Information processing method, device and system in cell switching process

Abstract

The invention discloses an indication method, device and system in a cell switching process, and the method comprises the steps: in a switching preparation stage, a source cell obtains air interface configuration information which is pre-configured for a terminal and is related to an artificial intelligence (AI) function from a target cell, and transmits the air interface configuration information to the terminal; the terminal judges whether the terminal itself can maintain the continuity of the AI reasoning function in the target cell environment based on the configuration information, and feeds back a judgment result to the source cell; and the source cell forwards the indication information to the target cell. The target cell determines a corresponding air interface configuration processing mode before the terminal accesses based on the indication information: if the indication supports, pre-configuration is directly used after the terminal accesses so as to maintain AI task continuity; and if the indication does not support, triggering a standard reconfiguration process, and enabling the terminal to return to the non-AI mode. Through cooperative advanced indication of the terminal and the network, the interruption time of the AI function of the terminal with the cross-cell generalization capability in the switching process is effectively shortened, and unnecessary signaling overhead is reduced.

Description

Technical Field

[0001] This application relates to the field of wireless communication technology, and in particular to an information processing method, device and system for cell handover. Background Technology

[0002] Leveraging artificial intelligence / machine learning (AI / ML) technologies to enhance 5G network performance is a crucial component in achieving the integration of 5G and AI / ML technologies and building 5G-Advanced intelligent networks. The 3GPP standards organization initiated standard research for intelligent radio access networks (RANs) starting with Rel-16, and in Rel-18, it initiated a project on AI / ML-based 5G air interface enhancement, thus beginning international standardization work on the integration of 5G air interface and AI / ML. With the further deep integration of 5G-A / 6G mobile communication technologies and AI / ML technologies, more and more air interface functions will utilize AI / ML technologies to improve user experience and optimize network performance, resource management, and energy consumption.

[0003] However, in mobile communication scenarios, terminal devices need to perform cell handover due to location changes. Traditional handover procedures (such as RRC reconfiguration and capability reporting in 5G) typically introduce latency and signaling overhead, potentially causing service interruptions to AI inference tasks during handover and affecting continuous user experience. Current standard handover procedures do not consider the cross-cell generalization capability of terminal AI models, nor do they design corresponding signaling interactions to utilize this information to optimize the handover process. For 5G evolution or future 6G air interfaces, the AI ​​models deployed on terminal devices during cell handover may possess cross-cell generalization capabilities. This means that after the device switches from its current source cell to the target cell, it can still perform AI inference functions based on its current AI capabilities. Therefore, during cell handover, RRC reconfiguration for AI functions is unnecessary, and the terminal does not need to repeatedly report the applicability of AI functions, thereby reducing the time interval of AI function disconnection during handover. However, current standard handover procedures do not consider the cross-cell generalization capability of terminal AI models, nor do they design corresponding signaling interactions to utilize this information to optimize the handover process. Summary of the Invention

[0004] This application proposes an information processing method, device, and system for cell handover, which aims to address the problem that terminal AI functions with cross-cell generalization capabilities may be unnecessarily interrupted during cell handover, optimize the handover process, and reduce latency and signaling overhead. It is particularly suitable for 5G-Advanced and subsequent evolution communication systems.

[0005] Firstly, this application proposes an information processing method during cell handover. This includes: acquiring air interface configuration information related to the target cell and artificial intelligence (AI) functions; based on the air interface configuration information, transmitting and receiving uplink signaling indication information characterizing the continuity of the terminal's AI inference function in the target cell environment; and, according to the indication information, performing handover control operations related to the continuity of the AI ​​function to maintain or terminate the terminal's AI inference task.

[0006] In one possible implementation, the step of performing a handover control operation related to the continuity of AI functions according to the indication information includes: in response to the indication information indicating support, determining to directly use the pre-configured air interface configuration to continue executing the AI ​​inference function after the terminal accesses the target cell; or, in response to the indication information indicating non-support, determining to fall back to the traditional non-AI mode after the terminal accesses the target cell and wait for the reconfiguration of the air interface configuration information related to the AI ​​function.

[0007] Secondly, this application proposes an indication method for a network-side device in a source cell during cell handover, comprising: during the handover process of a terminal from a source cell to a target cell, obtaining pre-configured air interface configuration information related to the AI ​​function of the terminal from the target cell; sending downlink information to the terminal, the downlink information including at least the identifier of the target cell and the air interface configuration information; receiving indication information from the terminal, the indication information indicating whether the terminal can continue to perform AI inference to achieve a specific air interface function under the target cell and the air interface configuration; and sending the indication information to the target cell.

[0008] In one possible implementation, after sending the indication information to the target network device, the method further includes: in response to the indication information indicating support, instructing the target network device to directly use the pre-configured air interface configuration for communication after the terminal accesses; or, in response to the indication information indicating non-support, instructing the target network device to reconfigure the air interface parameters for the terminal according to the standard non-AI handover procedure.

