WO2022206411A1 - 一种小区切换方法及装置 - Google Patents

一种小区切换方法及装置 Download PDF

Info

Publication number
WO2022206411A1
WO2022206411A1 PCT/CN2022/081498 CN2022081498W WO2022206411A1 WO 2022206411 A1 WO2022206411 A1 WO 2022206411A1 CN 2022081498 W CN2022081498 W CN 2022081498W WO 2022206411 A1 WO2022206411 A1 WO 2022206411A1
Authority
WO
WIPO (PCT)
Prior art keywords
information
cell
terminal device
target cell
base station
Prior art date
Application number
PCT/CN2022/081498
Other languages
English (en)
French (fr)
Inventor
耿婷婷
曾宇
曾清海
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to EP22778594.6A priority Critical patent/EP4287705A4/en
Publication of WO2022206411A1 publication Critical patent/WO2022206411A1/zh
Priority to US18/461,492 priority patent/US20230422124A1/en

Links

Images

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W36/00—Hand-off or reselection arrangements
    • H04W36/0005—Control or signalling for completing the hand-off
    • H04W36/0083—Determination of parameters used for hand-off, e.g. generation or modification of neighbour cell lists
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W36/00—Hand-off or reselection arrangements
    • H04W36/0005—Control or signalling for completing the hand-off
    • H04W36/0055—Transmission or use of information for re-establishing the radio link
    • H04W36/0064—Transmission or use of information for re-establishing the radio link of control information between different access points
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W36/00—Hand-off or reselection arrangements
    • H04W36/0005—Control or signalling for completing the hand-off
    • H04W36/0055—Transmission or use of information for re-establishing the radio link
    • H04W36/0072—Transmission or use of information for re-establishing the radio link of resource information of target access point
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W36/00—Hand-off or reselection arrangements
    • H04W36/08—Reselecting an access point
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04W—WIRELESS COMMUNICATION NETWORKS
    • H04W36/00—Hand-off or reselection arrangements
    • H04W36/24—Reselection being triggered by specific parameters
    • H04W36/249—Reselection being triggered by specific parameters according to timing information

