Resource allocation method and device based on AI traffic awareness, computer equipment, storage medium and program product

Abstract

The invention relates to a resource allocation method and device based on AI flow perception, computer equipment, a storage medium and a program product, and the method comprises the steps: obtaining AI flow perception information of a user terminal and a corresponding demand resource table, carrying out the clustering of target tasks of a plurality of user terminals, and obtaining a plurality of target task groups, the demand resource tables of all the target task groups are merged to obtain a target resource table, demand data and a demand model are obtained according to the target resource table for each target task group, and then communication resources and computing resources corresponding to the target task groups and corresponding resource allocation schemes are obtained. And establishing a resource mapping table on the basis of the resource allocation schemes corresponding to all the target task groups, so that the base station equipment transmits corresponding demand data and demand models to the user terminal on the basis of the resource mapping table, and allocates corresponding computing resources to the user terminal on the basis of the resource mapping table. By adopting the method, real-time resource allocation can be effectively realized.

Description

Technical Field

[0001] This application relates to the field of communication technologies, and in particular, to a resource allocation method, apparatus, computer device, storage medium, and program product based on AI traffic awareness. Background Art

[0002] With the rapid development of information technology, the 6G network will not only significantly improve data transmission speed, but also combine with cutting-edge technologies such as artificial intelligence, the Internet of Things, and edge computing to form a fully intelligent ecosystem. This transformation will enable the 6G network to provide more efficient and flexible communication services to meet the requirements of high-demand application scenarios such as autonomous driving, smart cities, and virtual reality.

[0003] In traditional communication networks, the traffic form mainly focuses on point-to-point communication, based on specific protocols and static resource allocation methods. However, in the 6G network, this traditional traffic form will undergo profound changes and gradually transform into a more dynamic and flexible "Artificial Intelligence (AI) traffic". AI traffic incorporates AI elements into the traditional traffic form, including AI models, AI services, AI-related data, AI resources, etc. Traditional traffic awareness and processing methods are no longer suitable for the new form of AI traffic.

[0004] Based on this, how to effectively sense the traffic for these AI elements, quickly obtain AI element information, and make decisions such as resource allocation, data transmission, and traffic control based on the traffic awareness information has become an urgent problem to be solved. Summary of the Invention

[0005] Based on this, in view of the above technical problems, it is necessary to provide a resource allocation method, apparatus, computer device, storage medium, and program product based on AI traffic awareness that can effectively achieve real-time resource allocation.

[0006] In a first aspect, this application provides a resource allocation method based on AI traffic awareness, including:

[0007] During the process of a user terminal sending AI traffic to a radio access network through a base station device, obtain the AI traffic awareness information corresponding to the user terminal, and based on the AI traffic awareness information, obtain the demand resource table corresponding to the user terminal; the AI traffic awareness information includes data information, model information, task information, resource information, and performance information; the task information includes a target task;

[0008] Perform clustering processing on the target tasks corresponding to multiple user terminals to obtain multiple target task groups, and respectively merge the demand resource tables corresponding to each target task group to obtain the target resource table corresponding to the target task group;

[0009] For each target task group, according to the target resource table corresponding to the target task group, obtain the demand data and demand model corresponding to the target task group, and based on the demand data and demand model, obtain the communication resources and computing resources corresponding to the target task group;

[0010] Obtain a resource allocation plan corresponding to the communication resources and computing resources, and based on the resource allocation plans corresponding to all target task groups, establish a resource mapping table, so that the base station device transmits the corresponding demand data and demand model for the user terminal based on the resource mapping table, and allocates the corresponding computing resources for the user terminal based on the resource mapping table; the resource mapping table is used to represent the mapping relationship between the target task group and the resource allocation plan.

[0011] In one embodiment, the demand resource table includes a data mapping table and a model mapping table; the step of obtaining the demand resource table corresponding to the user terminal according to the AI traffic awareness information includes:

[0012] For each target task, obtain the task data and task model of the target task; the task data includes the data content of the target task; the task model includes the model storage file and configuration file of the target task;

[0013] Establish a data mapping table according to all target tasks and the corresponding task data; the data mapping table is used to represent the mapping relationship between the target task and the task data;

[0014] Establish a model mapping table according to all target tasks and the model IDs of the corresponding task models; the model mapping table is used to represent the mapping relationship between the target task and the model ID.

[0015] In one embodiment, the step of clustering the target tasks corresponding to multiple user terminals to obtain multiple target task groups includes:

[0016] For each user terminal, respectively extract features from the data mapping table and the model mapping table to obtain the corresponding data feature information and model feature information, and based on the data feature information and the model feature information, obtain the feature vector corresponding to the target task of the user terminal;

[0017] Cluster the feature vectors corresponding to the target tasks of all user terminals to obtain multiple target task groups.

[0018] In one embodiment, the step of obtaining the demand data and demand model corresponding to the target task group according to the target resource table corresponding to the target task group includes:

[0019] Obtain the data storage node corresponding to the data mapping table;

[0020] Request the corresponding required data from the data storage node according to the data format and data type in the data mapping table;

[0021] For the model ID in the model mapping table, perform the corresponding life cycle management operation of the model ID, and obtain the required model according to the operation result.

[0022] In one embodiment, the steps of obtaining the communication resources and computing resources corresponding to the target task group according to the required data and the required model include:

[0023] For each user terminal corresponding to the target task group, obtain the user ID corresponding to the user terminal, and respectively obtain the transmission paths corresponding to the required data and the required model according to the user ID;

[0024] Obtain the communication resources corresponding to the transmission path;

[0025] Obtain the model identification information corresponding to the target task group, and obtain the computing resources corresponding to the target task group according to the model identification information.

[0026] In one embodiment, the intelligent control unit includes at least one computing power resource pool; the method further includes:

[0027] In the case of a sudden change in the AI traffic sent by the user terminal, allocate the corresponding computing power resource pool for the AI traffic according to the current traffic state of the AI traffic, so as to obtain the AI traffic perception information corresponding to the user terminal through the computing power resource pool.

