Communication method and device and storage medium

Abstract

The invention provides a communication method and device and a storage medium, and relates to the technical field of communication. In the method, a second functional entity sends first AI / ML related information to a third functional entity, and the first AI / ML related information comprises at least one of the following items: first data information for AI / ML model training or analysis, first AI / ML model information and first analysis information; receiving index information of the first AI / ML related information sent by the third functional entity; and the first functional entity acquires the index information of the first AI / ML related information of the second functional entity, acquires the first AI / ML related information according to the index information of the first AI / ML related information, and performs communication processing with the second functional entity by using the first AI / ML related information. The accuracy and real-time performance of communication processing between the first functional entity and the second functional entity are improved.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a communication method, device and storage medium. Background Art

[0002] In the current 5G mobile communication system, the data collection, model training and inference process of the access network can be as follows: Figure 1 As shown: the operation administration and maintenance (OAM) entity can obtain input data for artificial intelligence (AI) / machine learning (ML) model training from the access network (AN) device, and the input data includes data from the access network device itself and measurement data from the terminal; the OAM entity uses the input data to train the AI / ML model (for example, the AI / ML model for terminal mobility optimization) and sends the AI / ML model to the access network device; the access network device can use the AI / ML model and the input data to infer ( / predict) and output the inference ( / prediction) results, for example, terminal trajectory prediction, target cell prediction, target 5G wireless access network node prediction, etc. According to the inference ( / prediction) results, the access network device initiates the mobility optimization process of the terminal, for example, switching the terminal from access network device 1 to access network device 2.

[0003] Since OAM entities are mainly used for configuration scheduling and performance maintenance management of network resources, and do not directly participate in the control of terminals and networks (such as control of terminal mobility and sessions), the terminal and network control-related models trained and provided by OAM may not meet real-time requirements. Summary of the invention

[0004] The present application provides a communication method, device and storage medium, which solve the technical problem that OAM training, provision of terminal and network control related models may not meet real-time requirements.

[0005] In a first aspect, an embodiment of the present application provides a communication method, which is applied to a first functional entity, and the method includes:

[0006] Obtain index information of first artificial intelligence AI / machine learning ML related information of the second functional entity, where the index information of the first AI / ML related information is used to indicate the first AI / ML related information stored by the second functional entity in the third functional entity, where the first AI / ML related information includes at least one of the following: first data information for AI / ML model training or analysis, first AI / ML model information, and first analysis information;

[0007] Acquire the first AI / ML related information according to the index information of the first AI / ML related information;

[0008] Use the first AI / ML related information to communicate with the second functional entity.

[0009] In one implementation, obtaining index information of the first AI / ML related information of the second functional entity includes:

[0010] A first message sent by the second functional entity is received, where the first message carries index information of the first AI / ML related information.

[0011] In one implementation, before the receiving the first message sent by the second functional entity, the method further includes:

[0012] Send a second message to the second functional entity, where the second message is used to request the first AI / ML related information.

[0013] In one implementation, the sending the second message to the second functional entity includes:

[0014] Sending the second message to the second functional entity based on any one of the following triggering conditions:

[0015] Determining that data or an AI / ML model of the second functional entity is required for AI / ML model training or analysis;

[0016] receiving a third message sent by the second functional entity, where the third message is used to request access layer, non-access layer or application layer processing;

[0017] A fourth message sent by a fourth functional entity is received, where the fourth message is used to request access layer, non-access layer, or application layer control of the second functional entity.

[0018] In one implementation, the acquiring the first AI / ML related information according to the index information of the first AI / ML related information includes:

[0019] Using the index information of the first AI / ML related information, obtaining the first AI / ML related information from a third functional entity; or,

[0020] The first AI / ML related information is determined according to locally stored AI / ML related information and index information of the first AI / ML related information, where the locally stored AI / ML related information is AI / ML related information obtained by the first functional entity from the third functional entity and stored locally, and the locally stored AI / ML related information includes index information of the first AI / ML related information.

[0021] In one implementation, obtaining index information of the first AI / ML related information of the second functional entity includes:

[0022] receiving a fifth message sent by a fifth functional entity, where the fifth message carries index information of the first AI / ML related information and / or information of the third functional entity, and the fifth message is used to request switching or to provide terminal context;

[0023] The acquiring the first AI / ML related information according to the index information of the first AI / ML related information includes:

[0024] obtaining the first AI / ML related information from the third functional entity using the index information of the first AI / ML related information and / or the information of the third functional entity;

[0025] The second functional entity is a second terminal, the first functional entity is a functional entity currently serving the second functional entity, and the fifth functional entity is a functional entity that previously served the second functional entity.

[0026] In one embodiment, the method further comprises:

[0027] Sending a sixth message to the third functional entity, where the sixth message is used to request a subscription to the first AI / ML related information of the second functional entity;

[0028] Receive index information of the first AI / ML related information sent by the third functional entity.

[0029] In one implementation, before using the first AI / ML related information to communicate with the second functional entity, the method further includes:

[0030] Send index information of the first AI / ML related information to the second functional entity.

[0031] In one implementation, the second functional entity performs communication processing, including:

[0032] Using the first data information to perform AI / ML model training to obtain a second AI / ML model; or using the first data information to perform analysis to obtain second analysis information;

[0033] Use the second AI / ML model or the second analysis information to communicate with the second functional entity.

[0034] In one implementation, the first AI / ML related information is first AI / ML model information, and the using the first AI / ML related information to communicate with the second functional entity includes:

[0035] Determining a first AI / ML model according to the first AI / ML model information;

[0036] Use the first AI / ML model to communicate with the second functional entity.

[0037] In one implementation, the performing communication processing with the second functional entity includes:

[0038] performing access layer processing with the second functional entity;

[0039] The first functional entity and the second functional entity meet one of the following conditions:

[0040] The first functional entity is a first access network device, and the second functional entity is a second terminal;

[0041] The first functional entity is a first terminal, and the second functional entity is a second terminal;

[0042] The first functional entity is a first terminal, and the second functional entity is a second access network device.

[0043] In one implementation, the performing communication processing with the second functional entity includes:

[0044] Performing non-access layer or application layer processing with the second functional entity;

[0045] The first functional entity and the second functional entity meet one of the following conditions:

[0046] The first functional entity is a first core network functional entity, and the second functional entity is a second terminal;

[0047] The first functional entity is a first terminal, and the second functional entity is a second terminal;

[0048] The first functional entity is a first terminal, and the second functional entity is a second core network functional entity.

[0049] In a second aspect, an embodiment of the present application provides a communication method, which is applied to a second functional entity, and the method includes:

[0050] Sending first artificial intelligence AI / machine learning ML related information to the third functional entity, where the first AI / ML related information includes at least one of the following: first data information for AI / ML model training or analysis, first AI / ML model information, and first analysis information;

[0051] receiving index information of the first AI / ML related information sent by the third functional entity, where the index information of the first AI / ML related information is used to indicate the first AI / ML related information stored in the third functional entity by the second functional entity;

[0052] Use the first AI / ML related information to communicate with the first functional entity.

[0053] In one embodiment, after receiving the index information of the first AI / ML related information sent by the third functional entity, and before using the first AI / ML related information to perform communication processing with the first functional entity, the method further includes:

[0054] A first message is sent to the first functional entity, where the first message carries index information of the first AI / ML related information.

[0055] In one implementation, the performing communication processing with the first functional entity includes:

[0056] Performing access layer processing with the first functional entity;

[0057] The first functional entity and the second functional entity meet one of the following conditions:

[0058] The first functional entity is a first access network device, and the second functional entity is a second terminal;

[0059] The first functional entity is a first terminal, and the second functional entity is a second terminal;

[0060] The first functional entity is a first terminal, and the second functional entity is a second access network device.

[0061] In one implementation, the performing communication processing with the first functional entity includes:

[0062] Performing non-access layer or application layer processing with the first functional entity;

[0063] The first functional entity and the second functional entity meet one of the following conditions:

[0064] The first functional entity is a first core network functional entity, and the second functional entity is a second terminal;

[0065] The first functional entity is a first terminal, and the second functional entity is a second terminal;

[0066] The first functional entity is a first terminal, and the second functional entity is a second core network functional entity.

[0067] In a third aspect, an embodiment of the present application provides a communication device, applied to a first functional entity, the device comprising:

[0068] A first acquisition unit is used to acquire index information of first artificial intelligence AI / machine learning ML related information of a second functional entity, where the index information of the first AI / ML related information is used to indicate the first AI / ML related information stored by the second functional entity in a third functional entity, where the first AI / ML related information includes at least one of the following: first data information for AI / ML model training or analysis, first AI / ML model information, and first analysis information;

[0069] a second acquiring unit, configured to acquire the first AI / ML related information according to the index information of the first AI / ML related information;

[0070] A processing unit is configured to perform communication processing with the second functional entity using the first AI / ML related information.

