Computing task processing method, apparatus, base station, medium, and program product

Abstract

The present disclosure relates to the technical field of wireless communications, and provides a computing task processing method, an apparatus, a base station, a medium, and a program product. The computing task processing method comprises: when a terminal needs to be handed over from a first base station to a second base station, transmitting task context to the second base station, the task context being used for instructing the second base station to deploy a computing task of the terminal; receiving task deployment completion information sent by the second base station, the task deployment completion information carrying task instance entry point information of the second base station; and sending the task instance entry point information of the second base station to the terminal, for instructing the terminal to access a task instance of the second base station on the basis of the task instance entry point information of the second base station.

Description

Method, device, base station, medium and program product for processing computing task

[0001] Cross-reference to Related Applications

[0002] The present disclosure claims priority from Chinese Patent Application No. 202411338955.8 filed on September 25, 2024 in China, the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0003] The present disclosure relates to the technical field of wireless communication, and particularly refers to a method, device, base station, medium and program product for processing computing task. BACKGROUND

[0004] At present, considering that the computing capability of a terminal is limited by factors such as computing power, battery power and heating condition, and the sensitivity requirement of immersive service on time delay, it is necessary to study a scheme in which a base station provides computing service for a terminal and assists the terminal to complete a computing task in real time.

[0005] However, how to fully utilize the computing resources of the base station by the terminal, fully exert the value of the computing resources of the base station, and consider the distributed characteristics of the base station, need to uniformly manage and control the dispersed computing resources to form the effect of gathering sand into a tower, and meet the requirements of low time delay, large bandwidth and large computing power of service scenarios such as unmanned driving, digital currency, extended reality (XR) and virtual reality (VR), which need to be specifically studied. SUMMARY

[0006] The technical scheme of the present disclosure aims to provide a method, device, base station, medium and program product for processing computing task, to solve the problem of how the base station provides computing service for the terminal in the related art.

[0007] To achieve the above-mentioned purpose, the present disclosure is implemented as follows:

[0008] In a first aspect, an embodiment of the present disclosure provides a method for processing computing task, applied to a first base station, and the method comprises:

[0009] In a case where a terminal needs to be handed over from the first base station to a second base station, a task context is delivered to the second base station, the task context being used to instruct the second base station to deploy a computing task of the terminal;

[0010] Receiving task deployment completion information sent by the second base station, the task deployment completion information carrying task instance entry point information of the second base station;

[0011] sending the terminal the task instance entry point information of the second base station, the task instance entry point information of the second base station being used to instruct the terminal to access the task instance of the second base station.

[0012] Optionally, the method for processing a computing task, wherein after sending the terminal the task instance entry point information of the second base station, the method further comprises:

[0013] receiving a task context release request sent by the second base station;

[0014] releasing the task context according to the task context release request.

[0015] Optionally, the method for processing a computing task, wherein in the case that the terminal needs to be handed over from the first base station to the second base station, before transferring the task context to the second base station, the method further comprises:

[0016] receiving a computing task request of the terminal;

[0017] instantiating the computing task according to the computing task request, obtaining the task instance entry point information of the first base station, and recording computing requirement information in the task context;

[0018] configuring a data collection strategy of the first base station, and recording data session information in the task context;

[0019] establishing a computing session with the terminal, and recording communication session information in the task context;

[0020] running the task instance of the first base station.

[0021] Optionally, the method for processing a computing task, wherein after recording the computing requirement information in the task context, the method further comprises:

[0022] deploying a model according to the computing task request, and recording model requirement information in the task context.

[0023] Optionally, the method for processing a computing task, wherein instantiating the computing task according to the computing task request comprises:

[0024] determining the task instance of the first base station according to the computing task request;

[0025] determining the computing resource pool of the first base station corresponding to the task instance of the first base station according to the computing resource pool subscription information of the first base station;

[0026] deploying a task instance of the first base station to a computing resource pool of the first base station.

[0027] Optionally, the method for processing a computing task, wherein the computing task request comprises at least one of the following: communication requirement information, computing requirement information, data requirement information, and model requirement information.

[0028] In a second aspect, embodiments of the present disclosure further provide a method for processing a computing task, applied to a second base station, the method comprising:

[0029] receiving a task context delivered by a first base station;

[0030] deploying a computing task of a terminal according to the task context;

[0031] sending task deployment completion information to the first base station, the task deployment completion information carrying entry point information of a task instance of the second base station;

[0032] receiving a task access request of the terminal;

[0033] running the task instance of the second base station.

