Communication method, apparatus, communication device, communication system, and storage medium

Abstract

The present invention provides a communication method, an apparatus, a communication device, a communication system, and a storage medium. The method comprises: in response to a terminal determining that no available model is possessed, triggering a network device to send model-related information, wherein the model-related information is used for a terminal-side model. In the present invention, when determining that no locally available model is possessed, a terminal may trigger a network device to deliver model-related information; and then the terminal, on the basis of the model-related information, acquires a locally available model, so that the terminal can use the model to perform prediction and inference, improving the performance of a system.

Description

Communication methods and devices, communication equipment, communication systems, storage media Technical Field

[0001] This disclosure relates to the field of communication technology, and in particular to communication methods and apparatus, communication equipment, communication systems, and storage media. Background Technology

[0002] With the continuous development of AI (Artificial Intelligence) or machine learning technologies, the application areas of AI technology (such as image recognition, speech processing, and natural language processing) are becoming increasingly widespread. AI technology is not only widely used in education, transportation, home, healthcare, retail, and security, bringing convenience to people's lives, but also promoting industrial upgrading in various sectors. AI technology was also introduced in The 3rd Generation Partnership Project Release 18 (3GPP R18). Summary of the Invention

[0003] This disclosure proposes communication methods and apparatus, communication equipment, communication systems, and storage media.

[0004] According to a first aspect of the embodiments of this disclosure, a communication method is provided, executed by a terminal, the method comprising:

[0005] In response to the terminal determining that no model is available, the network device is triggered to send model-related information, wherein the model-related information is used for terminal-side models.

[0006] According to a second aspect of the embodiments of this disclosure, a communication method is provided, performed by a network device, the method comprising:

[0007] The receiving terminal sends a first indication message, which indicates that the terminal does not have a usable model.

[0008] Send model-related information to the terminal.

[0009] According to a third aspect of the embodiments of this disclosure, a communication method is provided, executed by a server, the method comprising:

[0010] Send the first information of the terminal-side model, which is used by the terminal to determine whether a usable model is available.

[0011] According to a fourth aspect of the present disclosure, a communication method is provided for a communication system, the communication system including a terminal, a network device, and a server, the method comprising:

[0012] The server sends first information about the terminal-side model, which is used by the terminal to determine whether a usable model is available.

[0013] When the terminal determines that it does not have a usable model based on the first information, it sends a first indication information to the network device. The first indication information is used to indicate that the terminal does not have a usable model.

[0014] The network device sends model-related information to the terminal.

[0015] According to a fifth aspect of the embodiments of this disclosure, a terminal is provided, comprising:

[0016] The transceiver module is used to trigger the network device to send model-related information when it is determined that no model is available, wherein the model-related information is used for the terminal-side model.

[0017] According to a sixth aspect of the embodiments of this disclosure, a network device is provided, comprising:

[0018] The transceiver module is used to receive first indication information sent by the terminal, the first indication information being used to indicate that the terminal does not have a usable model; and to send model-related information to the terminal.

[0019] According to a seventh aspect of the embodiments of this disclosure, a server is provided, comprising:

[0020] The transceiver module is used to send the first information of the terminal-side model, which is used by the terminal to determine whether a usable model is available.

[0021] According to an eighth aspect of the embodiments of this disclosure, a communication device is provided, comprising:

[0022] One or more processors;

[0023] The processor is configured to invoke instructions to cause the communication device to execute any of the communication methods described in the first to third aspects.

[0024] According to a ninth aspect of the present disclosure, a communication system is provided, characterized in that it includes a terminal, a network device, and a server, wherein the terminal is configured to implement the communication method described in the first aspect, the network device is configured to implement the communication method described in the second aspect, and the server is configured to implement the communication method described in the third aspect.

[0025] According to a tenth aspect of the present disclosure, a storage medium is provided that stores instructions, characterized in that, when the instructions are executed on a communication device, the communication device causes the communication device to perform a communication method as described in any one of the first to third aspects. Attached Figure Description

[0026] The above and / or additional aspects and advantages of this disclosure will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, in which:

[0027] Figure 1A is a schematic diagram of the architecture of some communication systems provided in the embodiments of this disclosure;

[0028] Figures 2A-2E are schematic flowcharts of a communication method provided in another embodiment of this disclosure;

[0029] Figure 3 is a flowchart illustrating a communication method provided in another embodiment of this disclosure;

[0030] Figure 4 is a flowchart illustrating a communication method provided in another embodiment of this disclosure;

[0031] Figure 5 is a flowchart illustrating a communication method provided in another embodiment of this disclosure;

[0032] Figure 6 is a flowchart illustrating a communication method provided in another embodiment of this disclosure;

[0033] Figure 7A is a schematic diagram of the structure of a terminal provided in an embodiment of this disclosure;

[0034] Figure 7B is a schematic diagram of the structure of a network device provided in an embodiment of this disclosure;

[0035] Figure 7C is a schematic diagram of the structure of a server provided in an embodiment of this disclosure;

[0036] Figure 8A is a schematic diagram of the structure of a communication device provided in an embodiment of this disclosure;

[0037] Figure 8B is a schematic diagram of the structure of a chip provided in an embodiment of this disclosure. Detailed Implementation

[0038] This disclosure provides embodiments of communication methods and apparatus, communication devices, communication systems, and storage media.

[0039] In a first aspect, embodiments of this disclosure provide a communication method executed by a terminal, the method comprising:

[0040] In response to the terminal determining that no model is available, the network device is triggered to send model-related information, wherein the model-related information is used for terminal-side models.

[0041] In the above embodiments, when the terminal determines that there is no available model locally, it can trigger the network device to send model-related information. Then, based on the model-related information, the terminal can obtain a locally available model, enabling the terminal to use the model for prediction and inference, thereby improving the system performance.

[0042] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0043] Based on the first information of the terminal-side model, determine whether a usable model is available.

[0044] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0045] The terminal-side model first information is received from the server; wherein, receiving the first information occurs before the network device is triggered to send model-related information.

[0046] In conjunction with some embodiments of the first aspect, in some embodiments, the first information includes at least one of the following information items:

[0047] First network ID;

[0048] First Community Identifier ID;

[0049] First geographical location area;

[0050] First model ID;

[0051] First version ID;

[0052] First network-side condition ID.

[0053] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0054] If any information item included in the first information fails to meet the condition, it is determined that the terminal does not have a usable model;

[0055] In response to the condition being met by the first information, it is determined that the terminal has a usable model.

[0056] In the above embodiments, the first information includes information items of multiple dimensions. The terminal can improve the accuracy of the terminal in judging whether a usable model is available by using information items of multiple dimensions.

[0057] In conjunction with some embodiments of the first aspect, determining that the first information condition is satisfied includes at least one of the following operations:

[0058] Determine the second network ID corresponding to the cell currently accessed by the terminal; if the second network ID is the same as the first network ID, determine that the condition is met.

[0059] Determine the second cell ID of the cell currently accessed by the terminal; if the second cell ID is the same as the first cell ID, determine that the condition is met.

[0060] Determine the geographical location of the terminal; if the geographical location is within the first geographical location area, determine that the condition is met.

[0061] Receive the second model ID sent by the network device; if the second model ID is the same as the first model ID, determine that the condition is met.

[0062] Receive the second version ID sent by the network device; if the second version ID is the same as the first version ID, determine that the condition is met.

[0063] Receive the second network-side condition ID sent by the network device. If the second network-side condition ID is consistent with the first network-side condition ID, determine that the condition is met.

[0064] In the above embodiments, the terminal can receive the first information of the terminal-side model sent by the server. The first information includes information items of multiple dimensions. The terminal can make judgments through the information items of multiple dimensions, which can improve the accuracy of the judgments. Moreover, the network device will only be triggered to send the model-related information when it is determined that model-related information is needed, which can save the signaling resources of the network device.

[0065] In conjunction with some embodiments of the first aspect, in some embodiments, triggering the network device to send the model-related information includes:

[0066] Send a first instruction message to the network device.

[0067] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0068] Receive the model-related information sent by the network device.

[0069] In the above embodiments, the terminal triggers the network device to send model-related information through the first indication information, which eliminates the need for the network device to send the information periodically, thus saving the signaling resources of the network device.

[0070] In conjunction with some embodiments of the first aspect, in some embodiments, the model-related information includes at least one of the following:

[0071] Training dataset;

[0072] Model architecture;

[0073] Model parameters.

[0074] In conjunction with some embodiments of the first aspect, in some embodiments, the first indication information is used to indicate the information content that the terminal needs to request from the network device, the information content including at least one of the following:

[0075] Training dataset;

[0076] Model architecture;

[0077] Model parameters.

[0078] In the above embodiments, the terminal notifies the network device of the required information content through the first indication information, so that the network device can send information in a targeted manner. This not only saves the signaling resources of the network device, but also enables the terminal to receive the required information content, which is beneficial to the updating or generation of the terminal-side model.

[0079] In conjunction with some embodiments of the first aspect, in some embodiments, before sending the first indication information to the network device, the method further includes:

[0080] Send a third indication message to the server, the third indication message being used to indicate that the terminal does not have a usable model;

[0081] The terminal receives a second instruction message sent by the server, which indicates the information content that the terminal needs to request from the network device.

[0082] In the above embodiments, the terminal can determine the required information content according to the second instruction information, and then notify the network device of the required information content through the first instruction information, so that the network device can send information in a targeted manner. This not only saves the signaling resources of the network device, but also enables the terminal to receive the required information content, which is beneficial to the updating or generation of the terminal-side model.

[0083] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes:

[0084] Send the model-related information to the server;

[0085] Receive the terminal-side model sent by the server.

[0086] In the above embodiments, the terminal can send model-related information to the server, enabling the server to train and update the terminal-side model. This eliminates the need for local training or updates on the terminal, avoiding the consumption of significant terminal computing resources. Furthermore, the server's strong computing power improves the training and update speed of the terminal-side model. For terminals with limited computing resources, the server's resources and capabilities can be leveraged to update the terminal-side model, allowing the terminal to use the model for prediction and inference, thus improving system performance.

[0087] Secondly, embodiments of this disclosure provide a communication method executed by a network device, the method comprising:

[0088] The receiving terminal sends a first indication message, which indicates that the terminal does not have a usable model.

[0089] Based on the first indication information, model-related information is sent to the terminal, and the model-related information is used for the terminal-side model.

[0090] In conjunction with some embodiments of the second aspect, in some embodiments, the model-related information includes at least one of the following:

[0091] Training dataset;

[0092] Model architecture;

[0093] Model parameters.

[0094] In conjunction with some embodiments of the second aspect, in some embodiments, the first indication information is used to indicate the information content that the terminal needs to request from the network device, the information content including at least one of the following:

[0095] Training dataset;

[0096] Model architecture;

[0097] Model parameters.

[0098] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes:

[0099] Send to the terminal at least one of the second ID, the second version ID, and the second network-side condition ID corresponding to the network-side model.

[0100] Thirdly, embodiments of this disclosure provide a communication method executed by a server, the method comprising:

[0101] The terminal sends first information about the terminal-side model to the terminal. The first information is used by the terminal to determine whether a usable model is available. The model-related information is used for the terminal-side model.