[0009] In another possible implementation, obtaining the air interface configuration information pre-configured for the terminal and related to its AI functions from the target network device includes: sending a handover request to the target network device; and receiving a handover request confirmation message from the target network device, which carries the air interface configuration information.

[0010] Thirdly, this application proposes an indication method for a network-side device in a target cell during cell handover, comprising: receiving a handover request from a source cell; responding to the handover request, generating and pre-configuring air interface configuration information related to the AI ​​function of a terminal; sending the air interface configuration information to the network device of the source cell; receiving indication information from the network device of the source cell, the indication information being used to indicate whether the terminal can continue to perform AI inference to achieve a specific air interface function under the target cell and the air interface configuration; and based on the indication information, determining the air interface configuration processing method related to the AI ​​function after the terminal accesses the network, so as to maintain or terminate the AI ​​inference task of the terminal. [Claim 6] In one possible implementation, determining the air interface configuration processing method related to the AI ​​function after the terminal accesses, based on the indication information, includes: in response to the indication information indicating support, determining to directly use the pre-configured air interface configuration to communicate with the terminal after the terminal accesses; in response to the indication information indicating non-support, determining to trigger a Radio Resource Control (RRC) reconfiguration process to reconfigure the air interface configuration information related to the AI ​​function for the terminal after the terminal accesses.

[0011] In another possible implementation, the generation and pre-configuration of air interface configuration information related to the AI ​​function of the terminal is done based on AI capability information or historical configuration information of the terminal received from the source network device.

[0012] Fourthly, this application proposes an indication method for a terminal-side device during cell handover, comprising: receiving downlink information from a source cell during cell handover, the downlink information including a target cell identifier and air interface configuration information pre-configured by the target cell and related to the AI ​​function of the terminal; determining, based on the air interface configuration information and the target cell identifier, whether the terminal can continue to perform AI inference to achieve a specific air interface function under the target cell and the air interface configuration; and sending indication information to the source cell, the indication information being used to indicate the result of the determination.

[0013] In one possible implementation, based on the indication information, a handover control operation related to the continuity of AI function is performed, including: if the indication information generated by the user indicates support, then it is determined that the current AI model will continue to be used for inference after accessing the target cell; or, if the indication information generated by the user indicates no support, then it is determined that the AI ​​inference function will be suspended and the user will fall back to the traditional non-AI mode after accessing the target cell.

[0014] Fifthly, this application also proposes a network-side device for implementing the method described in any one of the first to fourth aspects. The network-side device includes at least one module for processing at least one of the following functions: generating or acquiring air interface configuration information pre-configured for a terminal and related to its AI function; sending downlink information, the downlink information including at least the identifier of the target cell and the air interface configuration information; receiving or sending indication information, the indication information indicating whether the terminal can continue to perform AI inference to achieve a specific air interface function under the target cell and the air interface configuration; and determining, based on the indication information, the air interface configuration processing method related to the AI ​​function after the terminal accesses the network to maintain or terminate the terminal's AI inference task.

[0015] Sixthly, this application also proposes a terminal-side device for implementing the method described in any one of the first to fourth aspects. At least one module in the terminal-side device is configured to perform at least one of the following functions: receiving downlink information from a source cell, the downlink information including a target cell identifier and air interface configuration information pre-configured by the target cell and related to the AI ​​function of the terminal; determining, based on the air interface configuration information and the target cell identifier, whether the terminal can continue to perform AI inference to achieve a specific air interface function under the target cell and the air interface configuration; and sending indication information to the source cell, the indication information indicating the result of the determination.

[0016] In a seventh aspect, this application also proposes a communication device, comprising: a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the method as described in any one of the first to fourth aspects.

[0017] Eighthly, this application also proposes a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method described in any one of the first to fourth aspects.

[0018] Ninthly, this application also proposes a mobile communication system, characterized in that it comprises at least one network-side device as described in the fifth aspect and at least one terminal-side device as described in the sixth aspect. Of the network-side devices, at least one is used for a source cell and / or at least one is used for a target cell.