[0028] In a second aspect, the present application also provides a resource allocation device based on AI traffic perception, including:

[0029] A traffic perception module, configured to obtain the AI traffic perception information corresponding to the user terminal during the process of the user terminal sending AI traffic to the radio access network through the base station device, and obtain the required resource table corresponding to the user terminal according to the AI traffic perception information; the AI traffic perception information includes data information, model information, task information, resource information, and performance information;

[0030] A task clustering module, configured to cluster the target tasks corresponding to multiple user terminals to obtain multiple target task groups, and respectively merge the required resource tables corresponding to each target task group to obtain the target resource table corresponding to the target task group;

[0031] A resource acquisition module, configured to, for each target task group, obtain the required data and the required model corresponding to the target task group according to the target resource table corresponding to the target task group, and obtain the communication resources and computing resources corresponding to the target task group according to the required data and the required model;

[0032] A resource allocation module, configured to obtain a resource allocation scheme corresponding to communication resources and computing resources, and establish a resource mapping table based on the resource allocation schemes corresponding to all target task groups, so that the base station device transmits corresponding demand data and demand models to the user terminal based on the resource mapping table, and allocate corresponding computing resources to the user terminal based on the resource mapping table; the resource mapping table is used to represent the mapping relationship between the target task group and the resource allocation scheme.

[0033] In a third aspect, the present application further provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the method steps of any item in the first aspect are implemented.

[0034] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the method steps of any item in the first aspect are implemented.

[0035] In a fifth aspect, the present application further provides a computer program product, including a computer program. When the computer program is executed by a processor, the method steps of any item in the first aspect are implemented.

[0036] The above-mentioned resource allocation method, device, computer device, storage medium, and program product based on AI traffic awareness can efficiently sense AI traffic by deploying an intelligent control unit in the radio access network to form an intelligent layer of the radio access network, obtain the demand resource table of the user terminal in real time, provide a customized resource allocation scheme, and achieve a rapid response to user needs. By performing resource merging and optimized allocation according to the clustering results of the target task groups, intelligent allocation of model resources, data resources, communication resources, and computing resources is realized, thereby effectively realizing real-time resource allocation. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments of the present application or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, other related drawings can be obtained based on these drawings without creative efforts.

[0038] Figure 1 It is an application environment diagram of the resource allocation method for AI traffic awareness in an embodiment;

[0039] Figure 2 It is a flowchart of the resource allocation method for AI traffic awareness in an embodiment;

[0040] Figure 3 It is a flowchart of the resource allocation method for AI traffic awareness in another embodiment;

[0041] Figure 4 It is a structural block diagram of a resource allocation device for AI traffic perception in an embodiment;

[0042] Figure 5 It is an internal structure diagram of a computer device in an embodiment. Detailed implementation manners

[0043] In order to make the objectives, technical solutions, and advantages of the present application clearer and more understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0044] The resource allocation method for AI traffic perception provided by the embodiments of the present application can be applied to an application environment as Figure 1 shown. Among them, the user terminal 102 communicates with the intelligent control unit 106 through the base station device 104. Among them, the intelligent control unit 106 is used to obtain the AI traffic perception information corresponding to the user terminal 102 during the process that the user terminal 102 sends AI traffic to the radio access network through the base station device 104, and according to the AI traffic perception information, obtain the demand resource table corresponding to the user terminal 102, perform clustering processing on the target tasks corresponding to multiple user terminals 102 to obtain multiple target task groups, respectively merge the demand resource tables corresponding to each target task group to obtain the target resource table corresponding to the target task group, for each target task group, according to the target resource table corresponding to the target task group, obtain the demand data and demand model corresponding to the target task group, and according to the demand data and demand model, obtain the communication resources and computing resources corresponding to the target task group, obtain the resource allocation scheme corresponding to the communication resources and computing resources, and based on the resource allocation schemes corresponding to all target task groups, establish a resource mapping table, so that the base station device 104 transmits the corresponding demand data for the user terminal 102 based on the resource mapping table. Among them, the user terminal 102 can be but is not limited to various personal computers, laptop computers, smart phones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart vehicle-mounted devices, projection devices, etc. The portable wearable devices can be smart watches, smart bracelets, head-mounted devices, etc. The head-mounted device can be a virtual reality (VR) device, an augmented reality (AR) device, a smart glasses, etc. The base station device 104 is deployed at the network edge of the radio access network, and the intelligent control unit 106 is deployed in the intelligent layer of the radio access network.

[0045] In an exemplary embodiment, as Figure 2As shown, a resource allocation method based on AI traffic awareness is provided. Taking the intelligent control unit 106 in Figure 1 as an example for illustration, it includes the following steps 202 to 208. Among them:

[0046] S202: During the process that the user terminal sends AI traffic to the radio access network through the base station device, obtain the AI traffic awareness information corresponding to the user terminal, and according to the AI traffic awareness information, obtain the required resource table corresponding to the user terminal; the AI traffic awareness information includes data information, model information, task information, resource information, and performance information; the task information includes the target task.

[0047] Optionally, the user terminal is deployed at the user node, and the base station device is deployed at the transmission node, located at the network edge of the radio access network, including a Centralized Unit (CU), a Distributed Unit (DU), and a Radio Unit (RU). Among them, the CU includes a user plane (CU-UP) and a control plane (CU-CP). The intelligent control unit is deployed at the network node, located in the radio access network architecture. By introducing intelligent functions into the radio access network, the intelligent layer of the radio access network is obtained.

[0048] Optionally, during the process that the user terminal sends AI traffic to the radio access network through the base station device, the intelligent control unit parses the AI traffic packet to obtain the AI traffic awareness information corresponding to the user terminal. Among them, compared with traditional communication traffic, AI traffic contains more information in the IP header and data part (Payload), but still follows the basic format of the IP packet, that is, the format of Header + Payload. Among them, the AI traffic awareness information includes data information, model information, task information, resource information, and performance information, etc. In practical applications, since the information contained in AI traffic may be intertwined, methods such as data analysis and decoding are required to extract key information. And because the information contained in each AI traffic packet is different, it may be necessary to sense multiple AI traffic packets within a period of time, or sense each AI traffic packet one by one, or set other sensing rules. In some embodiments, the intelligent control unit generates an AI traffic awareness information list according to the AI traffic awareness information of all user terminals sensed, which is formed by arranging the AI traffic awareness information of each user node in sequence. Among them, the arrangement order can be in the order of the user ID in the user terminal.

