Communication method, device, equipment, storage medium, chip, product and program

Abstract

The embodiment of the invention provides a communication method and device, equipment, a storage medium, a chip, a product and a program. The method comprises the steps that terminal equipment is switched from a source cell to a target cell; wherein the target cell is determined according to a target AI model and target input information used for being input to the target AI model.

Description

Communication method, device, equipment, storage medium, chip, product and program

[0001] The embodiments of the present application relate to the field of communication technology, and specifically to a communication method, apparatus, device, storage medium, chip, product and program.

[0002] With the development of communication technology, current wireless communication systems provide greater flexibility than before.

[0003] In the current communication method, taking cell switching as an example, whether to switch the service cell of the terminal device is generally determined by whether the parameter value in the actual communication environment meets the threshold. However, this method of determining whether to switch the service cell of the terminal device cannot meet the switching requirements of the terminal device in complex communication scenarios.

[0004] Summary of the invention

[0005] Embodiments of the present application provide a communication method, apparatus, device, storage medium, chip, product, and program.

[0006] In a first aspect, an embodiment of the present application provides a communication method, the method comprising:

[0007] The terminal device switches from a source cell to a target cell; wherein the target cell is determined based on a target AI model and target input information for input into the target AI model.

[0008] In a second aspect, an embodiment of the present application provides a communication method, the method comprising:

[0009] The first network device executes switching of one or more terminal devices from a source cell to a target cell; wherein the target cell is determined based on a target AI model and target input information for input into the target AI model.

[0010] In a third aspect, an embodiment of the present application provides a communication device, including:

[0011] A communication unit, used to switch from a source cell to a target cell; wherein the target cell is determined based on a target AI model and target input information for input into the target AI model.

[0012] In a fourth aspect, an embodiment of the present application provides a communication device, including:

[0013] A communication unit, used to execute switching of one or more terminal devices from a source cell to a target cell; wherein the target cell is determined based on a target AI model and target input information for input into the target AI model.

[0014] In a fifth aspect, an embodiment of the present application provides a communication device, including: a processor and a memory,

[0015] The memory stores a computer program executable on the processor.

[0016] When the processor executes the program, the method of the first aspect or the second aspect is implemented.

[0017] In a sixth aspect, an embodiment of the present application provides a computer storage medium, wherein the computer storage medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the method described in the first aspect or the second aspect.

[0018] In a seventh aspect, an embodiment of the present application provides a chip, comprising: a processor, configured to call and run a computer program from a memory to implement the method described in the first aspect or the second aspect.

[0019] In an eighth aspect, an embodiment of the present application provides a computer program product, the computer program product comprising a computer storage medium, the computer storage medium storing a computer program, the computer program comprising instructions executable by at least one processor, and the method described in the first aspect or the second aspect is implemented when the instructions are executed by the at least one processor.

[0020] In a ninth aspect, an embodiment of the present application provides a computer program, which enables a computer to execute the method described in the first aspect or the second aspect.

[0021] In an embodiment of the present application, the terminal device switches from a source cell to a target cell; wherein the target cell is determined based on a target AI model and target input information for input into the target AI model. In this way, the target cell to which the terminal device switches is not determined by whether the parameter value in the actual communication environment meets the threshold, but is determined based on the target AI model and target input information for input into the target AI model, thereby combining AI technology with the communication system, so that the present solution can be applied to complex communication scenarios, meeting the terminal device's switching requirements for complex communication scenarios.

[0022] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0023] FIG1 is a schematic diagram of an application scenario of an embodiment of the present application;

[0024] FIG2 is a schematic diagram of a switching process provided in an embodiment of the present application;

[0025] FIG3 is a flow chart of a communication method provided in an embodiment of the present application;

[0026] FIG4 is a flow chart of another communication method provided in an embodiment of the present application;

[0027] FIG5 is a flow chart of another communication method provided in an embodiment of the present application;

[0028] FIG6 is a flow chart of another communication method provided in an embodiment of the present application;

[0029] FIG7 is a flow chart of a communication method provided in another embodiment of the present application;

[0030] FIG8 is a flow chart of a communication method provided in yet another embodiment of the present application;

[0031] FIG9 is a flow chart of a communication method provided in yet another embodiment of the present application;

[0032] FIG10 is a schematic diagram of the structure of a communication device provided in an embodiment of the present application;

[0033] FIG11 is a schematic diagram of the structure of another communication device provided in an embodiment of the present application;

[0034] FIG12 is a schematic structural diagram of a communication device provided in an embodiment of the present application;

[0035] FIG. 13 is a schematic structural diagram of a chip according to an embodiment of the present application.

[0036] The following will describe the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0037] The technical solutions described in the embodiments of the present application can be combined arbitrarily without conflict. In the description of the present application, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0038] Fig. 1 is a schematic diagram of an application scenario of an embodiment of the present application. As shown in Fig. 1, a communication system 100 may include a terminal device 110 and a network device 120. The network device 120 may communicate with the terminal device 110 via an air interface. The terminal device 110 and the network device 120 support multi-service transmission.

[0039] It should be understood that the embodiments of the present application are only exemplified by the communication system 100, but the embodiments of the present application are not limited thereto. That is to say, the technical solution of the embodiment of the present application can be applied to various communication systems, such as: Global System of Mobile communication (GSM) system, Code Division Multiple Access (CDMA) system, Wideband Code Division Multiple Access (WCDMA) system, General Packet Radio Service (GPRS), Long Term Evolution (LTE) system, Advanced long term evolution (LTE-A) system, New Radio (NR) system, NR system evolution system, LTE on unlicensed spectrum (LTE-based access to unlicensed spectrum, LTE-U) system, NR on unlicensed spectrum (NR-based access to unlicensed spectrum, NR-U) system, Universal Mobile Telecommunication System (UMTS), Wireless Local Area Networks (WLAN), Wireless Fidelity (WiFi), LTE Time Division Duplex (TDD), ... Wireless Fidelity (WiFi), Wireless Fidelity (WiFi), Wireless Fidelity (WiFi), Wireless Fidelity (WiFi), Wireless Fidelity (WiFi), Wireless Fidelity (WiFi), Wireless Fidelity (LTE), Advanced long term evolution (LTE-A), New Radio (NR) system, NR system evolution system, LTE on unlicensed spectrum (LTE-U) system, NR on unlicensed spectrum (NR-U) system, Universal Mobile Telecommunication System (UMTS), Wireless Local Area Networks (WLAN), Wireless Fidelity (WiFi), LTE Time Division Duplex (TDD), Universal Mobile Telecommunication System (UMTS), Wireless Local System, UMTS), Internet of Things (IoT) system, Narrow Band Internet of Things (NB-IoT) system, enhanced Machine-Type Communications (eMTC) system, or future communication systems (such as 6G, 7G communication systems), etc.

[0040] The network device 120 in the embodiment of the present application may include an access network device 121 and / or a core network device 122. The access network device may provide communication coverage for a specific geographical area and may communicate with a terminal device 110 (eg, UE) located in the coverage area.

[0041] The terminal in this application is a device with wireless communication function, which can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; it can also be deployed on the water surface (such as ships, etc.); it can also be deployed in the air (such as airplanes, balloons and satellites, etc.). The first terminal, second terminal, third terminal, fourth terminal or other terminals in this application can be called user equipment (User Equipment, UE), mobile station (Mobile Station, MS), mobile terminal (Mobile Terminal, MT), user unit, user station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication equipment, user agent or user device. The first terminal, the second terminal, the third terminal, the fourth terminal or other terminals may include one of the following or a combination of at least two of them: an Internet of Things device, a satellite terminal, a Wireless Local Loop (WLL) station, a Personal Digital Assistant (PDA), a handheld device with a wireless communication function, a computing device or other processing device connected to a wireless modem, a server, a mobile phone, a tablet computer (Pad), a computer with a wireless transceiver function, a handheld computer, a desktop computer, a personal digital assistant, a portable media player, a smart speaker, a navigation device, a smart watch, a smart glasses, a smart necklace and other wearable devices, a pedometer, a digital TV, a Virtual Reality (VR) terminal device, an Augmented Reality (AR) terminal device, a wireless terminal in industrial control, a wireless terminal in self driving, a wireless terminal in remote medical surgery, a wireless terminal in a smart grid, a wireless terminal in transportation safety, a wireless terminal in a smart city, a smart home, a wireless terminal in a smart city, a wireless terminal in a smart home, a wireless terminal in a smart grid, a wireless terminal in transportation safety, a wireless terminal in a smart city, a wireless terminal in a smart home ... The invention relates to wireless terminals in a connected home and vehicles, vehicle-mounted devices, vehicle-mounted modules, wireless modems, handheld devices, customer premises equipment (CPE), smart home appliances, etc. in the connected vehicle system.

[0042] Optionally, the terminal device 110 may be any terminal device, including but not limited to a terminal device connected to the network device 120 or other terminal devices by wire or wirelessly.

[0043] Optionally, the terminal device 110 may be used for device-to-device (D2D) communication.

[0044] The access network equipment 121 may include one of the following or a combination of at least two: an evolved base station (eNB or eNodeB) in a Long Term Evolution (LTE) system, a next generation radio access network (NG RAN) device, a base station (gNB) in an NR system, a small station, a micro station, a wireless controller in a cloud radio access network (CRAN), an access point for wireless fidelity (Wi-Fi), a transmission reception point (TRP), a relay station, an access point, a vehicle-mounted device, a wearable device, a hub, a switch, a bridge, a router, a network device in a future evolved public land mobile network (PLMN), etc.