[0019] The above-mentioned at least one technical solution adopted in the embodiments of this application can achieve the following beneficial effects: when the terminal AI model has cross-cell generalization capability, it can shorten the interruption time of the terminal device AI function during the handover process, avoid unnecessary model reconfiguration and signaling interaction delay; reduce the signaling overhead between the network side and the terminal, and avoid the complete RRC reconfiguration and capability reporting process. Attached Figure Description

[0020] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings: Figure 1 This is a schematic diagram of the traditional handover process between base stations; Figure 2 A schematic diagram of the traditional RRC signaling configuration process related to AI functions; Figure 3 This is a diagram illustrating the handover process between different cells for a terminal. Figure 4 This is a flowchart illustrating an embodiment of the method of this application; Figure 5 This is a flowchart illustrating an embodiment of the method of this application used in a network-side device of a source cell; Figure 6 This is a flowchart illustrating an embodiment of the method of this application used in a network-side device of a target cell; Figure 7 This is a flowchart illustrating an embodiment of the method of this application used in a terminal-side device; Figure 8 This is a schematic diagram of an embodiment of a network-side device; Figure 9 This is a schematic diagram of an embodiment of the terminal-side device; Figure 10 This is a schematic diagram of the structure of a network-side device according to another embodiment of the present invention; Figure 11 This is a block diagram of a terminal-side device according to another embodiment of the present invention. Detailed Implementation

[0021] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0022] First, combine Figure 1 , Figure 2 Explain the problems with existing technologies. Figure 1 This is a schematic diagram of traditional inter-gNB handover procedures, taken from standard TS 38.300 (section 9.2.3.1). Figure 1 As shown, during the handover process, the UE receives RRCReconfiguration signaling from the source cell, which contains access information of the target cell, such as frequency point and network identifier. After the UE accesses the target cell, the target cell will reissue the relevant network configuration to the UE through RRCConfiguration or RRCReconfiguration signaling. Figure 2 This is a schematic diagram of the RRC signaling configuration process related to AI functions (from Reportof3GPPTSGRANWG2meeting#127). Figure 2 As can be seen, the UE needs to re-exchange information such as UE Capability and Applicable Function Reporting with the target cell. Therefore, the AI ​​model inference function cannot be executed during cell handover, resulting in the interruption of AI service.

[0023] Figure 3 The diagram illustrates a terminal's inter-cell handover. However, with the development of AI model capabilities, the AI ​​models on terminal devices can exhibit better cross-cell generalization capabilities. This means that the terminal device's AI model can maintain stable inference performance under the network configuration of the source cell before handover, the network configuration during handover, and the network configuration of the target cell after handover. This implies that the AI ​​model can still perform model inference tasks normally during inter-cell handover without needing to readjust the model or reconfigure parameters for the target cell after handover. This provides new possibilities for reducing AI service interruption time during handover. Therefore, through coordinated instructions between the terminal and the network, the continuity of AI functions during cell handover can be achieved.

[0024] The basic idea of ​​this invention is as follows: When a terminal with air interface AI functionality is switching cells, the relevant AI air interface configuration information of the target cell is sent to the terminal via the source cell; the terminal determines whether it supports the configuration and reports it to the source cell. If it supports the configuration, the terminal will directly continue to run the AI ​​function after access; if it does not support the configuration, it will fall back to the traditional non-AI mode and reconfigure according to the standard procedure.

[0025] The technical solutions provided by the various embodiments of this application are described in detail below with reference to the accompanying drawings.

[0026] Figure 4This is a flowchart illustrating an embodiment of the method proposed in this application, showing the general flow of an information processing method during cell handover. This method is collaboratively executed by network-side entities (such as the source cell and target cell) and / or terminal-side entities participating in the cell handover process, aiming to optimize the handover continuity of AI functions through advance information exchange and decision-making. Figure 4 As shown, the method includes the following steps: Step 110: Obtain air interface configuration information related to the target cell and artificial intelligence (AI) functions.

[0027] This step is the starting point of the process, and its purpose is to prepare key information for subsequent decision-making. This "acquisition" action can be performed by different entities and corresponds to different specific implementations: When executed by the source cell network-side equipment, this manifests as follows: during the handover process from the source cell to the target cell, the air interface configuration information pre-configured for the terminal and related to its AI functions is obtained from the target cell. This is typically accomplished by the source cell sending a handover request to the target cell during the handover preparation phase, with the target cell including this pre-configured information in its response.

[0028] When executed by the terminal-side device, it manifests as receiving a downlink message from the source cell containing the air interface configuration information, which is reflected in subsequent steps.

[0029] The air interface configuration information related to the target cell and AI functions includes at least the target cell identifier and air interface configuration parameters pre-configured by the target cell. The target cell identifier may include one or more combinations of NR cell global identifier (NCGI), physical cell ID, base station gNB ID, public land mobile network identifier (PLMN ID), tracking area identifier (TAI), mobile country code (MCC), and mobile network code (MNC). This information collectively identifies the target cell to which the configuration applies and the specific set of AI air interface parameters.

[0030] Step 120: Based on the air interface configuration information, transmit and receive indication information representing the continuity of the terminal's AI inference function in the target cell environment via uplink signaling. This step is the core of information processing and interaction, involving the judgment and feedback of the information obtained in step 110.