[0071] In one implementation, the first acquisition unit is specifically configured to:

[0072] A first message sent by the second functional entity is received, where the first message carries index information of the first AI / ML related information.

[0073] In one embodiment, the device further includes a first sending unit, wherein the first sending unit is configured to:

[0074] Send a second message to the second functional entity, where the second message is used to request the first AI / ML related information.

[0075] In one implementation, the first sending unit is specifically configured to:

[0076] Sending the second message to the second functional entity based on any one of the following triggering conditions:

[0077] Determining that data or an AI / ML model of the second functional entity is required for AI / ML model training or analysis;

[0078] receiving a third message sent by the second functional entity, where the third message is used to request access layer, non-access layer or application layer processing;

[0079] A fourth message sent by a fourth functional entity is received, where the fourth message is used to request access layer, non-access layer, or application layer control of the second functional entity.

[0080] In one implementation, the second acquisition unit is specifically configured to:

[0081] Using the index information of the first AI / ML related information, obtaining the first AI / ML related information from a third functional entity; or,

[0082] The first AI / ML related information is determined according to locally stored AI / ML related information and index information of the first AI / ML related information, where the locally stored AI / ML related information is AI / ML related information obtained by the first functional entity from the third functional entity and stored locally, and the locally stored AI / ML related information includes index information of the first AI / ML related information.

[0083] In one implementation, the first acquisition unit is specifically configured to:

[0084] receiving a fifth message sent by a fifth functional entity, where the fifth message carries index information of the first AI / ML related information and / or information of the third functional entity, and the fifth message is used to request switching or to provide terminal context;

[0085] The second acquisition unit is specifically used to:

[0086] obtaining the first AI / ML related information from the third functional entity using the index information of the first AI / ML related information and / or the information of the third functional entity;

[0087] The second functional entity is a second terminal, the first functional entity is a functional entity currently serving the second functional entity, and the fifth functional entity is a functional entity that previously served the second functional entity.

[0088] In one embodiment, the device further includes a second sending unit and a receiving unit, wherein:

[0089] The second sending unit is configured to send a sixth message to the third functional entity, where the sixth message is used to request a subscription to the first AI / ML related information of the second functional entity;

[0090] The receiving unit is configured to receive index information of the first AI / ML related information sent by the third functional entity.

[0091] In one implementation, the first sending unit is further configured to:

[0092] Send index information of the first AI / ML related information to the second functional entity.

[0093] In one implementation, the first AI / ML related information is the first data information, and the processing unit is specifically configured to:

[0094] Using the first data information to perform AI / ML model training to obtain a second AI / ML model; or using the first data information to perform analysis to obtain second analysis information;

[0095] Use the second AI / ML model or the second analysis information to communicate with the second functional entity.

[0096] In one implementation, the first AI / ML related information is first AI / ML model information, and the processing unit is specifically configured to:

[0097] Determining a first AI / ML model according to the first AI / ML model information;

[0098] Use the first AI / ML model to communicate with the second functional entity.

[0099] In one embodiment, the processing unit is specifically configured to:

[0100] performing access layer processing with the second functional entity;

[0101] The first functional entity and the second functional entity meet one of the following conditions:

[0102] The first functional entity is a first access network device, and the second functional entity is a second terminal;

[0103] The first functional entity is a first terminal, and the second functional entity is a second terminal;

[0104] The first functional entity is a first terminal, and the second functional entity is a second access network device.

[0105] In one embodiment, the processing unit is specifically configured to:

[0106] Performing non-access layer or application layer processing with the second functional entity;

[0107] The first functional entity and the second functional entity meet one of the following conditions:

[0108] The first functional entity is a first core network functional entity, and the second functional entity is a second terminal;

[0109] The first functional entity is a first terminal, and the second functional entity is a second terminal;

[0110] The first functional entity is a first terminal, and the second functional entity is a second core network functional entity.

[0111] In a fourth aspect, an embodiment of the present application provides a communication device, applied to a second functional entity, the device comprising:

[0112] A sending unit, configured to send first artificial intelligence AI / machine learning ML related information to a third functional entity, where the first AI / ML related information includes at least one of the following: first data information for AI / ML model training or analysis, first AI / ML model information, and first analysis information;

[0113] a receiving unit, configured to receive index information of the first AI / ML related information sent by the third functional entity, where the index information of the first AI / ML related information is used to indicate the first AI / ML related information stored in the third functional entity by the second functional entity;

[0114] A processing unit is configured to perform communication processing with a first functional entity using the first AI / ML related information.

[0115] In one implementation, the sending unit is further configured to:

[0116] A first message is sent to the first functional entity, where the first message carries index information of the first AI / ML related information.

[0117] In one embodiment, the processing unit is specifically configured to:

[0118] Performing access layer processing with the first functional entity;

[0119] The first functional entity and the second functional entity meet one of the following conditions:

[0120] The first functional entity is a first access network device, and the second functional entity is a second terminal;

[0121] The first functional entity is a first terminal, and the second functional entity is a second terminal;

[0122] The first functional entity is a first terminal, and the second functional entity is a second access network device.

[0123] In one embodiment, the processing unit is specifically configured to:

[0124] Performing non-access layer or application layer processing with the first functional entity;

[0125] The first functional entity and the second functional entity meet one of the following conditions:

[0126] The first functional entity is a first core network functional entity, and the second functional entity is a second terminal;

[0127] The first functional entity is a first terminal, and the second functional entity is a second terminal;

[0128] The first functional entity is a first terminal, and the second functional entity is a second core network functional entity.

[0129] In a fifth aspect, an embodiment of the present application provides a communication device, applied to a first functional entity, the device comprising a memory, a transceiver, a processor,

[0130] The memory is used to store a computer program; the transceiver is used to send and receive data under the control of the processor; the processor is used to read the computer program in the memory and perform the following operations:

[0131] Obtain index information of first artificial intelligence AI / machine learning ML related information of the second functional entity, where the index information of the first AI / ML related information is used to indicate the first AI / ML related information stored by the second functional entity in the third functional entity, where the first AI / ML related information includes at least one of the following: first data information for AI / ML model training or analysis, first AI / ML model information, and first analysis information;

[0132] Acquire the first AI / ML related information according to the index information of the first AI / ML related information;

[0133] Use the first AI / ML related information to communicate with the second functional entity.

[0134] In one implementation, the processor is specifically configured to perform the following operations:

[0135] A first message sent by the second functional entity is received, where the first message carries index information of the first AI / ML related information.

[0136] In one implementation, the processor is further configured to perform the following operations:

[0137] Send a second message to the second functional entity, where the second message is used to request the first AI / ML related information.

[0138] In one implementation, the processor is specifically configured to perform the following operations:

[0139] Sending the second message to the second functional entity based on any one of the following triggering conditions:

[0140] Determining that data or an AI / ML model of the second functional entity is required for AI / ML model training or analysis;

[0141] receiving a third message sent by the second functional entity, where the third message is used to request access layer, non-access layer or application layer processing;

[0142] A fourth message sent by a fourth functional entity is received, where the fourth message is used to request access layer, non-access layer, or application layer control of the second functional entity.

[0143] In one implementation, the processor is specifically configured to perform the following operations:

[0144] Using the index information of the first AI / ML related information, obtaining the first AI / ML related information from a third functional entity; or,

[0145] The first AI / ML related information is determined according to locally stored AI / ML related information and index information of the first AI / ML related information, where the locally stored AI / ML related information is AI / ML related information obtained by the first functional entity from the third functional entity and stored locally, and the locally stored AI / ML related information includes index information of the first AI / ML related information.

[0146] In one implementation, the processor is specifically configured to perform the following operations:

[0147] receiving a fifth message sent by a fifth functional entity, where the fifth message carries index information of the first AI / ML related information and / or information of the third functional entity, and the fifth message is used to request switching or to provide terminal context;

[0148] obtaining the first AI / ML related information from the third functional entity using the index information of the first AI / ML related information and / or the information of the third functional entity;

[0149] The second functional entity is a second terminal, the first functional entity is a functional entity currently serving the second functional entity, and the fifth functional entity is a functional entity that previously served the second functional entity.

[0150] In one implementation, the processor is further configured to perform the following operations:

[0151] Sending a sixth message to the third functional entity, where the sixth message is used to request a subscription to the first AI / ML related information of the second functional entity;

[0152] Receive index information of the first AI / ML related information sent by the third functional entity.