[0045] The core network device 122 may be a 5G core network (5G Core, 5GC) device, and the core network device 122 may include one of the following or a combination of at least two: Access and Mobility Management Function (AMF), Authentication Server Function (AUSF), User Plane Function (UPF), Session Management Function (SMF), Location Management Function (LMF), Policy Control Function (PCF). In other embodiments, the core network device may also be an Evolved Packet Core (EPC) device of an LTE network, for example, a Session Management Function + Core Packet Gateway (SMF + PGW-C) device of a core network. It should be understood that SMF + PGW-C can simultaneously implement the functions that SMF and PGW-C can implement. In the process of network evolution, the above-mentioned core network device 122 may also be called other names, or a new network entity may be formed by dividing the functions of the core network, which is not limited to the embodiments of the present application.

[0046] The functional units in the communication system 100 may also establish connections through next generation (NG) network interfaces to achieve communication.

[0047] For example, the terminal device establishes an air interface connection with the access network device through the NR interface for transmitting user plane data and control plane signaling; the terminal device can establish a control plane signaling connection with the AMF through the NG interface 1 (N1 for short); the access network device, such as the next generation wireless access base station (gNB), can establish a user plane data connection with the UPF through the NG interface 3 (N3 for short); the access network device can establish a control plane signaling connection with the AMF through the NG interface 2 (N2 for short); the UPF can establish a control plane signaling connection with the SMF through the NG interface 4 (N4 for short); the UPF can exchange user plane data with the data network through the NG interface 6 (N6 for short); the AMF can establish a control plane signaling connection with the SMF through the NG interface 11 (N11 for short); the SMF can establish a control plane signaling connection with the PCF through the NG interface 7 (N7 for short).

[0048] FIG1 exemplarily shows a base station, a core network device and two terminal devices. Optionally, the wireless communication system 100 may include multiple base station devices and each base station may include another number of terminal devices within its coverage area, which is not limited in the embodiments of the present application.

[0049] It should be noted that FIG. 1 is only an example of the system to which the present application is applicable. Of course, the method shown in the embodiment of the present application can also be applied to other systems. In addition, the terms "system" and "network" are often used interchangeably in this article. The term "and / or" in this article is only a description of the association relationship of the associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship. It should also be understood that the "indication" mentioned in the embodiment of the present application can be a direct indication, an indirect indication, or an indication of an association relationship. For example, A indicates B, which can mean that A directly indicates B, for example, B can be obtained through A; it can also mean that A indirectly indicates B, for example, A indicates C, B can be obtained through C; it can also mean that A and B have an association relationship. It should also be understood that the "correspondence" mentioned in the embodiment of the present application can mean that there is a direct or indirect correspondence relationship between the two, or it can mean that there is an association relationship between the two, or it can mean that there is an indication and being indicated, configuration and being configured, etc. It should also be understood that the "predefined", "protocol agreed", "predetermined" or "predefined rules" mentioned in the embodiments of the present application can be implemented by pre-saving corresponding codes, tables or other methods that can be used to indicate relevant information in devices (for example, including terminal devices and network devices), and the present application does not limit its specific implementation method. For example, predefined may refer to the definition in the protocol. It should also be understood that in the embodiments of the present application, the "protocol" may refer to a standard protocol in the field of communications, such as LTE protocols, NR protocols, and related protocols used in future communication systems, and the present application does not limit this.

[0050] To facilitate understanding of the technical solutions of the embodiments of the present application, the relevant technologies of the embodiments of the present application are described below. The following related technologies can be arbitrarily combined with the technical solutions of the embodiments of the present application as optional solutions, and they all belong to the protection scope of the embodiments of the present application.

[0051] When a terminal device that is using network services moves from one cell to another, or due to wireless transmission service load adjustment, activation operation maintenance, equipment failure, etc., in order to ensure communication continuity and service quality, the system must transfer the communication link between the terminal device and the source cell to the new target cell, that is, perform a switching process.

[0052] FIG. 2 is a schematic diagram of a switching process provided by an embodiment of the present application. As shown in FIG. 2 , taking the Xn interface switching process as an example, the entire switching process can be divided into the following three stages:

[0053] (1) Handover preparation: including measurement control and reporting, handover request and confirmation. The handover confirmation message contains the handover command generated by the target cell. The source cell is not allowed to make any modification to the handover command generated by the target cell and directly forwards the handover command to the terminal device.

[0054] (2) Handover execution: After receiving the handover command, the terminal device immediately executes the handover process, that is, the terminal device disconnects from the source cell and connects to the target cell (such as performing random access, sending a Radio Resource Control (RRC) handover completion message to the target base station, etc.); sequence number (SN) state transfer and data forwarding.

[0055] (3) Handover completion: The target base station performs a path switch with the access and mobility management function (AMF) and the user port function (UPF) to release the terminal device context of the source base station.

[0056] In FIG. 2 , the switching process may include steps 1 to 12 below.

[0057] Before step 1, the terminal device exchanges user data with the source base station, and the source base station exchanges user data with UPF(s). Before step 1, there may also be step 0: providing mobile control information through AMF.

[0058] In any embodiment of the present application, the source base station may be a base station corresponding to a source cell or a network device corresponding to the source cell, and the target base station may be a base station corresponding to a target cell or a network device corresponding to the target cell.

[0059] Step 1: Measurement control and reporting. The source base station performs measurement configuration on the terminal device. The measurement results of the terminal device will be used to assist the source base station in making a handover decision. Then the terminal device performs measurement reporting according to the measurement configuration.

[0060] Step 2: Handover determination: the source base station refers to the measurement report results of the terminal device and makes a handover decision based on its own handover algorithm.

[0061] Step 3: The source base station sends a handover request to the target base station. The source base station sends a handover request message to the target base station. The message contains relevant information for handover preparation, mainly X2 and S1 signaling context references of the terminal device, target cell identifier, key, RRC context, access stratum (AS) configuration, Evolved Universal Terrestrial Radio Access Network (E-UTRAN) radio access bearer (E-UTRAN Radio Access Bearer, E-RAB) context, etc. It also contains the source cell physical layer identifier and message authentication verification code for the recovery process after possible handover failure. The X2 and S1 signaling context references of the terminal device can help the target base station find the location of the source base station. The E-RAB context includes the necessary radio network layer (RLN) and transport layer (TNL), addressing information, and E-RAB quality of service (QoS) information. A part of the handover preparation information is included in the interface message itself (eg, the target cell identifier), and another part exists in the RRC container of the interface message (eg, the RRC context).

[0062] Step 4: Admission control. The target base station performs admission control based on the received E-RAB QoS information to improve the success rate of handover. Admission control should consider reserving corresponding resources, C-RNTI, and allocating dedicated random access preamble codes. The AS configuration used by the target cell can be a complete configuration that is completely independent of the source cell, or an incremental configuration based on the source cell (incremental configuration means that the same part is not configured, and only different parts are reconfigured through signaling. The terminal device will continue to use the original configuration for the configuration that has not been received).

[0063] Step 5: The target base station sends a handover request confirmation to the source base station, the target base station prepares for the handover, and sends a positive confirmation (Acknowledgement, ACK) message of the handover request to the source base station. The message contains an RRC container, the specific content of which is the handover command that triggers the terminal device to switch. The source base station handover command is sent to the terminal device in a transparent manner (without any modification). The handover command contains a new cell radio network temporary identity (Cell Radio Network Temporary Identity, C-RNTI), the case algorithm identifier of the target base station, and may also carry a random access dedicated preamble code, access parameters, system information, etc. If necessary, the handover request ACK message may also carry radio network layer (Radio Network Layer, RNL) / transport network layer (Transport Network Layer, TNL) information for data forwarding. When the source base station receives the handover request ACK message or forwards the handover command to the terminal device, data forwarding can begin.

[0064] Step 6: RAN handover is initiated. Step 6 is that the source base station sends a handover command to the terminal device. The handover command (RRC connection reconfiguration message carrying mobility control information) is generated by the target base station and transparently transmitted to the terminal device through the source base station. When the terminal device receives the message, it will use the relevant parameters in the message to initiate the handover process. The terminal device does not need to wait for the Hybrid Automatic Repeat reQuest (HARQ) / Automatic Repeat reQuest (ARQ) response sent by the lower layer to the source base station to initiate the handover process.

[0065] After step 6, the terminal device leaves the source base station and synchronizes to the target base station.

[0066] Step 7: The source base station transfers the SN to the target base station, which can also be the SN status transmission. The source base station sends a sequence number (SN, Sequence Number) status transmission message to the target base station, transmitting the uplink PDCP SN reception status and downlink PDCP SN sending status of the E-RAB (only those E-RABs that need to retain the Packet Data Convergence Protocol (PDCP) status need to perform SN status forwarding, corresponding to the Radio Link Control (RLC) Acknowledged Mode (AM) mode).

[0067] After step 7, the source base station provides buffered data and new data from the UPF. Then, the UPF can send the user data to be transmitted to the terminal device to the source base station first, and the source base station forwards the user data to the target base station, and the target base station can buffer the user data from the source base station.

[0068] Step 8: RAN switching is completed. In 8, after the terminal device receives the switching command, it performs synchronization with the target cell. If a random access dedicated Preamble code is configured in the switching command, a non-competitive random access process is used to access the target cell. If no dedicated Preamble code is configured, a competitive random access process is used to access the target cell.

[0069] After step 8, the terminal device will transmit user data with the UPF through the target base station.

[0070] Step 9: The target base station sends a path switching request to the AMF. The target base station informs the AMF that the terminal device has changed cells through the path switching request message. At this time, the air interface switching has been successfully completed.

[0071] Step 10: Path switching in UPF can be achieved through the following steps: AMF sends a user plane update request to UPF, UPF converts the downlink data path, and UPF sends a user plane update response to AMF.