[0102] In conjunction with some embodiments of the third aspect, in some embodiments, the first information includes at least one of the following:

[0103] First network ID;

[0104] First Community ID;

[0105] First geographical location area;

[0106] First model ID;

[0107] First version ID;

[0108] First network-side condition ID.

[0109] In conjunction with some embodiments of the third aspect, in some embodiments, the method further includes:

[0110] Receive third indication information sent by the terminal, the third indication information being used to indicate that the terminal does not have a usable model;

[0111] Send a second instruction to the terminal, the second instruction being used to instruct the terminal to request the information content from the network device.

[0112] In conjunction with some embodiments of the third aspect, in some embodiments, the information content includes at least one of the following:

[0113] Training dataset;

[0114] Model architecture;

[0115] Model parameters.

[0116] In conjunction with some embodiments of the third aspect, in some embodiments, the method further includes:

[0117] Receive the model-related information sent by the terminal;

[0118] The terminal-side model is updated based on the model-related information.

[0119] Send the terminal-side model to the terminal.

[0120] Fourthly, embodiments of this disclosure provide a communication method for a communication system, the communication system including a terminal, a network device, and a server, the method comprising:

[0121] The server sends the terminal-side model's first information to the terminal, which is used by the terminal to determine whether a usable model is available.

[0122] When the terminal determines that there is no available model, it sends a first indication message to the network device, the first indication message being used to indicate that the terminal does not have an available model;

[0123] The network device receives the first indication information sent by the terminal;

[0124] Based on the first indication information, the network device sends model-related information to the terminal, and the model-related information is used for the terminal-side model.

[0125] Fifthly, embodiments of this disclosure provide a terminal, including:

[0126] The transceiver module is used to send a first indication message to the network device when it is determined that no available model is available. The first indication message is used to indicate that the terminal does not have an available model, and the model-related information is used for terminal-side models.

[0127] In conjunction with some embodiments of the fifth aspect, in some embodiments, the processing module is used to determine whether a usable model is available based on the first information of the terminal-side model.

[0128] In conjunction with some embodiments of the fifth aspect, in some embodiments, the transceiver module is further configured to receive first information of the terminal-side model sent by the server.

[0129] In conjunction with some embodiments of the fifth aspect, in some embodiments, the first information includes at least one of the following:

[0130] First network identifier ID;

[0131] First Community ID;

[0132] First geographical location area;

[0133] First model ID;

[0134] First version ID;

[0135] First network-side condition ID.

[0136] In conjunction with some embodiments of the fifth aspect, in some embodiments, the processing module is further configured to:

[0137] If any of the information included in the first information fails to meet the condition, it is determined that the terminal does not have a usable model;

[0138] In response to the condition being met by the first information, it is determined that the terminal has a usable model.

[0139] In conjunction with some embodiments of the fifth aspect, in some embodiments, the processing module is further configured to perform at least one of the following operations:

[0140] Determine the second network ID corresponding to the cell currently accessed by the terminal; if the second network ID is the same as the first network ID, determine that the condition is met.

[0141] Determine the second cell ID of the cell currently accessed by the terminal; if the second cell ID is the same as the first cell ID, determine that the condition is met.

[0142] Determine the geographical location of the terminal; if the geographical location is within the first geographical location area, determine that the condition is met.

[0143] In conjunction with some embodiments of the fifth aspect, in some embodiments, the transceiver module is further configured to receive a second model ID sent by the network device;

[0144] The processing module is also used to determine that the condition is met if the second model ID is the same as the first model ID;

[0145] In conjunction with some embodiments of the fifth aspect, in some embodiments, the transceiver module is further configured to receive a second version ID sent by the network device;

[0146] The processing module is also used to determine that the condition is met if the second version ID is the same as the first version ID;

[0147] In conjunction with some embodiments of the fifth aspect, in some embodiments, the transceiver module is further configured to receive a second network-side condition ID sent by the network device;

[0148] The processing module is further configured to determine that the condition is met if the second network-side condition ID is consistent with the first network-side condition ID.

[0149] In conjunction with some embodiments of the fifth aspect, in some embodiments, the transceiver module is further configured to send first indication information to the network device, the first indication information being used to trigger the network device to send the model-related information.

[0150] In conjunction with some embodiments of the fifth aspect, in some embodiments, the transceiver module is further configured to receive model-related information sent by the network device.

[0151] In conjunction with some embodiments of the fifth aspect, in some embodiments, the model-related information includes at least one of the following:

[0152] Training dataset;

[0153] Model architecture;

[0154] Model parameters.

[0155] In conjunction with some embodiments of the fifth aspect, in some embodiments, the first indication information is used to indicate the information content that the terminal needs to request from the network device, the information content including at least one of the following:

[0156] Training dataset;

[0157] Model architecture;

[0158] Model parameters.

[0159] In conjunction with some embodiments of the fifth aspect, in some embodiments, the transceiver module is further configured to send a third indication information to the server before sending the first indication information to the network device, the third indication information being used to indicate that the terminal does not have an available model;

[0160] The server sends a second instruction, which is used to indicate the content of the information.

[0161] In conjunction with some embodiments of the fifth aspect, in some embodiments, the transceiver module is further configured to send the model-related information to the server and receive the terminal-side model sent by the server.

[0162] Sixthly, embodiments of this disclosure provide a network device, including:

[0163] The transceiver module is used to receive first indication information sent by the terminal, the first indication information being used to indicate that the terminal does not have a usable model; based on the first indication information, it sends model-related information to the terminal, the model-related information being used for the model on the terminal side.

[0164] In conjunction with some embodiments of the sixth aspect, in some embodiments, the model-related information includes at least one of the following:

[0165] Training dataset;

[0166] Model architecture;

[0167] Model parameters.

[0168] In conjunction with some embodiments of the sixth aspect, in some embodiments, the first indication information is used to indicate the information content requested by the terminal from the network device, the information content including at least one of the following:

[0169] Training dataset;

[0170] Model architecture;

[0171] Model parameters.

[0172] In conjunction with some embodiments of the sixth aspect, in some embodiments, the transceiver module is further configured to send to the terminal at least one of the second ID, the second version ID, and the second network-side condition ID corresponding to the network-side model.

[0173] In a seventh aspect, embodiments of this disclosure provide a server, comprising:

[0174] The transceiver module is used to send the first information of the model on the terminal side to the terminal. The first information is used by the terminal to determine whether there is a usable model. The model-related information is used for the terminal side model.

[0175] In conjunction with some embodiments of the sixth aspect, in some embodiments, the first information includes at least one of the following:

[0176] First network ID;

[0177] First Community ID;

[0178] First geographical location area;

[0179] First model ID;

[0180] First version ID;

[0181] First network-side condition ID.

[0182] In conjunction with some embodiments of the sixth aspect, in some embodiments, the transceiver module is further configured to receive third indication information sent by the terminal, the third indication information being used to indicate that the terminal does not have an available model; and to send second indication information to the terminal, the second indication information being used to indicate the information content requested by the terminal from the network device.

[0183] In conjunction with some embodiments of the sixth aspect, in some embodiments, the information content includes at least one of the following:

[0184] Training dataset;

[0185] Model architecture;

[0186] Model parameters.

[0187] In conjunction with some embodiments of the sixth aspect, in some embodiments, the transceiver module is further configured to receive model-related information sent by the terminal;

[0188] The processing module is used to update the terminal-side model based on the model-related information.

[0189] The transceiver module is also used to send the terminal-side model to the terminal.

[0190] Eighthly, embodiments of this disclosure provide a communication device, the communication device comprising: one or more processors; one or more memories for storing instructions; wherein the processors are configured to invoke the instructions to cause the communication device to perform the communication method as described in the first aspect, an optional implementation of the first aspect, the second aspect, an optional implementation of the second aspect, the third aspect, and an optional implementation of the third aspect.

[0191] Ninthly, embodiments of this disclosure provide a communication system comprising: a terminal, a network device, and a server; wherein the terminal is configured to perform the method described in the first aspect and optional implementations thereof, the network device is configured to perform the method described in the second aspect and optional implementations thereof, and the server is configured to perform the method described in the third aspect and optional implementations thereof.

[0192] In a tenth aspect, embodiments of this disclosure provide a storage medium storing instructions that, when executed on a communication device, cause the communication device to perform the communication method as described in the first aspect, an optional implementation of the first aspect, the second aspect, an optional implementation of the second aspect, the third aspect, and an optional implementation of the third aspect.

[0193] In the eleventh aspect, embodiments of this disclosure provide a program product that, when executed by a communication device, causes the communication device to perform the communication method as described in the first aspect, the optional implementation of the first aspect, the second aspect, the optional implementation of the second aspect, the third aspect, and the optional implementation of the third aspect.

[0194] In a twelfth aspect, embodiments of this disclosure provide a computer program that, when run on a computer, causes the computer to perform the communication method as described in the first aspect, an optional implementation of the first aspect, the second aspect, an optional implementation of the second aspect, the third aspect, and an optional implementation of the third aspect.

[0195] It is understood that the aforementioned terminals, network devices, servers, communication devices, communication systems, storage media, program products, and computer programs are all used to execute the methods proposed in the embodiments of this disclosure. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.

[0196] The present invention is described in this disclosure. In some embodiments, the terms communication method, information processing method, information sending method, and information receiving method can be used interchangeably; the terms communication device, information processing device, information sending device, and information receiving device can be used interchangeably; and the terms information processing system, communication system, information sending system, and information receiving system can be used interchangeably.

[0197] This disclosure is not exhaustive, but merely illustrative of some embodiments, and is not intended to limit the scope of protection of this disclosure. Unless otherwise specified, each step in a particular embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a particular embodiment can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment can be arbitrarily interchanged. Furthermore, the optional implementation methods in a particular embodiment can be arbitrarily combined; moreover, the embodiments can be arbitrarily combined, for example, some or all steps of different embodiments can be arbitrarily combined, and a particular embodiment can be arbitrarily combined with the optional implementation methods of other embodiments.

[0198] In each of the disclosed embodiments, unless otherwise specified or in case of logical conflict, the terminology and / or descriptions of the embodiments are consistent and can be referenced by each other. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0199] The terminology used in the embodiments of this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the scope of this disclosure.

[0200] In this embodiment of the disclosure, unless otherwise stated, elements expressed in the singular form, such as "a," "an," "the," "the," "the," "the," "the," "the," "this," etc., can mean "one and only one," or "one or more," "at least one," etc. For example, when using articles such as "a," "an," "the," etc. in translation, the noun following the article can be understood as either a singular expression or a plural expression.

[0201] In the embodiments disclosed herein, "multiple" refers to two or more.

[0202] In some embodiments, the terms “at least one of”, “at least one of”, “at least one of”, “one or more”, “a plurality of”, “multiple”, etc., may be used interchangeably.

[0203] The descriptions in this disclosure, such as "at least one of A, B, C..." or "A and / or B and / or C...", include the case where any one of A, B, C... exists alone, as well as the case where any combination of any of A, B, C... exists alone. Each case can exist alone. For example, "at least one of A, B, C" includes the cases of A alone, B alone, C alone, A and B combination, A and C combination, B and C combination, and A and B and C combination. For example, A and / or B includes the cases of A alone, B alone, and A and B combination.