[0153] In one implementation, the processor is further configured to perform the following operations:

[0154] Send index information of the first AI / ML related information to the second functional entity.

[0155] In one implementation, the first AI / ML related information is the first data information, and the processor is specifically configured to perform the following operations:

[0156] Using the first data information to perform AI / ML model training to obtain a second AI / ML model; or using the first data information to perform analysis to obtain second analysis information;

[0157] Use the second AI / ML model or the second analysis information to communicate with the second functional entity.

[0158] In one implementation, the first AI / ML related information is first AI / ML model information, and the processor is specifically configured to perform the following operations:

[0159] Determining a first AI / ML model according to the first AI / ML model information;

[0160] Use the first AI / ML model to communicate with the second functional entity.

[0161] In one implementation, the processor is specifically configured to perform the following operations:

[0162] performing access layer processing with the second functional entity;

[0163] The first functional entity and the second functional entity meet one of the following conditions:

[0164] The first functional entity is a first access network device, and the second functional entity is a second terminal;

[0165] The first functional entity is a first terminal, and the second functional entity is a second terminal;

[0166] The first functional entity is a first terminal, and the second functional entity is a second access network device.

[0167] In one implementation, the processor is specifically configured to perform the following operations:

[0168] Performing non-access layer or application layer processing with the second functional entity;

[0169] The first functional entity and the second functional entity meet one of the following conditions:

[0170] The first functional entity is a first core network functional entity, and the second functional entity is a second terminal;

[0171] The first functional entity is a first terminal, and the second functional entity is a second terminal;

[0172] The first functional entity is a first terminal, and the second functional entity is a second core network functional entity.

[0173] In a sixth aspect, an embodiment of the present application provides a communication device, applied to a second functional entity, the device comprising a memory, a transceiver, a processor,

[0174] The memory is used to store a computer program; the transceiver is used to send and receive data under the control of the processor; the processor is used to read the computer program in the memory and perform the following operations:

[0175] Sending first artificial intelligence AI / machine learning ML related information to the third functional entity, where the first AI / ML related information includes at least one of the following: first data information for AI / ML model training or analysis, first AI / ML model information, and first analysis information;

[0176] receiving index information of the first AI / ML related information sent by the third functional entity, where the index information of the first AI / ML related information is used to indicate the first AI / ML related information stored in the third functional entity by the second functional entity;

[0177] Use the first AI / ML related information to communicate with the first functional entity.

[0178] In one implementation, the processor is further configured to perform the following operations:

[0179] A first message is sent to the first functional entity, where the first message carries index information of the first AI / ML related information.

[0180] In one implementation, the processor is specifically configured to perform the following operations:

[0181] Performing access layer processing with the first functional entity;

[0182] The first functional entity and the second functional entity meet one of the following conditions:

[0183] The first functional entity is a first access network device, and the second functional entity is a second terminal;

[0184] The first functional entity is a first terminal, and the second functional entity is a second terminal;

[0185] The first functional entity is a first terminal, and the second functional entity is a second access network device.

[0186] In one implementation, the processor is specifically configured to perform the following operations:

[0187] Performing non-access layer or application layer processing with the first functional entity;

[0188] The first functional entity and the second functional entity meet one of the following conditions:

[0189] The first functional entity is a first core network functional entity, and the second functional entity is a second terminal;

[0190] The first functional entity is a first terminal, and the second functional entity is a second terminal;

[0191] The first functional entity is a first terminal, and the second functional entity is a second core network functional entity.

[0192] In a seventh aspect, an embodiment of the present application provides a non-transitory readable storage medium, wherein the non-transitory readable storage medium stores a computer program, and the computer program is used to enable a processor to execute the method described in the first aspect.

[0193] In an eighth aspect, an embodiment of the present application provides a non-transitory readable storage medium, wherein the non-transitory readable storage medium stores a computer program, and the computer program is used to enable a processor to execute the method described in the second aspect.

[0194] The embodiment of the present application provides a communication method, device and storage medium, in which the second functional entity sends first AI / ML related information to the third functional entity, and the first AI / ML related information includes at least one of the following: first data information, first AI / ML model information, and first analysis information for AI / ML model training or analysis; receiving index information of the first AI / ML related information sent by the third functional entity, the index information of the first AI / ML related information is used to indicate the first AI / ML related information stored in the third functional entity by the second functional entity; the first functional entity obtains the index information of the first AI / ML related information of the second functional entity, obtains the first AI / ML related information according to the index information of the first AI / ML related information, and uses the first AI / ML related information to communicate with the second functional entity. The first functional entity can quickly obtain the first AI / ML related information by interacting with the second functional entity and the third functional entity, thereby improving the accuracy and real-time performance of its communication processing with the second functional entity.

[0195] It should be understood that the contents described in the above summary of the invention are not intended to limit the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0196] In order to more clearly illustrate the technical solutions in the present application or the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0197] Figure 1 A schematic diagram of the data collection, model training and inference process of the access network in the related technology;

[0198] Figure 2 A schematic diagram of an architecture of a communication system provided in an embodiment of the present application;

[0199] Figure 3 Another schematic diagram of the architecture of the communication system provided in the embodiment of the present application;

[0200] Figure 4 Schematic diagram of the communication method provided in the embodiment of the present application Figure 1 ;

[0201] Figure 5 Schematic diagram of the communication method provided in the embodiment of the present application Figure 2 ;

[0202] Figure 6Schematic diagram of the communication method provided in the embodiment of the present application Figure 3 ;

[0203] Figure 7 Schematic diagram of the communication method provided in the embodiment of the present application Figure 4 ;

[0204] Figure 8 Schematic diagram of the communication method provided in the embodiment of the present application Figure 5 ;

[0205] Fig. 9 Schematic diagram of the communication method provided in the embodiment of the present application Figure 6 ;

[0206] Fig.10 Schematic diagram of the communication method provided in the embodiment of the present application Figure 7 ;

[0207] Fig.11 Schematic diagram of the communication method provided in the embodiment of the present application Figure 8 ;

[0208] Fig.12 Schematic diagram of the communication method provided in the embodiment of the present application Figure 9 ;

[0209] Fig.13 A schematic diagram of the structure of a communication device 1300 provided in an embodiment of the present application;

[0210] Fig.14 A schematic diagram of the structure of a communication device 1400 provided in an embodiment of the present application;

[0211] Fig.15 A schematic diagram of the structure of a communication device 1500 provided in an embodiment of the present application;

[0212] Fig.16 A schematic diagram of the structure of a communication device 1600 provided in an embodiment of the present application. DETAILED DESCRIPTION

[0213] In the embodiments of the present invention, the term "and / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent three situations: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the associated objects before and after are in an "or" relationship.

[0214] In the embodiments of the present application, the term "plurality" refers to two or more than two, and other quantifiers are similar.

[0215] The terms "first", "second", etc. in the embodiments of the present application are only used for illustration and distinction of the described objects. There is no distinction in order, nor does it indicate a special limitation on the number of objects in the embodiments of the present application, and cannot constitute any limitation on the embodiments of the present application.

[0216] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0217] The embodiments of the present application provide a communication method, an apparatus, and a storage medium for improving the accuracy and real-time performance of communication processing between a first functional entity and a second functional entity.

[0218] Among them, the method and the device are based on the same application concept. Since the method and the device solve the problem in a similar principle, the implementation of the device and the method can refer to each other, and the repeated parts will not be repeated.

[0219] The technical solution provided in the embodiment of the present application can be applicable to a variety of systems, especially 5G systems. For example, the applicable system can be a global system of mobile communication (GSM) system, a code division multiple access (CDMA) system, a wideband code division multiple access (WCDMA) general packet radio service (GPRS) system, a long term evolution (LTE) system, a LTE frequency division duplex (FDD) system, a LTE time division duplex (TDD) system, an advanced long term evolution (LTE-A) system, a universal mobile telecommunication system (UMTS), a world-wide interoperability for microwave access (WiMAX) system, a 5G new radio (NR) system, etc. These various systems include terminal equipment and network equipment. The system may also include a core network part, such as an evolved packet system (EPS), a 5G system (5GS), etc.

