Network switching method and device, equipment, storage medium and program product

Abstract

The embodiment of the invention provides a network switching method and device, equipment, a storage medium and a program product. The method comprises the following steps: receiving a network quality parameter corresponding to at least one cell or beam of each PLMN in at least one PLMN; processing the identification information of the at least one cell or beam of each PLMN and the network quality parameter corresponding to the at least one cell or beam of each PLMN through an artificial intelligence (AI) model to obtain first identification information, the first identification information being one of the identification information of the at least one cell or beam of each PLMN; and when the cell or beam indicated by the first identification information is different from the serving cell or beam of the terminal, performing cell or beam switching. The method is used for achieving the effect of improving the timeliness of cell or beam switching of the terminal.

Description

Technical Field

[0001] The present application relates to technical fields such as artificial intelligence, communications, and autonomous driving, and in particular to a network switching method, apparatus, device, storage medium, and program product. Background Art

[0002] Cell handover technology refers to the switching of a terminal from one cell to another to ensure that the terminal always accesses the best cell. Currently, cell handover technology is mainly used in mobile communication devices, such as smartphones and mobile hotspot devices.

[0003] In cell handover technology, the terminal can send a measurement report (MR) to the source network device. The source network device evaluates whether to initiate a cell handover based on the measurement report, or the source network device evaluates whether to initiate a cell handover based on the measurement report through the core network. When the source network device determines to initiate a cell handover, it sends a handover command (Handover Command) to the terminal. The handover command is used to instruct the terminal to handover to another cell. The terminal switches to the other cell according to the handover command.

[0004] In related technologies, communication between a terminal and a network device, such as evaluating whether to initiate a cell handover and transmitting a handover command, is required for the terminal to switch to another cell. This results in poor timeliness in switching to another cell. Summary of the Invention

[0005] The embodiments of the present application provide a network switching method, apparatus, device, storage medium, and program product to improve the timeliness of terminal switching cells.

[0006] In a first aspect, an embodiment of the present application provides a network switching method, applied to a terminal, the method comprising:

[0007] receiving a network quality parameter corresponding to at least one cell or beam of each PLMN in at least one PLMN;

[0008] Processing, by an artificial intelligence (AI) model, identification information of at least one cell or beam of each PLMN and a network quality parameter corresponding to the at least one cell or beam of each PLMN to obtain first identification information, where the first identification information is one of the identification information of the at least one cell or beam of each PLMN;

[0009] When the cell or beam indicated by the first identification information is different from the serving cell or beam of the terminal, cell or beam switching is performed.

[0010] In a possible implementation, the processing, by an artificial intelligence (AI) model, of identification information of at least one cell or beam of each PLMN and a network quality parameter corresponding to at least one cell or beam of each PLMN to obtain the first identification information includes:

[0011] Processing, by the first submodel in the AI model, identification information of the at least one cell or beam of each PLMN and a network quality parameter corresponding to the at least one cell or beam of each PLMN to obtain a quality score of the at least one cell or beam of each PLMN;

[0012] Through the second sub-model in the AI model, the network quality parameters corresponding to at least one cell or beam of each PLMN and the quality score of at least one cell or beam of each PLMN are processed to obtain the first identification information.

[0013] In a possible implementation, the processing, by an artificial intelligence (AI) model, of identification information of at least one cell or beam of each PLMN and a network quality parameter corresponding to at least one cell or beam of each PLMN to obtain the first identification information includes:

[0014] Obtaining a signal quality parameter corresponding to at least one cell or beam of each PLMN;

[0015] Through the AI model, the identification information of at least one cell or beam of each PLMN, the signal quality parameter corresponding to at least one cell or beam of each PLMN, and the network quality parameter corresponding to at least one cell or beam of each PLMN are processed to obtain the first identification information.

[0016] In a possible implementation, the processing, by the AI model, of identification information of at least one cell or beam of each PLMN, a signal quality parameter corresponding to at least one cell or beam of each PLMN, and a network quality parameter corresponding to at least one cell or beam of each PLMN to obtain the first identification information includes:

[0017] Processing, by the first submodel in the AI model, identification information of the at least one cell or beam of each PLMN, a signal quality parameter corresponding to the at least one cell or beam of each PLMN, and a network quality parameter corresponding to the at least one cell or beam of each PLMN to obtain a quality score of the at least one cell or beam of each PLMN;

[0018] Through the second sub-model in the AI model, the signal quality parameters corresponding to at least one cell or beam of each PLMN, the network quality parameters corresponding to at least one cell or beam of each PLMN, and the quality score of at least one cell or beam of each PLMN are processed to obtain the first identification information.

[0019] In a possible implementation, the processing, by the AI model, of identification information of at least one cell or beam of each PLMN, a signal quality parameter corresponding to at least one cell or beam of each PLMN, and a network quality parameter corresponding to at least one cell or beam of each PLMN to obtain the first identification information includes:

[0020] Acquiring driving information of the terminal;

[0021] Through the AI model, the driving information of the terminal, the identification information of at least one cell or beam of each PLMN, the signal quality parameter corresponding to at least one cell or beam of each PLMN, and the network quality parameter corresponding to at least one cell or beam of each PLMN are processed to obtain the first identification information.

[0022] In a possible implementation, the processing of the terminal's driving information, identification information of at least one cell or beam of each PLMN, a signal quality parameter corresponding to at least one cell or beam of each PLMN, and a network quality parameter corresponding to at least one cell or beam of each PLMN by the AI model to obtain the first identification information includes:

[0023] Processing, by the first submodel in the AI model, the driving information of the terminal, the identification information of the at least one cell or beam of each PLMN, the signal quality parameter corresponding to the at least one cell or beam of each PLMN, and the network quality parameter corresponding to the at least one cell or beam of each PLMN to obtain a quality score of the at least one cell or beam of each PLMN;

[0024] The second sub-model in the AI model processes the driving information of the terminal, the signal quality parameters corresponding to at least one cell or beam of each PLMN, the network quality parameters corresponding to at least one cell or beam of each PLMN, and the quality score of at least one cell or beam of each PLMN to obtain the first identification information.

[0025] In a possible implementation, the travel information of the terminal is travel information of the terminal within a preset time period in the future;

[0026] The signal quality parameter corresponding to the at least one cell or beam of each PLMN is a signal quality parameter corresponding to the at least one cell or beam of each PLMN within the future preset time period;

[0027] The network quality parameter corresponding to the at least one cell or beam of each PLMN is the network quality parameter corresponding to the at least one cell or beam of each PLMN within the future preset time period.

[0028] In a possible implementation, performing cell handover includes:

[0029] switching from the serving cell to the cell indicated by the first identification information, wherein the serving cell and the cell indicated by the first identification information belong to the same PLMN, or the serving cell and the cell indicated by the first identification information belong to different PLMNs;

[0030] Perform beam switching, including:

[0031] Switch from the serving beam to the beam indicated by the first identification information, wherein the serving beam and the beam indicated by the first identification information belong to the same PLMN, or the serving beam and the beam indicated by the first identification information belong to different PLMNs.

[0032] In a possible implementation, the at least one PLMN is a PLMN that the terminal has already accessed.

[0033] In one possible implementation, the method further includes:

[0034] Send a request message to the network device corresponding to at least one cell or beam of each PLMN, wherein the request message is used to request to obtain the network quality parameter corresponding to the cell or beam.

[0035] In a possible implementation manner, the network quality parameters corresponding to the cell or beam include one or more of the following:

[0036] Network performance parameters corresponding to the cell or beam;

[0037] The quality of service parameter corresponding to the cell or beam; or

[0038] The network status parameters corresponding to the cell or beam.

[0039] In a possible implementation, the network performance parameter includes one or more of the following: bandwidth, delay, jitter, packet loss rate, throughput, or bit error rate.

[0040] In a possible implementation manner, the quality of service parameters include one or more of the following: bandwidth guarantee, maximum delay, maximum jitter, maximum packet loss rate, or priority.

[0041] In a possible implementation, the network status parameter includes one or more of the following: network load, connection establishment time, or service availability.

[0042] In a possible implementation, the identification information of the cell or beam is pre-configured in the terminal; or, the identification information of the cell or beam is carried in a system message sent by a network device corresponding to the cell or beam to the terminal.

[0043] In a possible implementation manner, the identification information of the cell or beam is pre-configured in the terminal, including one or more of the following:

[0044] The identification information of the cell or beam is pre-configured in an extensible markup language XML file of the terminal; or,

[0045] The identification information of the cell or beam is pre-configured in the subscriber identity module SIM of the terminal.

[0046] In a possible implementation manner, the identification information of the cell includes an identification of a PLMN to which the cell belongs and an identification of the cell;

[0047] The identification information of the beam includes an identification of the PLMN to which the beam belongs and beam information of the beam.

[0048] In a possible implementation manner, the signal quality parameter includes one or more of the following:

[0049] Reference signal received power RSRP;

[0050] Reference signal reception quality RSRQ;

[0051] Received Signal Strength Indicator RSSI; or

[0052] Signal to Interference and Noise Ratio SINR.

[0053] In a possible implementation, the driving information of the terminal includes one or more of the following:

[0054] The weather type of the scene where the terminal is located;

[0055] location information of the terminal;

[0056] The type of scenario in which the terminal is located;

[0057] the type of road on which the terminal is located;

[0058] the travel speed of the terminal;

[0059] the direction of travel of the terminal; or

[0060] The traffic conditions of the terminal.

[0061] In a possible implementation, the processing, by an artificial intelligence (AI) model, of identification information of at least one cell or beam of each PLMN and a network quality parameter corresponding to at least one cell or beam of each PLMN to obtain the first identification information includes:

[0062] When a preset condition is met, processing, by the AI model, identification information of at least one cell or beam of each PLMN and a network quality parameter corresponding to at least one cell or beam of each PLMN to obtain the first identification information;

[0063] The preset conditions include one or more of the following:

[0064] The signal quality parameter corresponding to the serving cell or beam is less than or equal to a preset quality threshold;

[0065] The network performance parameters corresponding to the serving cell or beam deteriorate;

[0066] The type of the scene in which the terminal is located changes;

[0067] The type of the road where the terminal is located changes; or

[0068] The current mode of the terminal is the automatic driving mode.

[0069] In a second aspect, an embodiment of the present application provides a network switching method, applied to a network device corresponding to a cell or beam of a PLMN, the method comprising:

[0070] The network quality parameters corresponding to the cell or beam are sent to the terminal, and the network quality parameters corresponding to the cell or beam are used for processing by the AI model of the terminal to obtain first identification information. The first identification information is used by the terminal to perform cell or beam switching when the cell or beam indicated by the first identification information is different from the serving cell or beam of the terminal.

[0071] In a possible implementation manner, the PLMN is a PLMN that the terminal has already accessed.

[0072] In one possible implementation, the method further includes:

[0073] Receive a request message sent by the terminal, wherein the request message is used to request to obtain the network quality parameters corresponding to the cell or beam.

[0074] In a possible implementation manner, the network quality parameters corresponding to the cell or beam include one or more of the following:

[0075] Network performance parameters corresponding to the cell or beam;

[0076] The quality of service parameter corresponding to the cell or beam; or

[0077] The network status parameters corresponding to the cell or beam.

[0078] In a possible implementation, the network performance parameter includes one or more of the following: bandwidth, delay, jitter, packet loss rate, throughput, or bit error rate.

[0079] In a possible implementation manner, the quality of service parameters include one or more of the following: bandwidth guarantee, maximum delay, maximum jitter, maximum packet loss rate, or priority.

[0080] In a possible implementation, the network status parameter includes one or more of the following: network load, connection establishment time, or service availability.

[0081] In a third aspect, an embodiment of the present application provides a network switching device, including:

[0082] a transceiver module, configured to receive network quality parameters corresponding to at least one cell or beam of each PLMN in at least one PLMN;

[0083] a processing module, configured to process, through an artificial intelligence (AI) model, identification information of at least one cell or beam of each PLMN and a network quality parameter corresponding to at least one cell or beam of each PLMN to obtain first identification information, where the first identification information is one of the identification information of at least one cell or beam of each PLMN;

[0084] The processing module is also used to perform cell or beam switching when the cell or beam indicated by the first identification information is different from the serving cell or beam of the terminal.

[0085] In a possible implementation, the processing module is specifically configured to:

[0086] Processing, by the first submodel in the AI model, identification information of the at least one cell or beam of each PLMN and a network quality parameter corresponding to the at least one cell or beam of each PLMN to obtain a quality score of the at least one cell or beam of each PLMN;

[0087] Through the second sub-model in the AI model, the network quality parameters corresponding to at least one cell or beam of each PLMN and the quality score of at least one cell or beam of each PLMN are processed to obtain the first identification information.

[0088] In a possible implementation, the processing module is specifically configured to:

[0089] Obtaining a signal quality parameter corresponding to at least one cell or beam of each PLMN;

[0090] Through the AI model, the identification information of at least one cell or beam of each PLMN, the signal quality parameter corresponding to at least one cell or beam of each PLMN, and the network quality parameter corresponding to at least one cell or beam of each PLMN are processed to obtain the first identification information.