[0072] To assist the reordering function at the target base station, the UPF sends one or more "End Marker Packets" on the old path immediately after the path switch. The "End Marker Packet" does not contain user data and is indicated by the GPRS Tunneling Protocol (GTP) header. After completing the sending of the packet containing the identifier, the UPF should not send any data packets on the old path. After receiving the "End Marker Packet", if forwarding is activated for this bearer, the source base station should send this packet to the target base station. After detecting the "End Marker Packet", the target base station should discard the "End Marker Packet" and initiate any necessary processes to maintain the in-order delivery of users, so that user data is transmitted between the UPF and the target base station.

[0073] Step 11: AMF sends a path switching request confirmation to the target base station, completing the path switching process.

[0074] Step 12: The target base station sends a terminal device context release to the source base station, and the source base station receives the terminal device context release sent by the target base station and releases the terminal device context.

[0075] Traditional mobility management executes the switching process based on the measurement report of the terminal device and the decision of the network side. The AI-based mobility management proposed in this application can select a more suitable target cell for the terminal device, thereby ensuring the continuity of the service. For the AI ​​mobility scenario, in order to ensure that the model works better, the embodiment of this application provides the deployment of the model and the interaction of related information.

[0076] To facilitate understanding of the technical solutions of the embodiments of the present application, the technical solutions of the present application are described in detail below through specific embodiments. The above related technologies can be combined arbitrarily with the technical solutions of the embodiments of the present application as optional solutions, and they all belong to the protection scope of the embodiments of the present application. The embodiments of the present application include at least part of the following contents.

[0077] FIG3 is a flow chart of a communication method provided in an embodiment of the present application. As shown in FIG3 , the method includes:

[0078] S301. The terminal device switches from a source cell to a target cell; wherein the target cell is determined based on a target AI model and target input information for inputting into the target AI model.

[0079] Optionally, in any embodiment of the present application, the AI ​​model may also be referred to as a machine learning (ML) model, a neural network model, or a neural network.

[0080] Optionally, the terminal device switching from the source cell to the target cell may include: the terminal device disconnecting from the source cell and connecting to the target cell.

[0081] Optionally, the target AI model may be a trained AI model. Optionally, the target AI model may be further trained to obtain a more accurate model. Optionally, the target AI model may include an input layer, at least one intermediate layer, and an output layer, and the target input information may be processed in sequence by the input layer, at least one intermediate layer, and the output layer to obtain the output cell information. Optionally, the output cell information may include at least one of the following: an output cell identifier, tracking area information to which the output cell belongs, and a public land mobile network (PLMN) identifier supported by the output cell.

[0082] Optionally, the target input information is input into the target AI model, and the cell output by the target AI model may be the first cell, thereby determining the target cell based on the first cell.

[0083] Optionally, the target input information is input into the target AI model, and the cell output by the target AI model is the first cell, and the first cell can be determined as the target cell. In this way, the cell output by the target AI model is the target cell.

[0084] Optionally, the target input information is input into the target AI model, and the cell output by the target AI model is the first cell. The second cell can be determined based on the first cell, and the second cell is determined as the target cell.

[0085] In some embodiments, when the target AI model is deployed on a terminal device, the target AI model of the terminal device may be pre-configured, or may be configured by a network device (e.g., a first network device or other network device other than the first network device) to the terminal device. Optionally, the network device may configure the weight and / or usage duration of the target AI model to the terminal device. In some embodiments, when the target AI model is deployed on a first network device, the target AI model of the first network device may be pre-configured, or may be configured by the terminal device to the first network device, or may be configured by a core network device. Optionally, the terminal device or the core network device may configure the weight and / or usage duration of the target AI model.

[0086] In an embodiment of the present application, the terminal device switches from a source cell to a target cell; wherein the target cell is determined based on a target AI model and target input information for input into the target AI model. In this way, the target cell to which the terminal device switches is not determined by whether the parameter value in the actual communication environment meets the threshold, but is determined based on the target AI model and target input information for input into the target AI model, thereby combining AI technology with the communication system, so that the present solution can be applied to complex communication scenarios, meeting the terminal device's switching requirements for complex communication scenarios.

[0087] In some embodiments, the target AI model can be deployed in the terminal device, so that the first cell of the output is determined by the target AI model deployed in the terminal device and the target input information.

[0088] In some embodiments, the target input information includes: first input information and / or second input information;

[0089] The terminal device receives the first input information sent by the first network device corresponding to the source cell, and / or the terminal device determines the second input information of the terminal device;

[0090] The terminal device determines the target cell based on the target AI model, and the first input information and / or the second input information.

[0091] Optionally, the first input information may be input information obtained by the first network device, and the second input information may be input information obtained by the terminal device.

[0092] In any embodiment of the present application, the first network device may be a network device corresponding to a source cell or a source network device, and the second network device may be a network device corresponding to a target cell or a target network device.

[0093] Exemplarily, the terminal device receives the first input information sent by the first network device corresponding to the source cell, and the terminal device determines the target cell based on the target AI model and the first input information.

[0094] Also exemplarily, the terminal device determines the second input information of the terminal device, and the terminal device determines the target cell based on the target AI model and the second input information.

[0095] Also exemplarily, the terminal device receives the first input information sent by the first network device corresponding to the source cell, and the terminal device determines the second input information of the terminal device; the terminal device determines the target cell based on the target AI model, and the first input information and the second input information.

[0096] Optionally, the terminal device determining the second input information of the terminal device may include: the terminal device acquiring the second input information of the terminal device from itself.

[0097] In some embodiments, the terminal device determines the target cell based on the target AI model, and the first input information and / or the second input information, including: the terminal device determines the first cell based on the target AI model, and the first input information and / or the second input information; the terminal device determines the target cell based on the first cell.

[0098] Exemplarily, the terminal device determines the first cell according to the target AI model and the first input information. Also exemplarily, the terminal device determines the first cell according to the target AI model and the second input information. Also exemplarily, the terminal device determines the first cell according to the target AI model, the first input information, and the second input information.

[0099] Optionally, in some embodiments, the terminal device determines the target cell according to the first cell, which may include: the terminal device determines the first cell as the target cell. Optionally, in other embodiments, the terminal device determines the target cell according to the first cell, which may include: the terminal device determines the second cell based on the first cell, and determines the second cell as the target cell.

[0100] In some embodiments, the target AI model may include a first AI model and a second AI model, the first AI model may be deployed in a first network device, and the second AI model may be deployed in a terminal device. Optionally, the first AI model may include an input layer, or may include an input layer and at least part of an intermediate layer. Optionally, the second AI model may include an output layer, or may include at least part of an intermediate layer and an output layer.

[0101] In some embodiments, the target input information includes: first input information and / or second input information; the target AI model includes a first AI model and a second AI model, and the method further includes:

[0102] The terminal device receives first intermediate information sent by a first network device corresponding to the source cell; the first intermediate information is determined according to the first AI model, and the first input information and / or the second input information;

[0103] The terminal device determines a first cell according to the second AI model and the first intermediate information;

[0104] The terminal device determines the target cell based on the first cell.

[0105] Optionally, the first intermediate information may be information output by the first AI model after the target input information is input into the first AI model.

[0106] Optionally, the terminal device determines the first cell according to the second AI model and the first intermediate information, including: the terminal device inputs the first intermediate information into the second AI model, and outputs the first cell through the second AI model.

[0107] In some embodiments, when determining the first cell, the terminal device can send the first cell to the first network device so that the first network device determines whether to determine the first cell as the target cell, or in other words, so that the first network device determines that the target cell is the first cell or the second cell.

[0108] In some embodiments, the terminal device determines the target cell based on the first cell, including: the terminal device sends indication information to the first network device; the indication information is used to indicate the first cell; the terminal device receives a switching command sent by the first network device; the switching command is used to indicate the target cell; wherein the target cell is the first cell or the second cell.

[0109] Optionally, the terminal device may determine the first cell once and send indication information to the first network device each time the terminal device receives the first input information sent by the first network device corresponding to the source cell. Optionally, the terminal device may periodically determine the first cell and periodically send indication information to the first network device. Optionally, the terminal device may determine the period of obtaining the first cell according to pre-configuration information and / or determine the period of obtaining the first cell according to configuration information of the first network device.

[0110] In some embodiments, the indication information is carried in a measurement report. In other embodiments, the indication information may be carried in a message other than a measurement report.

[0111] In some embodiments, the terminal device determines the target cell based on the first cell, including: the terminal device determines the first cell as the target cell.

[0112] In some other embodiments, the terminal device determines the target cell based on the first cell, including: the terminal device determines the target cell based on the first cell and a measurement result.

[0113] Optionally, the terminal device may determine the target cell based on the measurement result obtained by the terminal device and the first cell. Optionally, the terminal device may determine the target cell based on the measurement result obtained by the first network device and the first cell sent by the first network device. Optionally, the terminal device may determine the target cell based on the measurement result obtained by the terminal device, the measurement result obtained by the first network device, and the first cell.

[0114] Optionally, the terminal device may determine the target cell based on the first cell and the measurement result.

[0115] Exemplarily, the terminal device may determine whether the first cell meets the handover condition based on the measurement result, and determine the first cell as the target cell if the first cell meets the handover condition; if the first cell does not meet the handover condition, determine a second cell that meets the handover condition based on the measurement result, and determine the second cell as the target cell. Optionally, if it is determined based on the measurement result that there is no second cell that meets the handover condition, the terminal device and the first network device will not perform the handover process.

[0116] Optionally, satisfying the switching condition may include satisfying one of the following: an A1 event, an A2 event, an A3 event, an A4 event, an A5 event, a B1 event, or a B2 event.