[0034] Optionally, the method for processing a computing task, wherein deploying the computing task of the terminal according to the task context comprises:

[0035] instantiating the computing task according to the task context, obtaining the entry point information of the task instance of the second base station, and updating computing requirement information in the task context;

[0036] configuring a data collection strategy of the second base station, and updating data session information in the task context;

[0037] establishing a computing session with the terminal, and updating communication session information in the task context.

[0038] Optionally, the method for processing a computing task, wherein instantiating the computing task according to the task context comprises:

[0039] determining a task instance of the second base station according to the task context;

[0040] determining a computing resource pool of the second base station corresponding to the task instance of the second base station according to computing resource pool subscription information of the second base station;

[0041] deploying the task instance of the second base station to the computing resource pool of the second base station.

[0042] Optionally, the computing task processing method, wherein running the task instance of the second base station comprises:

[0043] sending a task context release request to the first base station;

[0044] receiving data reported by the terminal, and running the task instance of the computing resource pool deployed in the second base station.

[0045] In a third aspect, embodiments of the present disclosure further provide a computing task processing apparatus applied to a first base station, the apparatus comprising:

[0046] a passing module configured to pass a task context to a second base station in a case that a terminal needs to be handed over from the first base station to the second base station, the task context being used to instruct the second base station to deploy a computing task of the terminal;

[0047] a first receiving module configured to receive task deployment completion information sent by the second base station, the task deployment completion information carrying task instance entry point information of the second base station;

[0048] a first sending module configured to send the task instance entry point information of the second base station to the terminal, the task instance entry point information of the second base station being used to instruct the terminal to access the task instance of the second base station.

[0049] In a fourth aspect, embodiments of the present disclosure further provide a computing task processing apparatus applied to a second base station, the apparatus comprising:

[0050] a second receiving module configured to receive a task context passed by a first base station;

[0051] a deploying module configured to deploy a computing task of a terminal according to the task context;

[0052] a second sending module configured to send task deployment completion information to the first base station, the task deployment completion information carrying task instance entry point information of the second base station;

[0053] a third receiving module configured to receive a task access request of a terminal;

[0054] a first running module configured to run a task instance of the second base station.

[0055] In a fifth aspect, embodiments of the present disclosure further provide a base station, comprising a processor, a memory, and a program stored in the memory and executable on the processor, the program being executed by the processor to implement the computing task processing method according to the first aspect or the computing task processing method according to the second aspect.

[0056] In a sixth aspect, the embodiments of the present disclosure further provide a readable storage medium, which stores a program, and the program is executed by a processor to implement the computing task processing method in the first aspect or the computing task processing method in the second aspect.

[0057] In a seventh aspect, the embodiments of the present disclosure further provide a computer program product, which comprises computer instructions, and the computer instructions are executed by a processor to implement the computing task processing method in the first aspect or the computing task processing method in the second aspect.

[0058] The beneficial effects of the above technical solutions of the present disclosure are as follows:

[0059] The computing task processing method provided by the embodiments of the present disclosure is used for the case that a terminal needs to be handed over from a first base station to a second base station, and the first base station transmits a task context to the second base station, where the task context is used to instruct the second base station to deploy a computing task of the terminal. The first base station receives task deployment completion information transmitted by the second base station, where the task deployment completion information carries task instance entry point information of the second base station. The first base station transmits the task instance entry point information of the second base station to the terminal, where the task instance entry point information of the second base station is used to instruct the terminal to access a task instance of the second base station. In this way, the base station side instantiates the computing task to assist the terminal side in executing the computing task at the base station side, and continuous wireless computing service can be provided during base station handover. BRIEF DESCRIPTION OF DRAWINGS

[0060] FIG. 1 is a flowchart of the computing task processing method according to an embodiment of the present disclosure;

[0061] FIG. 2 is a flowchart of an implementation of the computing task processing method according to an embodiment of the present disclosure;

[0062] FIG. 3 is a flowchart of one of the implementations of the computing task processing method according to an embodiment of the present disclosure;

[0063] FIG. 4 is a flowchart of another of the implementations of the computing task processing method according to an embodiment of the present disclosure;

[0064] FIG. 5 is a schematic diagram of the relationship between the computing task and the task instance, the task context, and the task session context according to an embodiment of the present disclosure;

[0065] FIG. 6 is a flowchart of the computing task processing method according to another embodiment of the present disclosure;

[0066] FIG. 7 is a flowchart of the computing task processing apparatus according to an embodiment of the present disclosure;

[0067] FIG. 8 is a flowchart of a computing task processing apparatus according to another embodiment of the present disclosure;

[0068] FIG. 9 is a hardware structure diagram of a base station according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0069] To make the technical problems to be solved by the present disclosure, technical solutions and advantages clearer, specific embodiments will be described in detail below with reference to the drawings.

[0070] An embodiment of the present disclosure, as shown in FIG. 1, provides a computing task processing method applied to a first base station, and the method comprises the following steps.