[0091] In a possible implementation, the processing module is specifically configured to:

[0092] Processing, by the first submodel in the AI model, identification information of the at least one cell or beam of each PLMN, a signal quality parameter corresponding to the at least one cell or beam of each PLMN, and a network quality parameter corresponding to the at least one cell or beam of each PLMN to obtain a quality score of the at least one cell or beam of each PLMN;

[0093] Through the second sub-model in the AI model, the signal quality parameters corresponding to at least one cell or beam of each PLMN, the network quality parameters corresponding to at least one cell or beam of each PLMN, and the quality score of at least one cell or beam of each PLMN are processed to obtain the first identification information.

[0094] In a possible implementation, the processing module is specifically configured to:

[0095] Acquiring driving information of the terminal;

[0096] Through the AI model, the driving information of the terminal, the identification information of at least one cell or beam of each PLMN, the signal quality parameter corresponding to at least one cell or beam of each PLMN, and the network quality parameter corresponding to at least one cell or beam of each PLMN are processed to obtain the first identification information.

[0097] In a possible implementation, the processing module is specifically configured to:

[0098] Processing, by the first submodel in the AI model, the driving information of the terminal, the identification information of the at least one cell or beam of each PLMN, the signal quality parameter corresponding to the at least one cell or beam of each PLMN, and the network quality parameter corresponding to the at least one cell or beam of each PLMN to obtain a quality score of the at least one cell or beam of each PLMN;

[0099] The second sub-model in the AI model processes the driving information of the terminal, the signal quality parameters corresponding to at least one cell or beam of each PLMN, the network quality parameters corresponding to at least one cell or beam of each PLMN, and the quality score of at least one cell or beam of each PLMN to obtain the first identification information.

[0100] In a possible implementation, the travel information of the terminal is travel information of the terminal within a preset time period in the future;

[0101] The signal quality parameter corresponding to the at least one cell or beam of each PLMN is a signal quality parameter corresponding to the at least one cell or beam of each PLMN within the future preset time period;

[0102] The network quality parameter corresponding to the at least one cell or beam of each PLMN is the network quality parameter corresponding to the at least one cell or beam of each PLMN within the future preset time period.

[0103] In a possible implementation, the processing module is specifically configured to:

[0104] switching from the serving cell to the cell indicated by the first identification information, wherein the serving cell and the cell indicated by the first identification information belong to the same PLMN, or the serving cell and the cell indicated by the first identification information belong to different PLMNs;

[0105] Perform beam switching, including:

[0106] Switch from the serving beam to the beam indicated by the first identification information, wherein the serving beam and the beam indicated by the first identification information belong to the same PLMN, or the serving beam and the beam indicated by the first identification information belong to different PLMNs.

[0107] In a possible implementation, the at least one PLMN is a PLMN that the terminal has already accessed.

[0108] In a possible implementation, the transceiver module is further configured to:

[0109] Send a request message to the network device corresponding to at least one cell or beam of each PLMN, wherein the request message is used to request to obtain the network quality parameter corresponding to the cell or beam.

[0110] In a possible implementation manner, the network quality parameters corresponding to the cell or beam include one or more of the following:

[0111] Network performance parameters corresponding to the cell or beam;

[0112] The quality of service parameter corresponding to the cell or beam; or

[0113] The network status parameters corresponding to the cell or beam.

[0114] In a possible implementation, the network performance parameter includes one or more of the following: bandwidth, delay, jitter, packet loss rate, throughput, or bit error rate.

[0115] In a possible implementation manner, the quality of service parameters include one or more of the following: bandwidth guarantee, maximum delay, maximum jitter, maximum packet loss rate, or priority.

[0116] In a possible implementation, the network status parameter includes one or more of the following: network load, connection establishment time, or service availability.

[0117] In a possible implementation, the identification information of the cell or beam is pre-configured in the terminal; or, the identification information of the cell or beam is carried in a system message sent by a network device corresponding to the cell or beam to the terminal.

[0118] In a possible implementation manner, the identification information of the cell or beam is pre-configured in the terminal, including one or more of the following:

[0119] The identification information of the cell or beam is pre-configured in an extensible markup language XML file of the terminal; or,

[0120] The identification information of the cell or beam is pre-configured in the subscriber identity module SIM of the terminal.

[0121] In a possible implementation manner, the identification information of the cell includes an identification of a PLMN to which the cell belongs and an identification of the cell;

[0122] The identification information of the beam includes an identification of the PLMN to which the beam belongs and beam information of the beam.

[0123] In a possible implementation manner, the signal quality parameter includes one or more of the following:

[0124] Reference signal received power RSRP;

[0125] Reference signal reception quality RSRQ;

[0126] Received Signal Strength Indicator RSSI; or

[0127] Signal to Interference and Noise Ratio SINR.

[0128] In a possible implementation, the driving information of the terminal includes one or more of the following:

[0129] The weather type of the scene where the terminal is located;

[0130] location information of the terminal;

[0131] The type of scenario in which the terminal is located;

[0132] the type of road on which the terminal is located;

[0133] the travel speed of the terminal;

[0134] the direction of travel of the terminal; or

[0135] The traffic conditions of the terminal.

[0136] In a possible implementation, the processing module is specifically configured to:

[0137] When a preset condition is met, processing, by the AI model, identification information of at least one cell or beam of each PLMN and a network quality parameter corresponding to at least one cell or beam of each PLMN to obtain the first identification information;

[0138] The preset conditions include one or more of the following:

[0139] The signal quality parameter corresponding to the serving cell or beam is less than or equal to a preset quality threshold;

[0140] The network performance parameters corresponding to the serving cell or beam deteriorate;

[0141] The type of the scene in which the terminal is located changes;

[0142] The type of the road where the terminal is located changes; or

[0143] The current mode of the terminal is the automatic driving mode.

[0144] In a fourth aspect, an embodiment of the present application provides a network switching device, including:

[0145] A transceiver module is used to send the network quality parameters corresponding to the cell or beam to the terminal. The network quality parameters corresponding to the cell or beam are used for processing by the AI model of the terminal to obtain first identification information. The first identification information is used by the terminal to perform cell or beam switching when the cell or beam indicated by the first identification information is different from the serving cell or beam of the terminal.

[0146] In a possible implementation manner, the PLMN is a PLMN that the terminal has already accessed.

[0147] In one possible implementation, the transceiver module is further configured to:

[0148] Receive a request message sent by the terminal, wherein the request message is used to request to obtain the network quality parameters corresponding to the cell or beam.

[0149] In a possible implementation manner, the network quality parameters corresponding to the cell or beam include one or more of the following:

[0150] Network performance parameters corresponding to the cell or beam;

[0151] The quality of service parameter corresponding to the cell or beam; or

[0152] The network status parameters corresponding to the cell or beam.

[0153] In a possible implementation, the network performance parameter includes one or more of the following: bandwidth, delay, jitter, packet loss rate, throughput, or bit error rate.

[0154] In a possible implementation manner, the quality of service parameters include one or more of the following: bandwidth guarantee, maximum delay, maximum jitter, maximum packet loss rate, or priority.

[0155] In a possible implementation, the network status parameter includes one or more of the following: network load, connection establishment time, or service availability.

[0156] In a fifth aspect, an embodiment of the present application provides a terminal, characterized in that it includes: a memory and a processor;

[0157] The memory stores computer-executable instructions;

[0158] The processor executes the computer-executable instructions stored in the memory, so that the processor performs the first aspect and / or various possible implementations of the first aspect.

[0159] In a sixth aspect, an embodiment of the present application provides a network device, including: a memory and a processor;

[0160] The memory stores computer-executable instructions;

[0161] The processor executes the computer-executable instructions stored in the memory, so that the processor performs the second aspect and / or various possible implementations of the second aspect.

[0162] In the seventh aspect, an embodiment of the present application provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are executed by a processor, they are used to implement the above-mentioned first aspect and / or various possible implementation methods of the first aspect, as well as the second aspect and / or various possible implementation methods of the second aspect.

[0163] In an eighth aspect, an embodiment of the present application provides a computer program product, comprising a computer program, which, when executed by a processor, implements the above-mentioned first aspect and / or various possible implementations of the first aspect, as well as the second aspect and / or various possible implementations of the second aspect.

[0164] In a ninth aspect, an embodiment of the present application provides a computer program, which, when executed by a processor, implements the above-mentioned first aspect and / or various possible implementations of the first aspect, as well as the second aspect and / or various possible implementations of the second aspect.

[0165] The embodiments of the present application provide a network switching method, apparatus, device, storage medium and program product, which receive network quality parameters corresponding to at least one cell or beam of each PLMN in at least one PLMN; process the identification information of at least one cell or beam of each PLMN and the network quality parameters corresponding to at least one cell or beam of each PLMN through an artificial intelligence (AI) model to obtain first identification information, where the first identification information is one of the identification information of at least one cell or beam of each PLMN; when the cell or beam indicated by the first identification information is different from the service cell or beam of the terminal, perform cell or beam switching without evaluating whether to initiate cross-PLMN switching and transmitting switching commands, etc., thereby avoiding switching delays and connection interruptions, and improving the timeliness of the terminal switching to the cell or beam indicated by the first identification information, especially when the terminal is in automatic driving mode, which can improve the safety of the terminal. BRIEF DESCRIPTION OF THE DRAWINGS

[0166] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0167] Figure 1 A schematic diagram of a scenario of inter-PLMN handover provided in an embodiment of the present application;

[0168] Figure 2 Schematic diagram of the network switching method provided in the embodiment of the present application Figure 1 ;

[0169] Figure 3 Schematic diagram of the network switching method provided in the embodiment of the present application Figure 2 ;

[0170] Figure 4 Schematic diagram of the network switching method provided in the embodiment of the present application Figure 3 ;

[0171] Figure 5 Schematic diagram of the network switching method provided in the embodiment of the present application Figure 4 ;

[0172] Figure 6 Schematic diagram of the process of obtaining the AI model provided in the embodiment of this application Figure 1 ;

[0173] Figure 7 Schematic diagram of the process of obtaining the AI model provided in the embodiment of this application Figure 2 ;

[0174] Figure 8 A schematic diagram of the interaction process between the first sub-model and the second sub-model provided in an embodiment of the present application;

[0175] Figure 9 A schematic diagram of the structure of the network switching device provided in the embodiment of the present application Figure 1 ;

[0176] Figure 10 A schematic diagram of the structure of the network switching device provided in the embodiment of the present application Figure 2 ;

[0177] Figure 11 A schematic diagram of the structure of a terminal provided in an embodiment of the present application;

[0178] Figure 12 A schematic diagram of the structure of the network device provided in an embodiment of the present application.

[0179] The above drawings illustrate specific embodiments of the present application, which will be described in more detail below. These drawings and the textual description are not intended to limit the scope of the present application in any way, but rather to illustrate the concepts of the present application to those skilled in the art by reference to specific embodiments. DETAILED DESCRIPTION

[0180] Exemplary embodiments will be described in detail herein, and examples thereof are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0181] First, the terms involved in the present application will be explained:

[0182] In the embodiments of the present application, terms such as "first" and "second" are used to distinguish identical or similar items with basically the same functions and roles. For example, the first value and the second value are merely used to distinguish different values, and do not limit their sequence. Those skilled in the art can understand that terms such as "first" and "second" do not limit the quantity and execution order, and the terms "first" and "second" do not necessarily mean different.

[0183] It should be noted that in the embodiments of the present application, words such as "exemplarily" or "for example" are used to represent examples, illustrations or explanations. Any embodiment or design described as "exemplarily" or "for example" in the present application should not be construed as being more preferred or having more advantages than other embodiments or designs. Rather, the use of words such as "exemplarily" or "for example" is intended to present related concepts in a specific manner.

[0184] In the embodiments of the present application, "at least one" means one or more, and "multiple" means two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one (item)" or its similar expression refers to any combination of these items, including any combination of single item (item) or plural items (items). For example, at least one (item) of a, b, or c can represent: a, b, c, a - b, a - c, b - c, or a - b - c, where a, b, c can be single or multiple.

[0185] In some embodiments, terms such as greater than, greater than or equal to, not less than, more than, more than or equal to, not less than, higher than, higher than or equal to, not lower than, above, etc. can be replaced with each other, and terms such as less than, less than or equal to, not greater than, less than, less than or equal to, not more than, lower than, lower than or equal to, not higher than, below, etc. can be replaced with each other.

[0186] In some embodiments, the network device may be an access network device (AN device), a radio access network device (RAN device), a base station (BS), a radio base station, a fixed station, a node, an access point, a transmission point (TP), a reception point (RP), a transmission / reception point (TRP), a panel, an antenna panel, an antenna array, a cell, a macro cell, a small cell, a femto cell, a pico cell, a sector, a cell group, a serving cell, a carrier, a component carrier, a bandwidth part (BWP), etc.

[0187] In some embodiments, " / " represents or, for example, "transmission / reception" represents sending or receiving.