[0204] In some embodiments, the notation "in one case A, in another case B" or "in response to one case A, in response to another case B" may include the following technical solutions depending on the situation: A is executed regardless of B, i.e., A is executed in some embodiments; B is executed regardless of A, i.e., B is executed in some embodiments; A and B are selectively executed, i.e., A and B are selected for execution in some embodiments; A and B are both executed, i.e., A and B are executed in some embodiments. The same applies when there are more branches such as A, B, and C.

[0205] The prefixes "first," "second," etc., used in the embodiments of this disclosure are merely for distinguishing different descriptive objects and do not impose restrictions on the position, order, priority, quantity, or content of the descriptive objects. The description of the descriptive objects is found in the claims or the context of the embodiments, and the use of prefixes should not constitute unnecessary restrictions. For example, if the descriptive object is a "field," the ordinal numbers preceding "field" in "first field" and "second field" do not restrict the position or order of the "fields." "First" and "second" do not restrict whether the "fields" they modify are in the same message, nor do they restrict the order of "first field" and "second field." Similarly, if the descriptive object is a "level," the ordinal numbers preceding "level" in "first level" and "second level" do not restrict the priority between "levels." Furthermore, the number of descriptive objects is not limited by ordinal numbers and can be one or more. For example, in "first device," the number of "devices" can be one or more. Furthermore, the objects modified by different prefixes can be the same or different. For example, if the object being described is "device", then "first device" and "second device" can be the same device or different devices, and their types can be the same or different. Similarly, if the object being described is "information", then "first information" and "second information" can be the same information or different information, and their content can be the same or different.

[0206] In some embodiments, “including A,” “containing A,” “for indicating A,” and “carrying A” can be interpreted as directly carrying A or indirectly indicating A.

[0207] In some embodiments, the terms “in response to…”, “in response to determining…”, “in the case of…”, “when…”, “if…”, “if…”, etc., can be used interchangeably.

[0208] In some embodiments, the terms “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,” and “above” can be used interchangeably, as can the terms “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,” and “below”.

[0209] In some embodiments, devices, etc., can be interpreted as physical or virtual, and their names are not limited to the names recorded in the embodiments. Terms such as “device”, “equipment”, “circuit”, “network element”, “node”, “function”, “unit”, “section”, “system”, “network”, “chip”, “chip system”, “entity”, and “subject” can be used interchangeably.

[0210] In some embodiments, "network" can be interpreted as devices included in a network (e.g., access network devices, core network devices, etc.).

[0211] In some embodiments, the terms "access network device (AN device)," "radio access network device (RAN device)," "base station (BS)," "radio base station," "fixed station," "node," "access point," "transmission point (TP)," "reception point (RP)," "transmission / reception point (TRP)," "panel," "antenna panel," "antenna array," "cell," "macro cell," "small cell," "femto cell," "pico cell," "sector," "cell group," "carrier," "component carrier," and "bandwidth part (BWP)" can be used interchangeably.

[0212] In some embodiments, the terms "terminal", "terminal device", "user equipment (UE)", "user terminal", "mobile station (MS)", "mobile terminal (MT)", "subscriber station", "mobile unit", "subscriber unit", "wireless unit", "remote unit", "mobile device", "wireless device", "wireless communication device", "remote device", "mobile subscriber station", "access terminal", "mobile terminal", "wireless terminal", "remote terminal", "handset", "user agent", "mobile client", and "client" can be used interchangeably.

[0213] In some embodiments, access network devices, core network devices, or network devices can be replaced by terminals. For example, embodiments of this disclosure can also be applied to structures that replace communication between access network devices, core network devices, or network devices and terminals with communication between multiple terminals (e.g., also referred to as device-to-device (D2D), vehicle-to-everything (V2X), etc.). In this case, the structure can also be configured such that the terminal has all or part of the functions of the access network device. Furthermore, terms such as "uplink" and "downlink" can be replaced with terms corresponding to communication between terminals (e.g., "sidelink"). For example, uplink channel, downlink channel, etc., can be replaced with sidelink channel, uplink link, downlink link, etc., can be replaced with sidelink link.

[0214] In some embodiments, the terminal may be replaced by an access network device, a core network device, or a network device. In this case, the access network device, core network device, or network device may also be configured to have all or some of the functions of the terminal.

[0215] In some embodiments, the acquisition of data, information, etc., may comply with the laws and regulations of the country where the location is situated.

[0216] In some embodiments, data, information, etc., may be obtained with the user's consent.

[0217] Furthermore, each element, each row, or each column in the table of this disclosure can be implemented as an independent embodiment, and any combination of any element, any row, or any column can also be implemented as an independent embodiment.

[0218] The correspondences shown in the tables of this disclosure can be configured or predefined. The values ​​of the information in each table are merely examples and can be configured to other values; this disclosure is not limiting. When configuring the correspondences between information and parameters, it is not necessarily required to configure all the correspondences shown in each table. For example, the correspondences shown in some rows of the tables in this disclosure may not be configured. Furthermore, appropriate modifications and adjustments can be made based on the above tables, such as splitting, merging, etc. The names of the parameters shown in the headers of the above tables can also use other names that the communication device can understand, and the values ​​or representations of the parameters can also be other values ​​or representations that the communication device can understand. In the implementation of the above tables, other data structures can also be used, such as arrays, queues, containers, stacks, linear lists, pointers, linked lists, trees, graphs, structures, classes, heaps, hash tables, or hash tables, etc.

[0219] The predefined terms in this disclosure can be understood as defined, predefined, stored, pre-stored, pre-negotiated, pre-configured, solidified, or pre-burned.

[0220] Figure 1A is a schematic diagram of the architecture of a communication system according to an embodiment of the present disclosure. As shown in Figure 1A, the communication system 100 may include a terminal, a network device, and a server; wherein, the terminal is a device that communicates with the network device, and the terminal may be either a network device or a terminal. Optionally, the network device may include at least one of an access network device and a core network device.

[0221] In some embodiments, the terminal includes, but is not limited to, at least one of the following: mobile phone, wearable device, Internet of Things device, car with communication function, smart car, tablet computer, computer with wireless transceiver function, virtual reality (VR) terminal device, augmented reality (AR) terminal device, wireless terminal device in industrial control, wireless terminal device in self-driving, wireless terminal device in remote medical surgery, wireless terminal device in smart grid, wireless terminal device in transportation safety, wireless terminal device in smart city, and wireless terminal device in smart home.

[0222] In some embodiments, the access network device is, for example, a node or device that connects a terminal to a wireless network. The access network device may include, but is not limited to, at least one of the following in a 5G communication system: evolved Node B (eNB), next-generation eNB (ng-eNB), next-generation Node B (gNB), node B (NB), home node B (HNB), home evolved node B (HeNB), wireless backhaul device, radio network controller (RNC), base station controller (BSC), base transceiver station (BTS), base band unit (BBU), mobile switching center, base station in a 6G communication system, open RAN, cloud RAN, base station in other communication systems, and access node in a wireless fidelity (WiFi) system.

[0223] In some embodiments, the technical solutions of this disclosure can be applied to the Open RAN architecture. In this case, the interfaces between or within access network devices involved in the embodiments of this disclosure can be transformed into internal interfaces of Open RAN. The processes and information interactions between these internal interfaces can be implemented by software or programs.

[0224] In some embodiments, the access network device may be composed of a central unit (CU) and a distributed unit (DU). The CU may also be called a control unit. The CU-DU structure can separate the protocol layer of the access network device. Some of the protocol layer functions are centrally controlled by the CU, while the remaining part or all of the protocol layer functions are distributed in the DU and centrally controlled by the CU. However, this is not the only possibility.

[0225] In some embodiments, the core network device may be a single device comprising one or more network elements, or multiple devices or a group of devices, each comprising all or part of one or more network elements. Network elements may be virtual or physical. The core network may include, for example, at least one of an Evolved Packet Core (EPC), a 5G Core Network (5GCN), and a Next Generation Core (NGC). Alternatively, the core network device may also be a location management function network element. Exemplarily, the location management function network element includes a location server, which may be implemented as any of the following: a Location Management Function (LMF), an Enhanced Serving Mobile Location Centre (E-SMLC), a Secure User Plane Location (SUPL), and a Secure User Plane Location Platform (SUPLLP).

[0226] In some embodiments, a server is a specific network device that provides computing power and runs software applications, possessing high-speed CPU processing power, long-term reliable operation capability, powerful I / O data throughput capability, and high scalability. The server can train and update models for terminals. The server can communicate with terminals in the communication system, and can send models to terminals. Terminals can send information required for model training or updates to the server.

[0227] In some embodiments, the server may be a cloud server, a server of a distributed system, or a server incorporating blockchain technology.

[0228] It is understood that the communication system described in this disclosure is for the purpose of more clearly illustrating the technical solutions of this disclosure, and does not constitute a limitation on the technical solutions proposed in this disclosure. As those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical solutions proposed in this disclosure are also applicable to similar technical problems.

[0229] The following embodiments of this disclosure can be applied to the communication system 100 shown in FIG1A, or to some of the main bodies, but are not limited thereto. The main bodies shown in FIG1A are illustrative. The communication system may include all or some of the main bodies in FIG1A, or it may include other main bodies outside of FIG1A. The number and form of each main body are arbitrary. The connection relationship between the main bodies is illustrative. The main bodies may not be connected or may be connected. The connection can be in any way, it can be a direct connection or an indirect connection, it can be a wired connection or a wireless connection.

[0230] The embodiments disclosed herein can be applied to Long Term Evolution (LTE), LTE-Advanced (LTE-A), LTE-Beyond (LTE-B), SUPER 3G, IMT-Advanced, 4th generation mobile communication system (4G), 5th generation mobile communication system (5G), 5G new radio (NR), Future Radio Access (FRA), New-Radio Access Technology (RAT), New Radio (NR), New radio access (NX), Future generation radio access (FX), Global System for Mobile communications (GSM), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), and IEEE 802.20, Ultra-Wideband (UWB), Bluetooth (a registered trademark), Public Land Mobile Network (PLMN) networks, Device-to-Device (D2D) systems, Machine-to-Machine (M2M) systems, Internet of Things (IoT) systems, Vehicle-to-Everything (V2X) systems, systems utilizing other communication methods, and next-generation systems built upon them, etc. Furthermore, multiple systems can be combined (e.g., a combination of LTE or LTE-A with 5G).

[0231] Machine learning algorithms are one of the most important methods for implementing artificial intelligence technology. Machine learning can obtain models from large amounts of training data, and these models can then be used to predict events. In many fields, machine learning models can achieve very accurate predictions.

[0232] Wireless communication networks can use AI models for prediction and inference, improving system performance. Training AI models requires collecting large amounts of data, and the required data varies depending on the application scenario.

[0233] Optionally, application scenarios may include processes in mobile communication systems such as beam management, channel state information (CSI) reporting, CSI compression, positioning, handover, mobility management, and radio resource management.