[0071] S101. In a case where a terminal needs to be handed over from the first base station to a second base station, task context is delivered to the second base station, the task context being used to instruct the second base station to deploy a computing task of the terminal.

[0072] It should be noted that the terminal needs to be handed over from the first base station to the second base station due to terminal mobility or network resource optimization. In the case where the terminal needs to be handed over from the first base station to the second base station, the first base station delivers task context used to instruct the second base station to deploy the computing task of the terminal to the second base station, and the second base station deploys the computing task according to the task context, so that the terminal can access the second base station to run the computing task.

[0073] It should be further noted that before the base station handover is triggered, the computing task of the terminal is deployed in the first base station, and the terminal can access the first base station to run the computing task.

[0074] S102. Task deployment completion information sent by the second base station is received, the task deployment completion information carrying task instance entry point information of the second base station.

[0075] In an embodiment of the present disclosure, the task instance entry point information comprises at least one of the following: a uniform resource location (URL), an Internet Protocol (IP) address and a port.

[0076] S103. The task instance entry point information of the second base station is sent to the terminal, the task instance entry point information of the second base station being used to instruct the terminal to access the task instance of the second base station according to the task instance entry point information of the second base station.

[0077] Figure 2 is a flowchart of an embodiment of the method for processing a computing task according to the present disclosure. In Figure 2, an O-RAN architecture is taken as an example, a base station 1 represents a first base station, a base station 2 represents a second base station, and an O-Cloud represents a computing resource pool. A Near-RT RIC instantiates a task instance according to a region covered by a computing task, a number of terminals, and the like. Due to terminal movement, the task needs to be migrated from an original Near-RT RIC 1 (the first base station) to a target Near-RT RIC 2 (the second base station). The instantiation of the task at the target node and the release of the task at the original node are completed through the processes of "task migration request, task context transfer, and task instantiation", "terminal handover and access to a new task instance", and "original RIC release of the task and release of the task context". The specific task migration process is shown in Figure 2.

[0078] In the embodiment of the present disclosure, the first base station can send a radio resource control (RRC) reconfiguration request to the terminal, where the RRC reconfiguration request is used to indicate a handover command (HO Command) and carries the entry point information of the task instance of the second base station.

[0079] Specifically, after receiving a handover request (Handover Request) sent by the second base station and feeding back a handover request acknowledgement (Handover Request Acknowledge) to the second base station, the first base station sends an RRC reconfiguration request to the terminal.

[0080] In an embodiment, optionally, after sending the entry point information of the task instance of the second base station to the terminal, the method further includes:

[0081] receiving a task context release request sent by the second base station;

[0082] releasing the task context according to the task context release request.

[0083] Specifically, the first base station receives a terminal context release request (UE Context Release) sent by the second base station, sends a task context release request to the Near-RT RIC of the first base station, and releases the task session context, where the task session context includes data session information and communication session information.

[0084] Further, the Near-RT RIC of the first base station releases the computing resource pool for deploying the computing task of the terminal and releases the task context.

[0085] Further, the Near-RT RIC of the first base station also needs to release the data collection strategy.

[0086] In an implementation, optionally, in a case where the terminal needs to be handed over from the first base station to a second base station, the method further includes:

[0087] receiving a computing task request of the terminal;

[0088] instantiating the computing task according to the computing task request, obtaining task instance entry point information of the first base station, and recording computing requirement information in the task context;

[0089] configuring a data collection strategy of the first base station, and recording data session information in the task context;

[0090] establishing a computing session with the terminal, and recording communication session information in the task context;

[0091] running the task instance of the first base station.

[0092] In the embodiments of the present disclosure, the computing task request includes at least one of the following: an Artificial Intelligence (AI) model inference task request, a Machine Learning (ML) model inference task request, and an Extended Reality (XR) rendering task.

[0093] The computing task request is used to indicate resource requirements of the computing task for at least one of the following: communication, computation, data, and model. The computing task request includes at least one of the following: communication requirement information, computation requirement information, data requirement information, and model requirement information.

[0094] Specifically, the communication requirement information is illustrated by Table 1, the computation requirement information is illustrated by Table 2, the data requirement information is illustrated by Table 3, and the model requirement information is illustrated by Table 4, respectively.