[0188] In some embodiments, the terminal may be a terminal, a terminal device, a user equipment (UE), a user terminal, a mobile station (MS), a subscriber station, a mobile unit, a wireless unit, a remote unit, a mobile device, a wireless device, a wireless communication device, a remote device, a mobile subscriber station, an access terminal, a mobile terminal, a wireless terminal, a remote terminal, a handset, a user agent, a mobile client, or a client. The terminal may be a vehicle, or a terminal device, a user equipment, a user terminal, etc. in a vehicle.

[0189] The following is an explanation of the professional terms involved in this application.

[0190] 1. Cell switching technology switching

[0191] Cell switching technology switching refers to the switching of a terminal from one cell to another to ensure that the terminal always accesses the best cell. Currently, cell switching technology is mainly used in mobile communication devices, and terminals are such as smart phones and mobile hotspot devices. In the cell switching technology, the terminal can send a measurement report (MeasurementReport, MR) to the source network device, and the source network device evaluates whether to initiate a cell switch based on the measurement report, or the source network device evaluates whether to initiate a cell switch based on the measurement report through the core network. When it is determined to initiate a cell switch, the source network device sends a handover command (Handover Command) to the terminal, and the handover command is used to instruct the terminal to switch to another cell. The terminal switches to another cell according to the handover command. In related technologies, communication between the terminal and the network device, such as evaluating whether to initiate a cell switch and transmitting a handover command, can enable the terminal to switch to another cell, which will result in poor timeliness in switching to another cell.

[0192] 2. Handover across Public Land Mobile Networks (PLMNs)

[0193] PLMN handover refers to the terminal switching from the mobile network of one operator to the mobile network of another operator to ensure that the terminal always accesses the best PLMN. Currently, cross-PLMN network handover technology is mainly used in mobile communication devices, such as smartphones and mobile hotspot devices. In cross-PLMN handover technology, the terminal can send a measurement report (Measurement Report, MR) to the source network device, and the source network device evaluates whether to initiate cross-PLMN handover based on the measurement report, or the source network device evaluates whether to initiate cross-PLMN handover based on the measurement report through the core network. When it is determined to initiate cross-PLMN handover, the source network device sends a handover command (Handover Command) to the terminal. The handover command is used to instruct the terminal to switch to another PLMN. The terminal switches to another PLMN according to the handover command. In related technologies, communication between the terminal, network equipment, and core network, such as evaluating whether to initiate cross-PLMN handover and transmitting handover commands, can enable the terminal to switch to another PLMN. This will result in poor timeliness in switching to another PLMN.

[0194] Figure 1 A schematic diagram of a cross-PLMN handover scenario provided in an embodiment of the present application is shown in FIG. Figure 1 As shown, it includes a terminal, area A and area B.

[0195] Area A includes PLMNs of multiple mobile network operators (MNOs). For example, the multiple MNOs in area A include MNO a1, MNO a2, MNO a3, and so on.

[0196] Area B includes multiple PLMNs of mobile network operators (MNOs). For example, the multiple MNOs in area B include MNO b1, MNO b2, MNO b3, and so on.

[0197] In some scenarios, the terminal manufacturer may sign service agreements with the MNO in region A and the MNO in region B. If the terminal crosses the border from region A to region B, the PLMN used by the terminal needs to be switched from the PLMN of an MNO in region A to the PLMN of an MNO in region B.

[0198] In other scenarios, the terminal manufacturer may sign a service agreement with the MNO in region A, and the MNO in region A may sign a roaming agreement with the MNO in region B. If the terminal crosses the border from region A to region B, the PLMN used by the terminal needs to be switched from the PLMN of an MNO in region A to the PLMN of an MNO in region B that has a roaming agreement with the MNO in region A.

[0199] Optionally, if the terminal uses the existing technology to switch from the PLMN of an MNO in area A to the PLMN of an MNO in area B that has signed a roaming agreement with an MNO in area A, the communication process involved includes: the terminal sends a measurement report (Measurement Report, MR) to the network device corresponding to the PLMN of an MNO in area A, and the network device evaluates whether to initiate an inter-PLMN handover based on the measurement report, or the network device evaluates whether to initiate an inter-PLMN handover based on the measurement report through the core network. When it is determined to initiate an inter-PLMN handover, the network device sends a handover command to the terminal, and the handover command is used to instruct the terminal to switch to the PLMN of an MNO in area B. The terminal switches to the PLMN of an MNO in area B according to the handover command.

[0200] During the above communication process, since communication is required between the terminal, network equipment, and core network (for example, evaluating whether to initiate cross-PLMN switching and transmitting switching commands, etc.), switching delays or connection interruptions may occur. If the terminal is in autonomous driving mode at this time, the terminal will have poor security.

[0201] The network switching method provided by an embodiment of the present application determines first identification information in at least one cell of each PLMN based on network quality parameters corresponding to at least one cell or beam of each PLMN. When the cell or beam indicated by the first identification information is different from the service cell or beam of the terminal, cell or beam switching is performed without evaluating whether to initiate cell switching and transmit switching commands, or without evaluating whether to initiate cross-PLMN switching and transmit switching commands. This can avoid switching delays or connection interruptions, improve the timeliness of cell or beam switching of the terminal, and improve the safety of the terminal, especially when the terminal is in automatic driving mode.

[0202] The following specific embodiments describe in detail the technical solution of the present application and how the technical solution of the present application solves the above-mentioned technical problems. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below in conjunction with the accompanying drawings.

[0203] Figure 2Schematic diagram of the network switching method provided in the embodiment of the present application Figure 1 .like Figure 2 As shown, the method includes:

[0204] S201: A network device corresponding to at least one cell or beam of each PLMN in at least one PLMN sends a network quality parameter corresponding to the corresponding cell or beam to a terminal. Correspondingly, the terminal receives the network quality parameter corresponding to the at least one cell or beam of each PLMN.

[0205] In some embodiments, the at least one PLMN is a PLMN of at least one MNO.

[0206] In some embodiments, at least one MNO may be an MNO in the same region or an MNO in different regions. Figure 1 At least one MNO in region A or at least one MNO in region B. Exemplarily, when at least one MNO is an MNO in a different region, the at least one MNO includes, for example Figure 1 At least one MNO in region A or at least one MNO in region B.

[0207] In some embodiments, the at least one PLMN includes the PLMN to which the serving cell or beam of the terminal belongs.

[0208] For the PLMN to which the serving cell of the terminal belongs, the at least one cell of the PLMN may include the serving cell of the terminal and may also include a neighboring cell of the serving cell in the PLMN.

[0209] For the PLMN to which the service beam of the terminal belongs, at least one beam of the PLMN may include the service beam of the terminal and may also include an adjacent beam of the service beam in the PLMN.

[0210] For each PLMN in at least one PLMN except the PLMN to which the terminal's serving cell belongs, at least one cell of the PLMN includes a neighboring area of the serving cell in the PLMN. It should be understood that the serving cell and the neighboring area are adjacent, and the serving cell and the neighboring area belong to different PLMNs.

[0211] For each PLMN in at least one PLMN except the PLMN to which the service beam of the terminal belongs, at least one beam of the PLMN includes an adjacent beam of the service beam in the PLMN. It should be understood that the service beam and the adjacent beam are adjacent, and the service beam and the adjacent beam belong to different PLMNs.

[0212] In some embodiments, the network quality parameters corresponding to the cell or beam include one or more of the following:

[0213] Network performance parameters corresponding to the cell or beam;

[0214] Quality of service parameters corresponding to the cell or beam; or

[0215] Network status parameters corresponding to the cell or beam.

[0216] In some embodiments, the network quality parameters corresponding to the cell include one or more of the following:

[0217] Network performance parameters corresponding to the cell;

[0218] The quality of service parameters corresponding to the cell; or

[0219] Network status parameters corresponding to the cell.

[0220] In some embodiments, the network quality parameters corresponding to the beam include one or more of the following:

[0221] Network performance parameters corresponding to the beam;

[0222] The quality of service parameters corresponding to the beam; or,

[0223] Network status parameters corresponding to the beam.

[0224] In an embodiment of the present application, the network quality parameters corresponding to the cell or beam include one or more of the network performance parameters corresponding to the cell or beam, the service quality parameters corresponding to the cell or beam, or the network status parameters corresponding to the cell or beam, thereby achieving the purpose of determining the first identification information by referring to multiple parameters and helping to improve the accuracy of determining the first identification information.

[0225] In some embodiments, the network performance parameters corresponding to the cell or beam include one or more of the following:

[0226] Bandwidth corresponding to the cell or beam;

[0227] Latency corresponding to the cell or beam;

[0228] Jitter corresponding to the cell or beam;

[0229] Packet loss rate (PLR) corresponding to the cell or beam;

[0230] Throughput of the cell or beam; or

[0231] The bit error rate (BER) corresponding to the cell or beam.

[0232] In some embodiments, the network performance parameters corresponding to the cell include one or more of the following:

[0233] Bandwidth corresponding to the cell;

[0234] The delay corresponding to the cell (Latency);

[0235] Jitter corresponding to the cell;

[0236] Packet Loss Rate corresponding to the cell;

[0237] The throughput of the cell (Through put); or,

[0238] The bit error rate (BER) corresponding to the cell.

[0239] In some embodiments, the network performance parameters corresponding to the beam include one or more of the following:

[0240] Bandwidth corresponding to the beam;

[0241] The delay corresponding to the beam (Latency);

[0242] Jitter corresponding to the beam;

[0243] Packet Loss Rate corresponding to the beam;

[0244] Throughput corresponding to the beam (Through put); or,

[0245] The bit error rate (BER) corresponding to the beam.

[0246] The bandwidth corresponding to a cell or beam is used to characterize the amount of data that the network can transmit in the cell or beam, usually in bits per second (bps), kilobits per second (Kbps), megabits per second (Mbps), or gigabits per second (Gbps).

[0247] The delay corresponding to a cell or beam is used to represent the time required for data to be transmitted from a source end to a destination end in the cell or beam, and is usually measured in milliseconds (ms).

[0248] The jitter corresponding to a cell or beam is used to characterize the variation in the data packet transmission delay in the cell or beam, and is usually measured in milliseconds (ms).

[0249] The packet loss rate corresponding to a cell or beam is used to characterize the proportion of data packets lost during transmission in the cell or beam, and is usually expressed as a percentage.

[0250] The throughput corresponding to a cell or beam is used to characterize the amount of data successfully transmitted per unit time in the cell or beam, and is usually measured in bps, Kbps, Mbps, or Gbps.

[0251] The bit error rate corresponding to a cell or beam is used to represent the ratio of the number of erroneous bits to the total number of transmitted bits during data transmission in the cell or beam.

[0252] In some embodiments, the quality of service parameters corresponding to the cell or beam include one or more of the following:

[0253] Bandwidth Guarantee for cells or beams;

[0254] Maximum latency of the cell or beam;

[0255] Maximum jitter of the cell or beam;

[0256] Maximum Packet Loss Rate (MPLR) of a cell or beam; or

[0257] Priority of the cell or beam.

[0258] Optionally, the bandwidth guarantee of a cell or beam is the bandwidth reserved for a specific application or service in the cell or beam.

[0259] Optionally, the maximum delay of a cell or beam is a maximum delay allowed for a specific application or service in the cell or beam.

[0260] Optionally, the maximum jitter of a cell or beam is a maximum jitter allowed for a specific application or service in the cell or beam.

[0261] Optionally, the maximum packet loss rate of a cell or beam is a maximum packet loss rate allowed for a specific application or service in the cell or beam.

[0262] Optionally, the priority of a cell or beam is the priority of different services in the cell or beam, wherein the autonomous driving service is the highest priority service.

[0263] In some embodiments, the network status parameters corresponding to the cell or beam include one or more of the following:

[0264] Network load of the cell or beam;

[0265] Connection Establishment Time for a cell or beam; or

[0266] Service availability of the cell or beam.

[0267] Optionally, the network load of a cell or beam represents the amount of data being transmitted in the cell or beam, usually expressed as a percentage of bandwidth.

[0268] Optionally, the connection establishment time of a cell or beam represents the time required to establish a network connection in the cell or beam, typically in milliseconds (ms).

[0269] Optionally, the service availability of a cell or beam represents the proportion of network services available in the cell or beam within a specific time, usually expressed as a percentage.

[0270] S202. The terminal processes the identification information of at least one cell or beam of each PLMN and the network quality parameter corresponding to at least one cell or beam of each PLMN through an artificial intelligence (AI) model to obtain first identification information, where the first identification information is one of the identification information of at least one cell or beam of each PLMN.

[0271] In some embodiments, the identification information of the cell includes an identification of the PLMN to which the cell belongs (PLMN ID) and an identification of the cell.

[0272] In some embodiments, the cell identifier includes, for example, a cell ID of the cell or a physical cell identifier (PCI) of the cell.

[0273] In some embodiments, the cell identification information may further include one or more of the following:

[0274] The cell's Tracking Area Code (TAC);

[0275] The cell's downlink bandwidth (DL Bandwidth); or

[0276] The uplink bandwidth (UL Bandwidth) of the cell.