[0117] Optionally, the first cell satisfies the switching condition, which may include: the measurement value of the source cell is less than or equal to the first threshold, and the measurement value of the first cell is greater than the second threshold. Optionally, the first cell does not satisfy the switching condition, which may include: the measurement value of the first cell is less than or equal to the second threshold. Optionally, the first cell satisfies the switching condition, which may also include: the number of beams whose measurement value of the first cell is greater than the second threshold is greater than a third threshold. Optionally, the first cell does not satisfy the switching condition, which may also include: the number of beams whose measurement value of the first cell is greater than the second threshold is less than or equal to the third threshold.

[0118] Optionally, the measurement value may include at least one of the following: Reference Signal Received Power (RSRP), Reference Signal Received Quality (RSRQ), Received Signal Strength Indicator (RSSI), Signal to Interference and Noise Ratio (SINR). Optionally, the thresholds corresponding to the measurement values ​​of different measurement parameters may be the same or different.

[0119] In some embodiments, the measurement result includes a measurement value of the first cell;

[0120] The terminal device determines the target cell according to the first cell and the measurement result, including:

[0121] When the measurement value of the first cell is greater than a preset threshold, the terminal device determines that the first cell is the target cell; and / or,

[0122] In a case where the measurement value of the first cell is less than or equal to the preset threshold, the terminal device determines a cell in the measurement result whose measurement value is greater than the preset threshold as a second cell, and determines the second cell as the target cell.

[0123] Optionally, when there are multiple cells in the measurement results whose measurement values ​​are greater than the preset threshold, the terminal device can determine the cell corresponding to the maximum measurement value as the second cell, or the terminal device can determine the second cell from the multiple cells based on the location information and / or mobile trajectory information of the terminal device.

[0124] In some embodiments, the target AI model can be deployed on a first network device.

[0125] In some embodiments, the target input information includes: first input information and / or second input information; the method further includes:

[0126] The terminal device receives a handover command sent by a first network device corresponding to the source cell; the handover command is used to indicate the target cell; wherein the target cell is the first cell or the second cell;

[0127] The first cell is determined according to the target AI model, and the first input information and / or the second input information;

[0128] The first input information is determined by the first network device;

[0129] The second input information is sent by the terminal device to the first network device.

[0130] Optionally, the terminal device may actively send the second input information to the first network device. Optionally, the terminal device may determine the time to send the second input information to the first network device based on preconfigured information. Optionally, the terminal device may periodically or non-periodically send the second input information to the first network device. Optionally, the terminal device may send the second input information to the first network device each time a measurement report is obtained. Optionally, the terminal device may send the second input information to the first network device upon receiving a measurement request or a reporting request sent by the first network device.

[0131] Optionally, the switching command may carry indication information of the target cell, so that the terminal device may switch to the target cell according to the indication information of the target cell.

[0132] In some embodiments, the target AI model may include a third AI model and a fourth AI model, the third AI model may be deployed in the terminal device, and the fourth AI model may be deployed in the first network device. Optionally, the third AI model may include an input layer, or may include an input layer and at least part of an intermediate layer. Optionally, the fourth AI model may include an output layer, or may include at least part of an intermediate layer and an output layer.

[0133] In some embodiments, the target input information includes: first input information and / or second input information; the target AI model includes a third AI model and a fourth AI model, and the method further includes:

[0134] The terminal device receives the first input information sent by the first network device corresponding to the source cell, and / or the terminal device determines the second input information of the terminal device;

[0135] The terminal device determines second intermediate information according to the third AI model and the first input information and / or the second input information;

[0136] The terminal device sends the second intermediate information to the first network device; the second intermediate information is used to determine the first cell with the fourth AI model;

[0137] The terminal device receives a switching command sent by the first network device; the switching command is used to indicate the target cell; wherein the target cell is the first cell or the second cell.

[0138] Optionally, the second intermediate information may be information output by the third AI model after the target input information is input into the third AI model.

[0139] Optionally, an implementation manner in which the second intermediate information is used to determine the first cell with the fourth AI model may include: the first network device determines the first cell according to the fourth AI model and the second intermediate information.

[0140] Optionally, in some embodiments, the first network device may directly determine the first cell as the target cell. Optionally, in other embodiments, the first network device may determine the target cell according to the measurement result and the first cell.

[0141] In some embodiments, the terminal device sends a measurement result to the first network device; the measurement result is used to determine the target cell with the first cell.

[0142] Optionally, the measurement result sent by the terminal device to the first network device may be a measurement result obtained by the terminal device.

[0143] In some embodiments, the method further comprises:

[0144] The terminal device receives pre-configuration information sent by a first network device corresponding to the source cell; the pre-configuration information includes at least one candidate cell, and the at least one candidate cell includes the target cell.

[0145] Optionally, at least one candidate cell may be determined by the first network device according to a measurement report sent by the terminal device. Optionally, at least one candidate cell may be determined by the first network device according to a measurement value obtained by measuring the uplink signal of the terminal device. Optionally, at least one candidate cell may be determined by the first network device according to a measurement report sent by the terminal device and a measurement value obtained by measuring the uplink signal of the terminal device. Optionally, at least one candidate cell may be pre-configured in the first network device. Optionally, at least one candidate cell may be a neighboring cell of a source cell corresponding to the first network device.

[0146] In some embodiments, the first input information includes at least one of the following: cell information of the source cell, load information of the source cell, service type information supported by the source cell, and measurement results of an uplink reference signal corresponding to the source cell.

[0147] In some embodiments, the second input information includes at least one of the following: a measurement result of the terminal device, location information of the terminal device, movement track information of the terminal device, movement speed information of the terminal device, navigation information of the terminal device, and business demand information of the terminal device.

[0148] Optionally, the cell information of the source cell may include at least one of the following: location information of the first network device corresponding to the source cell, antenna angle information of the first network device corresponding to the source cell, cell radius information of the source cell, cell identifier of the source cell, tracking area information to which the source cell belongs, and PLMN identifier supported by the source cell. Optionally, the cell information of the source cell may be used to determine whether the terminal device is within the coverage of the source cell, and / or whether it resides in the source cell within a preset time length, and / or whether it leaves the coverage of the source cell within a preset time length.

[0149] Optionally, the load information of the source cell may include at least one of the following: the maximum number of terminal devices supported by the source cell, the number of terminal devices in a connected state in the source cell, the maximum service volume supported by the source cell, and the current service volume of the source cell. Optionally, the service volume may include bandwidth and / or the amount of data transmitted per unit time.

[0150] Optionally, the service type information may include at least the following services: video services, call services (including network call services and / or voice call services), game services, VR services, AR services, services corresponding to quality of service (Quality of Service, QoS) values ​​(different QoS values ​​correspond to different services), Internet of Things services, enhanced mobile broadband (enhanced Mobile BroadBand, eMBB) services, massive machine type communication (massive Machine Type Communication, mMTC) services, ultra-reliable and low latency communications (Ultra-Reliable and Low Latency Communications, URLLC) services, WiFi services, and Internet of Vehicles services.

[0151] Optionally, the uplink reference signal may include at least one of the following: a sounding reference signal (Sounding Reference Signal, SRS), a demodulation reference signal (DeModulation Reference Signal, DMRS), and a phase tracking reference signal (Phase Tracking Reference Signal, PTRS).

[0152] Optionally, the measurement result in any embodiment of the present application may include one or more measurement values.

[0153] Optionally, the measurement result of the terminal device may include: the measurement result of the terminal device on the downlink reference signal. Optionally, the downlink reference signal may include at least one of the following: a synchronization signal block (Synchronization Signal Block, SSB), a channel state information reference signal (Channel State Information-Reference Signal, CSI-RS). Among them, SSB may also be called a synchronization signal / physical broadcast channel block (Synchronization Signal / Physical Broadcast Channel Block, SS / PBCH block). The measurement result of the terminal device may include a cell measurement result and / or a beam measurement result.

[0154] Optionally, the location information of the terminal device may include at least one of the following: absolute location information of the terminal device, location information of the terminal device relative to the first network device, and a location identifier of the terminal device.

[0155] Optionally, at least one of the location information of the terminal device, the movement trajectory information of the terminal device, the movement speed information of the terminal device, and the navigation information of the terminal device can be used to predict the time when the terminal device leaves the source cell and / or enters the target cell.

[0156] Optionally, the service demand information may include at least one of the following: video service demand information, call service demand information, game service demand information, VR service demand information, AR service demand information, service demand information corresponding to QoS value, Internet of Things service demand information, eMBB service demand information, mMTC service demand information, URLLC service demand information, and Internet of Vehicles service demand information.

[0157] FIG. 4 is a flow chart of another communication method provided in an embodiment of the present application. As shown in FIG. 4 , the method includes:

[0158] S401. The first network device executes switching of one or more terminal devices from a source cell to a target cell; wherein the target cell is determined based on a target AI model and target input information for inputting into the target AI model.

[0159] Optionally, the first network device may execute a handover of a terminal device from a source cell to a target cell. Optionally, the first network device may execute a handover of multiple terminal devices from a source cell to a target cell at the same time.

[0160] Optionally, target input information corresponding to a terminal device may be input into the target AI model, thereby outputting a target cell corresponding to the terminal device through the target AI model.

[0161] Optionally, the target input information corresponding to multiple terminal devices can be simultaneously input into the target AI model, so that the target cells corresponding to the multiple terminal devices are output through the target AI model. In this way, the target cells corresponding to multiple terminal devices are obtained at the same time through the target AI model, so that the target cells corresponding to the multiple terminal devices can be reasonably determined. For example, if other conditions remain unchanged, when the current load information corresponding to the source cell is large, more terminal devices can be switched to the target cell through the target AI model, and / or, when the current load information corresponding to the source cell is small, fewer terminal devices can be switched to the target cell through the target AI model.