[0220] The terminal involved in the embodiment of the present application may be a device that provides voice and / or data connectivity to a user, a handheld device with a wireless connection function, or other processing devices connected to a wireless modem. In different systems, the name of the terminal may also be different. For example, in a 5G system, the terminal may be called a user equipment (UE). A wireless terminal can communicate with one or more core networks (CN) via a radio access network (RAN). The wireless terminal device may be a mobile terminal device, such as a mobile phone (or a "cellular" phone) and a computer with a mobile terminal device. For example, it may be a portable, pocket-sized, handheld, computer-built-in or vehicle-mounted mobile device that exchanges language and / or data with a wireless access network. For example, personal communication service (PCS) phones, cordless phones, session initiation protocol (SIP) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs) and other devices. The wireless terminal device may also be referred to as a system, a subscriber unit, a subscriber station, a mobile station, a mobile station, a remote station, an access point, a remote terminal device, an access terminal device, a user terminal device, a user agent, and a user device, but is not limited in the embodiments of the present application.

[0221] The access network equipment involved in the embodiments of the present application may also be referred to as wireless access network equipment, or as an access network functional entity, which can provide the function of accessing the communication network for authorized users in a specific area, and may specifically include wireless network equipment in the third generation partnership project (3GPP) network, or may include access points in non-3GPP networks. The access network equipment can be responsible for functions such as wireless resource management, quality of service (QoS) management, data compression and encryption on the air interface side. The access network equipment provides access services for the terminal, and then completes the forwarding of control signals and user data between the terminal and the core network. The access network device involved in the embodiments of the present application may be a device (base transceiver station, BTS) in the global system for mobile communications (global system for mobile communications, GSM) or code division multiple access (code division multiple access, CDMA), or a device (NodeB) in wide-band code division multiple access (WCDMA), or an evolutionary device (evolutional Node B, eNB or e-NodeB) in the long term evolution (long term evolution, LTE) system, a 5G base station (gNB) in the 5G network architecture (next generation system), or a home evolved node B (home evolved node B, HeNB), a relay node, a home base station (femto), a pico base station (pico), etc., which is not limited in the embodiments of the present application. In some network structures, the access network device may include a centralized unit (CU) node and a distributed unit (DU) node, and the centralized unit and the distributed unit may also be arranged geographically separately.

[0222] Combine the following Figure 2 The communication scenario of this application is described. Figure 2 A schematic diagram of the architecture of a communication system provided in an embodiment of the present application.

[0223] like Figure 2As shown in the figure, the architecture may include terminals, access network equipment, core network functional entities and data networks (DN). Among them, terminals, access network equipment and core network functional entities are the main parts of the architecture. Logically, they can be divided into two parts: user plane and control plane. The control plane is responsible for the management of mobile networks, and the user plane is responsible for the transmission of service data.

[0224] Core network function entity, also known as core network element, or core network equipment. As an example, the core network function entity may include any of the following: network data analytics function (NWDAF) entity, policy control function (PCF) entity, application function (AF) entity, access and mobility management function (AMF) entity, session management function (SMF) entity, network exposure function (NEF) entity, user plane function (UPF) entity, unified data repository (UDR) entity, network slice selection function (NSSF) entity, authentication server function (AUSF) entity, unified data management (UDM) entity, network function database function (NRF) entity, OAM entity.

[0225] The NWDAF entity can use the data provided by the core network functional entities (such as AMF entity, SMF entity, UPF entity, PCF entity, NEF entity, AF entity) and the data of the terminal application as input data to train the AI / ML model, and use the input data and the AI / ML model to perform network data analysis to obtain analysis information (including statistical and / or predictive information) on the behavior or performance of the terminal or core network. The core network functional entity controls the core network and the terminal based on the analysis information (including statistical and / or predictive information) provided by the NWDAF entity, for example, determining the service quality of the session data flow, selecting the core network functional entity of the service and the terminal, etc.

[0226] The NWDAF entity and the analytics data repository function (DCCF) entity can store input data, AI / ML models and / or analysis information to the analytics data repository function (ADRF) entity, and request input data, AI / ML models and / or analysis information from the ADRF entity.

[0227] Figure 3 Another schematic diagram of the architecture of a communication system provided in an embodiment of the present application. Figure 3 is Figure 2 The detailed architecture is determined based on the

[0228] In related technologies, the data collection, model training and inference process of the access network can be as follows: Figure 1 As shown in the figure, since OAM entities are mainly used for configuration scheduling and performance maintenance management of network resources, and do not directly participate in the control of terminals and networks (such as the control of terminal mobility and sessions), the terminal and network control-related models trained and provided by OAM may not meet the real-time requirements and are inconsistent with the data analysis architecture of the existing core network. In addition, the interface between OAM entities and access network equipment is not standardized, resulting in Figure 1 The process shown is difficult to implement.

[0229] Based on the problems in the prior art, the present application proposes the following technical concept: the first functional entity improves the accuracy and real-time performance of communication processing with the second functional entity by quickly acquiring first AI / ML related information.

[0230] The communication method provided by the present application is introduced below in conjunction with specific embodiments.

[0231] Figure 4 Schematic diagram of the communication method provided in the embodiment of the present application Figure 1 .like Figure 4 As shown, the method includes:

[0232] S401. The second functional entity sends first AI / ML related information to the third functional entity.

[0233] In other words, the third functional entity receives the first AI / ML related information sent by the second functional entity.

[0234] The first AI / ML related information is AI / ML related information of the second functional entity.

[0235] The first AI / ML related information includes at least one of the following: first data information for AI / ML model training or analysis, first AI / ML model information, and first analysis information.

[0236] The first data information may include data (referred to as first data) used by the second functional entity for AI / ML model training or analysis.

[0237] The first AI / ML model information may include information of the AI / ML model of the second functional entity.

[0238] The first analysis information may include analysis information on the behavior or performance of the second functional entity obtained by the second functional entity performing network data analysis using input data and an AI / ML model.

[0239] The first analysis information may include statistical information and / or predictive information.

[0240] The second functional entity may be a terminal, an access network device or a core network functional entity.

[0241] The third functional entity may be an ADRF entity.

[0242] When the second functional entity is a terminal, it can send the first AI / ML related information to the third functional entity through a core network functional entity (eg, AF entity, AMF entity) and / or an access network device.

[0243] For example, the terminal may send its first AI / ML related information to the AF entity through the user plane (application layer), and the AF entity then sends the first AI / ML related information to the third functional entity.

[0244] As another example, the terminal may send the first AI / ML related information to the AMF entity through a non-access stratum (NAS) message, and the AMF entity may then send the first AI / ML related information to the third functional entity.

[0245] In another example, the terminal may send the first AI / ML related information to the third functional entity through the access network device.

[0246] In another example, the terminal may send the first AI / ML related information to the AMF entity through the access network device, and the AMF entity may then send the first AI / ML related information to the third functional entity.

[0247] When the second functional entity is an access network device or a core network functional entity (e.g., an AMF entity, an SMF entity, a UPF entity, a PCF entity, a NEF entity, an AF entity, a NWDAF entity, a DCCF entity), the second functional entity can directly send its first AI / ML related information to the third functional entity.

[0248] In a possible implementation, when the second functional entity sends the first AI / ML related information to the third functional entity, it may also send the first description information to the third functional entity. The first description information includes at least one of the following: description information of the first data, description information of the first AI / ML model, and first analysis description information.

[0249] The description information of the first data may include at least one of the following: data collection time (segment), sampling frequency, and data accuracy.

[0250] The model description information of the first AI / ML model may include at least one of the following: model generation time, model identification, model type (indicating what function / feature the model is used for, such as a model of terminal mobility characteristics or mobility trajectory, a model of terminal communication characteristics or communication performance, a terminal energy consumption or energy efficiency model), and model accuracy (characterizing the accuracy of the analysis results obtained using the model).

[0251] The first analysis description information may include at least one of the following: generation time of the first analysis information, statistics or predictions, analysis identification (indicating what kind of function / characteristic the analysis information is, such as analysis information of terminal movement characteristics or movement trajectory, analysis information of terminal communication characteristics or communication performance, terminal energy consumption or energy efficiency analysis information), confidence level (applicable to prediction information), applicable duration, usage area, etc.

[0252] If the second functional entity simultaneously sends the first AI / ML related information and the first description information to the third functional entity, the first AI / ML related information includes the first data information, and the first description information includes the description information of the first data; if the first AI / ML related information includes the first AI / ML model information, the first description information includes the model description information of the first AI / ML model; if the first AI / ML related information includes the first analysis information, the first description information includes the first analysis description information.

[0253] After receiving the first AI / ML related information, the third functional entity stores the first AI / ML related information, determines index information of the first AI / ML related information, and executes S402.

[0254] S402. The third functional entity sends index information of the first AI / ML related information to the second functional entity.

[0255] In other words, the second functional entity receives index information of the first AI / ML related information sent by the third functional entity.