[0031] Judgment and Generation: Based on the acquired air interface configuration information (e.g., obtained by the terminal from the source cell), the terminal-side device needs to determine whether it can continue to perform AI inference to achieve specific air interface functions under the target cell and the air interface configuration. These specific air interface functions may include AI-based time-domain channel state information (CSI) prediction, AI-based beam physical layer reference signal received power (L1-RSRP) prediction, or AI-based channel estimation, etc. This judgment essentially assesses the terminal's own AI model's cross-cell generalization capability to the target cell's pre-configuration.

[0032] Information exchange: After the judgment is completed, the terminal-side device generates indication information representing this capability and sends it to the source cell network-side device via uplink signaling (e.g., RRC signaling). Subsequently, the source cell network-side device forwards the indication information to the target cell network-side device. Therefore, the "send and receive" action covers a complete signaling exchange chain, including terminal sending, source cell receiving and forwarding, and target cell receiving.

[0033] Step 130: According to the instruction information, perform a switching control operation related to the continuity of AI function to maintain or terminate the AI ​​inference task of the terminal.

[0034] This step is the final decision and execution based on the instructions, which determines the fate of the AI ​​function after the switch.

[0035] If the indicated information supports this, then control operations to maintain the continuity of the AI ​​inference task are executed. Specifically, this manifests as follows: The target cell network-side equipment determines that after the terminal accesses the network, it will directly use the pre-configured air interface configuration to communicate with the terminal. This avoids reconfiguration after access.

[0036] The source cell network side equipment can use this to instruct the target cell to adopt this fast access strategy, and the terminal can directly use the pre-configured air interface configuration for communication after access.

[0037] The terminal-side device or the target cell network testing device determines that the terminal-side device will continue to use the current AI model to perform inference after accessing the target cell.

[0038] If the indicated information does not support it, a control operation will be performed that may temporarily terminate the AI ​​inference task. Specifically: The target cell network-side equipment determines that after the terminal accesses the network, it triggers a Radio Resource Control (RRC) reconfiguration procedure to reconfigure the air interface configuration information related to the AI ​​function for the terminal. The terminal cannot use the AI ​​function until the reconfiguration is complete.

[0039] The source cell network-side equipment can instruct the target cell to operate according to the standard non-AI handover procedure to reconfigure the air interface parameters for the terminal.

[0040] The terminal-side device or the target cell network testing device determines that the terminal-side device suspends the AI ​​inference function and reverts to the traditional non-AI mode after accessing the target cell.

[0041] It should be noted that the above steps are used for network entities in a wireless communication system, including terminal-side devices, network-side devices, or other intermediate devices; the above steps can also be used for service devices that provide information processing for the network entity devices; the above steps can also be used for any device, system, subsystem, circuit, chip, or software entity that provides information reception, transmission, identification, and processing for terminal-side devices or network-side devices.

[0042] Figure 5 This is a flowchart illustrating an embodiment of the method of this application used in a source cell network-side device. The method described in any embodiment of the first aspect of this application, used in a source cell network-side device, includes the following steps 210-240: Step 210: During the process of the terminal switching from the source cell to the target cell, obtain the air interface configuration information pre-configured for the terminal and related to its AI function from the target cell.

[0043] Specifically, during the cell handover process, the source cell sends a request to the target cell, and the target cell sends the air interface configuration information pre-configured for the terminal and related to its AI functions back to the source cell. This acquisition action can be further specified as: sending a handover request to the target network device and receiving a handover request confirmation message from the target network device, which carries the air interface configuration information.

[0044] Step 220: Send downlink information to the terminal, the downlink information including at least the identifier of the target cell and the air interface configuration information.

[0045] That is, the source cell sends the identifier of the target cell and the air interface configuration information related to its AI function pre-configured by the target cell to the terminal. The identifier of the target cell may include, but is not limited to, one or more combinations of the following: NCGI (NR Cell Global Identifier), Physical Cell ID, Base Station gNB ID, PLMN ID, Tracking Area Identity (TAI), Mobile Country Code (MCC), and Mobile Network Code (MNC).

[0046] Step 230: Receive indication information from the terminal, the indication information being used to indicate whether the terminal can continue to perform AI inference to achieve specific air interface functions under the target cell and the air interface configuration.

[0047] After receiving the information in step 220, the terminal determines whether it can continue to perform AI inference to complete the specific air interface function under the target cell and air interface configuration, and then sends the instruction information back to the source cell.

[0048] Step 240: Send the instruction information to the target cell.

[0049] After receiving the instruction from the terminal, the source base station forwards the instruction to the target cell.

[0050] In a more specific implementation, after sending the indication information to the target network device, the source cell can also perform further control decisions based on the indication: if the indication information indicates support, the target network device is instructed to directly use the pre-configured air interface configuration for communication after the terminal accesses; if the indication information indicates no support, the target network device is instructed to reconfigure the air interface parameters for the terminal according to the standard non-AI handover procedure. This allows the source cell to more proactively coordinate post-handover behavior, ensuring a smooth process.