[0234] Optionally, in CSI compression, the UE can use a first AI model to compress the CSI measurement results and report the compressed CSI information to the network. The network then uses a second AI model to decompress the CSI measurement results to obtain the original CSI measurement results. This method can reduce the radio resources and signaling required for CSI reporting.

[0235] Optionally, the AI ​​model used on the UE side and the AI ​​model used on the network side need to be matched.

[0236] Alternatively, the matching between the AI ​​model used on the UE side and the AI ​​model used on the network side can be ensured by any of the following methods:

[0237] Method 1: The network device sends the structural parameters of the AI ​​model to the UE.

[0238] Method 2: The network device sends the dataset needed to train the AI ​​model to the UE.

[0239] Method 3: The network device sends the structural parameters of the AI ​​model and the dataset required to train the model to the UE.

[0240] Optionally, the UE can obtain an AI model through training based on the received training dataset or structural parameters.

[0241] Alternatively, due to limited computing power, the UE cannot train the model locally, and the model used by the UE can be obtained by the UE through training on the server.

[0242] Optionally, the AI ​​model or function can achieve better performance under specific application conditions, which can be divided into network-side conditions and UE-side conditions.

[0243] Optionally, network-side conditions may include the following:

[0244] Community types, such as macro, micro, and dense urban communities.

[0245] Network deployment scenarios, such as indoor and outdoor.

[0246] Wireless channel quality can be determined using RSRP, RSRQ, or SINR.

[0247] cell frequency

[0248] Location of the community

[0249] Distance between base stations

[0250] Antenna configuration, including the number of ports and the number of MIMO layers.

[0251] Transmit power

[0252] Numerology

[0253] Optionally, network-side conditions can be bound to IDs, with the network device indicating these conditions by providing the ID. The UE is unaware of which specific network-side conditions the ID represents. When the UE uses AI for inference, it determines whether the current network-indicated ID matches the network ID used when collecting AI function / model training data. If they do not match, the UE determines that the current AI function / model does not meet the network-side conditions.

[0254] Optionally, if the UE does not store a model that matches the network locally, the network device needs to transmit the model or dataset to ensure that the model on the UE side matches the model on the network side. How the UE determines whether the locally stored model matches the network-side model and how to trigger the network to transmit the model or dataset becomes a problem that needs to be solved.

[0255] Based on this, this disclosure provides a communication method to solve the above problems.

[0256] Figure 2A is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure. As shown in Figure 2A, this embodiment of the disclosure relates to a communication method for a communication system 100, the method comprising:

[0257] Step 2101: The server sends the first information of the terminal-side model to the terminal.

[0258] In some embodiments, the server may include, but is not limited to, a cloud server, a server in a distributed system, a server in a blockchain, etc.

[0259] In some embodiments, the model may include, but is not limited to: beam management model, channel state information (CSI) prediction model, CSI compression model, positioning model, handover model, mobility management model, radio resource management model, etc.

[0260] In some embodiments, the server may store multiple models. The server may train and update each model.

[0261] In some embodiments, the model can be an AI model, an ML model, or other types of models.

[0262] In some embodiments, the server may store first information for each model. Optionally, different models may correspond to different first information. Optionally, some models in the server may correspond to the same first information. For example, the server includes models 1 to n, where model 1 may correspond to first information 1, model 2 may have first information 2, ..., and model n may have first information n. As another example, the server includes models 1 to n, where models 1 and 2 may correspond to first information 1, models 3 to 5 may have first information 2, ..., and model n may have first information i, etc.

[0263] In some embodiments, the terminal-side model can be trained by the server, that is, one or more terminal-side models are stored on the server.

[0264] In some embodiments, the server may receive a first request sent by the terminal, and the server may determine the model identifier (ID) of the terminal-side model based on the first request of the terminal. Furthermore, the server may obtain the first information of the terminal-side model based on the model ID.

[0265] In some embodiments, the server can determine the model deployed on the terminal based on the terminal ID carried in the terminal's first request. Further, the server obtains the first information of the terminal-side model based on the model ID of the model deployed on the terminal, and uses it as the first information of the terminal-side model.

[0266] In some embodiments, the server may pre-store the mapping relationship between model ID and first information. After obtaining the model ID of the terminal-side model, the server can query the mapping relationship based on the model ID to obtain the first information of the terminal-side model.

[0267] In some embodiments, the server may also periodically send the first information of the terminal-side model to the terminal or when set conditions are met. For example, if the server updates the terminal-side model, it may send the first information of the terminal-side model to the terminal.

[0268] In some embodiments, the first information can be understood as the matching information of the terminal-side model. Optionally, the matching information of the terminal-side model may include, but is not limited to, network-related information, terminal-related information, and model-related information corresponding to the training phase of the terminal-side model.

[0269] In some embodiments, the first information of the terminal-side model includes at least one of the following:

[0270] First network ID;

[0271] First Community ID;

[0272] First geographical location area;

[0273] First model ID;

[0274] First version ID;

[0275] First network-side condition ID.

[0276] Optionally, the first network ID can be the identifier of the network corresponding to the data collected during the training phase of the terminal-side model, or the identifier of a network that can be used by the pre-configured terminal-side model during the inference phase.

[0277] Optionally, the first network ID can be a Public Land Mobile Network (PLMN) ID.

[0278] Optionally, the first cell is the cell corresponding to the data collected during the terminal-side model training phase, or a pre-configured cell that the terminal-side model can be applied to during the inference phase.

[0279] Optionally, the first geographic location region is the geographic location region corresponding to the data collected during the training phase of the terminal-side model, or a pre-configured geographic location region that the terminal-side model can be applied to during the inference phase.

[0280] Optionally, the first model ID is the model ID of the terminal-side model.

[0281] Optionally, the first version ID is the version ID of the terminal-side model.

[0282] Optionally, the first network-side condition ID can identify the network-side conditions corresponding to the data collected during the terminal-side model training phase, or identify the pre-configured network-side conditions applicable to the terminal-side model during the inference phase. In this disclosure, network-side conditions are bound to IDs, and the network device provides IDs to the terminal to indicate network-side conditions, making it impossible for the UE to obtain specific network-side conditions, thereby improving network-side security.

[0283] In some embodiments, the server can train and fine-tune the terminal-side model based on training samples. After training or fine-tuning is completed, the server can deploy the terminal-side model to the terminal.

[0284] Step 2102: The terminal determines whether a usable model is available based on the first information.

[0285] In some embodiments, the terminal determines whether it has a usable model based on the first information. If it is determined that the terminal does not have a usable model, the terminal needs model-related information to generate or update the terminal-side model, thereby enabling the terminal to have a usable model. If it is determined that the terminal has a usable model, the terminal does not need model-related information.

[0286] In some embodiments, in response to any of the information included in the first information not being satisfied, the terminal determines that there is no available model, that is, the terminal needs model-related information.

[0287] In some embodiments, in response to the first information condition being met, the terminal determines that it has an available model, meaning that the terminal does not need model-related information.

[0288] In some embodiments, the terminal may determine whether the terminal-side model matches the network-side model based on the first information.

[0289] In some embodiments, in response to a mismatch between the terminal-side model and the network-side model, it can be determined that the terminal does not have an available model, meaning that the terminal determines that it needs model-related information.

[0290] In some embodiments, in response to a match between the terminal-side model and the network-side model, it can be determined that the terminal has an available model, meaning that the terminal determines that it does not need model-related information.

[0291] In some embodiments, determining that the first information satisfies the condition includes at least one of the following operations:

[0292] Determine the second network ID corresponding to the cell currently accessed by the terminal. If the second network ID is the same as the first network ID, determine that the first information meets the conditions.

[0293] Determine the second cell ID of the cell currently accessed by the terminal. If the second cell ID is the same as the first cell ID, determine that the first information meets the condition.

[0294] Determine the geographical location of the terminal; if the geographical location is within the first geographical location area, determine that the first information meets the condition.

[0295] Receive the network-side model ID sent by the network device. If the network-side model ID and the terminal-side model ID are the same, determine that the first information meets the condition.

[0296] Receive the second version ID sent by the network device. If the second version ID is the same as the first version ID, determine that the first information meets the condition.

[0297] Receive the second network-side condition ID sent by the network device. If the second network-side condition ID is consistent with the first network-side condition ID, determine that the first information meets the condition.

[0298] In some embodiments, if the second PLMN and the first PLMN are consistent, the second cell ID and the first cell ID are consistent, the first model ID and the second model ID are consistent, the second version ID and the first version ID are consistent, the second network-side condition ID and the first network-side condition ID are consistent, and the terminal's geographical location is within the first geographical location area, the terminal can determine that it has an available model, or determine that the terminal-side model and the network-side model match, or determine that the terminal does not need model-related information.

[0299] In some embodiments, determining that the first information does not meet the condition includes at least one of the following operations:

[0300] Determine the second network ID corresponding to the cell currently accessed by the terminal. If the second network ID and the first network ID are inconsistent, determine that the first information does not meet the conditions.

[0301] Determine the second cell ID of the cell currently accessed by the terminal. If the second cell ID and the first cell ID are inconsistent, determine that the first information does not meet the conditions.

[0302] Determine the geographical location of the terminal; if the geographical location is not within the first geographical location area, determine that the first information does not meet the conditions.

[0303] Receive the network-side model ID sent by the network device. If the network-side model ID and the terminal-side model ID are inconsistent, determine that the first information condition is not met.

[0304] Receive the second version ID sent by the network device. If the second version ID is inconsistent with the first version ID, it is determined that the first information does not meet the conditions.

[0305] If the second network-side condition ID sent by the network device is inconsistent with the first network-side condition ID, it is determined that the first information does not meet the condition.

[0306] In some embodiments, after determining that the first information meets the conditions, it can be determined that the terminal-side model matches the network-side model, and that the terminal side has an available model, that is, the terminal determines that it does not need model-related information.

[0307] In some embodiments, if the first information condition is not met, it can be determined that the terminal-side model and the network-side model do not match, and that the terminal side does not have an available model, that is, the terminal determines that it needs model-related information.

[0308] In some embodiments, if the second network ID and the first network ID are inconsistent, that is, the first network ID corresponding to the terminal-side model is different from the second network ID corresponding to the cell currently accessed by the terminal, for example, the terminal-side model corresponds to a 4G network and the cell currently accessed by the terminal corresponds to a 5G network, or the terminal-side model corresponds to a first operator network and the cell currently accessed by the terminal corresponds to a second operator network, etc.

[0309] In some embodiments, if the second cell ID and the first cell ID are inconsistent, that is, the cell corresponding to the terminal-side model is different from the cell currently accessed by the terminal, for example, the terminal-side model corresponds to cell 1, while the cell currently accessed by the terminal is cell 2. In other words, the cell corresponding to the terminal-side model training phase is different from the cell accessed when performing inference based on the terminal-side model; or, the cell configured during the terminal-side model inference is different from the cell corresponding to the actual inference based on the terminal-side model.

[0310] It is understandable that if the second network ID and the first network ID are inconsistent, and / or the second cell ID and the first cell ID are inconsistent, it can be determined that the network configuration during the terminal-side model training phase is different from the network configuration during inference based on the terminal-side model. Alternatively, the network configuration configured during terminal-side model inference is different from the network configuration during actual inference based on the terminal-side model.