[0049] Exemplarily, the AI traffic awareness information includes various types of information as shown in Table 1.

[0050] Table 1 Example of AI Traffic Awareness Information

[0051]

[0052] Optionally, the intelligent control unit obtains a demand resource table corresponding to the user terminal according to the AI traffic perception information, where the demand resource table is used to represent the resources required to implement the target task requested by the user terminal, such as communication resources and computing resources, etc.

[0053] S204: Cluster the target tasks corresponding to multiple user terminals to obtain multiple target task groups, and merge the demand resource tables corresponding to each target task group respectively to obtain the target resource table corresponding to the target task group.

[0054] Optionally, in practical applications, the radio access network will receive AI traffic from multiple user nodes. By clustering the target tasks corresponding to multiple user terminals, the target tasks belonging to the same type are grouped together to obtain multiple target task groups. For each target task group, the demand resource tables corresponding to each user terminal within the group are merged, and the resource requirements of all tasks within the group are comprehensively considered to obtain the target resource table corresponding to the target task group. Since the required resources for the same type of target tasks are usually similar, through clustering processing, resource allocation can be directly performed for different target task groups, improving the efficiency of resource allocation.

[0055] S206: For each target task group, obtain the demand data and demand model corresponding to the target task group according to the target resource table corresponding to the target task group, and obtain the communication resources and computing resources corresponding to the target task group according to the demand data and demand model.

[0056] Optionally, for each target task group, obtain the corresponding demand data and demand model according to the demand resource data represented by the corresponding target resource table, where the demand data refers to the data resources that need to be allocated to the user terminal, and the demand model refers to the model resources that need to be allocated to the user terminal. Then, according to the demand data and demand model, obtain the communication resources and computing resources corresponding to the target task group, where the communication resources include the resources for realizing the transmission of demand data and the resources for realizing the transmission of demand models, and the computing resources include the resources for realizing the processing of demand data and the resources for realizing the processing of demand models.

[0057] S208: Obtain a resource allocation scheme corresponding to the communication resources and computing resources, and establish a resource mapping table based on the resource allocation schemes corresponding to all target task groups, so that the base station device transmits the corresponding demand data and demand models to the user terminal based on the resource mapping table, and allocates the corresponding computing resources to the user terminal based on the resource mapping table; the resource mapping table is used to represent the mapping relationship between the target task group and the resource allocation scheme.

[0058] Optionally, based on the communication resources and computing resources corresponding to the target task groups, determine a resource allocation scheme for implementing the allocation of communication resources and computing resources, that is, determine how to allocate the available communication resources and computing resources to each target task group. Based on the resource allocation schemes corresponding to all target task groups, establish a resource mapping table, where the resource mapping table is used to represent the mapping relationship between each target task group and the corresponding resource allocation scheme. After receiving the instruction from the intelligent control unit, the base station device transmits the corresponding demand data and demand model to the user terminal according to the resource mapping table, and allocates the corresponding computing resources to the user terminal based on the resource mapping table, ensuring that the AI tasks of each user terminal can obtain appropriate resource support.

[0059] In the above resource allocation method based on AI traffic awareness, by deploying an intelligent control unit in the radio access network to form an intelligent layer of the radio access network, it can efficiently sense AI traffic, obtain the demand resource table of the user terminal in real time, provide a customized resource allocation scheme, and achieve a rapid response to user demands. By performing resource merging and optimized allocation according to the clustering results of the target task groups, intelligent allocation of model resources, data resources, communication resources, and computing resources is achieved, thus effectively realizing real-time resource allocation.

[0060] In an exemplary embodiment, the demand resource table includes a data mapping table and a model mapping table; the step of obtaining the demand resource table corresponding to the user terminal according to the AI traffic awareness information includes: for each target task, obtaining the task data and task model of the target task; the task data includes the data content of the target task; the task model includes the model storage file and configuration file of the target task; establishing a data mapping table according to all target tasks and the corresponding task data; the data mapping table is used to represent the mapping relationship between the target task and the task data; establishing a model mapping table according to the model IDs of all target tasks and the corresponding task models; the model mapping table is used to represent the mapping relationship between the target task and the model ID.

[0061] Optionally, the demand resource table includes a data mapping table and a model mapping table, where the data mapping table is used to represent the mapping relationship between the target task and the demand data, and the model mapping table is used to represent the mapping relationship between the target task and the model ID. Specifically, for each target task, extract the required data content (i.e., demand data), model storage file, and configuration file (i.e., demand model) from the AI traffic awareness information, associate all target tasks and their corresponding demand data to form a data mapping table, and associate all target tasks and their corresponding model IDs to form a model mapping table. Through the data mapping table, each target task is accurately associated with the required data content to ensure the efficient allocation and use of data. Through the model mapping table, each target task is accurately associated with the required model to ensure the rapid invocation and deployment of the model.

[0062] Exemplarily, for the requirement data of the target task, information such as the data flow direction, data form, data storage location, data type, and data usage specification of the requirement data is obtained, and the formed data mapping table can be expressed as: [Target task 1: Data requirement 1;...; Target task k: Data requirement k]. For the requirement model of the target task, the mapping relationship between the model lifecycle management operations that the target task needs to execute and the specific model ID is obtained, and the formed model mapping table can be expressed as: [AI-related target task 1: Lifecycle management operation p, model ID m ;...; AI-related target task k: Lifecycle management operation q, model ID n .