Definitions

  • the embodiments of the present application relate to the field of communication technologies, and in particular, to a cell handover method and device.
  • terminal equipment can perform cell handover. For example, if the signal quality of the current serving cell of the terminal device is poor, but the signal quality of the neighboring cell is better, the terminal device can switch to the neighboring cell.
  • Cell handover may refer to a terminal device completing the migration of a wireless link connection from a source cell to a target cell under the control of a network device, and is a basic technical means to ensure seamless mobile communication services. How to improve the efficiency of cell handover is a problem worth studying.
  • the embodiments of the present application provide a cell handover method and device, which can improve the efficiency of cell handover to a certain extent by predicting an AI target cell in an artificial intelligence (AI) manner and interacting with a target base station corresponding to the AI target cell in advance.
  • AI artificial intelligence
  • a cell handover method is provided, and the execution body of the method may be a first network device, a component (processor, chip, circuit or others) configured in the first network device, or software module, etc., including: determining an AI target cell, the AI target cell is a predicted serving cell that the terminal device can switch to; outputting a first request message, the first request message is used to request the AI target cell corresponding to the cell.
  • the second network device allocates resources corresponding to the AI target cell to the terminal device, and the first request message is used to indicate at least one of the following: identification information of the AI target cell, and the handover type is AI handover , activation time information, failure time information, or the prediction accuracy of the AI target cell, the activation time information is used to indicate the earliest time for the terminal device to switch to the AI target cell, and the failure time information is used for Indicate the latest time for the terminal device to switch to the AI target cell.
  • the source base station Before determining the serving cell that the UE can switch to, the source base station predicts the serving cell that the UE can switch to based on the AI method, which is called the AI target cell.
  • the source base station sends a first request message to the base station corresponding to the AI target cell in advance to determine whether the base station corresponding to the AI target cell agrees to the request of the source base station. If the base station corresponding to the AI target cell does not agree with the request of the source base station, the source base station will no longer configure the cell to the UE and perform handover.
  • the source base station can perform handover preparation in advance and with the predicted AI target cell, thereby avoiding additional handover delay to a certain extent.
  • the AI target cell is predicted according to an AI method, including: the AI target cell is predicted according to at least one of the following pieces of information, where the at least one piece of information includes: measurement information, load information of the serving cell, load information of adjacent cells, trajectory information of the terminal device, geographic coordinate information of the terminal device, movement direction of the terminal device, or movement speed of the terminal device .
  • the method further includes: acquiring a first response message of the second network device, where the first response message responds to the first request message, and the first response message includes the second network device Indication information of the number of cells in which the terminal device is allowed to perform AI handover.
  • the first response message may include information indicating whether the second network device agrees to the request of the first network device. For example, if the first response message indicates ACK, it means that the second network device agrees to the request of the first network device, and if the indication is NACK, it means that the second network device does not agree to the request of the first network device. Further, if the above-mentioned first response message indicates ACK, the above-mentioned second network equipment may further include indication information of cell data that allows the terminal equipment to perform AI handover, and the like. The method can further align the understanding of the first network device and the second network device, reducing the probability of communication errors.
  • the method further includes: acquiring AI information of the second network device, where the AI information is used to indicate at least one of the following: indication information that the second network device supports or does not support AI handover, the Indication information of the AI handover type supported by the second network device, or cell information that the second network device allows to perform AI handover.
  • the method further includes: transferring the user plane data of the terminal device to the second network device; outputting a first state forwarding message, where the first state forwarding message is used to instruct the first network device to send the The number of the first downlink service data unit SDU in the user plane data transferred by the second network device, and/or the number of SDUs that can be discarded in the transferred user plane data.
  • the first network device can transfer user plane data to the second network device in advance, reducing the interruption time caused by handover.
  • the method further includes: determining to switch the terminal device to a first cell in the AI target cells; outputting a first configuration message, where the first configuration message is used to indicate to the terminal device the first cell Configuration information of a cell.
  • the method further includes: determining to switch the terminal device to a second cell, the AI target cell does not include the second cell; outputting a second configuration message, where the second configuration message is used to send the The terminal device indicates the configuration information of the second cell and the configuration information of the AI target cell.
  • the method further includes: outputting third configuration information, where the third configuration information is used to indicate the configuration information of the AI target cell and the handover trigger configuration information to the terminal device, and the handover trigger configuration information is used for to indicate to the terminal equipment a trigger condition for handover to the AI target cell.
  • the method further includes: determining to update the configuration information of the AI target cell, and/or updating the handover trigger configuration information;
  • Fourth configuration information is output, where the fourth configuration information is used to indicate the updated configuration information of the AI target cell and/or the updated handover trigger configuration information to the terminal device.
  • the configuration information of the AI target cell is used to indicate at least one of the following: identification information, random access information, activation time information, or outage time information of the AI target cell, the random access The information is used to instruct the terminal device to switch to the random access resource of the AI target cell, the activation time information indicates the earliest time when the terminal device switches to the AI target cell, and the outage time information indicates the The latest time for the terminal device to switch to the AI target cell.
  • a cell handover method is provided.
  • the execution body of the method may be a second network device, may also be a component configured in the second network device, or may be a software module, etc., including: acquiring the first network device
  • the first request message is used to request the second network device corresponding to the artificial intelligence AI target cell to allocate resources corresponding to the AI target cell to the terminal device; wherein, the first request message is used to indicate At least one of the following: identification information of the AI target cell, the type of the handover is AI handover, activation time information, outage time information, or prediction accuracy of the AI target cell, the activation time information is used to indicate The earliest time for the terminal device to switch to the AI target cell, and the outage time information is used to indicate the latest time for the terminal device to switch to the AI target cell.
  • the AI-based mobility mechanism predicts and infers a reasonable handover cell in advance, improves the success rate of handover preparation, and improves its robustness; in addition, the introduction of AI target cell Time information can occupy the resources of the AI target base station as little as possible and improve resource utilization.
  • the AI target cell is predicted according to at least one of the following pieces of information, where the at least one piece of information includes: first measurement information of the terminal device, load information of the serving cell, Load information, trajectory information of the terminal device, geographic coordinate information of the terminal device, movement direction of the terminal device, or movement speed of the terminal device.
  • the method further includes: outputting a first response message, where the first response message is in response to the first request message, and the first response message includes that the second network device allows the terminal device to perform Indication information of the number of cells for AI handover.
  • it further includes: outputting an AI message, where the AI information is used to indicate at least one of the following: indication information that the second network device supports or does not support AI handover, AI that the second network device supports The indication information of the handover type, or the number of cells allowed by the second network device to perform AI handover.
  • the method further includes: acquiring user plane data of the terminal device transferred by the first network device; acquiring a first state forwarding message of the first network device, where the first state forwarding message is used for Indicates the number of the first downlink service data unit SDU in the user plane data transferred from the first network device to the second network device, and/or the number of SDUs that can be discarded in the transferred user plane data.
  • a cell handover method is provided.
  • the execution body of the method may be a terminal device, may also be configured as a component in the terminal device, or may be a software module, etc., including: acquiring a second configuration of the first network device information, the second configuration information is used to indicate the configuration information of the second cell and the configuration information of the artificial intelligence AI target cell to the terminal device; according to the configuration information of the second cell, the handover to the second cell is performed.
  • the method further includes: when the connection between the terminal device and the second cell fails, determining the first target cell.
  • the method further includes: when the first target cell is a cell in the AI target cell, executing a handover procedure to the first target cell; or, when the first target cell is not a cell in the AI target cell, perform a reestablishment procedure to the first target cell.
  • the handover process is much simpler than the reestablishment process, the signaling interaction is much simpler. Therefore, during the connection failure between the UE and the second cell, if the first target cell selected by the UE is in the predicted AI target cell When a cell is located, the UE can directly initiate a handover process to the first target cell to quickly restore the connection, shorten the interruption delay of data transmission, and reduce signaling overhead.
  • the method further includes: performing a reestablishment process to the first target cell.
  • a cell handover method is provided.
  • the execution body of the method may be a first network device, a component configured in the first network device, or a software module, etc., including: outputting fifth configuration information , the fifth configuration information is used to indicate the trigger condition for the terminal device to report the first feedback information; obtain the first feedback information of the terminal device; determine the update result of the artificial intelligence AI target cell, the update result of the AI target cell It is determined according to the first feedback information, and the update result of the AI target cell is a serving cell to which the updated terminal device can be handed over.
  • the feedback results of the terminal equipment are introduced, and the inference results of the AI target cell are updated, which can ensure the accuracy of the AI inference results.
  • the fifth configuration information is used to indicate at least one of the following: information and quality threshold information of at least one cell, reference location information and first distance threshold information, trajectory change trigger information or time reporting indication information,
  • the time reporting indication information includes indication information that the terminal device carries or does not carry time information in the first feedback information, where the time information is the time when the terminal device satisfies the fifth configuration information, or The time when the terminal device reports the first feedback information.
  • the first feedback information is used to indicate the identification information of the cell that satisfies the fifth configuration information, And/or, the quality information of the cell that satisfies the fifth configuration information, or the first feedback information is used to indicate the identification information of the cell that does not meet the fifth configuration information, and/or, does not meet the the quality information of the cell of the fifth configuration information; or,
  • the first feedback information is used to indicate the latest location information of the terminal device.
  • a cell handover method is provided.
  • the execution body of the method may be a terminal device, a component configured in the terminal device, or a software module, etc., including: acquiring a fifth configuration of the first network device information, the fifth configuration information is used to indicate a trigger condition for the terminal device to report the first feedback information; output the first feedback information, the first feedback information is output when the trigger condition of the fifth configuration information is satisfied,
  • the first feedback information is used to update the artificial intelligence AI target cell, and the update result of the AI target cell is a serving cell that the updated terminal device can switch to.
  • the terminal device can report feedback information to the first network device, and the first network device can update the result of the AI target cell according to the feedback from the terminal device, which can ensure the accuracy and validity of the AI inference result .
  • the fifth configuration information is used to indicate at least one of the following: information and quality threshold information of at least one cell, reference location information and first distance threshold information, trajectory change trigger information or time reporting indication information,
  • the time reporting indication information includes indication information that the terminal device carries or does not carry time information in the first feedback information, where the time information is the time when the terminal device satisfies the fifth configuration information, or The time when the terminal device reports the first feedback information.
  • the first feedback information is used to indicate the identification information of the cell that satisfies the fifth configuration information, And/or, the quality information of the cell that satisfies the fifth configuration information, or the first feedback information is used to indicate the identification information of the cell that does not meet the fifth configuration information, and/or, does not meet the the quality information of the cell of the fifth configuration information; or,
  • the first feedback information is used to indicate the latest location information of the terminal device.
  • a sixth aspect provides an apparatus, the beneficial effects of which can be found in the description of the first aspect, and the apparatus may be a first network device, or a device configured in the first network device, or a device that can be matched with the first network device.
  • the apparatus includes a one-to-one unit for performing the methods/operations/steps/actions described in the first aspect.
  • the unit may be a hardware circuit, software, or a hardware circuit combined with software.
  • the apparatus may include a processing unit and a communication unit, and the processing unit and the communication unit may perform the corresponding functions in any one of the above design examples of the first aspect, specifically: the processing unit is configured to determine the AI target cell, where The AI target cell is a serving cell that is predicted according to the AI method and can be switched to by the terminal device; the communication unit is configured to output a first request message, and the first request message is used to request the second network corresponding to the AI target cell
  • the device allocates resources corresponding to the AI target cell to the terminal device, and the first request message is used to indicate at least one of the following: identification information of the AI target cell, the handover type is AI handover, activation time information, outage time information, or the prediction accuracy of the AI target cell, the activation time information is used to indicate the earliest time for the terminal device to switch to the AI target cell, and the outage time information is used to indicate the The latest time for the terminal device to switch to the AI target cell.
  • the processing unit and the communication unit may perform the corresponding functions in
  • an apparatus includes a memory for implementing the method described in the first aspect.
  • the apparatus may also include a memory for storing instructions and/or data.
  • the memory is coupled to the processor, and when the processor executes the program instructions stored in the memory, the method described in the first aspect can be implemented.
  • the apparatus may also include a communication interface for the apparatus to communicate with other devices.
  • the communication interface may be a transceiver, a circuit, a bus, a module, a pin or other type of communication interface, and the other device may be a second network device or a terminal device or the like.
  • the device includes:
  • the processor is configured to determine an AI target cell, where the AI target cell is a serving cell predicted according to the AI method and to which the terminal device can be handed over.
  • a communication interface used to output a first request message, where the first request message is used to request the second network device corresponding to the AI target cell to allocate resources corresponding to the AI target cell to the terminal device, the first request message
  • the request message is used to indicate at least one of the following: the identification information of the AI target cell, the type of the handover is AI handover, activation time information, outage time information, or the prediction accuracy of the AI target cell, the activation time
  • the time information is used to indicate the earliest time for the terminal device to switch to the AI target cell
  • the outage time information is used to indicate the latest time for the terminal device to switch to the AI target cell.
  • an apparatus is provided, the beneficial effects of which can be found in the description of the second aspect.
  • the apparatus may be a second network device, or a device configured in the second network device, or a device that can be matched with the second network device.
  • the apparatus includes a one-to-one unit for performing the method/operation/step/action described in the second aspect, and the unit may be a hardware circuit, software, or a hardware circuit combined with software implementation.
  • the apparatus may include a processing unit and a communication unit, and the processing unit and the communication unit may perform corresponding functions in any one of the design examples of the second aspect, specifically: a communication unit, configured to obtain the information of the first network device.
  • a first request message is used to request the second network device corresponding to the artificial intelligence AI target cell to allocate resources corresponding to the AI target cell to the terminal device; wherein, the first request message is used to indicate the following: At least one item: the identification information of the AI target cell, the type of the handover is AI handover, the activation time information, the failure time information, or the prediction accuracy of the AI target cell, and the activation time information is used to indicate the the earliest time at which the terminal device switches to the AI target cell, and the outage time information is used to indicate the latest time at which the terminal device switches to the AI target cell.
  • the processing unit is configured to process the first request message. For the specific execution process of the above processing unit and the communication unit, reference may be made to the second aspect, and details are not repeated here.
  • an apparatus includes a memory for implementing the method described in the second aspect.
  • the apparatus may also include a memory for storing instructions and/or data.
  • the memory is coupled to the processor, and when the processor executes the program instructions stored in the memory, the method described in the second aspect above can be implemented.
  • the apparatus may also include a communication interface for the apparatus to communicate with other devices.
  • the communication interface may be a transceiver, a circuit, a bus, a module, a pin or other type of communication interface, and the other device may be a first network device or a terminal device, or the like.
  • the device includes:
  • a communication interface used to obtain a first request message of the first network device, where the first request message is used to request the second network device corresponding to the artificial intelligence AI target cell to allocate resources corresponding to the AI target cell to the terminal device; wherein , the first request message is used to indicate at least one of the following: the identification information of the AI target cell, the type of the handover is AI handover, the activation time information, the failure time information, or the prediction accuracy of the AI target cell
  • the activation time information is used to indicate the earliest time for the terminal device to switch to the AI target cell
  • the outage time information is used to indicate the latest time for the terminal device to switch to the AI target cell.
  • the processor is configured to process the first request message.
  • an apparatus is provided, and the beneficial effects can be found in the description of the third aspect.
  • the apparatus may be a terminal device, or a device configured in the terminal device, or a device that can be matched with the terminal device.
  • the apparatus includes a one-to-one unit for performing the method/operation/step/action described in the third aspect, and the unit may be a hardware circuit, software, or a hardware circuit combined with software.
  • the apparatus may include a processing unit and a communication unit, and the processing unit and the communication unit may perform the corresponding functions in any one of the above design examples of the third aspect, specifically: a communication unit, configured to obtain the information of the first network device.
  • the processing unit is configured to, according to the configuration information of the second cell, execute to handover of the second cell.
  • an apparatus includes a memory for implementing the method described in the third aspect.
  • the apparatus may also include a memory for storing instructions and/or data.
  • the memory is coupled to the processor, and when the processor executes the program instructions stored in the memory, the method described in the third aspect can be implemented.
  • the apparatus may also include a communication interface for the apparatus to communicate with other devices.
  • the communication interface may be a transceiver, circuit, bus, module, pin or other type of communication interface, and the other device may be a first network device or a second network device, and so on.
  • the device includes:
  • a communication interface for acquiring second configuration information of the first network device, where the second configuration information is used to indicate the configuration information of the second cell and the configuration information of the artificial intelligence AI target cell to the terminal device;
  • a processor configured to perform handover to the second cell according to the configuration information of the second cell.
  • a twelfth aspect provides an apparatus, the beneficial effects of which can be found in the description of the fourth aspect, and the apparatus may be a first network device, or a device configured in the first network device, or a device that can be matched with the first network device. device.
  • the device includes a one-to-one unit for performing the method/operation/step/action described in the fourth aspect, and the unit may be a hardware circuit, software, or a hardware circuit combined with software.
  • the apparatus may include a processing unit and a communication unit, and the processing unit and the communication unit may perform corresponding functions in any one of the design examples of the fourth aspect, specifically: the communication unit, configured to output the fifth configuration information, The fifth configuration information is used to indicate a trigger condition for the terminal equipment to report the first feedback information; the communication unit is further used to obtain the first feedback information of the terminal equipment; the processing unit is used to determine the update of the artificial intelligence AI target cell As a result, the update result of the AI target cell is determined according to the first feedback information, and the update result of the AI target cell is a serving cell to which the updated terminal device can be handed over.
  • the fourth aspect which will not be repeated here.
  • an apparatus includes a memory for implementing the method described in the fourth aspect.
  • the apparatus may also include a memory for storing instructions and/or data.
  • the memory is coupled to the processor, and when the processor executes the program instructions stored in the memory, the method described in the fourth aspect can be implemented.
  • the apparatus may also include a communication interface for the apparatus to communicate with other devices.
  • the communication interface may be a transceiver, a circuit, a bus, a module, a pin or other type of communication interface, and the other device may be a second network device or a terminal device or the like.
  • the device includes:
  • a communication interface configured to output fifth configuration information, where the fifth configuration information is used to indicate a trigger condition for the terminal device to report the first feedback information, and obtain the first feedback information of the terminal device;
  • the processor is configured to determine the update result of the artificial intelligence AI target cell, the update result of the AI target cell is determined according to the first feedback information, and the terminal device whose update result of the AI target cell is updated may be The serving cell to switch to.
  • a fourteenth aspect provides an apparatus, the beneficial effects of which can be found in the description of the fifth aspect.
  • the apparatus may be a terminal device, or a device configured in the terminal device, or a device that can be matched with the terminal device.
  • the apparatus includes a one-to-one unit for performing the method/operation/step/action described in the fifth aspect, and the unit may be a hardware circuit, software, or a hardware circuit combined with software.
  • the apparatus may include a processing unit and a communication unit, and the processing unit and the communication unit may perform the corresponding functions in any one of the design examples of the fifth aspect, specifically:
  • a communication unit configured to acquire fifth configuration information of the first network device, where the fifth configuration information is used to indicate a trigger condition for the terminal device to report the first feedback information; a processing unit, configured to determine the first feedback information according to the fifth configuration information feedback information; the communication unit is further configured to output first feedback information, the first feedback information is output when the trigger condition of the fifth configuration information is satisfied, and the first feedback information is used to update the artificial intelligence AI target cell, the update result of the AI target cell is the updated serving cell to which the terminal device can be handed over.
  • the apparatus includes a memory for implementing the method described in the fifth aspect.
  • the apparatus may also include a memory for storing instructions and/or data.
  • the memory is coupled to the processor, and when the processor executes the program instructions stored in the memory, the method described in the fifth aspect can be implemented.
  • the apparatus may also include a communication interface for the apparatus to communicate with other devices.
  • the communication interface may be a transceiver, circuit, bus, module, pin or other type of communication interface
  • the other device may be a first network device or a second network device, and so on.
  • the device includes:
  • a communication interface configured to acquire fifth configuration information of the first network device, where the fifth configuration information is used to indicate a trigger condition for the terminal device to report the first feedback information;
  • a processor configured to determine the first feedback information according to the fifth configuration information
  • the communication interface is further configured to output first feedback information, the first feedback information is output when the trigger condition of the fifth configuration information is satisfied, and the first feedback information is used to update the artificial intelligence AI target cell, so The update result of the AI target cell is the updated serving cell that the terminal device can switch to.
  • embodiments of the present application further provide a computer-readable storage medium, including instructions, which, when executed on a computer, cause the computer to execute the method of any one of the first to fifth aspects.
  • an embodiment of the present application further provides a chip system, where the chip system includes a processor, and may further include a memory, for implementing the method of any one of the first to fifth aspects.
  • the chip system can be composed of chips, and can also include chips and other discrete devices.
  • the embodiments of the present application further provide a computer program product, including instructions, which, when executed on a computer, cause the computer to execute the method of any one of the first to fifth aspects.
  • an embodiment of the present application further provides a system, where the system includes the apparatus of the sixth aspect or the seventh aspect, and the apparatus of the eighth aspect or the ninth aspect.
  • the system may further include the device of the tenth aspect or the eleventh aspect; or, the system includes the device of the twelfth aspect or the thirteenth aspect, and the device of the fourteenth aspect or the fifteenth aspect .
  • FIG. 1 is a schematic diagram of a network architecture provided by an embodiment of the present application.
  • Fig. 2a, Fig. 2b, Fig. 2c and Fig. 2d are schematic diagrams of a protocol stack provided by an embodiment of the present application;
  • Fig. 3a, Fig. 3b, Fig. 3c and Fig. 3d are schematic diagrams of AI models provided by the embodiments of the present application;
  • FIG. 4 is a flowchart of cell handover provided by Embodiment 1 of the present application.
  • FIG. 5 is another flowchart of cell handover provided by Embodiment 1 of the present application.
  • FIG. 6 is a flowchart of cell handover provided by Embodiment 2 of the present application.
  • FIG. 7 is another flowchart of cell handover provided by Embodiment 2 of the present application.
  • FIG. 8 is a flowchart of cell handover provided by Embodiment 3 of the present application.
  • FIG. 9 is a schematic structural diagram of a device provided by an embodiment of the present application.
  • FIG. 10 is a schematic structural diagram of a terminal device provided by an embodiment of the present application.
  • FIG. 11 is a schematic structural diagram of a network device provided by an embodiment of the present application.
  • FIG. 1 is a schematic diagram of a network architecture to which an embodiment of the present application is applied.
  • a terminal device such as terminal device 1301 or terminal device 1302
  • the wireless network includes a radio access network (RAN) and a core network (CN), where the RAN is used to access the terminal equipment to the wireless network, and the CN is used to manage the terminal equipment and provide The gateway for external network communication.
  • RAN radio access network
  • CN core network
  • the terminal equipment, RAN and CN involved in FIG. 1 will be described in detail below.
  • a terminal device which may be referred to as a terminal for short, is a device with a wireless transceiver function.
  • Terminal equipment can be mobile or fixed.
  • Terminal equipment can be deployed on land, including indoor or outdoor, handheld or vehicle; can also be deployed on water (such as ships, etc.); can also be deployed in the air (such as aircraft, balloons and satellites, etc.).
  • the terminal device can be a mobile phone (mobile phone), a tablet computer (pad), a computer with wireless transceiver function, a virtual reality (virtual reality, VR) terminal device, an augmented reality (augmented reality, AR) terminal device, industrial control ( Wireless terminal equipment in industrial control, wireless terminal equipment in self driving, wireless terminal equipment in remote medical, wireless terminal equipment in smart grid, transportation security (transportation) wireless terminal equipment in safety), wireless terminal equipment in a smart city, and/or wireless terminal equipment in a smart home.
  • a virtual reality (virtual reality, VR) terminal device an augmented reality (augmented reality, AR) terminal device
  • industrial control Wireless terminal equipment in industrial control, wireless terminal equipment in self driving, wireless terminal equipment in remote medical, wireless terminal equipment in smart grid, transportation security (transportation) wireless terminal equipment in safety
  • wireless terminal equipment in a smart city and/or wireless terminal equipment in a smart home.
  • the terminal device may also be a cellular phone, a cordless phone, a session initiation protocol (SIP) phone, a wireless local loop (WLL) station, a personal digital assistant (PDA), a wireless communication Functional handheld devices or computing devices, in-vehicle devices, wearable devices, terminal devices in the future fifth generation (the 5th generation, 5G) network or future evolution of the public land mobile network (PLMN) in the terminal equipment terminal equipment, etc.
  • Terminal equipment may also sometimes be referred to as user equipment (user equipment, UE).
  • the terminal device can communicate with multiple access network devices of different technologies.
  • the terminal device can communicate with an access network device supporting long term evolution (LTE), or it can communicate with an access network device supporting 5G.
  • the network access device can communicate with the access network device supporting LTE and dual connection with the access network device supporting 5G.
  • the device for realizing the function of the terminal device may be a terminal device; it may also be a device capable of supporting the terminal device to realize the function, such as a chip system, a hardware circuit, a software module, or a hardware circuit plus a software module,
  • the apparatus can be installed in the terminal device or can be used in combination with the terminal device.
  • the technical solutions provided by the embodiments of the present application are described by taking the device for realizing the functions of the terminal device as the terminal device and the terminal device as the UE as an example.
  • the RAN may include one or more RAN devices, such as RAN device 1001 , RAN device 1002 .
  • the interface between the RAN device and the terminal device may be a Uu interface (or called an air interface).
  • Uu interface or called an air interface.
  • the names of these interfaces may remain unchanged, or may be replaced by other names, which are not limited in this application.
  • a RAN device is a node or device that accesses a terminal device to a wireless network, and the RAN device may also be referred to as a network device or a base station.
  • RAN devices include, but are not limited to: base stations, generation node B (gNB) in 5G, evolved node B (evolved node B, eNB), radio network controller (radio network controller, RNC), node B (node B, NB), base station controller (BSC), base transceiver station (base transceiver station, BTS), home base station (for example, home evolved nodeB, or home node B, HNB), baseband unit (base band unit, BBU), transmitting and receiving point (transmitting and receiving point, TRP), transmitting point (transmitting point, TP), and/or mobile switching center, etc.
  • gNB generation node B
  • eNB evolved node B
  • RNC radio network controller
  • node B node B
  • BSC base station controller
  • BTS
  • the access network device may also be a wireless controller, a centralized unit (CU), a distributed unit (DU), and a centralized unit control in a cloud radio access network (CRAN) scenario.
  • CU CU control plane
  • CU-UP centralized unit user plane
  • IAB integrated access and backhaul
  • the access network device may be a relay station, an access point, a vehicle-mounted device, a terminal device, a wearable device, an access network device in a future 5G network, or a future evolved public land mobile network (PLMN). access network equipment, etc.
  • PLMN public land mobile network
  • the device for implementing the function of the access network device may be the access network device; it may also be a device capable of supporting the access network device to realize the function, such as a chip system, a hardware circuit, a software module, or A hardware circuit plus a software module, the apparatus can be installed in the access network equipment or can be used in matching with the access network equipment.
  • the chip system may be composed of chips, or may include chips and other discrete devices.
  • the protocol layer structure may include a control plane protocol layer structure and a user plane protocol layer structure.
  • the control plane protocol layer structure may include a radio resource control (radio resource control, RRC) layer, a packet data convergence protocol (packet data convergence protocol, PDCP) layer, a radio link control (radio link control, RLC) layer, media Functions of protocol layers such as access control (media access control, MAC) layer and physical layer.
  • RRC radio resource control
  • PDCP packet data convergence protocol
  • RLC radio link control
  • media Functions of protocol layers such as access control (media access control, MAC) layer and physical layer.
  • the user plane protocol layer structure may include the functions of protocol layers such as the PDCP layer, the RLC layer, the MAC layer, and the physical layer.
  • the PDCP layer may also include a service data adaptation protocol (service data adaptation protocol). protocol, SDAP) layer.
  • service data adaptation protocol service data adaptation protocol
  • SDAP service data adaptation protocol
  • the data transmission needs to go through the user plane protocol layer, such as the SDAP layer, the PDCP layer, the RLC layer, the MAC layer, and the physical layer.
  • the SDAP layer, the PDCP layer, the RLC layer, the MAC layer and the physical layer may also be collectively referred to as the access layer.
  • the transmission direction of data it is divided into sending or receiving, and each layer is divided into sending part and receiving part.
  • FIG. 2a a schematic diagram of downlink data transmission between layers is shown.
  • the downward arrow in FIG. 2a indicates data transmission, and the upward arrow indicates data reception.
  • the PDCP layer After the PDCP layer obtains the data from the upper layer, it transmits the data to the RLC layer and the MAC layer, and then the MAC layer generates a transport block, and then transmits it wirelessly through the physical layer.
  • Data is encapsulated correspondingly in each layer.
  • the data received by a certain layer from the upper layer of this layer is regarded as the service data unit (SDU) of this layer, and after being encapsulated by this layer, it becomes a protocol data unit (PDU), and then passed to the next layer.
  • SDU service data unit
  • PDU protocol data unit
  • the terminal device also has an application layer and a non-access layer.
  • the application layer can be used to provide services to applications installed in the terminal device.
  • the downlink data received by the terminal device can be sequentially transmitted from the physical layer to the application layer, and then provided to the application by the application layer; for example, The application layer can acquire the data generated by the application program, and transmit the data to the physical layer in turn, and send it to other communication devices.
  • the non-access layer can be used for forwarding user data, for example, forwarding the uplink data received from the application layer to the SDAP layer or forwarding the downlink data received from the SDAP layer to the application layer.
  • a RAN device may include a CU and a DU, and multiple DUs may be centrally controlled by one CU.
  • the interface between the CU and the DU may be referred to as the F1 interface.
  • the control plane (control panel, CP) interface may be F1-C
  • the user plane (user panel, UP) interface may be F1-U.
  • the CU and DU can be divided according to the protocol layer of the wireless network: for example, as shown in Figure 2b, the functions of the PDCP layer and above are set in the CU, and the functions of the protocol layers below the PDCP layer (for example, the RLC layer and the MAC layer, etc.) are set in the DU; For another example, as shown in FIG. 2c, the functions of the protocol layers above the PDCP layer are set in the CU, and the functions of the PDCP layer and the following protocol layers are set in the DU.
  • the above division of the processing functions of the CU and DU according to the protocol layer is only an example, and it can also be divided in other ways.
  • the CU or DU can be divided into functions with more protocol layers, and
  • the CU or DU may also be divided into partial processing functions having the protocol layer.
  • some functions of the RLC layer and functions of the protocol layers above the RLC layer are placed in the CU, and the remaining functions of the RLC layer and the functions of the protocol layers below the RLC layer are placed in the DU.
  • the functions of the CU or DU can also be divided according to the service type or other system requirements, for example, by the delay, the functions whose processing time needs to meet the delay requirements are set in the DU, and do not need to meet the delay.
  • the required functionality is set in the CU.
  • the CU may also have one or more functions of the core network.
  • the CU can be set on the network side to facilitate centralized management; the DU has multiple radio functions, and the radio functions can also be set remotely. This embodiment of the present application does not limit this.
  • the DU and the radio frequency device may be divided at a physical layer (PHY).
  • the DU may implement high-level functions in the PHY layer
  • the radio frequency device may implement low-level functions in the PHY layer.
  • the functions of the PHY layer may include adding a cyclic redundancy check (CRC) code, channel coding, rate matching, scrambling, modulation, layer mapping, precoding, resource mapping, physical antennas Mapping, and/or RF transmit functions.
  • the functions of the PHY layer may include CRC, channel decoding, de-rate matching, descrambling, demodulation, de-layer mapping, channel detection, resource demapping, physical antenna demapping, and/or radio frequency reception functions.
  • the high-level function in the PHY layer may include a part of the function of the PHY layer, for example, this part of the function is closer to the MAC layer, and the lower-layer function in the PHY layer may include another part of the function of the PHY layer, for example, this part of the function is closer to the radio frequency function.
  • higher layer functions in the PHY layer may include adding CRC codes, channel coding, rate matching, scrambling, modulation, and layer mapping
  • lower layer functions in the PHY layer may include precoding, resource mapping, physical antenna mapping, and radio frequency transmission functions
  • higher layer functions in the PHY layer may include adding CRC codes, channel coding, rate matching, scrambling, modulation, layer mapping and precoding
  • lower layer functions in the PHY layer may include resource mapping, physical antenna mapping, and radio frequency send function.
  • the radio frequency device may also be referred to as a wireless device.
  • the functions of the CU may be implemented by one entity, or may also be implemented by different entities.
  • the functions of the CU can be further divided, that is, the control plane and the user plane can be separated and implemented by different entities, namely the control plane CU entity (ie the CU-CP entity) and the user plane CU entity (i.e. CU-UP entity).
  • the CU-CP entity and the CU-UP entity can be coupled with the DU to jointly complete the functions of the RAN device.
  • the signaling generated by the CU may be sent to the terminal device through the DU, or the signaling generated by the terminal device may be sent to the CU through the DU.
  • the DU may not parse the signaling, but directly encapsulate it through the protocol layer and transparently transmit it to the terminal device or CU.
  • the sending or receiving of the signaling by the DU includes this scenario.
  • the signaling of the RRC or PDCP layer is finally processed as the signaling of the physical layer and sent to the terminal device, or is converted from the received signaling of the physical layer.
  • the signaling of the RRC or PDCP layer can be considered to be sent by the DU, or sent by the DU and the radio frequency device.
  • any one of the above-mentioned DU, CU, CU-CP, CU-UP and radio frequency device may be a software module, a hardware structure, or a software module+hardware structure, which is not limited.