[0095] Table 1 Communication requirement information

[0096] Table 2 Computation requirement information

[0097] Table 3 Data requirement information

[0098] Table 4 Model requirement information

[0099] As shown in FIG. 3 is a flowchart of another embodiment of the computing task processing method, and as shown in FIG. 4 is a flowchart of another embodiment of the computing task processing method. The flowchart shown in FIG. 4 is subsequent to the flowchart shown in FIG. 3, and the two figures constitute a complete flowchart. In FIGS. 3 and 4, the O-RAN architecture is taken as an example. The Near-RT RIC instantiates two task instances according to the area covered by the computing task, the number of terminals, and the like, and completes the task deployment through the processes of “task instance computing deployment-start, creating a task context, and recording computing information”, “model deployment, task context, and recording model information”, “task instance data deployment, creating a task session context, and recording data session information”, and “task deployment-complete, task session context recording communication information”. The specific task establishment process is shown in FIG. 3.

[0100] Specifically, the terminal sends a computing task request to the first base station through a Uu interface, the first base station forwards the computing task request to the Near-RT RIC of the first base station through an E2 interface, the Near-RT RIC of the first base station feeds back task request successful reception information to the first base station through the E2 interface, and the first base station feeds back the task request successful reception information through the Uu interface.

[0101] The Near-RT RIC of the first base station creates a task context, and records task information in the task context according to the computing task request.

[0102] Further, the Near-RT RIC of the first base station instantiates the computing task according to the computing task request, obtains task instance entry point information of the first base station, and records computing requirement information in the task context according to the computing requirement information in the computing task request.

[0103] Further, the Near-RT RIC of the first base station generates a data collection strategy according to the data requirement information in the computing task request, the data collection strategy including at least one of the following: a node for data collection, a data object (terminal throughput and channel state information), a data sampling period, a collection and reporting period, a data reporting mode, and a data reporting address. The Near-RT RIC of the first base station sends the data collection configuration strategy to the first base station through an E2 interface, the first base station feeds back data collection configuration confirmation information to the Near-RT RIC of the first base station through the E2 interface, and then the first base station configures according to the data collection strategy and starts data collection. The first base station sends the data collection configuration strategy to the terminal through a Uu interface, the terminal configures according to the data collection strategy, and then the terminal feeds back data collection configuration completion information to the first base station through the Uu interface. The first base station feeds back the data collection configuration completion information to the Near-RT RIC of the first base station through the E2 interface, and the Near-RT RIC of the first base station records data session information in the task context.

[0104] The Near-RT RIC of the first base station sends task instance entry point information to the first base station. Then, the first base station establishes a computing session with the terminal, and the first base station needs to establish a computing task data bearer. The first base station sends terminal air interface task session context information to the Near-RT RIC of the first base station, the Near-RT RIC of the first base station records communication session information in the task context, and feeds back a task session context response to the first base station.

[0105] Next, the first base station reports the collected data to the computing resource pool, and the first base station reports the data collected by the terminal to the computing resource pool to run the task instance of the first base station, so that the computing resource pool of the first base station can provide computing services for the terminal.

[0106] In one embodiment, optionally, after recording the computing requirement information in the task context, the method further includes:

[0107] According to the computing task request, a model is deployed, and model requirement information is recorded in the task context.

[0108] It should be noted that the model is not included in the computing task application of the terminal, and the model needs to be provided by the scenario of the network. The Near-RT RIC of the first base station needs to deploy the model in the computing resource pool of the first base station according to the model requirement information in the computing task request, and record the model requirement information in the task context.

[0109] So far, the task context includes task information, computing requirement information, model requirement information, data session information, and communication session information, wherein the data session information and the communication session information can be referred to as task session context.

[0110] Here, the task context can be illustrated by Table 5 as follows, and the task session context can be illustrated by Table 6 as follows.

[0111] Table 5 Task Context

[0112] Table 6 Task Session Context

[0113] It should be noted that the task context and the task session context in the above Table 5 and Table 6 provide information for the lifecycle management and quality assurance of the computing task of the terminal.

[0114] In an embodiment, instantiating the computing task according to the computing task request comprises:

[0115] determining the task instance of the first base station according to the computing task request;

[0116] determining the computing resource pool of the first base station corresponding to the task instance of the first base station according to the computing resource pool subscription information of the first base station;

[0117] deploying the task instance of the first base station in the computing resource pool of the first base station.

[0118] In the embodiments of the present disclosure, the Near-RT RIC of the first base station determines the task instance of the first base station corresponding to the computing task according to the computing task request, and determines the computing resource pool of the first base station corresponding to the task instance of the first base station according to the computing resource pool subscription information. Then, the Near-RT RIC of the first base station deploys the task instance corresponding to the computing task in the computing resource pool, the computing resource pool of the first base station deploys the task instance, and when the task instance is deployed and runs normally, the Near-RT RIC of the first base station sends the entry point information of the task instance.