[0063] In this embodiment, by accurately associating the target task with the requirement data, it is ensured that each task can quickly obtain the required data content, avoiding waste and duplicate allocation of data resources. By accurately associating the target task with the model ID, it is ensured that each task can quickly call the required model, improving the utilization efficiency of model resources. Furthermore, through the data mapping table and the model mapping table, the intelligent matching of tasks and resources is realized, thereby improving the resource allocation efficiency.

[0064] In an exemplary embodiment, the steps of clustering the target tasks corresponding to multiple user terminals to obtain multiple target task groups include: for each user terminal, respectively extracting features from the data mapping table and the model mapping table to obtain the corresponding data feature information and model feature information, and based on the data feature information and the model feature information, obtaining the feature vector corresponding to the target task of the user terminal; clustering the feature vectors corresponding to the target tasks of all user terminals to obtain multiple target task groups.

[0065] Optionally, based on the data and model mapping relationship tables corresponding to each target task, the data and model feature information therein is extracted to generate the feature vector corresponding to the target task. Among them, the dimension of the feature vector needs to be consistent among all target tasks, and the feature vector includes multi-faceted features such as data and models. By summarizing the feature vectors corresponding to all target tasks, a clustering algorithm is executed, such as the K-Means algorithm, the DBSCAN clustering algorithm, the hierarchical clustering algorithm, etc. According to the output result of the clustering algorithm, all target tasks belonging to the same category are formed into a target task group, and target tasks belonging to different categories are formed into different target task groups. Among them, for each target task group, the information in the data mapping table and the model mapping table of each target task therein is summarized to form the target resource table corresponding to the target task group.

[0066] In this embodiment, through clustering processing, similar tasks of multiple user terminals are divided into the same group, enabling unified resource allocation and scheduling for the same group of tasks, thereby achieving efficient sharing of resources. Additionally, through task grouping, multiple target task groups can be processed in parallel, improving the efficiency of task processing.

[0067] In an exemplary embodiment, the steps of obtaining the demand data and demand model corresponding to the target task group according to the target resource table corresponding to the target task group include: obtaining the data storage node corresponding to the data mapping table; requesting the corresponding demand data from the data storage node according to the data format and data type in the data mapping table; for the model ID in the model mapping table, performing the corresponding life cycle management operation of the model ID, and obtaining the demand model according to the operation result.

[0068] Optionally, for the data mapping table, request the corresponding data resources from the data storage node corresponding to the data mapping table. For the model mapping table, perform the corresponding life cycle management operation of the model ID, and obtain the demand model according to the operation result, such as model training results, model inference results, or model update data, etc.

[0069] In this embodiment, through accurate positioning of the data storage node and data request, the latency of data acquisition is reduced. Through the model life cycle management operation, high-quality demand models are generated, ensuring the efficient execution of AI tasks, thereby achieving intelligent management of data resources.

[0070] In an exemplary embodiment, the steps of obtaining the communication resources and computing resources corresponding to the target task group according to the demand data and demand model include: for each user terminal corresponding to the target task group, obtaining the user ID corresponding to the user terminal, and respectively obtaining the transmission paths corresponding to the demand data and demand model according to the user ID; obtaining the communication resources corresponding to the transmission paths; obtaining the model identification information corresponding to the target task group, and obtaining the computing resources corresponding to the target task group according to the model identification information.

[0071] Optionally, obtain the user ID corresponding to each user terminal in the target task group respectively. The user ID can be determined according to the target task ID to ensure that each user terminal corresponds uniquely to the target task. The user ID is used to identify the user terminal and provide a unique identifier for data transmission and model transmission. Obtain the transmission paths corresponding to the demand data and the demand model respectively according to the user ID. Exemplarily, for the demand data, it can be carried by user plane signaling, and historical data can be obtained from the Operation, Administration and Maintenance (OAM) or Network Data Analytics Function (NWDAF), or real-time data can be collected from the Central Unit (CU) and the Distributed Unit (DU), so as to determine the transmission path of the demand data. For the demand model, it can be transmitted through user plane or control plane signaling. For example, it can be transmitted through the Media Access Control Control Element (MAC CE), Radio Resource Control (RRC) or Downlink Control Information (DCI), and methods such as model compression and encoding can be used to reduce the transmission overhead.

[0072] Further, according to the obtained demand data and demand model, obtain the communication resources and computing resources corresponding to the target task group. In practical applications, the allocation scheme of communication resources can adopt a serial or parallel method. The serial method means that all communication resources are allocated to a certain target task group for the transmission of data resources and model resources at the same time, and other target task groups are allocated at other times; the parallel scheme means that the communication resources are allocated to different target task groups without repetition for the transmission of data resources and model resources at the same time.

[0073] Optionally, the computing resources are used to implement processes such as model training and inference. The allocation scheme of the computing resources can adopt the principle of proportional fairness. According to the computing complexity and other information in the model identification information, the computing resources are allocated to all target task groups proportionally. Further, according to the resource allocation schemes corresponding to all target task groups, establish a resource mapping table. The resource mapping table is used to represent the mapping relationship between the target task group and the resource allocation scheme, so that the base station device can allocate corresponding resources, such as data resources, communication resources, computing resources, etc., to each target task group according to the information in the resource mapping table.

[0074] In this embodiment, by obtaining the transmission paths of the demand data and the demand model respectively according to the user ID, and obtaining the corresponding demand model according to the transmission paths, the transmission efficiency can be improved, the resource utilization can be optimized, and the real-time resource allocation can be effectively realized.

[0075] In an exemplary embodiment, the intelligent control unit includes at least one computing power resource pool; the method further includes: in the case of a sudden change in the AI traffic sent by the user terminal, according to the current traffic state of the AI traffic, allocating a corresponding computing power resource pool for the AI traffic, so as to obtain the AI traffic perception information corresponding to the user terminal through the computing power resource pool.

[0076] Optionally, the computing power resource pool is one or more computing resource sets in the intelligent control unit, which is used to support the execution of AI tasks. Through the computing power resource pool, dynamic computing resource allocation can be provided to support tasks such as AI traffic perception, model training, and inference. The intelligent control unit monitors the AI traffic state sent by the user terminal in real time, identifies sudden changes in the traffic (such as a sudden increase or decrease in traffic), and dynamically allocates a corresponding computing power resource pool according to the current traffic state of the AI traffic to ensure the efficient execution of AI tasks.