[0311] In some embodiments, if the terminal's current geographic location is not within the first geographic location area, that is, if the terminal has moved and is not in the location area where the terminal-side model collected training data, or is not in the location area where configuration inference is performed.

[0312] In some embodiments, if the second model ID and the first model ID are inconsistent, that is, the terminal-side model and the network-side model are two different models, for example, the terminal-side model is a beam management model and the network-side model is a CSI prediction model.

[0313] In some embodiments, if the second version ID is inconsistent with the first version ID, that is, the terminal-side model and the network-side model may be the same model, but the two different models are different versions of the model. For example, both the terminal-side model and the network-side model are beam management models, but the terminal-side model is a version 2.0 beam management model, while the network-side model is a version 3.0 beam management model.

[0314] In some embodiments, if the second network-side condition ID and the first network-side condition ID are inconsistent, wherein the second network-side condition associated with the second network-side condition ID is the network condition when the terminal performs inference based on the terminal-side model, and the first network-side condition associated with the first network-side condition ID is the network condition during the terminal-side model training phase, the first network condition and the second network condition are different. For example, the cell type in the first network-side condition is a macro cell, while the cell type in the second network-side condition is a micro cell; or, the network deployment scenario in the first network-side condition is an indoor deployment scenario, while the network deployment scenario in the first network-side condition is an outdoor deployment scenario; or, the wireless channel quality in the first network-side condition is different from the wireless channel quality in the second network-side condition; or the frequency of the cell in the first network-side condition is different from the frequency of the cell in the second network-side condition, etc.

[0315] In some embodiments, the terminal may obtain second information about the network model.

[0316] In some embodiments, the second information includes at least one of the following:

[0317] Second network ID;

[0318] Second network ID;

[0319] Second community ID;

[0320] Second geographical location area;

[0321] Second model ID;

[0322] Second version ID;

[0323] Second network-side condition ID.

[0324] Optionally, the second network ID can be the identifier of the network corresponding to the data collected during the network-side model training phase, or the identifier of the network that the pre-configured network-side model can use during the inference phase.

[0325] Optionally, the second network ID can be a Public Land Mobile Network (PLMN) ID.

[0326] Optionally, the second cell is the cell corresponding to the data collected during the network-side model training phase, or a cell that the pre-configured network-side model can be applied to during the inference phase.

[0327] Optionally, the second geographic location region is the geographic location region corresponding to the data collected during the training phase of the network-side model, or a pre-configured geographic location region that the network-side model can be applied to during the inference phase.

[0328] Optionally, the second model ID is the model ID of the network-side model.

[0329] Optionally, the second version ID is the version ID of the network-side model.

[0330] Optionally, the second network-side condition ID can identify the network-side conditions corresponding to the data collected during the network-side model training phase, or identify the network-side conditions applicable to the pre-configured network-side model during the inference phase.

[0331] In some embodiments, after the terminal obtains the first information and the second information, it can match the terminal-side model and the network-side model based on the first information and the second information.

[0332] In some embodiments, the second information can be understood as the matching information of the network-side model. Optionally, the matching information of the network-side model may include, but is not limited to, network-related information, terminal-related information, and model-related information corresponding to the training phase of the network-side model.

[0333] In some embodiments, if the first information and the second information are consistent, the terminal can determine that the terminal-side model and the network-side model match.

[0334] In some embodiments, if the first information and the second information are inconsistent, the terminal can determine that the terminal-side model and the network-side model do not match.

[0335] In some embodiments, the terminal may receive all or part of the information in the second information sent by the network device.

[0336] In some embodiments, the mismatch between the terminal-side model and the network-side model may include at least one of the following:

[0337] The second PLMN is inconsistent with the first PLMN;

[0338] The second cell ID is inconsistent with the first cell ID;

[0339] The second geographic location area is inconsistent with the first geographic location area;

[0340] The second model ID is inconsistent with the first model ID;

[0341] In some embodiments, if the second version ID and the first version ID are inconsistent;

[0342] The second network-side condition ID is inconsistent with the first network-side condition ID.

[0343] In some embodiments, if the second PLMN is consistent with the first PLMN, the second cell ID is consistent with the first cell ID, the second model ID is consistent with the first model ID, the second version ID is consistent with the first version ID, the second network-side condition ID is consistent with the first network-side condition ID, and the first geographical location area is within the second geographical location area, the terminal can determine that it has an available model, or determine that the terminal-side model and the network-side model match, or determine that the terminal does not need model-related information.

[0344] Step 2103: The terminal sends a third instruction message to the server.

[0345] In some embodiments, the third indication information may be used to indicate that no model is available on the terminal side.

[0346] In some embodiments, the third indication information may be used to indicate that the terminal-side model needs model-related information.

[0347] In some embodiments, the third indication information may be used to indicate that the terminal-side model and the network-side model do not match.

[0348] In some embodiments, the third indication information can be used to indicate that the terminal-side model and the network-side model have not matched successfully.

[0349] In some embodiments, the third indication information can be used to indicate information in the first information that does not meet the conditions. For example, the terminal can send at least one of the following to the server: network ID, cell ID, terminal location, model ID, version ID, and network-side condition ID.

[0350] Step 2104: The server sends a second instruction message to the terminal.

[0351] In some embodiments, the server may determine the information content that the terminal needs to request from the network device based on third instruction information.

[0352] For example, the server can determine the information content requested by the terminal as the training dataset when it is determined that the terminal-side model and the network-side model are different, based on the model ID.

[0353] In some embodiments, the information content requested by the terminal from the network device may include at least one of the following:

[0354] Training dataset;

[0355] Model architecture;

[0356] Model parameters.

[0357] In some embodiments, after determining the information content requested by the terminal from the network device, the server may send a second instruction to the terminal. In some embodiments, different information contents may be used in combination, model parameters and training datasets may be used in combination, the terminal-side model may be updated based on the model parameters, and the terminal-side model may be further optimized and trained based on the training dataset.

[0358] In some embodiments, the second indication information may be used to indicate the information content that the terminal needs to request from the network device.

[0359] In some embodiments, different information content can correspond to different model matching modes. For example, when the information content is a training dataset, the model matching mode is a model matching mode based on the training dataset, and the server can obtain the network-side model locally using the training dataset.

[0360] In some embodiments, the model matching mode may include, but is not limited to, at least one of the following modes:

[0361] Model matching patterns based on the training dataset;

[0362] Model matching patterns based on model architecture;

[0363] Model matching patterns based on model parameters.

[0364] In some embodiments, the model matching mode based on the training dataset is as follows: the terminal-side model is retrained based on the training dataset so that the terminal-side model and the network-side model can be matched.

[0365] In some embodiments, the model matching mode based on model architecture is as follows: the terminal-side model is updated to the network-side model based on the model structure so that the terminal-side model and the network-side model can be matched.

[0366] In some embodiments, the model matching mode based on model parameters involves updating the model parameters of the terminal-side model so that the terminal-side model and the network-side model can be matched.

[0367] Step 2105: The terminal sends the first instruction information to the network device.

[0368] In some embodiments, the first indication information may indicate to the network device that the terminal does not have an available model.

[0369] In some embodiments, the first indication information may indicate to the network device that the terminal-side model and the network-side model do not match.

[0370] In some embodiments, when the terminal-side model and the network-side model do not match, the terminal-side model needs to be updated or generated to ensure that the inference results of the terminal-side model can be understood by the network-side model. The terminal may send first indication information to the network device. Optionally, the network device may receive the first indication information sent by the terminal.

[0371] In some embodiments, when the terminal does not have an available model, that is, when the terminal-side model and the network-side model do not match, the terminal can send a first indication message to the network device. In other words, the first indication message is used to trigger the network device to send model-related information to the terminal.

[0372] In some embodiments, after determining the information content that the terminal needs to request from the network device based on the second instruction information sent by the server, the terminal can send the first instruction information to the network device based on the information content. That is, the first instruction information can be used to instruct the terminal to request the information content from the network device.

[0373] Step 2106: The network device sends model-related information to the terminal.

[0374] In some embodiments, model-related information includes at least one of the following:

[0375] Training dataset;

[0376] Model architecture;

[0377] Model parameters.

[0378] In some embodiments, model-related information can be used to train a terminal-side model or to generate a terminal-side model.

[0379] In some embodiments, the model parameters can be information about the terminal-side model. That is, the network device can train the terminal-side model and send the model parameters of the terminal-side model to the terminal to update the terminal-side model.

[0380] In some embodiments, the model architecture can be the architecture information of a network-side model. This model architecture allows the network-side model to be deployed to the terminal side. Optionally, the network device can determine whether to send the network-side model to the terminal.

[0381] In some embodiments, the network device may send a training dataset of the terminal-side model to the terminal, which may then train the terminal-side model based on the training dataset to provide a usable model or to match the terminal-side network with the network-side model. Optionally, the terminal may send the training dataset to a server, which may then train the terminal-side model based on the training dataset to obtain the trained terminal-side model. The server may then distribute the trained terminal-side model back to the terminal.

[0382] In some embodiments, the network device can send a training dataset of the network-side model to the terminal, which can then regenerate a terminal-side model based on the training dataset, so that the terminal has a usable model or that the terminal-side network and the network-side model can be matched. Optionally, the terminal can send the training dataset to a server, which can then generate a terminal-side model based on the training dataset, and the server can then distribute the generated terminal-side model to the terminal.

[0383] In some embodiments, the network device may send the model structure of the network-side model to the terminal, and the terminal may deploy the network-side model locally based on the model structure, so that the terminal has a usable model, or so that the terminal-side network and the network-side model can be matched.

[0384] In some embodiments, the network device can send model parameters of the terminal-side model to the terminal. Optionally, the terminal can update the terminal-side model based on the model parameters to make the terminal have a usable model, or to make the terminal-side network and the network-side model match. Optionally, after updating the terminal-side model according to the model parameters, the terminal can also collect a training dataset to fine-tune the updated terminal-side model. Optionally, the terminal can send the model parameters to the server, which can update the terminal-side model based on the model parameters and / or collect a training dataset to fine-tune the updated terminal-side model. The server can then distribute the trained terminal-side model to the terminal.

[0385] In some embodiments, the network device may send the model's training dataset and model parameters to the terminal. Optionally, the terminal may send the training dataset and model parameters to the server, which will then train the terminal-side model based on the training dataset. The server may then distribute the trained terminal-side model back to the terminal.

[0386] Step 2107: The terminal sends model-related information to the server.

[0387] Step 2108: The server updates the terminal-side model based on the model-related information.

[0388] Step 2109: The server sends the terminal-side model to the terminal.

[0389] In some embodiments, after receiving model-related information, the terminal can send the model-related information to the server, and the server can update the model on the terminal side based on the model-related information.

[0390] In some embodiments, the terminal can send the training dataset of the model to the server, and the server can train the terminal-side model using the training dataset to obtain an updated terminal-side model. Furthermore, the server sends the updated terminal-side model to the terminal.