[0277] In some embodiments, the identification information of the beam includes an identification of the PLMN to which the beam belongs and beam information of the beam.

[0278] In some embodiments, the identification information of the beam may further include one or more of the following:

[0279] Tracking Area Code (TAC) corresponding to the beam;

[0280] The downlink bandwidth (DL Bandwidth) corresponding to the cell; or,

[0281] The uplink bandwidth (UL Bandwidth) corresponding to the cell.

[0282] In some embodiments, identification information of at least one cell or beam of each PLMN is pre-configured in the terminal.

[0283] In some embodiments, identification information of at least one cell or beam of each PLMN is pre-configured in the terminal, including:

[0284] The identification information of at least one cell or beam of each PLMN is pre-configured in an Extensible Markup Language (XML) file of the terminal; or,

[0285] The identification information of at least one cell or beam of each PLMN is pre-configured in a subscriber identity module (SIM) of a terminal.

[0286] In some embodiments, the XML file is an XML file pre-configured before the terminal leaves the factory.

[0287] In some embodiments, when an XML file needs to be updated, the XML file can be updated via a cloud server based on Over-The-Air Technology (OTA).

[0288] In some embodiments, if the identification information of at least one cell or beam of each PLMN is pre-configured in the XML file of the terminal, the system application layer of the terminal can parse the XML file to obtain the identification information of at least one cell or beam of each PLMN.

[0289] In some embodiments, if the identification information of at least one cell or beam of each PLMN is pre-configured in the XML file of the terminal, the system application layer of the terminal can also read the SIM to obtain the identification information of at least one cell or beam of each PLMN.

[0290] In some embodiments, identification information of at least one cell or beam of each PLMN may also be hardware-encoded through a hardware abstraction layer (HAL) and configured in the terminal.

[0291] In some embodiments, for each cell or beam in at least one cell or beam of each PLMN, the identification information of the cell or beam is carried in a system message (System Information Block, SIB) sent by the network device corresponding to the cell or beam to the terminal.

[0292] In some embodiments, a network device sends a system message to a terminal, where the system message includes identification information of a cell or beam.

[0293] In some embodiments, for each cell or beam in at least one cell or beam of each PLMN, the identification information of the cell or beam is carried in the Equivalent Public Land Mobile Network (EPLMN) information sent by the network device corresponding to the cell or beam to the terminal.

[0294] In some embodiments, a network device sends an EPLMN message to a terminal, where the EPLMN message includes identification information of a cell or beam.

[0295] In some embodiments, when the identification information of a cell or beam is carried in a system message / EPLMN information sent by a network device to a terminal, the SoC of the terminal may parse the system message / EPLMN information to obtain the identification information of the cell or beam.

[0296] S203. When the cell or beam indicated by the first identification information is different from the serving cell or beam of the terminal, the terminal performs cell or beam switching.

[0297] In some embodiments, the terminal records the identification information of the service cell or beam. When the first identification information and the identification information of the service cell or beam are different, it is determined that the cell or beam indicated by the first identification information is different from the service cell or beam of the terminal, and cell or beam switching is performed at this time.

[0298] In some embodiments, when the cell indicated by the first identification information is different from the serving cell of the terminal, the terminal performs cell switching, that is, performs switching between cells.

[0299] It is worth noting that, in a cellular network, when the cell or beam indicated by the first identification information is different from the serving cell or beam of the terminal, cell switching is performed.

[0300] In some embodiments, performing cell switching includes: switching from a serving cell to a cell indicated by the first identification information; wherein the serving cell and the cell indicated by the first identification information belong to the same PLMN, or the serving cell and the cell indicated by the first identification information belong to different PLMNs.

[0301] In some embodiments, when the beam indicated by the first identification information is different from the serving beam of the terminal, the terminal performs beam switching, that is, performs switching between beams.

[0302] It is worth noting that, in a satellite network, when the beam indicated by the first identification information is different from the service beam of the terminal, beam switching is performed.

[0303] In some embodiments, performing beam switching includes: switching from a service beam to a beam indicated by first identification information; wherein the service beam and the beam indicated by the first identification information belong to the same PLMN, or the service beam and the beam indicated by the first identification information belong to different PLMNs.

[0304] In some embodiments, when the cell indicated by the first identification information is different from the serving beam of the terminal (or the beam indicated by the first identification information is the same as the serving cell of the terminal), the terminal performs switching between cells and beams.

[0305] It is worth noting that in a fused network of a cellular network and a satellite network, beam switching is performed when the beam indicated by the first identification information is different from the service beam of the terminal (or the beam indicated by the first identification information is different from the service cell of the terminal).

[0306] In some embodiments, the system on chip (SoC) in the terminal can perform a network search operation based on the first identification information. When searching for the cell or beam indicated by the first identification information, it registers to the PLMN to which the cell or beam indicated by the first identification information belongs, so as to switch to the cell or beam indicated by the first identification information.

[0307] In some embodiments, the SoC may perform a network search operation according to a preset standard (eg, 3GPP TS23.122) and based on the first identification information.

[0308] In some embodiments, when the cell or beam indicated by the first identification information is the same as the serving cell or beam, the terminal does not perform cell or beam switching and repeatedly performs S201 to S203.

[0309] In some embodiments, when the first identification information includes the identification of the PLMN to which the cell belongs and the beam information corresponding to the cell, and the cell or beam indicated by the first identification information is different from the service cell or beam of the terminal (that is, the beam indicated by the first identification information is different from the beam of the service cell), beam switching is performed.

[0310] When the PLMN to which the serving cell or beam belongs and the cell or beam indicated by the first identification information belong is the same, switching between different cells or beams of the same PLMN can be achieved. When the PLMN to which the serving cell or beam belongs and the cell or beam indicated by the first identification information belong are different, switching between cells or beams of different PLMNs can be achieved, that is, switching between cells or beams across PLMNs.

[0311] In the network switching method provided in an embodiment of the present application, the terminal obtains the network quality parameters corresponding to at least one cell or beam of each PLMN, and processes the identification information of at least one cell or beam of each PLMN and the network quality parameters corresponding to at least one cell or beam of each PLMN through an artificial intelligence AI model to obtain first identification information. When the cell or beam indicated by the first identification information is different from the service cell or beam of the terminal, cell or beam switching is performed without evaluating whether to initiate cell or beam switching and transmit switching commands, etc., and without evaluating whether to initiate cross-PLMN switching and transmit switching commands. Switching delays or connection interruptions can be avoided, and the timeliness of cell or beam switching of the terminal can be improved, especially when the terminal is in automatic driving mode, the safety of the terminal can be improved.

[0312] Unlike the prior art, in the prior art, in a multi-operator shared network (MOCN), the network switching efficiency is low, resulting in the terminal needing to traverse multiple PLMNs to switch PLMNs when the S1 / N2 interface between the core network and the base station (eNodeB) is disconnected, resulting in a long process of switching PLMNs, affecting the user experience. In the present application, when the S1 / N2 interface between the core network and the base station (eNodeB) is disconnected, the identification information of at least one cell or beam of each PLMN and the network quality parameters corresponding to at least one cell or beam of each PLMN can be processed by an AI model to obtain first identification information. When the cell or beam indicated by the first identification information is different from the serving cell or beam of the terminal, cell or beam switching is performed. When the cell or beam indicated by the first identification information is different from the PLMN to which the serving cell or beam of the terminal belongs, cross-PLMN cell or beam switching can be achieved. The terminal does not need to traverse multiple PLMNs to switch PLMNs, which can reduce the time taken to switch PLMNs and help improve the user experience.

[0313] In some embodiments, at least one PLMN cell is a PLMN that the terminal has already accessed. Therefore, when performing cell or beam switching, if the cell or beam indicated by the first identification information is different from the PLMN to which the terminal's serving cell or beam belongs, there is no need to access the PLMN to which the cell or beam indicated by the first identification information belongs. This allows the terminal to seamlessly switch between the PLMN to which the cell or beam indicated by the first identification information belongs and the PLMN to which the terminal's serving cell or beam belongs when the cell or beam indicated by the first identification information is different from the PLMN to which the terminal's serving cell or beam belongs, thereby helping to improve the timeliness of cell or beam switching across PLMNs for the terminal, and in particular, helping to improve the safety of the terminal when the terminal is in autonomous driving mode.

[0314] Figure 3 Schematic diagram of the network switching method provided in the embodiment of the present application Figure 2 .like Figure 3 As shown, the method includes:

[0315] S301. The terminal sends a request message to a network device corresponding to at least one cell or beam of each PLMN, where the request message is used to request to obtain a network quality parameter corresponding to the cell or beam.

[0316] In some embodiments, the terminal sends a request message to a network device corresponding to a cell or beam of a PLMN, wherein the request message is used to request to obtain a network quality parameter corresponding to the cell or beam.

[0317] In some embodiments, the terminal sends request information to a network device corresponding to at least one cell or beam of each PLMN based on identification information of at least one cell or beam of each PLMN.

[0318] S302. The network device corresponding to at least one cell or beam of each PLMN sends the network quality parameter corresponding to the cell or beam to the terminal according to the corresponding request information.

[0319] In some embodiments, in an autonomous driving service scenario, a network device sends a network quality parameter corresponding to a cell or beam to a terminal based on a corresponding request message.

[0320] In some embodiments, a network device corresponding to a cell or beam may send a first message to a terminal, where the first message carries network performance parameters corresponding to the cell or beam.

[0321] In some embodiments, the first information is, for example, SIB or EPLMN information.

[0322] In some embodiments, the explanation of the network quality parameters corresponding to the cell or beam can be found in S201 and will not be repeated here.

[0323] S303. The terminal processes the identification information of at least one cell or beam of each PLMN and the network quality parameter corresponding to at least one cell or beam of each PLMN through the AI model to obtain first identification information.

[0324] In some embodiments, S304 may be described by the methods shown in the following Examples A1, A2, and A3.

[0325] In Example A1, the terminal processes, through the AI model, identification information of at least one cell or beam of each PLMN and network quality parameters corresponding to at least one cell or beam of each PLMN to obtain a quality score corresponding to the identification information of at least one cell or beam of each PLMN.

[0326] The identification information corresponding to the maximum quality score among the quality scores corresponding to the identification information of at least one cell or beam of each PLMN is determined as the first identification information.

[0327] It is worth noting that in Example A1, the AI model can output identification information of at least one cell or beam of each PLMN, and the quality score corresponding to the identification information of at least one cell or beam of each PLMN.

[0328] Example A2: For each cell or beam in at least one cell or beam of each PLMN, the terminal determines a status corresponding to the cell or beam based on a network quality parameter corresponding to the cell or beam;

[0329] The AI model is used to process the state of at least one cell or beam of each PLMN to obtain first identification information. The first identification information is the action when the Q value in the Q table of the AI model is the maximum, wherein the action when the Q value is the maximum represents the identification information when the Q value is the maximum.

[0330] Example A3: Using the first submodel in the AI model, the identification information of at least one cell or beam of each PLMN and the network quality parameter corresponding to at least one cell or beam of each PLMN are processed to obtain a quality score of the at least one cell or beam of each PLMN.

[0331] Through the second sub-model in the AI model, the network quality parameters corresponding to at least one cell or beam of each PLMN and the quality score of at least one cell or beam of each PLMN are processed to obtain the first identification information.

[0332] In Example A3, the first sub-model may be the model in Example A1.

[0333] In Example A3, for each cell or beam in at least one cell or beam of each PLMN, the terminal determines a status corresponding to the cell or beam based on a network quality parameter corresponding to the cell or beam;

[0334] The state of at least one cell or beam of each PLMN and the quality score of at least one cell or beam of each PLMN are processed through the second sub-model to obtain first identification information.

[0335] Exemplarily, the input of the AI model in Example A1 or the first sub-model in Example A3 is shown in Table 1 below.

[0336] Table 1

[0337]

[0338] S304. When the cell or beam indicated by the first identification information is different from the serving cell or beam of the terminal, the terminal performs cell or beam switching.

[0339] Specifically, the execution method of S304 is the same as the execution method of S203, and will not be repeated here.

[0340] exist Figure 3 In the method provided in the embodiment, the terminal sends at least one request message to at least one network device based on the identifier of at least one cell of each PLMN, and at least one network device sends the network quality parameters corresponding to at least one cell or beam of each PLMN to the terminal based on its corresponding request information, which can prevent at least one network device from sending network quality parameters in real time.

[0341] Figure 4 Schematic diagram of the network switching method provided in the embodiment of the present application Figure 3 .like Figure 4 As shown, the method includes:

[0342] S401. A network device corresponding to at least one cell or beam of each PLMN in at least one PLMN sends a network quality parameter corresponding to the cell or beam to a terminal.

[0343] In some embodiments, the terminal sends a request message to a network device corresponding to at least one cell or beam of each PLMN in at least one PLMN, where the request message is used to request to obtain a network quality parameter corresponding to the cell or beam;

[0344] The network device corresponding to at least one cell or beam of each PLMN sends the network quality parameters corresponding to the cell or beam to the terminal according to the request information.