  • the existence forms of different entities may be different, which is not limited.
  • DU, CU, CU-CP, and CU-UP are software modules
  • the radio frequency device is a hardware structure.
  • the CN may include an access and mobility management function (AMF) network element and a session management function (SMF) Network element, user plane function (UPF) network element, policy control function (PCF) network element, unified data management (unified data management, UDM) network element, and application function (AF) ) network element, etc.
  • AMF access and mobility management function
  • SMF session management function
  • UPF user plane function
  • PCF policy control function
  • UDM unified data management
  • AF application function
  • the device for implementing the function of the core network device may be the core network device; it may also be a device capable of supporting the core network device to realize the function, such as a chip system, a hardware circuit, a software module, or a hardware circuit Adding software modules, the device can be installed in the core network equipment or can be used in matching with the core network equipment.
  • the technical solutions provided by the embodiments of the present application are described by taking the device for implementing the functions of the core network equipment as the core network equipment as an example.
  • each device in the communication system shown in FIG. 1 is only for illustration, and the embodiments of the present application are not limited to this. In practical applications, the communication system may also include more terminal devices and more RAN devices. Other devices may also be included.
  • the network architecture shown in FIG. 1 above can be applied to communication systems of various radio access technologies (RATs), such as 4G (or LTE) communication systems, or 5G (or 5G (or referred to as LTE) communication systems.
  • RATs radio access technologies
  • the new wireless (new radio, NR) communication system can also be a transition system between the LTE communication system and the 5G communication system.
  • the transition system can also be called a 4.5G communication system, and of course it can also be a future communication system For example, 6G communication system.
  • the network architecture and service scenarios described in the embodiments of the present application are for the purpose of illustrating the technical solutions of the embodiments of the present application more clearly, and do not constitute limitations on the technical solutions provided by the embodiments of the present application.
  • the evolution of the network architecture and the emergence of new service scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.
  • a UE can switch serving cells.
  • the base station to which the current serving cell of the UE belongs may be referred to as the source base station
  • the base station to which the serving cell to which the UE is to be handed over belongs may be referred to as the target base station.
  • the source base station sends a handover command to the UE, and the UE performs handover to the target cell according to the configuration information of the target cell in the handover command.
  • the UE may send a measurement report to the source base station, and the measurement report may include quality information of the serving cell and/or neighboring cells, and the like.
  • the source base station may determine the handover strategy, for example, determine the handover strategy according to information reported by the UE and cell load and other information, and indicate the handover strategy to the UE through a handover command.
  • the other is UE-triggered.
  • the UE selects a target cell from one or more candidate cells and performs handover to the target cell.
  • the source base station configures one or more candidate cells for the UE through a handover command, and the one or more candidate cells are configured with corresponding trigger conditions.
  • the UE may take the candidate cell corresponding to the trigger condition as the target cell, and the UE performs handover to the target cell.
  • the source base station determines the handover strategy or candidate cell in near real time, and the problem of poor accuracy of the determined handover strategy or candidate cell may occur, thereby causing additional handover delay.
  • the source base station determines the target cell for the UE (for example, the target cell with the optimal index or the optimal comprehensive index)
  • the source base station first sends a handover request to the target base station to which the target cell belongs. After the base station agrees, the source base station will configure the target cell to the UE.
  • the target base station may reject the handover request from the source base station due to excessive load or limited capacity of the target cell or management policy.
  • the source base station has to reselect a new target cell for the UE, and initiate a handover request to the target base station to which the new target cell belongs, which brings additional handover delay. Further, the additional handover delay may also cause the UE to fail to connect to the source base station. For example, the UE is in a moving state, and as the connection between the UE and the source base station becomes weaker and weaker, and the UE does not switch to a new serving cell for a long time, the connection between the UE and the source base station may fail.
  • the embodiment of the present application provides a cell handover method, which can solve the above-mentioned problems such as additional handover delay to a certain extent.
  • the method includes: before determining the serving cell that the UE can hand over, the source base station predicts the serving cell that the UE can hand over based on artificial intelligence (AI), which is called the AI target cell.
  • AI artificial intelligence
  • the source base station sends a first request message to the base station corresponding to the AI target cell in advance to determine whether the base station corresponding to the AI target cell agrees to the request of the source base station. If the base station corresponding to the AI target cell does not agree with the request of the source base station, the source base station will no longer configure the cell to the UE and perform handover.
  • the source base station can perform handover preparation in advance and with the predicted AI target cell, thereby avoiding additional handover delay to a certain extent.
  • the embodiments of the present application involve a process of predicting a serving cell to which a UE can be handed over by using an AI technology, for ease of understanding, the AI technology is first introduced. It can be understood that this introduction is not intended to limit the embodiments of the present application.
  • AI is a technology that performs complex calculations by simulating the human brain. With the improvement of data storage and capabilities, AI has been applied more and more.
  • 3rd generation partnership project (3GPP) version 17 (release17, R17) passed the study item (SI) and proposed to apply AI to NR.
  • Figure 3a shows an example of the first application framework of AI in NR:
  • the data source is used to store training data and inference data.
  • the model training node (model training host) obtains the AI model by analyzing or training the training data (training data) provided by the data source, and deploys the AI model in the model inference node (model inference host).
  • the model inference node uses the AI model to perform inference based on the inference data provided by the data source, and obtain the inference result.
  • the inference result is used to give reasonable AI-based predictions for network operation, or to guide the network to make policy configuration or policy adjustment.
  • the relevant policy configuration or policy adjustment is planned by an actor entity in a unified manner, and sent to multiple execution objects (eg, network entities) for execution. At the same time, after applying the relevant policies, the specific performance of the network can be input into the data source again for storage.
  • FIG. 3b An example diagram of the second application framework of AI in NR is shown in Figure 3b, Figure 3c or Figure 3d:
  • Training data is received by the first AI module independent of the base station.
  • the first AI module obtains an AI model by analyzing or training the training data.
  • the first AI module may use the corresponding AI model and inference data to infer to obtain the parameter, as shown in Figure 3b; or the first AI module may send the information of the AI model to the base station located in the base station
  • the second AI module performs inference by using the corresponding AI model and inference data to obtain the parameter, as shown in FIG. 3c.
  • the AI model used by the second AI module for reasoning may also be obtained by the second AI module receiving training data and training the training data, as shown in FIG. 3d .
  • the AI model can be simply referred to as a model, which can be regarded as a mapping from input measurement (measurement information) to output parameters.
  • the input measurement quantity can be one or more measurement quantities
  • the output parameter can be one or more parameters.
  • Training data may include known input measurements, or include known input measurements and corresponding output parameters, for training the AI model.
  • the training data may be data from base stations, CUs, CU-CPs, CU-UPs, DUs, radio modules, UEs and/or other entities, and/or data inferred by AI technology, without limitation.
  • Inference data includes input measurements that are used to infer parameters using the model.
  • Inference data may be data from base stations, CUs, CU-CPs, CU-UPs, DUs, radio modules, UEs, and/or other entities.
  • the inferred parameters can be regarded as policy information and sent to the execution object.
  • the inferred parameters may be sent to the base station, CU, CU-CP, CU-UP, DU, radio frequency module, or UE, etc., for policy configuration or policy adjustment.
  • the AI models used to reason about different parameters can be the same or different, without limitation.
  • the UE and/or the base station may perform some or all of the steps in the embodiments of the present application, these steps or operations are only examples, and the embodiments of the present application may also perform other operations or various operations. deformed.
  • various steps may be performed in different orders presented in the embodiments of the present application, and may not be required to perform all the operations in the embodiments of the present application.
  • Embodiment 1 of the present application provides a cell handover method, including: a source base station determining an AI target cell, where the AI target cell may also be called a first cell, a predicted cell, or a potential cell, which is not limited. Regardless of the name used, the cell determined by the source base station above is a predicted or inferred serving cell based on the AI technology, to which the UE can be handed over.
  • the AI target cell is used as an example for description.
  • the source base station outputs a first request message, where the first request message is used to request the target base station corresponding to the AI target cell to allocate resources corresponding to the AI target cell to the UE.
  • the method further includes: the source base station obtains a first response message of the target base station, where the first response message responds to the first request message.
  • the process of determining the AI target cell by the source base station can be described as follows:
  • an AI device is deployed separately, and the AI device is called a remote intelligent communication, a wireless intelligent controller, an AI node or others, which is not limited.
  • the above-mentioned AI device may include at least one of the data sources, model training nodes or model inference nodes shown in FIG. 3a above.
  • the AI device may include the first AI module and/or the second AI module, etc. in the above-mentioned FIG. 3b, FIG. 3c, or FIG. 3d.
  • the AI device may infer, based on the AI model, an AI target cell to which the UE can be handed over.
  • the source base station may acquire the first message from the AI device, where the first message is at least used to indicate the AI target cell.
  • the first message can also be used to indicate at least one of the following: at least one of the AI handover type that the source base station can perform, activation time information, outage time information, or the prediction accuracy of the AI target cell, etc. .
  • activation time information, deactivation time information and AI switching type please refer to the following description. It can be understood that the above-mentioned activation time information and expiration time information may be directly indicated by the first message, or may be determined by performing certain calculations through the information of the first message.
  • the first message indicates the activation time information and the effective duration information.
  • the expiration time information can be determined by the activation time information and the valid duration information, and it can also be understood that the first message is used to indicate the activation time information and the expiration time information at this time.
  • the source base station and the AI device may also interact.
  • the AI device sends first indication information to the source base station, where the first indication information is used to indicate the AI handover type supported by the AI device, and/or the accuracy of the AI prediction information of the AI device.
  • the source base station sends second indication information to the AI device, where the second indication information is used to indicate at least one type of AI handover type supported by the source base station, the number of supported AI target cells, and other information.
  • the function of the AI module can be integrated in the source base station, and the source base station can use the AI method to infer the serving cell that the UE can switch to, that is, the AI target cell, etc.
  • the source base station can send a first request message to the target base station to which the AI target cell belongs, so as to request the target base station to allocate resources corresponding to the access AI target cell for the UE.
  • the target base station may send a first response message in response to the first request message to the source base station.
  • the first response message is used to indicate whether the target base station agrees to the request of the source base station, and so on.
  • the source base station performs AI inference and determines the AI target cell as an example to describe, at least including:
  • Step 400 The UE reports the first measurement information to the source base station.
  • the UE may report a first measurement report to the source base station, where the measurement report carries the first measurement information. This step 400 is optional.
  • the above-mentioned first measurement information includes identification information of the cell, quality information of the cell, and the like.
  • the cell may be a serving cell and/or a neighboring cell, etc., which is not limited.
  • the UE may periodically report the first measurement information to the source base station.
  • the UE may periodically measure the quality information of the serving cell and/or the quality information of the neighboring cells, and then periodically report the measured information to the source base station.
  • the UE may periodically measure the quality information of the serving cell and/or the quality information of the neighboring cells, and report the measured information to the source base station when certain conditions are met.
  • the identification information of the cell may include a cell global identifier (CGI), a physical cell identifier (PCI), a frequency point, and a cell identifier (cell ID) of the cell. ), at least one of a non-public network identifier (non-public network identifier, NPN ID), a non-terrestrial network identifier (non-terrestrial network identifier, NTN ID), or other cell identifiers.
  • the CGI may include a public land mobile network (public land mobile network, PLMN ID), a cell ID, and the like.
  • the identification information of the cell may also include a tracking area code (tracking area code, TAC) and/or identification information of the network device to which the cell belongs, such as a global network device identification and the like.
  • TAC tracking area code
  • the identification information of the cell may be the identification of the cell corresponding to the cell accessed by the UE.
  • the cell accessed by the UE may also be referred to as the current serving cell of the UE.
  • a cell may be shared by multiple operators at the same time, different operators may assign different identities to the same cell, and the identity of the cell may also be the identity of at least one cell sent by the base station to which the cell accessed by the UE belongs.
  • the identifier of the first cell in .
  • a cell is shared by the networks of multiple operators at the same time, and different operators may assign different identities to the cell, and the cell will send the identities of multiple cells to the UE.
  • the identifier of the cell in the embodiment of the present application may refer to the identifier of the first cell among the multiple identifiers sent by the cell accessed by the UE.
  • the cell accessed by the UE is shared by two operators at the same time, and the identifiers of the cells allocated by the two operators to the cell are PLMN1+CELL ID1 and PLMN2+CELL ID2 respectively.
  • the sequence of the identifiers of the above-mentioned cells in the sent cell information list is ⁇ LMN1+CELL ID1, PLMN2+CELL ID2 ⁇
  • the identifiers of the cells in this embodiment of the present application may specifically refer to PLMN1+CELL ID1.
  • the UE can measure the downlink synchronization channel, channel state information reference signal, demodulation reference signal (DMRS), cell-specific reference signal (CRS) signal, synchronization signal block At least one of (synchronization signal block, SSB), synchronization signal/physical broadcast channel block or other downlink signals, to obtain the quality information of the cell.
  • DMRS demodulation reference signal
  • CRS cell-specific reference signal
  • synchronization signal block At least one of (synchronization signal block, SSB), synchronization signal/physical broadcast channel block or other downlink signals, to obtain the quality information of the cell.
  • the quality information of the cell may include received signal code power (received signal code power, RSCP), reference signal receiving power (reference signal receiving power, RSRP), reference signal receiving quality (reference signal receiving quality, RSRQ), At least one of a signal noise ratio (signal noise ratio, SNR), a signal to interference plus noise ratio (signal to interference plus noise ratio, SINR), a reference signal strength indication (reference signal strength indication, RSSI), or other signal qualities.
  • RSCP received signal code power
  • RSRP reference signal receiving power
  • RSRQ reference signal receiving quality
  • SNR signal noise ratio
  • SINR signal to interference plus noise ratio
  • RSSI reference signal strength indication
  • the cell quality information may be cell-level, beam-level, synchronization signal/physical broadcast channel block (synchronization signal/physical broadcast channel block, SS/PBCH Block) level, channel state information reference signal (channel-state At least one of information reference signal, CSI-RS) level, air interface technology (numerology) level, slicing (slicing) level, or bandwidth part (bandwidth part, BWP) level.
  • the level of the cell quality information refers to the granularity with which the quality information of the cell is measured. For example, the quality information of a cell is at the cell level, which means that the UE measures each cell in the multiple cells to be measured to obtain the quality of each cell.
  • the quality of the cell is at the beam level, which means that the cell includes at least one beam, and the UE obtains the cell quality information by measuring the beam in the cell.
  • a cell includes 3 beams, and the UE can obtain the quality information of beam 1 and the quality information of beam 2 that satisfy the beam quality conditions by measuring beam 1, beam 2 and beam 3 of the above-mentioned 3 beams respectively.
  • the UE may obtain the quality information of the cell based on the quality information of beam 1 and the quality information of beam 2, for example, taking a larger value, averaging, or weighted summation.
  • the UE may report the quality information of beam 1 and the quality information of beam 2 at the same time. The UE measures the quality information of the cell based on other granularities, which is similar to the above, and will not be described again.
  • the identification information of the cell also includes the corresponding At least one of beam identification information, synchronization signal/physical broadcast channel block identification information, channel state information reference signal identification information, air interface technology identification information, slice identification information, or partial bandwidth identification information.
  • the source base station when receiving the above-mentioned first measurement information, may determine whether to switch the serving cell for the UE based on the first measurement information. If the serving cell needs to be switched for the UE, the source base station executes the following step 401 .
  • Step 401 The source base station performs AI inference according to at least one of the following information to determine the AI target cell.
  • the source base station obtains the AI target cell through AI inference. Since the AI target cell is the serving cell predicted by the source base station to which the UE can be handed over, the AI target cell inferred above can also be called the predicted AI target cell, etc. .
  • the number of the AI target cells is one or more, which is not limited.
  • the source base station is used to infer at least one piece of information about the AI target cell, including at least one of the following:
  • the first measurement information may be reported by the UE in the foregoing step 400 .
  • the source base station Since the source base station is the base station to which the serving cell of the UE belongs, the source base station can acquire the load information of the serving cell.
  • the load information of the serving cell may be real-time load information of the serving cell, and/or historical load information of the serving cell, and the like.
  • the load information of adjacent cells may be real-time load information of adjacent cells, and/or historical load information of adjacent cells, and the like.
  • the relevant information of the UE may include at least one of the trajectory information of the UE, the geographic coordinate information of the UE, the movement direction of the UE, or the movement speed of the UE.
  • the above-mentioned UE related information may be reported by the UE to the source base station, or obtained by the source base station by monitoring the UE, or obtained by the source base station through other network devices, etc., which are not limited.
  • the relevant information about the above UE may be real-time information of the UE and/or historical information of the UE, and the like.
  • the geographic coordinate information of the UE may be the current real-time geographic coordinates of the UE, and/or the historical geographic coordinates of the UE.
  • the source base station may perform AI inference according to the above at least one item of information to obtain the AI target cell.
  • the AI reasoning process may include one or more times, etc., which is not limited.
  • the model training nodes in Fig. 3a to Fig. 3d can analyze the training data provided by the data source to obtain an AI model.
  • the model inference node inputs the above at least one piece of information into the AI model, and the output of the AI model is the AI target cell.
  • the model training nodes in Fig. 3a to Fig. 3d can analyze the training data provided by the data source to obtain AI model A and AI model B.
  • the model inference node may input the above at least one item of information into the AI model A, and the output of the AI model A is future information of the above at least one item of information. For example, at least one item of information such as future load information of the serving cell or neighboring cells, future trajectory of the UE, future running speed of the UE, or future geographic coordinates of the UE. Afterwards, the model inference node may input at least one item of real-time information, historical information, or future information among the above at least one item of information into AI model B, and the output of AI model B is the AI target cell.
  • at least one item of information such as future load information of the serving cell or neighboring cells, future trajectory of the UE, future running speed of the UE, or future geographic coordinates of the UE.
  • the model inference node may input at least one item of real-time information, historical information, or future information among the above at least one item of information into AI model B, and the output of AI model B is the AI target cell.
  • Step 402a The source base station sends a first request message to the target base station corresponding to the AI target cell.
  • the first request message may be referred to as a handover request.
  • the interface can be an X2 interface, an Xn interface, or other interfaces, which are not limited.
  • the source base station may send the first request message to the target base station through the above-mentioned interface.
  • the source base station may send part or all of the content of the first request message to the target base station through the core network device.
  • the source base station may send the above-mentioned first request message to the core network device through the S1 interface or the NG interface or other interfaces, and then the core network device forwards the above-mentioned first request message to the target base station and the like.
  • the source base station may directly receive the first response message from the target base station through a direct communication interface.
  • the source base station may receive the first response message from the target base station through the core network device, and the like.
  • the source base station may send a corresponding first request message for each AI target cell. For example, if the number of AI target cells inferred by the source base station is 3, the source base station may send a first request message to the target base station to which the above-mentioned three AI target cells belong. In one case, multiple cells in the AI target cells inferred by the source base station may belong to the same target base station. In order to save signaling overhead, for the above-mentioned multiple cells, the source base station may send a first request message to the target base station, where the first request message may request the target base station to allocate resources for the UE to access multiple cells. In the flow of FIG. 4 , the source base station sends the first request message to a target base station as an example for illustration.
  • the first request message is used to request the target base station corresponding to the AI target cell to allocate resources corresponding to the AI target cell to the UE, and the first request message is used to indicate at least one of the following:
  • the type of handover is AI handover.
  • the activation time information is used to indicate the earliest time at which the UE can switch to the AI target cell. Exemplarily, if the UE attempts to access the AI target cell earlier than the earliest time, the base station corresponding to the AI target cell may reject the access.
  • the outage time information is used to indicate the latest time when the UE can switch to the AI target cell.
  • the base station corresponding to the AI target cell may delete the information related thereto. For example, the user plane data of the following early transfer, and the context of the UE, etc.
  • the method may further include: exchanging AI information between the source base station and the target base station.
  • the target base station may send AI information to the source base station, where the AI information is used to indicate at least one of the following:
  • the target base station supports or does not support AI handover.
  • binary bits may be used to indicate whether the target base station supports AI handover, "0" indicates that the target base station does not support AI handover, "1" indicates that the target base station supports AI handover, and so on.
  • FALSE false
  • TURE true
  • the source base station may send the first request message in step 402a to the target base station, otherwise the source base station will not send the request message to the target base station.
  • the target base station sends the first request message in the above step 402a.
  • the current handover mechanism includes multiple types, such as normal handover (legacy handover or ordinary handover), dual active protocol stack handover (DAPS HO), conditional handover ( conditional handover, CHO), random access handover (RACH-less HO) or other types, etc.
  • the AI handover type may specifically refer to a handover mechanism that supports AI handover among the above-mentioned various handover mechanisms.
  • the AI prediction method when used to predict that the cell to be handed over by the UE is cell 1, if the above-mentioned normal handover mechanism supports AI handover, the UE can use the normal handover mechanism to switch to cell 1, and the above AI handover types can be Handover mechanism including normal handover.
  • the AI handover type supported by the target base station may be specifically: a handover mechanism supported by the target base station that can perform AI handover.
  • the target base station includes multiple cells, and whether each cell in the multiple cells supports AI handover can be pre-defined or set.
  • a cell supports AI handover, it means that if the cell is determined to be the cell to be handed over by the UE through AI prediction, that is, the AI target cell, the cell supports the UE to switch to this cell; if a cell does not support AI handover, it means that the source base station It is not allowed to determine the cell to be handed over by the UE by means of AI prediction, that is, the AI target cell, or if the cell is determined to be the cell to be handed over by the UE by means of AI prediction, that is, the AI target cell, the cell does not support The UE is handed over to this cell.
  • the target base station can send the source base station to the source base station. Explicitly indicate the identity information of the cell supporting AI handover in the target base station.
  • the identification information of the cells supporting AI handover in the target base station the number of cells that the target base station supports for AI handover can be implicitly indicated. That is, at this time, the information on the cells in the target base station that allows AI handover includes identification information of cells in the target base station that support AI handover.
  • the target base station can indicate the target base station to the source base station.
  • Cell information in the base station that allows AI handover may include the identity and/or number of cells, and the like.
  • Step 402b The source base station receives a first response message from the target base station, where the first response message is in response to the first request message.
  • the first response message may be referred to as a handover response message.
  • the above-mentioned first response message may be an acknowledgement (acknowledge, ACK), such as a handover request acknowledgement (handover request acknowledge) message.
  • the first response message may be a negative acknowledgement (negative acknowledgement, NACK), such as a handover preparation failure (handover preparation failure) message, or a handover failure (handover failure) message, and the like.
  • ACK acknowledgement
  • NACK negative acknowledgement
  • the above-mentioned first response message is ACK, it means that the target base station agrees that the UE is handed over to its subordinate cell; otherwise, it indicates that the target base station does not agree that the UE is handed over to its subordinate cell.
  • the above-mentioned first response message may also include indication information of a cell in the target base station that allows the UE to perform AI handover, for example, including the number and/or identification of the cell. instructions, etc.
  • the "number of cells in the target base station that allow the UE to perform AI handover" indicated in the first response message may be the same as the "number of cells that are allowed to perform AI handover in the target base station" indicated in step 402a above. , can also be different. For example, the number of cells in the source base station that allows the current UE to perform AI handover is less than or equal to the number of cells that allow AI handover in the source base station.
  • the number of cells allowed to perform AI handover in the target base station in the above step 402a is 8.
  • the number of cells that allow the current UE to perform AI handover is 4, then the number of cells that the target base station allows the UE to perform AI handover in the first response message is 4.
  • Step 402c the source base station transfers user plane data to the target base station.
  • the source base station sends a first state forwarding message to the target base station, where the first state forwarding message is used to indicate the number of the first SDU in the user plane data transferred from the source base station to the target base station, and/or the transfer The number of SDUs that can be discarded in the user plane data.
  • the source base station when the source base station receives the first response message from the target base station, and the first response message is ACK, it means that the target base station agrees that the UE is handed over to a cell subordinate to the target base station.
  • the source base station can start transferring user plane data to the target base station.
  • the source base station transfers the user plane data to the target base station, which can complete the user plane data transfer of the UE as soon as possible and reduce the data interruption time caused by the handover.
  • the source base station transfers the user plane data to the target base station in advance
  • the above-mentioned user plane transfer can be called early data transfer from the source base station to the target base station, and the first state forwarding message sent by the source base station to the target base station can be called early state forwarding. status transfer).
  • the source base station can send at least one first state forwarding message to the target base station, which is used to instruct the target base station to update the number of the first SDU in time, and/or discard unnecessary SDUs.
  • the source base station After the source base station receives the first response message from the target base station, there are 10 downlink (downlink, DL) SDUs in the source base station that have not been sent to the UE, and the source base station can send the above 10 DL SDUs to the target base station. . Further, the source base station may also send a first state forwarding message to the target base station, which is used to indicate the number of the first DL SDU in the above 10 DL SDUs. For example, if the number of the first DL SDU in the above 10 DL SDUs is 1, the target base station can sequentially number the remaining 9 DL SDUs as 2-9 according to the number 1 of the above-mentioned first DL SDU.
  • DL downlink
  • the source base station may also send the number of DL SDUs that can be discarded in the early transferred DL SDUs to the target base station. Still using the above example, in the process of early data transfer, the source base station transferred 10 DL SDUs to the target base station. Subsequently, the source base station transmits 5 DL SDUs to the UE, and receives the ACK feedback of the above 5 DL SDUs. The source base station can send a first status forwarding message to the target base station, which is used to notify the target base station of the number of the DL SDU that can be discarded.
  • the first state forwarding message may include information for indicating the SDUs that the source base station needs to discard.
  • the source base station can directly indicate numbers 1-5 to the target base station, indicating that the target base station can discard DL SDUs with numbers 1-5; or, the source base station can indicate the number 6 to the target base station, indicating that the target base station can discard DL SDUs with numbers less than 6 DL SDU etc.
  • step 403 the UE sends the second measurement information to the source base station.
  • the UE may send a second measurement report to the source base station, where the second measurement report carries the second measurement information.
  • the second measurement report For the content of the second measurement information, reference may be made to the first measurement information in step 400 above.
  • Step 404 The source base station determines to hand over the UE to the first cell in the AI target cells.
  • the source base station when receiving the second measurement information of the UE, determines which cell the UE should switch to according to the second measurement information.
  • the UE is handed over to the first cell in the AI target cell as an example for description.
  • the UE is handed over to the second cell, and the second cell does not belong to the AI target cell as an example for description.
  • Step 405 The source base station sends first configuration information to the UE, where the first configuration information is used to indicate the configuration information of the first cell.
  • the source base station may send an RRC reconfiguration message to the UE, where the RRC reconfiguration message carries the above-mentioned first configuration information.
  • step 405 since in the process from step 402a to step 402c, the target base station to which the first cell belongs has agreed that the UE is handed over to the first cell, so in step 405, the source base station directly sends the configuration information of the first cell to the UE That is, there is no need to send the first request message to the target cell.
  • Step 406 The UE establishes a connection with the target base station.
  • the UE may send an RRC reconfiguration complete message to the target base station, where the RRC reconfiguration complete message is used for the UE to establish a connection with the target base station.
  • Step 407 The source base station sends a second state forwarding message to the target base station, where the second state forwarding message is used to indicate the data transmission state between the source base station and the UE, and the data transmission state includes an uplink data transmission state and/or a downlink data transmission state Status, etc., are not limited.
  • the data transmission status between the source base station and the UE may be the sequence number of the SDU that has been transmitted by the source base station and the UE.
  • the above-mentioned second status forwarding message may also be referred to as a sequence number status transfer (sequence number, SN, status tansfer), or the like.
  • the source base station can send the SDU sequence number for data transmission with the UE to the target base station.
  • the target base station continues data transmission with the UE based on the SDU sequence number of the transmitted data, so as to avoid retransmission or missing data transmission to the UE.
  • Step 408 The target base station notifies the source base station to release the UE context (UE context release). Correspondingly, after receiving the above notification, the source base station releases the context of the UE.
  • using AI computational reasoning to predict the cell to be handed over by the UE can improve the accuracy of the predicted target cell and improve the robustness of the UE cell handover, which can refer to the stability of the UE cell handover, and success rate, etc.
  • the data interruption time after handover can be reduced.
  • an AI target cell includes cell 1 and cell 2, and cell 1 and cell 2 belong to different base stations as an example.
  • the process includes at least:
  • step 500 the UE sends the first measurement information to the source base station.
  • Step 501 The source base station determines an AI target cell according to AI reasoning, and the AI target cell includes cell 1 and cell 2.
  • the base station corresponding to cell 1 is target base station 1
  • the base station corresponding to cell 2 is target base station 2 .
  • Step 502a The source base station sends a handover request message to the target base station 1 and the target base station 2 respectively.
  • Step 502b The target base station 1 and the target base station 2 respectively send a handover request response message to the source base station.
  • Step 502c The source base station performs early data transfer with the target base station 1 and the target base station 2 respectively, and the source base station sends an early state forwarding message to the target base station 1 and the target base station 2 respectively.
  • step 503 the UE sends second measurement information to the source base station, where the second measurement information is similar to the content included in the foregoing first measurement information.
  • Step 504 the source base station determines to hand over the UE to cell 1 .
  • the source base station may determine to hand over the UE to cell 1 according to the foregoing second measurement information.
  • the base station determines that the UE is handed over to cell 1 in the AI target cell as an example for description.
  • Step 505 The source base station sends an RRC reconfiguration message to the UE, where the RRC reconfiguration message includes the configuration information of cell 1.
  • Step 506 The UE sends an RRC reconfiguration complete message to the target base station 1 corresponding to the cell 1.
  • Step 507 The source base station sends the SN state transition to the target base station 1 corresponding to the cell 1.
  • Step 508 The target base station 1 notifies the source base station to release the context of the UE. Correspondingly, when the source base station receives the above notification, it releases the context of the UE.
  • Step 509 The target base station 2 corresponding to the cell 2 automatically releases the UE context information after expiration. Optionally, if there is data of the UE, the data corresponding to the UE is also deleted.
  • Step 509 may be described as follows: the handover request message in the above step 502a may include outage time information, and the outage time information may indicate the latest time for the UE to access the target cell 2 . If the latest time is exceeded and the UE still does not access the target cell 2, the target base station 2 can delete the relevant information of the UE, including deleting the context information of the UE, and/or the received user plane data of the early transferred UE.
  • the AI-based mobility mechanism predicts and infers a reasonable handover cell in advance, improves the success rate of handover preparation, and improves its robustness; in addition, the introduction of AI target cell Time information can occupy the resources of the AI target base station as little as possible and improve resource utilization.
  • Embodiment 2 The difference between Embodiment 2 and Embodiment 1 above is that, in Embodiment 2, the cell determined by the source base station to be handed over by the UE is the second cell, and the second cell does not belong to the pre-inferred AI target cell.
  • the second embodiment provides a process of cell handover, which at least includes:
  • step 600 the UE reports the first measurement information to the source base station.
  • Step 601 The source base station determines the AI target cell.
  • Step 602a The source base station sends a first request message to the target base station corresponding to the AI target cell.
  • Step 602b The target base station sends a first response message to the source base station, where the first response message is in response to the first request message.
  • Step 602c the source base station transfers user plane data to the target base station, and the source base station sends a first state forwarding message to the target base station.
  • step 603 the UE sends the second measurement information to the source base station.
  • Step 604 The source base station determines to switch to the second cell, and the AI target cell inferred above does not include the second cell.
  • Step 605a The source base station sends a first request message to the second base station corresponding to the second cell, where the first request message is used to request the second base station to allocate resources for the UE to access the second cell.
  • Step 605b The second base station sends a first response message to the source base station, where the first response message is in response to the first request message. Similar to the above, the first response message may be ACK or NACK. If the first response message is ACK, it means that the second base station agrees that the UE is handed over to the second cell; otherwise, it means that the second base station does not agree that the UE is handed over to the second cell. If the second base station agrees that the UE is handed over to the second cell, the source base station may perform early data transfer to the second base station, that is, the process of the following step 605c.
  • Step 605c the source base station transfers user plane data to the second base station, and the source base station sends a first state forwarding message to the second base station.
  • Step 606 The source base station sends a second configuration message to the UE, where the second configuration message is used to indicate the configuration information of the second cell and the configuration information of the AI target cell to the UE.
  • the source base station may send an RRC reconfiguration message to the UE, where the RRC reconfiguration message includes the foregoing second configuration message.
  • the configuration information of the AI target cell may be used to indicate at least one of the following:
  • the random access information is used to instruct the UE to switch to the random access resource of the AI target cell;
  • Step 607 The UE performs handover to the second cell according to the configuration information of the second cell.
  • connection failure between the UE and the second cell may include: a connection failure occurs during the handover process of the UE to the second cell, or a connection failure occurs shortly after the UE successfully performs the handover to the second cell.
  • Step 608 The UE determines the first target cell.
  • the manner in which the UE determines the first target cell is not limited.
  • the first target cell may belong to the AI target cell or may not belong to the AI target cell.
  • Step 609 The UE establishes a connection with the first target cell.
  • the process of establishing a connection between the UE and the first target cell may include: in one design, if the UE side stores valid configuration information of the AI target cell, when the first target cell is the When a cell in the AI target cell is mentioned, the UE performs a handover procedure to the first target cell.