[0256] When the second functional entity is a terminal, the third functional entity may send index information of the first AI / ML related information to the terminal through a core network functional entity (eg, an AF entity, an AMF entity) or an access network device.

[0257] For example, if the terminal sends the first AI / ML related information to the third functional entity through the AF entity, the third functional entity can send the index information of the first AI / ML related information to the AF entity, and the AF entity sends the index information of the first AI / ML related information to the terminal through the user plane (application layer).

[0258] As another example, if the terminal sends the first AI / ML related information to the third functional entity through the AMF entity, the third functional entity can send the index information of the first AI / ML related information to the AMF entity, and the AMF entity sends the index information of the first AI / ML related information to the terminal through a NAS message.

[0259] As another example, if the terminal sends the first AI / ML related information to the third functional entity through the access network device, the third functional entity may send the index information of the first AI / ML related information to the access network device, and the access network device sends the index information of the first AI / ML related information to the terminal.

[0260] As another example, if the terminal sends the first AI / ML related information to the third functional entity through the access network device and the AMF entity, the third functional entity can send the index information of the first AI / ML related information to the access network device through the AMF entity, and the access network device sends the index information of the first AI / ML related information to the terminal.

[0261] When the second functional entity is an access network device or a core network functional entity (e.g., an AMF entity, an SMF entity, a UPF entity, a PCF entity, a NEF entity, an AF entity, a NWDAF entity, a DCCF entity), the third functional entity can directly send the index information of its first AI / ML related information to the second functional entity.

[0262] A reference point or a service-based interface may be defined between the access network device and the third functional entity so that the access network device and the third functional entity can communicate directly.

[0263] The index information of the first AI / ML related information may include an index value or identifier of each item of information in the first AI / ML related information.

[0264] Exemplarily, if the first AI / ML related information is the first data information, the index information is the index value of the first data information; if the first AI / ML related information is the first data information and the first AI / ML model information, the index information is the index identifier of the first data information and the index value of the first AI / ML model information; if the first is the first data information, the first AI / ML model information and the first analysis information, the index information is the index value of the first data information, the index value of the first AI / ML model information and the index value of the first analysis information.

[0265] S403. The first functional entity obtains index information of first AI / ML related information.

[0266] The index information of the first AI / ML related information may be used to indicate that the second functional entity stores the first AI / ML related information in the third functional entity.

[0267] The second functional entity may be a terminal, an access network device or a core network functional entity.

[0268] The first functional entity and the second functional entity meet one of the following conditions:

[0269] When the first functional entity is a first access network device, the second functional entity may be a second terminal;

[0270] When the first functional entity is a first terminal, the second functional entity may be a second terminal;

[0271] When the first functional entity is a first terminal, the second functional entity may be a second access network device;

[0272] When the first functional entity is a first core network functional entity, the second functional entity may be a second terminal;

[0273] When the first functional entity is a first terminal, the second functional entity may be a second core network functional entity.

[0274] S404. The first functional entity obtains first AI / ML related information according to index information of the first AI / ML related information.

[0275] In one possible implementation, if the first functional entity does not store the first AI / ML related information locally, the first functional entity may use the index information of the first AI / ML related information to obtain the first AI / ML related information from the third functional entity; if the AI / ML related information stored locally by the first functional entity includes the first AI / ML related information and its index information, the first functional entity may determine the first AI / ML related information based on the locally stored AI / ML related information and the index information of the first AI / ML related information; wherein the locally stored AI / ML related information is the AI / ML related information obtained by the first functional entity from the third functional entity and stored locally.

[0276] In a possible implementation manner, the first AI / ML related information may be obtained from the third functional entity using the index information of the first AI / ML related information in the following manner:

[0277] The first functional entity sends a request message to the third functional entity, where the request message carries index information of the first AI / ML related information; the third functional entity sends a reply message to the first functional entity based on the index information of the first AI / ML related information, where the reply message carries the file address of the first AI / ML related information; the first functional entity obtains the first AI / ML related information based on the file address of the first AI / ML related information.

[0278] The first functional entity can use the first AI / ML related information to perform local AI calculation, processing and / or decision-making, for example, performing access and mobility management based on terminal mobility characteristics (such as paging, switching, redirection, guiding the terminal to perform cell reselection, roaming guidance, slice reselection, etc.); performing data bearer resource scheduling, load balancing and / or energy efficiency control based on terminal communication characteristics; selecting a target cell and / or target access network equipment based on access network performance or load or energy consumption characteristics, selecting a core network functional entity (such as an AMF entity, an SMF entity) or a slice instance based on core network performance or load or energy consumption characteristics, etc.

[0279] S405. The first functional entity uses the first AI / ML related information to perform communication processing with the second functional entity.

[0280] In one possible implementation, when the first AI / ML related information is the first data information, the first functional entity may use the first data information to perform AI / ML model training to obtain a second AI / ML model; or, use the first data information for analysis to obtain second analysis information; and use the second AI / ML model or the second analysis information to communicate and process with the second functional entity.

[0281] In one possible implementation, when the first AI / ML related information is first AI / ML model information, the first functional entity can determine the first AI / ML model based on the first AI / ML model information, and use the first AI / ML model to perform communication processing with the second functional entity.

[0282] In a possible implementation, when the first AI / ML related information is first analysis information, the first functional entity directly uses the first analysis information to perform communication processing with the second functional entity.

[0283] Communication processing may include access layer processing (such as physical layer processing, wireless resource control, etc.), non-access layer processing (such as terminal access and mobility management, session management, policy control, etc.) or application layer processing (such as establishing, modifying or releasing application layer connections or sessions with terminals, adjusting terminal applications or service parameters, etc.).

[0284] When the first functional entity and the second functional entity perform access layer processing, the first functional entity and the second functional entity meet one of the following conditions:

[0285] The first functional entity is a first access network device, and the second functional entity is a second terminal;

[0286] The first functional entity is a first terminal, and the second functional entity is a second terminal;

[0287] The first functional entity is a first terminal, and the second functional entity is a second access network device.

[0288] Specifically, the first functional entity performs access layer communication processing with the second functional entity through the first AI / ML related information, including: for example, when the first AI / ML related information is the physical layer coding and decoding model information of the second functional entity, the first functional entity uses the physical layer coding and decoding model to perform physical layer encoding on the data sent to the second functional entity, and the second functional entity uses the physical layer coding and decoding model to perform physical layer decoding on the data received from the first functional entity. For another example, when the first AI / ML related information is the communication service related data of the second functional entity (such as the data transmission rate and transmission interval of the second terminal at a specific time or in a specific area) or related analysis information (such as the prediction information of the data transmission rate and transmission interval of the second terminal in the future at a specific time or in a specific area), the first functional entity can determine the resource allocation and scheduling strategy for communication with the second functional entity based on the first AI / ML related information, thereby allocating and configuring wireless resources based on this strategy to communicate with the second functional entity.

[0289] When the first functional entity and the second functional entity perform non-access layer or application layer processing, the first functional entity and the second functional entity meet one of the following conditions:

[0290] The first functional entity is a first core network functional entity, and the second functional entity is a second terminal;

[0291] The first functional entity is a first terminal, and the second functional entity is a second terminal;

[0292] The first functional entity is a first terminal, and the second functional entity is a second core network functional entity.

[0293] Specifically, the first functional entity performs non-access layer or application layer communication processing with the second functional entity through the first AI / ML related information, including: for example, when the first AI / ML related information is the mobility (such as moving range, moving trajectory, moving speed) related data, model or analysis information of the second functional entity, the first functional entity can determine the preferred network and / or access technology (such as a mobile communication network using satellite access, or proximity service communication (i.e. direct or relay communication between adjacent terminals, not via the network)) when communicating with the second functional entity based on the information, and use the preferred network and / or access technology to communicate with the second terminal. For another example, when the first AI / ML related information is the communication (such as idle, busy or congested service time period) related data, model or analysis information of the second functional entity, the first functional entity can determine the time period for establishing a connection or session with the second functional entity based on the information, thereby avoiding connection or service establishment failure and improving service experience and performance.

[0294] exist Figure 4 In the illustrated embodiment, the second functional entity sends first AI / ML related information to the third functional entity, and the first AI / ML related information includes at least one of the following: first data information, first AI / ML model information, and first analysis information for AI / ML model training or analysis; receives index information of the first AI / ML related information sent by the third functional entity, and the index information of the first AI / ML related information is used to indicate the first AI / ML related information stored in the third functional entity by the second functional entity; the first functional entity obtains the index information of the first AI / ML related information of the second functional entity, obtains the first AI / ML related information according to the index information of the first AI / ML related information, and uses the first AI / ML related information to communicate and process with the second functional entity. The first functional entity can quickly obtain the first AI / ML related information by interacting with the second functional entity and the third functional entity, thereby improving the accuracy and real-time performance of its communication and processing with the second functional entity.