[0119] Optionally, the Near-RT RIC of the first base station determines the task instance of the first base station corresponding to the computing task according to the computing task request, comprising:

[0120] judging whether to deploy multiple task instances for the computing task according to at least one of the number and area of the terminal in the computing task request and the load information of the computing resource pool, and obtaining a judgment result;

[0121] According to the judgment result, the task instance of the first base station corresponding to the computing task is determined.

[0122] In the embodiments of the present disclosure, the Near-RT RIC of the first base station can divide the computing task into 1 to n task instances according to the area that the computing task needs to cover, and each task instance is responsible for providing the computing task in an area, thereby reducing the time delay and making the computing task close to the user. The Near-RT RIC of the first base station can also divide the computing task into 1 to n task instances according to the number of terminals, and each task instance can support m terminals, so as to balance the load of the computing task. In addition, the Near-RT RIC of the first base station can also divide the computing task into 1 to n task instances according to the data requirement information in the computing task request, and each task instance is close to d data collection nodes for computing, thereby reducing the time delay and making the computing task close to the data source.

[0123] Optionally, the Near-RT RIC of the first base station determines the computing resource pool of the first base station corresponding to the task instance of the first base station according to the computing resource pool subscription information, including:

[0124] According to the computing resource information and / or load information in the computing resource pool subscription information, the computing resource pool corresponding to the task instance is determined.

[0125] As shown in FIG. 5, the relationship between the computing task and the task instance, the task context, and the task session context in the embodiments of the present disclosure is shown. Here, the relationship between the computing task, the task instance, the task context, and the task session context is described in combination with FIG. 5.

[0126] The computing task request involves four dimensions of requirement information: communication requirement information, computing requirement information, data requirement information, and model requirement information. After receiving the computing task request, the first base station establishes a session context for each dimension, maps the computing task to a computing resource, and associates the computing resource to a task instance.

[0127] Another embodiment of the present disclosure is shown in FIG. 6, which provides a computing task processing method applied to a second base station, and the method includes:

[0128] S601, receiving the task context delivered by the first base station;

[0129] S602, deploying the computing task of the terminal according to the task context;

[0130] S603, sending task deployment completion information to the first base station, wherein the task deployment completion information carries the task instance entry point information of the second base station;

[0131] S604, receiving the task access request of the terminal;

[0132] S605, running the task instance of the second base station.

[0133] In one embodiment, optionally, deploying the computing task of the terminal according to the task context comprises:

[0134] instantiating the computing task according to the task context, obtaining the task instance entry point information of the second base station, and updating the computing requirement information in the task context;

[0135] configuring the data collection strategy of the second base station, and updating the data session information in the task context;

[0136] establishing a computing session with the terminal, and updating the communication session information in the task context.

[0137] It should be noted that the specific steps of deploying the computing task of the terminal according to the task context by the second base station are the same as the steps of deploying the computing task of the terminal according to the task context by the first base station, which will not be repeated here.

[0138] In one embodiment, optionally, instantiating the computing task according to the task context comprises:

[0139] determining the task instance of the second base station according to the task context;

[0140] determining the computing resource pool of the second base station corresponding to the task instance of the second base station according to the computing resource pool subscription information of the second base station;

[0141] deploying the task instance of the second base station in the computing resource pool of the second base station.

[0142] It should be noted that the specific steps of instantiating the computing task according to the task context by the second base station are the same as the steps of instantiating the computing task according to the task context by the first base station, which will not be repeated here.

[0143] In one embodiment, optionally, running the task instance of the second base station comprises:

[0144] sending a task context release request to the first base station;

[0145] receiving the data reported by the terminal, and running the task instance deployed in the computing resource pool of the second base station.

[0146] To sum up, the computing task processing method provided in the embodiments of the present disclosure can maintain the demand information in four dimensions for the computing task request, implement the life cycle management of the computing task, such as resource allocation, adjustment, and release, and the like, implement the task context transfer in the wireless domain, guarantee the continuity of the computing task, and provide continuous computing service, and the computing task request can be transferred between domains to interact with the core network, so that the core network can schedule the computing task in a larger range.

[0147] As shown in FIG. 7, one of the embodiments of the present disclosure provides a computing task processing apparatus applied to a first base station, which comprises:

[0148] A transfer module 701 is configured to transfer a task context to a second base station in a case that a terminal needs to be handed over from the first base station to the second base station, the task context being used to instruct the second base station to deploy a computing task of the terminal;

[0149] A first receiving module 702 is configured to receive task deployment completion information sent by the second base station, the task deployment completion information carrying task instance entry point information of the second base station;

[0150] A first sending module 703 is configured to send the task instance entry point information of the second base station to the terminal, the task instance entry point information of the second base station being used to instruct the terminal to access the task instance of the second base station.

[0151] Optionally, the computing task processing apparatus further comprises:

[0152] A fourth receiving module is configured to receive a task context release request sent by the second base station;

[0153] A release module is configured to release the task context according to the task context release request.