  • the handover procedure performed by the UE to the first target cell includes: the UE sends an RRC reconfiguration complete message to the first target cell, or, when the first target cell is not a cell in the AI target cell, the UE performs to The reconstruction process of the first target cell.
  • the UE performs the reestablishment process to the first target cell.
  • the source base station sends the configuration information of the AI target cell to the UE.
  • the configuration information of the AI target cell includes outage time information, and the outage time information refers to the latest time when the UE accesses the AI target cell, or refers to the latest valid time of the configuration information of the AI target cell. If the latest time is exceeded and the UE has not yet accessed the AI target cell, the UE may delete the configuration information of the AI target cell.
  • the configuration information of the AI target cell stored on the UE side has not reached the time indicated by the above-mentioned failure time information, it can be said that the configuration information of the valid AI target cell is stored on the UE side, otherwise it is said that the valid AI target cell is not stored on the UE side. configuration information.
  • the UE may delete the configuration information of the AI target cell corresponding to the outage time information.
  • the UE detects that the connection with the second cell fails, and the UE does not store the configuration information of the valid AI target cell, then the UE can perform the reestablishment procedure to the first target cell.
  • Step 610 The base station corresponding to the first target cell sends the indication information that the handover is successful to the source base station.
  • Step 611 The source base station sends a second state forwarding message to the base station corresponding to the first target cell.
  • Step 612 The base station corresponding to the first target cell notifies the source base station to release the context of the UE.
  • the signaling interaction is much simpler. Therefore, during the connection failure between the UE and the second cell, if the first target cell selected by the UE is one of the predicted AI target cells, The UE can directly initiate a handover process to the first target cell, quickly restore the connection, shorten the interruption delay of data transmission, and reduce signaling overhead.
  • an exemplary process of cell handover including at least:
  • step 700 the UE reports the first measurement information to the source base station.
  • Step 701 The UE determines an AI target cell according to AI reasoning, and the AI target cell includes cell 1 and cell 2.
  • Step 702a The UE sends a handover request message to base station 1 corresponding to cell 1 and base station 2 corresponding to cell 2, respectively.
  • Step 702b The UE receives the handover response messages from base station 1 and base station 2.
  • Step 702c The source base station transfers the user plane data to the base station 1 and the base station 2, and the source base station sends the early state transition to the base station 1 and the base station 2.
  • step 703 the UE sends the second measurement information to the source base station.
  • Step 704 The source base station determines to switch to cell 3.
  • the source base station may determine to switch to cell 3 according to the second measurement information, and this cell 3 does not belong to the AI target cell.
  • Step 705a The source base station sends a handover request message to the base station 3 corresponding to the cell 3.
  • Step 705b The base station 3 sends a handover request response message to the source base station.
  • Step 705c the source base station transfers the user plane data to the base station 3, and the source base station sends the early state transition to the base station 3.
  • Step 706 The source base station sends a second configuration message to the UE, where the second configuration message may be an RRC reconfiguration message, and the second configuration message is used to indicate the configuration information of cell 3 and the configuration information of the AI target cell.
  • the second configuration message may be an RRC reconfiguration message
  • Step 707 The UE performs handover to cell 3, and detects a connection failure during the handover process, or detects a connection failure after handover to cell 3.
  • Step 708 The UE performs cell selection.
  • Step 709 The UE selects an AI target cell, such as cell 1, and the UE performs a handover process.
  • the UE performing the handover procedure includes: the UE sends an RRC reconfiguration complete message to the base station 1 corresponding to the cell 1.
  • Step 710 The base station 1 sends handover indication information, such as a handover success message, to the source base station, notifying the source base station that the UE has successfully completed the handover in the cell 1 .
  • handover indication information such as a handover success message
  • Step 711 the source base station may send the SN state transition to base station 1 .
  • Step 712 Base station 1 notifies the source base station to release the UE context.
  • Step 713 The base station 2 corresponding to the cell 2 automatically deletes the UE context after expiration, and also deletes the data corresponding to the UE if there is data.
  • the AI-based mobility mechanism predicts that when the final handover cell does not belong to the AI target cell, the configuration information of the AI target cell is still sent to the UE, which can improve the reliability of mobility.
  • introducing the time information of the AI target cell such as activation time information or invalidation time information, can occupy as little resources as possible of the base station corresponding to the AI target cell and improve system efficiency.
  • the base station triggering is taken as an example for description.
  • the solution of the first embodiment or the second embodiment can also be applied to a scenario where the UE triggers a handover. In one design, it is mainly different from FIG. 4 in the above-mentioned first embodiment or FIG. 6 in the second embodiment:
  • the first request message sent by the source base station to the target base station corresponding to the AI target cell may further carry indication information that the UE triggers the handover mechanism.
  • the source base station sends third configuration information to the UE, where the third configuration information is used to indicate the configuration information of the AI target cell and the handover trigger configuration information to the UE, and the handover trigger configuration information is used for It is used to indicate to the UE a triggering condition for handover to the AI target cell.
  • the configuration information may further include indication information such as activation time information and/or deactivation time information of the AI target cell.
  • the above-mentioned handover trigger configuration information is described as follows: in the UE-triggered handover mechanism, the source base station configures at least one candidate cell for the UE.
  • the above-mentioned AI target cell is a candidate cell configured by the source base station to the UE.
  • the UE may select a candidate cell corresponding to the trigger condition to perform handover.
  • the above handover trigger configuration information may specifically be: the source base station is a candidate cell, that is, an AI target cell, and the configured handover trigger condition.
  • the handover trigger conditions of different candidate cells may be the same or different.
  • Step 404 or 604 is replaced with: the source base station determines to update the configuration information of the AI target cell and/or update the handover trigger configuration information.
  • Step 405 or 605 is replaced by: the source base station sends fourth configuration information to the UE, where the fourth configuration information is used to indicate to the UE updated AI target cell configuration information and/or updated handover trigger configuration information.
  • the UE reports the first measurement information to the source base station, and the source base station determines the AI target cells, including cell 1 and cell 2, according to the first measurement information and other information.
  • the source base station sends third configuration information to the UE, where the third configuration information includes configuration information of cell 1 and cell 2, and handover trigger configuration information of cell 1 and cell 2.
  • the UE reports the second measurement information to the source base station, and the source base station determines, according to the second measurement information, that the added cell 3 is a candidate cell, and the source base station may send the updated third configuration information, that is, the fourth configuration information, to the UE.
  • the configuration information includes configuration information of cell 1, cell 2, and cell 3, and handover trigger configuration information corresponding to cell 1, cell 2, or cell 3, and the like.
  • the fourth configuration information may only include configuration information of cell 3, handover trigger configuration information corresponding to cell 3, and the like. Further, the above-mentioned fourth configuration information may further include activation time information and/or indication information of the deactivation time information of the cell 3, and the like.
  • the third embodiment provides a method for cell handover, and the method for cell handover can update the result of the AI target cell inferred in the first embodiment or the second embodiment.
  • the third embodiment can be used in combination with the above-mentioned first embodiment or the second embodiment, or can be used alone, etc., which is not limited.
  • the method for cell handover provided by the third embodiment includes: the source base station outputs fifth configuration information, where the fifth configuration information is used to indicate a trigger condition for the UE to report the first feedback information; the source base station obtains the first feedback information of the UE; The source base station determines an update result of the AI target cell, where the update result of the AI target cell is a serving cell to which the updated UE can be handed over.
  • the AI device may be deployed independently.
  • the AI device may determine a trigger condition for the UE to report the first feedback information, and the AI device sends the fifth configuration information to the source base station.
  • the source base station forwards the fifth configuration information to the UE to indicate a trigger condition for the UE to report the first feedback information.
  • the source base station receives the first feedback information from the UE, and the source base station forwards the first feedback information to the AI device.
  • the AI device updates the result of the AI target cell according to the first feedback information.
  • the AI device and the UE may directly interact without going through the transfer of the source base station.
  • the AI device may directly send the fifth configuration information to the UE, and the UE also directly reports the first feedback information to the AI device.
  • the function of the AI module may be integrated in the source base station.
  • the source base station may send fifth configuration information to the UE.
  • the source base station may receive the first feedback information sent by the UE, and the source base station may update the result of the AI target cell according to the first feedback information, and the like.
  • a process of cell handover is provided, which at least includes:
  • Step 800 The UE sends the first measurement information to the source base station.
  • Step 801 The source base station determines the AI target cell.
  • the AI target cell includes cell 1 and cell 2, the base station corresponding to cell 1 is base station 1, and the base station corresponding to cell 2 is base station 2.
  • Step 802a The source base station sends handover request messages to base station 1 and base station 2 respectively.
  • Step 802b Base station 1 and base station 2 respectively send a handover request response message to the source base station.
  • Step 802c The source base station transfers user plane data to base station 1 and base station 2 early and sends an early state forwarding message.
  • the above steps 800 to 802c are optional.
  • the source base station may, under the condition that the above steps 800 to 802c are satisfied, execute the following step 803 to send the fifth configuration information to the UE.
  • the source base station may use other conditions as a trigger to execute the following step 803 to send fifth configuration information to the UE, etc., which is not limited.
  • Step 803 The source base station sends fifth configuration information to the UE, where the fifth configuration is used to indicate a trigger condition for the UE to report the first feedback information.
  • the source base station may send an RRC reconfiguration message to the UE, where the RRC reconfiguration message includes fifth configuration information.
  • the foregoing fifth configuration information may be used to indicate at least one of the following:
  • the identification information of the cell may be the identification information of the serving cell of the UE, and/or the identification information of neighboring cells.
  • the adjacent cell may be the AI target cell.
  • the quality threshold information is used for the UE to report the first feedback information when it determines that the quality of the cell meets the quality threshold.
  • the quality threshold information may be the first quality threshold information.
  • the UE may report the first feedback information; or, the threshold information may include the second quality threshold information and the third quality threshold information; when the quality of the current serving cell of the UE is When the quality is lower than or equal to the second quality threshold, and the quality of the neighboring cell is higher than or equal to the third quality threshold, the UE may report the first feedback information.
  • the first feedback information may include the identification information of the cell that satisfies the fifth configuration information, and/or the quality information corresponding to the identification information of the cell that satisfies the fifth configuration information, and the like.
  • the UE reports the first feedback information.
  • the first feedback information may include the latest location information of the UE.
  • Time reporting indication information which is used to indicate that the UE carries or does not carry time information in the first feedback information, where the time information is the time when the UE satisfies the fifth configuration information, or the UE reports the time information the time of the first feedback information, etc.
  • the UE reports the first feedback information.
  • the previous trajectory of the UE obtained by the base station is A.
  • the UE finds that it deviates from the previous trajectory A, or when the distance or time from the previous trajectory A exceeds a certain threshold, the UE sends the first feedback information to the base station.
  • Step 804 When the above trigger condition is satisfied, the UE reports the first feedback information to the source base station.
  • Step 805 The source base station determines the update result of the AI target cell according to the first feedback information.
  • the source base station may use the first feedback information as an input into the AI model, and the output of the AI model is the update result of the AI target cell.
  • the source base station may update the AI model according to the first feedback information, and obtain the update result of the AI target cell by using the updated AI model.
  • introducing the UE for AI inference feedback can assist the source base station to improve the AI inference results in a timely manner and ensure the accuracy and validity of the AI inference results.
  • the functions of the access network equipment may be implemented by multiple common standard modules.
  • the functions of the base station may be implemented by a CU module or a DU module.
  • the actions of the source base station and the target base station can be described as a whole: the source base station determines the AI target cell, and the source base station sends a first request message to the target base station corresponding to the AI target cell. The target base station sends a first response message to the source base station, where the first response message is in response to the first request message.
  • the target base station includes the CU2 module and the DU2 module.
  • the transmission path of the first request message may include: the CU1 module may determine the AI target cell, the CU1 module sends the first request message to the CU2 module, and the like. If the AI target cell is a cell managed by DU2, the CU2 module may send a second request message to the DU2 module, and the content and function of the second request message are similar to the first request message.
  • the transmission path of the first response message may include: the DU2 module sends a second response message to the CU2 module, the second response message is in response to the first response message; CU2 combines the notification of DU2 (that is, the second response message), and CU2's own It is judged that a first response message is generated, and CU2 sends the first response message to CU1.
  • the device outputs a certain message
  • the source base station outputs the first request message
  • the source base station outputs the fifth configuration information, and so on.
  • the device outputs a certain message may include: “the device sends the above-mentioned message A to other devices", or, "the device sends the above-mentioned message A to other devices”
  • a module in the device outputs message A to another module in the device, which sends message A to other devices, etc.”
  • the device obtains the message of other devices for example, the source base station obtains the first feedback information of the UE, the source base station obtains the first response message of the target base station, and the like.
  • a device obtains messages from other devices may be “the device receives messages from other devices", or, "a module in the device receives messages from other devices, and a module in the device will Received messages, forwarded to other modules in the device, etc.
  • the first request message may include indication information of at least one item of information, and the like.
  • the message may directly indicate the corresponding information, for example, the information may be directly carried in the message.
  • the message may indirectly indicate the corresponding information, for example, the message carries the indication information of the corresponding information, and the like.
  • the message A includes the indication information of the information X, and the message A may directly indicate the information X, for example, the message A may carry the information X.
  • the message A may indicate information X indirectly.
  • the message A may carry other information used to represent the information X, and the like.
  • the source base station is the network device to which the serving cell of the UE belongs, which may be referred to as the first network device
  • the target base station may be the network device to which the AI target cell belongs, and may be referred to as the second network device
  • the UE may be the network device to be handed over.
  • the terminal equipment of the serving cell For the description of the network device and the terminal device, reference may be made to the description in the aforementioned FIG. 1 .
  • FIG. 9 shows a possible block diagram of the apparatus involved in the embodiment of the present application.
  • the apparatus 900 may include: a communication unit 901 for supporting the communication between the apparatus and other devices.
  • the communication unit 901 is also called a transceiver unit, and may include a receiving unit and/or a sending unit, which are respectively configured to perform receiving and sending operations.
  • the processing unit 902 is used to support the device to perform processing.
  • the apparatus 900 may further include a storage unit 903 for storing program codes and/or data of the apparatus 900 .
  • the above-mentioned apparatus 900 may be a network device or a module, chip or circuit in the network device.
  • the communication unit 901 is configured to perform the transceiving operation of the source base station in the first or second embodiment of the above method;
  • the processing unit 902 is configured to perform the processing-related operation of the source base station in the first or second embodiment of the above method.
  • the processing unit 902 is configured to determine an AI target cell, where the AI target cell is a predicted serving cell to which the terminal device can be handed over; the communication unit 901 is configured to output a first request message, the first request message using In order to request the second network device corresponding to the AI target cell to allocate resources corresponding to the AI target cell to the terminal device, the first request message is used to indicate at least one of the following: identification information of the AI target cell , the type of the handover is AI handover, activation time information, failure time information, or the prediction accuracy of the AI target cell, and the activation time information is used to instruct the terminal device to switch to the earliest time of the AI target cell. time, the failure time information is used to indicate the latest time for the terminal device to switch to the AI target cell.
  • the AI target cell is predicted according to an AI method, including: the AI target cell is predicted according to at least one item of the following information, and the at least one item of information includes: the terminal equipment the first measurement information, the load information of the serving cell, the load information of the adjacent cell, the trajectory information of the terminal device, the geographic coordinate information of the terminal device, the movement direction of the terminal device, or the Movement speed.
  • the communication unit 901 is further configured to acquire a first response message of the second network device, where the first response message responds to the first request message, and the first response message includes Indication information of the number of cells in the second network device that allow the terminal device to perform AI handover.
  • the communication unit 901 is further configured to: acquire AI information of the second network device, where the AI information is used to indicate at least one of the following: the second network device supports or does not support AI Handover indication information, indication information of the AI handover type supported by the second network device, or cell information that the second network device allows to perform AI handover.
  • the communication unit 901 is further configured to: transfer the user plane data of the terminal device to the second network device, and output a first state forwarding message, where the first state forwarding message is used for Indicates the number of the first downlink service data unit SDU in the user plane data transferred from the first network device to the second network device, and/or the number of SDUs that can be discarded in the transferred user plane data.
  • the processing unit 902 is further configured to determine to switch the terminal device to the first cell in the AI target cells; the communication unit 901 is further configured to output a first configuration message, the first The configuration message is used to indicate the configuration information of the first cell to the terminal device.
  • the processing unit 902 is further configured to determine to switch the terminal device to a second cell, and the AI target cell does not include the second cell; the communication unit 901 is further configured to output the second cell A configuration message, where the second configuration message is used to indicate the configuration information of the second cell and the configuration information of the AI target cell to the terminal device.
  • the communication unit 901 is further configured to output third configuration information, where the third configuration information is used to indicate the configuration information of the AI target cell and the handover trigger configuration information to the terminal device, so The handover trigger configuration information is used to indicate to the terminal equipment a trigger condition for handover to the AI target cell.
  • the configuration information of the AI target cell is used to indicate at least one of the following: identification information, random access information, activation time information, or outage time information of the AI target cell, the random The access information is used to instruct the terminal device to switch to the random access resource of the AI target cell, the activation time information indicates the earliest time for the terminal device to switch to the AI target cell, and the outage time information indicates The latest time for the terminal device to switch to the AI target cell.
  • the above-mentioned apparatus 900 may be a network device or a module, chip or circuit in the network device.
  • the communication unit 901 is configured to perform the transceiving related operations of the target base station in the above method Embodiment 1 or Embodiment 2; the processing unit 902 is configured to perform the processing related operations of the target base station in the above method Embodiment 1 or Embodiment 2.
  • the communication unit 901 is configured to obtain a first request message of the first network device, where the first request message is used to request the second network device corresponding to the artificial intelligence AI target cell to allocate the terminal device corresponding to the AI target cell resources; wherein the first request message is used to indicate at least one of the following: the identification information of the AI target cell, the type of the handover is AI handover, activation time information, outage time information, or the AI target cell
  • the activation time information is used to indicate the earliest time for the terminal device to switch to the AI target cell
  • the failure time information is used to indicate the latest time for the terminal device to switch to the AI target cell. time.
  • the AI target cell is predicted according to at least one of the following pieces of information, where the at least one piece of information includes: first measurement information of the terminal device, load information of the serving cell, neighboring Load information of the cell, trajectory information of the terminal device, geographic coordinate information of the terminal device, movement direction of the terminal device, or movement speed of the terminal device.
  • the communication unit 901 is further configured to: output a first response message, where the first response message responds to the first request message, and the first response message includes the second network device Indication information of the number of cells in which the terminal device is allowed to perform AI handover.
  • the communication unit 901 is further configured to: output an AI message, where the AI information is used to indicate at least one of the following: indication information that the second network device supports or does not support AI handover, the Indication information of the AI handover type supported by the second network device, or cell information that the second network device allows to perform AI handover.
  • the communication unit 901 is further configured to: obtain the user plane data of the terminal device transferred by the first network device, and obtain the first state forwarding message of the first network device, so The first state forwarding message is used to indicate the number of the first downlink service data unit SDU in the user plane data transferred from the first network device to the second network device, and/or the transferred user plane data may The number of the discarded SDU.
  • the above-mentioned apparatus 900 may be a terminal device or a module, a chip or a circuit in the terminal device.
  • the communication unit 901 is configured to perform the UE's transceiving related operations in the second method embodiment above; the processing unit 902 is configured to perform the UE's processing-related operations in the above method embodiment.
  • the communication unit 901 is configured to acquire second configuration information of the first network device, where the second configuration information is used to indicate the configuration information of the second cell and the configuration information of the artificial intelligence AI target cell to the terminal device; the processing unit 902 is configured to use for performing handover to the second cell according to the configuration information of the second cell.
  • the processing unit 902 is further configured to determine the first target cell when the connection between the terminal device and the second cell fails.
  • the processing unit 902 is further configured to, when the first target cell is a cell in the AI target cell when the handover procedure is performed to the first target cell; or, when the first target cell is not a cell in the AI target cell, the reestablishment procedure to the first target cell is performed.
  • the processing unit 902 is further configured to perform the reconstruction process to the first target cell.
  • the above-mentioned apparatus 900 may be a network device or a module, chip or circuit in the network device.
  • the communication unit 901 is configured to perform the transceiving related operations of the source base station in the third method embodiment above; the processing unit 902 is configured to perform the processing related operations of the source base station in the third method embodiment above.
  • the communication unit 901 is configured to output fifth configuration information, where the fifth configuration information is used to indicate a trigger condition for the terminal device to report the first feedback information; the communication unit 901 is further configured to acquire the first feedback of the terminal device information; a processing unit 902, configured to determine the update result of the artificial intelligence AI target cell, the update result of the AI target cell is determined according to the first feedback information, and the update result of the AI target cell is the updated The serving cell to which the terminal device can be handed over.
  • the fifth configuration information is used to indicate at least one of the following: information and quality threshold information of at least one cell, reference location information and first distance threshold information, trajectory change trigger information or time reporting indication information, the time reporting indication information includes indication information that the terminal device carries or does not carry time information in the first feedback information, and the time information is the time when the terminal device satisfies the fifth configuration information , or the time when the terminal device reports the first feedback information.
  • the first feedback information is used to indicate the identity of the cell that satisfies the fifth configuration information information, and/or, the quality information of the cell that satisfies the fifth configuration information, or the first feedback information is used to indicate the identification information of the cell that does not meet the fifth configuration information, and/or, does not meet the The quality information of the cell of the fifth configuration information; or, when the fifth configuration information is used to indicate the reference location information and the first distance threshold information, the first feedback information is used to indicate the latest information of the terminal equipment. location information.
  • the above-mentioned apparatus 900 may be a terminal device or a module, a chip or a circuit in the terminal device.
  • the communication unit 901 is configured to perform the operations related to sending and receiving of the UE in the third method embodiment above; the processing unit 902 is configured to perform the processing related operations of the UE in the third method embodiment above.
  • the communication unit 901 is configured to acquire fifth configuration information of the first network device, where the fifth configuration information is used to indicate a trigger condition for the terminal device to report the first feedback information; the communication unit 901 is further configured to output the first feedback information, the first feedback information is output when the trigger condition of the fifth configuration information is met, the first feedback information is used to update the artificial intelligence AI target cell, and the update result of the AI target cell is updated The serving cell to which the terminal device can be handed over.
  • the fifth configuration information is used to indicate at least one of the following: information and quality threshold information of at least one cell, reference location information and first distance threshold information, trajectory change trigger information or time reporting indication information, the time reporting indication information includes indication information that the terminal device carries or does not carry time information in the first feedback information, and the time information is the time when the terminal device satisfies the fifth configuration information , or the time when the terminal device reports the first feedback information.
  • the first feedback information is used to indicate the identity of the cell that satisfies the fifth configuration information information, and/or, the quality information of the cell that satisfies the fifth configuration information, or the first feedback information is used to indicate the identification information of the cell that does not meet the fifth configuration information, and/or, does not meet the The quality information of the cell of the fifth configuration information; or, when the fifth configuration information is used to indicate the reference location information and the first distance threshold information, the first feedback information is used to indicate the latest information of the terminal equipment. location information.
  • each unit in the above apparatus can be realized in the form of software calling through the processing element; also can all be realized in the form of hardware; some units can also be realized in the form of software calling through the processing element, and some units can be realized in the form of hardware.
  • each unit can be a separately established processing element, or can be integrated in a certain chip of the device to be implemented, and can also be stored in the memory in the form of a program, which can be called by a certain processing element of the device and execute the unit's processing. Function.
  • each operation of the above method or each of the above units may be implemented by an integrated logic circuit of hardware in the processor element or implemented in the form of software being invoked by the processing element.
  • a unit in any of the above apparatuses may be one or more integrated circuits configured to implement the above methods, eg, one or more application specific integrated circuits (ASICs), or, one or more Multiple microprocessors (digital singnal processors, DSPs), or, one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.
  • ASICs application specific integrated circuits
  • DSPs digital singnal processors
  • FPGAs field programmable gate arrays
  • a unit in the apparatus can be implemented in the form of a processing element scheduler
  • the processing element can be a processor, such as a general-purpose central processing unit (CPU), or other processors that can invoke programs.
  • these units can be integrated together and implemented in the form of a system-on-a-chip (SOC).
  • SOC system-on-a-chip
  • the above unit for receiving is an interface circuit of the device for receiving signals from other devices.
  • the receiving unit is an interface circuit used by the chip to receive signals from other chips or devices.
  • the above unit for sending is an interface circuit of the device for sending signals to other devices.
  • the sending unit is an interface circuit used by the chip to send signals to other chips or devices.
  • FIG. 10 is a schematic structural diagram of a terminal device according to an embodiment of the present application.
  • the terminal device includes: an antenna 1010 , a radio frequency part 1020 , and a signal processing part 1030 .
  • the antenna 1010 is connected to the radio frequency part 1020 .
  • the radio frequency part 1020 receives the information sent by the network device through the antenna 1010, and sends the information sent by the network device to the signal processing part 1030 for processing.
  • the signal processing part 1030 processes the information of the terminal equipment and sends it to the radio frequency part 1020
  • the radio frequency part 1020 processes the information of the terminal equipment and sends it to the network equipment through the antenna 1010.
  • the signal processing part 1030 may include a modulation and demodulation subsystem, which is used to implement the processing of each communication protocol layer of the data; it may also include a central processing subsystem, which is used to implement the processing of the terminal device operating system and the application layer; in addition, it can also Including other subsystems, such as multimedia subsystem, peripheral subsystem, etc., wherein the multimedia subsystem is used to realize the control of the terminal equipment camera, screen display, etc., and the peripheral subsystem is used to realize the connection with other devices.
  • the modem subsystem can be a separate chip.
  • the modem subsystem may include one or more processing elements 1031, including, for example, a host CPU and other integrated circuits.
  • the modulation and demodulation subsystem may further include a storage element 1032 and an interface circuit 1033 .
  • the storage element 1032 is used to store data and programs, but the program used to execute the method performed by the terminal device in the above method may not be stored in the storage element 1032, but in a memory outside the modulation and demodulation subsystem, When used, the modem subsystem is loaded for use.
  • Interface circuit 1033 is used to communicate with other subsystems.
  • the modulation and demodulation subsystem can be implemented by a chip, the chip includes at least one processing element and an interface circuit, wherein the processing element is used to execute each step of any one of the methods performed by the above terminal equipment, and the interface circuit is used to communicate with other devices.
  • the unit for the terminal device to implement each step in the above method may be implemented in the form of a processing element scheduler.
  • an apparatus for a terminal device includes a processing element and a storage element, and the processing element calls the program stored in the storage element to Execute the method executed by the terminal device in the above method embodiments.
  • the storage element may be a storage element on the same chip as the processing element, ie, an on-chip storage element.
  • the program for executing the method performed by the terminal device in the above method may be in a storage element on a different chip from the processing element, that is, an off-chip storage element.
  • the processing element calls or loads the program from the off-chip storage element to the on-chip storage element, so as to call and execute the method performed by the terminal device in the above method embodiments.
  • the unit for the terminal device to implement each step in the above method may be configured as one or more processing elements, and these processing elements are provided on the modulation and demodulation subsystem, and the processing element here may be an integrated circuit, For example: one or more ASICs, or, one or more DSPs, or, one or more FPGAs, or a combination of these types of integrated circuits. These integrated circuits can be integrated together to form chips.
  • the units of the terminal device implementing each step in the above method may be integrated together and implemented in the form of an SOC, and the SOC chip is used to implement the above method.
  • At least one processing element and a storage element may be integrated in the chip, and the method executed by the above terminal device may be implemented in the form of a program stored in the storage element being invoked by the processing element; or, at least one integrated circuit may be integrated in the chip to implement the above terminal.
  • the above apparatus for a terminal device may include at least one processing element and an interface circuit, where the at least one processing element is configured to execute any method performed by the terminal device provided in the above method embodiments.
  • the processing element can execute part or all of the steps performed by the terminal device in the first way: by calling the program stored in the storage element; or in the second way: by combining the instructions with the integrated logic circuit of the hardware in the processor element Part or all of the steps performed by the terminal device may be performed in the manner of the first method; of course, some or all of the steps performed by the terminal device may also be performed in combination with the first manner and the second manner.
  • the processing elements here are the same as those described above, which can be implemented by a processor, and the functions of the processing elements can be the same as those of the processing unit described in FIG. 9 .
  • the processing element may be a general-purpose processor, such as a CPU, or may be one or more integrated circuits configured to implement the above methods, such as: one or more ASICs, or, one or more microprocessors, DSPs , or, one or more FPGAs, etc., or a combination of at least two of these integrated circuit forms.
  • the storage element may be implemented by a memory, and the function of the storage element may be the same as that of the storage unit described in FIG. 9 .
  • the storage element may be implemented by a memory, and the function of the storage element may be the same as that of the storage unit described in FIG. 9 .
  • the storage element can be one memory or a collective term for multiple memories.
  • the terminal device shown in FIG. 10 can implement each process involving the terminal device in the foregoing method embodiments.
  • the operations and/or functions of each module in the terminal device shown in FIG. 10 are respectively to implement the corresponding processes in the foregoing method embodiments.
  • the network device may be an access network device (eg, a base station).
  • Access network equipment 110 may include one or more DUs 1101 and one or more CUs 1102.
  • the DU 1101 may include at least one antenna 11011, at least one radio frequency unit 11012, at least one processor 11013 and at least one memory 11014.
  • the DU 1101 part is mainly used for the transmission and reception of radio frequency signals, the conversion of radio frequency signals and baseband signals, and part of baseband processing.
  • the CU 1102 may include at least one processor 11022 and at least one memory 11021 .
  • the CU 1102 part is mainly used to perform baseband processing, control access network equipment, and the like.
  • the DU 1101 and the CU 1102 may be physically set together, or may be physically separated, that is, a distributed base station.
  • the CU 1102 is the control center of the access network equipment, which can also be called a processing unit, and is mainly used to complete the baseband processing function.
  • the CU 1102 may be used to control the access network device to perform the operation process of the access network device in the foregoing method embodiments.
  • the access network device 110 may include one or more radio frequency units, one or more DUs, and one or more CUs.
  • the DU may include at least one processor 11013 and at least one memory 11014
  • the radio unit may include at least one antenna 11011 and at least one radio frequency unit 11012
  • the CU may include at least one processor 11022 and at least one memory 11021 .
  • the CU1102 may be composed of one or more single boards, and multiple single boards may jointly support a wireless access network (such as a 5G network) with a single access indication, or may respectively support wireless access systems of different access standards.
  • Access network such as LTE network, 5G network or other network.
  • the memory 11021 and the processor 11022 may serve one or more single boards. That is to say, the memory and processor can be provided separately on each single board. It can also be that multiple boards share the same memory and processor. In addition, necessary circuits may also be provided on each single board.
  • the DU1101 can be composed of one or more boards, and multiple boards can jointly support a wireless access network (such as a 5G network) with a single access indication, or can support a wireless access network with different access standards (such as a 5G network). LTE network, 5G network or other network).
  • the memory 11014 and processor 11013 may serve one or more single boards. That is to say, the memory and processor can be provided separately on each single board. It can also be that multiple boards share the same memory and processor. In addition, necessary circuits may also be provided on each single board.
  • the access network device shown in FIG. 11 can implement each process involving the access network device in the foregoing method embodiments.
  • the operations and/or functions of each module in the access network device shown in FIG. 11 are respectively to implement the corresponding processes in the foregoing method embodiments.
  • system and “network” in the embodiments of the present application may be used interchangeably.
  • At least one means one or more, and “plurality” means two or more.
  • And/or which describes the association relationship of the associated objects, means that there can be three kinds of relationships, for example, A and/or B, which can mean: the existence of A alone, the existence of A and B at the same time, and the existence of B alone, where A, B can be singular or plural.
  • the character “/” generally indicates that the associated objects are an “or” relationship.
  • At least one item(s) below” or similar expressions thereof refer to any combination of these items, including any combination of single item(s) or plural items(s).
  • At least one of A, B or C includes A, B, C, AB, AC, BC or ABC.
  • the ordinal numbers such as “first” and “second” mentioned in the embodiments of the present application are used to distinguish multiple objects, and are not used to limit the order, sequence, priority or importance of multiple objects degree, etc.
  • the embodiments of the present application may be provided as a method, a system, or a computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.
  • computer-usable storage media including, but not limited to, disk storage, CD-ROM, optical storage, etc.
  • These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory result in an article of manufacture comprising instruction means, the instructions
  • the apparatus implements the functions specified in the flow or flow of the flowcharts and/or the block or blocks of the block diagrams.