[0295] exist Figure 4 Based on the illustrated embodiment, the following describes in detail how the functional entities interact with each other to obtain index information of the first AI / ML related information in different situations.

[0296] Figure 5 Schematic diagram of the communication method provided in the embodiment of the present application Figure 2 .like Figure 5 As shown, the method includes:

[0297] S501. The second functional entity sends first AI / ML related information to the third functional entity.

[0298] S502. The third functional entity determines index information of first AI / ML related information.

[0299] S503. The third functional entity sends index information of the first AI / ML related information to the second functional entity.

[0300] It should be noted that the execution process of S501 to S503 can refer to the execution process of S401 to S402, and will not be repeated here.

[0301] S504. The second functional entity sends a first message to the first functional entity, where the first message carries index information of first AI / ML related information.

[0302] In other words, the first functional entity receives the first message sent by the second functional entity.

[0303] The first message may be used to request the first functional entity to perform communication processing with the second functional entity using the first AI / ML related information corresponding to the index information.

[0304] In a possible implementation manner, the first message may be a reply message or a request message.

[0305] Exemplarily, the first may be an air interface reply message or an air interface request message sent by the access network device to the terminal, or a reply or request message related to terminal access and mobility management sent by the access network device to the AMF entity, or a reply or request message related to terminal session management sent by the access network device to the SMF entity, or a reply or request message related to terminal policy control sent by the access network device to the PCF entity.

[0306] If the first functional entity has previously sent a request message or a command message related to the first AI / ML related information to the second functional entity, the second functional entity may send a reply message (first message) to the first functional entity so that the first functional entity uses the first AI / ML related information to communicate with the second functional entity.

[0307] If the first functional entity has not previously sent a request message or command message related to the first AI / ML related information to the second functional entity, the second functional entity may send a request message (first message) to the first functional entity, where the request message carries index information of the first AI / ML related information; if the first functional entity confirms that the first AI / ML related information corresponding to the index information will be used for communication processing, a confirmation message or a reply message may be sent to the second functional entity, where the confirmation message or the reply message carries the index information of the first AI / ML related information, so as to confirm to the second functional entity that the first AI / ML related information will be used for communication processing.

[0308] S505. The first functional entity obtains first AI / ML related information according to index information of the first AI / ML related information.

[0309] It should be noted that the execution process of S505 can refer to the execution process of S404, which will not be repeated here.

[0310] S506. The first functional entity sends index information of the first AI / ML related information to the second functional entity.

[0311] In other words, the second functional entity receives index information of the first AI / ML related information sent by the first functional entity.

[0312] The first functional entity sending the index information of the first AI / ML related information to the second functional entity may be for confirming to the second functional entity that it will use the first AI / ML related information corresponding to the index information for communication processing.

[0313] S507: The first functional entity uses the first AI / ML related information to perform communication processing with the second functional entity.

[0314] It should be noted that the execution process of S507 can refer to the execution process of S403, which will not be repeated here.

[0315] exist Figure 5 In the illustrated embodiment, the first functional entity obtains first AI / ML related information based on a request from the second functional entity, and performs communication processing with the second functional entity based on the first AI / ML related information, thereby improving the accuracy and real-time performance of the communication processing between the first functional entity and the second functional entity.

[0316] Figure 6 Schematic diagram of the communication method provided in the embodiment of the present application Figure 3 .like Figure 6 As shown, the method includes:

[0317] S601. The second functional entity sends first AI / ML related information to the third functional entity.

[0318] S602. The third functional entity determines index information of the first AI / ML related information.

[0319] S603. The third functional entity sends index information of the first AI / ML related information to the second functional entity.

[0320] It should be noted that the execution process of S601 to S603 can refer to the execution process of S401 to S402, and will not be repeated here.

[0321] S604. The first functional entity sends a second message to the second functional entity, where the second message is used to request first AI / ML related information.

[0322] In other words, the second functional entity receives the second message sent by the first functional entity.

[0323] The second message may carry the index information of the first AI / ML related information, or may not carry the index information of the first AI / ML related information.

[0324] S605. The second functional entity sends a first message to the first functional entity, where the first message carries index information of first AI / ML related information.

[0325] S606. The first functional entity obtains first AI / ML related information according to index information of the first AI / ML related information.

[0326] S607. The first functional entity sends index information of the first AI / ML related information to the second functional entity.

[0327] S608. The first functional entity uses the first AI / ML related information to perform communication processing with the second functional entity.

[0328] It should be noted that the execution process of S605 to S608 can refer to the execution process of S504 to S507, and will not be repeated here.

[0329] exist Figure 6 In the illustrated embodiment, the first functional entity actively requests to obtain first AI / ML related information, and communicates and processes with the second functional entity based on the first AI / ML related information, thereby improving the accuracy and real-time performance of the communication and processing between the first functional entity and the second functional entity.

[0330] Figure 7 Schematic diagram of the communication method provided in the embodiment of the present application Figure 4 .like Figure 7 As shown, the method includes:

[0331] S701. The second functional entity sends first AI / ML related information to the third functional entity.

[0332] S702. The third functional entity determines index information of the first AI / ML related information.

[0333] S703. The third functional entity sends index information of the first AI / ML related information to the second functional entity.

[0334] It should be noted that the execution process of S701 to S703 can refer to the execution process of S401 to S402, and will not be repeated here.

[0335] S704: The first functional entity sends a second message to the second functional entity based on the trigger condition.

[0336] In a possible implementation, the trigger condition may include any of the following:

[0337] 1) Determine the data or AI / ML model that requires the second functional entity for AI / ML model training or analysis.

[0338] That is, the first functional entity determines that the data of the second functional entity is needed to train the AI / ML model, or the first functional entity determines that the data of the second functional entity is needed for analysis, or the first functional entity determines that the AI / ML model of the second functional entity is needed to train the local AI / ML model of the first functional entity (such as federated learning, transfer learning), or the first functional entity determines that the AI / ML model of the second functional entity is needed for analysis.

[0339] 2) A third message sent by the second functional entity is received, where the third message is used to request access layer, non-access layer or application layer processing.

[0340] The third message may be an air interface message, such as an access request message or a measurement report message.

[0341] 3) A fourth message sent by a fourth functional entity is received, where the fourth message is used to request access layer, non-access layer or application layer control of the second functional entity.

[0342] For example, the fourth message may be a request or command message related to terminal access and mobility management sent by an AMF entity; it may also be a request or command message related to terminal session management sent by an SMF entity; it may also be a request or command message related to terminal policy (such as proximity service-related policy) control sent by a PCF entity.

[0343] S705. The second functional entity sends a first message to the first functional entity, where the first message carries index information of first AI / ML related information.

[0344] S706. The first functional entity obtains the first AI / ML related information according to the index information of the first AI / ML related information.

[0345] S707. The first functional entity sends index information of the first AI / ML related information to the second functional entity.

[0346] S708. The first functional entity uses the first AI / ML related information to perform communication processing with the second functional entity.

[0347] It should be noted that the execution process of S705 to S708 can refer to the execution process of S504 to S507, and will not be repeated here.

[0348] exist Figure 7 In the illustrated embodiment, the first functional entity actively requests to obtain first AI / ML related information based on a trigger condition, and communicates and processes with the second functional entity according to the first AI / ML related information, thereby improving the accuracy and real-time performance of the communication and processing between the first functional entity and the second functional entity.

[0349] Figure 8 Schematic diagram of the communication method provided in the embodiment of the present application Figure 5 .like Figure 8 As shown, the method includes:

[0350] S801. The first functional entity sends a sixth message to the third functional entity, where the sixth message is used to request to subscribe to first AI / ML related information of the second functional entity.

[0351] In other words, the third functional entity receives the sixth message sent by the first functional entity.

[0352] In a possible implementation manner, the sixth message may carry at least one of the following information:

[0353] 1) Identification information of the second functional entity.

[0354] When the second functional entity is a terminal, the identification information of the second functional entity may be the identification of one or more terminals, the terminal group identification or the information of a terminal that meets certain conditions, wherein the information of the terminal that meets certain conditions may be slice information or slice instance information (indicating all / any terminals served by a specified slice or slice instance), or area information (indicating all / any terminals in a specified area, and the specified area may be a tracking area, a cell area or a geographic area).

[0355] For example, if the identification information of the second functional entity is information of cell 1, it means that the first functional entity requests the third functional entity to subscribe to the first AI / ML related information of all terminals in cell 1.

