligent wireless access network; the first node of the intelligent wireless access network is also used to send the inference result to the target device.

[0122] Storage unit 920 may include readable media in the form of volatile storage units, such as random access memory (RAM) 9201 and / or cache memory 9202, and may further include read-only memory (ROM) 9203.

[0123] Storage unit 920 may also include a program / utility 9204 having a set (at least one) program module 9205, such program module 9205 including but not limited to: operating system, one or more application programs, other program modules and program data, each or some combination of these examples may include an implementation of a network environment.

[0124] Bus 930 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0125] Electronic device 900 can also communicate with one or more external devices 940 (e.g., keyboard, pointing device, Bluetooth device, etc.), and with one or more devices that enable a user to interact with electronic device 900, and / or with any device that enables electronic device 900 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 950. Furthermore, electronic device 900 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 960. As shown, network adapter 960 communicates with other modules of electronic device 900 via bus 930. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 900, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0126] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0127] In particular, according to embodiments of this disclosure, the process described above with reference to the flowchart can be implemented as a computer program product, which includes a computer program that, when executed by a processor, implements the above-described communication method.

[0128] In exemplary embodiments of this disclosure, a computer-readable storage medium is also provided, which may be a readable signal medium or a readable storage medium. A program product capable of implementing the methods described above is stored thereon. In some possible implementations, various aspects of this disclosure may also be implemented as a program product including program code, which, when run on a terminal device, causes the terminal device to perform the steps according to various exemplary embodiments of this disclosure described in the "Exemplary Methods" section of this specification.

[0129] More specific examples of computer-readable storage media in this disclosure may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0130] In this disclosure, a computer-readable storage medium may include a data signal propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of transmitting, propagating, or transmitting a program for use by or in connection with an instruction execution system, apparatus, or device.

[0131] Optionally, the program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0132] In practical implementation, program code for performing the operations of this disclosure can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0133] It should be noted that although several modules or units for the device used to perform actions have been mentioned in the detailed description above, this division is not mandatory. In fact, according to embodiments of this disclosure, the features and functions of two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units.

[0134] Furthermore, although the steps of the method in this disclosure are described in a specific order in the accompanying drawings, this does not require or imply that the steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additional or alternative steps may be omitted, multiple steps may be combined into one step, and / or a step may be broken down into multiple steps.

[0135] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, mobile terminal, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0136] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the appended claims.

Claims

1. A communication method, characterized in that, The method, applied to the general computing resource scheduling function, which belongs to the wireless intelligent management and orchestration function layer, includes: The system receives a service request forwarded by a first node of the intelligent wireless access network; the first node of the intelligent wireless access network is connected to the target device, and the service request is sent from the target device to the first node of the intelligent wireless access network. According to the service request, the target artificial intelligence model is deployed to the second node of the intelligent wireless access network, so that the second node of the intelligent wireless access network completes the inference of the target artificial intelligence model and sends the inference result to the first node of the intelligent wireless access network; the first node of the intelligent wireless access network is also used to send the inference result to the target device; Wherein, the target device is in a business scenario, and the business request is determined by the target device according to the business instructions in the business scenario. The business request includes: the network requirements and the artificial intelligence model requirements of the target device when executing the business instructions in the business scenario. Wherein, the first node of the intelligent wireless access network is an intelligent wireless access network node that is adjacent to the target device in the service scenario; The target device is a robot, and the business scenario is an embodied intelligence scenario.

2. The communication method according to claim 1, characterized in that, Before forwarding the service request, the first node of the intelligent wireless access network further includes: The first node of the intelligent wireless access network determines that the current network condition meets the network requirements in the service request.

3. The communication method according to claim 2, characterized in that, According to the aforementioned service request, the target artificial intelligence model is deployed to the second node of the intelligent wireless access network, including: Based on the network requirements in the service request, determine the second node of the intelligent wireless access network registered with the general computing resource scheduling function; Based on the requirements for artificial intelligence models in the business request, determine the target artificial intelligence model; The target artificial intelligence model is deployed to the second node of the intelligent wireless access network.

4. The communication method according to claim 1, characterized in that, Also includes: The target device is also used to execute the business instruction in the business scenario based on the reasoning result.

5. A communication method, characterized in that, Applied to the first node of an intelligent wireless access network, the method includes: Receive a service request sent by a target device; the target device is connected to the first node of the intelligent wireless access network; The service request is forwarded to the general computing resource scheduling function, so that the general computing resource scheduling function deploys the target artificial intelligence model to the second node of the intelligent wireless access network according to the service request; the general computing resource scheduling function belongs to the wireless intelligent management and orchestration function layer; the second node of the intelligent wireless access network is used to complete the inference of the target artificial intelligence model and send the inference result to the first node of the intelligent wireless access network; Receive the inference result and forward it to the target device; Wherein, the target device is in a business scenario, and the business request is determined by the target device according to the business instructions in the business scenario. The business request includes: the network requirements and the artificial intelligence model requirements of the target device when executing the business instructions in the business scenario. Wherein, the first node of the intelligent wireless access network is an intelligent wireless access network node that is adjacent to the target device in the service scenario; The target device is a robot, and the business scenario is an embodied intelligence scenario.

6. A communication device, characterized in that, The device, which is used for general computing resource scheduling, and which belongs to the wireless intelligent management and orchestration function layer, includes: A service request receiving module is used to receive service requests forwarded by the first node of the intelligent wireless access network; the first node of the intelligent wireless access network is connected to the target device, and the service request is sent from the target device to the first node of the intelligent wireless access network. The target AI model deployment module is used to deploy the target AI model to the second node of the intelligent wireless access network according to the service request, so that the second node of the intelligent wireless access network can complete the inference of the target AI model and send the inference result to the first node of the intelligent wireless access network; the first node of the intelligent wireless access network is also used to send the inference result to the target device; Wherein, the target device is in a business scenario, and the business request is determined by the target device according to the business instructions in the business scenario. The business request includes: the network requirements and the artificial intelligence model requirements of the target device when executing the business instructions in the business scenario. Wherein, the first node of the intelligent wireless access network is an intelligent wireless access network node that is adjacent to the target device in the service scenario; The target device is a robot, and the business scenario is an embodied intelligence scenario.

7. A communication device, characterized in that, The device, applied to the first node of a smart wireless access network, includes: A service request receiving module is used to receive service requests sent by a target device; the target device is connected to the first node of the intelligent wireless access network. A service request forwarding module is used to forward the service request to the general computing resource scheduling function, so that the general computing resource scheduling function can deploy the target artificial intelligence model to the second node of the intelligent wireless access network according to the service request; the general computing resource scheduling function belongs to the wireless intelligent management and orchestration function layer; the second node of the intelligent wireless access network is used to complete the inference of the target artificial intelligence model and send the inference result to the first node of the intelligent wireless access network; The inference result forwarding module is used to receive the inference result and forward it to the target device; Wherein, the target device is in a business scenario, and the business request is determined by the target device according to the business instructions in the business scenario. The business request includes: the network requirements and the artificial intelligence model requirements of the target device when executing the business instructions in the business scenario. Wherein, the first node of the intelligent wireless access network is an intelligent wireless access network node that is adjacent to the target device in the service scenario; The target device is a robot, and the business scenario is an embodied intelligence scenario.

8. An electronic device, characterized in that, include: processor; as well as Memory for storing the executable instructions of the processor; The processor is configured to execute the communication method of any one of claims 1 to 4 or claim 5 by executing the executable instructions.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the communication method according to any one of claims 1 to 4 or claim 5.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the communication method according to any one of claims 1 to 4 or claim 5.

Images