Task processing method and apparatus, device, and storage medium

Abstract

Embodiments of the present disclosure provide a task processing method and apparatus, a device, and a storage medium. A terminal device acquires a measurement report of the terminal device; and the measurement report is sent. The measurement report is used for determining a first time at which the terminal device switches to access a first network device and / or a first node. The first time is used for instructing to switch a processing path of a subtask of the terminal device. In the embodiments of the present disclosure, when the terminal device switches an accessed network device and / or network node, a processing path of a current subtask of the terminal device can be switched in a timely manner, thereby ensuring that the subtask can be processed normally, ensuring service continuity, and improving user experience.

Description

Task processing methods, devices, equipment and storage media

[0001] This disclosure claims priority to Chinese Patent Application No. 202510130314.1, filed on February 5, 2025, entitled “Task Processing Method, Apparatus, Device and Storage Medium”, the entire contents of which are incorporated herein by reference. Technical Field

[0002] This disclosure relates to the field of communication technology, and in particular to a task processing method, apparatus, device and storage medium. Background Technology

[0003] With the rapid development of communication technology, 6th Generation Mobile Communication (6G) technology has enabled more application scenarios. In addition to autonomous driving and intelligent manufacturing, 6G will also combine sensing, imaging and other technologies with mobility to truly unleash the potential of artificial intelligence (AI) and intelligent networks, empower innovative applications, and further integrate communication technology into society.

[0004] In related technologies, terminal devices are mobile, and the movement of terminal devices may affect the continuity of services, thereby reducing the user experience. Summary of the Invention

[0005] This disclosure provides a task processing method, apparatus, device, and storage medium for timely switching of the processing path of the current subtask of a terminal device after switching the network device and / or network node it accesses during the movement of the terminal device, thereby ensuring that the subtask can be processed normally, ensuring business continuity, and improving user experience.

[0006] In a first aspect, embodiments of this disclosure provide a task processing method applied to a terminal device, the method comprising:

[0007] Obtain measurement reports from terminal devices;

[0008] A measurement report is sent, which is used to determine the first time when the terminal device switches access to the first network device and / or the first node; the first time is used to indicate the processing path of the subtask of switching the terminal device.

[0009] In some embodiments, the measurement report carries at least one of the following information: the current location, speed, direction of movement of the terminal device, identification information of the currently executing subtask, and execution time of the next subtask.

[0010] In some embodiments, obtaining a measurement report from a terminal device includes at least one of the following:

[0011] Measure the terminal equipment and obtain a measurement report;

[0012] Alternatively, predictions can be made about the terminal devices to obtain measurement reports.

[0013] In some embodiments, a measurement report is sent, including at least one of the following:

[0014] The second network device sends a measurement report to the first network device, and the second network device switches the terminal device to the network device it was previously connected to before connecting to the first network device.

[0015] Alternatively, a measurement report can be sent to the first device via a second network device, where the first device is located in a second node, which is the node the terminal device connected to before switching to the first node.

[0016] In some embodiments, the method further includes:

[0017] Receive a model sent by a first network device and / or a second network device; wherein the model is used to process subtasks, and the second network device is the network device that the terminal device was connected to before switching to the first network device.

[0018] In some embodiments, the method further includes:

[0019] Send model requirements to the first network device and / or the second network device. The model requirements are obtained based on the task partitioning results of the terminal device. The task partitioning results include at least one subtask corresponding to the task of the terminal device.

[0020] Model requirements include at least one of the following: the required model type, application scenario, task requirements, model operating environment, and the dimensions of the model's input data.

[0021] In some embodiments, the method further includes at least one of the following:

[0022] The tasks of the terminal devices are divided to obtain the task division results;

[0023] Alternatively, receive the task allocation results sent by the first network device and / or the second network device.

[0024] Secondly, embodiments of this disclosure provide a task processing method applied to a first network device, the method comprising:

[0025] Obtain a measurement report from the terminal device, which is used to determine the first time when the terminal device switches access to the first network device and / or the first node;

[0026] According to the measurement report, a first handover request is sent to the first device, which is located in the second node. The second node is the node that the terminal accessed before switching to the first node. The first handover request is used to request the processing path of the subtask of the terminal device to be switched.

[0027] In some embodiments, the measurement report carries at least one of the following information: the current location, speed, direction of movement of the terminal device, identification information of the currently executing subtask, and execution time of the next subtask.

[0028] In some embodiments, obtaining a measurement report from a terminal device includes at least one of the following:

[0029] Receive measurement reports sent by the second network device, which is the network device that the terminal device was connected to before switching to the first network device;

[0030] Receive the measurement report sent by the first device.

[0031] In some embodiments, the method further includes: receiving a first handover confirmation sent by a first device; wherein the first handover confirmation is used to indicate the processing path of a subtask for successfully switching terminal devices.

[0032] In some embodiments, the method further includes: receiving an end identifier sent by a second network device, the end identifier being used to indicate successful path switching; wherein the end identifier is sent by the second device to the second network device, and the second device is located in the second node.

[0033] In some embodiments, the method further includes:

[0034] The first network device receives a second handover request sent by a third device located in the first node. The second handover request is used to instruct the first network device to perform a path switch.

[0035] A second handover confirmation is sent to the third device, which indicates that the handover path is permitted.

[0036] In some embodiments, the first handover request carries at least one of the following:

[0037] The handover time of the terminal device is determined based on the first time the terminal device switches to the first network device and / or the execution time of the subtask. The first time is obtained from the measurement report.

[0038] Device information of the terminal equipment;

[0039] The identification information of the first network device, where the first network device is the network device that the terminal device needs to switch to access;

[0040] Alternatively, the identification information of the PDU session to be switched.

[0041] In some embodiments, the method further includes:

[0042] Obtain a model for processing subtasks on the terminal device;

[0043] Send the model to the terminal device.

[0044] In some embodiments, obtaining a model for processing subtasks of a terminal device includes at least one of the following:

[0045] Based on the model requirements of the terminal device, obtain the model corresponding to the model requirements;

[0046] Based on the task partitioning results of the terminal device, obtain the model corresponding to the task partitioning results;

[0047] The terminal device receives a model sent by a second network device, which is the network device that the terminal device was connected to before switching to the first network device.

[0048] Alternatively, it may receive a model sent by the first node and / or the second node, where the second node is the node that the terminal device connected to before switching to the first node;

[0049] The model requirements include at least one of the following: the required model type, application scenario, task requirements, model operating environment, and the dimensions of the model's input data.

[0050] In some embodiments, obtaining the model requirements of the terminal device includes at least one of the following:

[0051] Receive model requirements sent by the terminal device;

[0052] Receive model requirements sent by the second network device;

[0053] Alternatively, the model requirements can be determined based on the task allocation results of the terminal devices.

[0054] In some embodiments, the task partitioning result is obtained by at least one of the following:

[0055] The tasks of the terminal devices are divided to obtain the task division results;

[0056] Receive the task allocation results sent by the terminal device;

[0057] Alternatively, it can receive the task allocation results sent by the second network device.

[0058] Thirdly, this disclosure also provides a task processing method applied to a second network device, the method comprising:

[0059] Obtain measurement reports from terminal devices;

[0060] A measurement report is sent to a first device and / or a first network device, the first device being located in a second node, the second node being the node the terminal accessed before switching to the first node; the measurement report is used to determine the first time the terminal device switches to the first network device and / or the first node; the first time is used to indicate the processing path of the subtask of switching the terminal device.

[0061] In some embodiments, obtaining a measurement report from a terminal device includes at least one of the following:

[0062] Receive measurement reports sent by terminal devices;

[0063] Measure the terminal equipment and obtain a measurement report;

[0064] Alternatively, predictions can be made about the terminal devices to obtain measurement reports.

[0065] In some embodiments, the measurement report carries at least one of the following information: the current location, speed, direction of movement of the terminal device, identification information of the currently executing subtask, and execution time of the next subtask.

[0066] In some embodiments, the method further includes:

[0067] Receive the end identifier sent by the second device, which is located in the second node;

[0068] Forward the end identifier to the first network device. The end identifier is used to indicate that the path switch was successful.

[0069] In some embodiments, the method further includes sending a model to a terminal device, the model being used to process subtasks.

[0070] In some embodiments, sending the model to the terminal device includes:

[0071] Obtain the model requirements for the terminal devices;

[0072] Based on the model requirements, obtain the model corresponding to the model requirements;

[0073] Send the model to the terminal device;

[0074] The model requirements include at least one of the following: the required model type, application scenario, task requirements, model operating environment, and the dimensions of the model's input data.

[0075] In some embodiments, obtaining the model requirements of the terminal device includes at least one of the following:

[0076] Receive model requirements sent by the terminal device;

[0077] Alternatively, the model requirements can be determined based on the task allocation results of the terminal devices.

[0078] In some embodiments, the task partitioning result is obtained by at least one of the following:

[0079] The tasks of the terminal devices are divided to obtain the task division results;

[0080] Alternatively, receive the task allocation results sent by the terminal device.

[0081] Fourthly, this disclosure provides a task processing method applied to a first device, the first device being located in a second node, the second node being the node that the terminal device accessed before switching to the first node;

[0082] The method includes:

[0083] Receive a measurement report and / or a first handover request from the terminal device. The measurement report is used to determine the first time when the terminal device switches access to the first network device and / or the first node. The first handover request is used to request the processing path of the subtask of the terminal device.

[0084] Based on the measurement report and / or the first handover request, switch the processing path of the subtask on the terminal device.

[0085] In some embodiments, the measurement report carries at least one of the following information: the current location, speed, direction of movement of the terminal device, identification information of the currently executing subtask, and execution time of the next subtask.

[0086] In some embodiments, the first handover request carries at least one of the following:

[0087] The handover time of the terminal device is determined based on the first time the terminal device switches to the first network device and / or the execution time of the subtask;

[0088] Device information of the terminal equipment;

[0089] Identification information of the first network device;

[0090] Alternatively, the identification information of the PDU session to be switched.

[0091] In some embodiments, the method further includes:

[0092] Send a first handover confirmation to the first network device. The first handover confirmation is used to indicate the processing path of the subtask of successfully switching terminal devices.

[0093] Fifthly, embodiments of this disclosure provide a task processing method applied to a first node or a second node, the method comprising:

[0094] Obtain a model for processing subtasks on the terminal device;

[0095] The model is sent to the terminal device through a first network device and / or a second network device; wherein the first network device is the network device that the terminal device switches to, and the second network device is the network device that the terminal device was connected to before switching to the first network device.

[0096] In some embodiments, obtaining a model for processing sub-tasks of a terminal device includes at least one of the following:

[0097] Based on the model requirements of the terminal device, obtain the model corresponding to the model requirements;

[0098] Alternatively, based on the task partitioning results of the terminal device, obtain the model corresponding to the task partitioning results;

[0099] The model requirements include at least one of the following: the required model type, application scenario, task requirements, model operating environment, and the dimensions of the model's input data.

[0100] In some embodiments, model requirements are obtained through at least one of the following methods:

[0101] Receive the model requirements sent by the first network device;

[0102] Receive model requirements sent by the second network device;

[0103] Alternatively, the model requirements can be determined based on the task allocation results of the terminal devices.

[0104] Sixthly, embodiments of this disclosure provide a task processing apparatus applied to a terminal device, the apparatus comprising:

[0105] The first acquisition module is used to acquire the measurement report from the terminal device;

[0106] The first sending module is used to send a measurement report, which is used to determine the first time when the terminal device switches access to the first network device and / or the first node; the first time is used to indicate the processing path of the sub-task of switching the terminal device.

[0107] In a seventh aspect, embodiments of this disclosure provide a task processing apparatus applied to a first network device, the apparatus comprising:

[0108] The second acquisition module is used to acquire the measurement report of the terminal device. The measurement report is used to determine the first time when the terminal device switches to the first network device and / or the first node.

[0109] The second sending module is used to send a first handover request to the first device based on the measurement report. The first device is located in the second node, which is the node that the terminal accessed before switching to the first node. The first handover request is used to request the processing path of the subtask of the terminal device to be switched.

[0110] Eighthly, embodiments of this disclosure provide a task processing apparatus applied to a second network device, the apparatus comprising:

[0111] The third acquisition module is used to acquire the measurement report from the terminal device;

[0112] The third sending module is used to send a measurement report to the first device and / or the first network device, wherein the first device is located in the second node, and the second node is the node that the terminal connected to before switching to the first node; the measurement report is used to determine the first time when the terminal device switches to the first network device and / or the first node; the first time is used to indicate the processing path of the sub-task of the switching terminal device.

[0113] Ninthly, embodiments of this disclosure provide a task processing apparatus applied to a first device, the first device being located in a second node, the second node being the node a terminal device accessed before switching to the first node; the apparatus includes:

[0114] The receiving module is used to receive a measurement report and / or a first handover request from the terminal device. The measurement report is used to determine the first time when the terminal device switches access to the first network device and / or the first node. The first handover request is used to request the processing path of the sub-task of the terminal device.

[0115] The processing module is used to switch the processing path of the subtask of the terminal device based on the measurement report and / or the first switching request.

[0116] In a tenth aspect, embodiments of this disclosure provide a task processing apparatus applied to a first node or a second node, the apparatus comprising:

[0117] The fourth acquisition module is used to acquire the model for processing the subtasks of the terminal device;

[0118] The fourth sending module is used to send the model to the terminal device through the first network device and / or the second network device;

[0119] The first network device is the network device that the terminal device switches to, and the second network device is the network device that the terminal device was connected to before switching to the first network device.

[0120] Eleventhly, embodiments of this disclosure provide a terminal device, including:

[0121] Memory, used to store computer programs;

[0122] A transceiver is used to send and receive data under the control of a processor.

[0123] A processor is used to read computer programs from memory and perform the following operations:

[0124] Obtain measurement reports from terminal devices;

[0125] A measurement report is sent, which is used to determine the first time when the terminal device switches access to the first network device and / or the first node; the first time is used to indicate the processing path of the subtask of switching the terminal device.

[0126] In some embodiments, the measurement report carries at least one of the following information: the current location, speed, direction of movement of the terminal device, identification information of the currently executing subtask, and execution time of the next subtask.