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Mobile Radio Communication Systems (AREA)

Abstract

一种小区切换方法及装置，该方法包括：确定AI目标小区，该AI目标小区为预测的、终端设备可以切换到的服务小区；发送第一请求消息，该第一请求消息用于请求AI目标小区对应的网络设备为终端设备分配AI目标小区对应的资源。其中，第一请求消息用于指示以下至少一项：AI目标小区的标识信息、切换的类型为AI切换、激活时间信息、失效时间信息、或AI目标小区的预测准确度等。其中，激活时间信息用于指示终端设备切换到AI目标小区的最早时间，失效时间信息用于指示终端设备切换到AI目标小区的最晚时间。采用本申请的方法及装置，可在一定程度上提高小区切换效率。

Description

一种小区切换方法及装置
相关申请的交叉引用
本申请要求在2021年04月02日提交中华人民共和国知识产权局、申请号为202110361698.X、发明名称为“一种小区切换方法及装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请实施例涉及通信技术领域，尤其涉及一种小区切换方法及装置。
背景技术
在通信系统中，终端设备可以进行小区切换。比如，终端设备的当前服务小区的信号质量较差，而邻区的信号质量较好，则终端设备可以切换到邻区。小区切换可以指终端设备在网络设备的控制下完成从源小区到目标小区的无线链路连接的迁移，是保证无缝的移动通信服务的基本技术手段。如何提高小区切换的效率是一个值得研究的问题。
发明内容
本申请实施例提供一种小区切换方法及装置，通过采用人工智能AI方式预测AI目标小区，提前与AI目标小区对应的目标基站进行交互，可在一定程度上提高小区切换的效率。
第一方面，提供一种小区切换方法，该方法的执行主体可以为第一网络设备，还可以为配置于第一网络设备中的部件(处理器、芯片、电路或其它)，或者可以为软件模块等，包括：确定AI目标小区，所述AI目标小区为预测的、终端设备可以切换到的服务小区；输出第一请求消息，所述第一请求消息用于请求所述AI目标小区对应的第二网络设备为所述终端设备分配所述AI目标小区对应的资源，所述第一请求消息用于指示以下至少一项：所述AI目标小区的标识信息、所述切换的类型为AI切换、激活时间信息、失效时间信息、或所述AI目标小区的预测准确度，所述激活时间信息用于指示所述终端设备切换到所述AI目标小区的最早时间，所述失效时间信息用于指示所述终端设备切换到所述AI目标小区的最晚时间。
采用上述方案，以第一网络设备为源基站，第二网络设备为目标基站，终端设备为UE为例。源基站在确定UE可以切换的服务小区之前，基于AI方式，预测UE可以切换到的服务小区，称为AI目标小区。源基站提前向AI目标小区对应的基站发送第一请求消息，以确定AI目标小区对应的基站是否同意源基站的请求。若AI目标小区对应的基站不同意源基站的请求，则源基站将不会再将该小区配置给UE，进行切换。采用本申请实施例的方法，源基站可以提前和预测的AI目标小区执行切换准备，在一定程度上避免额外的切换时延。
在一种设计中，所述AI目标小区为根据AI方式预测的，包括：所述AI目标小区是根据以下至少一项信息预测的，所述至少一项信息中包括：所述终端设备的第一测量信息、 服务小区的负载信息、相邻小区的负载信息、所述终端设备的轨迹信息、所述终端设备的地理坐标信息、所述终端设备的运动方向、或所述终端设备的运动速度。
在一种设计中，还包括：获取所述第二网络设备的第一响应消息，所述第一响应消息响应于所述第一请求消息，所述第一响应消息包括所述第二网络设备中允许所述终端设备进行AI切换的小区数量的指示信息。
采用上述设计，上述第一响应消息中可包括第二网络设备是否同意第一网络设备的请求的指示信息。例如，所述第一响应消息若指示ACK，代表第二网络设备同意第一网络设备的请求，若指示为NACK，代表第二网络设备不同意第一网络设备的请求。进一步的，若上述第一响应消息指示ACK时，还可进一步包括上述第二网络设备中允许所述终端设备进行AI切换的小区数据的指示信息等。该方法可以进一步对齐第一网络设备和第二网络设备的理解，降低通信错误的概率。
在一种设计中，还包括：获取所述第二网络设备的AI信息，所述AI信息用于指示以下至少一项：所述第二网络设备支持或不支持AI切换的指示信息、所述第二网络设备所支持AI的切换类型的指示信息、或所述第二网络设备允许进行AI切换的小区信息。
在一种设计中，还包括：向所述第二网络设备转移所述终端设备的用户面数据；输出第一状态转发消息，所述第一状态转发消息用于指示第一网络设备向所述第二网络设备转移的用户面数据中的第一个下行业务数据单元SDU的编号，和/或所述转移的用户面数据中可以丢弃的SDU的编号。
采用上述设计，第一网络设备可提前向第二网络设备转移用户面数据，减少由于切换引起的中断时间。
在一种设计中，还包括：确定切换所述终端设备到所述AI目标小区中的第一小区；输出第一配置消息，所述第一配置消息用于向所述终端设备指示所述第一小区的配置信息。
通过该设计，可以提高小区切换效率。
在一种设计中，还包括：确定切换所述终端设备到第二小区，所述AI目标小区中不包含所述第二小区；输出第二配置消息，所述第二配置消息用于向所述终端设备指示所述第二小区的配置信息和所述AI目标小区的配置信息。
通过该设计，可以提高小区切换效率。
在一种设计中，还包括：输出第三配置信息，所述第三配置信息用于向所述终端设备指示所述AI目标小区的配置信息和切换触发配置信息，所述切换触发配置信息用于向所述终端设备指示切换到所述AI目标小区的触发条件。
通过该设计，可以提高小区切换效率。
在一种设计中，还包括：确定更新所述AI目标小区的配置信息，和/或更新所述切换触发配置信息；
输出第四配置信息，所述第四配置信息用于向所述终端设备指示更新的AI目标小区的配置信息，和/或，更新的切换触发配置信息。
在一种设计中，所述AI目标小区的配置信息用于指示以下至少一项：所述AI目标小区的标识信息、随机接入信息、激活时间信息、或失效时间信息，所述随机接入信息用于指示所述终端设备切换到所述AI目标小区的随机接入资源，所述激活时间信息指示所述终端设备切换到所述AI目标小区的最早时间，所述失效时间信息指示所述终端设备切换到所述AI目标小区的最晚时间。
第二方面，提供一种小区切换方法，该方法的执行主体可为第二网络设备，还可以为配置为第二网络设备中的部件，或者可以为软件模块等，包括：获取第一网络设备的第一请求消息，所述第一请求消息用于请求人工智能AI目标小区对应的第二网络设备为终端设备分配所述AI目标小区对应的资源；其中，所述第一请求消息用于指示以下至少一项：所述AI目标小区的标识信息、所述切换的类型为AI切换、激活时间信息、失效时间信息、或所述AI目标小区的预测准确度，所述激活时间信息用于指示所述终端设备切换到所述AI目标小区的最早时间，所述失效时间信息用于指示所述终端设备切换到所述AI目标小区的最晚时间。
采用上述方案，将AI技术与移动性结合起来，使得基于AI的移动性机制预测，提前推理出合理的切换小区，提高切换准备的成功率，提升其鲁棒性；此外，引入AI目标小区的时间信息，可以尽可能少的占用AI目标基站的资源，提高资源利用率。
在一种设计中，所述AI目标小区是根据以下至少一项信息预测的，所述至少一项信息中包括：所述终端设备的第一测量信息、服务小区的负载信息、相邻小区的负载信息、所述终端设备的轨迹信息、所述终端设备的地理坐标信息、所述终端设备的运动方向、或所述终端设备的运动速度。
在一种设计中，还包括：输出第一响应消息，所述第一响应消息响应于所述第一请求消息，所述第一响应消息包括所述第二网络设备中允许所述终端设备进行AI切换的小区数量的指示信息。
在一种设计中，还包括：输出AI消息，所述AI信息用于指示以下至少一项：所述第二网络设备支持或不支持AI切换的指示信息、所述第二网络设备所支持AI的切换类型的指示信息、或所述第二网络设备允许进行AI切换的小区数量。
在一种设计中，还包括：获取所述第一网络设备转移的所述终端设备的用户面数据；获取所述第一网络设备的第一状态转发消息，所述第一状态转发消息用于指示第一网络设备向所述第二网络设备转移的用户面数据中的第一个下行业务数据单元SDU的编号，和/或所述转移的用户面数据中可以丢弃的SDU的编号。
第三方面，提供一种小区切换方法，该方法的执行主体可以为终端设备，还可以为配置为终端设备中的部件，或者可以为软件模块等，包括：获取第一网络设备的第二配置信息，所述第二配置信息用于向终端设备指示第二小区的配置信息和人工智能AI目标小区的配置信息；根据所述第二小区的配置信息，执行到所述第二小区的切换。
在一种设计中，还包括：当终端设备与所述第二小区的连接失败时，确定第一目标小区。
在一种设计中，若所述终端设备侧存储有有效的所述AI目标小区的配置信息，所述方法还包括：当所述第一目标小区为所述AI目标小区中的小区时，执行到所述第一目标小区的切换流程；或者，当所述第一目标小区不为所述AI目标小区中的小区时，执行到所述第一目标小区的重建流程。
采用上述设计，由于切换流程相对于重建流程，信令交互要简单许多，因此，在UE与第二小区的连接失败的过程中，若UE所选择的第一目标小区为预测的AI目标小区中的小区时，UE可以直接向第一目标小区发起切换流程，快速恢复连接，缩短数据传输中断时延，并减少信令开销。
在一种设计中，若所述终端设备侧未存储有有效的所述AI目标小区的配置信息，所 述方法还包括：执行到所述第一目标小区的重建流程。
第四方面，提供一种小区切换方法，该方法的执行主体可以为第一网络设备，还可以为配置于第一网络设备中的部件，或者可以为软件模块等，包括：输出第五配置信息，所述第五配置信息用于指示终端设备上报第一反馈信息的触发条件；获取所述终端设备的第一反馈信息；确定人工智能AI目标小区的更新结果，所述AI目标小区的更新结果是根据所述第一反馈信息确定的，所述AI目标小区的更新结果为更新的所述终端设备可以切换到的服务小区。
采用上述方案，将终端设备的反馈结果引入，更新AI目标小区的推理结果，可以保证AI推理结果的准确性。
在一种设计中，所述第五配置信息用于指示以下至少一项：至少一个小区的信息和质量门限信息、参考位置信息和第一距离门限信息、轨迹变更触发信息或时间上报指示信息，所述时间上报指示信息包括所述终端设备在所述第一反馈信息中携带或不携带时间信息的指示信息，所述时间信息为所述终端设备满足所述第五配置信息时的时间，或者所述终端设备上报所述第一反馈信息的时间。
在一种设计中，当所述第五配置信息用于指示至少一个小区的标识信息和质量门限信息时，所述第一反馈信息用于指示满足所述第五配置信息的小区的标识信息，和/或，满足所述第五配置信息的小区的质量信息，或者，所述第一反馈信息用于指示不满足所述第五配置信息的小区的标识信息，和/或，不满足所述第五配置信息的小区的质量信息；或者，
当所述第五配置信息用于指示参考位置信息和第一距离门限信息时，所述第一反馈信息用于指示所述终端设备最新的位置信息。
第五方面，提供一种小区切换方法，该方法的执行主体可以为终端设备，还可以为配置于终端设备中的部件，或者可以为软件模块等，包括：获取第一网络设备的第五配置信息，所述第五配置信息用于指示终端设备上报第一反馈信息的触发条件；输出第一反馈信息，所述第一反馈信息是在满足所述第五配置信息的触发条件时输出的，所述第一反馈信息用于更新人工智能AI目标小区，所述AI目标小区的更新结果为更新的所述终端设备可以切换到的服务小区。
通过上述方案，在满足条件时，终端设备可以向第一网络设备上报反馈信息，第一网络设备可以根据终端设备的反馈，更新AI目标小区的结果，可以保证AI推理结果的准确性和有效性。
在一种设计中，所述第五配置信息用于指示以下至少一项：至少一个小区的信息和质量门限信息、参考位置信息和第一距离门限信息、轨迹变更触发信息或时间上报指示信息，所述时间上报指示信息包括所述终端设备在所述第一反馈信息中携带或不携带时间信息的指示信息，所述时间信息为所述终端设备满足所述第五配置信息时的时间，或者所述终端设备上报所述第一反馈信息的时间。
在一种设计中，当所述第五配置信息用于指示至少一个小区的标识信息和质量门限信息时，所述第一反馈信息用于指示满足所述第五配置信息的小区的标识信息，和/或，满足所述第五配置信息的小区的质量信息，或者，所述第一反馈信息用于指示不满足所述第五配置信息的小区的标识信息，和/或，不满足所述第五配置信息的小区的质量信息；或者，
当所述第五配置信息用于指示参考位置信息和第一距离门限信息时，所述第一反馈信息用于指示所述终端设备最新的位置信息。
第六方面，提供一种装置，有益效果可参见第一方面的记载，该装置可以是第一网络设备，或者配置于第一网络设备中的装置，或者能够和第一网络设备匹配使用的装置。一种设计中，该装置包括执行第一方面中所描述的方法/操作/步骤/动作一一对应的单元，该单元可以是硬件电路，也可是软件，也可以是硬件电路结合软件实现。示例性地，该装置可以包括处理单元和通信单元，且处理单元和通信单元可以执行上述第一方面任一种设计示例中的相应功能，具体的：处理单元，用于确定AI目标小区，所述AI目标小区为根据AI方式预测的、终端设备可以切换到的服务小区；通信单元，用于输出第一请求消息，所述第一请求消息用于请求所述AI目标小区对应的第二网络设备为所述终端设备分配所述AI目标小区对应的资源，所述第一请求消息用于指示以下至少一项：所述AI目标小区的标识信息、所述切换的类型为AI切换、激活时间信息、失效时间信息、或所述AI目标小区的预测准确度，所述激活时间信息用于指示所述终端设备切换到所述AI目标小区的最早时间，所述失效时间信息用于指示所述终端设备切换到所述AI目标小区的最晚时间。上述处理单元和通信单元的具体执行过程可以参考第一方面，这里不再赘述。
第七方面，提供一种装置，有益效果可参见第一方面的记载，所述装置包括存储器，用于实现上述第一方面描述的方法。所述装置还可以包括存储器，用于存储指令和/或数据。所述存储器与所述处理器耦合，所述处理器执行所述存储器中存储的程序指令时，可以实现上述第一方面描述的方法。所述装置还可以包括通信接口，所述通信接口用于该装置和其它设备进行通信。示例性地，通信接口可以是收发器、电路、总线、模块、管脚或其它类型的通信接口，其它设备可以为第二网络设备或终端设备等。在一种可能的设计中，该装置包括：
存储器，用于存储程序指令；
处理器，用于确定AI目标小区，所述AI目标小区为根据AI方式预测的、终端设备可以切换到的服务小区。
通信接口，用于输出第一请求消息，所述第一请求消息用于请求所述AI目标小区对应的第二网络设备为所述终端设备分配所述AI目标小区对应的资源，所述第一请求消息用于指示以下至少一项：所述AI目标小区的标识信息、所述切换的类型为AI切换、激活时间信息、失效时间信息、或所述AI目标小区的预测准确度，所述激活时间信息用于指示所述终端设备切换到所述AI目标小区的最早时间，所述失效时间信息用于指示所述终端设备切换到所述AI目标小区的最晚时间。关于通信接口与处理器的具体执行过程，可参见上述第一方面的记载，不再赘述。
第八方面，提供一种装置，有益效果可参见第二方面的记载，该装置可以是第二网络设备，或者配置于第二网络设备中的装置，或者能够和第二网络设备匹配使用的装置。一种设计中，该装置包括执行第二方面中所描述的方法/操作/步骤/动作一一对应的单元，该单元可以是硬件电路，也可是软件，也可以是硬件电路结合软件实现。示例性地，该装置可以包括处理单元和通信单元，且处理单元和通信单元可以执行上述第二方面任一种设计示例中的相应功能，具体的：通信单元，用于获取第一网络设备的第一请求消息，所述第一请求消息用于请求人工智能AI目标小区对应的第二网络设备为终端设备分配所述AI目标小区对应的资源；其中，所述第一请求消息用于指示以下至少一项：所述AI目标小区的标识信息、所述切换的类型为AI切换、激活时间信息、失效时间信息、或所述AI目标小区的预测准确度，所述激活时间信息用于指示所述终端设备切换到所述AI目标小区的 最早时间，所述失效时间信息用于指示所述终端设备切换到所述AI目标小区的最晚时间。处理单元，用于对第一请求消息进行处理。上述处理单元和通信单元的具体执行过程可以参考第二方面，这里不再赘述。
第九方面，提供一种装置，有益效果可参见第二方面的记载，所述装置包括存储器，用于实现上述第二方面描述的方法。所述装置还可以包括存储器，用于存储指令和/或数据。所述存储器与所述处理器耦合，所述处理器执行所述存储器中存储的程序指令时，可以实现上述第二方面描述的方法。所述装置还可以包括通信接口，所述通信接口用于该装置和其它设备进行通信。示例性地，通信接口可以是收发器、电路、总线、模块、管脚或其它类型的通信接口，其它设备可以为第一网络设备或终端设备等。在一种可能的设计中，该装置包括：
存储器，用于存储程序指令；
通信接口，用于获取第一网络设备的第一请求消息，所述第一请求消息用于请求人工智能AI目标小区对应的第二网络设备为终端设备分配所述AI目标小区对应的资源；其中，所述第一请求消息用于指示以下至少一项：所述AI目标小区的标识信息、所述切换的类型为AI切换、激活时间信息、失效时间信息、或所述AI目标小区的预测准确度，所述激活时间信息用于指示所述终端设备切换到所述AI目标小区的最早时间，所述失效时间信息用于指示所述终端设备切换到所述AI目标小区的最晚时间。
处理器，用于对第一请求消息进行处理。
关于通信接口与处理器的具体执行过程，可参见上述第二方面的记载，不再赘述。
第十方面，提供一种装置，有益效果可参见第三方面的记载，该装置可以是终端设备，或者配置于终端设备中的装置，或者能够和终端设备匹配使用的装置。一种设计中，该装置包括执行第三方面中所描述的方法/操作/步骤/动作一一对应的单元，该单元可以是硬件电路，也可是软件，也可以是硬件电路结合软件实现。示例性地，该装置可以包括处理单元和通信单元，且处理单元和通信单元可以执行上述第三方面任一种设计示例中的相应功能，具体的：通信单元，用于获取第一网络设备的第二配置信息，所述第二配置信息用于向终端设备指示第二小区的配置信息和人工智能AI目标小区的配置信息；处理单元，用于根据所述第二小区的配置信息，执行到所述第二小区的切换。上述处理单元和通信单元的具体执行过程可以参考第三方面，这里不再赘述。
第十一方面，提供一种装置，有益效果可参见第三方面的记载，所述装置包括存储器，用于实现上述第三方面描述的方法。所述装置还可以包括存储器，用于存储指令和/或数据。所述存储器与所述处理器耦合，所述处理器执行所述存储器中存储的程序指令时，可以实现上述第三方面描述的方法。所述装置还可以包括通信接口，所述通信接口用于该装置和其它设备进行通信。示例性地，通信接口可以是收发器、电路、总线、模块、管脚或其它类型的通信接口，其它设备可以为第一网络设备或第二网络设备等。在一种可能的设计中，该装置包括：
存储器，用于存储程序指令；
通信接口，用于获取第一网络设备的第二配置信息，所述第二配置信息用于向终端设备指示第二小区的配置信息和人工智能AI目标小区的配置信息；
处理器，用于根据所述第二小区的配置信息，执行到所述第二小区的切换。
关于通信接口与处理器的具体执行过程，可参见上述第三方面的记载，不再赘述。
第十二方面，提供一种装置，有益效果可参见第四方面的记载，该装置可以是第一网络设备，或者配置于第一网络设备中的装置，或者能够和第一网络设备匹配使用的装置。一种设计中，该装置包括执行第四方面中所描述的方法/操作/步骤/动作一一对应的单元，该单元可以是硬件电路，也可是软件，也可以是硬件电路结合软件实现。示例性地，该装置可以包括处理单元和通信单元，且处理单元和通信单元可以执行上述第四方面任一种设计示例中的相应功能，具体的：通信单元，用于输出第五配置信息，所述第五配置信息用于指示终端设备上报第一反馈信息的触发条件；通信单元，还用于获取所述终端设备的第一反馈信息；处理单元，用于确定人工智能AI目标小区的更新结果，所述AI目标小区的更新结果是根据所述第一反馈信息确定的，所述AI目标小区的更新结果为更新的所述终端设备可以切换到的服务小区。上述处理单元和通信单元的具体执行过程可以参考第四方面，这里不再赘述。
第十三方面，提供一种装置，有益效果可参见第四方面的记载，所述装置包括存储器，用于实现上述第四方面描述的方法。所述装置还可以包括存储器，用于存储指令和/或数据。所述存储器与所述处理器耦合，所述处理器执行所述存储器中存储的程序指令时，可以实现上述第四方面描述的方法。所述装置还可以包括通信接口，所述通信接口用于该装置和其它设备进行通信。示例性地，通信接口可以是收发器、电路、总线、模块、管脚或其它类型的通信接口，其它设备可以为第二网络设备或终端设备等。在一种可能的设计中，该装置包括：
存储器，用于存储程序指令；
通信接口，用于输出第五配置信息，所述第五配置信息用于指示终端设备上报第一反馈信息的触发条件，获取所述终端设备的第一反馈信息；
处理器，用于确定人工智能AI目标小区的更新结果，所述AI目标小区的更新结果是根据所述第一反馈信息确定的，所述AI目标小区的更新结果为更新的所述终端设备可以切换到的服务小区。关于通信接口与处理器的具体执行过程，可参见上述第四方面的记载，不再赘述。
第十四方面，提供一种装置，有益效果可参见第五方面的记载，该装置可以是终端设备，或者配置于终端设备中的装置，或者能够和终端设备匹配使用的装置。一种设计中，该装置包括执行第五方面中所描述的方法/操作/步骤/动作一一对应的单元，该单元可以是硬件电路，也可是软件，也可以是硬件电路结合软件实现。示例性地，该装置可以包括处理单元和通信单元，且处理单元和通信单元可以执行上述第五方面任一种设计示例中的相应功能，具体的：
通信单元，用于获取第一网络设备的第五配置信息，所述第五配置信息用于指示终端设备上报第一反馈信息的触发条件；处理单元，用于根据第五配置信息，确定第一反馈信息；通信单元，还用于输出第一反馈信息，所述第一反馈信息是在满足所述第五配置信息的触发条件时输出的，所述第一反馈信息用于更新人工智能AI目标小区，所述AI目标小区的更新结果为更新的所述终端设备可以切换到的服务小区。上述处理单元和通信单元的具体执行过程可以参考第五方面，这里不再赘述。
第十五方面，提供一种装置，有益效果可参见第五方面的记载，所述装置包括存储器，用于实现上述第五方面描述的方法。所述装置还可以包括存储器，用于存储指令和/或数据。所述存储器与所述处理器耦合，所述处理器执行所述存储器中存储的程序指令时，可以实 现上述第五方面描述的方法。所述装置还可以包括通信接口，所述通信接口用于该装置和其它设备进行通信。示例性地，通信接口可以是收发器、电路、总线、模块、管脚或其它类型的通信接口，其它设备可以为第一网络设备或第二网络设备等。在一种可能的设计中，该装置包括：
存储器，用于存储程序指令；
通信接口，用于获取第一网络设备的第五配置信息，所述第五配置信息用于指示终端设备上报第一反馈信息的触发条件；
处理器，用于根据第五配置信息，确定第一反馈信息；
通信接口，还用于输出第一反馈信息，所述第一反馈信息是在满足所述第五配置信息的触发条件时输出的，所述第一反馈信息用于更新人工智能AI目标小区，所述AI目标小区的更新结果为更新的所述终端设备可以切换到的服务小区。
关于通信接口与处理器的具体执行过程，可参见上述第五方面的记载，不再赘述。
第十六方面，本申请实施例还提供一种计算机可读存储介质，包括指令，当其在计算机上运行时，使得计算机执行第一方面至第五方面任一方面的方法。
第十七方面，本申请实施例还提供一种芯片系统，该芯片系统包括处理器，还可以包括存储器，用于实现第一方面至第五方面任一方面的方法。该芯片系统可以由芯片构成，也可以包含芯片和其他分立器件。
第十八方面，本申请实施例中还提供一种计算机程序产品，包括指令，当其在计算机上运行时，使得计算机执行第一方面至第五方面任一方面的方法。
第十九方面，本申请实施例中还提供一种系统，该系统中包括第六方面或第七方面的装置，和第八方面或第九方面的装置。可选的，该系统还可以包括第十方面或第十一方面的装置；或者，该系统中包括第十二方面或第十三方面的装置，和第十四方面或第十五方面的装置。
附图说明
图1为本申请实施例提供的网络架构的示意图；
图2a，图2b，图2c和图2d为本申请实施例提供的协议栈的示意图；
图3a，图3b，图3c和图3d为本申请实施例提供的AI模型的示意图；
图4为本申请实施例一提供的小区切换的一流程图；
图5为本申请实施例一提供的小区切换的另一流程图；
图6为本申请实施例二提供的小区切换的一流程图；
图7为本申请实施例二提供的小区切换的另一流程图；
图8为本申请实施例三提供的小区切换的流程图；
图9为本申请实施例提供的装置的结构示意图；
图10为本申请实施例提供的终端设备的结构示意图；
图11为本申请实施例提供的网络设备的结构示意图。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行描述。
图1为本申请实施例适用的一种网络架构示意图。如图1所示，终端设备(比如终端设备1301或终端设备1302)可接入到无线网络，以通过无线网络获取外网(例如因特网)的服务，或者通过无线网络与其它设备通信，如可以与其它终端设备通信。该无线网络包括无线接入网(radio access network，RAN)和核心网(core network，CN)，其中，RAN用于将终端设备接入到无线网络，CN用于对终端设备进行管理并提供与外网通信的网关。
下面分别对图1所涉及的终端设备、RAN和CN进行详细说明。
一、终端设备
终端设备可以简称为终端，是一种具有无线收发功能的设备。终端设备可以是移动的，或固定的。终端设备可以部署在陆地上，包括室内或室外，手持或车载；也可以部署在水面上(如轮船等)；还可以部署在空中(例如飞机、气球和卫星上等)。所述终端设备可以是手机(mobile phone)、平板电脑(pad)、带无线收发功能的电脑、虚拟现实(virtual reality，VR)终端设备、增强现实(augmented reality，AR)终端设备、工业控制(industrial control)中的无线终端设备、无人驾驶(self driving)中的无线终端设备、远程医疗(remote medical)中的无线终端设备、智能电网(smart grid)中的无线终端设备、运输安全(transportation safety)中的无线终端设备、智慧城市(smart city)中的无线终端设备、和/或智慧家庭(smart home)中的无线终端设备。终端设备还可以是蜂窝电话、无绳电话、会话启动协议(session initiation protocol，SIP)电话、无线本地环路(wireless local loop，WLL)站、个人数字助理(personal digital assistant，PDA)、具有无线通信功能的手持设备或计算设备、车载设备、可穿戴设备，未来第五代(the 5th generation，5G)网络中的终端设备或者未来演进的公用陆地移动通信网络(public land mobile network，PLMN)中的终端设备等。终端设备有时也可以称为用户设备(user equipment，UE)。可选的，终端设备可以与不同技术的多个接入网设备进行通信，例如，终端设备可以与支持长期演进(long term evolution，LTE)的接入网设备通信，也可以与支持5G的接入网设备通信，又可以与支持LTE的接入网设备以及支持5G的接入网设备的双连接。本申请实施例并不限定。
本申请实施例中，用于实现终端设备的功能的装置可以是终端设备；也可以是能够支持终端设备实现该功能的装置，例如芯片系统、硬件电路、软件模块、或硬件电路加软件模块，该装置可以被安装在终端设备中或可以与终端设备匹配使用。本申请实施例提供的技术方案中，以用于实现终端设备的功能的装置是终端设备，终端设备是UE为例，描述本申请实施例提供的技术方案。
二、RAN
RAN可以包括一个或多个RAN设备，比如RAN设备1001、RAN设备1002。RAN设备与终端设备之间的接口可以为Uu接口(或称为空口)。当然，在未来通信中，这些接口的名称可以不变，或者也可以用其它名称代替，本申请对此不作限定。
RAN设备为将终端设备接入到无线网络的节点或设备，RAN设备又可以称为网络设备或基站。RAN设备例如包括但不限于：基站、5G中的下一代节点B(generation nodeB，gNB)、演进型节点B(evolved node B，eNB)、无线网络控制器(radio network controller，RNC)、节点B(node B，NB)、基站控制器(base station controller，BSC)、基站收发台(base transceiver station，BTS)、家庭基站(例如，home evolved nodeB，或home node B，HNB)、基带单元(base band unit，BBU)、收发点(transmitting and receiving point，TRP)、发射点(transmitting point，TP)、和/或移动交换中心等。或者，接入网设备还可以是云无线接入网 络(cloud radio access network，CRAN)场景下的无线控制器、集中单元(centralized unit，CU)、分布单元(distributed unit,DU)、集中单元控制面(CU control plane，CU-CP)节点、集中单元用户面(CU user plane，CU-UP)节点、或接入回传一体化(integrated access and backhaul，IAB)等中的至少一个。或者，接入网设备可以为中继站、接入点、车载设备、终端设备、可穿戴设备、未来5G网络中的接入网设备或者未来演进的公共陆地移动网络(public land mobile network，PLMN)中的接入网设备等。
本申请实施例中，用于实现接入网设备的功能的装置可以是接入网设备；也可以是能够支持接入网设备实现该功能的装置，例如芯片系统、硬件电路、软件模块、或硬件电路加软件模块，该装置可以被安装在接入网设备中或可以与接入网设备匹配使用。本申请实施例中，芯片系统可以由芯片构成，也可以包括芯片和其他分立器件。在本申请实施例提供的技术方案中，以用于实现接入网设备的功能的装置是接入网设备，接入网设备是基站为例，描述本申请实施例提供的技术方案。
(1)协议层结构
RAN设备和终端设备之间的通信遵循一定的协议层结构。该协议层结构可以包括控制面协议层结构和用户面协议层结构。例如，控制面协议层结构可以包括无线资源控制(radio resource control，RRC)层、分组数据汇聚层协议(packet data convergence protocol，PDCP)层、无线链路控制(radio link control，RLC)层、媒体接入控制(media access control，MAC)层和物理层等协议层的功能。例如，用户面协议层结构可以包括PDCP层、RLC层、MAC层和物理层等协议层的功能，在一种可能的实现中，PDCP层之上还可以包括业务数据适配协议(service data adaptation protocol，SDAP)层。
以网络设备和终端设备之间的数据传输为例，数据传输需要经过用户面协议层，比如经过SDAP层、PDCP层、RLC层、MAC层、物理层。其中，SDAP层、PDCP层、RLC层、MAC层和物理层也可以统称为接入层。根据数据的传输方向分为发送或接收，上述每层又分为发送部分和接收部分。以下行数据传输为例，参见图2a所示为下行数据在各层间传输示意图，图2a中向下的箭头表示数据发送，向上的箭头表示数据接收。PDCP层自上层取得数据后，将数据传送到RLC层与MAC层，再由MAC层生成传输块，然后通过物理层进行无线传输。数据在各个层中进行相对应的封装。例如，某一层从该层的上层收到的数据视为该层的服务数据单元(service data unit，SDU)，经过该层封装后成为协议数据单元(protocol data unit，PDU)，再传递给下一个层。
示例性的，根据图2a还可以看出，终端设备还具有应用层和非接入层。其中，应用层可以用于向终端设备中所安装的应用程序提供服务，比如，终端设备接收到的下行数据可以由物理层依次传输到应用层，进而由应用层提供给应用程序；又比如，应用层可以获取应用程序产生的数据，并将数据依次传输到物理层，发送给其它通信装置。非接入层可以用于转发用户数据，比如将从应用层接收到的上行数据转发给SDAP层或者将从SDAP层接收到的下行数据转发给应用层。
(2)集中式单元(central unit，CU)和分布式单元(distributed unit，DU)
本申请实施例中，RAN设备可以包括CU和DU，多个DU可以由一个CU集中控制。作为示例，CU和DU之间的接口可以称为F1接口。其中，控制面(control panel，CP)接口可以为F1-C，用户面(user panel，UP)接口可以为F1-U。CU和DU可以根据无线网络的协议层划分：比如图2b所示，PDCP层及以上协议层的功能设置在CU，PDCP层 以下协议层(例如RLC层和MAC层等)的功能设置在DU；又比如图2c所示，PDCP层以上协议层的功能设置在CU，PDCP层及以下协议层的功能设置在DU。
可以理解的是，上述对CU和DU的处理功能按照协议层的划分仅仅是一种举例，也可以按照其他的方式进行划分，例如可以将CU或者DU划分为具有更多协议层的功能，又例如将CU或DU还可以划分为具有协议层的部分处理功能。在一种设计中，将RLC层的部分功能和RLC层以上的协议层的功能设置在CU，将RLC层的剩余功能和RLC层以下的协议层的功能设置在DU。在另一种设计中，还可以按照业务类型或者其他系统需求对CU或者DU的功能进行划分，例如按时延划分，将处理时间需要满足时延要求的功能设置在DU，不需要满足该时延要求的功能设置在CU。在另一种设计中，CU也可以具有核心网的一个或多个功能。示例性的，CU可以设置在网络侧方便集中管理；DU具有多个射频功能，也可以将射频功能拉远设置。本申请实施例对此不作限定。
可选的，DU和射频装置可以在物理层(physical layer，PHY)进行划分。例如，DU可以实现PHY层中的高层功能，射频装置可以实现PHY层中的低层功能。其中，用于发送时，PHY层的功能可以包括添加循环冗余校验(cyclic redundancy check，CRC)码、信道编码、速率匹配、加扰、调制、层映射、预编码、资源映射、物理天线映射、和/或射频发送功能。用于接收时，PHY层的功能可以包括CRC、信道解码、解速率匹配、解扰、解调、解层映射、信道检测、资源解映射、物理天线解映射、和/或射频接收功能。其中，PHY层中的高层功能可以包括PHY层的一部分功能，例如该部分功能更加靠近MAC层，PHY层中的低层功能可以包括PHY层的另一部分功能，例如该部分功能更加靠近射频功能。例如，PHY层中的高层功能可以包括添加CRC码、信道编码、速率匹配、加扰、调制、和层映射，PHY层中的低层功能可以包括预编码、资源映射、物理天线映射、和射频发送功能；或者，PHY层中的高层功能可以包括添加CRC码、信道编码、速率匹配、加扰、调制、层映射和预编码，PHY层中的低层功能可以包括资源映射、物理天线映射、和射频发送功能。
可选的，射频装置还可以称为无线装置。
示例性的，CU的功能可以由一个实体来实现，或者也可以由不同的实体来实现。例如，如图2d所示，可以对CU的功能进行进一步划分，即将控制面和用户面分离并通过不同实体来实现，分别为控制面CU实体(即CU-CP实体)和用户面CU实体(即CU-UP实体)。该CU-CP实体和CU-UP实体可以与DU相耦合，共同完成RAN设备的功能。