[0162] Optionally, the first network device executes switching of the terminal device from the source cell to the target cell, which may include at least one of the following: the first network device sends a switching command to the terminal device; the switching command is used to indicate the target cell; the first network device sends the SN status to the second network device corresponding to the target cell; the first network device forwards the user data to the second network device.

[0163] In some embodiments, the target input information includes second input information, so that the terminal device can autonomously determine to input the second input information into the target AI model deployed in the terminal device, and output the first cell through the target AI model deployed in the terminal device, and determine the target cell based on the first cell.

[0164] In some embodiments, the target input information includes: first input information, or the first input information and second input information; the method further includes:

[0165] The first network device sends first input information to the terminal device; the first input information is used to determine the target cell with the target AI model, or the first input information is used to determine the target cell with the target AI model and the second input information.

[0166] In this way, in one embodiment, the terminal device can input first input information to the target AI model deployed in the terminal device, and output the first cell through the target AI model deployed in the terminal device, and determine the target cell based on the first cell; in another embodiment, the terminal device can input first input information and second input information to the target AI model deployed in the terminal device, and output the first cell through the target AI model deployed in the terminal device, and determine the target cell based on the first cell.

[0167] In some embodiments, the target input information includes: first input information and / or second input information; the target AI model includes a first AI model and a second AI model, and the method further includes:

[0168] The first network device determines first intermediate information according to the first AI model, and the first input information and / or the second input information;

[0169] The first network device sends the first intermediate information to the terminal device;

[0170] The first intermediate information is used to determine the target cell with the second AI model.

[0171] In some embodiments, the method further comprises:

[0172] The first network device receives indication information sent by the terminal device; the indication information is used to indicate a first cell; the first cell is determined according to the target AI model, and the first input information and / or the second input information, or the first cell is determined according to the second AI model and the first intermediate information;

[0173] The first network device determines the target cell according to the first cell; wherein the target cell is the first cell or the second cell;

[0174] The first network device executes the switching of one or more terminal devices from a source cell to a target cell, including: the first network device sends a switching command to the terminal device; the switching command is used to indicate the target cell.

[0175] In some embodiments, the indication information is carried in a measurement report. In other embodiments, the indication information may be carried in a message other than a measurement report.

[0176] In some embodiments, the target input information includes: first input information and / or second input information; the method further includes:

[0177] The first network device determines first input information of the first network device, and / or the first network device receives second input information sent by the terminal device;

[0178] The first network device determines the target cell according to the target AI model, and the first input information and / or the second input information; wherein the target cell is the first cell or the second cell;

[0179] The first network device executes the switching of one or more terminal devices from a source cell to a target cell, including: the first network device sends a switching command to the terminal device; the switching command is used to indicate the target cell.

[0180] Optionally, the first network device determining the first input information of the first network device may include: the first network device obtaining the first input information of the first network device from itself.

[0181] Exemplarily, the first network device determines first input information of the first network device, and the first network device determines the target cell according to the target AI model and the first input information.

[0182] Also exemplarily, the first network device receives second input information sent by the terminal device, and the first network device determines the target cell based on the target AI model and the second input information.

[0183] Also exemplarily, the first network device determines the first input information of the first network device, and the first network device receives the second input information sent by the terminal device, and the first network device determines the target cell based on the target AI model, and the first input information and the second input information.

[0184] In some embodiments, the first network device determines the target cell based on the target AI model, and the first input information and / or the second input information, including: the first network device determines the first cell based on the target AI model, and the first input information and / or the second input information; the terminal device determines the target cell based on the first cell.

[0185] In some embodiments, the first network device determines the target cell according to the target AI model and the first input information and / or the second input information, including:

[0186] The first network device determines the first cell according to the target AI model and the first input information and / or the second input information;

[0187] The first network device determines the target cell according to the first cell.

[0188] In some embodiments, the target input information includes: first input information and / or second input information; the target AI model includes a third AI model and a fourth AI model, and the method further includes:

[0189] The first network device receives second intermediate information sent by the terminal device; wherein the second intermediate information is determined according to the third AI model, and the first input information and / or the second input information;

[0190] The first network device determines a target cell according to the fourth AI model and the second intermediate information; wherein the target cell is the first cell or the second cell;

[0191] The first network device executes the switching of one or more terminal devices from a source cell to a target cell, including: the first network device sends a switching command to the terminal device; the switching command is used to indicate the target cell.

[0192] In some embodiments, the first network device determines the target cell according to the fourth AI model and the second intermediate information, including:

[0193] The first network device determines a first cell according to the fourth AI model and the second intermediate information;

[0194] The first network device determines the target cell according to the first cell.

[0195] In some embodiments, the first network device determines the target cell according to the first cell, including:

[0196] The first network device determines the first cell as the target cell.

[0197] In some embodiments, the method also includes: the first network device receives the measurement results sent by the terminal device; the first network device determines the target cell based on the first cell, including: the first network device determines the target cell based on the first cell and the measurement results.

[0198] Optionally, the measurement result sent by the terminal device may be a measurement result of the terminal device.

[0199] Exemplarily, the first network device may determine whether the first cell meets the handover condition based on the measurement result, and determine the first cell as the target cell if the first cell meets the handover condition; if the first cell does not meet the handover condition, determine a second cell that meets the handover condition based on the measurement result, and determine the second cell as the target cell. Optionally, if it is determined that there is no second cell that meets the handover condition based on the measurement result, the terminal device and the first network device will not perform the handover process.

[0200] In some embodiments, the measurement result includes a measurement value of the first cell;

[0201] The first network device determines the target cell according to the first cell and the measurement result, including:

[0202] When the measurement value of the first cell is greater than a preset threshold, the first network device determines that the first cell is the target cell; and / or,

[0203] When the measurement value of the first cell is less than or equal to the preset threshold, the first network device determines a cell in the measurement result whose measurement value is greater than the preset threshold as a second cell, and determines the second cell as the target cell.

[0204] Optionally, the preset threshold may be the same as the second threshold mentioned above.

[0205] In some embodiments, the method further comprises:

[0206] The first network device sends pre-configuration information to the terminal device; the pre-configuration information includes at least one candidate cell, and the at least one candidate cell includes the target cell.

[0207] In some embodiments, the first input information includes at least one of the following: cell information of the source cell, load information of the source cell, service type information supported by the source cell, and measurement results of an uplink reference signal corresponding to the source cell.

[0208] In some embodiments, the second input information includes at least one of the following: a measurement result of the terminal device, location information of the terminal device, movement track information of the terminal device, movement speed information of the terminal device, navigation information of the terminal device, and business demand information of the terminal device.

[0209] The communication method of the embodiment of the present application is described below from other aspects:

[0210] FIG5 is a flow chart of another communication method provided in an embodiment of the present application. As shown in FIG5 , in the embodiment corresponding to FIG5 , the target AI model is deployed on the terminal device side, and the method includes:

[0211] S501. A first network device sends first input information to a terminal device.

[0212] S502. The terminal device obtains the second input information, and the terminal device determines the first cell and beam information based on the model reasoning result, reports the first cell and beam information to the first network device through a measurement report, and the first network device evaluates whether the first cell is suitable (ie, model output verification) to determine the target cell.

[0213] Optionally, the terminal device can perform a model reasoning process based on the first input information, the second input information and the target AI model.

[0214] Optionally, the beam information may correspond to the first cell. Optionally, the beam information may be the beam measurement result in the above embodiment.

[0215] Optionally, when the first cell is suitable, the first cell is determined as the target cell; when the first cell is not suitable, the second cell is determined as the target cell. Optionally, the second cell may be determined based on a traditional handover decision algorithm. Among them, the second cell determined by the traditional handover decision algorithm may be a cell not determined by the target AI model. Exemplarily, the second cell may be determined by the method in the protocol before this application.

[0216] S503: The first network device sends a switching request to the second network device.

[0217] S504: The first network device receives a switching request confirmation sent by the second network device.

[0218] S505. The first network device sends an RRC reconfiguration (RRC Reconfiguration) to the terminal device.

[0219] Among them, RRC Reconfiguration can carry a switching command.

[0220] S506: The terminal device switches to the target cell and sends a switching completion message to the second network device.

[0221] Optionally, the handover complete message may be referred to as RRC reconfiguration complete.

[0222] FIG6 is a flow chart of another communication method provided in an embodiment of the present application. As shown in FIG6 , in the embodiment corresponding to FIG6 , the target AI model is deployed on the terminal device side, and the method includes:

[0223] S601. A first network device sends pre-configuration information to a terminal device. The pre-configuration information may include one or more candidate cells.

[0224] S602: The first network device sends first input information to the terminal device.

[0225] S603: The terminal device obtains second input information, and the terminal device determines a target cell based on a model reasoning result.

[0226] Optionally, during implementation, the terminal device may determine the first cell and beam information based on the model reasoning result, and the terminal device evaluates whether the first cell is suitable (ie, model output verification) to determine the target cell.

[0227] S604: The terminal device performs a switching process from a source cell to a target cell based on pre-configuration information.

[0228] In the embodiment corresponding to FIG. 6 , when the terminal device determines the target cell, it directly switches from the source cell to the target cell without the first network device sending a switching command to the terminal device for switching, thereby improving switching efficiency.

[0229] FIG. 7 is a flow chart of a communication method provided by another embodiment of the present application. As shown in FIG. 7 , in the embodiment corresponding to FIG. 7 , the target AI model is deployed on the network device side, and the method includes:

[0230] S701. The terminal device sends a measurement report to the first network device.

[0231] The terminal device may measure the source cell and one or more candidate cells based on the measurement configuration to obtain a measurement report.

[0232] In some embodiments, the terminal device may report the second input information to the first network device.

[0233] S702: The first network device determines a target cell based on model reasoning.

[0234] Optionally, the first network device may determine the first cell through model reasoning, and determine the target cell based on the first cell.