[0127] In some embodiments, obtaining a measurement report from a terminal device includes at least one of the following:

[0128] Measure the terminal equipment and obtain a measurement report;

[0129] Alternatively, predictions can be made about the terminal devices to obtain measurement reports.

[0130] In some embodiments, a measurement report is sent, including at least one of the following:

[0131] The second network device sends a measurement report to the first network device, and the second network device switches the terminal device to the network device it was previously connected to before connecting to the first network device.

[0132] Alternatively, a measurement report can be sent to the first device via a second network device, where the first device is located in a second node, which is the node the terminal device connected to before switching to the first node.

[0133] In some embodiments, the processor is further configured to:

[0134] Receive a model sent by a first network device and / or a second network device; wherein the model is used to process subtasks, and the second network device is the network device that the terminal device was connected to before switching to the first network device.

[0135] In some embodiments, the processor is further configured to:

[0136] Send model requirements to the first network device and / or the second network device. The model requirements are obtained based on the task partitioning results of the terminal device. The task partitioning results include at least one subtask corresponding to the task of the terminal device.

[0137] Model requirements include at least one of the following: the required model type, application scenario, task requirements, model operating environment, and the dimensions of the model's input data.

[0138] In some embodiments, the processor is also used for at least one of the following:

[0139] The tasks of the terminal devices are divided to obtain the task division results;

[0140] Alternatively, receive the task allocation results sent by the first network device and / or the second network device.

[0141] In a twelfth aspect, embodiments of this disclosure provide a network device, which is a first network device, comprising:

[0142] Memory, used to store computer programs;

[0143] A transceiver is used to send and receive data under the control of a processor.

[0144] A processor is used to read computer programs from memory and perform the following operations:

[0145] Obtain a measurement report from the terminal device, which is used to determine the first time when the terminal device switches access to the first network device and / or the first node;

[0146] According to the measurement report, a first handover request is sent to the first device, which is located in the second node. The second node is the node that the terminal accessed before switching to the first node. The first handover request is used to request the processing path of the subtask of the terminal device to be switched.

[0147] In some embodiments, the measurement report carries at least one of the following information: the current location, speed, direction of movement of the terminal device, identification information of the currently executing subtask, and execution time of the next subtask.

[0148] In some embodiments, obtaining a measurement report from a terminal device includes at least one of the following:

[0149] Receive measurement reports sent by the second network device, which is the network device that the terminal device was connected to before switching to the first network device;

[0150] Receive the measurement report sent by the first device.

[0151] In some embodiments, the processor is further configured to: receive a first handover confirmation sent by a first device; wherein the first handover confirmation is used to indicate the processing path of a subtask for successfully switching terminal devices.

[0152] In some embodiments, the processor is further configured to: receive an end identifier sent by a second network device, the end identifier being used to indicate successful path switching; wherein the end identifier is sent by the second device to the second network device, and the second device is located in the second node.

[0153] In some embodiments, the processor is further configured to:

[0154] The first network device receives a second handover request sent by a third device located in the first node. The second handover request is used to instruct the first network device to perform a path switch.

[0155] A second handover confirmation is sent to the third device, which indicates that the handover path is permitted.

[0156] In some embodiments, the first handover request carries at least one of the following:

[0157] The handover time of the terminal device is determined based on the first time the terminal device switches to the first network device and / or the execution time of the subtask. The first time is obtained from the measurement report.

[0158] Device information of the terminal equipment;

[0159] The identification information of the first network device, where the first network device is the network device that the terminal device needs to switch to access;

[0160] Alternatively, the identification information of the PDU session to be switched.

[0161] In some embodiments, the processor is further configured to:

[0162] Obtain a model for processing subtasks on the terminal device;

[0163] Send the model to the terminal device.

[0164] In some embodiments, obtaining a model for processing subtasks of a terminal device includes at least one of the following:

[0165] Based on the model requirements of the terminal device, obtain the model corresponding to the model requirements;

[0166] Based on the task partitioning results of the terminal device, obtain the model corresponding to the task partitioning results;

[0167] The terminal device receives a model sent by a second network device, which is the network device that the terminal device was connected to before switching to the first network device.

[0168] Alternatively, it may receive a model sent by the first node and / or the second node, where the second node is the node that the terminal device connected to before switching to the first node;

[0169] The model requirements include at least one of the following: the required model type, application scenario, task requirements, model operating environment, and the dimensions of the model's input data.

[0170] In some embodiments, obtaining the model requirements of the terminal device includes at least one of the following:

[0171] Receive model requirements sent by the terminal device;

[0172] Receive model requirements sent by the second network device;

[0173] Alternatively, the model requirements can be determined based on the task allocation results of the terminal devices.

[0174] In some embodiments, the task partitioning result is obtained by at least one of the following:

[0175] The tasks of the terminal devices are divided to obtain the task division results;

[0176] Receive the task allocation results sent by the terminal device;

[0177] Alternatively, it can receive the task allocation results sent by the second network device.

[0178] In a thirteenth aspect, embodiments of this disclosure provide a network device, which is a second network device, comprising:

[0179] Memory, used to store computer programs;

[0180] A transceiver is used to send and receive data under the control of a processor.

[0181] A processor is used to read computer programs from memory and perform the following operations:

[0182] Obtain measurement reports from terminal devices;

[0183] A measurement report is sent to a first device and / or a first network device, the first device being located in a second node, the second node being the node the terminal accessed before switching to the first node; the measurement report is used to determine the first time the terminal device switches to the first network device and / or the first node; the first time is used to indicate the processing path of the subtask of switching the terminal device.

[0184] In some embodiments, obtaining a measurement report from a terminal device includes at least one of the following:

[0185] Receive measurement reports sent by terminal devices;

[0186] Measure the terminal equipment and obtain a measurement report;

[0187] Alternatively, predictions can be made about the terminal devices to obtain measurement reports.

[0188] In some embodiments, the measurement report carries at least one of the following information: the current location, speed, direction of movement of the terminal device, identification information of the currently executing subtask, and execution time of the next subtask.

[0189] In some embodiments, the processor is further configured to:

[0190] Receive the end identifier sent by the second device, which is located in the second node;

[0191] Forward the end identifier to the first network device. The end identifier is used to indicate that the path switch was successful.

[0192] In some embodiments, the processor is further configured to: send a model to a terminal device, the model being used to process subtasks.

[0193] In some embodiments, sending the model to the terminal device includes:

[0194] Obtain the model requirements for the terminal devices;

[0195] Based on the model requirements, obtain the model corresponding to the model requirements;

[0196] Send the model to the terminal device;

[0197] The model requirements include at least one of the following: the required model type, application scenario, task requirements, model operating environment, and the dimensions of the model's input data.

[0198] In some embodiments, obtaining the model requirements of the terminal device includes at least one of the following:

[0199] Receive model requirements sent by the terminal device;

[0200] Alternatively, the model requirements can be determined based on the task allocation results of the terminal devices.

[0201] In some embodiments, the task partitioning result is obtained by at least one of the following:

[0202] The tasks of the terminal devices are divided to obtain the task division results;

[0203] Alternatively, receive the task allocation results sent by the terminal device.

[0204] In a fourteenth aspect, embodiments of this disclosure provide a communication device, which is a first device located in a second node, the second node being the node that the terminal device accessed before switching to the first node;

[0205] Communication equipment includes:

[0206] Memory, used to store computer programs;

[0207] A transceiver is used to send and receive data under the control of a processor.

[0208] A processor is used to read computer programs from memory and perform the following operations:

[0209] Receive a measurement report and / or a first handover request from the terminal device. The measurement report is used to determine the first time when the terminal device switches access to the first network device and / or the first node. The first handover request is used to request the processing path of the subtask of the terminal device.

[0210] Based on the measurement report and / or the first handover request, switch the processing path of the subtask on the terminal device.

[0211] In some embodiments, the measurement report carries at least one of the following information:

[0212] The terminal device's current location, speed, direction of movement, identifier information of the currently executing subtask, and execution time of the next subtask.

[0213] In some embodiments, the first handover request carries at least one of the following:

[0214] The handover time of the terminal device is determined based on the first time the terminal device switches to the first network device and / or the execution time of the subtask;

[0215] Device information of the terminal equipment;

[0216] Identification information of the first network device;

[0217] Alternatively, the identification information of the PDU session to be switched.

[0218] In some embodiments, the processor is further configured to: send a first handover confirmation to a first network device, the first handover confirmation being used to indicate the processing path of a subtask for successfully handing over a terminal device.

[0219] In a fifteenth aspect, embodiments of this disclosure provide a communication device, which is a first node or a second node, and the communication device includes;

[0220] The communication device includes:

[0221] Memory, used to store computer programs;

[0222] A transceiver is used to send and receive data under the control of a processor.

[0223] A processor is used to read computer programs from memory and perform the following operations:

[0224] Obtain a model for processing subtasks on the terminal device;

[0225] The model is sent to the terminal device through a first network device and / or a second network device; wherein the first network device is the network device that the terminal device switches to, and the second network device is the network device that the terminal device was connected to before switching to the first network device.

[0226] In some embodiments, obtaining a model for processing sub-tasks of a terminal device includes at least one of the following:

[0227] Based on the model requirements of the terminal device, obtain the model corresponding to the model requirements;

[0228] Alternatively, based on the task division results of the terminal device, obtain the model corresponding to the task division results; wherein, the model requirements include at least one of the following: required model type, application scenario, task requirements, model operating environment, and model input data dimension.

[0229] In some embodiments, model requirements are obtained through at least one of the following methods:

[0230] Receive the model requirements sent by the first network device;

[0231] Receive model requirements sent by the second network device;

[0232] Alternatively, the model requirements can be determined based on the task allocation results of the terminal devices.

[0233] In a sixteenth aspect, embodiments of this disclosure provide a non-transitory readable storage medium storing a computer program for causing a processor to perform the methods of any one of the first, second, third, fourth, or fifth aspects.

[0234] In a seventeenth aspect, embodiments of this disclosure provide a computer program product, comprising: a computer program that, when executed by a processor, implements the method as described in any one of the first, second, third, fourth, or fifth aspects above.

[0235] In the eighteenth aspect, embodiments of this disclosure provide a communication system, including at least one of the following: a terminal device of the eleventh aspect, a first network device of the second aspect, a second network device of the thirteenth aspect, a communication device of the fourteenth aspect, or a communication device of the fifteenth aspect.

[0236] This disclosure provides a task processing method, apparatus, device, and storage medium. A terminal device acquires a measurement report; sends the measurement report, which is used to determine the first time the terminal device switches access to a first network device and / or a first node; the first time is used to indicate the processing path of the subtask of the switched terminal device. In this embodiment, after the terminal device switches access to the network device and / or network node, the processing path of the current subtask of the terminal device can be switched in a timely manner, thereby ensuring that the subtask can be processed normally, ensuring service continuity, and improving user experience. Furthermore, determining the first time the terminal device switches access to the first network device and / or the first node based on the measurement report, and then switching the subtask path based on the first time, provides higher real-time performance and higher reliability of the switching process, further ensuring service continuity and improving user experience.

[0237] It should be understood that the description in the foregoing summary section is not intended to limit the key or essential features of the embodiments of this disclosure, nor is it intended to restrict the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0238] To more clearly illustrate the technical solutions in this disclosure or related technologies, the accompanying drawings used in the description of the embodiments or related technologies will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this disclosure. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0239] Figure 1 is a schematic diagram of a network architecture provided in an embodiment of this disclosure;

[0240] Figure 2a is a schematic diagram of the terminal device switching process provided in an embodiment of this disclosure;

[0241] Figure 2b is an interactive schematic diagram of a task processing method provided in an embodiment of this disclosure;

[0242] Figure 2c is a schematic diagram of the interaction of a task processing method provided in an embodiment of this disclosure;

[0243] Figure 2d is a schematic diagram of the terminal device switching process provided in the embodiment of this disclosure.

[0244] Figure 2e is an interactive schematic diagram of a task processing method provided in an embodiment of this disclosure;

[0245] Figure 2f is an interactive schematic diagram of a task processing method provided in an embodiment of this disclosure;

[0246] Figure 2g is a schematic diagram of the terminal device switching process provided in the embodiments of this disclosure.

[0247] Figure 2h is an interactive schematic diagram of a task processing method provided in an embodiment of this disclosure;

[0248] Figure 2i is an interactive schematic diagram of the model sharing process provided in an embodiment of this disclosure;

[0249] Figure 2j is a second interactive schematic diagram of the model sharing process provided in the embodiments of this disclosure;

[0250] Figure 2k is a schematic diagram of the interaction of the model sharing process provided in the embodiments of this disclosure;

[0251] Figure 21 is an interactive schematic diagram of the model sharing process provided in the embodiments of this disclosure;

[0252] Figure 3a is a schematic diagram of a task processing device according to an embodiment of the present disclosure;

[0253] Figure 3b is a schematic diagram of the structure of a task processing device provided in an embodiment of this disclosure;

[0254] Figure 3c is a schematic diagram of the structure of a task processing device according to an embodiment of this disclosure.

[0255] Figure 3d is a schematic diagram of the structure of a task processing device provided in an embodiment of this disclosure;

[0256] Figure 3e is a schematic diagram of the structure of a task processing device provided in an embodiment of this disclosure;

[0257] Figure 4a is a schematic diagram of the structure of a terminal device provided in an embodiment of this disclosure;

[0258] Figure 4b is a schematic diagram of the structure of a network device provided in an embodiment of this disclosure;

[0259] Figure 4c is a schematic diagram of the structure of a network device provided in an embodiment of this disclosure;

[0260] Figure 4d is a schematic diagram of the structure of a communication device provided in an embodiment of this disclosure;

[0261] Figure 4e is a schematic diagram of the structure of a communication device provided in an embodiment of this disclosure. Detailed Implementation

[0262] In this disclosure, the term "and / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship. In this disclosure, the term "multiple" refers to two or more objects, and other quantifiers are similar.

[0263] The technical solutions of the embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. Based on the embodiments of this disclosure, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this disclosure.