[0345] Specifically, the terminal sends a request message to a network device corresponding to a cell or beam of a PLMN, where the request message is used to request to obtain the network quality parameters corresponding to the cell or beam;

[0346] The network device sends the network quality parameters corresponding to the cell or beam to the terminal based on the request information.

[0347] S402. The terminal obtains a signal quality parameter corresponding to at least one cell or beam of each PLMN.

[0348] In some embodiments, the signal quality parameter corresponding to the cell or beam is obtained by the terminal measuring a signal (eg, a reference signal) sent by a network device corresponding to the cell or beam.

[0349] In some embodiments, the signal quality parameter includes one or more of the following:

[0350] Reference Signal Received Power (RSRP);

[0351] Reference Signal Received Quality (RSRQ);

[0352] Received Signal Strength Indicator (RSSI); or

[0353] Signal-to-Interference-plus-Noise Ratio (SINR).

[0354] Optionally, RSRP is used to describe the received power of a reference signal and measure the strength of a wireless signal.

[0355] Optionally, RSRQ is used to describe the signal quality of a reference signal.

[0356] Optionally, RSSI is an indicator used to measure the signal power strength detected by a receiving end (eg, a terminal or a network device).

[0357] Optionally, SINR is a ratio of useful signal power to interference and noise power.

[0358] S403. The terminal processes the identification information of at least one cell or beam of each PLMN, the signal quality parameter corresponding to at least one cell or beam of each PLMN, and the network quality parameter corresponding to at least one cell or beam of each PLMN through the AI model to obtain first identification information.

[0359] In some embodiments, S403 may be described by the methods shown in the following examples B1, B2, and B3.

[0360] In Example B1, the terminal processes, through the AI model, identification information of at least one cell or beam of each PLMN, a signal quality parameter corresponding to at least one cell or beam of each PLMN, and a network quality parameter corresponding to at least one cell or beam of each PLMN to obtain a quality score corresponding to the identification information of at least one cell or beam of each PLMN.

[0361] An identifier corresponding to a maximum quality score among the quality scores corresponding to the identifiers of at least one cell of each PLMN is determined as the first identifier information.

[0362] Example B2: For each cell or beam in at least one cell or beam of each PLMN, the terminal determines a status corresponding to the cell or beam based on a signal quality parameter and a network quality parameter corresponding to the cell or beam;

[0363] The AI model is used to process the state of at least one cell or beam of each PLMN to obtain first identification information. The first identification information is the action when the Q value in the Q table of the AI model is the maximum, wherein the action when the Q value is the maximum represents the identification information when the Q value is the maximum.

[0364] Example B3: Using the first submodel in the AI model, the identification information of at least one cell or beam of each PLMN, the signal quality parameter corresponding to at least one cell or beam of each PLMN, and the network quality parameter corresponding to at least one cell or beam of each PLMN are processed to obtain a quality score of at least one cell or beam of each PLMN.

[0365] Through the second sub-model in the AI model, the signal quality parameters corresponding to at least one cell or beam of each PLMN, the network quality parameters corresponding to at least one cell or beam of each PLMN, and the quality score of at least one cell or beam of each PLMN are processed to obtain the first identification information.

[0366] In example B3, the first sub-model may be the model in example B1.

[0367] In example B3, for each cell or beam in at least one cell or beam of each PLMN, a state corresponding to the cell or beam is determined based on a signal quality parameter and a network quality parameter corresponding to the cell or beam;

[0368] The state of at least one cell or beam of each PLMN and the quality score of at least one cell or beam of each PLMN are processed through the second sub-model to obtain first identification information.

[0369] Exemplarily, the input of the AI model in Example B1 or the first sub-model in Example B3 is shown in Table 2 below.

[0370] Table 2

[0371]

[0372] S404. When the cell or beam indicated by the first identification information is different from the serving cell or beam of the terminal, the terminal performs cell or beam switching.

[0373] In the network switching method provided in the embodiment of the present application, the identification information of at least one cell or beam of each PLMN, the signal quality parameters corresponding to at least one cell or beam of each PLMN, and the network quality parameters corresponding to at least one cell or beam of each PLMN are processed through an AI model to obtain first identification information, thereby achieving the purpose of simultaneously determining the first identification information based on the signal quality parameters and network quality parameters corresponding to the cell or beam, and helping to improve the accuracy of determining the first identification information. Furthermore, when the cell or beam indicated by the first identification information is different from the serving cell or beam, cell or beam switching is performed without the need to evaluate whether to initiate cell or beam switching, transmit switching commands, etc., nor is there the need to evaluate whether to initiate cross-PLMN switching, and transmit switching commands. This can avoid switching delays or connection interruptions, and can improve the timeliness of cell or beam switching of the terminal, especially when the terminal is in autonomous driving mode, which can improve the safety of the terminal.

[0374] Figure 5 Schematic diagram of the network switching method provided in the embodiment of the present application Figure 4 .like Figure 5 As shown, the method includes:

[0375] S501. A network device corresponding to at least one cell or beam of each PLMN in at least one PLMN sends a network quality parameter corresponding to the cell or beam to a terminal.

[0376] In some embodiments, the execution method of S501 is the same as the execution method of S401, and the execution process of S501 is not repeated here.

[0377] S502. The terminal obtains a signal quality parameter corresponding to at least one cell or beam of each PLMN.

[0378] In some embodiments, the execution method of S502 is the same as the execution method of S402, and the execution process of S502 is not repeated here.

[0379] S503: The terminal obtains the driving information of the terminal.

[0380] In some embodiments, the terminal's driving information includes one or more of the following:

[0381] The weather type of the scene where the terminal is located;

[0382] Terminal location information;

[0383] The type of scenario in which the terminal is located;

[0384] The type of road where the terminal is located;

[0385] The terminal's travel speed;

[0386] The terminal's direction of travel; or,

[0387] Traffic conditions at the terminal.

[0388] In some embodiments, the weather type is, for example, sunny, rainy, or snowy.

[0389] In some embodiments, the location information of the terminal includes, for example, the longitude and / or latitude of the terminal.

[0390] In some embodiments, the type of scene is, for example, city, countryside, etc.

[0391] In some embodiments, the type of road is, for example, a highway, a tunnel, etc.

[0392] In some embodiments, the current traffic condition of the terminal is, for example, congested, unobstructed, etc.

[0393] In some embodiments, the weather type and location information can be obtained by the terminal from the Internet, or obtained by the terminal from the vehicle. It is worth noting that the terminal can be a terminal installed in the vehicle.

[0394] In some embodiments, the scene type, road type, and traffic conditions may be acquired by the terminal from a road side unit (RSU).

[0395] In some embodiments, the driving speed and the driving direction may be obtained by the terminal from an electronic control unit (ECU) of the vehicle.

[0396] S504. The terminal processes the terminal's driving information, identification information of at least one cell or beam of each PLMN, signal quality parameters corresponding to at least one cell or beam of each PLMN, and network quality parameters corresponding to at least one cell or beam of each PLMN through the AI model to obtain first identification information.

[0397] In some embodiments, S504 may be described by the methods shown in the following examples C1, C2, and C3.

[0398] Example C1: The terminal processes, through an AI model, driving information of the terminal, identification information of at least one cell or beam of each PLMN, signal quality parameters corresponding to at least one cell or beam of each PLMN, and network quality parameters corresponding to at least one cell or beam of each PLMN to obtain a quality score corresponding to the identification information of at least one cell or beam of each PLMN.

[0399] Identification information corresponding to the maximum quality score among the quality scores corresponding to the identifiers of at least one cell of each PLMN is determined as the first identification information.

[0400] Example C2: For each cell or beam in at least one cell or beam of each PLMN, determine the status of the cell or beam based on the signal quality parameter and network quality parameter corresponding to the cell or beam and the driving information of the terminal;

[0401] The AI model processes the state corresponding to at least one cell or beam of each PLMN to obtain first identification information. The first identification information is the action when the Q value in the Q table of the AI model is the maximum, wherein the action when the Q value is the maximum represents the identification information when the Q value is the maximum.

[0402] Example C3: Using the first submodel in the AI model, the terminal's driving information, identification information of at least one cell or beam of each PLMN, signal quality parameters corresponding to at least one cell or beam of each PLMN, and network quality parameters corresponding to at least one cell or beam of each PLMN are processed to obtain a quality score for at least one cell or beam of each PLMN.

[0403] Through the second sub-model in the AI model, the driving information of the terminal, the signal quality parameters corresponding to at least one cell or beam of each PLMN, the network quality parameters corresponding to at least one cell or beam of each PLMN, and the quality score of at least one cell or beam of each PLMN are processed to obtain the first identification information.

[0404] In example C3, the first sub-model may instantiate the model in C1.

[0405] In example C3, for each cell or beam in at least one cell or beam of each PLMN, the terminal determines a status corresponding to the cell or beam based on a signal quality parameter and a network quality parameter corresponding to the cell or beam and driving information of the terminal;

[0406] The state corresponding to at least one cell or beam of each PLMN and the quality score of at least one cell or beam of each PLMN are processed through the second sub-model to obtain first identification information.

[0407] Exemplarily, the input of the AI model in Example B1 or the first sub-model in Example B3 is shown in Table 3 below.

[0408] Table 3

[0409]

[0410] S505. When the cell or beam indicated by the first identification information is different from the serving cell or beam of the terminal, the terminal performs cell or beam switching.

[0411] Unlike existing technologies, existing network selection algorithms are mainly based on static signal strength and network coverage, and lack the ability to intelligently process dynamic environments and complex scenarios. In autonomous driving scenarios, vehicles travel at high speeds and in complex environments. Existing network selection algorithms are difficult to adapt to changes in driving speed and environment, resulting in poor prediction accuracy of the network selection algorithm, thereby reducing the accuracy of the selected network. In the present application, first identification information is obtained based on the driving information of the terminal, the signal quality parameters corresponding to at least one cell or beam of each PLMN, and the network quality parameters corresponding to at least one cell or beam of each PLMN, so as to achieve the driving speed and environment (such as the weather type of the scene, the type of scene, the type of road, and traffic conditions, etc.) of the reference terminal, so that the AI model can adapt to these changes, thereby improving the prediction accuracy of the AI model and thereby improving the accuracy of the first identification information.

[0412] In the present application, the weather type of the scene in which the terminal is currently located may affect the signal strength and network stability of the cell. The type of scene in which the terminal is currently located and the type of road on which the terminal is currently located may also affect the network coverage and signal quality of the cell. The current location information of the terminal can help identify the coverage and signal strength of the cell. The current driving speed of the terminal may affect the frequency and stability of the cell's switching. The current driving direction of the terminal can help predict the future coverage of the cell. The current traffic conditions of the terminal may affect the load and performance of the cell. Therefore, in the present application, the driving information of the terminal determines the first identification information, which can improve the accuracy of the first identification information.

[0413] In some embodiments, the driving information of the terminal may be driving information collected by the terminal.

[0414] In some embodiments, the driving information collected by the terminal may include one or more of the following:

[0415] The weather type of the scene where the terminal is located, as queried by the terminal from the Internet;

[0416] The terminal's location information retrieved from the Internet;

[0417] The type of scenario in which the terminal is located obtained by the terminal from the RSU;

[0418] The type of road on which the terminal is located obtained by the terminal from the RSU;

[0419] The terminal's traffic status obtained from the RSU;

[0420] The terminal's driving speed obtained from the vehicle's ECU;

[0421] The terminal obtains the terminal's driving direction from the vehicle's ECU.

[0422] In some embodiments, the driving information of the terminal may also be driving information of the terminal within a preset time period in the future obtained by predicting the driving information collected by the terminal.

[0423] In some embodiments, the signal quality parameter corresponding to at least one cell or beam of each PLMN is the signal quality parameter corresponding to at least one cell or beam of each PLMN obtained by the terminal measurement, or it may be the signal quality parameter corresponding to at least one cell or beam of each PLMN within a preset time period in the future obtained by predicting the signal quality parameter corresponding to at least one cell or beam of each PLMN obtained by the terminal measurement.

[0424] In some embodiments, the network quality parameter corresponding to at least one cell or beam of each PLMN is the corresponding network quality parameter sent by the network device corresponding to at least one cell or beam of each PLMN to the terminal, or it may be the network quality parameter corresponding to at least one cell or beam of each PLMN within a preset time period in the future obtained by predicting the corresponding network quality parameter sent by the network device corresponding to at least one cell or beam of each PLMN to the terminal.

[0425] Exemplarily, the future preset duration is, for example, 5 minutes (min) to 10 minutes. It should be understood that the future preset duration may also be other.

[0426] In some embodiments, the driving information of the terminal within a preset time period in the future can be predicted based on the driving information of the terminal, the signal quality parameter corresponding to at least one cell or beam of each PLMN within a preset time period in the future can be predicted based on the signal quality parameter corresponding to at least one cell or beam of each PLMN, and the network quality parameter corresponding to at least one cell or beam of each PLMN within a preset time period in the future can be predicted based on the network quality parameter corresponding to at least one cell or beam of each PLMN. The above-mentioned operations can be performed based on the driving information of the terminal within a preset time period in the future, the signal quality parameter corresponding to at least one cell or beam of each PLMN within a preset time period in the future, and the network quality parameter corresponding to at least one cell or beam of each PLMN within a preset time period in the future. Figure 2-Figure 5 The method described in any one of the embodiments.