[0051] Figure 6 This is a flowchart illustrating an embodiment of the method of this application used in a network-side device of a target cell. The method described in any embodiment of the first aspect of this application, used in a network-side device of a target cell, includes the following steps 310-350: Step 310: Receive a handover request from the source cell.

[0052] Step 320: In response to the handover request, generate and pre-configure air interface configuration information related to the terminal's AI functions. The target cell generates a set of pre-configured air interface parameters related to the terminal's AI functions based on the request. The generation and pre-configuration of the air interface configuration information related to the terminal's AI functions can be based on AI capability information or historical configuration information received from the source network device. This helps improve the accuracy of pre-configuration and the terminal's acceptance.

[0053] Step 330: Send the air interface configuration information to the network device of the source cell.

[0054] The target cell sends the generated pre-configuration information back to the source cell for it to forward to the terminal.

[0055] Step 340: Receive indication information from the network device of the source cell, the indication information being used to indicate whether the terminal can continue to perform AI inference to achieve a specific air interface function under the target cell and the air interface configuration.

[0056] Step 350: Based on the indication information, determine the air interface configuration processing method related to the AI ​​function after the terminal is connected, so as to maintain or terminate the AI ​​inference task of the terminal.

[0057] The "processing method" here refers to the service plan decision made by the target cell before terminal access. Specifically: if the indication is "supported," then the pre-configured air interface configuration will be used directly to communicate with the terminal after access; if the indication is "not supported," then the process will fall back to the standard handover procedure, that is, the Radio Resource Control (RRC) reconfiguration procedure will be triggered after terminal access, and the air interface configuration information related to AI functions will be reconfigured for the terminal in the target cell via RRC signaling. This decision directly corresponds to "maintaining" or "terminating" the continuity of the terminal's AI inference task in the target cell.

[0058] Figure 7 This is a flowchart illustrating an embodiment of the method of this application used in a terminal-side device. The method described in any embodiment of the first aspect of this application, used in a terminal-side device, includes the following steps 410-430: Step 410: During cell handover, receive downlink information from the source cell. This downlink information includes the target cell identifier and air interface configuration information pre-configured by the target cell and related to the terminal's AI functions. At this time, the terminal is moving, meeting the cell handover conditions, and the cell handover process needs to be executed.

[0059] Step 420: Based on the air interface configuration information and the target cell identifier, determine whether the terminal can continue to perform AI inference to achieve specific air interface functions under the target cell and the air interface configuration.

[0060] This judgment is based on the cross-cell generalization capability of the terminal's own AI model. The specific air interface functions implemented by the AI ​​inference function may include AI-based time-domain channel state information (CSI) prediction, AI-based beam physical layer reference signal received power (L1-RSRP) prediction, or AI-based channel estimation.

[0061] Step 430: Send indication information to the source cell, the indication information being used to indicate the result of the judgment.

[0062] The terminal sends an instruction to the source cell, informing it of its judgment result.

[0063] Furthermore, after executing step 430, the terminal itself plans subsequent actions based on the generated indication information: if the indication information indicates support, it determines to continue using the current AI model to perform inference after accessing the target cell; if the indication information indicates non-support, it determines to pause the AI ​​inference function and fall back to the traditional non-AI mode after accessing the target cell. This allows the terminal to prepare for mode switching in advance, optimizing the user experience.

[0064] Figure 8This is a schematic diagram of an embodiment of a network-side device.

[0065] This application also proposes a network-side device for implementing the method of any embodiment of this application. The network-side device is used to implement the information processing method proposed in this application. Specifically, it is configured to process a switching instruction process related to the continuity of terminal AI functions.

[0066] The network-side device includes at least one module for processing at least one of the following functions: generating or acquiring air interface configuration information pre-configured for the terminal and related to its AI function; sending downlink information, the downlink information including at least the identifier of the target cell and the air interface configuration information; receiving or sending indication information, the indication information indicating whether the terminal can continue to perform AI inference to achieve a specific air interface function under the target cell and the air interface configuration; and, based on the indication information, determining whether the air interface configuration processing method related to the AI ​​function after the terminal accesses the network is to maintain or terminate the terminal's AI inference task.

[0067] To implement the above technical solution, this application proposes a network-side device 500, which includes a network transmitting module 501, a network determining module 502, and a network receiving module 503 that are interconnected.

[0068] When the network-side device is defined in the source cell, each module is configured as follows: The network receiving module 503 is used to obtain AI air interface configuration information pre-configured for the terminal from the target cell; The network sending module 501 is used to send downlink information containing the target cell identifier and air interface configuration information to the terminal, and to send the indication information from the terminal to the target cell. The network determination module 502 can be used to generate corresponding operation instructions for the target cell after processing the instruction information.