[0264] With the rapid development of communication technology, 6G technology, building upon 5G, empowers more application scenarios. Beyond autonomous driving and intelligent manufacturing, 6G will leverage sensing, imaging, and other technologies combined with mobility to truly unleash the potential of artificial intelligence (AI) and intelligent networks, enabling innovative applications and further integrating communication technology into society. Among these, services with high real-time requirements and strong time-series dependencies, such as large-space XR digital gaming and future AR services, are highly sensitive to switching latency and have strong requirements for device mobility. Simultaneously, tasks requiring AI processing will also experience interruptions due to mobility limitations.

[0265] Therefore, ensuring business continuity and improving user experience when users are on the move has become a major challenge.

[0266] To address the aforementioned issues, this disclosure provides a task processing method, apparatus, device, and storage medium. The method involves acquiring a measurement report from a terminal device; sending the measurement report, which determines the first time the terminal device switches access to a first network device and / or a first node; and using this first time to indicate the processing path of the subtasks of the switched terminal device. In this disclosure, after the terminal device switches its access to a network device and / or network node, the processing path of the terminal device's current subtasks can be switched promptly, ensuring that the subtasks can be processed normally, guaranteeing service continuity, and improving user experience. Furthermore, determining the first time the terminal device switches access to the first network device and / or the first node based on the terminal device's measurement report, and then switching the subtask path based on this first time, provides higher real-time performance and greater reliability of the switching process, further ensuring service continuity and improving user experience.

[0267] Please refer to Figure 1, which is a schematic diagram of a network architecture provided in an embodiment of this disclosure. As shown in Figure 1, the network architecture includes: a terminal device, multiple network devices (network device 1, network device 2, and network device 3 are shown as examples), and multiple network nodes (node ​​1, node 2, and node 3 are shown as examples). During movement, the terminal device switches the network device and / or network node it accesses. For example, when the terminal device is located at position 1, the terminal device accesses network device 1 and then accesses node 1 through network device 1.

[0268] When the terminal device moves to location 2, the terminal device switches to network device 2 and accesses node 1 through network device 2 (the terminal device switches the network device it accesses during the process of moving from location 1 to location 2, but does not switch the node it accesses).

[0269] When the terminal device moves to position 3, the terminal device switches to network device 3 and then switches to node 2 through network device 3 (during the process of the terminal device moving from position 2 to position 3, the network device it connects to is switched, and the node it connects to is also switched).

[0270] When the terminal device moves to position 4, the terminal device accesses network device 3 and switches to node 3 through network device 3 (during the process of the terminal device moving from position 3 to position 4, the network device it accesses is not switched, but the node it accesses is switched).

[0271] It should be noted that the terminal device involved in the embodiments of this disclosure may be a device that provides voice and / or data connectivity to a user, a handheld device with wireless connectivity, or other processing devices connected to a wireless modem. The name of the terminal device may differ in different systems; for example, in a 5G or 6G system, the terminal may be called User Equipment (UE). The wireless terminal may be a USB storage device, other personal computer memory devices, or a dongle. It may also communicate with one or more core networks (CNs) via a Radio Access Network (RAN). The wireless terminal may be a mobile terminal, such as a mobile phone (or "cellular" phone) and a computer with a mobile terminal, for example, a portable, pocket-sized, handheld, computer-embedded, or vehicle-mounted mobile device that exchanges voice and / or data with the radio access network. Examples of such devices include Personal Communication Service (PCS) phones, cordless phones, Session Initiated Protocol (SIP) phones, Wireless Local Loop (WLL) stations, Personal Digital Assistants (PDAs), personal computers, tablets, and Machine-type Communication (MTC) terminals. Wireless terminals can also be referred to as systems, subscriber units, subscriber stations, mobile stations, mobile devices, remote stations, access points, remote terminals, access terminals, user terminals, user agents, user devices, and wireless access devices and routers / modems that meet the limitations of this definition, but are not limited to these in the embodiments of this disclosure.

[0272] The network device involved in this disclosure can be a base station, which may include multiple cells providing services to terminals. Depending on the specific application, the base station may also be called an access point, or a device in the access network that communicates with wireless terminal devices through one or more sectors on the air interface, or other names. The network device can be used to exchange received air frames with Internet Protocol (IP) packets, acting as a router between the wireless terminal device and the rest of the access network, where the rest of the access network may include an Internet Protocol (IP) communication network. The network device can also coordinate the attribute management of the air interface. For example, the network device involved in this disclosure can be an evolved Node B (eNB or e-NodeB) in a long term evolution (LTE) system, a 5G base station (gNB) in a next generation system, or a Home evolved Node B (HeNB), relay node, femto, pico, network testing equipment, etc., and is not limited in this disclosure. In some network architectures, network devices may include centralized unit (CU) nodes and distributed unit (DU) nodes, which may also be geographically separated.

[0273] The nodes involved in the embodiments of this disclosure are not limited thereto. For example, in some embodiments, a node may also be referred to as a "subnet," "device," "network node," "network device," etc. For example, in a distributed network architecture, a node may be a distributed node or a central node. It should be understood that "central" and "distributed" in the embodiments of this disclosure are relative and not strictly physical locations.

[0274] The technical solutions provided in this disclosure can be applied to a variety of systems. For example, applicable systems may include Long Term Evolution (LTE) systems, LTE Frequency Division Duplex (FDD) systems, LTE Time Division Duplex (TDD) systems, Long Term Evolution Advanced (LTE-A) systems, Universal Mobile Telecommunications System (UMTS), Worldwide Interoperability for Microwave Access (WiMAX) systems, 5G New Radio (NR) systems and their evolved communication systems, and 6G (sixth generation mobile communication technology) systems. These systems may include terminals and network equipment. The systems may also include a core network component, such as the Evolved Packet Core (EPC) or the 5G Core Network (5GC).

[0275] In some embodiments, the present disclosure can be applied to a distributed network scenario, where the aforementioned nodes can be distributed network nodes in a distributed network architecture.

[0276] In some embodiments, the present disclosure can be applied to non-distributed network scenarios. In non-distributed network scenarios, both the service servers in the core network and the servers deployed at the edge can provide service to the terminal devices, and the terminal devices can establish sessions with the service servers in the core network and the servers deployed at the edge.

[0277] The technical solutions of the embodiments of this disclosure and how the technical solutions of this disclosure solve the above-mentioned technical problems are described in detail below with specific examples. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments.

[0278] In some embodiments, when a terminal device switches to access different network devices, but the second network device before the switch and the first network device after the switch are connected to the same node (denoted as the second node), the task processing method provided in this disclosure embodiment is shown in Figures 2a, 2b and 2c below.

[0279] Figure 2a is a schematic diagram of the terminal device switching process provided in an embodiment of this disclosure. As shown in Figure 2a, when the terminal device is at position 1, it connects to the second network device and then connects to the second node based on the second network device; when the terminal device moves to position 2, it switches to the first network device and then connects to the second node based on the first network device.

[0280] Figure 2a illustrates the service processing flow of a terminal device, including Task 1, Task 2, Task 3, Task 4, and Task 5. Taking the terminal device's service as a 6G new application service—cloud rendering-based digital e-sports / cloud gaming—as an example, the sub-tasks and processing flow of this service are as follows:

[0281] Task 1: The terminal device (such as Extended Reality (XR) glasses, helmet, etc.) performs motion capture and transmits the capture results to the second node through the network device;

[0282] Task 2: Parse the action from the second node and update the image;

[0283] Task 3: The second node encodes the image and transmits the encoding result to the terminal device;

[0284] Task 4: Decode the screen using the terminal device;

[0285] Task 5: The terminal device renders and displays the image on the screen.

[0286] As shown in Figure 2a, this business processing logic is time-dependent, meaning that the next task can only begin after the previous task is completed, and the output of the previous task is the input of the next task. Furthermore, each task can be further subdivided into subtask 1, subtask 2, ..., subtask n. Different subtasks can be offloaded to different locations for processing, or a suitable model can be requested from different network devices or nodes for local deployment and processing.

[0287] In some embodiments, the terminal device may switch network devices during movement, while network nodes, with their relatively large service range, do not easily switch. Taking cloud-rendered digital esports / cloud gaming services as an example, the motion capture task performed by the terminal device is continuous, meaning that it continuously captures motion (e.g., every t seconds) and transmits the motion signal to the network node, where the XR server of the network node parses the motion and updates the image. In this embodiment, the motion capture task (task 1) can be divided into subtasks 1 (t*n), where n = 1, 2, 3… In some embodiments, this task division can be performed by the terminal device or by the currently connected network device, which then informs the terminal device of the task division result.

[0288] For example, at time t*n, the terminal device is located at L(t*n). Figure 2a shows the relevant logic of service processing by taking the terminal device leaving the second network device after processing subtask 1(t) as an example. The processing result of the subtask refers to the processing result after all subsequent steps are completed.

[0289] As shown in Figure 2a, taking subtask t as an example, before the terminal device switches network devices, the uplink data transmission path of the terminal device's task is: terminal device → second network device → second node; the downlink data transmission path is: second node → second network device → terminal device.

[0290] After the terminal device switches network devices, the uplink data transmission path for the terminal device's task is: terminal device → first network device → second node; the downlink data transmission path is: second node → first network device → terminal device.

[0291] It should be noted that the task division time interval t can be set by the terminal device or network device according to the task granularity and the resources required by the task. Furthermore, the time involved in this embodiment is a unified time, and the situation of time asynchrony between network devices or network nodes is not considered.

[0292] Secondly, if the network device divides the tasks into subtasks, the terminal device can report task requirements to the network device, such as task size, task type, task requirements (required resources, latency guarantees, etc.), etc. The network device will then parse the data and divide the tasks to obtain the task division results.

[0293] In the scenario shown in Figure 2a, please refer to Figures 2b and 2c for the task processing method:

[0294] Figure 2b is an interactive schematic diagram of a task processing method provided in an embodiment of this disclosure. As shown in Figure 2b, the task processing method includes the following steps:

[0295] S211. The terminal device obtains the measurement report of the terminal device.

[0296] In some embodiments, the measurement report includes, but is not limited to, at least one of the following information:

[0297] The terminal device's current location, speed, direction of movement, identification information of the currently executing subtask, and execution time of the next subtask, etc.

[0298] In some embodiments, a measurement report from the terminal device is obtained, including but not limited to at least one of the following:

[0299] 1. The terminal device performs measurements on itself and obtains a measurement report. In some embodiments, the terminal device can use built-in sensors and technologies to measure and acquire its own measurement results, thereby generating a measurement report. For example, the terminal device can obtain the measurement report in at least one of the following ways:

[0300] The terminal device is located to obtain its location information;

[0301] The speed and direction of the terminal device are measured to obtain measurement results such as the speed and direction of the terminal device. For example, the speed, direction of motion and orientation of the terminal device can be determined by accelerometers, gyroscopes and magnetometers.

[0302] By using task management applications on the terminal device, the identification information of the currently executing task and subtask, as well as the execution time of the task, can be determined.

[0303] 2. The terminal device makes predictions and obtains a measurement report. In some embodiments, the terminal device can use artificial intelligence (AI) algorithms to predict the terminal device's position, speed, direction of movement, identification information of the currently executed subtask, and execution time of the next subtask, thereby obtaining a measurement report. The specific method of prediction based on AI algorithms is not limited in this disclosure.

[0304] In some embodiments, the measurement report of the terminal device may also be generated and sent to the terminal device by the network device. For example, taking the network device to which the terminal device is connected as a second network device, the second network device can obtain the measurement report of the terminal device in at least one of the following ways:

[0305] 1. The second network device measures the terminal device and obtains a measurement report. In some embodiments, the second network device may obtain the measurement report of the terminal device through at least one of the following methods:

[0306] Signal strength is measured on the terminal device to determine the distance between the terminal device and the network device. For example, the network device can measure the received signal strength (RSSI) from the terminal device to determine the distance between the terminal device and the network device.

[0307] The angle of arrival (AoA) of a signal is measured on the terminal device to determine its orientation. For example, network devices can use antenna arrays to measure the angle of arrival of a signal, thereby determining the orientation of the terminal device.

[0308] The network device receives feedback from the terminal device to obtain its measurement results. For example, the terminal device can send its measurement results (such as location, speed, direction, task, etc.) to the network device.

[0309] 2. The second network device makes predictions about the terminal device and obtains a measurement report. In some embodiments, the network device can predict the terminal device's position, speed, direction of movement, identification information of the currently executed subtask, and execution time of the next subtask based on AI algorithms, thereby obtaining a measurement report for the terminal device. The specific method of prediction based on AI algorithms is not limited in this embodiment.

[0310] In some embodiments, when a terminal device moves regularly, its position can be measured or predicted using the terminal device's own measurement results or the network device's measurement results, thereby obtaining a measurement report. For example, when the terminal device is located at the junction of the coverage areas of the second network device and the first network device, the next subtask can be transmitted from the first network device to the second node, and the second node can be notified to perform downlink transmission through the first network device.

[0311] In some embodiments, when the terminal device moves irregularly, the terminal device can predict its own position L(t*(n+1)) based on its own will / ability and report it to the second network device, or the second network device can predict the position L(t*(n+1)) of the terminal device based on the historical position of the terminal device received, thereby obtaining a measurement report of the terminal device, so as to analyze the time when the terminal device leaves the second network device and enters the first network device based on the measurement report.

[0312] The present disclosure does not limit the method for determining whether the terminal device moves regularly or irregularly. For example, if the measurement results determine that the terminal device moves the same distance within the same time period and the direction does not change during the movement, it can be considered regular movement. Conversely, if the terminal device moves different distances within the same time period and / or the direction of movement changes during the movement, it is considered irregular movement.

[0313] It should be noted that if the measurement report is generated by the network device and sent to the terminal device, step S212 can be omitted; if the measurement report is generated by the terminal device, step S212 can be performed.

[0314] S212, The terminal device sends a measurement report to the second network device.

[0315] S213, The second network device sends a measurement report to the first network device.

[0316] In some embodiments, the second network device may perform behavioral analysis on the terminal device based on the measurement report to obtain the time when the terminal device leaves the second network device, for example, the terminal device leaves the second network device at time t*n.

[0317] In some embodiments, the second network device and the first network device can exchange measurement reports, so that the first network device and the second network device can analyze the first time when the terminal device enters the first network device. For example, if the terminal device enters the first network device at time t*n, the first network device can reserve resources for the terminal device in advance according to the first time, so that the terminal device can perform tasks based on the resources reserved by the first network device after entering the first network device, thereby ensuring the continuity of services.