[0077] In this embodiment, by dynamically allocating the computing power resource pool according to the sudden change in the AI traffic, the AI traffic can be quickly processed to generate the AI traffic perception information corresponding to the user terminal, so as to effectively realize real-time resource allocation based on the AI traffic perception information.

[0078] In an exemplary embodiment, as Figure 3 shown, a resource allocation method based on AI traffic perception is provided, and the method includes the following steps:

[0079] (1) Obtain the AI traffic perception information corresponding to the user terminal through AI traffic perception: During the process that the user terminal sends AI traffic to the radio access network through the base station device, obtain the AI traffic perception information corresponding to the user terminal. Among them, the AI traffic perception information includes data information, model information, task information, resource information, and performance information; the task information includes target tasks.

[0080] (2) Generate a demand resource table according to the AI traffic perception information: The demand resource table includes a data mapping table and a model mapping table. For each target task, obtain the task data and task model of the target task; the task data includes the data content of the target task; the task model includes the model storage file and configuration file of the target task; establish a data mapping table according to all target tasks and the corresponding task data; the data mapping table is used to represent the mapping relationship between the target task and the task data; establish a model mapping table according to the model IDs of all target tasks and the corresponding task models; the model mapping table is used to represent the mapping relationship between the target task and the model ID.

[0081] (3) Cluster the target tasks to obtain multiple target task groups: For each user terminal, extract features from the data mapping table and the model mapping table respectively to obtain the corresponding data feature information and model feature information, and based on the data feature information and the model feature information, obtain the feature vectors corresponding to the target tasks of the user terminal; perform clustering processing on the feature vectors corresponding to the target tasks of all user terminals to obtain multiple target task groups; merge the demand resource tables corresponding to each target task group respectively to obtain the target resource table corresponding to the target task group.

[0082] (4) Obtain the demand data and demand model corresponding to the target task group according to the target resource table: For each target task group, obtain the data storage node corresponding to the data mapping table; according to the data format and data type in the data mapping table, request the corresponding demand data from the data storage node; for the model ID in the model mapping table, perform the corresponding life cycle management operation of the model ID, and obtain the demand model according to the operation result.

[0083] (5) Obtain the communication resources and computing resources corresponding to the target task group according to the transmission path of the resources: For each user terminal corresponding to the target task group, obtain the user ID corresponding to the user terminal, and respectively obtain the transmission paths corresponding to the demand data and the demand model according to the user ID; obtain the communication resources corresponding to the transmission path; obtain the model identification information corresponding to the target task group, and obtain the computing resources corresponding to the target task group according to the model identification information.

[0084] (6) Establish a resource mapping table based on the resource allocation scheme to achieve resource allocation for the user terminal: Obtain the resource allocation scheme corresponding to the communication resources and the computing resources, and based on the resource allocation schemes corresponding to all target task groups, establish a resource mapping table, so that the base station device transmits the corresponding demand data and demand model for the user terminal based on the resource mapping table, and allocates the corresponding computing resources for the user terminal based on the resource mapping table; the resource mapping table is used to represent the mapping relationship between the target task group and the resource allocation scheme. In the case of sudden changes in the AI traffic sent by the user terminal, allocate the corresponding computing resource pool for the AI traffic according to the current traffic state of the AI traffic, so as to obtain the AI traffic perception information corresponding to the user terminal through the computing resource pool.

[0085] In this embodiment, by deploying an intelligent control unit in the radio access network to form an intelligent layer of the radio access network, it can efficiently sense the AI traffic, obtain the demand resource table of the user terminal in real time, provide a customized resource allocation scheme, achieve a rapid response to user demands, and through resource merging and optimized allocation according to the clustering results of the target task groups, achieve intelligent allocation of model resources, data resources, communication resources and computing resources, thereby effectively realizing real-time resource allocation.

[0086] It should be understood that although the steps in the flowcharts involved in the above embodiments are shown in sequence according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless specifically stated herein, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0087] Based on the same inventive concept, an embodiment of the present application also provides an AI traffic awareness-based resource allocation device for implementing the above-mentioned AI traffic awareness-based resource allocation method. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the AI traffic awareness-based resource allocation device provided below can refer to the limitations on the AI traffic awareness-based resource allocation method in the above text, and will not be repeated here.

[0088] In an exemplary embodiment, as Figure 4 shown, an AI traffic awareness-based resource allocation device is provided, including: a traffic awareness module 10, a task clustering module 20, a resource acquisition module 30, and a resource allocation module 40, where:

[0089] The traffic awareness module 10 is configured to obtain AI traffic awareness information corresponding to a user terminal during the process of the user terminal sending AI traffic to the radio access network through a base station device, and obtain a demand resource table corresponding to the user terminal according to the AI traffic awareness information; the AI traffic awareness information includes data information, model information, task information, resource information, and performance information; the task information includes target tasks.

[0090] The task clustering module 20 is configured to perform clustering processing on the target tasks corresponding to multiple user terminals to obtain multiple target task groups, and merge the demand resource tables corresponding to each target task group respectively to obtain a target resource table corresponding to the target task group.

[0091] The resource acquisition module 30 is configured to, for each target task group, obtain the demand data and demand model corresponding to the target task group according to the target resource table corresponding to the target task group, and obtain the communication resources and computing resources corresponding to the target task group according to the demand data and demand model.

[0092] A resource allocation module 40, configured to obtain a resource allocation scheme corresponding to communication resources and computing resources, and establish a resource mapping table based on the resource allocation schemes corresponding to all target task groups, so that the base station device transmits corresponding required data and required models to the user terminal based on the resource mapping table, and allocates corresponding computing resources to the user terminal based on the resource mapping table; the resource mapping table is used to represent the mapping relationship between the target task group and the resource allocation scheme.