[0069] When the network-side device is configured as the target cell device, each module is specifically configured as follows: The network receiving module 503 is used to receive the handover request from the source cell and the indication information fed back by the terminal; The network determination module 502 is used to generate AI air interface pre-configuration information for the terminal and determine the processing method after access based on the indication information; The network sending module 501 is used to send the air interface configuration information to the source cell.

[0070] The specific methods for implementing the functions of the network sending module, network determining module, and network receiving module are as described in the various method embodiments of this application, and will not be repeated here.

[0071] The network-side equipment described in this application may refer to base station facilities, network-side equipment or servers connected to base stations, systems that provide services for the aforementioned equipment, or any system, subsystem, module, circuit, chip or software operating device that provides information reception, transmission, identification and processing for the aforementioned equipment.

[0072] Figure 9 This is a schematic diagram of an embodiment of the terminal-side device.

[0073] This application also proposes a terminal-side device for implementing the method of any embodiment of this application. The terminal-side device is used to autonomously judge and provide feedback based on the target cell AI air interface configuration information sent by the network side during cell handover, in order to support the continuous optimization of AI functions.

[0074] At least one module in the terminal-side device is configured to perform at least one of the following functions: receiving downlink information from a source cell, the downlink information including a target cell identifier and air interface configuration information pre-configured by the target cell and related to the AI ​​function of the terminal; determining, based on the air interface configuration information and the target cell identifier, whether the terminal can continue to perform AI inference to achieve a specific air interface function under the target cell and the air interface configuration; and sending indication information to the source cell, the indication information being used to indicate the result of the determination.

[0075] To implement the above technical solution, this application proposes a terminal-side device 600, which includes a terminal transmitting module 601, a terminal determining module 602, and a terminal receiving module 603 connected to each other.

[0076] Each module is configured as follows: the terminal receiving module 603 is used to receive downlink information from the source cell during cell handover, which includes the target cell identifier and pre-configured AI air interface information; the terminal determining module 602 is used to determine the terminal's ability to continue performing AI inference functions in the target cell environment based on the received information, and can further determine its initial working mode in the target cell based on the determination result; the terminal sending module 601 is used to send indication information representing the determination result to the source cell.

[0077] The specific methods for implementing the functions of the terminal sending module, the terminal determining module, and the terminal receiving module are as described in the various method embodiments of this application, and will not be repeated here.

[0078] The terminal-side equipment described in this application may refer to user equipment (UE), personal mobile terminal, smart terminal, mobile phone, computer with communication function, system that provides services for the above-mentioned equipment, or any system, subsystem, module, circuit, chip or software running device that provides information reception, transmission, identification and processing for the above-mentioned equipment.

[0079] Figure 10 A schematic diagram of a network-side device according to another embodiment of the present invention is shown. As shown, the network-side device 700 includes a processor 701, a wireless interface 702, and a memory 703. The wireless interface may consist of multiple components, including a transmitter and a receiver, providing a unit for communication with various other devices over a transmission medium. The wireless interface implements communication functions with the terminal-side device, processes wireless signals through receiving and transmitting devices, and the data carried by the signals is communicated with the memory or processor via an internal bus structure. The memory 703 contains a computer program that executes any embodiment of this application, and the computer program runs or modifies the processor 701. When the memory, processor, and wireless interface circuit are connected through a bus system, the bus system includes a data bus, a power bus, a control bus, and a status signal bus, which will not be described in detail here.

[0080] Figure 11 This is a block diagram of a terminal-side device according to another embodiment of the present invention. The terminal-side device 800 includes at least one processor 801, a memory 802, a user interface 803, and at least one wireless network interface 804. The various components in the terminal-side device 800 are coupled together via a bus system. The bus system is used to implement communication between these components. The bus system includes a data bus, a power bus, a control bus, and a status signal bus.

[0081] User interface 803 may include a display, keyboard, or clicking device, such as a mouse, trackball, touchpad, or touchscreen.

[0082] The memory 802 stores executable modules or data structures. The memory may store an operating system and application programs. The operating system includes various system programs, such as a framework layer, core library layer, and driver layer, used to implement various basic business functions and handle hardware-based tasks. Application programs include various applications, such as media players and browsers, used to implement various application functions.

[0083] In an embodiment of the present invention, the memory 802 contains a computer program that executes any embodiment of the present application, the computer program being run on or modified by the processor 801.

[0084] The memory 802 includes a computer-readable storage medium. The processor 801 reads the information in the memory 802 and, in conjunction with its hardware, completes the steps of the above-described method. Specifically, the computer-readable storage medium stores a computer program, which, when executed by the processor 801, implements the steps of the method embodiments described in any of the above embodiments.