[0318] In some embodiments, if the second network device and the first network device cannot directly exchange information, the message can be relayed by the Access and Mobility Management Function (AMF) network element or the Operations, Administration and Maintenance (OAM) device.

[0319] S214. The second network device sends a measurement report to the first device.

[0320] In some embodiments, the measurement report is used to determine the first time when the terminal device switches access to the first network device; the first time is used to indicate the processing path of the subtask of the switching terminal device.

[0321] In some embodiments, the first device is located in the second node. The type of the first device is not limited in this disclosure; for example, the first device can be a device performing functions such as access management, mobility management, and connection management. For instance, if the second node is a distributed network node, the first device can be an AMF network element.

[0322] S215. The first network device sends a first handover request to the first device based on the measurement report.

[0323] S216. The first device switches the processing path of the subtask of the terminal device according to the measurement report and / or the first handover request.

[0324] In some embodiments, the first switching request is an N2 path switching request.

[0325] In some embodiments, the first switching request carries, but is not limited to, at least one of the following:

[0326] 1. Terminal device handover time: The handover time is determined based on the first time the terminal device switches to the first network device and / or the execution time of the subtask. The first time is obtained from the measurement report. The handover time is the minimum of the execution time of the terminal device's next subtask and the first time.

[0327] 2. Device information of the terminal equipment;

[0328] 3. Identification information of the first network device, which is the network device that the terminal device needs to switch to;

[0329] 4. Identification information of the Protocol Data Unit (PDU) session to be switched.

[0330] In some embodiments, after receiving the measurement report, the first device can obtain the content carried in the first switching request based on the content of the measurement report.

[0331] It should be noted that this embodiment does not involve changes in network nodes. Therefore, the PDU Session Anchor (PSA) remains unchanged. Only the N4 session modification and establishment process related to the User Plane Function (UPF) is performed, and the handover time is carried in the signaling interaction information.

[0332] In this embodiment of the disclosure, before path switching, the uplink data transmission path of the service is: terminal device → second network device → second node; the downlink data transmission path is: second node → second network device → terminal device; after path switching, the uplink data transmission path of the service is: terminal device → first network device → second node; the downlink data transmission path is: second node → first network device → terminal device.

[0333] Figure 2c is a second interactive schematic diagram of a task processing method provided in an embodiment of this disclosure. As shown in Figure 2c, the task processing method includes the following steps:

[0334] S221. The terminal device obtains the measurement report of the terminal device.

[0335] It should be noted that if the measurement report is obtained by the network device and sent to the terminal device, step S222 below can be omitted; if the measurement report is obtained by the terminal device, step S222 below can be performed.

[0336] S222, The terminal device sends a measurement report to the second network device.

[0337] S223. The second network device sends a measurement report to the first network device.

[0338] S224. The second network device sends a measurement report to the first device.

[0339] S225. The first network device sends a first handover request to the first device based on the measurement report.

[0340] It should be noted that the implementation of steps S221 to S225 is similar to steps S211 to S215 in the embodiment shown in Figure 2b. For details, please refer to the above embodiment, which will not be repeated here.

[0341] S226. The first device modifies and establishes the N4 session based on the measurement report and / or the first handover request.

[0342] It should be noted that other devices participating in the N4 session modification and establishment process in the second node are not shown in this embodiment. For example, taking the second node as a distributed node, other devices participating in the N4 session modification and establishment process in the second node include, but are not limited to, at least one of the following:

[0343] Second Session Management Function (SMF) network element;

[0344] Target User UPF;

[0345] Source User Plane Functionality (Source UPF);

[0346] UPF(PSA);

[0347] As for the content executed by each device during the N4 session modification and establishment process, please refer to the content in the existing standards, which will not be elaborated here.

[0348] S227. The second device sends an end identifier to the second network device.

[0349] S228. The second network device forwards the end identifier to the first network device.

[0350] In some embodiments, the second device is located in the second node. The type of the second device is not limited in this disclosure; for example, the second device may be a device responsible for processing user data traffic. For instance, in the case where the second node is a distributed network node, the second device may be a UPF network element within the second node.

[0351] In some embodiments, when a terminal device enters the first network device, the second device sends an end identifier to the second network device. The end identifier can be an N3 end identifier.

[0352] In some embodiments, an end flag is used to indicate that the path switch was successful.

[0353] S229. The first device sends a first handover confirmation to the first network device.

[0354] The first handover confirmation is used to indicate the processing path of the subtask of successfully switching terminal devices.

[0355] In some embodiments, the first switch confirmation is an N2 path switch confirmation.

[0356] It should be noted that, referring to Figures 2a and 2c, before the path switching, during the task processing of the terminal device, the uplink data transmission path is: terminal device → second network device → second node; the downlink data transmission path is: second node → second network device → terminal device.

[0357] After the path switch, during the task processing of the terminal device, the uplink data transmission path is: terminal device → first network device → second node; the downlink data transmission path is: second node → first network device → terminal device.

[0358] In one example, for subtask 1(t*n), after subtask 1(t*n) is transmitted from terminal device → second network device → second node, the uplink path of subtask 1(t*(n+1)) becomes "terminal device → first network device → second node". The downlink data transmission path after the subtask is processed is "second node → first network device → terminal device". If the terminal device has left the service range of the second network device before subtask 1(t*n) is finished, the subsequent processing result of subtask 1(t*n) can be transmitted via the path "second node → second network device → first network device → terminal device" or directly to the terminal device via the path "second node → first network device → terminal device".

[0359] In some embodiments, after the path switching is completed, the second network device may release the relevant resources and sessions of the terminal device.

[0360] In some embodiments, when a terminal device is moving at high speed, it may not only switch network devices but also switch distributed nodes. When a terminal device switches to different network devices, and the nodes accessed by the second network device before and after the switch are different (e.g., the first network device accesses the first node, and the second network device accesses the second node), the task processing method provided in this embodiment is illustrated in Figures 2d, 2e, and 2f.

[0361] Figure 2d is a schematic diagram of the terminal device switching process provided in this embodiment of the present disclosure. As shown in Figure 2d, taking cloud-rendered digital e-sports / cloud gaming services as an example, after the XR server in the network node receives the action captured by the terminal device, it will perform action parsing (task 2) and image encoding (task 3). When the XR server receives the sub-task 1 (t*n) transmitted from the uplink, it will process the corresponding sub-task 2 (t*n) and sub-task 3 (t*n). During the processing of Tasks 2 and 3, the movement of the terminal device may cause a switchover of network devices and network nodes. For example, after the second node receives sub-task 1 (t*n), it begins processing sub-tasks 2 (t*n) and 3 (t*n). Before processing is complete, the terminal device moves to the first node, and sub-task 1 (t*(n+1)) is transmitted to the first node. The processing results of sub-tasks 2 (t*n) and 3 (t*n) can be exchanged between the first and second nodes, or relayed through the central node to transmit the processing results to the first node. Therefore, the downlink data transmission path for the processing results of sub-tasks 2 (t*n) and 3 (t*n) is "first node → first network device → terminal device". Subsequent tasks are transmitted through the terminal device, the first network node, and the first node.

[0362] Figure 2e is a schematic diagram of the interaction of a task processing method provided in an embodiment of this disclosure. As shown in Figure 2e, the task processing method includes the following steps:

[0363] S231. The terminal device obtains the measurement report of the terminal device.

[0364] It should be noted that if the measurement report is obtained by the network device and sent to the terminal device, step S232 below can be omitted; if the measurement report is obtained by the terminal device, step S232 below can be performed.

[0365] S232. The terminal device sends a measurement report to the second network device.

[0366] S233, The second network device sends a measurement report to the first network device.

[0367] S234. The second network device sends a measurement report to the first device.

[0368] S235, The first network device sends a first handover request to the first device.

[0369] It should be noted that the implementation of steps S231 to S235 is similar to steps S211 to S215 in the embodiment shown in Figure 2b. For details, please refer to the above embodiment, which will not be repeated here.

[0370] S236. The first device in the second node and the third device in the first node switch the processing path of the subtask of the terminal device according to the first switching request.

[0371] In some embodiments, the first switching request is an N2 path switching request.

[0372] In some embodiments, the first switching request carries, but is not limited to, at least one of the following:

[0373] 1. Terminal device handover time: The handover time is determined based on the first time the terminal device switches to the first network device and / or the execution time of the subtask. The first time is obtained from the measurement report. The handover time is the minimum of the execution time of the terminal device's next subtask and the first time.

[0374] 2. Device information of the terminal equipment;

[0375] 3. Identification information of the first network device, which is the network device that the terminal device needs to switch to;

[0376] 4. Identification information of the PDU session to be switched.

[0377] In this embodiment of the disclosure, before the path switching, the uplink data transmission path of the service is "terminal device → second network device → second node"; the downlink data transmission path is "second node → second network device → terminal device"; after the path switching, the uplink data transmission path of the service is "terminal device → first network device → first node"; the downlink data transmission path is "first node → first network device → terminal device".

[0378] Figure 2f is an interactive schematic diagram of a task processing method provided in an embodiment of this disclosure. As shown in Figure 2c, the task processing method includes the following steps:

[0379] S241. The terminal device obtains the measurement report of the terminal device.

[0380] It should be noted that if the measurement report is obtained by the network device and sent to the terminal device, step S242 can be omitted; if the measurement report is obtained by the terminal device, step S242 can be performed.

[0381] S242. The terminal device sends a measurement report to the second network device.

[0382] S243, The second network device sends a measurement report to the first network device.

[0383] S244. The second network device sends a measurement report to the first device.

[0384] S245, The first network device sends a first handover request to the first device.

[0385] It should be noted that the implementation of steps S241 to S245 is similar to steps S211 to S215 in the embodiment shown in Figure 2b. For details, please refer to the above embodiment, which will not be repeated here.

[0386] S246. The first node and the second node establish the second path and modify the first path.

[0387] As shown in Figures 2d and 2f, the first path is "terminal device → second network device → second node"; the second path is "terminal device → first network device → first node".

[0388] It should be noted that the following are examples of devices or network elements participating in the N4 session modification and establishment process in the second and first nodes:

[0389] Other devices participating in the N4 session modification and establishment process in the second node include, but are not limited to, at least one of the following:

[0390] First equipment, second equipment, fourth equipment, etc.

[0391] Other devices participating in the N4 session modification and establishment process in the first node include, but are not limited to, at least one of the following:

[0392] Third equipment, fifth equipment, sixth equipment, etc.

[0393] The types of the first, second, third, fourth, fifth, and sixth devices are not limited in this embodiment. For example, the first device can be a network element or device in the second node used for functions such as access management, mobility management, and connection management. For instance, if the second node is a distributed network node, the first device can be an AMF network element.

[0394] The second device can be a network element or device in the second node used to process data streams in the user plane. For example, if the second node is a distributed network node, the second device can be a UPF network element.

[0395] The fourth device can be a network element or device in the second node used to manage user sessions. For example, if the second node is a distributed network node, the fourth device can be an SMF network element.

[0396] The third device can be a network element or device in the first node that performs functions such as access management, mobility management, and connection management. For example, if the first node is a distributed network node, the third device can be an AMF network element.

[0397] The fifth device can be a network element or device in the first node used to manage user sessions. For example, if the first node is a distributed network node, the fifth device can be an SMF network element.

[0398] The sixth device can be a network element or device used to process data streams in the user plane. For example, if the first node is a distributed network node, the sixth device can be a UPF network element.

[0399] In some embodiments, the process of establishing the second path includes, but is not limited to, the following two methods:

[0400] Method 1: The first device in the second node (e.g., AMF) selects the fourth device in the first node (e.g., SMF) based on information interaction. The fourth device in the first node interacts with the first device in the second node (e.g., AMF) and the sixth device in the first node (e.g., UPF) to establish a session path within the first node.

[0401] Method 2: The fourth device (e.g., SMF) in the second node selects the fifth device (e.g., SMF) in the first node based on information exchange. The fifth device (e.g., SMF) in the first node interacts with the fourth device (e.g., SMF) and the sixth device (e.g., UPF) in the first node to establish a session path within the first node.

[0402] As for the content performed by an individual device during the N4 session modification and establishment process, please refer to the existing standards; it will not be elaborated here.

[0403] S247. The third device sends a second handover request to the first network device.

[0404] In some embodiments, the second handover request is used to instruct the first network device to perform a path switch.

[0405] S248, The first network device sends a second handover confirmation to the third device.

[0406] In some embodiments, the second switching confirmation is used to indicate that the switching path is permitted.

[0407] S249, The first node and the second node modify the session of the first path and the second path.

[0408] In some embodiments, the air interface connection of the first path can be released, and the second path can be established. At this point, the session path from the terminal device to the second node has been modified, and the terminal device has been disconnected from the second network device. If the subsequent processing results of subtasks 2(t*n) and 3(t*n) have not yet been transmitted to the terminal device, the following two downlink transmission paths are available:

[0409] Path 1 (see downlink data 1 in Figure 2d): Second node → Second network device → First network device → Terminal device;

[0410] Path 2 (see downlink data 2 in Figure 2d): Second node → First node → First network device → Terminal device.

[0411] The path between the second node and the first node can also be traversed through the central node.

[0412] S250, the first node and the second node perform session modification of the second path and session release of the first path.

[0413] Specifically, the second path is modified, and the uplink path of the second path is opened; at the same time, the session-related resources of the first path are released, and all user plane connections of the first path are released.

[0414] In this embodiment of the disclosure, please refer to Figure 2d. Before the path switching (before step S241), the uplink data transmission path of the service is "terminal device → second network device → second node"; the downlink data transmission path is "second node → second network device → terminal device"; after the path switching (after step S250), the uplink data transmission path of the service is "terminal device → first network device → first node"; the downlink data transmission path is "(second node →) first node → first network device → terminal device".

[0415] In some embodiments, when the network device accessed by the terminal device after the location changes is the same as the network device accessed before the location change, but the nodes accessed by the network device before and after the switch are different (for example, the terminal device first accesses the second network device and the second node, and then accesses the second network device and the first node), the task processing method provided in this disclosure embodiment is shown in Figures 2g and 2h below.