[0391] In some embodiments, the terminal can send model parameters to the server, which can update the terminal-side model using the model parameters and fine-tune the terminal-side model by collecting a training dataset to obtain the updated terminal-side model. Furthermore, the server sends the terminal-side model to the terminal.

[0392] In some embodiments, the terminal can send the model's training dataset and model parameters to the server. The server can then train the terminal-side model using the training dataset and model parameters to obtain an updated terminal-side model. Furthermore, the server sends the terminal-side model to the terminal.

[0393] In some embodiments, the terminal can also train or generate the terminal-side model locally. Optionally, the terminal has the ability to train the model, and the terminal-side model is a lightweight small model. The terminal can train the terminal-side model based on the model's training dataset, so that the terminal has a usable model.

[0394] In some embodiments, the terminal can deploy the terminal-side model based on the model structure. That is, the network device trains the terminal-side model, and then sends the trained model parameters to the terminal. The terminal then deploys the terminal-side model trained by the network device locally based on the sent model parameters, so that the terminal has a usable model.

[0395] In some embodiments, the terminal can update the terminal-side model based on the model parameters. Furthermore, the terminal-side model can be trained using the model's training dataset, enabling the terminal to possess a usable model.

[0396] In some embodiments, the names of information, etc., are not limited to the names described in the embodiments. Terms such as "information", "message", "signal", "signaling", "report", "configuration", "indication", "instruction", "command", "channel", "parameter", "domain", "field", "symbol", "symbol", "codebook", "codeword", "codepoint", "bit", "data", "program", and "chip" can be used interchangeably.

[0397] In some embodiments, the terms “downlink control information (DCI),” “downlink (DL) assignment,” “DL DCI,” “uplink (UL) grant,” and “UL DCI” can be used interchangeably.

[0398] In some embodiments, the terms "synchronization signal (SS)," "synchronization signal block (SSB)," "reference signal (RS)," "pilot," and "pilot signal" can be used interchangeably.

[0399] In some embodiments, terms such as “send,” “transmit,” “report,” “distribute,” “transfer,” “bidirectional transmission,” “send and / or receive” can be used interchangeably.

[0400] In some embodiments, "acquire," "get," "obtain," "receive," "transmit," "bidirectional transmission," and "send and / or receive" can be used interchangeably and can be interpreted as receiving from other entities, acquiring from protocols, acquiring from higher layers, obtaining through self-processing, or autonomous implementation. Protocols include, for example, at least one of the 3GPP protocol, Wi-Fi protocol, and audio and / or video protocols.

[0401] The communication method involved in the embodiments of this disclosure may include at least one of steps 2101 to 2108. For example, step 2101 may be implemented as an independent embodiment, step 2102 may be implemented as an independent embodiment, step 2105 may be implemented as an independent embodiment, step 2106 may be implemented as an independent embodiment; steps 2101+2102 may be implemented as an independent embodiment, steps 2105+2106 may be implemented as an independent embodiment, steps 2107+2108+2109 may be implemented as an independent embodiment, but are not limited thereto.

[0402] In some embodiments, steps 2103 and 22104 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0403] In this implementation or embodiment, unless there is contradiction, each step can be independent, arbitrarily combined or exchanged in order, optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other implementations or other embodiments.

[0404] Figure 2B is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure. As shown in Figure 2B, this embodiment of the disclosure relates to a communication method for a communication system 100; the method includes:

[0405] Step 2201: The server sends the first information to the terminal.

[0406] Step 2202: The terminal determines whether there is a usable model based on the first information.

[0407] Step 2203: When the terminal determines that there is no available model, it triggers the network device to send model-related information.

[0408] Step 2204: The network device sends model-related information to the terminal.

[0409] Step 2205: The terminal sends model-related information to the server.

[0410] Step 2206: The server updates the terminal-side model based on the model-related information.

[0411] Step 2207: The server sends the terminal-side model to the terminal.

[0412] For a detailed description of steps 2201 to 2207, please refer to the above embodiment description.

[0413] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0414] In this implementation or embodiment, unless there is contradiction, each step can be independent, arbitrarily combined or exchanged in order, optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other implementations or other embodiments.

[0415] Figure 2C is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure. As shown in Figure 2C, this embodiment of the disclosure relates to a communication method for a communication system 100; the method includes:

[0416] Step 2301: The server sends the first information to the terminal.

[0417] Step 2302: The terminal matches the terminal-side model and the network-side model based on the first information.

[0418] Step 2303: When the terminal-side model and the network-side model do not match, the terminal sends a first indication message to the network device.

[0419] Step 2304: The network device sends model-related information to the terminal.

[0420] Step 2305: The terminal sends model-related information to the server.

[0421] Step 2306: The server updates the terminal-side model based on the model-related information.

[0422] Step 2307: The server sends the terminal-side model to the terminal.

[0423] For a detailed description of steps 2301 to 2307, please refer to the above embodiment description.

[0424] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0425] In this implementation or embodiment, unless there is contradiction, each step can be independent, arbitrarily combined or exchanged in order, optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other implementations or other embodiments.

[0426] Figure 2D is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure. As shown in Figure 2D, this disclosure relates to a communication method for a communication system 100; the method includes:

[0427] Step 2401: When the terminal determines that no model is available, it triggers the network device to send model-related information.

[0428] Step 2402: The network device sends model-related information to the terminal.

[0429] Step 2403: The terminal sends model-related information to the server.

[0430] Step 2404: The server updates the terminal-side model based on the model-related information.

[0431] Step 2405: The server sends the terminal-side model to the terminal.

[0432] For a detailed description of steps 2401 to 2405, please refer to the above embodiment description.

[0433] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0434] In this implementation or embodiment, unless there is contradiction, each step can be independent, arbitrarily combined or exchanged in order, optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other implementations or other embodiments.

[0435] Figure 2E is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure. As shown in Figure 2E, this disclosure relates to a communication method for a communication system 100; the method includes:

[0436] Step 2501: When the terminal determines that there is no available model, it triggers the network device to send model-related information.

[0437] Step 2502: The network device sends model-related information to the terminal.

[0438] Step 2503: The terminal determines the terminal-side model based on model-related information.

[0439] In some embodiments, the terminal has the capability to train models, enabling it to train terminal-side models based on training datasets, thus equipping the terminal with usable models. For example, the terminal can train lightweight, small models locally.

[0440] In some embodiments, the terminal can generate a terminal-side model based on the model structure of the model. That is, the network device trains the terminal-side model, and then sends the trained model parameters to the terminal. The terminal then deploys the terminal-side model trained by the network device locally based on the sent model parameters, so that the terminal has a usable model.

[0441] In some embodiments, the terminal can update the terminal-side model based on the model parameters. Furthermore, the terminal-side model can be trained using the model's training dataset, enabling the terminal to possess a usable model.

[0442] For a detailed description of steps 2401 to 2405, please refer to the above embodiment description.

[0443] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0444] In this implementation or embodiment, unless there is contradiction, each step can be independent, arbitrarily combined or exchanged in order, optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other implementations or other embodiments.

[0445] Figure 3 is a flowchart illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 3, the present disclosure relates to an information processing method for a terminal, the method comprising:

[0446] Step 3101: In response to determining that no model is available, the network device is triggered to send model-related information, wherein the model-related information is used for the model on the terminal side.

[0447] In some embodiments, the method further includes:

[0448] Based on the first information of the model on the terminal side, it is determined whether a usable model is available.

[0449] In some embodiments, the method further includes:

[0450] The terminal receives first information about the model sent by the server; wherein the receipt of the first information occurs before the network device is triggered to send model-related information.

[0451] In some embodiments, the first information includes at least one of the following:

[0452] First network identifier ID;

[0453] First Community ID;

[0454] First geographical location area;

[0455] Terminal-side model ID;

[0456] First version ID;

[0457] First network-side condition ID.

[0458] In some embodiments, the method further includes:

[0459] If any of the information included in the first information fails to meet the condition, it is determined that the terminal does not have a usable model;

[0460] In response to the condition being met by the first information, it is determined that the terminal has a usable model.

[0461] In some embodiments, determining that the first information satisfies a condition includes at least one of the following operations:

[0462] Determine the second network ID corresponding to the cell currently accessed by the terminal; if the second network ID is the same as the first network ID, determine that the condition is met.

[0463] Determine the second cell ID of the cell currently accessed by the terminal; if the second cell ID is the same as the first cell ID, determine that the condition is met.

[0464] Determine the geographical location of the terminal; if the geographical location is within the first geographical location area, determine that the condition is met.

[0465] Receive the second model ID sent by the network device; if the second model ID is the same as the first model ID, determine that the condition is met.

[0466] Receive the second version ID sent by the network device; if the second version ID is the same as the first version ID, determine that the condition is met.

[0467] Receive the second network-side condition ID sent by the network device. If the second network-side condition ID is consistent with the first network-side condition ID, determine that the condition is met.

[0468] In some embodiments, triggering the network device to send the model-related information includes:

[0469] Send a first indication message to the network device, the first indication message being used to trigger the network device to send the model-related information.

[0470] In some embodiments, the method further includes:

[0471] Receive the model-related information sent by the network device.

[0472] In some embodiments, the model-related information includes at least one of the following:

[0473] Training dataset;

[0474] Model architecture;

[0475] Model parameters.

[0476] In some embodiments, the first indication information is used to indicate the information content requested by the terminal from the network device, the information content including at least one of the following:

[0477] Training dataset;

[0478] Model architecture;

[0479] Model parameters.

[0480] In some embodiments, before sending the first indication information to the network device, the method further includes:

[0481] Send a third indication message to the server, the third indication message being used to indicate that the terminal does not have a usable model;

[0482] The terminal receives a second instruction message sent by the server, the second instruction message being used to instruct the terminal to request information content from the network device.

[0483] In some embodiments, the method further includes:

[0484] Send the model-related information to the server;

[0485] Receive the terminal-side model sent by the server.

[0486] For a detailed description of step 3101, please refer to the above embodiment.

[0487] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0488] In this implementation or embodiment, unless there is contradiction, each step can be independent, arbitrarily combined or exchanged in order, optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other implementations or other embodiments.

[0489] Figure 4 is a flowchart illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 4, the present disclosure relates to a communication method for a network device, the method comprising:

[0490] Step 4101: Receive first indication information sent by the terminal. The first indication information is used to indicate that the terminal does not have an available model.

[0491] Step 4102: Based on the first instruction information, send model-related information to the terminal. The model-related information is used for the model on the terminal side.

[0492] In some embodiments, the model-related information includes at least one of the following:

[0493] Training dataset;

[0494] Model architecture;

[0495] Model parameters.

[0496] In some embodiments, the first indication information is used to indicate the information content requested by the terminal from the network device, the information content including at least one of the following:

[0497] Training dataset;

[0498] Model architecture;

[0499] Model parameters.

[0500] In some embodiments, the method further includes:

[0501] Send to the terminal at least one of the second ID, the second version ID, and the second network-side condition ID corresponding to the network-side model.

[0502] For a detailed description of step 4101, please refer to the above embodiment.

[0503] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0504] In this implementation or embodiment, unless there is contradiction, each step can be independent, arbitrarily combined or exchanged in order, optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other implementations or other embodiments.