需要说明的是：在上述图2b至图2d所示意的架构中，CU产生的信令可以通过DU发送给终端设备，或者终端设备产生的信令可以通过DU发送给CU。DU可以不对该信令进行解析而直接通过协议层封装后透传给终端设备或CU。以下实施例中如果涉及这种信令在DU和终端设备之间的传输，此时，DU对信令的发送或接收包括这种场景。例如，RRC或PDCP层的信令最终会处理为物理层的信令发送给终端设备，或者，由接收到的物理层的信令转变而来。在这种架构下，该RRC或PDCP层的信令，即可以认为是由DU发送的，或者，由DU和射频装置发送的。
可选的，上述DU、CU、CU-CP、CU-UP和射频装置中的任一个可以是软件模块、硬件结构、或者软件模块+硬件结构，不予限制。其中，不同实体的存在形式可以是不同的，不予限制。例如DU、CU、CU-CP、CU-UP是软件模块，射频装置是硬件结构。这些模块及其执行的方法也在本申请实施例的保护范围内。
三、CN
CN中可以包括一个或多个CN设备，例如，CN设备120。以第五代(the 5 th generation，5G)通信系统为例，CN中可以包括接入和移动性管理功能(access and mobility management function，AMF)网元、会话管理功能(session management function，SMF)网元、用户面功能(user plane function，UPF)网元、策略控制功能(policy control function，PCF)网元、统一数据管理(unified data management，UDM)网元、和应用功能(application function，AF)网元等。
在本申请实施例中，用于实现核心网设备的功能的装置可以是核心网设备；也可以是能够支持核心网设备实现该功能的装置，例如芯片系统、硬件电路、软件模块、或硬件电路加软件模块，该装置可以被安装在核心网设备中或可以与核心网设备匹配使用。在本申请实施例提供的技术方案中，以用于实现核心网设备的功能的装置是核心网设备为例，描述本申请实施例提供的技术方案。
应理解，图1所示的通信系统中各个设备的数量仅作为示意，本申请实施例并不限于此，实际应用中在通信系统中还可以包括更多的终端设备、更多的RAN设备，还可以包括其它设备。
上述图1所示的网络架构可以适用于各种无线接入技术(radio access technology，RAT)的通信系统中，例如可以是4G(或者称为LTE)通信系统，也可以是5G(或者称为新无线(new radio，NR))通信系统，也可以是LTE通信系统与5G通信系统之间的过渡系统，该过渡系统也可以称为4.5G通信系统，当然也可以是未来的通信系统中，例如6G通信系统。本申请实施例描述的网络架构以及业务场景是为了更加清楚的说明本申请实施例的技术方案，并不构成对于本申请实施例提供的技术方案的限定，本领域普通技术人员可知，随着通信网络架构的演变和新业务场景的出现，本申请实施例提供的技术方案对于类似的技术问题，同样适用。
在无线通信系统中，UE可以切换服务小区。在以下描述中，可以将UE当前服务小区所属的基站称为源基站，将UE待切换至的服务小区所属的基站称为目标基站。UE切换服务小区的机制主要包括两种：一种是基站触发。源基站发送切换命令给UE，UE根据切换命令中的目标小区的配置信息执行到目标小区的切换。其中，UE可以向源基站发送测量报告，该测量报告中可包括服务小区和/或邻区的质量信息等。源基站可以确定切换策略，比如根据UE上报的信息和小区负载等信息确定切换策略，并通过切换命令将该切换策略指示给UE。另一种是UE触发。UE从一个或多个候选小区中选择目标小区，并执行到目标小区的切换。例如，源基站通过切换命令给UE配置一个或多个候选小区，上述一个或多个候选小区配置有对应的触发条件。当UE确定满足触发条件时，UE可以将该触发条件对应的候选小区，作为目标小区，UE执行到目标小区的切换。
无论上述哪一种切换方式，源基站近实时地决定切换策略或候选小区，可能会出现所确定的切换策略或候选小区的准确性较差的问题，从而带来额外的切换时延。以基站触发为例，当源基站为UE确定目标小区(例如某个指标最优或者某些指标综合最优的目标小区)后，首先由源基站向目标小区所属的目标基站发送切换请求，目标基站同意后，源基站才会将目标小区配置给UE。而当源基站向目标基站发送切换请求时，有可能目标小区的负载过多或者容量有限或者管理策略等原因，该目标基站会拒绝来自源 基站的切换请求。源基站不得不为UE重新选择新的目标小区，并向新的目标小区所属的目标基站发起切换请求，这样带来了额外的切换时延。进一步，额外的切换时延，还有可能造成UE在源基站的连接失败。例如，UE处于移动状态，而随着UE移动与源基站的连接越来越弱，UE长时间未切换到新的服务小区，会导致UE与源基站的连接失败。
本申请实施例提供一种小区切换方法，该方法可以在一种程度上解决上述额外的切换时延等问题。该方法包括：源基站在确定UE可以切换的服务小区之前，基于人工智能(artificial intelligence，AI)，预测UE可以切换到的服务小区，称为AI目标小区。源基站提前向AI目标小区对应的基站发送第一请求消息，以确定AI目标小区对应的基站是否同意源基站的请求。若AI目标小区对应的基站不同意源基站的请求，则源基站将不会再将该小区配置给UE，进行切换。采用本申请实施例的方法，源基站可以提前和预测的AI目标小区执行切换准备，在一定程度上避免额外的切换时延。
由于本申请实施例涉及利用AI技术，预测UE可以切换到的服务小区的过程，为了便于理解，首先对AI技术进行介绍。可以理解的是，该介绍并不作为对本申请实施例的限定。
AI，是一种通过模拟人脑进行复杂计算的技术。随着数据存储和能力的能升，AI得到了越来越多的应用。第三代合作伙伴计划(3 rd generation partnership project，3GPP)的版本17(release17，R17)通过了研究项目(study item，SI)，提出了将AI运用到NR中。如图3a所示为AI在NR中的第一种应用框架的示例图：
数据源(data source)用于存储训练数据和推理数据。模型训练节点(model trainning host)通过对数据源提供的训练数据(training data)进行分析或训练，得到AI模型，且将AI模型部署在模型推理节点(model inference host)中。模型推理节点使用AI模型，基于数据源提供的推理数据进行推理，得到推理结果。该推理结果用于对网络运行给出基于AI的合理预测，或者指导网络做出策略配置或策略调整。相关的策略配置或者策略调整，由执行(actor)实体统一规划，并发送给多个执行对象(例如，网络实体)去执行。同时，应用了相关策略后，网络的具体表现，可以被再次输入到数据源存储起来。
如图3b、图3c或图3d所示为AI在NR中的第二种应用框架的示例图：
独立于基站的第一AI模块接收训练数据。第一AI模块通过对训练数据进行分析或训练，得到AI模型。针对某个参数，可以是第一AI模块利用相应的AI模型和推理数据进行推理，得到该参数，可参见图3b；或者可以是由第一AI模块将该AI模型的信息发送给位于基站中(或描述为位于RAN中)的第二AI模块，由第二AI模块利用相应的AI模型和推理数据进行推理，得到该参数，可参见图3c。或者，第二AI模块用于推理的AI模型也可以是第二AI模块接收训练数据，并通过对该训练数据进行训练得到的，可参见图3d。
需要说明的是，在上述图3a至图3d中的框架中，AI模型可以简称为模型，其可以看做是从输入的测量量(测量信息)到输出的参数之间的映射。输入的测量量可以是一个或多个测量量，输出的参数可以是一个或多个参数。训练数据可以包括已知的输入测量量，或包括已知的输入测量量和对应的输出参数，用于训练AI模型。训练数据可以是来自基站、CU、CU-CP、CU-UP、DU、射频模块、UE和/或其它实体的数据， 和/或是通过AI技术推理出的数据，不予限制。推理数据包括输入测量量，用于利用模型推理出参数。推理数据可以是来自基站、CU、CU-CP、CU-UP、DU、射频模块、UE和/或其它实体的数据。推理出的参数可以看做策略信息，发送给执行对象。推理出的参数可以被发送给基站、CU、CU-CP、CU-UP、DU、射频模块、或UE等，用于进行策略配置或策略调整。用于推理不同参数的AI模型可以是相同的，也可以是不同的，不予限制。
可以理解的，本申请实施例中，UE和/或基站可以执行本申请实施例中的部分或全部步骤，这些步骤或操作仅是示例，本申请实施例还可以执行其它操作或者各种操作的变形。此外，各个步骤可以按照本申请实施例呈现的不同的顺序来执行，并且有可能并非要执行本申请实施例中的全部操作。
在本申请的各个实施例中，如果没有特殊说明以及逻辑冲突，不同的实施例之间的术语和/或描述具有一致性、且可以相互引用，不同的实施例中的技术特征根据其内在的逻辑关系可以组合形成新的实施例。
实施例一
本申请实施例一提供一种小区切换方法，包括：源基站确定AI目标小区，所述AI目标小区还可以称为第一小区，预测小区，或潜在小区等，不作限定。无论采用何用名称，上述源基站所确定的小区为预测的或者是根据AI技术推理出的、UE可以切换到的服务小区。后续，以AI目标小区为例描述。源基站输出第一请求消息，所述第一请求消息用于请求AI目标小区对应的目标基站为UE分配AI目标小区对应的资源。可选的，还包括：源基站获取目标基站的第一响应消息，第一响应消息响应于第一请求消息。关于源基站确定AI目标小区的过程，可以作如下说明：
在一种设计中，单独布署AI设备，该AI设备称为远程智能通信、无线智能控制器、AI节点或其它等，不作限定。在一种可能的实现中，上述AI设备可包括上述图3a所示的数据源、模型训练节点或模型推理节点等中的至少一项。在另一种可能的实现中，该AI设备可以包括上述图3b、图3c、或图3d中的第一AI模块和/或第二AI模块等。示例的，AI设备可以基于AI模型，推理UE可以切换到的AI目标小区。源基站可以获取来自AI设备的第一消息，该第一消息至少用于指示AI目标小区。可选的，该第一消息还可以用于指示以下至少一项：源基站可以执行的AI切换类型、激活时间信息、失效时间信息、或AI目标小区的预测准确度等信息的至少一项种。关于激活时间信息、和失效时间信息以及AI切换类型可参见下述说明。可以理解的，上述激活时间信息、失效时间信息可以是第一消息直接指示的，也可以是通过第一消息的信息进行一定的计算确定的，比如第一消息指示了激活时间信息和有效时长信息，通过激活时间信息和有效时长信息可以确定失效时间信息，此时也可以理解为第一消息用于指示激活时间信息和失效时间信息。
进一步，可选的，在源基站在获取来自AI设备的第一消息之前，源基站与AI设备间还可以进行交互。例如，AI设备向源基站发送第一指示信息，该第一指示信息用于指示AI设备所支持的AI切换类型，和/或，AI设备的AI预测信息的准确度等。源基站向AI设备发送第二指示信息，该第二指示信息用于指示源基站所支持的AI切换类型、支持的AI目标小区的数量等信息的至少一种。
在另一种设计中，AI模块的功能可以集成于源基站中，源基站可以利用AI方式，推理UE可以切换的服务小区，即AI目标小区等。
在上述两种设计中，源基站在确定上述AI目标小区后，源基站可以向AI目标小区所属的目标基站发送第一请求消息，以请求目标基站为UE分配接入AI目标小区对应的资源。可选的，目标基站在接收到上述第一请求消息时，可以向源基站发送响应于第一请求消息的第一响应消息。例如，该第一响应消息用于指示目标基站是否同意源基站的请求等。
如图4所示，提供一种小区切换方法的流程，在该流程中，以源基站进行AI推理，确定AI目标小区为例描述，至少包括：
步骤400：UE向源基站上报第一测量信息。在一种设计中，UE可以向源基站上报第一测量报告，该测量报告中携带有第一测量信息。该步骤400是可选的。
示例性的，上述第一测量信息中包括小区的标识信息和小区的质量信息等。所述小区可以为服务小区和/或邻区等，不作限定。在一种设计中，UE可以周期性向源基站上报第一测量信息。例如，UE可以周期性测量服务小区的质量信息和/或邻区的质量信息，然后周期性的向源基站上报所测量的信息。或者，UE可以周期性测量服务小区的质量信息和/或邻区的质量信息，在满足一定的条件时，再向源基站上报所测量的信息等。
1、第一测量信息中包括的小区标识信息
在本申请实施例中，所述小区的标识信息可以包括小区的小区全局标识(cell global identifier，CGI)、物理小区标识(physical cell identifier，PCI)和频点、小区标识(cell identifier，cell ID)、非公网标识(non-public network identifier,NPN ID)、非陆地网络标识(non-terrestrial network identifier,NTN ID)或者其它小区标识等中的至少一种。其中，CGI可以包括公共陆地移动网络(public land mobile network，PLMN ID)和cell ID等。可选的，小区的标识信息中还可以包括跟踪区码(tracking area code，TAC)和/或小区所属的网络设备的标识信息，比如全局网络设备标识等。
应当指出，在本申请的描述中，小区的标识信息可以是UE接入的小区对应的小区的标识。其中，UE接入的小区还可以称为UE的当前服务小区。考虑到一个小区可能同时被多个运营商共享的情况，不同的运营商可能为同一个小区分配不同的标识，小区的标识也可以是UE接入的小区所属的基站发送的至少一个小区的标识中的第一个小区的标识。例如，一个小区同时被多个运营商的网络共享，不同的运营商可能为该小区分配不同的标识，该小区会向UE发送多个小区的标识。本申请实施例中的小区的标识，可以指UE接入的小区发送的多个标识中的第一个小区的标识。举例来说，UE接入的小区同时被两个运营商共享，该两个运营商为该小区分配的小区的标识分别为PLMN1+CELL ID1，和PLMN2+CELL ID2。若上述小区的标识在发送的小区信息列表中的顺序为{LMN1+CELL ID1，PLMN2+CELL ID2}，本申请实施例中的小区的标识可以具体指PLMN1+CELL ID1。
2、第一测量信息中包括的小区的质量信息
在本申请实施例中，UE可以通过测量下行同步信道、信道状态信息参考信号、解调参考信号(demodulation reference signal，DMRS)、小区参考信号(cell-specific reference signal，CRS)信号、同步信号块(synchronization signal block，SSB)、同步信号/物理广播信道块或者其它下行信号中的至少一种，获得小区的质量信息。示例的，所述小区的质量信息可以包括接收信号码功率(received signal code power，RSCP)、参考信号接收功率(reference  signal receiving power，RSRP)、参考信号接收质量(reference signal receiving quality，RSRQ)、信噪比(signal noise ratio，SNR)、信号与干扰加噪声比(signal to interference plus noise ratio，SINR)、参考信号强度指示(reference signal strength indication，RSSI)或其它信号质量中的至少一种。
可选的，小区质量信息可以是小区级的，波束级的，同步信号/物理广播信道块(synchronization signal/physical broadcast channel block，SS/PBCH Block)级的，信道状态信息参考信号(channel-state information reference signal，CSI-RS)级的，空口技术(numerology)级的，切片(slicing)级的，或带宽部分(bandwidth part，BWP)级的至少一种。关于小区质量信息是何种级的，是指该小区的质量信息是以何种粒度测量的。比如，小区的质量信息是小区级的，是指UE对待测量的多个小区中的每个小区进行测量，得到各小区的质量。或者，小区的质量是波束级的，是指该小区包括至少一个波束，UE通过对该小区中的波束进行测量，获得的小区质量信息。例如，一小区包括3个波束，UE可对通过对上述3个波束中的波束1，波束2和波束3分别进行测量，得到满足波束质量条件的波束1的质量信息和波束2的质量信息。可选的，之后，UE可基于波束1的质量信息和波束2的质量信息，例如取较大值、求平均或者加权求和等，得到该小区的质量信息。或者，UE可以同时上报波束1的质量信息和波束2的质量信息。关于UE基于其它粒度测量小区的质量信息，与上述相似，不再说明。
需要说明的是，若小区质量信息为波束级的，同步信号/物理广播信道块级的，空口技术级的，切片级的，或部分带宽级的等，则小区的标识信息中还包括对应的波束的标识信息，同步信号/物理广播信道块的标识信息，信道状态信息参考信号的标识信息，空口技术的标识信息，切片的标识信息，或部分带宽的标识信息等中的至少一项。
在一种设计中，源基站在接收到上述第一测量信息时，可基于第一测量信息判断是否需要为UE切换服务小区。若需要为UE切换服务小区，则源基站执行下述步骤401。
步骤401：源基站根据以下至少一项信息，进行AI推理，确定AI目标小区。
应当指出，源基站通过AI推理，得到AI目标小区，由于该AI目标小区是源基站预测的UE可以切换到的服务小区，因此，上述推理的AI目标小区也可以称为预测的AI目标小区等。所述AI目标小区的数量为一个或多个，不作限定。
在一种设计中，源基站用于推理AI目标小区的至少一项信息，包括以下至少一项：
-所述UE的第一测量信息。该第一测量信息可以是UE在上述步骤400中上报的。
-服务小区的负载信息。由于源基站为UE的服务小区所归属的基站，因此源基站可以获取服务小区的负载信息。服务小区的负载信息可以是服务小区的实时负载信息，和/或服务小区的历史负载信息等。
-相邻小区的负载信息。若相邻小区归属于源基站，则源基站可以直接获取相邻小区的负载信息；否则，源基站可以通过相邻小区所归属的基站，获取相邻小区的负载信息等。相邻小区的负载信息可以为相邻小区的实时负载信息，和/或相邻小区的历史负载信息等。
-UE的相关信息，可以包括UE的轨迹信息、UE的地理坐标信息、UE的运动方向、或UE的运动速度等中的至少一项。上述UE的相关信息可以为UE上报给源基站的，或者源基站通过对UE监测获取的，或者源基站通过其它网络设备 获取的等，不作限定。关于上述UE的相关信息，可以为UE的实时信息和/或UE的历史信息等。例如，UE的地理坐标信息可以为UE的当前实时地理坐标，和/或，UE的历史地理坐标等。
在一种设计中，源基站可以根据上述至少一项信息，进行AI推理，得到AI目标小区。所述AI推理的过程可以包括一次或多次等，不作限定。例如，在一种可能的实现方式中，图3a至图3d中的模型训练节点可以对数据源提供的训练数据进行分析，得到AI模型。模型推理节点将上述至少一项信息，输入到AI模型，该AI模型的输出为所述AI目标小区。或者，在另一种可能的实现方式中，图3a至图3d中的模型训练节点可以对数据源提供的训练数据进行分析，得到AI模型A和AI模型B。模型推理节点可以将上述至少一项信息，输入到AI模型A，该AI模型A的输出为上述至少一项信息的未来信息。例如，服务小区或邻区的未来负载信息、UE未来的轨迹、UE未来的运行速度、或UE未来的地理坐标等至少一项信息。之后，模型推理节点可以将上述至少一项信息中的实时信息、历史信息或未来信息等中的至少一项，输入到AI模型B中，AI模型B的输出为所述AI目标小区。
步骤402a：源基站向AI目标小区对应的目标基站发送第一请求消息。在一种设计中，该第一请求消息，可称为切换请求(handover request)。
在一种设计中，源基站与目标基站间存在可以直接通信的接口，该接口可以为X2接口、Xn接口或其它接口等，不作限定。源基站可以通过上述接口向目标基站发送第一请求消息。
在另一种设计中，源基站与目标基站间不存在可以直接通信的接口。源基站可以通过核心网设备向目标基站发送第一请求消息的部分或全部内容。例如，源基站可以通过S1接口或NG接口或其它接口向核心网设备发送上述第一请求消息，然后核心网设备将上述第一请求消息转发给目标基站等。
下文所有涉及源基站与目标基站通信的过程，可能都存在上述说明，不再一一说明。例如，在下述步骤402b中，源基站可以通过直接通信的接口，直接接收来自目标基站的第一响应消息。或者，源基站可以通过核心网设备接收来自目标基站的第一响应消息等。
通过上述描述可知，上述AI目标小区的数量为一个或多个。源基站可以针对每一个AI目标小区均发送对应的第一请求消息。举例来说，源基站推理出的AI目标小区的数量为3个，那么源基站可以向上述3个AI目标小区所属的目标基站，分别发送一个第一请求消息。在一种情况下，源基站推理出的AI目标小区中的多个小区可能归属于同一个目标基站。为了节省信令开销，针对上述多个小区，源基站可以向目标基站发送一个第一请求消息，该第一请求消息可以请求目标基站为UE接入多个小区分配资源。在图4的流程中，以源基站向一个目标基站发送第一请求消息为例说明的。
在一种设计中，上述第一请求消息用于请求所述AI目标小区对应的目标基站为所述UE分配AI目标小区对应的资源，第一请求消息用于指示以下至少一项：
-所述AI目标小区的标识信息。
-所述切换的类型为AI切换。
-激活时间信息，所述激活时间信息用于指示所述UE能够切换到所述AI目标小区的最早时间。示例的，若早于上述最早的时间，UE尝试接入AI目标小区时，则AI目标小区所对应的基站可以拒绝该接入。
-失效时间信息，所述失效时间信息用于指示所述UE能够切换到所述AI目标小区的最晚时间。示例的，若超过上述最晚的时间，UE还是未接入AI目标小区，则AI目标小区所对应的基站可以删除与之相关的信息。例如下述早期转移的用户面数据，以及UE的上下文等。
-或所述目标小区的预测准确度。
可选的，上述步骤402a之前，还可以包括：源基站与目标基站交互AI信息。例如，目标基站可以向源基站发送AI信息，该AI信息用于指示以下至少一项：
-目标基站支持或不支持AI切换。例如，可以用二进制比特指示目标基站是否支持AI切换，“0”表示目标基站不支持AI切换，“1”表示目标基站支持AI切换等。或者，用“错误(FALSE)”表示目标基站不支持AI切换，用“正确(TURE)”表示目标基站支持AI切换等。示例的，若目标基站支持AI切换，后续若源基站预测出的AI目标小区包括上述目标基站中的小区，源基站可以向目标基站发送上述步骤402a中的第一请求消息，否则源基站不向目标基站发送上述步骤402a中的第一请求消息。
-目标基站所支持的AI切换类型。首先介绍AI切换类型的含义：例如，目前的切换机制包括多种类型，例如，正常切换(legacy handover或者ordinary handover)、双激活协议栈切换(dual active protocol stack handover，DAPS HO)、条件切换(conditional handover，CHO)、无随机接入切换(RACH-less HO)或其它类型等。AI切换类型可具体指上述多种切换机制中支持AI切换的切换机制。举例来说，当采用AI预测的方式预测出UE待切换的小区为小区1，若上述正常切换机制支持AI切换，则UE可以利用正常切换机制，切换到小区1，则上述AI切换类型中可包括正常切换的切换机制。上述目标基站所支持的AI切换类型，可以具体为：目标基站所支持的可以进行AI切换的切换机制。
-目标基站中允许进行AI切换的小区信息。例如，目标基站中允许进行AI切换的小区数量和/或小区标识，或者，目标基站中允许进行某种AI切换类型的小区数量和/或小区标识等。可以理解的是，目标基站中包括多个小区，可以预先定义或设置上述多个小区中的每个小区是否支持AI切换。若一个小区支持AI切换，表示若该小区通过AI预测的方式确定为UE待切换的小区，即AI目标小区时，该小区支持UE切换到该小区；若一个小区不支持AI切换，表示源基站不允许通过AI预测的方式确定该小区为UE待切换的小区，即AI目标小区，或者，若该小区通过AI预测的方式确定为UE待切换的小区，即AI目标小区时，该小区不支持UE切换到该小区。关于目标基站中允许进行AI切换的小区信息，作如下说明：在一种可能的实现方式中，若目标基站中部分小区支持AI切换，部分小区不支持AI切换，此时目标基站可以向源基站显式的指示目标基站中支持AI切换的小区的标识信息。通过上述目标基站中支持AI切换的小区的标识信息，可以隐示的指示目标基站支持进行AI切换的小区数量。即此时，上述目标基站中允许进行AI切换的小区信息包括目标基站中支持进行AI切换的小区的标识信息。或者，若目标基站中所有的小区都支持AI切换，但是目标基站考虑到资源情况，因为支持AI切换需要预留资源，可能只允许部分小区做AI切换；此时目标基站可以向源基站指示目标基站中允许进行AI切换的小区信息，该小区信息可以包括小区的标 识和/或数量等。
步骤402b：源基站接收来自目标基站的第一响应消息，所述第一响应消息响应于所述第一请求消息。示例的，该第一响应消息可称为切换响应消息。
示例性的，上述第一响应消息可以为肯定确认(acknowledge，ACK)，比如切换请求确认(handover request acknowledge)消息。或者，第一响应消息可以为否定性确认(negative acknowledge，NACK)，比如切换准备失败(handover preparation failure)消息，或者切换失败(handover failure)消息等。若上述第一响应消息为ACK，表示目标基站同意UE切换到其下属的小区，否则表示目标基站不同意UE切换到其下属的小区。进一步的，若上述第一响应消息为ACK时，上述第一响应消息中还可以包括所述目标基站中允许UE进行AI切换的小区的指示信息，例如包括所述小区的数量和/或标识的指示信息等。需要说明的是，第一响应消息中指示的“目标基站中允许UE进行AI切换的小区数量”，与上述步骤402a中指示的“目标基站中允许进行AI切换的小区数量”，两者可以相同，也可以不同。例如，上述源基站中允许当前UE进行AI切换的小区数量，小于或等于，源基站中允许进行AI切换的小区数量。例如，源基站中包括10个小区，该10个小区中有8个小区支持AI切换，则上述步骤402a中目标基站中允许进行AI切换的小区数量为8。作为一种实现方式，若上述8个小区中，允许当前UE进行AI切换的小区数量为4，那么上述第一响应消息中目标基站允许UE进行AI切换的小区数量为4。
步骤402c：源基站向目标基站转移用户面数据。
可选的，源基站向目标基站发送第一状态转发消息，该第一状态转发消息用于指示源基站向目标基站转移的用户面数据中的第一SDU的编号，和/或，所述转移的用户面数据中可以丢弃的SDU的编号。
在本申请实施例中，在源基站接收到来自目标基站的第一响应消息，且该第一响应消息为ACK时，代表目标基站同意UE切换到目标基站下属的小区。源基站可以开始向目标基站转移用户面数据。相对于，在UE成功接入到目标基站时，源基站再向目标基站转移用户面数据，可以尽早的完成UE的用户面数据转移，减少切换造成的数据中断时间。由于源基站提前向目标基站转移用户面数据，因此上述用户面转移可称为源基站向目标基站早期转移数据，源基站向目标基站发送的第一状态转发消息，可称为早期状态转发(early status transfer)。可以理解的，源基站可以向目标基站发送至少一条第一状态转发消息，用于指示目标基站及时刷新第一SDU的编号，和/或，丢弃不需要的SDU。
举例来说，在源基站接收到来自目标基站的第一响应消息后，源基站中有10个下行(downlink，DL)SDU未发送给UE，源基站可以将上述10个DL SDU发送给目标基站。进一步的，源基站还可以向目标基站发送第一状态转发消息，用于指示上述10个DL SDU中的第一个DL SDU的编号。例如，若上述10个DL SDU中的第一个DL SDU的编号为1，目标基站可以根据上述第一个DL SDU的编号1，对剩余的9个DL SDU按顺序依次编号为2-9。
可以理解的是，由于在源基站和目标基站间进行早期数据转移的过程中，源基站与UE仍然在进行数据传输。源基站还可以向目标基站发送早期转移的DL SDU中可以丢弃的DL SDU的编号。仍沿用上述举例，在早期转移数据的过程中，源基站向目标基站转移了10个DL SDU。后续源基站向UE传输了5个DL SDU，且收到了上述5个DL SDU的ACK反馈。源基站可以向目标基站发送第一状态转发消息，用于通知目标基站可以丢弃的DL SDU的编 号。第一状态转发消息可以包括用于指示源基站需要丢弃的SDU的信息。示例的，源基站可以直接将编号1-5指示给目标基站，指示目标基站可以丢弃编号1-5的DL SDU；或者，源基站可以将编号6指示给目标基站，指示目标基站可以丢弃编号小于6的DL SDU等。
可选的，步骤403：UE向源基站发送第二测量信息。在一种设计中，UE可以向源基站发送第二测量报告，该第二测量报告中携带有第二测量信息。关于该第二测量信息的内容可参见上述步骤400中的第一测量信息。
步骤404：源基站确定切换所述UE到AI目标小区中的第一小区。
在一种设计中，源基站在接收到UE的第二测量信息时，根据第二测量信息，确定UE切换到哪个小区。在该实施例一中的描述中，是以UE切换到AI目标小区中的第一小区为例进行说明的。在下述实施例二中，是以UE切换到第二小区，且第二小区不属于AI目标小区为例进行说明的。
步骤405：源基站向UE发送第一配置信息，该第一配置信息用于指示所述第一小区的配置信息。
在一种设计中，源基站可以向UE发送RRC重配置消息，该RRC重配置消息中携带有上述第一配置信息。
需要说明的是，由于在步骤402a至步骤402c的过程中，第一小区所属的目标基站已经同意UE切换到第一小区，所以在步骤405中，源基站直接向UE发送第一小区的配置信息即可，无需再向目标小区发送第一请求消息。
步骤406：UE和目标基站建立连接。
在一种设计中，UE可以向目标基站发送RRC重配置完成消息，该RRC重配置完成消息用于UE和目标基站建立连接。
步骤407：源基站向目标基站发送第二状态转发消息，该第二状态转发消息用于指示源基站与UE的数据传输状态，该数据传输状态包括上行数据传输状态，和/或，下行数据传输状态等，不作限定。在一种设计中，上述源基站与UE的数据传输状态可以为源基站与UE已传输的SDU的序列号。在一种设计中，上述第二状态转发消息还可称为序列号状态转移(sequence number，SN，status tansfer)等。
在上述设计中，UE成功接入目标基站后，源基站可以将与UE数据传输的SDU序列号发送给目标基站。目标基站基于传输数据的SDU序列号，继续与UE进行数据传输，以避免向UE重传或漏传数据等。
步骤408：目标基站通知源基站释放UE上下文(UE context release)。相应的，源基站在接收到上述通知后，释放UE的上下文。
采用上述方案，将AI计算推理用于预测UE待切换的小区，可以提升预测的目标小区的准确性，提升UE小区切换的鲁棒性，该鲁棒性可以指UE小区切换的稳定性，和成功率等。此外，通过向AI目标小区对应的基站尽早转发数据，可减少切换后的数据中断时间。
如图5所示，提供一种小区切换的示例流程，在该流程中，以AI目标小区包括小区1和小区2，且小区1和小区2属于不同的基站为例。该流程至少包括：
可选的，步骤500：UE向源基站发送第一测量信息。
步骤501：源基站根据AI推理，确定AI目标小区，该AI目标小区中包括小区1和小区2。且小区1对应的基站为目标基站1，小区2对应的基站为目标基站2。
步骤502a：源基站向目标基站1和目标基站2分别发送切换请求消息。
步骤502b：目标基站1和目标基站2分别向源基站发送切换请求响应消息。
步骤502c：源基站分别与目标基站1和目标基站2间进行早期数据转移，源基站向目标基站1和目标基站2分别发送早期状态转发消息。
可选的，步骤503：UE向源基站发送第二测量信息，该第二测量信息与上述第一测量信息中包括的内容相似。
步骤504：源基站确定切换UE到小区1。
在一种设计中，源基站可以根据上述第二测量信息，确定切换UE到小区1。在图5所示的流程中，以基站确定UE切换到AI目标小区中的小区1为例描述的。
步骤505：源基站向UE发送RRC重配置消息，该RRC重配置消息中包括小区1的配置信息。
步骤506：UE向小区1对应的目标基站1发送RRC重配置完成消息。
步骤507：源基站向小区1对应的目标基站1发送SN状态转移。
步骤508：目标基站1通知源基站释放UE的上下文。相应的，源基站接收到上述通知时，释放UE的上下文。
步骤509：小区2对应的目标基站2到期后自动释放UE上下文信息。可选的，若有UE的数据，也删除UE对应的数据。
关于步骤509可以作如下说明：在上述步骤502a中的切换请求消息中可以包括失效时间信息，该失效时间信息可以指示UE接入到目标小区2的最晚时间。若超过该最晚时间，UE还是未接入目标小区2，目标基站2可以删除UE的相关信息，包括删除UE的上下文信息，和/或，接收的早期转移的UE的用户面数据等。
采用上述方案，将AI技术与移动性结合起来，使得基于AI的移动性机制预测，提前推理出合理的切换小区，提高切换准备的成功率，提升其鲁棒性；此外，引入AI目标小区的时间信息，可以尽可能少的占用AI目标基站的资源，提高资源利用率。
实施例二
该实施例二与上述实施例一的区别在于，在该实施例二中，源基站确定的UE切换的小区为第二小区，该第二小区不属于预先推理的AI目标小区。
如图6所示，该实施例二提供一种小区切换的流程，至少包括：
可选的，步骤600：UE向源基站上报第一测量信息。
步骤601：源基站确定AI目标小区。
步骤602a：源基站向AI目标小区对应的目标基站发送第一请求消息。
步骤602b：目标基站向源基站发送第一响应消息，该第一响应消息响应于第一请求消息。
步骤602c：源基站向目标基站转移用户面数据，源基站向目标基站发送第一状态转发消息。
可选的，步骤603：UE向源基站发送第二测量信息。
关于上述步骤600至步骤603可参见上述实施一中的步骤400至步骤403的相关说明。
步骤604：源基站确定切换到第二小区，上述推理的AI目标小区中不包含第二小区。
步骤605a：源基站向第二小区对应的第二基站发送第一请求消息，该第一请求消息用 于请求第二基站为UE接入第二小区分配资源。
步骤605b：第二基站向源基站发送第一响应消息，该第一响应消息响应于第一请求消息。与上述相似，第一响应消息中可以为ACK或NACK。若第一响应消息为ACK，表示第二基站同意UE切换到第二小区；否则表示第二基站不同意UE切换到第二小区。若第二基站同意UE切换到第二小区，源基站可以向第二基站进行早期数据转移，即下述步骤605c的过程。
步骤605c：源基站向第二基站转移用户面数据，源基站向第二基站发送第一状态转发消息。
步骤606：源基站向UE发送第二配置消息，该第二配置消息中用于向UE指示第二小区的配置信息和AI目标小区的配置信息。在一种设计中，源基站可以向UE发送RRC重配置消息，该RRC重配置消息中包括上述第二配置消息。
示例性的，AI目标小区的配置信息中可用于指示以下至少一项：
-AI目标小区的标识信息；
-随机接入信息，随机接入信息用于指示所述UE切换到AI目标小区的随机接入资源；
-激活时间信息；
-失效时间信息。
步骤607：UE根据第二小区的配置信息，执行到第二小区的切换。
在一种设计中，若UE与第二小区的连接失败，则UE执行下述步骤608。UE与第二小区的连接失败可以包括：UE执行到第二小区的切换过程中发生连接失败，或者，UE执行到第二小区的切换成功后短时间发生连接失败。
步骤608：UE确定第一目标小区。关于UE确定第一目标小区的方式，不作限定。第一目标小区可以属于AI目标小区，或者不属于AI目标小区。
步骤609：UE和第一目标小区建立连接。