[0093] In an exemplary embodiment, the required resource table includes a data mapping table and a model mapping table; the traffic awareness module 10 is further configured to, for each target task, obtain the task data and task model of the target task; the task data includes the data content of the target task; the task model includes the model storage file and configuration file of the target task; establish a data mapping table according to all target tasks and the corresponding task data; the data mapping table is used to represent the mapping relationship between the target task and the task data; establish a model mapping table according to the model IDs of all target tasks and the corresponding task models; the model mapping table is used to represent the mapping relationship between the target task and the model ID.

[0094] In an exemplary embodiment, the task clustering module 20 is further configured to, for each user terminal, respectively extract features from the data mapping table and the model mapping table to obtain corresponding data feature information and model feature information, and obtain a feature vector corresponding to the target task of the user terminal according to the data feature information and the model feature information; perform clustering processing on the feature vectors corresponding to the target tasks of all user terminals to obtain multiple target task groups.

[0095] In an exemplary embodiment, the resource acquisition module 30 is configured to obtain a data storage node corresponding to the data mapping table; request corresponding required data from the data storage node according to the data format and data type in the data mapping table; for the model ID in the model mapping table, perform a life cycle management operation corresponding to the model ID, and obtain the required model according to the operation result.

[0096] In an exemplary embodiment, the resource acquisition module 30 is further configured to, for each user terminal corresponding to the target task group, obtain the user ID corresponding to the user terminal, and respectively obtain the transmission paths corresponding to the required data and the required model according to the user ID; obtain the communication resources corresponding to the transmission paths; obtain the model identification information corresponding to the target task group, and obtain the computing resources corresponding to the target task group according to the model identification information.

[0097] In an exemplary embodiment, the intelligent control unit includes at least one computing power resource pool; the resource allocation module 40 is further configured to, when there is a sudden change in the AI traffic sent by the user terminal, allocate a corresponding computing power resource pool for the AI traffic according to the current traffic state of the AI traffic, so as to obtain the AI traffic perception information corresponding to the user terminal through the computing power resource pool.

[0098] Each module in the above resource allocation device based on AI traffic perception can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor in the computer device in the form of hardware or be independent of the processor, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0099] In an exemplary embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 5 shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit, and an input device. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface, the display unit, and the input device are connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used for exchanging information between the processor and external devices. The communication interface of the computer device is used for communicating with external terminals in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a resource allocation method based on AI traffic perception. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device, or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, a touchpad, or a mouse, etc.

[0100] Those skilled in the art can understand that Figure 5 the structure shown in is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0101] In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the following steps are implemented: during the process that a user terminal sends AI traffic to a radio access network through a base station device, obtain the AI traffic perception information corresponding to the user terminal, and according to the AI traffic perception information, obtain the demand resource table corresponding to the user terminal; the AI traffic perception information includes data information, model information, task information, resource information, and performance information; the task information includes a target task; perform clustering processing on the target tasks corresponding to multiple user terminals to obtain multiple target task groups, and respectively merge the demand resource tables corresponding to each target task group to obtain the target resource table corresponding to the target task group; for each target task group, according to the target resource table corresponding to the target task group, obtain the demand data and demand model corresponding to the target task group, and according to the demand data and demand model, obtain the communication resources and computing resources corresponding to the target task group; obtain the resource allocation scheme corresponding to the communication resources and computing resources, and based on the resource allocation schemes corresponding to all target task groups, establish a resource mapping table, so that the base station device transmits the corresponding demand data and demand model to the user terminal based on the resource mapping table, and allocates the corresponding computing resources to the user terminal based on the resource mapping table; the resource mapping table is used to represent the mapping relationship between the target task group and the resource allocation scheme.

[0102] In an embodiment, the demand resource table includes a data mapping table and a model mapping table; obtaining the demand resource table corresponding to the user terminal according to the AI traffic perception information involved when the processor executes the computer program includes: for each target task, obtain the task data and task model of the target task; the task data includes the data content of the target task; the task model includes the model storage file and configuration file of the target task; establish a data mapping table according to all target tasks and the corresponding task data; the data mapping table is used to represent the mapping relationship between the target task and the task data; establish a model mapping table according to the model IDs of all target tasks and the corresponding task models; the model mapping table is used to represent the mapping relationship between the target task and the model ID.

[0103] In an embodiment, the clustering processing on the target tasks corresponding to multiple user terminals to obtain multiple target task groups involved when the processor executes the computer program includes: for each user terminal, respectively perform feature extraction on the data mapping table and the model mapping table to obtain the corresponding data feature information and model feature information, and according to the data feature information and model feature information, obtain the feature vector corresponding to the target task of the user terminal; perform clustering processing on the feature vectors corresponding to the target tasks of all user terminals to obtain multiple target task groups.

[0104] In one embodiment, when the processor executes a computer program, obtaining the requirement data and requirement model corresponding to the target task group according to the target resource table corresponding to the target task group includes: obtaining the data storage node corresponding to the data mapping table; requesting the corresponding requirement data from the data storage node according to the data format and data type in the data mapping table; performing the corresponding life cycle management operation on the model ID in the model mapping table, and obtaining the requirement model according to the operation result.

[0105] In one embodiment, when the processor executes a computer program, obtaining the communication resources and computing resources corresponding to the target task group according to the requirement data and requirement model includes: for each user terminal corresponding to the target task group, obtaining the user ID corresponding to the user terminal, and respectively obtaining the transmission paths corresponding to the requirement data and requirement model according to the user ID; obtaining the communication resources corresponding to the transmission path; obtaining the model identification information corresponding to the target task group, and obtaining the computing resources corresponding to the target task group according to the model identification information.

[0106] In one embodiment, the intelligent control unit includes at least one computing power resource pool; when the processor executes a computer program, the following steps are further implemented: in the case of a sudden change in the AI traffic sent by the user terminal, according to the current traffic state of the AI traffic, allocating the corresponding computing power resource pool for the AI traffic, so as to obtain the AI traffic perception information corresponding to the user terminal through the computing power resource pool.