[0427] In the embodiment of the present application, the above-mentioned operation is performed according to the driving information of the terminal within the future preset time period, the signal quality parameter corresponding to at least one cell or beam of each PLMN within the future preset time period, and the network quality parameter corresponding to at least one cell or beam of each PLMN within the future preset time period. Figure 2-Figure 5 The method shown in any one of the embodiments can determine the first identification information in advance, thereby realizing predictive switching, and then realizing seamless switching of the terminal between the currently used PLMN and the PLMN indicated by the first identification information, so that the user is unaware, ensuring the best network connection, and determining the safety and stability of autonomous driving.

[0428] In the present application, when a preset condition is met, S202, S304, S403, or S504 is executed.

[0429] In some embodiments, the preset conditions include one or more of the following:

[0430] The signal quality parameter corresponding to the serving cell or beam is less than or equal to the preset quality threshold;

[0431] The network performance parameters corresponding to the serving cell or beam deteriorate;

[0432] The type of scenario where the terminal is located changes;

[0433] The type of road on which the terminal is located changes; or,

[0434] The terminal is currently in autonomous driving mode.

[0435] In some embodiments, the network performance parameters corresponding to the terminal serving cell or beam deteriorate, including one or more of the following:

[0436] The delay corresponding to the serving cell or beam is greater than or equal to a preset delay threshold;

[0437] The bandwidth corresponding to the serving cell or beam is smaller than the bandwidth required when the terminal is in autonomous driving mode;

[0438] The packet loss rate corresponding to the serving cell or beam is greater than or equal to a preset packet loss rate threshold; or,

[0439] The bit error rate corresponding to the serving cell or beam is greater than or equal to the preset bit error rate threshold.

[0440] In an embodiment of the present application, when the preset conditions are met, executing the network switching method provided in the embodiment of the present application can prevent the terminal from frequently switching cells or beams, which helps to save energy consumption of the terminal.

[0441] In some embodiments, the AI models in Example A1, Example B1, and Example C1 are obtained by training a supervised learning model, such as a support vector machine (SVM).

[0442] The following, combined Figure 6 The embodiment illustrates the process of training a supervised learning model to obtain an AI model.

[0443] Figure 6 Schematic diagram of the process of obtaining the AI model provided in the embodiment of this application Figure 1 .like Figure 6 As shown, the method includes:

[0444] S601: Acquire historical feature data.

[0445] In some embodiments, the historical feature data includes multiple sets of sample data.

[0446] Exemplarily, each set of sample data includes driving information of the terminal, identification information of a cell or beam of a PLMN, network quality parameters corresponding to the cell or beam, and signal quality parameters corresponding to the cell or beam.

[0447] Exemplarily, the driving information of the terminal includes: the location information of the terminal, the driving speed of the terminal, the driving direction of the terminal, the type of road where the terminal is located, the traffic conditions of the terminal, and the weather type of the scene where the terminal is located.

[0448] Exemplarily, the signal quality parameter corresponding to the cell or beam includes: RSRP corresponding to the cell or beam.

[0449] Exemplarily, the network quality parameters corresponding to the cell or beam include: the bandwidth corresponding to the cell or beam, the delay corresponding to the cell or beam, and the packet loss rate corresponding to the cell or beam.

[0450] S602: Use historical feature data to pre-train the SVM to obtain an initial model, and store the initial model.

[0451] In some embodiments, the historical feature data may be stored in a data structure, such as a CSV file, a database, or an in-memory data structure.

[0452] In some embodiments, the label score corresponding to each group of sample data in the historical feature data is determined, and the SVM is pre-trained based on each group of sample data and the label score corresponding to each group of sample data to obtain an initial model.

[0453] In some embodiments, determining a label score corresponding to a group of sample data includes: processing the group of sample data through the decision function of SVM to obtain a decision result value, and processing the decision result value through the sigmoid function to obtain a label score corresponding to the group of sample data.

[0454] In some embodiments, determining a label score corresponding to a set of sample data includes: using a first preset rule to process the set of sample data to obtain a label score corresponding to the set of sample data.

[0455] Exemplarily, the first preset rule includes but is not limited to a weighted sum of the parameters in the set of sample data.

[0456] In some embodiments, the initial model is obtained when the number of pre-training operations on the SVM is equal to a preset number, or when the model parameters of the SVM converge.

[0457] In some embodiments, the historical feature data is preprocessed, the preprocessed feature data is standardized, the SVM is pre-trained using the standardized historical feature data to obtain an initial model, and the initial model is stored.

[0458] In some embodiments, preprocessing includes, for example, data cleaning, feature selection, etc.

[0459] Optionally, data cleaning includes one or more of processing missing values, removing outliers, and removing duplicate values.

[0460] Optionally, processing missing values includes deleting at least one set of sample data having an incorrect number of parameters among the multiple sets of sample data in the historical feature data. For example, if one set of sample data should include 11 parameters, but some sets of sample data only include 10 parameters, then these sets are deleted.

[0461] Optionally, removing outliers includes: deleting some groups of sample data that lose position information when the driving speed is 0.

[0462] Optionally, removing duplicate values includes: for some identical groups of sample data in the multiple groups of sample data, retaining only one group of sample data in the identical groups of sample data.

[0463] In some embodiments, feature selection includes selecting some parameters from each group of sample data. For example, a group of sample data includes identification information of a cell or beam of a PLMN, RSRP corresponding to the cell or beam, bandwidth corresponding to the cell or beam, delay corresponding to the cell or beam, packet loss rate corresponding to the cell or beam, location information of a terminal, driving speed of the terminal, driving direction of the terminal, type of road where the terminal is located, traffic conditions of the terminal, and weather type of a scene where the terminal is located. Some of the selected parameters include: identification information of a cell or beam of a PLMN, RSRP corresponding to the cell or beam, bandwidth corresponding to the cell or beam, delay corresponding to the cell or beam, packet loss rate corresponding to the cell or beam, location information of the terminal, driving speed of the terminal, type of road where the terminal is located, traffic conditions of the terminal, and weather type of a scene where the terminal is located.

[0464] In some embodiments, the preprocessed feature data is standardized, including: standardizing the RSRP corresponding to the cell or beam, the bandwidth corresponding to the cell or beam, the delay corresponding to the cell or beam, the packet loss rate corresponding to the cell or beam, the location information of the terminal, the driving speed of the terminal, the driving direction of the terminal, the type of road where the terminal is located, the traffic conditions of the terminal, and the weather type of the scene where the terminal is located.

[0465] Exemplarily, the standardization of the RSRP corresponding to a cell or beam includes: standardizing the RSRP corresponding to the cell or beam according to the standard deviation value and variance value corresponding to the RSRP, wherein the standard deviation value corresponding to the RSRP is the standard deviation value of all RSRPs in multiple groups of sample data, and the variance value corresponding to the RSRP is the variance value of all RSRPs in multiple groups of sample data.

[0466] It is worth noting that the standardization of the bandwidth corresponding to the cell or beam, the delay corresponding to the cell or beam, the packet loss rate corresponding to the cell or beam, and the driving speed of the terminal is similar to the standardization of the RSRP corresponding to the cell or beam, and will not be repeated here.

[0467] Exemplarily, the normalization of the terminal's driving direction includes: quantizing the terminal's driving direction into a corresponding value according to a second preset rule. The second preset rule is shown in Table 4 below.

[0468] Table 4

[0469]

[0470]

[0471] It is worth noting that the standardization of the type of road where the terminal is located, the traffic conditions of the terminal, and the weather type of the scene where the terminal is located is similar to the standardization of the terminal's driving direction, and will not be repeated here.

[0472] In some embodiments, the label score corresponding to each group of sample data in the standardized historical feature data is determined, and the SVM is pre-trained based on each group of sample data and the label score corresponding to each group of sample data to obtain an initial model.

[0473] In some embodiments, determining the label score corresponding to a group of sample data in the standardized historical feature data includes: processing the group of sample data through the decision function of SVM to obtain a decision result value, and processing the decision result value through the sigmoid function to obtain the label score corresponding to the group of sample data.

[0474] In some embodiments, determining a label score corresponding to a group of sample data in the standardized historical feature data includes: using a first preset rule to process the group of sample data to obtain a label score corresponding to the group of sample data.

[0475] In some embodiments, the initial model is obtained when the number of pre-training operations on the SVM is equal to a preset number, or when the model parameters of the SVM converge.

[0476] In some embodiments, the initial model may be determined as an AI model, and in this case, S603 to S605 do not need to be executed.

[0477] S603: Acquire real-time feature data.

[0478] In some embodiments, the real-time feature data is feature parameters obtained by the terminal during driving.

[0479] For example, the content types included in the real-time feature data and the historical feature data are not described in detail here.

[0480] S604: Use real-time feature data to train the initial model to obtain an AI model.

[0481] In some embodiments, the execution method of S602 is similar to the execution method of S604 and will not be repeated here.

[0482] S605: Update the initial model to an AI model.

[0483] In some embodiments, the AI model in Example A2, Example B2, and Example C2 is obtained by training a reinforcement learning model, such as a model based on the Q-learning algorithm.

[0484] The following, combined Figure 7 The embodiment illustrates the process of training a reinforcement learning model to obtain an AI model.

[0485] Figure 7 Schematic diagram of the process of obtaining the AI model provided in the embodiment of this application Figure 2 .like Figure 7 As shown, the method includes:

[0486] S701: Initialize model parameters of the reinforcement learning model.

[0487] Exemplarily, after initialization, the model parameters of the reinforcement learning model include: learning rate a=0.1, discount factor y=0.9, and exploration rate e=1.0→0.01.

[0488] S702: Load the reinforcement learning model and determine whether a Q table exists.

[0489] If so, execute S703.

[0490] Otherwise, execute S704.

[0491] S703: Read the Q table.

[0492] S704. Create a new Q table.

[0493] In some embodiments, the Q table in S703 and S704 includes multiple actions, multiple states, and a Q value corresponding to each pair of actions and states.

[0494] In some embodiments, the multiple actions are identification information of each cell or beam of each sample PLMN in a plurality of sample PLMNs, wherein the plurality of sample PLMNs include the at least one PLMN mentioned above.

[0495] In some embodiments, the multiple states may be states of each cell of each sample PLMN determined according to a method similar to the above examples A2, B2, or C2.

[0496] S705: Get the current status.

[0497] When S705 is executed for the first time, the current status is any of the following:

[0498] The terminal determines the status of a cell or beam based on the network quality parameter corresponding to the cell or beam;

[0499] The terminal determines the state of a cell or beam based on the signal quality parameter and network quality parameter corresponding to the cell or beam; or

[0500] The terminal determines the status of a cell based on the signal quality parameters and network quality parameters corresponding to a cell or beam, as well as the terminal's driving information.

[0501] S706 . Select an action (ie, identification information of a cell or beam) in the Q table according to the current state and probability ε through greedy selection (ε-greedy selection).

[0502] Alternatively, an action can be randomly selected in the Q-table with probability ε.

[0503] Alternatively, an action with the maximum Q value can be randomly selected from the Q table with probability (1-ε).

[0504] S707: Execute cell switching, switching from the cell corresponding to the current state to the cell indicated by the selected action.

[0505] S708. According to the cell indicated by the action, obtain a new status and reward.

[0506] S709: Determine a new Q value based on the new state and reward.

[0507] [Q(s,a)←Q(s,a)+α[r+γmax(Q(s',a'))-Q(s,a)]]

[0508] Where s represents the current state, s' represents the new state, and the new Q value is Q(s,a) on the left side of "←". Q(s,a) represents the Q value of performing action a in state s, max(Q(s',a')) represents the maximum Q value of all possible actions in state s', γ represents the reward, γ is the discount factor, and α is the learning rate.

[0509] S710: Update the Q value in the Q table according to the new Q value.

[0510] In some embodiments, the new Q value updates the Q value in the Q table, including: updating the Q(s, a) on the right side of “←” in S709 to the Q(s, a) on the left side of “←”.

[0511] S711, state migration, migration from the current state to the new state.

[0512] S712: Determine whether the number of state transitions is greater than 100.

[0513] If so, execute S713.

[0514] Otherwise, execute S707.

[0515] S713. Reduce ε.

[0516] S714. Record the average reward during 100 state transitions.

[0517] S715: Determine whether the number of training times is greater than 1000.

[0518] If so, execute S716.

[0519] Otherwise, execute S717.

[0520] S716, obtain the Q table and AI model.

[0521] S717: Update the new state to the current state, and continue to execute S705 based on the reduced ε.

[0522] Based on Example A1, the following takes the second sub-model as an example based on the Q-learning algorithm, combined with Figure 8 The embodiment illustrates the interaction process between the first sub-model and the second sub-model.