[0085] As a communication device, whether configured on the network side or the terminal side, processors 701 and 801 may be integrated circuit chips with signal processing capabilities. In implementation, each step of the method in this application can be completed by integrated logic circuits in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, a digital signal processor, an application-specific integrated circuit (ASIC), a readily available programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in the embodiments of this invention can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor.

[0086] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. In a typical configuration, the device of this application includes one or more processors (CPUs), an input / output user interface, a network interface, and memory.

[0087] Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0088] Therefore, this application also proposes a computer-readable medium storing a computer program that, when executed by a processor, implements the steps of the method described in any embodiment of this application. For example, the memory 703, 802 of the present invention may include non-permanent memory in the form of computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM.

[0089] Based on the embodiments of the above-described apparatus in this application, this application also proposes a mobile communication system, comprising at least one embodiment of any terminal-side device described in this application and / or at least one embodiment of any network-side device described in this application. This system, by executing the aforementioned method embodiments through each device, can achieve the objective of this invention: during cell handover, when the terminal AI model possesses cross-cell generalization capabilities, it shortens the AI ​​function interruption time and avoids unnecessary signaling interaction and reconfiguration delays.

[0090] It should be noted that the mobile communication system may include any two or three of the source cell network-side equipment, target cell network-side equipment, and terminal equipment in the embodiments of this application. For example, in actual network deployment, a complete handover process necessarily involves the interaction of the source cell, target cell, and terminal; while in some test or simplified scenarios, the system may only include one or two combinations of the terminal used for verification and the simulated source / target cell equipment, or a combination of the source cell network-side equipment and the target cell network-side equipment.

[0091] It should be noted that the specific mobile communication technology described in this invention is not limited, and can be WCDMA, CDMA2000, TD-SCDMA, WiMAX, LTE / LTE-A, LAA, MuLTEfire, 5G NR, and the sixth-generation and Nth-generation mobile communication technologies that may appear in the future.

[0092] The terminal described in this invention refers to a terminal-side product that can support the communication protocols of terrestrial mobile communication systems, and a specially designed wireless modem module that can be integrated into various types of terminal forms such as mobile phones, tablets, and data cards to complete communication functions.

[0093] For ease of description, a fifth-generation mobile communication system is used as an example, where the mobile communication terminal can be represented as UE (User Equipment), and the network-side access equipment can be represented as a base station or access point.

[0094] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0095] Those skilled in the art will understand that, unless otherwise stated, the singular forms “a,” “an,” “the,” and “the” used herein may also include the plural forms. It should be understood that when a device or component is “connected” to another device or component, it may be directly connected to the other device or component, or there may be an intermediary device or component. Furthermore, the term “connection” as used herein may include partially wireless connections as well as partially wired connections.

[0096] In the description of this application, it should be understood that the terms "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. Those skilled in the art can understand the specific meaning of the above terms in this application based on the specific circumstances. Furthermore, in the description of this application, unless otherwise stated, "multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship.

[0097] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. An information processing method during cell handover, characterized in that, include: Obtain air interface configuration information related to the target cell and artificial intelligence (AI) functions; Based on the air interface configuration information, uplink signaling is used to transmit and receive indication information that characterizes the continuity of the AI ​​inference function of the terminal in the target cell environment; Based on the indicated information, perform switching control operations related to the continuity of AI functions to maintain or terminate the AI ​​inference task of the terminal.

2. The method as described in claim 1, characterized in that, The step of performing a switching control operation related to the continuity of AI functions based on the instruction information includes: In response to the indication information indicating support, it is determined that after the terminal accesses the target cell, it can directly use the pre-configured air interface configuration to continue executing the AI ​​inference function; or, In response to the indication that the AI ​​function is not supported, the system determines that after the terminal accesses the target cell, it will fall back to the traditional non-AI mode and wait for the air interface configuration information related to the AI ​​function to be reconfigured.

3. A method for indicating during cell handover, used by network-side equipment of the source cell, characterized in that, include: During the process of the terminal switching from the source cell to the target cell, air interface configuration information pre-configured for the terminal and related to its AI functions is obtained from the target cell; Send downlink information to the terminal, the downlink information including at least the identifier of the target cell and the air interface configuration information; The terminal receives an indication message, which indicates whether the terminal can continue to perform AI inference to achieve a specific air interface function under the target cell and the air interface configuration. The instruction information is sent to the target cell.

4. The method as described in claim 3, characterized in that, After sending the instruction information to the target network device, the method further includes: In response to the indication information indicating support, the target network device is instructed to directly use the pre-configured air interface configuration for communication after the terminal accesses; or, In response to the indication that the instruction information does not support it, the target network device is instructed to reconfigure the air interface parameters of the terminal according to the standard non-AI handover procedure.