[0107] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: during the process that the user terminal sends AI traffic to the radio access network through the base station device, obtaining the AI traffic perception information corresponding to the user terminal, and obtaining the requirement resource table corresponding to the user terminal according to the AI traffic perception information; the AI traffic perception information includes data information, model information, task information, resource information and performance information; the task information includes the target task; clustering the target tasks corresponding to multiple user terminals to obtain multiple target task groups, respectively merging the requirement resource tables corresponding to each target task group to obtain the target resource table corresponding to the target task group; for each target task group, obtaining the requirement data and requirement model corresponding to the target task group according to the target resource table corresponding to the target task group, and obtaining the communication resources and computing resources corresponding to the target task group according to the requirement data and requirement model; obtaining the resource allocation scheme corresponding to the communication resources and computing resources, and establishing a resource mapping table based on the resource allocation schemes corresponding to all target task groups, so that the base station device transmits the corresponding requirement data and requirement model for the user terminal based on the resource mapping table, and allocates the corresponding computing resources for the user terminal based on the resource mapping table; the resource mapping table is used to represent the mapping relationship between the target task group and the resource allocation scheme.

[0108] In one embodiment, the demand resource table includes a data mapping table and a model mapping table; when the computer program is executed by a processor, obtaining the demand resource table corresponding to the user terminal according to the AI traffic perception information involves: for each target task, obtaining the task data and task model of the target task; the task data includes the data content of the target task; the task model includes the model storage file and configuration file of the target task; establishing a data mapping table according to all target tasks and the corresponding task data; the data mapping table is used to represent the mapping relationship between the target task and the task data; establishing a model mapping table according to the model IDs of all target tasks and the corresponding task models; the model mapping table is used to represent the mapping relationship between the target task and the model ID.

[0109] In one embodiment, when the computer program is executed by a processor, clustering the target tasks corresponding to multiple user terminals to obtain multiple target task groups involves: for each user terminal, respectively extracting features from the data mapping table and the model mapping table to obtain the corresponding data feature information and model feature information, and obtaining the feature vector corresponding to the target task of the user terminal according to the data feature information and the model feature information; clustering the feature vectors corresponding to the target tasks of all user terminals to obtain multiple target task groups.

[0110] In one embodiment, when the computer program is executed by a processor, obtaining the demand data and demand model corresponding to the target task group according to the target resource table corresponding to the target task group involves: obtaining the data storage node corresponding to the data mapping table; requesting the corresponding demand data from the data storage node according to the data format and data type in the data mapping table; for the model ID in the model mapping table, performing the corresponding life cycle management operation of the model ID, and obtaining the demand model according to the operation result.

[0111] In one embodiment, when the computer program is executed by a processor, obtaining the communication resources and computing resources corresponding to the target task group according to the demand data and demand model involves: for each user terminal corresponding to the target task group, obtaining the user ID corresponding to the user terminal, and respectively obtaining the transmission paths corresponding to the demand data and demand model according to the user ID; obtaining the communication resources corresponding to the transmission path; obtaining the model identification information corresponding to the target task group, and obtaining the computing resources corresponding to the target task group according to the model identification information.

[0112] In one embodiment, the intelligent control unit includes at least one computing power resource pool; when the computer program is executed by a processor, the following steps are further implemented: in the case of a sudden change in the AI traffic sent by the user terminal, allocating the corresponding computing power resource pool for the AI traffic according to the current traffic state of the AI traffic, so as to obtain the AI traffic perception information corresponding to the user terminal through the computing power resource pool.

[0113] In one embodiment, a computer program product is provided, including a computer program which, when executed by a processor, implements the following steps: during the process of a user terminal sending AI traffic to a radio access network through a base station device, obtaining AI traffic perception information corresponding to the user terminal, and obtaining a demand resource table corresponding to the user terminal according to the AI traffic perception information; the AI traffic perception information includes data information, model information, task information, resource information, and performance information; the task information includes a target task; clustering the target tasks corresponding to multiple user terminals to obtain multiple target task groups, and respectively merging the demand resource tables corresponding to each target task group to obtain a target resource table corresponding to the target task group; for each target task group, obtaining demand data and a demand model corresponding to the target task group according to the target resource table corresponding to the target task group, and obtaining communication resources and computing resources corresponding to the target task group according to the demand data and the demand model; obtaining a resource allocation scheme corresponding to the communication resources and the computing resources, and establishing a resource mapping table based on the resource allocation schemes corresponding to all target task groups, so that the base station device transmits corresponding demand data and demand models to the user terminal based on the resource mapping table, and allocates corresponding computing resources to the user terminal based on the resource mapping table; the resource mapping table is used to represent the mapping relationship between the target task group and the resource allocation scheme.

[0114] In one embodiment, the demand resource table includes a data mapping table and a model mapping table; obtaining the demand resource table corresponding to the user terminal according to the AI traffic perception information involved when the computer program is executed by the processor includes: for each target task, obtaining task data and a task model of the target task; the task data includes the data content of the target task; the task model includes the model storage file and the configuration file of the target task; establishing a data mapping table according to all target tasks and the corresponding task data; the data mapping table is used to represent the mapping relationship between the target task and the task data; establishing a model mapping table according to the model IDs of all target tasks and the corresponding task models; the model mapping table is used to represent the mapping relationship between the target task and the model ID.

[0115] In one embodiment, clustering the target tasks corresponding to multiple user terminals to obtain multiple target task groups involved when the computer program is executed by the processor includes: for each user terminal, respectively extracting features from the data mapping table and the model mapping table to obtain corresponding data feature information and model feature information, and obtaining a feature vector corresponding to the target task of the user terminal according to the data feature information and the model feature information; clustering the feature vectors corresponding to the target tasks of all user terminals to obtain multiple target task groups.

[0116] In one embodiment, when the computer program is executed by a processor, obtaining the requirement data and requirement model corresponding to the target task group according to the target resource table corresponding to the target task group includes: obtaining the data storage node corresponding to the data mapping table; requesting the corresponding requirement data from the data storage node according to the data format and data type in the data mapping table; performing the corresponding life cycle management operation on the model ID in the model mapping table, and obtaining the requirement model according to the operation result.