[0416] Figure 2g is a schematic diagram of the terminal device switching process provided in this embodiment of the present disclosure. As shown in Figure 2g, taking cloud-rendered digital e-sports / cloud gaming services as an example, after the XR server in the network node receives the action captured by the terminal device, it will perform action parsing (task 2) and image encoding (task 3). When the XR server receives the uplink transmission of subtask 1 (t*n), it will process subtask 2 (t*n) and subtask 3 (t*n) accordingly. During the processing of Tasks 2 and 3, the movement of the terminal device may cause a switch of network nodes. For example, after the second node receives subtask 1 (t*n), it begins processing subtasks 2 (t*n) and 3 (t*n). Before processing is complete, the terminal device moves to the first node, and subtask 1 (t*(n+1)) is transmitted to the first node. The processing results of subtasks 2 (t*n) and 3 (t*n) can be exchanged between the first and second nodes, or relayed through the central node to transmit the processing results to the first node. Therefore, the downlink transmission path of the processing results of subtasks 2 (t*n) and 3 (t*n) is first node → second network device → terminal device. Subsequent tasks are transmitted through the terminal device, the second network node, and the first node.

[0417] Figure 2h is a schematic diagram of the interaction of a task processing method provided in an embodiment of this disclosure. As shown in Figure 2h, the task processing method includes the following steps:

[0418] S251. The terminal device obtains the measurement report of the terminal device.

[0419] S252, The terminal device sends a measurement report to the second network device.

[0420] S253, The second network device sends a measurement report to the first device.

[0421] S254. The second network device sends a first handover request to the first device.

[0422] It should be noted that the implementation of steps S251 to S254 can be referred to steps S211 to S212 and S214 to S215 in the embodiment shown in Figure 2b, which will not be repeated here.

[0423] S255. The first device switches the processing path of the subtask of the terminal device according to the measurement report and / or the first handover request.

[0424] It should be noted that the implementation of step S255 differs from the embodiments shown in Figures 2c and 2f in that, in this embodiment, it is only necessary to modify and release the N4 session in the second node and establish and modify the N4 session in the first node based on the measurement report and / or the first handover request. Other implementation methods can be referred to the implementation methods in Figures 2b and 2f, which will not be repeated here.

[0425] This disclosure provides a task processing method for various mobile scenarios of terminal devices, which can solve the business continuity problem caused by the mobility of terminal devices in various scenarios. After the terminal device switches the network device and / or network node it accesses, it can switch the processing path of the current sub-task of the terminal device in a timely manner, thereby ensuring that the sub-task can be processed normally, ensuring business continuity, and improving user experience.

[0426] In some embodiments, in non-distributed network scenarios, both the service servers within the core network and the servers deployed at the edge can provide service to the terminal devices, and the terminal devices can establish sessions with both the service servers within the core network and the servers deployed at the edge. Service continuity assurance in this case can refer to the solutions described in the above embodiments, and will not be repeated here.

[0427] In some embodiments, the terminal device may switch network devices and network nodes during movement. For tasks requiring AI inference, if the terminal device does not have a suitable AI model, model sharing can be performed across different network devices and network nodes to use the shared model for AI inference. For example, for services such as XR applications and immersive multimedia applications, the terminal device can divide a large task into multiple sub-tasks, with the output of the previous sub-task serving as the input of the next sub-task. Different model acquisition requests and shared model queries can be performed on different network devices and network nodes to provide a shared model for the terminal device. Alternatively, the connected network device can divide a large task into multiple sub-tasks, perform different model acquisition requests and shared model queries on different distributed nodes to provide a shared model for the terminal device.

[0428] Specifically, please refer to Figure 2i, which is an interactive schematic diagram of the model sharing process provided in this embodiment of the disclosure. As shown in Figure 2i, the model sharing process includes the following steps:

[0429] S261. The terminal device sends model requirements and / or task partitioning results to the first network device and / or the second network device.

[0430] In some embodiments, the first network device is a network device that the terminal device switches to; the second network device is a network device that the terminal device accessed before switching to the first network device.

[0431] In some embodiments, model requirements include, but are not limited to, at least one of the following:

[0432] The required model type, application scenario, task requirements, model operating environment, and input data dimensions, etc.

[0433] The task partitioning result includes multiple subtasks after the task is divided. For example, for task 1, task 1 can be divided into subtasks (t*n), where n = 1, 2, 3...

[0434] In some embodiments, the task allocation can be performed by the terminal device; or, the task allocation can be performed by the network device to which the terminal device is connected, and the task allocation result can be sent to the terminal device.

[0435] S262. The first network device and / or the second network device obtain the model according to the model requirements and / or the task partitioning results.

[0436] S263. The first network device and / or the second network device send the model to the terminal device.

[0437] The acquired model meets the model requirements.

[0438] The present disclosure does not limit the method by which the first network device and / or the second network device obtains the model. For example, the first network device and / or the second network device may obtain a model that meets the model requirements from their own storage devices and send it to the terminal device; or, the first network device and / or the second network device may also obtain a model that meets the model requirements from the network nodes they are connected to and send the model to the terminal device. For example, when the terminal device is connected to the first network device and the first network device is currently connected to the second node, the first network device may obtain the model from the second node and forward the model to the terminal device.

[0439] In this embodiment of the disclosure, by proposing a model sharing method, multiple model acquisition methods can be provided based on the mobility of terminal devices, which can reduce network resource utilization, reduce bandwidth usage, reduce latency, improve service processing efficiency, and enhance user experience.

[0440] In some embodiments, when a terminal device switches to access different network devices, but the network devices before and after the switch are connected to the same node, the model sharing process provided in this disclosure embodiment is shown in Figure 2j below.

[0441] Figure 2j is a second interactive schematic diagram of the model sharing process provided in this embodiment of the disclosure. As shown in Figure 2j, the model sharing process includes the following steps:

[0442] S2701. The terminal device divides the task into tasks and obtains the task division results.

[0443] In some embodiments, the task partitioning result includes multiple subtasks, for example, subtasks (t*n), where n = 1, 2, 3...

[0444] It should be noted that step S2701 is an optional step. If step S2701 is not performed, step S2702 can be performed directly.

[0445] S2702, The terminal device sends a model request to the second network device.

[0446] In some embodiments, model requirements include at least one of the following: the required model type, application scenario, task requirements, model operating environment, and model input data dimensions.

[0447] It should be noted that if step S2701 is not performed, then steps S2703 and S2704 below need to be performed; if step S2701 is performed, then step S2703 below is not performed, and step S2705 is performed directly.

[0448] S2703. The second network device divides the task according to the task requirements and obtains the task division results.

[0449] S2704. The second network device sends the task allocation results to the terminal device.

[0450] S2705. The second network device queries whether it has a model that matches the task partitioning results.

[0451] In some embodiments, if the second network device itself has a model that matches the task partitioning result, it directly executes step S2709 to send its own model to the terminal device; if the second network device itself does not have a model that matches the task partitioning result, it executes steps S2706, S2707, S2708, and S2709 to obtain the model from the second node and forward it to the terminal device.

[0452] S2706, The second network device sends the model request to the second node.

[0453] S2707. The second node queries whether it has a model that matches the task partitioning results.

[0454] S2708, The second node sends the model to the second network device.

[0455] S2709, The second network device sends the model to the terminal device.

[0456] In some embodiments, when the second node does not have a model that matches the task partitioning result, it can send a response to the terminal device through the second network device to indicate that there is currently no model that matches the task partitioning result.

[0457] In some embodiments, after the terminal device moves and connects to the first network node, if the subtask (t*n) does not obtain a suitable model, the terminal device can continue to send model requirements that meet the requirements of the subtask (t*n) to the first network node; if the subtask (t*n) has obtained a suitable model, it can send model requirements required for subsequent subtasks, such as the model requirements for the next subtask (t*(n+1)), to the first network device. Specifically, please refer to steps S2710 to S2716 below:

[0458] S2710, The terminal device sends a model request to the first network device.

[0459] S2711, The second network device sends the task allocation result to the first network device.

[0460] In some embodiments, the subtask execution progress and the model acquisition results required by the subtask can also be sent.

[0461] In some embodiments, steps S2710 and S2711 are optional steps. For example, if the terminal device performs task partitioning on its own, it directly sends the task partitioning result to the first network device; if a second network device performs task partitioning, the second network device sends the task partitioning result to the first network device.

[0462] S2712, The second network device sends a model request to the first network device.

[0463] S2713. The first network device queries whether it has a shared model that meets the requirements of the subtask.

[0464] In some embodiments, if the first network device has a model that matches the task partitioning result, it directly executes step S2717 to send its own model to the terminal device; if the first network device does not have a model that matches the task partitioning result, it executes steps S2714, S2715, S2716, and S2717 to obtain the model from the second node and forward it to the terminal device.

[0465] S2714. The first network device sends the model request to the second node.

[0466] S2715. The second node queries whether it has a model that matches the task partitioning results.

[0467] S2716, The second node sends the model to the first network device.

[0468] S2717, The first network device sends the model to the terminal device.

[0469] In some embodiments, if a model that meets the requirements of the current subtask has been found but not yet transmitted to the terminal device before the terminal device leaves the second network device, the model can be sent to the terminal device through interaction between the second network device and the first network device. Specifically, the model can be sent from the second network device to the first network device, and then from the first network device to the terminal device.

[0470] In some embodiments, when a terminal device switches to access different network devices, and the nodes accessed by the network devices before and after the switch are different, the model acquisition process provided in this disclosure embodiment is shown in Figure 2k below.

[0471] Figure 2k is a schematic diagram of the interaction of the model sharing process provided in this embodiment of the present disclosure. As shown in Figure 2k, the model sharing process includes the following steps:

[0472] S2801. The terminal device divides the task into tasks and obtains the task division results.

[0473] It should be noted that step S2801 above is an optional step. If step S2801 is not performed, step S2802 below can be performed directly.

[0474] S2802, The terminal device sends a model request to the second network device.

[0475] In some embodiments, model requirements include at least one of the following: the required model type, application scenario, task requirements, model operating environment, and model input data dimensions.

[0476] It should be noted that step S2803 below is an optional step. If step S2801 above is not performed, then step S2803 below must be performed; if step S2801 above is performed, then step S2803 below is not performed.

[0477] S2803, the second network device divides the task according to the task requirements and obtains the task division results.

[0478] S2804. The second network device sends the task allocation results to the terminal device.

[0479] S2805. The second network device queries whether it has a model that matches the task partitioning results.

[0480] In some embodiments, if the second network device itself has a model that matches the task partitioning results, then step S2809 is executed directly; if the second network device itself does not have a model that matches the task partitioning results, then steps S2806, S2807, S2808, and S2809 are executed.

[0481] S2806, The second network device sends the model request to the second node.

[0482] S2807. The second node queries whether it has a model that matches the task partitioning results.

[0483] S2808, The second node sends the model to the second network device.

[0484] S2809, The second network device sends the model to the terminal device.

[0485] After the terminal device moves and connects to the first network device and the first node, if the subtask (t*n) does not obtain a model that meets the requirements of the subtask (t*n), it continues to send a model requirement that meets the requirements of the subtask (t*n) to the first network device; if the subtask (t*n) has obtained a model that meets the requirements of the subtask, it sends the model requirement required by the subsequent subtask to the first network device, such as the model requirement of the next subtask (t*(n+1)).

[0486] S2810, The terminal device directly sends the model request to the first network device.

[0487] S2811, The second network device sends the task allocation result to the first network device.

[0488] In some embodiments, the subtask execution progress and the model acquisition results required by the subtask can also be sent.

[0489] S2812. The first network device queries whether it has a shared model that meets the requirements of the subtask.

[0490] If the first network device has a model that matches the task partitioning result, it directly executes step S2816 to send its own model to the terminal device; if the first network device does not have a model that matches the task partitioning result, it executes steps S2813, S2814, S2815, and S2816 to obtain the model from the first node and forward the model to the terminal device.

[0491] S2813, The first network device sends the model request to the first node.

[0492] S2814. The first node queries whether it has a model that matches the task partitioning results.

[0493] S2815, The first node sends the model to the first network device.

[0494] S2816, The first network device sends the model to the terminal device.

[0495] In some embodiments, if the model that meets the requirements of the subtask (t*n) has not been transmitted to the terminal device before the terminal device leaves the second network device, the transmission path can be "second node → second network device → first network device → terminal device"; or "second node → first node → first network device → terminal device", wherein the model transmission between the second node and the first node can also be relayed through the central node.

[0496] In some embodiments, when the network device accessed by the terminal device after the location changes is the same as the network device accessed before the location change, but the nodes accessed by the network device before and after the handover are different, the task processing method provided in this embodiment is shown in Figure 21 below.

[0497] Figure 21 is a schematic diagram of the interaction of the model sharing process provided in this embodiment of the present disclosure. As shown in Figure 2k, the model sharing process includes the following steps:

[0498] S2901, The terminal device divides the task into tasks and obtains the task division results.

[0499] It should be noted that if step S2901 is not performed, step S2902 can be performed directly.

[0500] S2902, The terminal device sends a model request to the second network device.

[0501] In some embodiments, model requirements include at least one of the following:

[0502] The required model type, application scenario, task requirements, model operating environment, and input data dimensions.

[0503] It should be noted that step S2901 is an optional step. If step S2901 is not performed, step S2903 must be performed; if step S2901 is performed, step S2903 does not need to be performed.

[0504] S2903. The second network device divides the task according to the task requirements and obtains the task division results.

[0505] S2904. The second network device sends the task allocation results to the terminal device.

[0506] S2905. The second network device queries whether it has a model that matches the task partitioning results.

[0507] In some embodiments, if the second network device has a model that matches the task partitioning result, it directly executes step S2909 to send its own model to the terminal device; if the second network device does not have a model that matches the task partitioning result, it executes steps S2906, S2907, S2908, and S2909 to obtain the model from the first node and forward the model to the terminal device.

[0508] S2906, The second network device sends the model request to the first node.

[0509] S2907. The second node queries whether it has a model that matches the task partitioning results.

[0510] S2908, The second node sends the model to the second network device.

[0511] S2909, The second network device sends the model to the terminal device.