[0154] Optionally, the computing task processing apparatus further comprises:

[0155] A fifth receiving module is configured to receive a computing task request of the terminal;

[0156] An acquisition module is configured to instantiate the computing task according to the computing task request, acquire task instance entry point information of the first base station, and record computing demand information in the task context;

[0157] A configuration module is configured to configure a data collection strategy of the first base station, and record data session information in the task context;

[0158] An establishment module is configured to establish a computing session with the terminal, and record communication session information in the task context.

[0159] a second running module, configured to run a task instance of the first base station.

[0160] Optionally, the computing task processing apparatus further includes:

[0161] a second deployment module, configured to deploy a model according to the computing task request, and record model requirement information in the task context.

[0162] Optionally, the computing task processing apparatus further includes:

[0163] determine a task instance of the first base station according to the computing task request;

[0164] determine a computing resource pool of the first base station corresponding to the task instance of the first base station according to the computing resource pool subscription information of the first base station;

[0165] deploy the task instance of the first base station in the computing resource pool of the first base station.

[0166] Optionally, the computing task request includes at least one of the following: communication requirement information, computing requirement information, data requirement information, and model requirement information.

[0167] The computing task processing apparatus provided by the embodiments of the present disclosure can execute the computing task processing method applied to the first base station, and the implementation principle and technical effects are similar, which will not be described here.

[0168] As shown in FIG. 8, one of the embodiments of the present disclosure provides a computing task processing apparatus applied to a second base station, which includes:

[0169] a second receiving module 801, configured to receive a task context transmitted by a first base station;

[0170] a first deployment module 802, configured to deploy a computing task of a terminal according to the task context;

[0171] a second sending module 803, configured to send task deployment completion information to the first base station, the task deployment completion information carrying task instance entry point information of the second base station;

[0172] a third receiving module 804, configured to receive a task access request of a terminal;

[0173] a first running module 805, configured to run a task instance of the second base station.

[0174] Optionally, the computing task processing apparatus, wherein the first deployment module 802 comprises:

[0175] The acquisition unit is configured to instantiate the computing task according to the task context, acquire task instance entry point information of the second base station, and update computing requirement information in the task context.

[0176] The configuration unit is configured to configure a data collection strategy of the second base station, and update data session information in the task context.

[0177] The establishment unit is configured to establish a computing session with the terminal, and update communication session information in the task context.

[0178] Optionally, the computing task processing apparatus, wherein the acquisition unit is specifically configured to:

[0179] determine the task instance of the second base station according to the task context;

[0180] determine the computing resource pool of the second base station corresponding to the task instance of the second base station according to the computing resource pool subscription information of the second base station;

[0181] deploy the task instance of the second base station in the computing resource pool of the second base station.

[0182] Optionally, the computing task processing apparatus, wherein the first running module 805 is specifically configured to:

[0183] send a task context release request to the first base station;

[0184] receive data reported by the terminal, and run the task instance deployed in the computing resource pool of the second base station.

[0185] The computing task processing apparatus provided by the embodiments of the present disclosure can execute the above-mentioned computing task processing method applied to the second base station, and has similar implementation principles and technical effects, which will not be described here again.

[0186] As shown in FIG. 9, the embodiments of the present disclosure further provide a base station, comprising: a processor 901; and a memory 902 connected with the processor 901 through a bus interface, the memory 902 being used for storing programs and data used by the processor 901 in performing operations, and the processor 901 calling and executing the programs and data stored in the memory 902.

[0187] The base station further comprises a transceiver 903 connected with the bus interface, and the transceiver 903 is configured to perform the following processes under the control of the processor 901:

[0188] in case that the terminal needs to be handed over from the first base station to a second base station, passing a task context to the second base station, the task context being used to instruct the second base station to deploy a computing task of the terminal;

[0189] receiving task deployment completion information sent by the second base station, the task deployment completion information carrying task instance entry point information of the second base station;

[0190] sending the task instance entry point information of the second base station to the terminal, the task instance entry point information of the second base station being used to instruct the terminal to access a task instance of the second base station.

[0191] In FIG. 9, the bus architecture can include any number of interconnecting buses and bridges, depending on the specific application of the processor 901 and the memory 902 that are linked together by the various circuits representing one or more processors and memories. The bus architecture can also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art, and therefore, not described further. The bus interface provides a user interface 904. The transceiver 903 can be a plurality of elements, including a transmitter and a receiver, which provides a means for communicating with various other apparatus over a transmission medium. The processor 901 is responsible for managing the bus architecture and general processing, and the memory 902 can store data used by the processor 901 in executing its operations.