[0117] In one embodiment, when the computer program is executed by a processor, obtaining the communication resources and computing resources corresponding to the target task group according to the requirement data and requirement model includes: for each user terminal corresponding to the target task group, obtaining the user ID corresponding to the user terminal, and respectively obtaining the transmission paths corresponding to the requirement data and requirement model according to the user ID; obtaining the communication resources corresponding to the transmission path; obtaining the model identification information corresponding to the target task group, and obtaining the computing resources corresponding to the target task group according to the model identification information.

[0118] In one embodiment, the intelligent control unit includes at least one computing power resource pool; when the computer program is executed by a processor, the following steps are further implemented: in the case of a sudden change in the AI traffic sent by the user terminal, allocating the corresponding computing power resource pool for the AI traffic according to the current traffic state of the AI traffic, so as to obtain the AI traffic perception information corresponding to the user terminal through the computing power resource pool.

[0119] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in this application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, artificial intelligence (AI) processors, etc., without limitation.

[0120] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope recorded in this application.

[0121] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A resource allocation method based on AI traffic awareness, characterized in that, Applied to the intelligent control unit; The intelligent control unit is deployed in the radio access network architecture; the method includes: During the process that the user terminal sends AI traffic to the radio access network through the base station device, obtaining the AI traffic perception information corresponding to the user terminal, and according to the AI traffic perception information, obtaining the demand resource table corresponding to the user terminal; the AI traffic perception information includes data information, model information, task information, resource information, and performance information; the task information includes the target task; Performing clustering processing on the target tasks corresponding to multiple user terminals to obtain multiple target task groups, and respectively merging the demand resource tables corresponding to each target task group to obtain the target resource table corresponding to the target task group; For each target task group, according to the target resource table corresponding to the target task group, obtaining the demand data and demand model corresponding to the target task group, and according to the demand data and the demand model, obtaining the communication resources and computing resources corresponding to the target task group; Obtaining a resource allocation scheme corresponding to the communication resources and the computing resources, and based on the resource allocation schemes corresponding to all target task groups, establishing a resource mapping table, so that the base station device transmits the corresponding demand data and demand model for the user terminal based on the resource mapping table, and allocates the corresponding computing resources for the user terminal based on the resource mapping table; the resource mapping table is used to represent the mapping relationship between the target task group and the resource allocation scheme.

2. The method according to claim 1, wherein The demand resource table includes a data mapping table and a model mapping table; the obtaining the demand resource table corresponding to the user terminal according to the AI traffic perception information includes: For each target task, obtaining the task data and task model of the target task; the task data includes the data content required by the target task; the task model includes the model storage file and configuration file required by the target task; Establishing a data mapping table according to all target tasks and the corresponding task data; the data mapping table is used to represent the mapping relationship between the target task and the task data; Establishing a model mapping table according to the model IDs of all target tasks and the corresponding task models; the model mapping table is used to represent the mapping relationship between the target task and the model ID.

3. The method according to claim 2, wherein The performing clustering processing on the target tasks corresponding to multiple user terminals to obtain multiple target task groups includes: For each user terminal, respectively performing feature extraction on the data mapping table and the model mapping table to obtain the corresponding data feature information and model feature information, and according to the data feature information and the model feature information, obtaining the feature vector corresponding to the target task of the user terminal; Performing clustering processing on the feature vectors corresponding to the target tasks of all user terminals to obtain multiple target task groups.

4. The method according to claim 2, wherein The obtaining the demand data and demand model corresponding to the target task group according to the target resource table corresponding to the target task group includes: Obtaining the data storage node corresponding to the data mapping table; Request the corresponding required data from the data storage node according to the data format and data type in the data mapping table; For the model ID in the model mapping table, perform the corresponding life cycle management operation of the model ID, and obtain the required model according to the operation result.

5. The method according to claim 1, wherein Obtaining the communication resources and computing resources corresponding to the target task group according to the required data and the required model includes: For each user terminal corresponding to the target task group, obtain the user ID corresponding to the user terminal, and respectively obtain the transmission paths corresponding to the required data and the required model according to the user ID; Obtain the communication resources corresponding to the transmission path; Obtain the model identification information corresponding to the target task group, and obtain the computing resources corresponding to the target task group according to the model identification information.

6. The method according to claim 1, wherein The intelligent control unit includes at least one computing power resource pool; the method further includes: In the case of a sudden change in the AI traffic sent by the user terminal, allocate the corresponding computing power resource pool for the AI traffic according to the current traffic state of the AI traffic, so as to obtain the AI traffic perception information corresponding to the user terminal through the computing power resource pool.

7. A resource allocation device based on AI traffic awareness, characterized in that, The device includes: A traffic perception module, configured to obtain the AI traffic perception information corresponding to the user terminal during the process that the user terminal sends AI traffic to the radio access network through the base station device, and obtain the required resource table corresponding to the user terminal according to the AI traffic perception information; the AI traffic perception information includes data information, model information, task information, resource information, and performance information; the task information includes target tasks; A task clustering module, configured to perform clustering processing on the target tasks corresponding to multiple user terminals to obtain multiple target task groups, and respectively merge the required resource tables corresponding to each target task group to obtain the target resource table corresponding to the target task group; A resource acquisition module, configured to, for each target task group, obtain the required data and the required model corresponding to the target task group according to the target resource table corresponding to the target task group, and obtain the communication resources and computing resources corresponding to the target task group according to the required data and the required model; A resource allocation module, configured to obtain a resource allocation scheme corresponding to the communication resources and the computing resources, and establish a resource mapping table based on the resource allocation schemes corresponding to all target task groups, so that the base station device transmits the corresponding required data and required model for the user terminal based on the resource mapping table, and allocates the corresponding computing resources for the user terminal based on the resource mapping table; the resource mapping table is used to represent the mapping relationship between the target task group and the resource allocation scheme.

8. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images