[0512] After the terminal device moves and connects to the first node, if the subtask (t*n) does not obtain a model that meets the requirements of the subtask (t*n), it continues to send a model requirement that meets the requirements of the subtask (t*n) to the second network device; if the subtask (t*n) has obtained a model that meets the requirements of the subtask, it sends the model requirement required by the subsequent subtask to the second network device, such as the model requirement of the next subtask (t*(n+1)).

[0513] S2910, The second network device sends the model request to the first node.

[0514] S2911, The first node queries whether it has a model that matches the task partitioning results.

[0515] S2912, The first node sends the model to the second network device.

[0516] S2913, The second network device sends the model to the terminal device.

[0517] After the terminal device moves and connects to the first node, if the subtask (t*n) does not obtain a model that meets the requirements of the subtask (t*n), it continues to send a model requirement that meets the requirements of the subtask (t*n) to the second network device; if the subtask (t*n) has obtained a model that meets the requirements of the subtask, it sends the model requirement required by the subsequent subtask to the second network device, such as the model requirement of the next subtask (t*(n+1)).

[0518] In this embodiment of the disclosure, if the shared model that meets the requirements of the subtask (t*n) has not been transmitted to the terminal device before the terminal device leaves the second node, the transmission path can be "second node → first node → second network device → terminal device". The model transmission between the second node and the first node can also be relayed through the central node.

[0519] Figure 3a is a schematic diagram of a task processing device according to an embodiment of this disclosure. The task processing device is applied to a terminal device. As shown in Figure 3a, the task processing device 310 includes:

[0520] The first acquisition module 311 is used to acquire the measurement report of the terminal device;

[0521] The first sending module 312 is used to send a measurement report, which is used to determine the first time when the terminal device switches access to the first network device and / or the first node; the first time is used to indicate the processing path of the sub-task of switching the terminal device.

[0522] In some embodiments, the measurement report carries at least one of the following information:

[0523] The terminal device's current location, speed, direction of movement, identifier information of the currently executing subtask, and execution time of the next subtask.

[0524] In some embodiments, the first acquisition module 311 is specifically used for at least one of the following:

[0525] Measure the terminal equipment and obtain a measurement report;

[0526] Alternatively, predictions can be made about the terminal devices to obtain measurement reports.

[0527] In some embodiments, the first sending module 312 is specifically used for at least one of the following:

[0528] The second network device sends a measurement report to the first network device, and the second network device switches the terminal device to the network device it was previously connected to before connecting to the first network device.

[0529] The measurement report is sent to the first device through the second network device. The first device is located in the second node, which is the node that the terminal device connected to before switching to the first node.

[0530] In some embodiments, the first acquisition module 311 is further configured to:

[0531] Receive the model sent by the first network device and / or the second network device;

[0532] The model is used to process subtasks, and the second network device is the network device that the terminal device accessed before switching to the first network device.

[0533] In some embodiments, the first transmitting module 312 is further configured to:

[0534] Send model requirements to the first network device and / or the second network device. The model requirements are obtained based on the task partitioning results of the terminal device. The task partitioning results include at least one subtask corresponding to the task of the terminal device.

[0535] The model requirements include at least one of the following:

[0536] The required model type, application scenario, task requirements, model operating environment, and input data dimensions.

[0537] In some embodiments, the first acquisition module 311 is further configured to perform at least one of the following:

[0538] The tasks of the terminal devices are divided to obtain the task division results;

[0539] Alternatively, receive the task allocation results sent by the first network device and / or the second network device.

[0540] It should be noted that the apparatus provided in this embodiment can implement all the method steps implemented by the terminal device in the above method embodiment and can achieve the same technical effect. Therefore, the parts and beneficial effects that are the same as those in the method embodiment will not be described in detail here.

[0541] Figure 3b is a schematic diagram of a task processing device according to an embodiment of this disclosure. The task processing device is applied to a first network device. As shown in Figure 3b, the task processing device 320 includes:

[0542] The second acquisition module 321 is used to acquire the measurement report of the terminal device. The measurement report is used to determine the first time when the terminal device switches to the first network device and / or the first node.

[0543] The second sending module 322 is used to send a first switching request to the first device according to the measurement report. The first device is located in the second node, which is the node that the terminal accessed before switching to the first node. The first switching request is used to request the processing path of the subtask of the terminal device to switch.

[0544] In some embodiments, the measurement report carries at least one of the following information:

[0545] The terminal device's current location, speed, direction of movement, identifier information of the currently executing subtask, and execution time of the next subtask.

[0546] In some embodiments, the second acquisition module 321 is specifically used for at least one of the following:

[0547] Receive measurement reports sent by the second network device, which is the network device that the terminal device was connected to before switching to the first network device;

[0548] Receive the measurement report sent by the first device.

[0549] The second acquisition module 321 is also configured to: receive a first handover confirmation sent by the first device;

[0550] The first handover confirmation is used to indicate the processing path of the subtask of successfully switching terminal devices.

[0551] In some embodiments, the second acquisition module 321 is further configured to:

[0552] Receive the end identifier sent by the second network device. The end identifier is used to indicate that the path switch was successful.

[0553] The end identifier is sent by the second device to the second network device, which is located in the second node.

[0554] In some embodiments, the second acquisition module 321 is further configured to: receive a second handover request sent by a third device, the third device being located in the first node, the second handover request being used to instruct the first network device to perform a path handover;

[0555] A second handover confirmation is sent to the third device, which indicates that the handover path is permitted.

[0556] In some embodiments, the first handover request carries at least one of the following:

[0557] The handover time of the terminal device is determined based on the first time the terminal device switches to the first network device and / or the execution time of the subtask. The first time is obtained from the measurement report.

[0558] Device information of the terminal equipment;

[0559] The identification information of the first network device, where the first network device is the network device that the terminal device needs to switch to access;

[0560] Identification information of the PDU session to be switched.

[0561] In some embodiments, the second acquisition module 321 is further configured to: acquire a model for processing subtasks of the terminal device;

[0562] The second sending module 322 is also used to send the model to the terminal device.

[0563] In some embodiments, the second acquisition module 321 is specifically used for at least one of the following:

[0564] Based on the model requirements of the terminal device, obtain the model corresponding to the model requirements;

[0565] Based on the task partitioning results of the terminal device, obtain the model corresponding to the task partitioning results;

[0566] The terminal device receives a model sent by a second network device, which is the network device that the terminal device was connected to before switching to the first network device.

[0567] Alternatively, it may receive a model sent by the first node and / or the second node, where the second node is the node that the terminal device connected to before switching to the first node;

[0568] The model requirements include at least one of the following:

[0569] The required model type, application scenario, task requirements, model operating environment, and input data dimensions.

[0570] In some embodiments, the second acquisition module 321 is specifically used for at least one of the following:

[0571] Receive model requirements sent by the terminal device;

[0572] Receive model requirements sent by the second network device;

[0573] Based on the task division results of the terminal devices, the model requirements are determined.

[0574] In some embodiments, the task partitioning result is obtained by at least one of the following:

[0575] The tasks of the terminal devices are divided to obtain the task division results;

[0576] Receive the task allocation results sent by the terminal device;

[0577] Receive the task allocation results sent by the second network device.

[0578] It should be noted that the apparatus provided in this embodiment can implement all the method steps implemented by the first network device in the above method embodiment and can achieve the same technical effect. Therefore, the parts and beneficial effects that are the same as those in the method embodiment will not be described in detail here.

[0579] Figure 3c is a schematic diagram of a task processing device according to an embodiment of this disclosure. The task processing device is applied to a second network device. As shown in Figure 3c, the task processing device 330 includes:

[0580] The third acquisition module 331 is used to acquire the measurement report of the terminal device;

[0581] The third sending module 332 is used to send a measurement report to the first device and / or the first network device, wherein the first device is located in the second node, and the second node is the node that the terminal connected to before switching to the first node; the measurement report is used to determine the first time when the terminal device switches to the first network device and / or the first node; the first time is used to indicate the processing path of the sub-task of the switching terminal device.

[0582] In some embodiments, the third acquisition module 331 is specifically used for:

[0583] Receive measurement reports sent by terminal devices;

[0584] Measure the terminal equipment and obtain a measurement report;

[0585] Alternatively, predictions can be made about the terminal devices to obtain measurement reports.

[0586] In some embodiments, the measurement report carries at least one of the following information:

[0587] The terminal device's current location, speed, direction of movement, identifier information of the currently executing subtask, and execution time of the next subtask.

[0588] In some embodiments, the third acquisition module 331 is further configured to:

[0589] Receive the end identifier sent by the second device, which is located in the second node;

[0590] The third transmitting module 332 is also used for:

[0591] Forward the end identifier to the first network device. The end identifier is used to indicate that the path switch was successful.

[0592] In some embodiments, the third sending module 332 is further configured to:

[0593] The model is sent to the terminal device, and the model is used to process subtasks.

[0594] In some embodiments, the third acquisition module 331 is further configured to:

[0595] Obtain the model requirements for the terminal devices;

[0596] Based on the model requirements, obtain the model corresponding to the model requirements;

[0597] The third transmitting module 332 is specifically used for:

[0598] Send the model to the terminal device;

[0599] The model requirements include at least one of the following:

[0600] The required model type, application scenario, task requirements, model operating environment, and input data dimensions.

[0601] In some embodiments, the third acquisition module 331 is specifically used for at least one of the following:

[0602] Receive model requirements sent by the terminal device;

[0603] Based on the task division results of the terminal devices, the model requirements are determined.

[0604] In some embodiments, the task partitioning result is obtained by at least one of the following:

[0605] The tasks of the terminal devices are divided to obtain the task division results;

[0606] Receive the task allocation results sent by the terminal device.

[0607] It should be noted that the apparatus provided in this embodiment can implement all the method steps implemented by the second network device in the above method embodiment and can achieve the same technical effect. Therefore, the parts and beneficial effects that are the same as those in the method embodiment will not be described in detail here.

[0608] Figure 3d is a schematic diagram of a task processing device according to an embodiment of this disclosure. The task processing device is applied to a first device. As shown in Figure 3d, the task processing device 340 includes:

[0609] The receiving module 341 is used to receive a measurement report and / or a first handover request from the terminal device. The measurement report is used to determine the first time when the terminal device switches to access the first network device and / or the first node. The first handover request is used to request the processing path of the sub-task of the terminal device.

[0610] Processing module 342 is used to switch the processing path of the subtask of the terminal device according to the measurement report and / or the first switching request.

[0611] In some embodiments, the measurement report carries at least one of the following information:

[0612] The terminal device's current location, speed, direction of movement, identifier information of the currently executing subtask, and execution time of the next subtask.

[0613] In some embodiments, the first handover request carries at least one of the following:

[0614] The handover time of the terminal device is determined based on the first time the terminal device switches to the first network device and / or the execution time of the subtask;

[0615] Device information of the terminal equipment;

[0616] Identification information of the first network device;

[0617] Identification information of the PDU session to be switched.

[0618] In some embodiments, the task processing device 340 further includes a sending module 343, configured to send a first handover confirmation to a first network device, the first handover confirmation indicating the processing path of a subtask for successfully switching terminal devices.

[0619] Figure 3e is a schematic diagram of a task processing device according to an embodiment of this disclosure. The task processing device is applied to a first node or a second node. As shown in Figure 3e, the task processing device 350 includes:

[0620] The fourth acquisition module 351 is used to acquire the model for processing the sub-tasks of the terminal device;

[0621] The fourth sending module 352 is used to send a model to the terminal device through the first network device and / or the second network device;

[0622] The first network device is the network device that the terminal device switches to, and the second network device is the network device that the terminal device was connected to before switching to the first network device.

[0623] In some embodiments, the fourth acquisition module 351 is used for at least one of the following:

[0624] Based on the model requirements of the terminal device, obtain the model corresponding to the model requirements;

[0625] Alternatively, based on the task partitioning results of the terminal device, obtain the model corresponding to the task partitioning results;

[0626] The model requirements include at least one of the following:

[0627] The required model type, application scenario, task requirements, model operating environment, and input data dimensions.

[0628] In some embodiments, model requirements are obtained through at least one of the following methods:

[0629] Receive the model requirements sent by the first network device;

[0630] Receive model requirements sent by the second network device;

[0631] Based on the task division results of the terminal devices, the model requirements are determined.

[0632] It should be noted that the apparatus provided in this embodiment can implement all the method steps implemented by the first or second node in the above method embodiment, and can achieve the same technical effect. Therefore, the parts and beneficial effects that are the same as those in the method embodiment will not be described in detail here.

[0633] Figure 4a is a schematic diagram of the structure of a terminal device provided in an embodiment of this disclosure. As shown in Figure 4a, the terminal device provided in this embodiment includes:

[0634] Transceiver 411 is used to send and receive data under the control of processor 412;

[0635] Memory 413 is used to store computer programs;

[0636] In Figure 4a, the bus architecture may include any number of interconnected buses and bridges, specifically linking various circuits of one or more processors represented by processor 412 and memory represented by memory 413. The bus architecture may also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface provides an interface. Transceiver 411 may be multiple elements, including transmitters and receivers, providing a unit for communicating with various other devices over transmission media, including wireless channels, wired channels, optical fibers, etc. Processor 412 is responsible for managing the bus architecture and general processing, and memory 413 may store data used by processor 412 during operation.

[0637] The processor 412 is responsible for managing the bus architecture and general processing, while the memory 413 can store the data used by the processor 412 when performing operations.

[0638] In some embodiments, the processor 412 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a complex programmable logic device (CPLD), and the processor may also adopt a multi-core architecture.

[0639] The processor 412 executes any of the methods related to the UPF provided in this disclosure embodiment according to the obtained executable instructions by calling a computer program stored in the memory 413. The processor and the memory may also be physically separated.

[0640] Specifically, processor 412 is used to read computer programs from memory and perform the following operations:

[0641] Obtain measurement reports from terminal devices;

[0642] A measurement report is sent, which is used to determine the first time when the terminal device switches access to the first network device and / or the first node; the first time is used to indicate the processing path of the subtask of switching the terminal device.

[0643] In some embodiments, the measurement report carries at least one of the following information:

[0644] The terminal device's current location, speed, direction of movement, identifier information of the currently executing subtask, and execution time of the next subtask.