[0356] 2) Subscription type.

[0357] The subscription type may be used to indicate the type of AI / ML related information subscription requested.

[0358] Subscription types can be divided into model data type, analysis data type, model type, and analysis information type.

[0359] For example, when the subscription type is a model data type, it means requesting to subscribe to data information used for AI / ML model training.

[0360] 3) Description of the AI / ML-related information requested for subscription.

[0361] The description information may include at least one of the following:

[0362] Data type (indicating what function / characteristics the terminal is related to, such as data on terminal movement characteristics or movement trajectory, data on terminal communication characteristics or communication performance, terminal energy consumption or energy efficiency data), data collection time (segment), data collection area, and data accuracy;

[0363] AI / ML model type (indicating what function / feature the model is used for, such as a model of terminal mobility characteristics or movement trajectory, a model of terminal communication characteristics or communication performance, or a model of terminal energy consumption or energy efficiency), model accuracy (characterizing the accuracy of the analysis results obtained using the model);

[0364] Analysis identification (indicating what kind of function / characteristic the analysis information is, such as analysis information of terminal mobility characteristics or mobility trajectory, analysis information of terminal communication characteristics or communication performance, terminal energy consumption or energy efficiency analysis information), analysis information confidence level (applicable to prediction information), analysis information applicability time, analysis information applicability area, etc.

[0365] 4) Information of the first functional entity.

[0366] By way of example, the information of the first functional entity may include an identifier or address of the first functional entity, a subscription association identifier, an address for receiving subscription information (or notification / report), and the like.

[0367] S802. The second functional entity sends first AI / ML related information to the third functional entity.

[0368] S803. The third functional entity determines index information of the first AI / ML related information.

[0369] S804. The third functional entity sends index information of the first AI / ML related information to the second functional entity.

[0370] It should be noted that the execution process of S902 to S904 can refer to the execution process of S401 to S402, and will not be repeated here.

[0371] S805. The third functional entity sends index information of the first AI / ML related information to the first functional entity.

[0372] In other words, the first functional entity receives index information of the first AI / ML related information sent by the third functional entity.

[0373] The third functional entity may send index information of the most recently stored first AI / ML related information to the first functional entity.

[0374] In a possible implementation, when the third functional entity sends index information of the first AI / ML related information to the first functional entity, it may also send first description information to the first functional entity. For the relevant description of the first description information, refer to S401 and will not be repeated here.

[0375] S806. The first functional entity sends a second message to the second functional entity, where the second message carries index information of the first AI / ML related information.

[0376] The second message may be used to instruct or request the second functional entity to use the first AI / ML related information corresponding to the index information to perform communication processing.

[0377] The first functional entity may send the second message to the second functional entity based on a trigger condition. For a description of the trigger condition, refer to S704 and will not be repeated here.

[0378] S807. The second functional entity sends a first message to the first functional entity, where the first message carries index information of first AI / ML related information.

[0379] The first message may be used to confirm that it will use the first AI / ML related information corresponding to the index information for communication processing.

[0380] S808. The first functional entity obtains the first AI / ML related information according to the index information of the first AI / ML related information.

[0381] S809. The first functional entity sends index information of the first AI / ML related information to the second functional entity.

[0382] S810. The first functional entity uses the first AI / ML related information to perform communication processing with the second functional entity.

[0383] It should be noted that the execution process of S808 to S810 can refer to the execution process of S505 to S507, and will not be repeated here.

[0384] exist Figure 8 In the illustrated embodiment, the first functional entity actively requests to obtain first AI / ML related information, and communicates and processes with the second functional entity based on the first AI / ML related information, thereby improving the accuracy and real-time performance of the communication and processing between the first functional entity and the second functional entity.

[0385] Fig. 9 Schematic diagram of the communication method provided in the embodiment of the present application Figure 6 .like Fig. 9 As shown, taking the second functional entity as a terminal and the first functional entity as an access network device as an example, the method includes:

[0386] S901. The terminal sends first AI / ML related information to a third functional entity.

[0387] S902. The third functional entity determines index information of the first AI / ML related information.

[0388] S903. The third functional entity sends index information of the first AI / ML related information to the terminal.

[0389] It should be noted that the execution process of S901 to S903 can refer to the execution process of S401 to S402, and will not be repeated here.

[0390] S904. The fifth functional entity sends a fifth message to the first functional entity. The fifth message carries index information of the first AI / ML related information and / or information of the third functional entity. The fifth message is used to request switching of the access network device.

[0391] The fifth functional entity is the access network device that previously served the terminal, and may also be referred to as a source access network device.

[0392] The first functional entity is an access network device that will serve the terminal, and may also be referred to as a target access network device.

[0393] The fifth functional entity may determine to initiate a handover according to the measurement report of the terminal and the analysis information of the mobility characteristics of the terminal.

[0394] In addition to carrying switching target cell information, wireless resource information of the terminal in the fifth functional entity and other switching related information, the fifth message also carries the first description information. For the relevant description of the first description information, please refer to S401 and will not be repeated here.

[0395] The information of the third functional entity may include an identifier, an address, and routing information (eg, a fully qualified domain name (FQDN) or a uniform resource identifier (URI)) of the third functional entity.

[0396] S905. The first functional entity sends a handover request confirmation message to the fifth functional entity.

[0397] S906. The terminal switches from the fifth functional entity to the first functional entity.

[0398] S907. The first functional entity uses index information of the first AI / ML related information and / or information of the third functional entity to obtain the first AI / ML related information from the third functional entity.

[0399] If the fifth message carries information about the third functional entity, the first functional entity can determine the third functional entity based on the information about the third functional entity, and then use the index information of the first AI / ML related information to obtain the first AI / ML related information from the third functional entity. The acquisition method can refer to the relevant description in S404 and will not be repeated here.

[0400] If the fifth message does not carry the information of the third functional entity, the first functional entity may determine the third functional entity by other means.

[0401] S908. The first functional entity sends index information of first AI / ML related information to the terminal.

[0402] S909. The first functional entity uses the first AI / ML related information to perform communication processing with the terminal.

[0403] It should be noted that the execution process of S908 to S909 can refer to the execution process of S506 to S507, and will not be repeated here.

[0404] exist Fig. 9 In the illustrated embodiment, when the terminal switches the access network device, the source access network device provides the target access network device with the index information of the first AI / ML related information and / or the information of the third functional entity. The target access network device quickly obtains the first AI / ML related information from the third functional entity according to the index information of the first AI / ML related information, and performs communication processing with the terminal according to the first AI / ML related information, thereby improving the accuracy and real-time performance of the communication processing between the access network device and the terminal.

[0405] Fig.10 Schematic diagram of the communication method provided in the embodiment of the present application Figure 7 .like Fig.10As shown, taking the second functional entity as a terminal and the first functional entity as an access network device as an example, the method includes:

[0406] S1001. The terminal sends first AI / ML related information to a third functional entity.

[0407] S1002. The third functional entity determines index information of the first AI / ML related information.

[0408] S1003. The third functional entity sends index information of the first AI / ML related information to the terminal.

[0409] S1004. The fifth functional entity sends a fifth message to the first functional entity. The fifth message carries index information of the first AI / ML related information and / or information of the third functional entity. The fifth message is used to request switching of the access network device.

[0410] S1005. The first functional entity sends a switching request confirmation message to the fifth functional entity.

[0411] S1006. The terminal switches from the fifth functional entity to the first functional entity.

[0412] It should be noted that the execution process of S1001 to S1006 can refer to the execution process of S901 to S906, which will not be repeated here.

[0413] S1007. The first functional entity sends a sixth message to the third functional entity, where the sixth message is used to request a subscription to first AI / ML related information.

[0414] If the fifth message carries information about the third functional entity, the first functional entity may determine the third functional entity according to the information about the third functional entity, and send the sixth message to the third functional entity.

[0415] If the fifth message does not carry the information of the third functional entity, the first functional entity may determine the third functional entity by other means.

[0416] The content carried in the sixth message can be found in the description of S801 and will not be repeated here.

[0417] S1008. The third functional entity sends index information of the first AI / ML related information to the first functional entity.

[0418] The third functional entity may send index information of the most recently stored first AI / ML related information to the first functional entity.

[0419] That is, the index information of the first AI / ML related information sent by the third functional entity to the first functional entity may be the same as or different from the index information of the first AI / ML related information carried by the fifth message; when the two are different, the index information of the first AI / ML related information sent by the third functional entity to the first functional entity may be used.

[0420] S1009. The first functional entity uses index information of the first AI / ML related information to obtain the first AI / ML related information from the third functional entity.