示例性的，UE和第一目标小区建立连接的过程可包括：在一种设计中，若所述UE侧存储有有效的所述AI目标小区的配置信息，当所述第一目标小区为所述AI目标小区中的小区时，UE执行到第一目标小区的切换流程。示例的，UE执行到第一目标小区的切换流程包括：UE向第一目标小区发送RRC重配置完成消息，或者，当第一目标小区不为所述AI目标小区中的小区时，UE执行到第一目标小区的重建流程。或者，在另一种设计中，若所述UE未存储有有效的AI目标小区的配置信息，UE执行到第一目标小区的重建流程。
可选的，关于UE侧是否存储有有效的AI目标小区的配置信息，作如下说明：在上述步骤606中，源基站将AI目标小区的配置信息发送给UE。其中，AI目标小区的配置信息中包括失效时间信息，该失效时间信息是指UE接入该AI目标小区的最晚时间，或者，是指该AI目标小区的配置信息的最晚有效时间。若超过该最晚时间，UE还未接入到AI目标小区，UE可以删除AI目标小区的配置信息。若UE侧存储的AI目标小区的配置信息还未到上述失效时间信息指示的时间，可称UE侧存储有有效的AI目标小区的配置信息，否则称为UE侧未存储有有效的AI目标小区的配置信息。
举例来说，UE执行到第二小区的切换成功后，经过一段时间，失效时间信息指示的时间到期，UE可以删除该失效时间信息对应的AI目标小区的配置信息。之后，UE检测到与第二小区的连接失败，UE未存储有有效的AI目标小区的配置信息，则UE可以执行 到第一目标小区的重建流程。
步骤610：第一目标小区对应的基站向源基站发送切换成功的指示信息。
步骤611：源基站向第一目标小区对应的基站发送第二状态转发消息。
步骤612：第一目标小区对应的基站通知源基站释放UE的上下文。
由于切换流程相对于重建流程，信令交互要简单许多，因此，在UE与第二小区的连接失败的过程中，若UE所选择的第一目标小区为预测的AI目标小区中的小区时，UE可以直接向第一目标小区发起切换流程，快速恢复连接，缩短数据传输中断时延，并减少信令开销。
如图7所示，提供一种小区切换的示性流程，至少包括：
可选的，步骤700：UE向源基站上报第一测量信息。
步骤701：UE根据AI推理，确定AI目标小区，该AI目标小区中包括小区1和小区2。
步骤702a：UE分别向小区1对应的基站1和小区2对应的基站2发送切换请求消息。
步骤702b：UE接收来自基站1和基站2的切换响应消息。
步骤702c：源基站向基站1和基站2转移用户面数据，且源基站向基站1和基站2发送早期状态转移。
可选的，步骤703：UE向源基站发送第二测量信息。
步骤704：源基站确定切换到小区3。在一种设计中，源基站可以根据第二测量信息，确定切换到小区3，且该小区3不属于AI目标小区。
步骤705a：源基站向小区3对应的基站3发送切换请求消息。
步骤705b：基站3向源基站发送切换请求响应消息。
步骤705c：源基站向基站3转移用户面数据，且源基站向基站3发送早期状态转移。
步骤706：源基站向UE发送第二配置消息，该第二配置消息可以为RRC重配置消息，该第二配置消息用于指示小区3的配置信息和AI目标小区的配置信息。
步骤707：UE执行到小区3的切换，在切换过程中检测到连接失败，或者切换到小区3后检测到连接失败。
步骤708：UE执行小区选择。
步骤709：UE选择到AI目标小区，比如小区1，UE执行切换流程。在一种设计中，UE执行切换流程包括：UE向小区1对应的基站1发送RRC重配置完成消息。
步骤710：基站1向源基站发送切换指示信息，比如切换成功消息，通知源基站UE在小区1成功完成切换。
步骤711：源基站可以向基站1发送SN状态转移。
步骤712：基站1通知源基站释放UE上下文。
步骤713：小区2对应的基站2到期后自动删除UE上下文，若有数据，也删除UE对应的数据。
采用上述方案，将AI技术与移动性结合起来，使得基于AI的移动性机制预测，在最终切换小区不属于AI目标小区时，依然向UE发送AI目标小区的配置信息，可以提升移动性的鲁棒性。此外，引入AI目标小区的时间信息，例如激活时间信息或失效时间信息等，可以尽能少的占用AI目标小区对应的基站的资源，提升系统效率。
可以理解的是，在上述实施例一和实施例二的描述中，是以基站触发为例进行描述的。实际上，上述实施例一或实施例二的方案，也可以应用于UE触发切换的场景中。在一种设计中，其与上述实施例一中的图4或实施例二中的图6，主要有以下区别：
在步骤402a或602a中：源基站向AI目标小区对应的目标基站发送的第一请求消息中，还可以携带有UE触发切换机制的指示信息。
在步骤402c或602c之后，新增步骤：源基站向UE发送第三配置信息，该第三配置信息用于向UE指示AI目标小区的配置信息和切换触发配置信息，所述切换触发配置信息用于向UE指示切换到所述AI目标小区的触发条件。可选的，该配置信息中还可以包括AI目标小区的激活时间信息和/或失效时间信息等的指示信息。
关于上述切换触发配置信息作如下说明：由于在UE触发的切换机制中，源基站为UE配置至少一个候选小区。在该示例中，上述AI目标小区即为源基站配置给UE的候选小区。在UE确定满足触发条件时，UE可以选择该触发条件对应的候选小区，执行切换。而上述切换触发配置信息可以具体为：源基站为候选小区，即AI目标小区，配置的切换触发条件。不同的候选小区的切换触发条件可以相同，也可以不同。
步骤404或604替换为：源基站确定更新AI目标小区的配置信息和/或更新切换触发配置信息。
步骤405或605替换为：源基站向UE发送第四配置信息，该第四配置信息用于向UE指示更新的AI目标小区的配置信息，和/或，更新的切换触发配置信息。
在一种设计中，UE向源基站上报第一测量信息，源基站根据第一测量信息等信息，确定AI目标小区，包括小区1和小区2。源基站向UE发送第三配置信息，该第三配置信息中包括小区1和小区2的配置信息，以及小区1和小区2的切换触发配置信息。后续，UE向源基站上报第二测量信息，源基站根据第二测量信息，确定添加小区3为候选小区，源基站可以向UE发送更新的第三配置信息，即第四配置信息，该第四配置信息中包括小区1、小区2和小区3的配置信息，以及小区1、小区2或小区3各自对应的切换触发配置信息等。或者，在第四配置信息中，可以仅包括小区3的配置信息，和小区3对应的切换触发配置信息等。进一步的，上述第四配置信息中还可以包括小区3的激活时间信息和/或失效时间信息的指示信息等。
实施例三
该实施例三提供一种小区切换的方法，该小区切换的方法可以更新上述实施例一或实施例二中推理的AI目标小区的结果。该实施例三可以与上述实施例一或实施例二相结合使用，或者单独使用等，不作限定。
该实施例三提供的小区切换的方法，包括：源基站输出第五配置信息，所述第五配置信息用于指示UE上报第一反馈信息的触发条件；源基站获取UE的第一反馈信息；源基站确定AI目标小区的更新结果，所述AI目标小区的更新结果为更新的UE可以切换到的服务小区。关于上述过程，作如下说明：
在一种设计中，AI设备可以单独布署，关于该单独布署的AI设备的说明，可参见上述实施例一。在一种可能的实现方式中，AI设备可以确定UE上报第一反馈信息的触发条件，AI设备向源基站发送第五配置信息。源基站向UE转发上述第五配置信息，以指示 UE上报第一反馈信息的触发条件。源基站接收来自UE的第一反馈信息，源基站向AI设备转发第一反馈信息。AI设备根据第一反馈信息，更新AI目标小区的结果。或者，在另一种可能的实现方式中，AI设备与UE可以直接进行交互，不再经过源基站的中转。例如，AI设备可以直接将上述第五配置信息发送给UE，UE也直接向AI设备上报第一反馈信息等。
在另一种设计中，源基站中可以集成有AI模块的功能。例如，源基站可以向UE发送第五配置信息。源基站可以接收UE发送的第一反馈信息，源基站可以根据第一反馈信息，更新AI目标小区的结果等。
如图8所示，以源基站集成AI模块的功能为例，提供一种小区切换的流程，至少包括：
步骤800：UE向源基站发送第一测量信息。
步骤801：源基站确定AI目标小区。例如，AI目标小区包括小区1和小区2，小区1对应的基站为基站1，小区2对应的基站为基站2。
步骤802a：源基站分别向基站1和基站2发送切换请求消息。
步骤802b：基站1和基站2分别向源基站发送切换请求响应消息。
步骤802c：源基站向基站1和基站2早期转移用户面数据和发送早期状态转发消息。
上述步骤800至802c是可选的。原因如下：源基站可以在满足上述步骤800至802c的条件下，执行下述步骤803向UE发送第五配置信息。或者，源基站可以其它条件作为触发，执行下述步骤803向UE发送第五配置信息等，不作限定。
步骤803：源基站向UE发送第五配置信息，该第五配置用于指示UE上报第一反馈信息的触发条件。在一种设计中，源基站可以向UE发送RRC重配置消息，该RRC重配置消息中包括第五配置信息。
示例性的，上述第五配置信息可用于指示以下至少一项：
-至少一个小区的标识信息和质量门限信息；所述小区的标识信息可以为UE的服务小区的标识信息，和/或，相邻小区的标识信息。其中，相邻小区可以为AI目标小区。质量门限信息用于UE确定小区的质量满足质量门限时上报第一反馈信息。作为具体的示例，质量门限信息可以为第一质量门限信息。当UE确定小区的信号质量低于或等于第一质量门限时，UE可以上报第一反馈信息；或者，门限信息可以包括第二质量门限信息和第三质量门限信息；当UE当前服务小区的质量低于或等于第二质量门限，且相邻小区的质量高于或等于第三质量门限时，UE可以上报第一反馈信息。可以理解的是，此时第一反馈信息可以包括满足第五配置信息的小区的标识信息，和/或满足第五配置信息的小区的标识信息对应的质量信息等。
-参考位置信息和第一距离门限信息；示例的，当UE的最新位置与参考位置之间的距离高于或等于第一距离门限时，UE上报第一反馈信息。可以理解的是，第一反馈信息中可以包括UE最新的位置信息。
-时间上报指示信息，用于指示UE在第一反馈信息中携带或不携带时间信息的指示信息，该时间信息为所述UE满足所述第五配置信息时的时间，或者所述UE上报所述第一反馈信息的时间等。
-轨迹变更触发信息，用于指示UE的最新轨迹偏离之前的轨迹时，所述UE上报第 一反馈信息。比如，基站获取的UE之前的轨迹为A，当UE发现其偏离之前的轨迹A时，或者偏离之前的轨迹A的距离或时间超过某一门限时，UE向基站发送第一反馈信息。
步骤804：UE在满足上述触发条件时，向源基站上报第一反馈信息。
步骤805：源基站根据第一反馈信息，确定AI目标小区的更新结果。
在一种设计中，源基站可将第一反馈信息作为输入，输入到AI模型中，该AI模型的输出为AI目标小区的更新结果。或者，源基站可以根据第一反馈信息，更新AI模型，利用更新后的AI模型，获得AI目标小区的更新结果。
采用上述方案，引入UE进行AI推理反馈，可以辅助源基站及时完善AI推理结果，保证AI推理结果的准确性及有效性。
针对上述实施例一至实施例三，需要说明的是：
1、上文侧重描述了实施例一、实施例二和实施例三的区别之处，除区别之外的其它内容，可相互参见。
2、实施例一至实施例三所描述的各个流程图中所示意的步骤并非全部是必须执行的步骤，可以根据实际需要在各个流程图的基础上增添或删除部分步骤，比如，上述步骤400和步骤800-802c等可以选择性执行等。
3、在实施例一至实施例三的描述中，以某个硬件设备作为一个整体为例进行描述的，并没有描述该硬件设备内部各模块的动作。为了支持该硬件设备作为一个整体，实现上述实施例描述的相关功能，该硬件设备内部模块间的操作，也在本申请实施例的保护范围内。
例如，在一种设计中，随着开放无线接入网络(open，radio access network，RAN，O-RAN)的提出，接入网设备的功能可能被多个通用标准的模块实现。如图2b所示，基站的功能可能由CU模块或DU模块实现。举例来说，在上述实施例一中，从整体上描述，源基站和目标基站的动作可以为：源基站确定AI目标小区，源基站向AI目标小区对应的目标基站发送第一请求消息。目标基站向源基站发送第一响应消息，该第一响应消息响应于第一请求消息。
若源基站包括CU1模块和DU1模块，目标基站包括CU2模块和DU2模块。上述第一请求消息的传输路径可包括：CU1模块可以确定AI目标小区，CU1模块向CU2模块发送第一请求消息等。若AI目标小区为DU2管理的小区，CU2模块可以向DU2模块发送第二请求消息，该第二请求消息的内容与功能，与第一请求消息相似。第一响应消息的传输路径可包括：DU2模块向CU2模块发送第二响应消息，该第二响应消息响应于第一响应消息；CU2结合DU2的通知(即第二响应消息)，以及CU2自己的判断，生成第一响应消息，CU2向CU1发送第一响应消息等。
4、在上述实施例一至实施例三的描述中，采用了以下描述：“设备输出某个消息”，例如，源基站输出第一请求消息，源基站输出第五配置信息等。在本申请的描述中，“设备输出某个消息(为了便于区分，可将上述某个消息下述称为消息A)”可以包括：“设备向其它设备发送上述消息A”，或者，“设备中的某个模块输出消息A至该设备中的另一模块，由另一模块将消息A发送到其它设备等”。
“设备获取其它设备的消息”，例如，源基站获取UE的第一反馈信息，源基站获取目标基站的第一响应消息等。在本申请的描述中，“设备获取其它设备的消息”可以 为“该设备接收其它设备的消息”，或者，“设备中的某一模块接收其它设备的消息，该设备中的某一模块将接收的消息，转发给该设备中的其它模块等。
5、在实施例一至实施例三的描述中，采用在“一个消息中包括某个信息的指示信息”的描述。例如，在第一请求消息中可以包括至少一项信息的指示信息等。关于上述描述，作如下说明：该消息可以直接指示对应的信息，例如，在该消息中直接携带该信息。或者，该消息可以间接指示对应的信息，例如，在该消息中携带对应信息的指示信息等。举例来说，消息A中包括信息X的指示信息，该消息A可以直接指示信息X，例如，该消息A可以携带信息X。或者，该消息A可以间接指示信息X。例如，该消息A中可以携带用于表示信息X的其它信息等。
6、为了便于理解，在上述实施例一至实施例三的描述中，直接采用了源基站、目标基站和UE等名称。可以理解的是，源基站为UE的服务小区归属的网络设备，可称为第一网络设备，目标基站可以为AI目标小区归属的网络设备，可称为第二网络设备，UE可以为待切换服务小区的终端设备。关于网络设备和终端设备的说明，可参见前述图1中的说明。
以上结合图1、图2a至图2d、图3a至图3d、图4至图8详细说明了本申请实施例提供的方法，以下结合图9至图11详细说明本申请实施例提供的装置。应理解，装置实施例的描述与方法实施例的描述相互对应。因此，未详细描述的内容可参见上文方法实施例中的描述。
图9示出了本申请实施例所涉及的装置的可能的框图。如图9所示，装置900可以包括：通信单元901用于支持装置与其他设备的通信。可选的，通信单元901也称为收发单元，可以包括接收单元和/或发送单元，分别用于执行接收和发送操作。处理单元902用于支持装置进行处理。可选的，装置900还可以包括存储单元903，用于存储装置900的程序代码和/或数据。
在第一个实施例中，上述装置900可以为网络设备或网络设备中的模块、芯片或电路。通信单元901用于执行上文方法实施例一或实施例二中源基站的收发操作；处理单元902用于执行上文方法实施例一或实施例二中源基站的处理相关操作。
例如，处理单元902，用于确定AI目标小区，所述AI目标小区为预测的、终端设备可以切换到的服务小区；通信单元901，用于输出第一请求消息，所述第一请求消息用于请求所述AI目标小区对应的第二网络设备为所述终端设备分配所述AI目标小区对应的资源，所述第一请求消息用于指示以下至少一项：所述AI目标小区的标识信息、所述切换的类型为AI切换、激活时间信息、失效时间信息、或所述AI目标小区的预测准确度，所述激活时间信息用于指示所述终端设备切换到所述AI目标小区的最早时间，所述失效时间信息用于指示所述终端设备切换到所述AI目标小区的最晚时间。
在一种可能的设计中，所述AI目标小区为根据AI方式预测的，包括：所述AI目标小区是根据以下至少一项信息预测的，所述至少一项信息中包括：所述终端设备的第一测量信息、服务小区的负载信息、相邻小区的负载信息、所述终端设备的轨迹信息、所述终端设备的地理坐标信息、所述终端设备的运动方向、或所述终端设备的运动速度。
在一种可能的设计中，通信单元901，还用于获取所述第二网络设备的第一响应消息，所述第一响应消息响应于所述第一请求消息，所述第一响应消息包括所述第二网络设备中 允许所述终端设备进行AI切换的小区数量的指示信息。
在一种可能的设计中，通信单元901，还用于：获取所述第二网络设备的AI信息，所述AI信息用于指示以下至少一项：所述第二网络设备支持或不支持AI切换的指示信息、所述第二网络设备所支持AI的切换类型的指示信息、或所述第二网络设备允许进行AI切换的小区信息。
在一种可能的设计中，通信单元901，还用于：向所述第二网络设备转移所述终端设备的用户面数据，以及输出第一状态转发消息，所述第一状态转发消息用于指示第一网络设备向所述第二网络设备转移的用户面数据中的第一个下行业务数据单元SDU的编号，和/或所述转移的用户面数据中可以丢弃的SDU的编号。
在一种可能的设计中，处理单元902，还用于确定切换所述终端设备到所述AI目标小区中的第一小区；通信单元901，还用于输出第一配置消息，所述第一配置消息用于向所述终端设备指示所述第一小区的配置信息。
在一种可能的设计中，处理单元902，还用于确定切换所述终端设备到第二小区，所述AI目标小区中不包含所述第二小区；通信单元901，还用于输出第二配置消息，所述第二配置消息用于向所述终端设备指示所述第二小区的配置信息和所述AI目标小区的配置信息。
在一种可能的设计中，通信单元901，还用于输出第三配置信息，所述第三配置信息用于向所述终端设备指示所述AI目标小区的配置信息和切换触发配置信息，所述切换触发配置信息用于向所述终端设备指示切换到所述AI目标小区的触发条件。
在一种可能的设计中，处理单元902，还用于确定更新所述AI目标小区的配置信息，和/或更新所述切换触发配置信息；通信单元901，用于输出第四配置信息，所述第四配置信息用于向所述终端设备指示更新的AI目标小区的配置信息，和/或，更新的切换触发配置信息。
在一种可能的设计中，所述AI目标小区的配置信息用于指示以下至少一项：所述AI目标小区的标识信息、随机接入信息、激活时间信息、或失效时间信息，所述随机接入信息用于指示所述终端设备切换到所述AI目标小区的随机接入资源，所述激活时间信息指示所述终端设备切换到所述AI目标小区的最早时间，所述失效时间信息指示所述终端设备切换到所述AI目标小区的最晚时间。
在第二个实施例中，上述装置900可以为网络设备或网络设备中的模块、芯片或电路。通信单元901用于执行上文方法实施例一或实施例二中目标基站的收发相关操作；处理单元902用于执行上文方法实施例一或实施例二中目标基站的处理相关操作。
例如，通信单元901，用于获取第一网络设备的第一请求消息，所述第一请求消息用于请求人工智能AI目标小区对应的第二网络设备为终端设备分配所述AI目标小区对应的资源；其中，所述第一请求消息用于指示以下至少一项：所述AI目标小区的标识信息、所述切换的类型为AI切换、激活时间信息、失效时间信息、或所述AI目标小区的预测准确度，所述激活时间信息用于指示所述终端设备切换到所述AI目标小区的最早时间，所述失效时间信息用于指示所述终端设备切换到所述AI目标小区的最晚时间。
在一种可能的设计中，所述AI目标小区是根据以下至少一项信息预测的，所述至少一项信息中包括：所述终端设备的第一测量信息、服务小区的负载信息、相邻小区的负载 信息、所述终端设备的轨迹信息、所述终端设备的地理坐标信息、所述终端设备的运动方向、或所述终端设备的运动速度。
在一种可能的设计中，通信单元901，还用于：输出第一响应消息，所述第一响应消息响应于所述第一请求消息，所述第一响应消息包括所述第二网络设备中允许所述终端设备进行AI切换的小区数量的指示信息。
在一种可能的设计中，通信单元901，还用于：输出AI消息，所述AI信息用于指示以下至少一项：所述第二网络设备支持或不支持AI切换的指示信息、所述第二网络设备所支持AI的切换类型的指示信息、或所述第二网络设备允许进行AI切换的小区信息。
在一种可能的设计中，通信单元901，还用于：获取所述第一网络设备转移的所述终端设备的用户面数据，以及获取所述第一网络设备的第一状态转发消息，所述第一状态转发消息用于指示第一网络设备向所述第二网络设备转移的用户面数据中的第一个下行业务数据单元SDU的编号，和/或所述转移的用户面数据中可以丢弃的SDU的编号。
在第三个实施例中，上述装置900可以为终端设备或终端设备中的模块、芯片或电路。通信单元901用于执行上文方法实施例二中UE的收发相关操作；处理单元902用于执行上文方法实施例中UE的处理相关操作。
通信单元901，用于获取第一网络设备的第二配置信息，所述第二配置信息用于向终端设备指示第二小区的配置信息和人工智能AI目标小区的配置信息；处理单元902，用于根据所述第二小区的配置信息，执行到所述第二小区的切换。
在一种可能的设计中，处理单元902，还用于当终端设备与所述第二小区的连接失败时，确定第一目标小区。
在一种可能的设计中，若所述终端设备侧存储有有效的所述AI目标小区的配置信息，处理单元902，还用于当所述第一目标小区为所述AI目标小区中的小区时，执行到所述第一目标小区的切换流程；或者，当所述第一目标小区不为所述AI目标小区中的小区时，执行到所述第一目标小区的重建流程。
在一种可能的设计中，若所述终端设备侧未存储有有效的所述AI目标小区的配置信息，处理单元902，还用于执行到所述第一目标小区的重建流程。
在第四个实施例中，上述装置900可以为网络设备或网络设备中的模块、芯片或电路。通信单元901用于执行上文方法实施例三中源基站的收发相关操作；处理单元902用于执行上文方法实施例三中源基站的处理相关操作。
例如，通信单元901，用于输出第五配置信息，所述第五配置信息用于指示终端设备上报第一反馈信息的触发条件；通信单元901，还用于获取所述终端设备的第一反馈信息；处理单元902，用于确定人工智能AI目标小区的更新结果，所述AI目标小区的更新结果是根据所述第一反馈信息确定的，所述AI目标小区的更新结果为更新的所述终端设备可以切换到的服务小区。
在一种可能的设计中，所述第五配置信息用于指示以下至少一项：至少一个小区的信息和质量门限信息、参考位置信息和第一距离门限信息、轨迹变更触发信息或时间上报指示信息，所述时间上报指示信息包括所述终端设备在所述第一反馈信息中携带或不携带时间信息的指示信息，所述时间信息为所述终端设备满足所述第五配置信息时的时间，或者 所述终端设备上报所述第一反馈信息的时间。
在一种可能的设计中，当所述第五配置信息用于指示至少一个小区的标识信息和质量门限信息时，所述第一反馈信息用于指示满足所述第五配置信息的小区的标识信息，和/或，满足所述第五配置信息的小区的质量信息，或者，所述第一反馈信息用于指示不满足所述第五配置信息的小区的标识信息，和/或，不满足所述第五配置信息的小区的质量信息；或者，当所述第五配置信息用于指示参考位置信息和第一距离门限信息时，所述第一反馈信息用于指示所述终端设备最新的位置信息。
在第五个实施例中，上述装置900可以为终端设备或终端设备中的模块、芯片或电路。通信单元901用于执行上文方法实施例三中UE的收发相关操作；处理单元902用于执行上文方法实施例三中UE的处理相关操作。
例如，通信单元901，用于获取第一网络设备的第五配置信息，所述第五配置信息用于指示终端设备上报第一反馈信息的触发条件；通信单元901，还用于输出第一反馈信息，所述第一反馈信息是在满足所述第五配置信息的触发条件时输出的，所述第一反馈信息用于更新人工智能AI目标小区，所述AI目标小区的更新结果为更新的所述终端设备可以切换到的服务小区。
在一种可能的设计中，所述第五配置信息用于指示以下至少一项：至少一个小区的信息和质量门限信息、参考位置信息和第一距离门限信息、轨迹变更触发信息或时间上报指示信息，所述时间上报指示信息包括所述终端设备在所述第一反馈信息中携带或不携带时间信息的指示信息，所述时间信息为所述终端设备满足所述第五配置信息时的时间，或者所述终端设备上报所述第一反馈信息的时间。
在一种可能的设计中，当所述第五配置信息用于指示至少一个小区的标识信息和质量门限信息时，所述第一反馈信息用于指示满足所述第五配置信息的小区的标识信息，和/或，满足所述第五配置信息的小区的质量信息，或者，所述第一反馈信息用于指示不满足所述第五配置信息的小区的标识信息，和/或，不满足所述第五配置信息的小区的质量信息；或者，当所述第五配置信息用于指示参考位置信息和第一距离门限信息时，所述第一反馈信息用于指示所述终端设备最新的位置信息。
应理解以上装置中单元的划分仅仅是一种逻辑功能的划分，实际实现时可以全部或部分集成到一个物理实体上，也可以物理上分开。且装置中的单元可以全部以软件通过处理元件调用的形式实现；也可以全部以硬件的形式实现；还可以部分单元以软件通过处理元件调用的形式实现，部分单元以硬件的形式实现。例如，各个单元可以为单独设立的处理元件，也可以集成在装置的某一个芯片中实现，此外，也可以以程序的形式存储于存储器中，由装置的某一个处理元件调用并执行该单元的功能。此外这些单元全部或部分可以集成在一起，也可以独立实现。这里所述的处理元件又可以成为处理器，可以是一种具有信号的处理能力的集成电路。在实现过程中，上述方法的各操作或以上各个单元可以通过处理器元件中的硬件的集成逻辑电路实现或者以软件通过处理元件调用的形式实现。
在一个例子中，以上任一装置中的单元可以是被配置成实施以上方法的一个或多个集成电路，例如：一个或多个特定集成电路(application specific integrated circuit，ASIC)，或，一个或多个微处理器(digital singnal processor，DSP)，或，一个或者多个现场可编程门阵列(field programmable gate array，FPGA)，或这些集成电路形式中至少两种的组合。 再如，当装置中的单元可以通过处理元件调度程序的形式实现时，该处理元件可以是处理器，比如通用中央处理器(central processing unit，CPU)，或其它可以调用程序的处理器。再如，这些单元可以集成在一起，以片上系统(system-on-a-chip，SOC)的形式实现。
以上用于接收的单元是一种该装置的接口电路，用于从其它装置接收信号。例如，当该装置以芯片的方式实现时，该接收单元是该芯片用于从其它芯片或装置接收信号的接口电路。以上用于发送的单元是一种该装置的接口电路，用于向其它装置发送信号。例如，当该装置以芯片的方式实现时，该发送单元是该芯片用于向其它芯片或装置发送信号的接口电路。
图10为本申请实施例提供的一种终端设备的结构示意图。如图10所示，该终端设备包括：天线1010、射频部分1020、信号处理部分1030。天线1010与射频部分1020连接。在下行方向上，射频部分1020通过天线1010接收网络设备发送的信息，将网络设备发送的信息发送给信号处理部分1030进行处理。在上行方向上，信号处理部分1030对终端设备的信息进行处理，并发送给射频部分1020，射频部分1020对终端设备的信息进行处理后经过天线1010发送给网络设备。
信号处理部分1030可以包括调制解调子系统，用于实现对数据各通信协议层的处理；还可以包括中央处理子系统，用于实现对终端设备操作系统以及应用层的处理；此外，还可以包括其它子系统，例如多媒体子系统，周边子系统等，其中多媒体子系统用于实现对终端设备相机，屏幕显示等的控制，周边子系统用于实现与其它设备的连接。调制解调子系统可以为单独设置的芯片。
调制解调子系统可以包括一个或多个处理元件1031，例如，包括一个主控CPU和其它集成电路。此外，该调制解调子系统还可以包括存储元件1032和接口电路1033。存储元件1032用于存储数据和程序，但用于执行以上方法中终端设备所执行的方法的程序可能不存储于该存储元件1032中，而是存储于调制解调子系统之外的存储器中，使用时调制解调子系统加载使用。接口电路1033用于与其它子系统通信。
该调制解调子系统可以通过芯片实现，该芯片包括至少一个处理元件和接口电路，其中处理元件用于执行以上终端设备执行的任一种方法的各个步骤，接口电路用于与其它装置通信。在一种实现中，终端设备实现以上方法中各个步骤的单元可以通过处理元件调度程序的形式实现，例如用于终端设备的装置包括处理元件和存储元件，处理元件调用存储元件存储的程序，以执行以上方法实施例中终端设备执行的方法。存储元件可以为与处理元件处于同一芯片上的存储元件，即片内存储元件。
在另一种实现中，用于执行以上方法中终端设备所执行的方法的程序可以在与处理元件处于不同芯片上的存储元件，即片外存储元件。此时，处理元件从片外存储元件调用或加载程序于片内存储元件上，以调用并执行以上方法实施例中终端设备执行的方法。
在又一种实现中，终端设备实现以上方法中各个步骤的单元可以是被配置成一个或多个处理元件，这些处理元件设置于调制解调子系统上，这里的处理元件可以为集成电路，例如：一个或多个ASIC，或，一个或多个DSP，或，一个或者多个FPGA，或者这些类集成电路的组合。这些集成电路可以集成在一起，构成芯片。
终端设备实现以上方法中各个步骤的单元可以集成在一起，以SOC的形式实现，该SOC芯片，用于实现以上方法。该芯片内可以集成至少一个处理元件和存储元件，由处理 元件调用存储元件的存储的程序的形式实现以上终端设备执行的方法；或者，该芯片内可以集成至少一个集成电路，用于实现以上终端设备执行的方法；或者，可以结合以上实现方式，部分单元的功能通过处理元件调用程序的形式实现，部分单元的功能通过集成电路的形式实现。
可见，以上用于终端设备的装置可以包括至少一个处理元件和接口电路，其中至少一个处理元件用于执行以上方法实施例所提供的任一种终端设备执行的方法。处理元件可以以第一种方式：即调用存储元件存储的程序的方式执行终端设备执行的部分或全部步骤；也可以以第二种方式：即通过处理器元件中的硬件的集成逻辑电路结合指令的方式执行终端设备执行的部分或全部步骤；当然，也可以结合第一种方式和第二种方式执行终端设备执行的部分或全部步骤。
这里的处理元件同以上描述，可以通过处理器实现，处理元件的功能可以和图9中所描述的处理单元的功能相同。示例性地，处理元件可以是通用处理器，例如CPU，还可以是被配置成实施以上方法的一个或多个集成电路，例如：一个或多个ASIC，或，一个或多个微处理器DSP，或，一个或者多个FPGA等，或这些集成电路形式中至少两种的组合。存储元件可以通过存储器实现，存储元件的功能可以和图9中所描述的存储单元的功能相同。存储元件可以通过存储器实现，存储元件的功能可以和图9中所描述的存储单元的功能相同。存储元件可以是一个存储器，也可以是多个存储器的统称。
图10所示的终端设备能够实现上述方法实施例中涉及终端设备的各个过程。图10所示的终端设备中的各个模块的操作和/或功能，分别为了实现上述方法实施例中的相应流程。具体可参见上述方法实施例中的描述，为避免重复，此处适当省略详述描述。
参见图11，为本申请实施例提供的网络设备的结构示意图，该网络设备可以为接入网设备(如基站)。接入网设备110可包括一个或多个DU 1101和一个或多个CU 1102。所述DU 1101可以包括至少一个天线11011，至少一个射频单元11012，至少一个处理器11013和至少一个存储器11014。所述DU 1101部分主要用于射频信号的收发以及射频信号与基带信号的转换，以及部分基带处理。CU1102可以包括至少一个处理器11022和至少一个存储器11021。
所述CU 1102部分主要用于进行基带处理，对接入网设备进行控制等。所述DU 1101与CU 1102可以是物理上设置在一起，也可以物理上分离设置的，即分布式基站。所述CU 1102为接入网设备的控制中心，也可以称为处理单元，主要用于完成基带处理功能。例如所述CU 1102可以用于控制接入网设备执行上述方法实施例中关于接入网设备的操作流程。
此外，可选的，接入网设备110可以包括一个或多个射频单元，一个或多个DU和一个或多个CU。其中，DU可以包括至少一个处理器11013和至少一个存储器11014，射频单元可以包括至少一个天线11011和至少一个射频单元11012，CU可以包括至少一个处理器11022和至少一个存储器11021。
在一个实例中，所述CU1102可以由一个或多个单板构成，多个单板可以共同支持单一接入指示的无线接入网(如5G网)，也可以分别支持不同接入制式的无线接入网(如LTE网，5G网或其他网)。所述存储器11021和处理器11022可以服务于一个或多个单板。也就是说，可以每个单板上单独设置存储器和处理器。也可以是多个单板共用相同的存储 器和处理器。此外每个单板上还可以设置有必要的电路。所述DU1101可以由一个或多个单板构成，多个单板可以共同支持单一接入指示的无线接入网(如5G网)，也可以分别支持不同接入制式的无线接入网(如LTE网，5G网或其他网)。所述存储器11014和处理器11013可以服务于一个或多个单板。也就是说，可以每个单板上单独设置存储器和处理器。也可以是多个单板共用相同的存储器和处理器。此外每个单板上还可以设置有必要的电路。
图11所示的接入网设备能够实现上述方法实施例中涉及接入网设备的各个过程。图11所示的接入网设备中的各个模块的操作和/或功能，分别为了实现上述方法实施例中的相应流程。具体可参见上述方法实施例中的描述，为避免重复，此处适当省略详述描述。
本申请实施例中的术语“系统”和“网络”可被互换使用。“至少一个”是指一个或者多个，“多个”是指两个或两个以上。“和/或”，描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A、同时存在A和B、单独存在B的情况，其中A，B可以是单数或者复数。字符“/”一般表示前后关联对象是一种“或”的关系。“以下至少一项(个)”或其类似表达，是指的这些项中的任意组合，包括单项(个)或复数项(个)的任意组合。例如“A，B或C中的至少一个”包括A，B，C，AB，AC，BC或ABC。以及，除非有特别说明，本申请实施例提及“第一”、“第二”等序数词是用于对多个对象进行区分，不用于限定多个对象的顺序、时序、优先级或者重要程度等。
本领域内的技术人员应明白，本申请的实施例可提供为方法、系统、或计算机程序产品。因此，本申请可采用完全硬件实施例、完全软件实施例、或结合软件和硬件方面的实施例的形式。而且，本申请可采用在一个或多个其中包含有计算机可用程序代码的计算机可用存储介质(包括但不限于磁盘存储器、CD-ROM、光学存储器等)上实施的计算机程序产品的形式。
本申请是参照根据本申请的方法、设备(系统)、和计算机程序产品的流程图和/或方框图来描述的。应理解可由计算机程序指令实现流程图和/或方框图中的每一流程和/或方框、以及流程图和/或方框图中的流程和/或方框的结合。可提供这些计算机程序指令到通用计算机、专用计算机、嵌入式处理机或其他可编程数据处理设备的处理器以产生一个机器，使得通过计算机或其他可编程数据处理设备的处理器执行的指令产生用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的装置。
这些计算机程序指令也可存储在能引导计算机或其他可编程数据处理设备以特定方式工作的计算机可读存储器中，使得存储在该计算机可读存储器中的指令产生包括指令装置的制造品，该指令装置实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能。
这些计算机程序指令也可装载到计算机或其他可编程数据处理设备上，使得在计算机或其他可编程设备上执行一系列操作步骤以产生计算机实现的处理，从而在计算机或其他可编程设备上执行的指令提供用于实现在流程图一个流程或多个流程和/或方框图一个方框或多个方框中指定的功能的步骤。
显然，本领域的技术人员可以对本申请进行各种改动和变型而不脱离本申请的精神和范围。这样，倘若本申请的这些修改和变型属于本申请权利要求及其等同技术的范围之内，则本申请也意图包含这些改动和变型在内。