[0645] In some embodiments, obtaining a measurement report from a terminal device includes at least one of the following:

[0646] Measure the terminal equipment and obtain a measurement report;

[0647] Alternatively, predictions can be made about the terminal devices to obtain measurement reports.

[0648] In some embodiments, a measurement report is sent, including at least one of the following:

[0649] The second network device sends a measurement report to the first network device, and the second network device switches the terminal device to the network device it was previously connected to before connecting to the first network device.

[0650] The measurement report is sent to the first device through the second network device. The first device is located in the second node, which is the node that the terminal device connected to before switching to the first node.

[0651] In some embodiments, the processor 412 is further configured to:

[0652] Receive the model sent by the first network device and / or the second network device;

[0653] The model is used to process subtasks, and the second network device is the network device that the terminal device accessed before switching to the first network device.

[0654] In some embodiments, the processor 412 is further configured to: send a model requirement to a first network device and / or a second network device, the model requirement being obtained based on the task partitioning result of the terminal device, the task partitioning result including at least one subtask corresponding to the task of the terminal device;

[0655] The model requirements include at least one of the following:

[0656] The required model type, application scenario, task requirements, model operating environment, and input data dimensions.

[0657] In some embodiments, the processor is also used for at least one of the following:

[0658] The tasks of the terminal devices are divided to obtain the task division results;

[0659] Alternatively, receive the task allocation results sent by the first network device and / or the second network device.

[0660] It should be noted that the terminal device provided in this disclosure can implement all the method steps implemented by the terminal device in the above method embodiments and can achieve the same technical effect. Therefore, the parts and beneficial effects that are the same as those in the method embodiments will not be described in detail here.

[0661] Figure 4b is a schematic diagram of the structure of a network device provided in an embodiment of this disclosure. As shown in Figure 4b, the network device provided in this embodiment includes:

[0662] Transceiver 421 is used to send and receive data under the control of processor 422;

[0663] Memory 423 is used to store computer programs;

[0664] In Figure 4a, the bus architecture may include any number of interconnected buses and bridges, specifically linking various circuits of one or more processors represented by processor 422 and memory represented by memory 423. The bus architecture may also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface provides an interface. Transceiver 421 may be multiple elements, including transmitters and receivers, providing a unit for communicating with various other devices over transmission media, including wireless channels, wired channels, optical fibers, etc. Processor 422 is responsible for managing the bus architecture and general processing, and memory 423 may store data used by processor 422 during operation.

[0665] The processor 422 is responsible for managing the bus architecture and general processing, while the memory 423 can store the data used by the processor 422 when performing operations.

[0666] In some embodiments, the processor 422 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a complex programmable logic device (CPLD), and the processor may also adopt a multi-core architecture.

[0667] The processor 422 executes any of the methods related to the UPF provided in this disclosure embodiment according to the obtained executable instructions by calling a computer program stored in the memory 423. The processor and the memory may also be physically separated.

[0668] Specifically, processor 422 is used to read computer programs from memory and perform the following operations:

[0669] Obtain a measurement report from the terminal device, which is used to determine the first time when the terminal device switches access to the first network device and / or the first node;

[0670] According to the measurement report, a first handover request is sent to the first device, which is located in the second node. The second node is the node that the terminal accessed before switching to the first node. The first handover request is used to request the processing path of the subtask of the terminal device to be switched.

[0671] In some embodiments, the measurement report carries at least one of the following information:

[0672] The terminal device's current location, speed, direction of movement, identifier information of the currently executing subtask, and execution time of the next subtask.

[0673] In some embodiments, obtaining a measurement report from a terminal device includes at least one of the following:

[0674] Receive measurement reports sent by the second network device, which is the network device that the terminal device was connected to before switching to the first network device;

[0675] Receive the measurement report sent by the first device.

[0676] In some embodiments, the processor 422 is further configured to: receive a first handover confirmation sent by the first device;

[0677] The first handover confirmation is used to indicate the processing path of the subtask of successfully switching terminal devices.

[0678] In some embodiments, the processor 422 is further configured to: receive an end identifier sent by the second network device, the end identifier being used to indicate that the path switching was successful;

[0679] The end identifier is sent by the second device to the second network device, which is located in the second node.

[0680] In some embodiments, the processor 422 is further configured to:

[0681] The first network device receives a second handover request sent by a third device located in the first node. The second handover request is used to instruct the first network device to perform a path switch.

[0682] A second handover confirmation is sent to the third device, which indicates that the handover path is permitted.

[0683] In some embodiments, the first handover request carries at least one of the following:

[0684] The handover time of the terminal device is determined based on the first time the terminal device switches to the first network device and / or the execution time of the subtask. The first time is obtained from the measurement report.

[0685] Device information of the terminal equipment;

[0686] The identification information of the first network device, where the first network device is the network device that the terminal device needs to switch to access;

[0687] Alternatively, the identification information of the PDU session to be switched.

[0688] In some embodiments, the processor is further configured to:

[0689] Obtain a model for processing subtasks on the terminal device;

[0690] Send the model to the terminal device.

[0691] In some embodiments, obtaining a model for processing subtasks of a terminal device includes at least one of the following:

[0692] Based on the model requirements of the terminal device, obtain the model corresponding to the model requirements;

[0693] Based on the task partitioning results of the terminal device, obtain the model corresponding to the task partitioning results;

[0694] The terminal device receives a model sent by a second network device, which is the network device that the terminal device was connected to before switching to the first network device.

[0695] Alternatively, it may receive a model sent by the first node and / or the second node, where the second node is the node that the terminal device connected to before switching to the first node;

[0696] The model requirements include at least one of the following: the required model type, application scenario, task requirements, model operating environment, and the dimensions of the model's input data.

[0697] In some embodiments, obtaining the model requirements of the terminal device includes at least one of the following:

[0698] Receive model requirements sent by the terminal device;

[0699] Receive model requirements sent by the second network device;

[0700] Alternatively, the model requirements can be determined based on the task allocation results of the terminal devices.

[0701] In some embodiments, the task partitioning result is obtained by at least one of the following:

[0702] The tasks of the terminal devices are divided to obtain the task division results;

[0703] Receive the task allocation results sent by the terminal device;

[0704] Alternatively, it can receive the task allocation results sent by the second network device.

[0705] It should be noted that the network device provided in this disclosure can implement all the method steps implemented by the first network device in the above method embodiment and can achieve the same technical effect. Therefore, the parts and beneficial effects that are the same as those in the method embodiment will not be described in detail here.

[0706] Figure 4c is a second schematic diagram of the structure of a network device provided in an embodiment of this disclosure. As shown in Figure 4c, the network device provided in this embodiment includes:

[0707] Transceiver 431 is used to send and receive data under the control of processor 432;

[0708] Memory 433 is used to store computer programs;

[0709] In Figure 4a, the bus architecture may include any number of interconnected buses and bridges, specifically linking various circuits of one or more processors represented by processor 432 and memory represented by memory 433. The bus architecture may also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface provides an interface. The transceiver 431 may be multiple elements, including a transmitter and a receiver, providing a unit for communicating with various other devices over a transmission medium, including wireless channels, wired channels, optical fibers, etc. Processor 432 is responsible for managing the bus architecture and general processing, and memory 433 may store data used by processor 432 during operation.

[0710] The processor 432 is responsible for managing the bus architecture and general processing, while the memory 433 can store the data used by the processor 432 when performing operations.

[0711] In some embodiments, the processor 432 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a complex programmable logic device (CPLD), and the processor may also adopt a multi-core architecture.

[0712] The processor 432 executes any of the methods related to the UPF provided in this disclosure embodiment according to the obtained executable instructions by calling a computer program stored in the memory 433. The processor and the memory may also be physically separated.

[0713] Specifically, processor 432 is used to read computer programs from memory and perform the following operations:

[0714] Obtain measurement reports from terminal devices;

[0715] A measurement report is sent to a first device and / or a first network device, the first device being located in a second node, the second node being the node the terminal accessed before switching to the first node; the measurement report is used to determine the first time the terminal device switches to the first network device and / or the first node; the first time is used to indicate the processing path of the subtask of switching the terminal device.

[0716] In some embodiments, obtaining a measurement report from a terminal device includes at least one of the following:

[0717] Receive measurement reports sent by terminal devices;

[0718] Measure the terminal equipment and obtain a measurement report;

[0719] Alternatively, predictions can be made about the terminal devices to obtain measurement reports.

[0720] In some embodiments, the measurement report carries at least one of the following information:

[0721] The terminal device's current location, speed, direction of movement, identifier information of the currently executing subtask, and execution time of the next subtask.

[0722] In some embodiments, the processor 432 is further configured to:

[0723] Receive the end identifier sent by the second device, which is located in the second node;

[0724] Forward the end identifier to the first network device. The end identifier is used to indicate that the path switch was successful.

[0725] In some embodiments, the processor 432 is further configured to: send a model to a terminal device, the model being used to process subtasks.

[0726] In some embodiments, sending the model to the terminal device includes:

[0727] Obtain the model requirements for the terminal devices;

[0728] Based on the model requirements, obtain the model corresponding to the model requirements;

[0729] Send the model to the terminal device;

[0730] The model requirements include at least one of the following: the required model type, application scenario, task requirements, model operating environment, and the dimensions of the model's input data.

[0731] In some embodiments, obtaining the model requirements of the terminal device includes at least one of the following:

[0732] Receive model requirements sent by the terminal device;

[0733] Alternatively, the model requirements can be determined based on the task allocation results of the terminal devices.

[0734] In some embodiments, the task partitioning result is obtained by at least one of the following:

[0735] The tasks of the terminal devices are divided to obtain the task division results;

[0736] Alternatively, receive the task allocation results sent by the terminal device.

[0737] It should be noted that the network device provided in this disclosure can implement all the method steps implemented by the second network device in the above method embodiment and can achieve the same technical effect. Therefore, the parts and beneficial effects that are the same as those in the method embodiment will not be described in detail here.

[0738] Figure 4d is a schematic diagram of the structure of a communication device provided in an embodiment of this disclosure. As shown in Figure 4d, the communication device provided in this embodiment includes:

[0739] Transceiver 441 is used to send and receive data under the control of processor 442;

[0740] Memory 443 is used to store computer programs;

[0741] In Figure 4a, the bus architecture may include any number of interconnected buses and bridges, specifically linking various circuits of one or more processors represented by processor 442 and memory represented by memory 443. The bus architecture may also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface provides an interface. Transceiver 441 may be multiple elements, including transmitters and receivers, providing a unit for communicating with various other devices over transmission media, including wireless channels, wired channels, optical fibers, etc. Processor 442 is responsible for managing the bus architecture and general processing, and memory 443 may store data used by processor 442 during operation.

[0742] Processor 442 is responsible for managing the bus architecture and general processing, while memory 443 can store the data used by processor 442 when performing operations.

[0743] In some embodiments, the processor 442 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a complex programmable logic device (CPLD), and the processor may also adopt a multi-core architecture.

[0744] The processor 442 executes any of the methods related to the UPF provided in this disclosure embodiment according to the obtained executable instructions by calling a computer program stored in the memory 443. The processor and the memory may also be physically separated.

[0745] Specifically, processor 442 is used to read computer programs from memory and perform the following operations:

[0746] Receive a measurement report and / or a first handover request from the terminal device. The measurement report is used to determine the first time when the terminal device switches access to the first network device and / or the first node. The first handover request is used to request the processing path of the subtask of the terminal device.

[0747] Based on the measurement report and / or the first handover request, switch the processing path of the subtask on the terminal device.

[0748] In some embodiments, the measurement report carries at least one of the following information: the current location, speed, direction of movement of the terminal device, identification information of the currently executing subtask, and execution time of the next subtask.

[0749] In some embodiments, the first handover request carries at least one of the following:

[0750] The handover time of the terminal device is determined based on the first time the terminal device switches to the first network device and / or the execution time of the subtask;

[0751] Device information of the terminal equipment;

[0752] Identification information of the first network device;

[0753] Alternatively, the identification information of the PDU session to be switched.

[0754] In some embodiments, the processor 442 is further configured to: send a first handover confirmation to a first network device, the first handover confirmation being used to indicate the processing path of a subtask for successfully handing over a terminal device.

[0755] It should be noted that the communication device provided in this disclosure can implement all the method steps implemented by the first device in the above method embodiment and can achieve the same technical effect. Therefore, the parts and beneficial effects that are the same as those in the method embodiment will not be described in detail here.

[0756] Figure 4e is a second schematic diagram of the structure of a communication device provided in an embodiment of this disclosure. As shown in Figure 4e, the communication device provided in this embodiment includes:

[0757] Transceiver 451 is used to send and receive data under the control of processor 452;

[0758] Memory 453 is used to store computer programs;

[0759] In Figure 4a, the bus architecture may include any number of interconnected buses and bridges, specifically linking various circuits of one or more processors represented by processor 452 and memory represented by memory 453. The bus architecture may also link various other circuits such as peripheral devices, voltage regulators, and power management circuits, which are well known in the art and therefore will not be described further herein. The bus interface provides an interface. Transceiver 451 may be multiple elements, including transmitters and receivers, providing a unit for communicating with various other devices over transmission media, including wireless channels, wired channels, optical fibers, etc. Processor 452 is responsible for managing the bus architecture and general processing, and memory 453 may store data used by processor 452 during operation.

[0760] The processor 452 is responsible for managing the bus architecture and general processing, while the memory 453 can store the data used by the processor 452 when performing operations.

[0761] In some embodiments, the processor 452 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or a complex programmable logic device (CPLD), and the processor may also adopt a multi-core architecture.

[0762] The processor 452 executes any of the methods related to the UPF provided in this disclosure embodiment according to the obtained executable instructions by calling a computer program stored in the memory 453. The processor and the memory may also be physically separated.

[0763] Specifically, processor 452 is used to read computer programs from memory and perform the following operations:

[0764] Obtain a model for processing subtasks on the terminal device;

[0765] The model is sent to the terminal device through the first network device and / or the second network device;

[0766] The first network device is the network device that the terminal device switches to, and the second network device is the network device that the terminal device was connected to before switching to the first network device.