[0192] The processor 901 is responsible for managing the bus architecture and general processing, and the memory 902 can store data used by the processor 901 in executing its operations.

[0193] Optionally, the base station, wherein the transceiver 903 is further configured to perform the following process under the control of the processor 901:

[0194] receiving a task context release request sent by the second base station;

[0195] The processor 901 is further configured to read the computer program and perform the following steps:

[0196] releasing the task context according to the task context release request.

[0197] Optionally, the base station, wherein the transceiver 903 is further configured to perform the following process under the control of the processor 901:

[0198] receiving a computing task request of the terminal;

[0199] The processor 901 is further configured to read the computer program and perform the following steps:

[0200] According to the computing task request, instantiating the computing task, obtaining task instance entry point information of the first base station, and recording computing requirement information in the task context;

[0201] Configuring a data collection strategy of the first base station, and recording data session information in the task context;

[0202] Establishing a computing session with the terminal, and recording communication session information in the task context;

[0203] Running the task instance of the first base station.

[0204] Optionally, the base station, wherein the processor 901 is further configured to read the computer program and perform the following steps:

[0205] According to the computing task request, deploying a model, and recording model requirement information in the task context.

[0206] Optionally, the base station, wherein the processor 901 is further configured to read the computer program and perform the following steps:

[0207] According to the computing task request, determining a task instance of the first base station;

[0208] According to the computing resource pool subscription information of the first base station, determining a computing resource pool of the first base station corresponding to the task instance of the first base station;

[0209] Deploying the task instance of the first base station in the computing resource pool of the first base station.

[0210] Optionally, the base station, wherein the computing task request comprises at least one of the following: communication requirement information, computing requirement information, data requirement information, and model requirement information.

[0211] In addition, the embodiments of the present disclosure also provide a base station, which has the same structure as the base station shown in FIG. 9, comprising: a processor; and a memory connected with the processor through a bus interface, the memory being used to store programs and data used by the processor when performing operations, and the processor calling and executing the programs and data stored in the memory.

[0212] The base station further comprises a transceiver connected with the bus interface, and the transceiver is used to perform the following processes under the control of the processor:

[0213] Receiving a task context delivered by a first base station;

[0214] The processor is configured to read the program in the memory and perform the following processes:

[0215] deploy a computing task according to the task context;

[0216] the transceiver is configured to perform the following process under control of the processor:

[0217] send task deployment completion information to the first base station, the task deployment completion information carrying task instance entry point information of the second base station;

[0218] receive a task access request of the terminal;

[0219] the processor is configured to read a program in the memory and perform the following process:

[0220] run the task instance of the second base station.

[0221] Optionally, the base station, wherein the processor is specifically configured to read the computer program and perform the following steps:

[0222] instantiate the computing task according to the task context, obtain task instance entry point information of the second base station, and update computing requirement information in the task context;

[0223] configure a data collection strategy of the second base station, and update data session information in the task context;

[0224] establish a computing session with the terminal, and update communication session information in the task context.

[0225] Optionally, the base station, wherein the processor is specifically configured to read the computer program and perform the following steps:

[0226] determine the task instance of the second base station according to the task context;

[0227] determine a computing resource pool of the second base station corresponding to the task instance of the second base station according to computing resource pool subscription information of the second base station;

[0228] deploy the task instance of the second base station to the computing resource pool of the second base station.

[0229] Optionally, the base station, wherein the processor is specifically configured to read the computer program and perform the following steps:

[0230] send a task context release request to the first base station;

[0231] receive data reported by the terminal, and run the task instance deployed in the computing resource pool of the second base station.

[0232] The embodiment of the present disclosure further provides a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to implement the steps of the above-mentioned computing task processing method and achieve the same technical effects. To avoid repetition, details are not described herein.

[0233] In addition, the embodiment of the present disclosure further provides a computer program product, which includes computer instructions. The computer instructions are executed by a processor to implement each process of the method embodiments shown in FIG. 1 or FIG. 6 and achieve the same technical effects. To avoid repetition, details are not described herein.

[0234] In several embodiments provided by the present disclosure, it should be understood that the disclosed method and device can be implemented by other manners. For example, the above-mentioned device embodiments are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or other forms.

[0235] In addition, each functional unit in each embodiment of the present disclosure can be integrated in one processing unit, or each unit can be physically included separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be realized in the form of hardware, or in the form of hardware plus software functional unit.

[0236] The integrated unit realized in the form of software functional unit can be stored in a computer readable storage medium. The software functional unit stored in a storage medium includes a plurality of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute part of the steps of the transceiving method described in each embodiment of the present disclosure. The above-mentioned storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0237] The above-mentioned is the preferred embodiment of the present disclosure. It should be noted that, for those skilled in the art, without departing from the principles of the present disclosure, a number of improvements and refinements can be made, which should also be considered as the protection scope of the present disclosure.