Claims (37)

  1. 一种小区切换方法，其特征在于，包括：
    确定人工智能AI目标小区，所述AI目标小区为预测的、终端设备可以切换到的服务小区；
    输出第一请求消息，所述第一请求消息用于请求所述AI目标小区对应的第二网络设备为所述终端设备分配所述AI目标小区对应的资源，所述第一请求消息用于指示以下至少一项：所述AI目标小区的标识信息、所述切换的类型为AI切换、激活时间信息、失效时间信息、或所述AI目标小区的预测准确度，所述激活时间信息用于指示所述终端设备切换到所述AI目标小区的最早时间，所述失效时间信息用于指示所述终端设备切换到所述AI目标小区的最晚时间。
  2. 如权利要求1所述的方法，其特征在于，所述AI目标小区为根据AI方式预测的，包括：
    所述AI目标小区是根据以下至少一项信息预测的，所述至少一项信息中包括：所述终端设备的第一测量信息、服务小区的负载信息、相邻小区的负载信息、所述终端设备的轨迹信息、所述终端设备的地理坐标信息、所述终端设备的运动方向、或所述终端设备的运动速度。
  3. 如权利要求1或2所述的方法，其特征在于，还包括：
    获取所述第二网络设备的第一响应消息，所述第一响应消息响应于所述第一请求消息，所述第一响应消息包括所述第二网络设备中允许所述终端设备进行AI切换的小区数量的指示信息。
  4. 如权利要求1至3中任一项所述的方法，其特征在于，还包括：
    获取所述第二网络设备的AI信息，所述AI信息用于指示以下至少一项：所述第二网络设备支持或不支持AI切换的指示信息、所述第二网络设备所支持的AI切换类型的指示信息、或所述第二网络设备允许进行AI切换的小区信息。
  5. 如权利要求1至4中任一项所述的方法，其特征在于，还包括：
    向所述第二网络设备转移所述终端设备的用户面数据；
    输出第一状态转发消息，所述第一状态转发消息用于指示第一网络设备向所述第二网络设备转移的用户面数据中的第一个下行业务数据单元SDU的编号，和/或所述转移的用户面数据中可以丢弃的SDU的编号。
  6. 如权利要求1至5中任一项所述的方法，其特征在于，还包括：
    确定切换所述终端设备到所述AI目标小区中的第一小区；
    输出第一配置消息，所述第一配置消息用于向所述终端设备指示所述第一小区的配置信息。
  7. 如权利要求1至5中任一项所述的方法，其特征在于，还包括：
    确定切换所述终端设备到第二小区，所述AI目标小区中不包含所述第二小区；
    输出第二配置消息，所述第二配置消息用于向所述终端设备指示所述第二小区的配置信息和所述AI目标小区的配置信息。
  8. 如权利要求1至5中任一项所述的方法，其特征在于，还包括：
    输出第三配置信息，所述第三配置信息用于向所述终端设备指示所述AI目标小区的 配置信息和切换触发配置信息，所述切换触发配置信息用于向所述终端设备指示切换到所述AI目标小区的触发条件。
  9. 如权利要求8所述的方法，其特征在于，还包括：
    确定更新所述AI目标小区的配置信息，和/或更新所述切换触发配置信息；
    输出第四配置信息，所述第四配置信息用于向所述终端设备指示更新的AI目标小区的配置信息，和/或，更新的切换触发配置信息。
  10. 如权利要求7至9中任一项所述的方法，其特征在于，所述AI目标小区的配置信息用于指示以下至少一项：所述AI目标小区的标识信息、随机接入信息、激活时间信息、或失效时间信息，所述随机接入信息用于指示所述终端设备切换到所述AI目标小区的随机接入资源，所述激活时间信息指示所述终端设备切换到所述AI目标小区的最早时间，所述失效时间信息指示所述终端设备切换到所述AI目标小区的最晚时间。
  11. 一种小区切换方法，其特征在于，包括：
    获取第一网络设备的第一请求消息，所述第一请求消息用于请求人工智能AI目标小区对应的第二网络设备为终端设备分配所述AI目标小区对应的资源；
    其中，所述第一请求消息用于指示以下至少一项：所述AI目标小区的标识信息、所述切换的类型为AI切换、激活时间信息、失效时间信息、或所述AI目标小区的预测准确度，所述激活时间信息用于指示所述终端设备切换到所述AI目标小区的最早时间，所述失效时间信息用于指示所述终端设备切换到所述AI目标小区的最晚时间。
  12. 如权利要求11所述的方法，其特征在于，所述AI目标小区是根据以下至少一项信息预测的，所述至少一项信息中包括：所述终端设备的第一测量信息、服务小区的负载信息、相邻小区的负载信息、所述终端设备的轨迹信息、所述终端设备的地理坐标信息、所述终端设备的运动方向、或所述终端设备的运动速度。
  13. 如权利要求11或12所述的方法，其特征在于，还包括：
    输出第一响应消息，所述第一响应消息响应于所述第一请求消息，所述第一响应消息包括所述第二网络设备中允许所述终端设备进行AI切换的小区数量的指示信息。
  14. 如权利要求11至13中任一项所述的方法，其特征在于，还包括：
    输出AI消息，所述AI信息用于指示以下至少一项：所述第二网络设备支持或不支持AI切换的指示信息、所述第二网络设备所支持的AI切换类型的指示信息、或所述第二网络设备允许进行AI切换的小区信息。
  15. 如权利要求11至14中任一项所述的方法，其特征在于，还包括：
    获取所述第一网络设备转移的所述终端设备的用户面数据；
    获取所述第一网络设备的第一状态转发消息，所述第一状态转发消息用于指示第一网络设备向所述第二网络设备转移的用户面数据中的第一个下行业务数据单元SDU的编号，和/或所述转移的用户面数据中可以丢弃的SDU的编号。
  16. 一种小区切换方法，其特征在于，包括：
    获取第一网络设备的第二配置信息，所述第二配置信息用于向终端设备指示第二小区的配置信息和人工智能AI目标小区的配置信息；
    根据所述第二小区的配置信息，执行到所述第二小区的切换。
  17. 如权利要求16所述的方法，其特征在于，还包括：
    当终端设备与所述第二小区的连接失败时，确定第一目标小区。
  18. 如权利要求17所述的方法，其特征在于，若所述终端设备侧存储有有效的所述AI目标小区的配置信息，所述方法还包括：
    当所述第一目标小区为所述AI目标小区中的小区时，执行到所述第一目标小区的切换流程；或者，
    当所述第一目标小区不为所述AI目标小区中的小区时，执行到所述第一目标小区的重建流程。
  19. 如权利要求17或18所述的方法，其特征在于，若所述终端设备侧未存储有有效的所述AI目标小区的配置信息，所述方法还包括：
    执行到所述第一目标小区的重建流程。
  20. 一种小区切换方法，其特征在于，包括：
    输出第五配置信息，所述第五配置信息用于指示终端设备上报第一反馈信息的触发条件；
    获取所述终端设备的第一反馈信息；
    确定人工智能AI目标小区的更新结果，所述AI目标小区的更新结果是根据所述第一反馈信息确定的，所述AI目标小区的更新结果为更新的所述终端设备可以切换到的服务小区。
  21. 如权利要求20所述的方法，其特征在于，所述第五配置信息用于指示以下至少一项：至少一个小区的信息和质量门限信息、参考位置信息和第一距离门限信息、轨迹变更触发信息、或时间上报指示信息，所述时间上报指示信息包括所述终端设备在所述第一反馈信息中携带或不携带时间信息的指示信息，所述时间信息为所述终端设备满足所述第五配置信息时的时间，或者所述终端设备上报所述第一反馈信息的时间。
  22. 如权利要求21所述的方法，其特征在于，当所述第五配置信息用于指示至少一个小区的标识信息和质量门限信息时，所述第一反馈信息用于指示满足所述第五配置信息的小区的标识信息，和/或，满足所述第五配置信息的小区的质量信息，或者，所述第一反馈信息用于指示不满足所述第五配置信息的小区的标识信息，和/或，不满足所述第五配置信息的小区的质量信息；或者，
    当所述第五配置信息用于指示参考位置信息和第一距离门限信息时，所述第一反馈信息用于指示所述终端设备最新的位置信息。
  23. 一种小区切换方法，其特征在于，包括：
    获取第一网络设备的第五配置信息，所述第五配置信息用于指示终端设备上报第一反馈信息的触发条件；
    输出第一反馈信息，所述第一反馈信息是在满足所述第五配置信息的触发条件时输出的，所述第一反馈信息用于更新人工智能AI目标小区，所述AI目标小区的更新结果为更新的所述终端设备可以切换到的服务小区。
  24. 如权利要求23所述的方法，其特征在于，所述第五配置信息用于指示以下至少一项：至少一个小区的信息和质量门限信息、参考位置信息和第一距离门限信息、轨迹变更触发信息或时间上报指示信息，所述时间上报指示信息包括所述终端设备在所述第一反馈信息中携带或不携带时间信息的指示信息，所述时间信息为所述终端设备满足所述第五配置信息时的时间，或者所述终端设备上报所述第一反馈信息的时间。
  25. 如权利要求24所述的方法，其特征在于，当所述第五配置信息用于指示至少一个 小区的标识信息和质量门限信息时，所述第一反馈信息用于指示满足所述第五配置信息的小区的标识信息，和/或，满足所述第五配置信息的小区的质量信息，或者，所述第一反馈信息用于指示不满足所述第五配置信息的小区的标识信息，和/或，不满足所述第五配置信息的小区的质量信息；或者，
    当所述第五配置信息用于指示参考位置信息和第一距离门限信息时，所述第一反馈信息用于指示所述终端设备最新的位置信息。
  26. 一种装置，其特征在于，用于实现权利要求1至10任一项所述的方法，或用于实现权利要求20至22任一项所述的方法。
  27. 一种装置，其特征在于，包括处理器和存储器，所述处理器和所述存储器耦合，所述处理器用于实现权利要求1至10任一项所述的方法，或用于实现权利要求20至22任一项所述的方法。
  28. 一种装置，其特征在于，包括处理器和通信接口，所述处理器利用所述通信接口，实现权利要求1至10任一项所述的方法，或用于实现权利要求20至22任一项所述的方法。
  29. 一种装置，其特征在于，用于实现权利要求11至15任一项所述的方法。
  30. 一种装置，其特征在于，包括处理器和存储器，所述处理器和所述存储器耦合，所述处理器用于实现权利要求11至15任一项所述的方法。
  31. 一种装置，其特征在于，包括处理器和通信接口，所述处理器利用所述通信接口，实现权利要求11至15任一项所述的方法。
  32. 一种装置，其特征在于，用于实现权利要求16至19任一项所述的方法，或者用于实现权利要求23至25任一项所述的方法。
  33. 一种装置，其特征在于，包括处理器和存储器，所述处理器和所述存储器耦合，所述处理器用于实现权利要求16至19任一项所述的方法，或用于实现权利要求23至25任一项所述的方法。
  34. 一种装置，其特征在于，包括处理器和通信接口，所述处理器利用所述通信接口，实现权利要求16至19任一项所述的方法，或用于实现权利要求23至25任一项所述的方法。
  35. 一种通信系统，其特征在于，包括权利要求26至28任一项所述的装置，和权利要求29至31任一项所述的装置；或，
    包括权利要求26至28任一项所述的装置，和权利要求32至34任一项所述的装置；或，
    包括权利要求26至28任一项所述的装置，权利要求29至31任一项所述的装置，和权利要求32至34任一项所述的装置。
  36. 一种计算机可读存储介质，其特征在于，所述计算机可读存储介质上存储有指令，当所述指令在计算机上运行时，使得计算机执行权利要求1至10任一项所述的方法，或者权利要求11至15任一项所述的方法，或者权利要求16至19任一项所述的方法，或者权利要求20至22任一项所述的方法，或者权利要求23至25任一项所述的方法。
  37. 一种计算机程序产品，其特征在于，包括指令，当所述指令在计算机上运行时，使得计算机执行权利要求1至10任一项所述的方法，或者权利要求11至15任一项所述的方法，或者权利要求16至19任一项所述的方法，或者权利要求20至22任一项所述的方法， 或者权利要求23至25任一项所述的方法。
PCT/CN2022/081498 2021-04-02 2022-03-17 一种小区切换方法及装置 WO2022206411A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP22778594.6A EP4287705A4 (en) 2021-04-02 2022-03-17 CELL TRANSFER METHOD AND APPARATUS
US18/461,492 US20230422124A1 (en) 2021-04-02 2023-09-05 Cell handover method and apparatus

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110361698.XA CN115190550A (zh) 2021-04-02 2021-04-02 一种小区切换方法及装置
CN202110361698.X 2021-04-02

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/461,492 Continuation US20230422124A1 (en) 2021-04-02 2023-09-05 Cell handover method and apparatus

Publications (1)

Publication Number Publication Date
WO2022206411A1 true WO2022206411A1 (zh) 2022-10-06

Family

ID=83455607

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/081498 WO2022206411A1 (zh) 2021-04-02 2022-03-17 一种小区切换方法及装置

Country Status (4)

Country Link
US (1) US20230422124A1 (zh)
EP (1) EP4287705A4 (zh)
CN (1) CN115190550A (zh)
WO (1) WO2022206411A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024093739A1 (zh) * 2022-11-04 2024-05-10 华为技术有限公司 一种通信方法及装置
WO2024098299A1 (zh) * 2022-11-09 2024-05-16 Oppo广东移动通信有限公司 通信方法以及通信设备

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116744375A (zh) * 2022-03-01 2023-09-12 维沃移动通信有限公司 小区切换方法、装置及用户设备
CN117998437A (zh) * 2022-11-03 2024-05-07 展讯通信（上海）有限公司 Ai模型更新方法及通信装置
WO2024109114A1 (en) * 2023-07-14 2024-05-30 Zte Corporation Slice resource optimization method for wireless communication, apparatus, and computer-readable storage medium

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109447275A (zh) * 2018-11-09 2019-03-08 西安邮电大学 Udn中基于机器学习的切换算法
WO2020077517A1 (zh) * 2018-10-16 2020-04-23 华为技术有限公司 一种高速移动场景下的小区切换方法及装置
CN111083753A (zh) * 2019-11-08 2020-04-28 中兴通讯股份有限公司 一种切换方法、切换装置及网络系统
CN112020108A (zh) * 2019-05-30 2020-12-01 华为技术有限公司 小区切换方法和装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2020077517A1 (zh) * 2018-10-16 2020-04-23 华为技术有限公司 一种高速移动场景下的小区切换方法及装置
CN109447275A (zh) * 2018-11-09 2019-03-08 西安邮电大学 Udn中基于机器学习的切换算法
CN112020108A (zh) * 2019-05-30 2020-12-01 华为技术有限公司 小区切换方法和装置
CN111083753A (zh) * 2019-11-08 2020-04-28 中兴通讯股份有限公司 一种切换方法、切换装置及网络系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4287705A4 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2024093739A1 (zh) * 2022-11-04 2024-05-10 华为技术有限公司 一种通信方法及装置
WO2024098299A1 (zh) * 2022-11-09 2024-05-16 Oppo广东移动通信有限公司 通信方法以及通信设备

Also Published As

Publication number Publication date
EP4287705A4 (en) 2024-07-31
US20230422124A1 (en) 2023-12-28
CN115190550A (zh) 2022-10-14
EP4287705A1 (en) 2023-12-06

Similar Documents

Publication Publication Date Title
WO2022206411A1 (zh) 一种小区切换方法及装置
WO2022148489A1 (zh) 切换处理方法与装置、终端、网络设备和存储介质
WO2022227995A1 (zh) 一种节能方法及装置
KR20220038091A (ko) 무선 통신 시스템에서 rrm 측정을 수행하는 방법 및 단말
WO2022041285A1 (zh) 一种模型数据传输方法及通信装置
WO2022067643A1 (zh) 一种小区选择方法、寻呼方法及装置
US20240040450A1 (en) Information transmission method and apparatus
CN115278763A (zh) 用于获取负载信息的通信方法及装置
KR20230131252A (ko) 통신 방법 및 장치
WO2022209234A1 (ja) Ｒａｎノード、ｕｅ及び方法
CN116321277A (zh) 一种测量上报方法及装置
WO2023131406A1 (en) Apparatus, methods, and computer programs for predicting network performance before triggering handover
US20230292198A1 (en) Machine Learning in Radio Connection Management
US20240121687A1 (en) Apparatus, method, and computer program
WO2024152978A1 (zh) 测量预测方法与装置、终端设备、网络设备和芯片
WO2023201746A1 (en) Method, device, and system for resource status report in wireless networks
US20240049089A1 (en) Network energy saving mode enhancements
EP4366382A2 (en) Apparatus, method, and computer program
EP4408071A1 (en) Communication method and communication apparatus
US20240244499A1 (en) Methods and apparatus for providing mobility state information
US20240340678A1 (en) Measurement reporting
US20240205690A1 (en) Method for sharing baseband computing resources
WO2023108354A1 (zh) 无线通信的方法、终端设备和网络设备
WO2023138669A1 (zh) 一种通信方法及装置
WO2024170439A1 (en) Methods to signal ue-associated types of available ai/ml assistance information

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22778594

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 202317057598

Country of ref document: IN

WWE Wipo information: entry into national phase

Ref document number: 2022778594

Country of ref document: EP

ENP Entry into the national phase

Ref document number: 2022778594

Country of ref document: EP

Effective date: 20230831

NENP Non-entry into the national phase

Ref country code: DE