5. The method as described in claim 3, characterized in that, The step of obtaining the air interface configuration information pre-configured for the terminal and related to its AI function from the target network device includes: sending a handover request to the target network device; and receiving a handover request confirmation message from the target network device, which carries the air interface configuration information.

6. A method for indicating during cell handover, used by network-side equipment of a target cell, characterized in that, include: Receive a handover request from the source cell; In response to the switching request, generate and pre-configure air interface configuration information related to its AI functions for the terminal; Send the air interface configuration information to the network device of the source cell; The terminal receives an indication from the network device of the source cell, the indication being used to indicate whether the terminal can continue to perform AI inference to achieve a specific air interface function under the target cell and the air interface configuration. Based on the indicated information, the air interface configuration processing method related to AI functions is determined after the terminal is connected, so as to maintain or terminate the AI ​​inference task of the terminal.

7. The method as described in claim 6, characterized in that, The step of determining the air interface configuration processing method related to AI functions after the terminal accesses, based on the indication information, includes: In response to the indication information indicating support, it is determined that after the terminal accesses, the pre-configured air interface configuration will be used directly to communicate with the terminal; In response to the indication that the terminal does not support the feature, the system determines that a Radio Resource Control (RRC) reconfiguration procedure will be triggered after the terminal accesses the system in order to reconfigure the air interface configuration information related to the AI ​​function for the terminal.

8. The method as described in claim 6, characterized in that, The generation and pre-configuration of air interface configuration information related to the AI ​​function of the terminal is completed based on the AI ​​capability information or historical configuration information of the terminal received from the source network device.

9. A method for indicating during cell handover, used in terminal-side equipment, characterized in that, include: During cell handover, downlink information is received from the source cell. The downlink information includes the target cell identifier and air interface configuration information pre-configured by the target cell and related to the AI ​​function of the terminal. Based on the air interface configuration information and the target cell identifier, determine whether the terminal can continue to perform AI inference to achieve specific air interface functions under the target cell and the air interface configuration; Send indication information to the source cell, the indication information being used to indicate the result of the judgment.

10. The method as described in claim 9, characterized in that, Based on the indicated information, perform handover control operations related to the continuity of AI functions, including: if the self-generated indicated information indicates support, then determine to continue using the current AI model to perform inference after accessing the target cell; or, if the self-generated indicated information indicates no support, then determine to pause the AI ​​inference function and fall back to the traditional non-AI mode after accessing the target cell.

11. The method according to any one of claims 1 to 10, characterized in that, The air interface configuration information related to the target cell and the artificial intelligence (AI) function includes at least the target cell identifier and the air interface configuration parameters pre-configured by the target cell.

12. The method as described in claim 11, characterized in that, The target cell identifier includes one or more combinations of the following: NR cell global identifier NCGI, physical cell ID, base station gNB ID, public land mobile network identifier PLMN ID, tracking area identifier TAI, mobile country code MCC, and mobile network code MNC.

13. The method according to any one of claims 1 to 10, characterized in that, The AI ​​inference function is used to implement specific air interface functions, including AI-based time-domain channel state information (CSI) prediction, AI-based beam physical layer reference signal received power (L1-RSRP) prediction, or AI-based channel estimation.

14. A network-side device for implementing the method according to any one of claims 1-8, 11-13, characterized in that, The network-side device includes at least one module for performing at least one of the following functions: Generate or acquire air interface configuration information pre-configured for the terminal and related to its AI functions; Send downlink information, the downlink information including at least the identifier of the target cell and the air interface configuration information; Receive or send indication information, the indication information being used to indicate whether the terminal can continue to perform AI inference to achieve a specific air interface function under the target cell and the air interface configuration; Based on the indicated information, it is determined that the air interface configuration processing method related to AI function after the terminal accesses is to maintain or terminate the AI ​​inference task of the terminal.

15. A terminal-side device for implementing the method according to any one of claims 1-2 and 9-13, characterized in that... At least one module in the terminal-side device is configured to perform at least one of the following functions: Receive downlink information from the source cell, the downlink information including the target cell identifier and air interface configuration information pre-configured by the target cell and related to the AI ​​function of the terminal; Based on the air interface configuration information and the target cell identifier, determine whether the terminal can continue to perform AI inference to achieve specific air interface functions under the target cell and the air interface configuration; Send indication information to the source cell, the indication information being used to indicate the result of the judgment.

16. A communication device, characterized in that, include: A processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements the steps of the method as described in any one of claims 1 to 13.

17. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the method as described in any one of claims 1 to 13.

18. A mobile communication system, characterized in that, It includes at least one network-side device as described in claim 14 and / or at least one terminal-side device as described in claim 15; Of the network-side devices, at least one is used for the source cell and / or at least one is used for the target cell.

Images