[0523] Figure 8 The following is a flow chart of the interaction process between the first sub-model and the second sub-model provided in the embodiment of the present application. Figure 8 As shown, the method includes:

[0524] S801. A terminal system obtains network quality parameters corresponding to at least one cell or beam of each PLMN from the network.

[0525] S802. The terminal system sends network quality parameters corresponding to at least one cell or beam of each PLMN and identification information of at least one cell or beam of each PLMN to the first submodel.

[0526] S803. The first sub-model sends the quality score corresponding to the identification information of at least one cell or beam of each PLMN to the system of the terminal.

[0527] S804. For each cell or beam in at least one cell or beam of each PLMN, the terminal system determines the status of the cell or beam according to the network quality parameter corresponding to the cell or beam.

[0528] S805. The terminal system sends at least one cell or beam of each PLMN and a quality score corresponding to identification information of at least one cell or beam of each PLMN to the second submodel.

[0529] S806. The second sub-model determines first identification information according to at least one cell or beam of each PLMN and a quality score corresponding to identification information of at least one cell or beam of each PLMN.

[0530] S807: The second sub-model sends the first identification information to the terminal system.

[0531] S808. When the cell or beam indicated by the first identification information is different from the serving cell or beam, the system of the terminal switches to the cell or beam indicated by the first identification information.

[0532] In some embodiments, the second sub-model may also update the Q table through S809 to S811.

[0533] S809. The terminal system obtains the throughput corresponding to the cell or beam indicated by the first identification information from the network.

[0534] S810. The terminal system calculates a reward according to the throughput corresponding to the cell or beam indicated by the first identification information and the quality score corresponding to the first identification information.

[0535] In some embodiments, reward r = throughput x 0.7 + quality score x 0.3.

[0536] S811: The terminal system sends a reward to the second sub-model, so that the second sub-model updates the Q table according to the reward.

[0537] Figure 9 A schematic diagram of the structure of the network switching device provided in the embodiment of the present application Figure 1 .like Figure 9 As shown, the network switching device 90 provided in this embodiment includes:

[0538] The transceiver module 901 receives a network quality parameter corresponding to at least one cell or beam of each PLMN in at least one PLMN;

[0539] The processing module 902 processes, through an artificial intelligence (AI) model, identification information of the at least one cell or beam of each PLMN and a network quality parameter corresponding to the at least one cell or beam of each PLMN to obtain first identification information, where the first identification information is one of the identification information of the at least one cell or beam of each PLMN;

[0540] The processing module 902 performs cell or beam switching when the cell or beam indicated by the first identification information is different from the serving cell or beam of the terminal.

[0541] The network switching device 90 provided in this embodiment can execute the method executed by the terminal in the above method embodiment. Its implementation principle and technical effects are similar and will not be described in detail in this embodiment.

[0542] In a possible implementation, the processing module 902 is specifically configured to:

[0543] Processing, by the first submodel in the AI model, identification information of the at least one cell or beam of each PLMN and a network quality parameter corresponding to the at least one cell or beam of each PLMN to obtain a quality score of the at least one cell or beam of each PLMN;

[0544] Through the second sub-model in the AI model, the network quality parameters corresponding to at least one cell or beam of each PLMN and the quality score of at least one cell or beam of each PLMN are processed to obtain the first identification information.

[0545] In a possible implementation, the processing module 902 is specifically configured to:

[0546] Obtaining a signal quality parameter corresponding to at least one cell or beam of each PLMN;

[0547] Through the AI model, the identification information of at least one cell or beam of each PLMN, the signal quality parameter corresponding to at least one cell or beam of each PLMN, and the network quality parameter corresponding to at least one cell or beam of each PLMN are processed to obtain the first identification information.

[0548] In a possible implementation, the processing module 902 is specifically configured to:

[0549] Processing, by the first submodel in the AI model, identification information of the at least one cell or beam of each PLMN, a signal quality parameter corresponding to the at least one cell or beam of each PLMN, and a network quality parameter corresponding to the at least one cell or beam of each PLMN to obtain a quality score of the at least one cell or beam of each PLMN;

[0550] Through the second sub-model in the AI model, the signal quality parameters corresponding to at least one cell or beam of each PLMN, the network quality parameters corresponding to at least one cell or beam of each PLMN, and the quality score of at least one cell or beam of each PLMN are processed to obtain the first identification information.

[0551] In a possible implementation, the processing module 902 is specifically configured to:

[0552] Acquiring driving information of the terminal;

[0553] Through the AI model, the driving information of the terminal, the identification information of at least one cell or beam of each PLMN, the signal quality parameter corresponding to at least one cell or beam of each PLMN, and the network quality parameter corresponding to at least one cell or beam of each PLMN are processed to obtain the first identification information.

[0554] In a possible implementation, the processing module 902 is specifically configured to:

[0555] Processing, by the first submodel in the AI model, the driving information of the terminal, the identification information of the at least one cell or beam of each PLMN, the signal quality parameter corresponding to the at least one cell or beam of each PLMN, and the network quality parameter corresponding to the at least one cell or beam of each PLMN to obtain a quality score of the at least one cell or beam of each PLMN;

[0556] The second sub-model in the AI model processes the driving information of the terminal, the signal quality parameters corresponding to at least one cell or beam of each PLMN, the network quality parameters corresponding to at least one cell or beam of each PLMN, and the quality score of at least one cell or beam of each PLMN to obtain the first identification information.

[0557] In a possible implementation, the travel information of the terminal is travel information of the terminal within a preset time period in the future;

[0558] The signal quality parameter corresponding to the at least one cell or beam of each PLMN is a signal quality parameter corresponding to the at least one cell or beam of each PLMN within the future preset time period;

[0559] The network quality parameter corresponding to the at least one cell or beam of each PLMN is the network quality parameter corresponding to the at least one cell or beam of each PLMN within the future preset time period.

[0560] In a possible implementation, the processing module 902 is specifically configured to:

[0561] switching from the serving cell to the cell indicated by the first identification information, wherein the serving cell and the cell indicated by the first identification information belong to the same PLMN, or the serving cell and the cell indicated by the first identification information belong to different PLMNs;

[0562] The processing module 902 is specifically used to: switch from the service beam to the beam indicated by the first identification information, wherein the PLMN to which the service beam and the beam indicated by the first identification information belong is the same, or the PLMN to which the service beam and the beam indicated by the first identification information belong is different.

[0563] In a possible implementation, the at least one PLMN is a PLMN that the terminal has already accessed.

[0564] In a possible implementation, the transceiver module is further configured to:

[0565] Send a request message to the network device corresponding to at least one cell or beam of each PLMN, wherein the request message is used to request to obtain the network quality parameter corresponding to the cell or beam.

[0566] In a possible implementation manner, the network quality parameters corresponding to the cell or beam include one or more of the following:

[0567] Network performance parameters corresponding to the cell or beam;

[0568] The quality of service parameter corresponding to the cell or beam; or

[0569] The network status parameters corresponding to the cell or beam.

[0570] In a possible implementation, the network performance parameter includes one or more of the following: bandwidth, delay, jitter, packet loss rate, throughput, or bit error rate.

[0571] In a possible implementation manner, the quality of service parameters include one or more of the following: bandwidth guarantee, maximum delay, maximum jitter, maximum packet loss rate, or priority.

[0572] In a possible implementation, the network status parameter includes one or more of the following: network load, connection establishment time, or service availability.

[0573] In a possible implementation manner, the identification information of the cell or beam is pre-configured in the terminal; or,

[0574] The identification information of the cell or beam is carried in a system message sent by the network device corresponding to the cell or beam to the terminal.

[0575] In a possible implementation manner, the identification information of the cell or beam is pre-configured in the terminal, including one or more of the following:

[0576] The identification information of the cell or beam is pre-configured in an extensible markup language XML file of the terminal; or,

[0577] The identification information of the cell or beam is pre-configured in the subscriber identity module SIM of the terminal.

[0578] In a possible implementation manner, the identification information of the cell includes an identification of a PLMN to which the cell belongs and an identification of the cell;

[0579] The identification information of the beam includes an identification of the PLMN to which the beam belongs and beam information of the beam.

[0580] In a possible implementation manner, the signal quality parameter includes one or more of the following:

[0581] Reference signal received power RSRP;

[0582] Reference signal reception quality RSRQ;

[0583] Received Signal Strength Indicator RSSI; or

[0584] Signal to Interference and Noise Ratio SINR.

[0585] In a possible implementation, the driving information of the terminal includes one or more of the following:

[0586] The weather type of the scene where the terminal is located;

[0587] location information of the terminal;

[0588] The type of scenario in which the terminal is located;

[0589] the type of road on which the terminal is located;

[0590] the travel speed of the terminal;

[0591] the direction of travel of the terminal; or

[0592] The traffic conditions of the terminal.

[0593] In a possible implementation, the processing module 902 is specifically configured to:

[0594] When a preset condition is met, processing, by the AI model, identification information of at least one cell or beam of each PLMN and a network quality parameter corresponding to at least one cell or beam of each PLMN to obtain the first identification information;

[0595] The preset conditions include one or more of the following:

[0596] The signal quality parameter corresponding to the serving cell or beam is less than or equal to a preset quality threshold;

[0597] The network performance parameters corresponding to the serving cell or beam deteriorate;

[0598] The type of the scene in which the terminal is located changes;

[0599] The type of the road where the terminal is located changes; or

[0600] The current mode of the terminal is the automatic driving mode.

[0601] The network switching device 90 provided in this embodiment can execute the method executed by the terminal in the above method embodiment. Its implementation principle and technical effects are similar and will not be described in detail in this embodiment.

[0602] Figure 10 A schematic diagram of the structure of the network switching device provided in the embodiment of the present application Figure 2 .like Figure 10 As shown, the network switching device 100 provided in this embodiment includes:

[0603] The transceiver module 1001 is used to send the network quality parameters corresponding to the cell or beam to the terminal. The network quality parameters corresponding to the cell or beam are used by the AI model of the terminal to process to obtain first identification information. The first identification information is used by the terminal to perform cell or beam switching when the cell or beam indicated by the first identification information is different from the serving cell or beam of the terminal.

[0604] The network switching device 100 provided in this embodiment can execute the method executed by the network device in the above method embodiment. Its implementation principle and technical effects are similar and will not be described in detail in this embodiment.

[0605] In a possible implementation manner, the PLMN is a PLMN that the terminal has already accessed.

[0606] In a possible implementation, the transceiver module 1001 is further configured to:

[0607] Receive a request message sent by the terminal, wherein the request message is used to request to obtain the network quality parameters corresponding to the cell or beam.

[0608] In a possible implementation manner, the network quality parameters corresponding to the cell or beam include one or more of the following:

[0609] Network performance parameters corresponding to the cell or beam;

[0610] The quality of service parameter corresponding to the cell or beam; or

[0611] The network status parameters corresponding to the cell or beam.

[0612] In a possible implementation, the network performance parameter includes one or more of the following: bandwidth, delay, jitter, packet loss rate, throughput, or bit error rate.

[0613] In a possible implementation manner, the quality of service parameters include one or more of the following: bandwidth guarantee, maximum delay, maximum jitter, maximum packet loss rate, or priority.

[0614] In a possible implementation, the network status parameter includes one or more of the following: network load, connection establishment time, or service availability.

[0615] The network switching device 100 provided in this embodiment can execute the method executed by the network device in the above method embodiment. Its implementation principle and technical effects are similar and will not be described in detail in this embodiment.

[0616] Figure 11 This is a schematic diagram of the structure of the terminal provided in the embodiment of the present application. Figure 11 As shown, the terminal 110 provided in this embodiment includes: at least one processor 1101 and a memory 1102. Optionally, the device 110 further includes a communication component 1103. The processor 1101, the memory 1102, and the communication component 1103 are connected via a bus 1104.

[0617] During the specific implementation process, at least one processor 1101 executes the computer-executable instructions stored in the memory 1102, so that the at least one processor 1101 performs the above method.

[0618] The specific implementation process of the processor 1101 can refer to the method executed by the terminal in the above method embodiment. The implementation principle and technical effects are similar and will not be repeated here in this embodiment.

[0619] Figure 12 This is a schematic diagram of the structure of the network device provided in the embodiment of the present application. Figure 12As shown, the network device 120 provided in this embodiment includes: at least one processor 1201 and a memory 1202. Optionally, the device 120 further includes a communication component 1203. The processor 1201, the memory 1202, and the communication component 1203 are connected via a bus 1204.

[0620] During the specific implementation process, at least one processor 1201 executes the computer-executable instructions stored in the memory 1202, so that the at least one processor 1201 performs the above method.

[0621] The specific implementation process of the processor 1201 can refer to the method executed by the network device in the above method embodiment. The implementation principle and technical effects are similar and will not be repeated here in this embodiment.

[0622] In the above embodiments, it should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the present invention may be directly implemented by a hardware processor or implemented by a combination of hardware and software modules in the processor.