[0235] S703: The first network device sends a switching request to the second network device.

[0236] S704: The first network device receives a switching request confirmation sent by the second network device.

[0237] S705. The first network device sends an RRC reconfiguration to the terminal device.

[0238] S706. The terminal device switches to the target cell and sends a switching completion message to the second network device.

[0239] FIG8 is a flow chart of a communication method provided by another embodiment of the present application. As shown in FIG8 , in the embodiment corresponding to FIG8 , the target AI model includes a first AI model and a second AI model, the first AI model is deployed on the first network device side, and the second AI model is deployed on the terminal device side. The method includes:

[0240] S801. The terminal device performs model inference, obtains first intermediate information, and sends the first intermediate information to the first network device.

[0241] Optionally, before S801, the terminal device may negotiate a model split point with the first network device. In this way, through the negotiated model split point, the terminal device and the first network device can each deploy a portion of the target AI model. Before S801, the terminal device may also receive the first input information sent by the first network device (i.e., interact with the first input information).

[0242] Optionally, the terminal device may negotiate a model split point with the first network device based on its own computing power.

[0243] Optionally, the terminal device may input the first input information and / or the second input information into the second AI model, and obtain the first intermediate information through model reasoning.

[0244] S802: The first network device performs model inference to obtain a target cell.

[0245] Optionally, the first network device may input the first intermediate information into the first AI model, obtain the first cell through model reasoning, and determine the target cell based on the first cell.

[0246] S803: The first network device sends a switching request to the second network device.

[0247] S804: The first network device receives a switching request confirmation sent by the second network device.

[0248] S805. The first network device sends an RRC reconfiguration to the terminal device.

[0249] S806. The terminal device switches to the target cell and sends a switching completion message to the second network device.

[0250] FIG9 is a flow chart of a communication method provided by another embodiment of the present application. As shown in FIG9 , in the embodiment corresponding to FIG9 , the target AI model includes a third AI model and a fourth AI model, the third AI model is deployed on the terminal device side, and the fourth AI model is deployed on the first network device side. The method includes:

[0251] S901. The first network device performs model inference to obtain second intermediate information, and sends the second intermediate information to the terminal device.

[0252] Optionally, before S901, the terminal device may negotiate the model split point with the first network device. In this way, through the negotiated model split point, the terminal device and the first network device can each deploy a portion of the target AI model. Before S901, the terminal device may also send the second input information to the first network device (i.e., exchange the second input information).

[0253] Optionally, the first network device may input the first input information and / or the second input information into the fourth AI model, and obtain the second intermediate information through model reasoning.

[0254] S902: The terminal device performs model inference to obtain a target cell.

[0255] Optionally, the terminal device can input the second intermediate information into the third AI model, obtain the first cell through model reasoning, and determine the target cell based on the first cell.

[0256] S903: The terminal device performs a switching process from a source cell to a target cell based on pre-configuration information.

[0257] In the embodiments corresponding to Figures 8 and 9, by deploying some AI models on the terminal device, the calculation examples of the terminal device can be saved. In addition, through the embodiment corresponding to Figure 8, the terminal device reports the first intermediate information to the first network device, thereby reducing the risk of information leakage and avoiding the situation where the target AI model is deployed on the first network device side and the user is unwilling to provide the first network device with information such as historical trajectory, resulting in inaccurate determination of the first cell.

[0258] In some embodiments, the first network device can output the first cells of multiple terminal devices at one time through the deployed target AI model, the first AI model or the fourth AI model, and the first cells of different terminal devices can be the same or different. Further, the first network device can determine whether each determined first cell is suitable, thereby determining the target cells of multiple terminal devices.

[0259] In some embodiments, both the value network and the policy network are deployed on the first network device. The policy network can be the target AI model in the embodiments of the present application. The value network is used to improve the policy network. In other embodiments, the policy network can be deployed on the terminal device side, while the value network is deployed on the first network device side, or both the value network and the policy network are deployed on the terminal device side.

[0260] In the embodiments of the present application, a process of model deployment and interaction is proposed, including scenarios where the model is reasoned on the terminal side, the network side, or both sides, thereby ensuring the use of the AI ​​mobility model and further ensuring the success rate of switching.

[0261] The preferred embodiments of the present application are described in detail above in conjunction with the accompanying drawings. However, the present application is not limited to the specific details in the above embodiments. Within the technical concept of the present application, the technical solution of the present application can be subjected to a variety of simple modifications, and these simple modifications all belong to the protection scope of the present application. For example, the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present application will not further explain various possible combinations. For another example, the various different embodiments of the present application can also be arbitrarily combined, as long as they do not violate the idea of ​​the present application, they should also be regarded as the contents disclosed in the present application. For another example, the various embodiments and / or the technical features in the various embodiments described in the present application can be arbitrarily combined with the relevant technologies within the scope of the technical concept of the present application, and the technical solution obtained after the combination should also fall within the protection scope of the present application.

[0262] It should also be understood that in various method embodiments of the present application, the size of the sequence number of each process does not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiment of the present application. In addition, in the embodiment of the present application, the terms "downlink", "uplink" and "side" are used to indicate the transmission direction of the signal or data, wherein "downlink" is used to indicate that the transmission direction of the signal or data is the first direction sent from the site to the user equipment of the cell, "uplink" is used to indicate that the transmission direction of the signal or data is the second direction sent from the user equipment of the cell to the site, and "side" is used to indicate that the transmission direction of the signal or data is the third direction sent from user equipment 1 to user equipment 2. For example, "downlink signal" indicates that the transmission direction of the signal is the first direction. In addition, in the embodiment of the present application, the term "and / or" is only a description of the association relationship of the associated objects, indicating that three relationships can exist. Specifically, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the front and back associated objects are in an "or" relationship.

[0263] FIG10 is a schematic diagram of the structure of a communication device provided in an embodiment of the present application, which is applied to a terminal device. As shown in FIG10 , the communication device 1000 includes:

[0264] The communication unit 1001 is used to switch from a source cell to a target cell; wherein the target cell is determined based on a target AI model and target input information for inputting into the target AI model.

[0265] In some embodiments, the communication device 1000 further includes: a determination unit 1002, configured to determine a target cell.

[0266] In some embodiments, the target input information includes: first input information and / or second input information;

[0267] The communication unit 1001 is used to receive the first input information sent by the first network device corresponding to the source cell, and / or the determination unit 1002 is further used to determine the second input information of the terminal device;

[0268] The determination unit 1002 is further used to determine the target cell according to the target AI model, and the first input information and / or the second input information.

[0269] In some embodiments, the determination unit 1002 is further used to: determine the first cell according to the target AI model, and the first input information and / or the second input information; and determine the target cell according to the first cell.

[0270] In some embodiments, the target input information includes: first input information and / or second input information; the target AI model includes a first AI model and a second AI model, and the communication unit 1001 is further used to: receive first intermediate information sent by a first network device corresponding to the source cell; the first intermediate information is determined according to the first AI model, and the first input information and / or the second input information;

[0271] The determination unit 1002 is further used to: determine the first cell according to the second AI model and the first intermediate information; and determine the target cell according to the first cell.

[0272] In some embodiments, the communication unit 1001 is also used to: send indication information to the first network device; the indication information is used to indicate the first cell; receive a switching command sent by the first network device; the switching command is used to indicate the target cell; wherein the target cell is the first cell or the second cell.

[0273] In some embodiments, the indication information is carried in a measurement report.

[0274] In some embodiments, the determining unit 1002 is further configured to: determine that the first cell is the target cell; or determine the target cell according to the first cell and a measurement result.

[0275] In some embodiments, the measurement result includes a measurement value of the first cell; the determination unit 1002 is further used to: when the measurement value of the first cell is greater than a preset threshold, determine that the first cell is the target cell; and / or, when the measurement value of the first cell is less than or equal to the preset threshold, determine the cell in the measurement result whose measurement value is greater than the preset threshold as the second cell, and determine the second cell as the target cell.

[0276] In some embodiments, the target input information includes: first input information and / or second input information; the communication unit 1001 is further used to: receive a handover command sent by a first network device corresponding to the source cell; the handover command is used to indicate the target cell; wherein the target cell is the first cell or the second cell;

[0277] Among them, the first cell is determined according to the target AI model, and the first input information and / or the second input information; the first input information is determined by the first network device; and the second input information is sent by the terminal device to the first network device.

[0278] In some embodiments, the target input information includes: first input information and / or second input information; the target AI model includes a third AI model and a fourth AI model, and the communication unit 1001 is also used to: receive the first input information sent by the first network device corresponding to the source cell, and / or the terminal device determines the second input information of the terminal device; the determination unit 1002 is also used to: determine the second intermediate information according to the third AI model, and the first input information and / or the second input information; the communication unit 1001 is also used to: send the second intermediate information to the first network device; the second intermediate information is used to determine the first cell with the fourth AI model; receive the switching command sent by the first network device; the switching command is used to indicate the target cell; wherein the target cell is the first cell or the second cell.

[0279] In some embodiments, the communication unit 1001 is further used to: send a measurement result to the first network device; and the measurement result is used to determine the target cell with the first cell.

[0280] In some embodiments, the communication unit 1001 is further used to: receive pre-configuration information sent by a first network device corresponding to the source cell; the pre-configuration information includes at least one candidate cell, and the at least one candidate cell includes the target cell.

[0281] In some embodiments, the first input information includes at least one of the following: cell information of the source cell, load information of the source cell, service type information supported by the source cell, and measurement results of uplink reference signals corresponding to the source cell;

[0282] The second input information includes at least one of the following: a measurement result of the terminal device, location information of the terminal device, movement track information of the terminal device, movement speed information of the terminal device, navigation information of the terminal device, and business demand information of the terminal device.