Claims

1. A method for processing a computing task, applied to a first base station, the method comprising: in a case where a terminal needs to be handed over from the first base station to a second base station, transferring a task context to the second base station, the task context being used to instruct the second base station to deploy a computing task of the terminal; receiving task deployment completion information sent by the second base station, the task deployment completion information carrying task instance entry point information of the second base station; sending the task instance entry point information of the second base station to the terminal, the task instance entry point information of the second base station being used to instruct the terminal to access a task instance of the second base station.

2. The computing task processing method of claim 1, wherein, After sending the task instance entry point information of the second base station to the terminal, the method further comprises: receiving a task context release request sent by the second base station; releasing the task context according to the task context release request.

3. The method of claim 1, wherein, Before transferring the task context to the second base station in a case where a terminal needs to be handed over from the first base station to a second base station, the method further comprises: receiving a computing task request of the terminal; instantiating the computing task according to the computing task request, obtaining task instance entry point information of the first base station, and recording computing requirement information in the task context; configuring a data collection strategy of the first base station, and recording data session information in the task context; establishing a computing session with the terminal, and recording communication session information in the task context; running a task instance of the first base station.

4. The method of claim 3, wherein, After recording the computing requirement information in the task context, the method further comprises: deploying a model according to the computing task request, and recording model requirement information in the task context.

5. The method of claim 3, wherein, The instantiating the computing task according to the computing task request comprises: determining a task instance of the first base station according to the computing task request; determining a computing resource pool of the first base station corresponding to the task instance of the first base station according to computing resource pool subscription information of the first base station; deploying the task instance of the first base station in the computing resource pool of the first base station.

6. The method of claim 3, wherein, The computing task request comprises at least one of the following: communication requirement information, computing requirement information, data requirement information, and model requirement information. 7.A method for processing a computing task, applied to a second base station, the method comprising: receiving a task context transferred by a first base station; deploying a computing task of a terminal according to the task context; sending task deployment completion information to the first base station, the task deployment completion information carrying task instance entry point information of the second base station; receiving a task access request of the terminal; running a task instance of the second base station.

8. The computing task processing method of claim 7, wherein, The deploying the computing task of the terminal according to the task context comprises: instantiating the computing task according to the task context, obtaining task instance entry point information of the second base station, and updating computing requirement information in the task context; configuring a data collection strategy of the second base station, and updating data session information in the task context; establish a computing session with the terminal and update the communication session information in the task context.

9. The computing task processing method of claim 8, wherein, instantiating the computing task according to the task context, comprising: determining the task instance of the second base station according to the task context; determining the computing resource pool of the second base station corresponding to the task instance of the second base station according to the computing resource pool subscription information of the second base station; deploying the task instance of the second base station to the computing resource pool of the second base station.

10. The method of claim 7, wherein, running the task instance of the second base station, comprising: sending a task context release request to the first base station; receiving data reported by the terminal and running the task instance deployed to the computing resource pool of the second base station. 11.A computing task processing apparatus applied to a first base station, the apparatus comprising: a delivery module configured to deliver a task context to a second base station in a case that a terminal needs to be handed over from the first base station to the second base station, the task context being used to instruct the second base station to deploy a computing task of the terminal; a first receiving module configured to receive task deployment completion information sent by the second base station, the task deployment completion information carrying task instance entry point information of the second base station; a first sending module configured to send the task instance entry point information of the second base station to the terminal, the task instance entry point information of the second base station being used to instruct the terminal to access the task instance of the second base station. 12.A computing task processing apparatus applied to a second base station, the apparatus comprising: a second receiving module configured to receive a task context delivered by a first base station; a first deploying module configured to deploy a computing task of a terminal according to the task context; a second sending module configured to send task deployment completion information to the first base station, the task deployment completion information carrying task instance entry point information of the second base station; a third receiving module configured to receive a task access request of a terminal; a first running module configured to run a task instance of the second base station.

13. A base station comprising: a processor, a memory, and a program stored on the memory and executable on the processor, the program, when executed by the processor, implements the computing task processing method according to any one of claims 1 to 6, or implements the computing task processing method according to any one of claims 7 to 10. 14.A readable storage medium having a program stored thereon, the program, when executed by a processor, implements the computing task processing method according to any one of claims 1 to 6, or implements the computing task processing method according to any one of claims 7 to 10. 15.A computer program product comprising computer instructions, the computer instructions, when executed by a processor, implements the computing task processing method according to any one of claims 1 to 6, or implements the computing task processing method according to any one of claims 7 to 10.

Images