[0623] The memory may include a high-speed memory (Random Access Memory, RAM), and may also include a non-volatile memory (NVM), such as at least one disk memory.

[0624] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus. Buses can be classified into address buses, data buses, and control buses. For ease of illustration, the buses in the drawings of this application are not limited to just one bus or just one type of bus.

[0625] The present application also provides a communication system, comprising the above-mentioned terminal and the above-mentioned at least one network device.

[0626] The present application also provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0627] The present application also provides a computer-readable storage medium, in which computer-executable instructions are stored. When a processor executes the computer-executable instructions, the above method is implemented.

[0628] The present application also provides a computer program, which implements the above method when executed by a processor.

[0629] The above-mentioned readable storage medium can be implemented by any type of volatile or non-volatile memory device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk or optical disk. The readable storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0630] An exemplary readable storage medium is coupled to a processor so that the processor can read information from the readable storage medium and write information to the readable storage medium. Of course, the readable storage medium can also be an integral part of the processor. The processor and the readable storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the readable storage medium can also exist in the device as discrete components.

[0631] The division of units is merely a logical functional division; actual implementations may employ alternative divisions, such as combining or integrating multiple units or components into another system, or omitting or disabling certain features. Furthermore, any direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection between devices or units, either through an interface, electrical, mechanical, or other means.

[0632] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0633] In addition, each functional unit in each embodiment of the present invention 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.

[0634] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or the portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or PLMN, etc.) to execute all or part of the steps of the various embodiments of the method of the present invention. The aforementioned storage medium includes various media that can store program code, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0635] Those skilled in the art will appreciate that all or part of the steps in the above-described method embodiments can be implemented by hardware associated with program instructions. The aforementioned program can be stored in a computer-readable storage medium. When executed, the program performs the steps of the above-described method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as ROM, RAM, magnetic disks, or optical disks.

[0636] Finally, it should be noted that other embodiments of the present invention will readily occur to those skilled in the art after considering the specification and practicing the invention disclosed herein. The present invention is intended to cover any variations, uses, or adaptations of the present invention that follow the general principles of the present invention and include common knowledge or customary techniques in the art not disclosed herein. The present invention is not limited to the precise structure described above and illustrated in the accompanying drawings, and various modifications and variations may be made without departing from the scope thereof. The scope of the present invention is limited solely by the appended claims.

Claims

1. A network switching method, characterized in that: Applied to a terminal, the method includes: receiving a network quality parameter corresponding to at least one cell or beam of each PLMN in at least one PLMN; Processing, by an artificial intelligence (AI) model, identification information of at least one cell or beam of each PLMN and a network quality parameter corresponding to the at least one cell or beam of each PLMN to obtain first identification information, where the first identification information is one of the identification information of the at least one cell or beam of each PLMN; When the cell or beam indicated by the first identification information is different from the serving cell or beam of the terminal, cell or beam switching is performed.

2. The method according to claim 1, characterized in that The processing, by the artificial intelligence (AI) model, of identification information of at least one cell or beam of each PLMN and a network quality parameter corresponding to at least one cell or beam of each PLMN to obtain first identification information includes: Processing, by the first submodel in the AI model, identification information of the at least one cell or beam of each PLMN and a network quality parameter corresponding to the at least one cell or beam of each PLMN to obtain a quality score of the at least one cell or beam of each PLMN; Through the second sub-model in the AI model, the network quality parameters corresponding to at least one cell or beam of each PLMN and the quality score of at least one cell or beam of each PLMN are processed to obtain the first identification information.

3. The method according to claim 1, characterized in that The processing, by the artificial intelligence (AI) model, of identification information of at least one cell or beam of each PLMN and a network quality parameter corresponding to at least one cell or beam of each PLMN to obtain first identification information includes: Obtaining a signal quality parameter corresponding to at least one cell or beam of each PLMN; Through the AI model, the identification information of at least one cell or beam of each PLMN, the signal quality parameter corresponding to at least one cell or beam of each PLMN, and the network quality parameter corresponding to at least one cell or beam of each PLMN are processed to obtain the first identification information.

4. The method according to claim 3, characterized in that The processing, by the AI model, of identification information of at least one cell or beam of each PLMN, a signal quality parameter corresponding to at least one cell or beam of each PLMN, and a network quality parameter corresponding to at least one cell or beam of each PLMN to obtain the first identification information includes: Processing, by the first submodel in the AI model, identification information of the at least one cell or beam of each PLMN, a signal quality parameter corresponding to the at least one cell or beam of each PLMN, and a network quality parameter corresponding to the at least one cell or beam of each PLMN to obtain a quality score of the at least one cell or beam of each PLMN; Through the second sub-model in the AI model, the signal quality parameters corresponding to at least one cell or beam of each PLMN, the network quality parameters corresponding to at least one cell or beam of each PLMN, and the quality score of at least one cell or beam of each PLMN are processed to obtain the first identification information.

5. The method according to claim 3, characterized in that The processing, by the AI model, of identification information of at least one cell or beam of each PLMN, a signal quality parameter corresponding to at least one cell or beam of each PLMN, and a network quality parameter corresponding to at least one cell or beam of each PLMN to obtain the first identification information includes: Acquiring driving information of the terminal; Through the AI model, the driving information of the terminal, the identification information of at least one cell or beam of each PLMN, the signal quality parameter corresponding to at least one cell or beam of each PLMN, and the network quality parameter corresponding to at least one cell or beam of each PLMN are processed to obtain the first identification information.

6. The method according to claim 5, characterized in that The processing, by the AI model, of the driving information of the terminal, the identification information of the at least one cell or beam of each PLMN, the signal quality parameter corresponding to the at least one cell or beam of each PLMN, and the network quality parameter corresponding to the at least one cell or beam of each PLMN to obtain the first identification information includes: Processing, by the first submodel in the AI model, the driving information of the terminal, the identification information of the at least one cell or beam of each PLMN, the signal quality parameter corresponding to the at least one cell or beam of each PLMN, and the network quality parameter corresponding to the at least one cell or beam of each PLMN to obtain a quality score of the at least one cell or beam of each PLMN; The second sub-model in the AI model processes the driving information of the terminal, the signal quality parameters corresponding to at least one cell or beam of each PLMN, the network quality parameters corresponding to at least one cell or beam of each PLMN, and the quality score of at least one cell or beam of each PLMN to obtain the first identification information.

7. The method according to claim 5 or 6, characterized in that The terminal's driving information is the terminal's driving information within a preset time period in the future; The signal quality parameter corresponding to the at least one cell or beam of each PLMN is a signal quality parameter corresponding to the at least one cell or beam of each PLMN within the future preset time period; The network quality parameter corresponding to the at least one cell or beam of each PLMN is the network quality parameter corresponding to the at least one cell or beam of each PLMN within the future preset time period.

8. The method according to any one of claims 1 to 7, characterized in that Perform cell handover, including: switching from the serving cell to the cell indicated by the first identification information, wherein the serving cell and the cell indicated by the first identification information belong to the same PLMN, or the serving cell and the cell indicated by the first identification information belong to different PLMNs; Perform beam switching, including: Switch from the serving beam to the beam indicated by the first identification information, wherein the serving beam and the beam indicated by the first identification information belong to the same PLMN, or the serving beam and the beam indicated by the first identification information belong to different PLMNs.

9. The method according to any one of claims 1 to 8, characterized in that The at least one PLMN is a PLMN that the terminal has accessed.

10. The method according to any one of claims 1 to 9, characterized in that The method further comprises: Send a request message to the network device corresponding to at least one cell or beam of each PLMN, wherein the request message is used to request to obtain the network quality parameter corresponding to the cell or beam.

11. The method according to any one of claims 1 to 10, characterized in that The network quality parameters corresponding to the cell or beam include one or more of the following: Network performance parameters corresponding to the cell or beam; The quality of service parameter corresponding to the cell or beam; or The network status parameters corresponding to the cell or beam.

12. The method according to claim 11, characterized in that The network performance parameters include one or more of the following: bandwidth, delay, jitter, packet loss rate, throughput, or bit error rate.

13. The method according to claim 11, characterized in that The quality of service parameters include one or more of the following: bandwidth guarantee, maximum delay, maximum jitter, maximum packet loss rate, or priority.

14. The method according to claim 11, characterized in that The network status parameters include one or more of the following: network load, connection establishment time, or service availability.

15. The method according to any one of claims 1 to 14, characterized in that The identification information of the cell or beam is pre-configured in the terminal; or, The identification information of the cell or beam is carried in a system message sent by the network device corresponding to the cell or beam to the terminal.

16. The method according to claim 15, characterized in that The identification information of the cell or beam is pre-configured in the terminal, including one or more of the following: The identification information of the cell or beam is pre-configured in an extensible markup language XML file of the terminal; or, The identification information of the cell or beam is pre-configured in the subscriber identity module SIM of the terminal.

17. The method according to any one of claims 1 to 16, characterized in that The identification information of the cell includes an identification of the PLMN to which the cell belongs and an identification of the cell; The identification information of the beam includes an identification of the PLMN to which the beam belongs and beam information of the beam.

18. The method according to any one of claims 3 to 7, characterized in that: The signal quality parameters include one or more of the following: Reference signal received power RSRP; Reference signal reception quality RSRQ; Received Signal Strength Indicator RSSI; or Signal to Interference and Noise Ratio SINR.

19. The method according to any one of claims 5 to 7, characterized in that: The terminal's driving information includes one or more of the following: The weather type of the scene where the terminal is located; location information of the terminal; The type of scenario in which the terminal is located; the type of road on which the terminal is located; the travel speed of the terminal; the direction of travel of the terminal; or The traffic conditions of the terminal.

20. The method according to any one of claims 1 to 19, characterized in that The processing, by the artificial intelligence (AI) model, of identification information of at least one cell or beam of each PLMN and a network quality parameter corresponding to at least one cell or beam of each PLMN to obtain first identification information includes: When a preset condition is met, processing, by the AI model, identification information of at least one cell or beam of each PLMN and a network quality parameter corresponding to at least one cell or beam of each PLMN to obtain the first identification information; The preset conditions include one or more of the following: The signal quality parameter corresponding to the serving cell or beam is less than or equal to a preset quality threshold; The network performance parameters corresponding to the serving cell or beam deteriorate; The type of the scene in which the terminal is located changes; The type of the road where the terminal is located changes; or The current mode of the terminal is the automatic driving mode.

21. A network switching method, characterized in that: Applied to a network device corresponding to a cell or beam of a PLMN, the method includes: The network quality parameters corresponding to the cell or beam are sent to the terminal, and the network quality parameters corresponding to the cell or beam are used for processing by the AI model of the terminal to obtain first identification information. The first identification information is used by the terminal to perform cell or beam switching when the cell or beam indicated by the first identification information is different from the serving cell or beam of the terminal.

22. The method according to claim 21, characterized in that The PLMN is the PLMN that the terminal has accessed.

23. The method according to claim 21, characterized in that The method further comprises: Receive a request message sent by the terminal, wherein the request message is used to request to obtain the network quality parameters corresponding to the cell or beam.

24. The method according to any one of claims 21 to 23, characterized in that The network quality parameters corresponding to the cell or beam include one or more of the following: Network performance parameters corresponding to the cell or beam; The quality of service parameter corresponding to the cell or beam; or The network status parameters corresponding to the cell or beam.

25. The method according to claim 24, characterized in that The network performance parameters include one or more of the following: bandwidth, delay, jitter, packet loss rate, throughput, or bit error rate.

26. The method according to claim 24, characterized in that The quality of service parameters include one or more of the following: bandwidth guarantee, maximum delay, maximum jitter, maximum packet loss rate, or priority.

27. The method according to claim 24, characterized in that The network status parameters include one or more of the following: network load, connection establishment time, or service availability.

28. A network switching device, characterized in that: include: a transceiver module, configured to receive network quality parameters corresponding to at least one cell or beam of each PLMN in at least one PLMN; a processing module, configured to process, through an artificial intelligence (AI) model, identification information of at least one cell or beam of each PLMN and a network quality parameter corresponding to at least one cell or beam of each PLMN to obtain first identification information, where the first identification information is one of the identification information of at least one cell or beam of each PLMN; The processing module is also used to perform cell or beam switching when the cell or beam indicated by the first identification information is different from the serving cell or beam of the terminal.

29. A network switching device, characterized in that: include: A transceiver module is used to send network quality parameters corresponding to a cell or beam to a terminal. The network quality parameters corresponding to the cell or beam are used for processing by the AI model of the terminal to obtain first identification information. The first identification information is used by the terminal to perform cell or beam switching when the cell or beam indicated by the first identification information is different from the serving cell or beam of the terminal.

30. A terminal, characterized in that: include: memory and processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 1 to 20.

31. A network device, characterized in that: include: memory and processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory, so that the processor performs the method according to any one of claims 21 to 27.

32. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer-executable instructions, which, when executed by a processor, are used to implement the method according to any one of claims 1 to 20 or the method according to any one of claims 21 to 27.

33. A computer program product, characterized in that The method comprises a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 20 or the method according to any one of claims 21 to 27.

Images