[0505] Figure 5 is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure. As shown in Figure 5, the present disclosure relates to a communication method for a server, the method including:

[0506] Step 5101: Send the first information of the model on the terminal side to the terminal. The first information is used by the terminal to determine whether there is a usable model. The model-related information is used for the model on the terminal side.

[0507] In some embodiments, the first information includes at least one of the following:

[0508] First network ID;

[0509] First Community ID;

[0510] First geographical location area;

[0511] Terminal-side model ID;

[0512] First version ID;

[0513] First network-side condition ID.

[0514] In some embodiments, the method further includes:

[0515] Receive third indication information sent by the terminal, the third indication information being used to indicate that the terminal does not have a usable model;

[0516] Send a second instruction to the terminal, the second instruction being used to indicate the information content that the terminal needs to request from the network device.

[0517] In some embodiments, the information content includes at least one of the following:

[0518] Training dataset;

[0519] Model architecture;

[0520] Model parameters.

[0521] In some embodiments, the method further includes:

[0522] Receive the model-related information sent by the terminal;

[0523] The terminal-side model is updated based on the model-related information.

[0524] Send the terminal-side model to the terminal.

[0525] For a detailed description of step 5101, please refer to the above embodiment.

[0526] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0527] In this implementation or embodiment, unless there is contradiction, each step can be independent, arbitrarily combined or exchanged in order, optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other implementations or other embodiments.

[0528] Figure 6 is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure. As shown in Figure 6, the present disclosure relates to a communication method for a communication system, the communication system including a terminal, a network device, and a server, and the method includes at least one of the following:

[0529] Step 6101: The server sends the first information of the model on the terminal side to the terminal. The first information is used by the terminal to determine whether a usable model is available.

[0530] Step 6102: When the terminal determines that there is no available model, it sends a first indication message to the network device. The first indication message is used to instruct the terminal to determine that there is no available model.

[0531] Step 6103: The network device receives the first indication information sent by the terminal.

[0532] Step 6104: The network device sends model-related information to the terminal based on the first instruction information. The model-related information is used for the terminal-side model.

[0533] Optional implementations of steps 6101-6104 can be found in the above embodiments.

[0534] In some embodiments, the above methods may include the methods described in the embodiments of the communication system side, terminal side, network device side, etc., which will not be repeated here.

[0535] The communication method involved in the embodiments of this disclosure may include at least one of steps 6101 to 6104. For example, step 6101 may be implemented as a standalone embodiment, step S6102 may be implemented as a standalone embodiment, steps S6102+6103 may be implemented as standalone embodiments, and steps S6103+6104 may be implemented as standalone embodiments, but are not limited thereto.

[0536] In this implementation or embodiment, unless there is contradiction, each step can be independent, arbitrarily combined or exchanged in order, optional methods or optional examples can be arbitrarily combined, and can be arbitrarily combined with any steps of other implementations or other embodiments.

[0537] The following is an exemplary description of the above method.

[0538] This invention provides a transmission control method for AI models, clarifying how the UE determines whether the locally stored model matches the network-side model, and how to trigger the network to transmit the model or dataset.

[0539] The main invention involves the UE determining whether the stored model matches the network-side model. If they do not match, the network is triggered to transmit the model or dataset.

[0540] Invention Point 1: The UE receives the model matching information sent by the server and determines whether it matches the network-side model based on the matching information.

[0541] The model is the model transmitted from the server to the UE. The model can also be a model stored locally by the UE.

[0542] The UE can store multiple models, each corresponding to different matching information.

[0543] The matching information can be determined by at least one of the following:

[0544] 1. PLMN, one or more PLMNs. Whether the PLMN of the cell to which the UE is connected is consistent with the PLMN mentioned above.

[0545] 2. Cell identifier, one or more cells. Whether the identifier of the cell the UE is connected to is consistent with the cell identifier.

[0546] 3. Geographic location information. Whether the UE's geographic location is within the stated geographic location area.

[0547] 4. Model identifier or version identifier. The network provides a network-side model identifier or version identifier, and the UE determines whether it matches the stated model identifier or version identifier.

[0548] 5. Network-side conditions can be indicated by an ID. The network provides a network-side condition ID, and the UE determines whether it matches the network-side condition ID corresponding to the model.

[0549] If all matching information meets the requirements, the model is determined to match the network-side model. Otherwise, there is no match.

[0550] Invention Point 2: If the UE determines that the model stored in the UE does not match the model on the network side, it sends a first indication message to the network, instructing the network to transmit the model or dataset.

[0551] The first instruction information indicates the required model matching method, which can be one or more of the following:

[0552] 1. Dataset transfer

[0553] 2. Model Architecture

[0554] 3. Model parameters

[0555] The UE determines which model matching method to use based on the server's instructions. In another embodiment, the UE sends mismatched network-side model information to the network, and the server instructs the UE to use a specific model matching method.

[0556] Invention Point 3: After receiving the dataset or model architecture parameters sent by the network, the UE sends the dataset or model architecture parameters to the server.

[0557] This disclosure also provides an apparatus for implementing any of the above methods. For example, an apparatus is provided that includes units or modules for implementing the steps performed by the terminal in any of the above methods. Alternatively, another apparatus is provided that includes units or modules for implementing the steps performed by a network device (e.g., an access network device, a core network functional node, a core network device, etc.) in any of the above methods.

[0558] It should be understood that the division of units or modules in the above device is only a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, the units or modules in the device can be implemented by a processor calling software: for example, the device includes a processor connected to a memory containing instructions. The processor calls the instructions stored in the memory to implement any of the above methods or to implement the functions of the units or modules in the above device. The processor can be, for example, a general-purpose processor, such as a Central Processing Unit (CPU) or a microprocessor, and the memory can be internal or external to the device. Alternatively, the units or modules in the device can be implemented in the form of hardware circuits. The functionality of some or all of the units or modules can be achieved through the design of these hardware circuits, which can be understood as one or more processors. For example, in one implementation, the hardware circuit is an application-specific integrated circuit (ASIC). The functionality of some or all of the units or modules is achieved through the design of the logical relationships between the components within the circuit. In another implementation, the hardware circuit can be implemented using a programmable logic device (PLD). Taking a field-programmable gate array (FPGA) as an example, it can include a large number of logic gates. The connection relationships between the logic gates are configured through configuration files, thereby achieving the functionality of some or all of the units or modules. All units or modules of the above device can be implemented entirely through processor-called software, entirely through hardware circuits, or partially through processor-called software with the remaining parts implemented through hardware circuits.

[0559] In this embodiment, the processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction read and execute capabilities, such as a Central Processing Unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), or a digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. The logical relationships of the aforementioned hardware circuits are fixed or reconfigurable. For example, the processor is a hardware circuit implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units or modules. Furthermore, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a Neural Network Processing Unit (NPU), a Tensor Processing Unit (TPU), or a Deep Learning Processing Unit (DPU).

[0560] Figure 7A is a schematic diagram of the structure of the terminal proposed in an embodiment of this disclosure. As shown in Figure 7A, it includes:

[0561] The transceiver module is used to trigger the network device to send model-related information when it is determined that no model is available. The model-related information is used for the model on the terminal side.

[0562] In some embodiments, the processing module is configured to determine whether a usable model is available based on the first information of the model on the terminal side.

[0563] In some embodiments, the transceiver module is further configured to receive first information about the model on the terminal side sent by the server; wherein receiving the first information occurs before the network device is triggered to send model-related information.

[0564] In some embodiments, the first information includes at least one of the following:

[0565] First network identifier ID;

[0566] First Community ID;

[0567] First geographical location area;

[0568] Terminal-side model ID;

[0569] First version ID;

[0570] First network-side condition ID.

[0571] In some embodiments, the processing module is further configured to:

[0572] If any of the information included in the first information fails to meet the condition, it is determined that the terminal does not have a usable model;

[0573] In response to the condition being met by the first information, it is determined that the terminal has a usable model.

[0574] In some embodiments, the processing module is further configured to perform at least one of the following operations:

[0575] Determine the second network ID corresponding to the cell currently accessed by the terminal; if the second network ID is the same as the first network ID, determine that the condition is met.

[0576] Determine the second cell ID of the cell currently accessed by the terminal; if the second cell ID is the same as the first cell ID, determine that the condition is met.

[0577] Determine the geographical location of the terminal; if the geographical location is within the first geographical location area, determine that the condition is met.

[0578] Receive the second model ID sent by the network device; if the second model ID is the same as the first model ID, determine that the condition is met.

[0579] Receive the second version ID sent by the network device; if the second version ID is the same as the first version ID, determine that the condition is met.

[0580] Receive the second network-side condition ID sent by the network device. If the second network-side condition ID is consistent with the first network-side condition ID, determine that the condition is met.

[0581] In some embodiments, the transceiver module is further configured to send first indication information to the network device, the first indication information being used to trigger the network device to send the model-related information.

[0582] In some embodiments, the transceiver module is further configured to receive model-related information sent by the network device.

[0583] In some embodiments, the model-related information includes at least one of the following:

[0584] Training dataset;

[0585] Model architecture;

[0586] Model parameters.

[0587] In some embodiments, the first indication information is used to indicate the information content requested by the terminal from the network device, the information content including at least one of the following:

[0588] Training dataset;

[0589] Model architecture;

[0590] Model parameters.

[0591] In some embodiments, the transceiver module is further configured to send a third indication message to the server before sending the first indication message to the network device, the third indication message being used to indicate that the terminal does not have an available model; and to receive a second indication message sent by the server, the second indication message being used to indicate the information content.

[0592] In some embodiments, the transceiver module is further configured to send model-related information to the server and receive terminal-side models sent by the server.

[0593] Optionally, the transceiver module described above is used to execute the steps related to "processing" executed by the terminal in any of the above methods. The terminal further includes a transceiver module, which is used to execute the steps related to "sending and receiving" executed by the terminal in any of the above methods. Further details are omitted here.

[0594] Figure 7B is a schematic diagram of the structure of a network device proposed in an embodiment of this disclosure. As shown in Figure 7B, it includes:

[0595] The transceiver module is used to receive first indication information sent by the terminal, the first indication information being used to indicate that the terminal does not have a usable model; based on the first indication information, it sends model-related information to the terminal, the model-related information being used for the model on the terminal side.

[0596] In some embodiments, the model-related information includes at least one of the following:

[0597] Training dataset;

[0598] Model architecture;

[0599] Model parameters.

[0600] In some embodiments, the first indication information is used to indicate the information content requested by the terminal from the network device, the information content including at least one of the following:

[0601] Training dataset;

[0602] Model architecture;

[0603] Model parameters.

[0604] In some embodiments, the transceiver module is further configured to send at least one of the second ID, the second version ID, and the second network-side condition ID corresponding to the network-side model to the terminal.

[0605] Optionally, the transceiver module described above is used to execute the steps related to "processing" performed by the terminal in any of the above methods. The network device also includes a transceiver module, which is used to execute the steps related to "sending and receiving" performed by the network device in any of the above methods. Further details are omitted here.