[0283] FIG. 11 is a schematic diagram of the structure of another communication device provided in an embodiment of the present application, which is applied to a terminal device. As shown in FIG. 11 , the communication device 1100 includes:

[0284] The communication unit 1101 is used to execute the switching of one or more terminal devices from a source cell to a target cell; wherein the target cell is determined based on a target AI model and target input information for inputting into the target AI model.

[0285] In some embodiments, the communication device 1101 further includes: a determination unit 1102, configured to determine a target cell.

[0286] In some embodiments, the target input information includes: first input information, or the first input information and second input information; the communication unit 1101 is also used to: send the first input information to the terminal device; the first input information is used to determine the target cell with the target AI model, or the first input information is used to determine the target cell with the target AI model and the second input information.

[0287] In some embodiments, the target input information includes: first input information and / or second input information; the target AI model includes a first AI model and a second AI model, and the determination unit 1102 is also used to: determine the first intermediate information based on the first AI model, and the first input information and / or the second input information; the communication unit 1101 is also used to: send the first intermediate information to the terminal device; wherein the first intermediate information is used to determine the target cell with the second AI model.

[0288] In some embodiments, the communication unit 1101 is also used to: receive indication information sent by the terminal device; the indication information is used to indicate a first cell; the first cell is determined based on the target AI model, and the first input information and / or the second input information, or the first cell is determined based on the second AI model and the first intermediate information; the determination unit 1102 is also used to: determine the target cell based on the first cell; wherein the target cell is the first cell or the second cell; the communication unit 1101 is also used to: send a switching command to the terminal device; the switching command is used to indicate the target cell.

[0289] In some embodiments, the indication information is carried in a measurement report.

[0290] In some embodiments, the target input information includes: first input information and / or second input information;

[0291] In some embodiments, the determination unit 1102 is also used to: determine the first input information of the first network device, and / or the communication unit 1101 is also used to: receive the second input information sent by the terminal device; the determination unit 1102 is also used to: determine the target cell according to the target AI model, and the first input information and / or the second input information; wherein the target cell is the first cell or the second cell; the communication unit 1101 is also used to: send a switching command to the terminal device; the switching command is used to indicate the target cell.

[0292] In some embodiments, the determination unit 1102 is further used to: determine the first cell based on the target AI model, and the first input information and / or the second input information; and determine the target cell based on the first cell.

[0293] In some embodiments, the target input information includes: first input information and / or second input information; the target AI model includes a third AI model and a fourth AI model, and the communication unit 1101 is also used to: receive second intermediate information sent by the terminal device; wherein the second intermediate information is determined based on the third AI model, and the first input information and / or the second input information; the determination unit 1102 is also used to: determine the target cell based on the fourth AI model and the second intermediate information; wherein the target cell is the first cell or the second cell; the communication unit 1101 is also used to: send a switching command to the terminal device; the switching command is used to indicate the target cell.

[0294] In some embodiments, the determination unit 1102 is further used to: determine the first cell according to the fourth AI model and the second intermediate information; and determine the target cell according to the first cell.

[0295] In some embodiments, the determination unit 1102 is further used to: determine that the first cell is the target cell.

[0296] In some embodiments, the communication unit 1101 is further used to: receive a measurement result sent by the terminal device; the determination unit 1102 is further used to: determine the target cell according to the first cell and the measurement result.

[0297] In some embodiments, the measurement result includes a measurement value of the first cell; the determination unit 1102 is further used to: when the measurement value of the first cell is greater than a preset threshold, determine that the first cell is the target cell; and / or, when the measurement value of the first cell is less than or equal to the preset threshold, determine the cell in the measurement result whose measurement value is greater than the preset threshold as the second cell, and determine the second cell as the target cell.

[0298] In some embodiments, the communication unit 1101 is further used to: send pre-configuration information to the terminal device; the pre-configuration information includes at least one candidate cell, and the at least one candidate cell includes the target cell.

[0299] In some embodiments, the first input information includes at least one of the following: cell information of the source cell, load information of the source cell, service type information supported by the source cell, and measurement results of uplink reference signals corresponding to the source cell;

[0300] The second input information includes at least one of the following: a measurement result of the terminal device, location information of the terminal device, movement track information of the terminal device, movement speed information of the terminal device, navigation information of the terminal device, and business demand information of the terminal device.

[0301] Those skilled in the art should understand that the relevant description of the above-mentioned communication device in the embodiment of the present application can be understood by referring to the relevant description of the communication method in the embodiment of the present application.

[0302] FIG12 is a schematic structural diagram of a communication device provided in an embodiment of the present application, and the communication device 1200 may include one of the following: a terminal device, a first network device. The communication device 1200 shown in FIG12 may include a processor 1210 and a memory 1220, wherein the memory 1220 stores a computer program that can be run on the processor 1210, and the processor 1210 implements the communication method in any of the above embodiments when executing the program.

[0303] Optionally, the memory 1220 may be a separate device independent of the processor 1210 , or may be integrated into the processor 1210 .

[0304] In some embodiments, as shown in FIG. 12 , the communication device 1200 may further include a transceiver 1230 , and the processor 1210 may control the transceiver 1230 to communicate with other devices, specifically, may send information or data to other devices, or receive information or data sent by other devices.

[0305] The transceiver 1230 may include a transmitter and a receiver. The transceiver 1230 may further include an antenna, and the number of antennas may be one or more.

[0306] In some embodiments, the communication device 1200 may specifically be a terminal device or a first network device of an embodiment of the present application, and the communication device 1200 may implement the corresponding processes implemented by the terminal device or the first network device in each method of the embodiment of the present application, which will not be repeated here for the sake of brevity.

[0307] An embodiment of the present application further provides a computer storage medium, which stores one or more programs. The one or more programs can be executed by one or more processors to implement the communication method in any embodiment of the present application.

[0308] In some embodiments, the computer-readable storage medium can be applied to the terminal device or the first network device in the embodiments of the present application, and the computer program enables the computer to execute the corresponding processes implemented by the terminal device or the first network device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0309] FIG13 is a schematic structural diagram of a chip according to an embodiment of the present application. The chip 1300 shown in FIG13 includes a processor 1310. The processor 1310 is used to call and run a computer program from a memory to implement a method in any embodiment of the present application.

[0310] In some embodiments, as shown in FIG13 , the chip 1300 may further include a memory 1320. The processor 1310 may call and run a computer program from the memory 1320 to implement the method in the embodiment of the present application.

[0311] The memory 1320 may be a separate device independent of the processor 1310 , or may be integrated into the processor 1310 .

[0312] In some embodiments, the chip 1300 may further include an input interface 1330. The processor 1310 may control the input interface 1330 to communicate with other devices or chips, and specifically, may obtain information or data sent by other devices or chips.

[0313] In some embodiments, the chip 1300 may further include an output interface 1340. The processor 1310 may control the output interface 1340 to communicate with other devices or chips, and specifically, may output information or data to other devices or chips.

[0314] In some embodiments, the chip can be applied to the terminal device or the first network device in the embodiments of the present application, and the chip can implement the corresponding processes implemented by the terminal device or the first network device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0315] It should be understood that the chip mentioned in the embodiments of the present application can also be called a system-level chip, a system chip, a chip system or a system-on-chip chip, etc.

[0316] An embodiment of the present application also provides a computer program product, which includes a computer storage medium, the computer storage medium storing a computer program, and the computer program including instructions that can be executed by at least one processor. When the instructions are executed by the at least one processor, the communication method in any embodiment of the present application is implemented.

[0317] In some embodiments, the computer program product can be applied to the terminal device or the first network device in the embodiments of the present application, and the computer program instructions enable the computer to execute the corresponding processes implemented by the terminal device or the first network device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0318] Optionally, the computer program product in the embodiments of the present application may also be referred to as a software product in other embodiments.

[0319] An embodiment of the present application also provides a computer program, which enables a computer to execute the communication method in any embodiment of the present application.

[0320] In some embodiments, the computer program can be applied to the terminal device or the first network device in the embodiments of the present application. When the computer program runs on the computer, the computer executes the corresponding processes implemented by the terminal device or the first network device in the various methods of the embodiments of the present application. For the sake of brevity, they will not be repeated here.

[0321] The processor, communication device or chip of the embodiment of the present application may be an integrated circuit chip with signal processing capability. In the implementation process, each step of the above method embodiment can be completed by the hardware integrated logic circuit or software instruction in the processor. The above processor, communication device or chip may include any one or more of the following integrations: general processor, application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), digital signal processor (Digital Signal Processor, DSP), digital signal processing device (Digital Signal Processing Device, DSPD), programmable logic device (Programmable Logic Device, PLD), field programmable gate array (Field Programmable Gate Array, FPGA), central processing unit (Central Processing Unit, CPU), graphics processing unit (Graphics Processing Unit, GPU), embedded neural network processor (neural-network processing units, NPU), controller, microcontroller, microprocessor, programmable logic device, discrete gate or transistor logic device, discrete hardware component. The disclosed methods, steps and logic block diagrams in the embodiment of the present application can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as being executed by a hardware decoding processor, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0322] It is understood that the memory or computer storage medium in the embodiments of the present application may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memories. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), or a flash memory. The volatile memory may be a random access memory (RAM), which is used as an external cache. By way of example and not limitation, many forms of RAM are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), and direct memory bus random access memory (DR RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0323] It should be understood that the above-mentioned memory or computer storage medium is exemplary but not restrictive. For example, the memory in the embodiments of the present application may also be static random access memory (static RAM, SRAM), dynamic random access memory (dynamic RAM, DRAM), synchronous dynamic random access memory (synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (double data rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (enhanced SDRAM, ESDRAM), synchronous link dynamic random access memory (synch link DRAM, SLDRAM) and direct memory bus random access memory (Direct Rambus RAM, DR RAM), etc. That is to say, the memory in the embodiments of the present application is intended to include but not limited to these and any other suitable types of memory.