[0767] In some embodiments, obtaining a model for processing sub-tasks of a terminal device includes at least one of the following:

[0768] Based on the model requirements of the terminal device, obtain the model corresponding to the model requirements;

[0769] Alternatively, based on the task partitioning results of the terminal device, obtain the model corresponding to the task partitioning results;

[0770] The model requirements include at least one of the following: the required model type, application scenario, task requirements, model operating environment, and the dimensions of the model's input data.

[0771] In some embodiments, model requirements are obtained through at least one of the following methods:

[0772] Receive the model requirements sent by the first network device;

[0773] Receive model requirements sent by the second network device;

[0774] Alternatively, the model requirements can be determined based on the task allocation results of the terminal devices.

[0775] It should be noted that the communication device provided in this disclosure can implement all the method steps implemented by the first node or the second node in the above method embodiment, and can achieve the same technical effect. Therefore, the parts and beneficial effects that are the same as those in the method embodiment will not be described in detail here.

[0776] This disclosure also provides a non-transient readable storage medium storing a computer program. The computer program is used to cause a processor to execute any of the methods provided in the embodiments of this disclosure, enabling the processor to implement all the method steps implemented by any of the terminal devices, first network devices, second network devices, first devices, first nodes, or second nodes in the above method implementation, and to achieve the same technical effect. Here, the parts that are the same as those in the method embodiments and the beneficial effects will not be described again.

[0777] The non-transiently readable storage medium can be any available medium or data storage device that the processor can access, including but not limited to magnetic memory (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MOs), etc.), optical memory (such as CDs, DVDs, BDs, HVDs, etc.), and semiconductor memory (such as ROMs, EPROMs, EEPROMs, non-volatile memory (NAND FLASH), solid-state drives (SSDs)).

[0778] Those skilled in the art will understand that embodiments of this disclosure can be provided as methods, systems, or computer program products. Therefore, this disclosure can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this disclosure can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0779] This disclosure is described with reference to signaling interaction diagrams and / or block diagrams of methods, apparatus, and computer program products according to embodiments of this disclosure. It will be understood that each block of the signaling interaction diagrams and / or block diagrams, and combinations of blocks in the signaling interaction diagrams and / or block diagrams, can be implemented by computer-executable instructions. These computer-executable instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in one or more blocks of the signaling interaction diagrams and / or one or more blocks of the block diagrams.

[0780] These processor-executable instructions may also be stored in a processor-readable memory that can instruct a computer or other programmable data processing device to operate in a particular manner, such that the instructions stored in the processor-readable memory produce an article of manufacture including instruction means that implement the functions specified in one or more flow diagrams and / or one or more blocks in a block diagram.

[0781] These processor-executable instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide steps for implementing the functions specified in one or more flow diagrams and / or one or more blocks in a block diagram.

[0782] Obviously, those skilled in the art can make various modifications and variations to this disclosure without departing from its spirit and scope. Therefore, if such modifications and variations fall within the scope of the claims of this disclosure and their equivalents, this disclosure is also intended to include such modifications and variations.

Claims

1. A task processing method, wherein, Applied to a terminal device, the method includes: Obtain the measurement report from the terminal device; The measurement report is sent to determine the first time when the terminal device switches access to the first network device and / or the first node; the first time is used to indicate the processing path of the subtask of switching the terminal device.

2. The method according to claim 1, wherein, The measurement report carries at least one of the following information: The terminal device's current position, speed, direction of movement, identifier information of the currently executing subtask, and execution time of the next subtask.

3. The method according to claim 1, wherein, The acquisition of the measurement report from the terminal device includes at least one of the following: The terminal device is measured to obtain the measurement report; Alternatively, the terminal device can be predicted to obtain the measurement report.

4. The method according to claim 1, wherein, Sending the measurement report includes at least one of the following: The measurement report is sent to the first network device via a second network device, wherein the second network device is the network device that the terminal device was connected to before switching to the first network device; The measurement report is sent to the first device via the second network device, where the first device is located in the second node, which is the node that the terminal device accessed before switching to the first node.

5. The method according to any one of claims 1-4, wherein, Also includes: Receive the model sent by the first network device and / or the second network device; The model is used to process the sub-task, and the second network device is the network device that the terminal device accessed before switching to the first network device.

6. The method according to claim 5, wherein, Also includes: Send a model requirement to the first network device and / or the second network device. The model requirement is obtained based on the task partitioning result of the terminal device. The task partitioning result includes at least one subtask corresponding to the task of the terminal device. The model requirements include at least one of the following: The required model type, application scenario, task requirements, model operating environment, and input data dimensions.

7. The method according to claim 6, wherein, It also includes at least one of the following: The tasks of the terminal device are divided to obtain the task division results; Alternatively, it may receive the task partitioning results sent by the first network device and / or the second network device.

8. A task processing method, wherein, Applied to a first network device, the method includes: Obtain a measurement report from the terminal device, the measurement report being used to determine the first time when the terminal device switches access to the first network device and / or the first node; Based on the measurement report, a first switching request is sent to a first device, which is located in a second node. The second node is the node that the terminal accessed before switching to the first node. The first switching request is used to request a change in the processing path of the terminal device's subtasks.

9. The method according to claim 8, wherein, The measurement report carries at least one of the following information: The terminal device's current position, speed, direction of movement, identifier information of the currently executing subtask, and execution time of the next subtask.

10. The method according to claim 8, wherein, The acquisition of the measurement report from the terminal device includes at least one of the following: The terminal device receives the measurement report sent by the second network device, which is the network device that the terminal device accessed before switching to the first network device. Receive the measurement report sent by the first device.

11. The method according to claim 10, wherein, Also includes: Receive the first handover confirmation sent by the first device; The first switching confirmation is used to indicate the processing path of the subtask of the terminal device that has been successfully switched.

12. The method according to claim 11, wherein, Also includes: Receive an end identifier sent by the second network device, the end identifier being used to indicate successful path switching; The end identifier is sent by the second device to the second network device, which is located in the second node.

13. The method according to claim 8, wherein, Also includes: The first network device receives a second handover request sent by a third device located in the first node. The second handover request is used to instruct the first network device to perform a path switch. A second handover confirmation is sent to the third device, the second handover confirmation indicating that the handover path is permitted.

14. The method according to claim 8, wherein, The first handover request carries at least one of the following: The switching time of the terminal device is determined based on the first time the terminal device switches to the first network device and / or the execution time of the subtask, wherein the first time is obtained based on the measurement report; The device information of the terminal device; The identification information of the first network device, wherein the first network device is the network device that the terminal device needs to switch to access; Identification information of the Protocol Data Unit (PDU) session to be switched.

15. The method according to any one of claims 8-14, wherein, Also includes: Obtain a model for processing subtasks of the terminal device; Send the model to the terminal device.

16. The method according to claim 15, wherein, The model for obtaining the sub-tasks for processing the terminal device includes at least one of the following: Based on the model requirements of the terminal device, obtain the model corresponding to the model requirements; Based on the task partitioning results of the terminal device, obtain the model corresponding to the task partitioning results; The terminal device receives the model sent by the second network device, which is the network device that the terminal device accessed before switching to the first network device; Alternatively, the device may receive the model sent by the first node and / or the second node, where the second node is the node that the terminal device connected to before switching to the first node; The model requirements include at least one of the following: The required model type, application scenario, task requirements, model operating environment, and input data dimensions.

17. The method according to claim 16, wherein, The requirement to obtain the model of the terminal device includes at least one of the following: Receive the model requirements sent by the terminal device; Receive the model requirements sent by the second network device; Alternatively, the model requirements can be determined based on the task division results of the terminal device.

18. The method according to claim 16, wherein, The task partitioning results were obtained through at least one of the following: The tasks of the terminal device are divided to obtain the task division results; Receive the task allocation result sent by the terminal device; Alternatively, it may receive the task allocation result sent by the second network device.

19. A task processing method, wherein, Applied to a second network device, the method includes: Obtain measurement reports from terminal devices; The measurement report is sent to a first device and / or a first network device, the first device being located in a second node, the second node being the node the terminal accessed before switching to the first node; the measurement report is used to determine the first time the terminal device switched to the first network device and / or the first node; the first time is used to indicate the processing path of the subtask of switching the terminal device.

20. The method according to claim 19, wherein, The acquisition of the measurement report from the terminal device includes at least one of the following: Receive the measurement report sent by the terminal device; The terminal device is measured to obtain the measurement report; Alternatively, the terminal device can be predicted to obtain the measurement report.

21. The method according to claim 19, wherein, The measurement report carries at least one of the following information: The terminal device's current position, speed, direction of movement, identifier information of the currently executing subtask, and execution time of the next subtask.

22. The method according to claim 19, wherein, Also includes: Receive the end identifier sent by the second network element in the second node; The termination identifier is forwarded to the first network device, and the termination identifier is used to indicate that the path switch was successful.

23. The method according to any one of claims 19-22, wherein, Also includes: A model is sent to the terminal device, the model being used to process the subtask.

24. The method according to claim 23, wherein, Sending the model to the terminal device includes: Obtain the model requirements of the terminal device; Based on the model requirements, obtain the model corresponding to the model requirements; Send the model to the terminal device; The model requirements include at least one of the following: the required model type, application scenario, task requirements, model operating environment, and model input data dimensions.

25. The method according to claim 23, wherein, The requirement to obtain the model of the terminal device includes at least one of the following: Receive the model requirements sent by the terminal device; Alternatively, the model requirements can be determined based on the task division results of the terminal device.

26. The method of claim 25, wherein, The task partitioning results were obtained through at least one of the following: The tasks of the terminal device are divided to obtain the task division results; Alternatively, it may receive the task allocation result sent by the terminal device.

27. A task processing method, wherein, It is applied to a first device, which is located in a second node, and the second node is the node that the terminal device accessed before switching to the first node; The method includes: The system receives a measurement report and / or a first handover request from the terminal device. The measurement report is used to determine the first time when the terminal device switches access to the first network device and / or the first node. The first handover request is used to request a change in the processing path of the subtask of the terminal device. Based on the measurement report and / or the first switching request, switch the processing path of the subtask of the terminal device.

28. The method according to claim 27, wherein, The measurement report carries at least one of the following information: the current position, speed, direction of movement of the terminal device, the identifier of the currently executing subtask, and the execution time of the next subtask.

29. The method according to claim 27, wherein, The first handover request carries at least one of the following: The switching time of the terminal device is determined based on the first time the terminal device switches to the first network device and / or the execution time of the subtask; The device information of the terminal device; The identification information of the first network device; Alternatively, the identification information of the PDU session to be switched.

30. The method according to any one of claims 27-29, wherein, Also includes: A first handover confirmation is sent to the first network device, the first handover confirmation being used to indicate the processing path of the subtask of the terminal device being successfully switched.

31. A task processing method, wherein, Applied to a first node or a second node, the method includes: Obtain a model for processing subtasks on the terminal device; The model is sent to the terminal device through a first network device and / or a second network device; wherein the first network device is the network device that the terminal device switches to, and the second network device is the network device that the terminal device was connected to before switching to the first network device.

32. The method according to claim 31, wherein, The model for obtaining the sub-tasks for processing the terminal device includes at least one of the following: Based on the model requirements of the terminal device, obtain the model corresponding to the model requirements; Alternatively, based on the task partitioning result of the terminal device, obtain the model corresponding to the task partitioning result; The model requirements include at least one of the following: the required model type, application scenario, task requirements, model operating environment, and model input data dimensions.

33. The method according to claim 32, wherein, The model requirements were obtained through at least one of the following methods: Receive the model requirements sent by the first network device; Receive the model requirements sent by the second network device; Alternatively, the model requirements can be determined based on the task division results of the terminal device.

34. A terminal device, wherein, include: Memory, used to store computer programs; A transceiver is used to send and receive data under the control of a processor. Processor, configured to read the computer program in the memory and perform the following operations: Obtain the measurement report from the terminal device; The measurement report is sent to determine the first time when the terminal device switches access to the first network device and / or the first node; the first time is used to indicate the processing path of the subtask of switching the terminal device.

35. A network device, wherein, The network device is a first network device, which includes: Memory, used to store computer programs; A transceiver is used to send and receive data under the control of a processor. Processor, configured to read the computer program in the memory and perform the following operations: Obtain a measurement report from the terminal device, the measurement report being used to determine the first time when the terminal device switches access to the first network device and / or the first node; Based on the measurement report, a first switching request is sent to a first device, which is located in a second node. The second node is the node that the terminal accessed before switching to the first node. The first switching request is used to request a change in the processing path of the terminal device's subtasks.

36. A network device, wherein, The network device is a second network device, which includes: Memory, used to store computer programs; A transceiver is used to send and receive data under the control of a processor. Processor, configured to read the computer program in the memory and perform the following operations: Obtain measurement reports from terminal devices; The measurement report is sent to a first device and / or a first network device, the first device being located in a second node, the second node being the node the terminal accessed before switching to the first node; the measurement report is used to determine the first time the terminal device switched to the first network device and / or the first node; the first time is used to indicate the processing path of the subtask of switching the terminal device.

37. A communication device, wherein, The communication device is a first device, located in a second node, which is the node the terminal device accessed before switching to the first node; the communication device includes: Memory, used to store computer programs; A transceiver is used to send and receive data under the control of a processor. Processor, configured to read the computer program in the memory and perform the following operations: The system receives a measurement report and / or a first handover request from the terminal device. The measurement report is used to determine the first time when the terminal device switches access to the first network device and / or the first node. The first handover request is used to request a change in the processing path of the subtask of the terminal device. Based on the measurement report and / or the first switching request, switch the processing path of the subtask of the terminal device.

38. A communication device, characterized in that, The communication device is a first node or a second node, and the communication device includes: Memory, used to store computer programs; A transceiver is used to send and receive data under the control of a processor. Processor, configured to read the computer program in the memory and perform the following operations: Obtain a model for processing subtasks on the terminal device; The model is sent to the terminal device through a first network device and / or a second network device; wherein the first network device is the network device that the terminal device switches to, and the second network device is the network device that the terminal device was connected to before switching to the first network device.

39. A non-transitory readable storage medium, wherein, The non-transiently readable storage medium stores a computer program that causes a processor to perform the method of any one of claims 1-7, or the method of any one of claims 8-18, or the method of any one of claims 19-26, or the method of any one of claims 27-30, or the method of any one of claims 31-33.

Images