[0606] Figure 7C is a schematic diagram of the server structure proposed in an embodiment of this disclosure. As shown in Figure 7C, it includes:

[0607] The transceiver module is used to send the first information of the model on the terminal side to the terminal. The first information is used by the terminal to determine whether there is a usable model. The model-related information is used by the terminal side for the model.

[0608] In some embodiments, the first information includes at least one of the following:

[0609] First network ID;

[0610] First Community ID;

[0611] First geographical location area;

[0612] Terminal-side model ID;

[0613] First version ID;

[0614] First network-side condition ID.

[0615] In some embodiments, the transceiver module is further configured to receive third indication information sent by the terminal, the third indication information being used to indicate that the terminal does not have an available model; and to send second indication information to the terminal, the second indication information being used to indicate that the terminal needs to request information content from the network device.

[0616] In some embodiments, the information content includes at least one of the following:

[0617] Training dataset;

[0618] Model architecture;

[0619] Model parameters.

[0620] In some embodiments, the transceiver module is further configured to receive model-related information sent by the terminal;

[0621] The processing module is used to update the terminal-side model based on the model-related information.

[0622] The transceiver module is also used to send the terminal-side model to the terminal.

[0623] Figure 8A is a schematic diagram of the structure of the communication device 8100 proposed in an embodiment of this disclosure. The communication device 8100 can be a network device (e.g., access network device, core network device, etc.), a terminal (e.g., user equipment, etc.), a chip, chip system, or processor that supports the network device in implementing any of the above methods, or a chip, chip system, or processor that supports the terminal in implementing any of the above methods. The communication device 8100 can be used to implement the methods described in the above method embodiments; for details, please refer to the descriptions in the above method embodiments.

[0624] As shown in Figure 8A, the communication device 8100 includes one or more processors 8101. The processor 8101 can be a general-purpose processor or a dedicated processor, such as a baseband processor or a central processing unit (CPU). The baseband processor can be used to process communication protocols and communication data, while the CPU can be used to control communication devices (e.g., base stations, baseband chips, terminal devices, terminal device chips, DUs or CUs, etc.), execute programs, and process program data. The processor 8101 is used to invoke instructions to cause the communication device 8100 to execute any of the above methods.

[0625] In some embodiments, the communication device 8100 further includes one or more memories 8102 for storing instructions. Optionally, all or part of the memories 8102 may also be located outside the communication device 8100.

[0626] In some embodiments, the communication device 8100 further includes one or more transceivers 8103. When the communication device 8100 includes one or more transceivers 8103, the communication steps such as sending and receiving in the above method are performed by the transceivers 8103, and other steps are performed by the processor 8101.

[0627] In some embodiments, a transceiver may include a receiver and a transmitter, which may be separate or integrated. Optionally, the terms transceiver, transceiver unit, transceiver, transceiver circuit, etc., may be used interchangeably; the terms transmitter, transmitting unit, transmitter, transmitting circuit, etc., may be used interchangeably; and the terms receiver, receiving unit, receiver, receiving circuit, etc., may be used interchangeably.

[0628] Optionally, the communication device 8100 further includes one or more interface circuits 8104, which are connected to the memory 8102. The interface circuits 8104 can be used to receive signals from the memory 8102 or other devices, and can be used to send signals to the memory 8102 or other devices. For example, the interface circuits 8104 can read instructions stored in the memory 8102 and send the instructions to the processor 8101.

[0629] The communication device 8100 described in the above embodiments may be a network device or a terminal, but the scope of the communication device 8100 described in this disclosure is not limited thereto, and the structure of the communication device 8100 may not be limited by FIG8a. The communication device may be a standalone device or may be part of a larger device. For example, the communication device may be: (1) a standalone integrated circuit IC, or chip, or chip system or subsystem; (2) a collection of one or more ICs, optionally, the IC collection may also include storage components for storing data and programs; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (5) a receiver, terminal device, smart terminal device, cellular phone, wireless device, handheld device, mobile unit, vehicle device, network device, cloud device, artificial intelligence device, etc.; (6) others, etc.

[0630] Figure 8B is a schematic diagram of the structure of chip 8200 according to an embodiment of this disclosure. For cases where the communication device 8100 can be a chip or a chip system, please refer to the schematic diagram of chip 8200 shown in Figure 8B, but it is not limited thereto.

[0631] Chip 8200 includes one or more processors 8201, which are used to invoke instructions to cause chip 8200 to perform any of the above methods.

[0632] In some embodiments, chip 8200 further includes one or more interface circuits 8202 connected to memory 8203. Interface circuits 8202 can be used to receive signals from memory 8203 or other devices, and can also be used to send signals to memory 8203 or other devices. For example, interface circuit 8202 can read instructions stored in memory 8203 and send those instructions to processor 8201. Optionally, terms such as interface circuit, interface, transceiver pin, and transceiver can be used interchangeably.

[0633] In some embodiments, chip 8200 further includes one or more memories 8203 for storing instructions. Optionally, all or part of the memories 8203 may be located outside of chip 8200.

[0634] This disclosure also proposes a storage medium storing instructions that, when executed on a communication device 8100, cause the communication device 8100 to perform any of the above methods. Optionally, the storage medium is an electronic storage medium. Optionally, the storage medium is a computer-readable storage medium, but not limited thereto; it may also be a storage medium readable by other devices. Optionally, the storage medium may be a non-transitory storage medium, but not limited thereto; it may also be a temporary storage medium.

[0635] This disclosure also provides a program product that, when executed by the communication device 8100, causes the communication device 8100 to perform any of the above methods. Optionally, the program product is a computer program product.

[0636] This disclosure also proposes a computer program that, when run on a computer, causes the computer to perform any of the above methods.

[0637] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer programs. When the computer program is loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this disclosure are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer program can be stored in a computer-readable storage medium or transferred from one computer-readable storage medium to another. For example, the computer program can be transferred from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media may be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., high-density digital video discs (DVDs)), or semiconductor media (e.g., solid-state disks (SSDs)).

[0638] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this disclosure.

[0639] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0640] The above description is merely a specific embodiment of this disclosure, but the scope of protection of this disclosure is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this disclosure should be included within the scope of protection of this disclosure. Therefore, the scope of protection of this disclosure should be determined by the scope of the claims.

Claims

1. A communication method, characterized in that, The method, executed by a terminal, includes: In response to determining that no model is available, the network device is triggered to send model-related information, wherein the model-related information is used for terminal-side models.

2. The method according to claim 1, characterized in that, The method further includes: Based on the first information of the terminal-side model, determine whether a usable model is available.

3. The method according to claim 2, characterized in that, The method further includes: The terminal-side model first information is received from the server; wherein, receiving the first information occurs before the network device is triggered to send model-related information.

4. The method according to claim 2 or 3, characterized in that, The first information includes at least one of the following: First network identifier ID; First Community ID; First geographical location area; First model ID; First version ID; First network-side condition ID.

5. The method according to any one of claims 2-4, characterized in that, The method further includes: If any of the information included in the first information fails to meet the condition, it is determined that the terminal does not have a usable model; In response to the condition being met by the first information, it is determined that the terminal has a usable model.

6. The method according to claim 5, characterized in that, Determining that the first information meets the conditions includes at least one of the following operations: Determine the second network ID corresponding to the cell currently accessed by the terminal; if the second network ID is the same as the first network ID, determine that the condition is met. Determine the second cell ID of the cell currently accessed by the terminal; if the second cell ID is the same as the first cell ID, determine that the condition is met. Determine the geographical location of the terminal; if the geographical location is within the first geographical location area, determine that the condition is met. Receive the second model ID sent by the network device; if the second model ID is the same as the first model ID, determine that the condition is met. Receive the second version ID sent by the network device; if the second version ID is the same as the first version ID, determine that the condition is met. Receive the second network-side condition ID sent by the network device. If the second network-side condition ID is consistent with the first network-side condition ID, determine that the condition is met.

7. The method according to any one of claims 1-6, characterized in that, The step of triggering the network device to send the model-related information includes: Send a first indication message to the network device, the first indication message being used to indicate that the terminal does not have an available model; receive the model-related information sent by the network device.

8. The method according to any one of claims 1-7, characterized in that, The model-related information includes at least one of the following: Training dataset; Model architecture; Model parameters.

9. The method according to claim 7 or 8, characterized in that, Before sending the first indication information to the network device, the method further includes: Send a third indication message to the server, the third indication message being used to indicate that the terminal does not have a usable model; The terminal receives a second instruction message sent by the server, the second instruction message being used to instruct the terminal to request information content from the network device.

10. The method according to any one of claims 1-9, characterized in that, The method further includes: Send the model-related information to the server; Receive the terminal-side model sent by the server.

11. A communication method, characterized in that, Performed by a network device, the method includes: The receiving terminal sends a first indication message, which indicates that the terminal does not have a usable model. Based on the first indication information, model-related information is sent to the terminal, and the model-related information is used for the terminal-side model.

12. The method according to claim 11, characterized in that, The model-related information includes at least one of the following: Training dataset; Model architecture; Model parameters.

13. The method according to claim 12, characterized in that, The method further includes: Send to the terminal at least one of the second ID, the second version ID, and the second network-side condition ID corresponding to the network-side model.

14. A communication method, characterized in that, The method, executed by the server, includes: The terminal sends first information about the terminal-side model to the terminal. The first information is used by the terminal to determine whether a usable model is available. The model-related information is used for the terminal-side model.

15. The method according to claim 14, characterized in that, The first information includes at least one of the following: First network ID; First Community ID; First geographical location area; First model ID; First version ID; First network-side condition ID.

16. The method according to claim 14 or 15, characterized in that, The method further includes: Receive third indication information sent by the terminal, the third indication information being used to indicate that the terminal does not have a usable model; Send a second instruction to the terminal, the second instruction being used to instruct the terminal to request the information content from the network device.

17. The method according to any one of claims 14-16, characterized in that, The method further includes: Receive the model-related information sent by the terminal; The terminal-side model is updated based on the model-related information. Send the terminal-side model to the terminal.

18. A communication method, characterized in that, For a communication system, the communication system including a terminal, network equipment, and a server, the method includes: The server sends the terminal-side model's first information to the terminal, which is used by the terminal to determine whether a usable model is available. When the terminal determines that there is no available model, it sends a first indication message to the network device, the first indication message being used to indicate that the terminal does not have an available model; The network device receives the first indication information sent by the terminal; Based on the first indication information, the network device sends model-related information to the terminal, and the model-related information is used for the terminal-side model.

19. A communication device, characterized in that, The communication device is used to perform the method according to any one of claims 1 to 10, 11 to 13, and 14 to 16.

20. A communication system, characterized in that, The device includes a terminal, a network device, and a server, wherein the terminal is configured to implement the method of any one of claims 1 to 10, the network device is configured to implement the method of any one of claims 11 to 13, and the server is configured to implement the method of any one of claims 14 to 16.

21. A storage medium storing instructions, characterized in that, When the instructions are executed on a communication device, the communication device performs the method as described in any one of claims 1 to 10, 11 to 13, and 14 to 16.

22. A program product comprising at least one of a program and instructions, characterized in that, When at least one of the programs or instructions is executed by a communication device, it implements the method according to any one of claims 1 to 10, 11 to 13, and 14 to 16.

Images