[0324] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0325] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0326] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0327] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0328] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0329] In any embodiment of the present application, the time interval, time period, duration range, duration or time window, etc. may include all endpoint times, or may include part of the endpoint times (for example, including the left endpoint time but not the right endpoint time, or including the right endpoint time but not the left endpoint time), or may not include the endpoint time.

[0330] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the relevant technology. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., and other media that can store program codes.

[0331] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

A communication method, the method comprising: The terminal device switches from a source cell to a target cell; wherein the target cell is determined based on a target AI model and target input information for input into the target AI model. The method according to claim 1, wherein the target input information comprises: first input information and / or second input information; The method further includes: the terminal device receiving the first input information sent by the first network device corresponding to the source cell, and / or the terminal device determining the second input information of the terminal device; The terminal device determines the target cell based on the target AI model, and the first input information and / or the second input information. According to the method of claim 2, the terminal device determines the target cell according to the target AI model, and the first input information and / or the second input information, including: The terminal device determines a first cell according to the target AI model and the first input information and / or the second input information; The terminal device determines the target cell based on the first cell. The method according to claim 1, wherein the target input information comprises: first input information and / or second input information; The target AI model includes a first AI model and a second AI model, and the method further includes: the terminal device receiving first intermediate information sent by a first network device corresponding to the source cell; The first intermediate information is determined based on the first AI model, and the first input information and / or the second input information; the terminal device determines the first cell based on the second AI model and the first intermediate information; the terminal device determines the target cell based on the first cell. According to the method of claim 3 or 4, the terminal device determines the target cell according to the first cell, comprising: The terminal device sends indication information to the first network device; The indication information is used to indicate the first cell; The terminal device receives a switching command sent by the first network device; the switching command is used to indicate the target cell; wherein the target cell is the first cell or the second cell. According to the method according to claim 5, the indication information is carried in a measurement report. According to the method of claim 3 or 4, the terminal device determines the target cell according to the first cell, comprising: The terminal device determines that the first cell is the target cell; Alternatively, the terminal device determines the target cell based on the first cell and the measurement result. The method according to claim 7, wherein the measurement result comprises a measurement value of the first cell; The terminal device determines the target cell according to the first cell and the measurement result, including: When the measurement value of the first cell is greater than a preset threshold, the terminal device determines that the first cell is the target cell; And / or, when the measurement value of the first cell is less than or equal to the preset threshold, the terminal device determines the cell in the measurement result whose measurement value is greater than the preset threshold as the second cell, and determines the second cell as the target cell. The method according to claim 1, wherein the target input information comprises: first input information and / or second input information; The method also includes: the terminal device receives a switching command sent by the first network device corresponding to the source cell; the switching command is used to indicate the target cell; wherein the target cell is the first cell or the second cell; wherein the first cell is determined based on the target AI model, and the first input information and / or the second input information; the first input information is determined by the first network device; and the second input information is sent by the terminal device to the first network device. The method according to claim 1, wherein the target input information comprises: first input information and / or second input information; The target AI model includes a third AI model and a fourth AI model, and the method also includes: the terminal device receives the first input information sent by the first network device corresponding to the source cell, and / or the terminal device determines the second input information of the terminal device; the terminal device determines the second intermediate information according to the third AI model, and the first input information and / or the second input information; the terminal device sends the second intermediate information to the first network device; the second intermediate information is used to determine the first cell with the fourth AI model; the terminal device receives the switching command sent by the first network device; the switching command is used to indicate the target cell; wherein the target cell is the first cell or the second cell. The method according to claim 5, 9 or 10, further comprising: The terminal device sends a measurement result to the first network device; the measurement result is used to determine the target cell with the first cell. The method according to any one of claims 1 to 11, further comprising: The terminal device receives pre-configuration information sent by the first network device corresponding to the source cell; The pre-configuration information includes at least one candidate cell, and the at least one candidate cell includes the target cell. According to the method described in any one of claims 2 to 11, the first input information includes at least one of the following: cell information of the source cell, load information of the source cell, service type information supported by the source cell, and measurement results of uplink reference signals corresponding to the source cell; the second input information includes at least one of the following: measurement results of the terminal device, location information of the terminal device, moving trajectory information of the terminal device, moving speed information of the terminal device, navigation information of the terminal device, and service demand information of the terminal device. A communication method, the method comprising: The first network device executes switching of one or more terminal devices from a source cell to a target cell; wherein the target cell is determined based on a target AI model and target input information for input into the target AI model. The method according to claim 14, wherein the target input information comprises: first input information, or the first input information and second input information; The method further includes: the first network device sending first input information to the terminal device; The first input information is used to determine the target cell together with the target AI model, or the first input information is used to determine the target cell together with the target AI model and the second input information. The method according to claim 14, wherein the target input information comprises: first input information and / or second input information; The target AI model includes a first AI model and a second AI model, and the method also includes: the first network device determines first intermediate information based on the first AI model, and the first input information and / or the second input information; the first network device sends the first intermediate information to the terminal device; wherein the first intermediate information is used to determine the target cell with the second AI model. The method according to any one of claims 14 to 16, further comprising: The first network device receives the indication information sent by the terminal device; The indication information is used to indicate the first cell; The first cell is determined according to the target AI model, and the first input information and / or the second input information, or the first cell is determined according to the second AI model and the first intermediate information; the first network device determines the target cell according to the first cell; wherein the target cell is the first cell or the second cell; the first network device executes one or more terminal devices switching from the source cell to the target cell, including: the first network device sends a switching command to the terminal device; the switching command is used to indicate the target cell. According to the method of claim 17, the indication information is carried in a measurement report. The method according to claim 14, wherein the target input information comprises: first input information and / or second input information; The method also includes: the first network device determines the first input information of the first network device, and / or the first network device receives the second input information sent by the terminal device; the first network device determines the target cell according to the target AI model, and the first input information and / or the second input information; wherein the target cell is the first cell or the second cell; the first network device executes one or more terminal devices switching from the source cell to the target cell, including: the first network device sends a switching command to the terminal device; the switching command is used to indicate the target cell. According to the method of claim 19, the first network device determines the target cell according to the target AI model, and the first input information and / or the second input information, comprising: The first network device determines the first cell according to the target AI model and the first input information and / or the second input information; The first network device determines the target cell according to the first cell. The method according to claim 14, wherein the target input information comprises: first input information and / or second input information; The target AI model includes a third AI model and a fourth AI model, and the method also includes: the first network device receives second intermediate information sent by the terminal device; wherein the second intermediate information is determined according to the third AI model, and the first input information and / or the second input information; the first network device determines a target cell according to the fourth AI model and the second intermediate information; wherein the target cell is the first cell or the second cell; the first network device executes switching of one or more terminal devices from a source cell to a target cell, including: the first network device sends a switching command to the terminal device; the switching command is used to indicate the target cell. The method according to claim 21, wherein the first network device determines the target cell according to the fourth AI model and the second intermediate information, comprising: The first network device determines a first cell according to the fourth AI model and the second intermediate information; The first network device determines the target cell according to the first cell. According to the method of claim 17, 20 or 22, the first network device determining the target cell according to the first cell comprises: The first network device determines the first cell as the target cell. The method according to claim 17, 20 or 22, further comprising: The first network device receives the measurement result sent by the terminal device; The first network device determines the target cell according to the first cell, including: the first network device determines the target cell according to the first cell and the measurement result. The method according to claim 24, wherein the measurement result comprises a measurement value of the first cell; The first network device determines the target cell according to the first cell and the measurement result, including: When the measurement value of the first cell is greater than a preset threshold, the first network device determines that the first cell is the target cell; And / or, when the measurement value of the first cell is less than or equal to the preset threshold, the first network device determines a cell in the measurement result whose measurement value is greater than the preset threshold as a second cell, and determines the second cell as the target cell. The method according to any one of claims 14 to 25, further comprising: The first network device sends pre-configuration information to the terminal device; The pre-configuration information includes at least one candidate cell, and the at least one candidate cell includes the target cell. According to the method described in any one of claims 15 to 25, the first input information includes at least one of the following: cell information of the source cell, load information of the source cell, service type information supported by the source cell, and measurement results of uplink reference signals corresponding to the source cell; the second input information includes at least one of the following: measurement results of the terminal device, location information of the terminal device, moving trajectory information of the terminal device, moving speed information of the terminal device, navigation information of the terminal device, and service demand information of the terminal device. A communication device, comprising: A communication unit, used to switch from a source cell to a target cell; wherein the target cell is determined based on a target AI model and target input information for input into the target AI model. A communication device, comprising: A communication unit, used to execute the switching of one or more terminal devices from a source cell to a target cell; wherein the target cell is determined based on a target AI model and target input information for input into the target AI model. A communication device, comprising: A processor and a memory, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the program, the method described in any one of claims 1 to 13 or any one of claims 14 to 27 is implemented. A computer storage medium storing one or more programs, wherein the one or more programs can be executed by one or more processors to implement the method described in any one of claims 1 to 13 or any one of claims 14 to 27. A chip, comprising: A processor, configured to call and run a computer program from a memory to implement the method as claimed in any one of claims 1 to 13 or any one of claims 14 to 27. A computer program product, comprising a computer storage medium storing a computer program, wherein the computer program comprises instructions executable by at least one processor, and when the instructions are executed by the at least one processor, the method described in any one of claims 1 to 13 or any one of claims 14 to 27 is implemented. A computer program, wherein the computer program enables a computer to execute the method according to any one of claims 1 to 13 or any one of claims 14 to 27.

Images