[0421] S1010. The first functional entity sends index information of first AI / ML related information to the terminal.

[0422] S1011. The first functional entity uses the first AI / ML related information to perform communication processing with the terminal.

[0423] It should be noted that the execution process of S1009 to S1011 can refer to the execution process of S907 to S909, which will not be repeated here.

[0424] exist Fig.10 In the illustrated embodiment, when the terminal switches the access network device, the source access network device provides the target access network device with the index information of the first AI / ML related information and / or the information of the third functional entity. The target access network device can subscribe to the first AI / ML related information from the third functional entity according to the information of the third functional entity, and can quickly obtain the latest first AI / ML related information from the third functional entity according to the index information of the latest first AI / ML related information fed back by the third functional entity, and communicate and process with the terminal according to the latest first AI / ML related information, thereby improving the accuracy and real-time performance of the communication and processing between the access network device and the terminal.

[0425] Fig.11 Schematic diagram of the communication method provided in the embodiment of the present application Figure 8 .like Fig.11 As shown, taking the second functional entity as a terminal and the first functional entity as an access network device as an example, the method includes:

[0426] S1101. The terminal sends first AI / ML related information to a third functional entity.

[0427] S1102. The third functional entity determines index information of the first AI / ML related information.

[0428] S1103. The third functional entity sends index information of the first AI / ML related information to the terminal.

[0429] It should be noted that the execution process of S1101 to S1103 can refer to the execution process of S401 to S402, and will not be repeated here.

[0430] S1104. The terminal sends a connection recovery request message to the first functional entity.

[0431] The terminal is in a radio resource control (RRC) inactive state.

[0432] S1105. The first functional entity sends a request message for obtaining a terminal context to the fifth functional entity.

[0433] The fifth functional entity is the access network device that previously served the terminal, and may also be referred to as a source access network device.

[0434] The first functional entity is an access network device currently serving the terminal, and may also be referred to as a target access network device.

[0435] S1106. The fifth functional entity sends a fifth message to the first functional entity. The fifth message carries index information of the first AI / ML related information and / or information of the third functional entity. The fifth message is used to provide terminal context.

[0436] In addition to carrying the context of the terminal (terminal capabilities, information about sessions established by the terminal, and other information), the fifth message also carries the first description information. For the relevant description of the first description information, see S401, which will not be repeated here.

[0437] S1107. The first functional entity sends a connection recovery confirmation message to the terminal.

[0438] S1108. The first functional entity uses index information of the first AI / ML related information and / or information of the third functional entity to obtain the first AI / ML related information from the third functional entity.

[0439] S1109. The first functional entity sends index information of first AI / ML related information to the terminal.

[0440] S1110. The first functional entity uses the first AI / ML related information to perform communication processing with the terminal.

[0441] It should be noted that the execution process of S1108 to S1110 can refer to the execution process of S907 to S909, which will not be repeated here.

[0442] exist Fig.11In the illustrated embodiment, during the connection recovery process, the source access network device provides the target access network device with index information of the first AI / ML related information and / or information of the third functional entity. The target access network device quickly obtains the first AI / ML related information from the third functional entity according to the index information of the first AI / ML related information, and performs communication processing with the terminal according to the first AI / ML related information, thereby improving the accuracy and real-time performance of communication processing between the access network device and the terminal.

[0443] Fig.12 Schematic diagram of the communication method provided in the embodiment of the present application Figure 9 .like Fig.12 As shown, taking the second functional entity as a terminal and the first functional entity as an access network device as an example, the method includes:

[0444] S1201. The terminal sends first AI / ML related information to a third functional entity.

[0445] S1202. The third functional entity determines index information of the first AI / ML related information.

[0446] S1203. The third functional entity sends index information of the first AI / ML related information to the terminal.

[0447] S1204. The terminal sends a connection recovery request message to the first functional entity.

[0448] S1205. The first functional entity sends a request message for obtaining a terminal context to the fifth functional entity.

[0449] S1206. The fifth functional entity sends a fifth message to the first functional entity. The fifth message carries index information of the first AI / ML related information and / or information of the third functional entity. The fifth message is used to provide terminal context.

[0450] S1207. The first functional entity sends a connection recovery confirmation message to the terminal.

[0451] It should be noted that the execution process of S1201 to S1207 can refer to the execution process of S1101 to S1107, which will not be repeated here.

[0452] S1208. The first functional entity sends a sixth message to the third functional entity, where the sixth message is used to request to subscribe to the first AI / ML related information of the second functional entity.

[0453] S1209. The third functional entity sends index information of the first AI / ML related information to the first functional entity.

[0454] S1210. The first functional entity uses index information of the first AI / ML related information to obtain the first AI / ML related information from the third functional entity.

[0455] S1211. The first functional entity sends index information of first AI / ML related information to the terminal.

[0456] S1212. The first functional entity uses the first AI / ML related information to perform communication processing with the terminal.

[0457] It should be noted that the execution process of S1208 to S1212 can refer to the execution process of S1007 to S1011, and will not be repeated here.

[0458] exist Fig.12 In the illustrated embodiment, during the connection recovery process, the source access network device provides the target access network device with index information of the first AI / ML related information and / or information of the third functional entity. The target access network device can subscribe to the first AI / ML related information from the third functional entity based on the information of the third functional entity, and can quickly obtain the latest first AI / ML related information from the third functional entity based on the index information of the latest first AI / ML related information fed back by the third functional entity, and communicate and process with the terminal based on the latest first AI / ML related information, thereby improving the accuracy and real-time performance of communication and processing between the access network device and the terminal.

[0459] To facilitate understanding, several specific examples are given below to illustrate the various steps in the communication method of the present application.

[0460] Example 1: Take the access network device as the first functional entity, the terminal as the second functional entity, and the ADRF as the third functional entity as an example.

[0461] S1. The access network device sends a sixth message to the ADRF entity. The sixth message is used to request subscription to first AI / ML related information of the terminal. The first AI / ML related information includes at least one of the following: terminal data, terminal AI / ML model, and terminal analysis information.

[0462] The sixth message carries the following information:

[0463] a) Terminal identification, which may include: identification of one or more terminals, terminal group identification, information of terminals that meet certain conditions (for example, slice or slice instance information, indicating all / any terminals served by a specified slice or slice instance; or area information (for example, tracking area, cell or geographic area), indicating all / any terminals in a specified area).

[0464] b) a subscription type, which is used to indicate a request to subscribe to at least one of the terminal's data, the terminal's AI / ML model, and the terminal's analysis information;

[0465] c) Description or filtering information of the first AI / ML related information of the terminal requesting subscription, for example:

[0466] - Data type (indicating what function / characteristics of the terminal are related to, such as data on terminal movement characteristics or movement trajectory, data on terminal communication characteristics or communication performance, terminal energy consumption or energy efficiency data), data collection time (segment), data collection area, and data accuracy;

[0467] - AI / ML model type (indicating what function / feature the model is used for, such as a model of terminal mobility characteristics or movement trajectory, a model of terminal communication characteristics or communication performance, or a model of terminal energy consumption or energy efficiency), model accuracy (characterizing the accuracy of the analysis results obtained using the model);

[0468] -Analysis identification (indicating what kind of function / characteristic the analysis information is, such as analysis information of terminal mobility characteristics or mobility trajectory, analysis information of terminal communication characteristics or communication performance, terminal energy consumption or energy efficiency analysis information), confidence level of analysis information (applicable to prediction information), applicable time of analysis information, applicable area of ​​analysis information, etc.

[0469] d) Information about the access network device, such as the ID or address of the access network device, subscription association identifier, address for receiving subscription information ( / notification or report), etc.

[0470] S2. The terminal sends the first AI / ML related information of the terminal to the AF entity through the user plane (application layer) (or sends it to the AMF entity through a NAS layer message).

[0471] Optionally, the message sending the first AI / ML related information of the terminal may also include description information corresponding to the first AI / ML related information, and the description information includes at least one of the following: terminal data description information, terminal model description information, and terminal analysis description information. Specifically: the terminal data description information may include the following information: data collection time (segment), sampling frequency, and data accuracy. The terminal model description information may include the following information: model generation time, model identifier, model type (indicating what function / characteristic the model is used for, such as a model of terminal mobile characteristics or mobile trajectories, a model of terminal communication characteristics or communication performance, and a terminal energy consumption or energy efficiency model), and model accuracy (characterizing the accuracy of the analysis results obtained using the model). The terminal analysis description information may include the following information: generation time of the analysis information, statistics or predictions, analysis identifier (indicating what function / characteristic analysis information, such as analysis information of terminal mobile characteristics or mobile trajectories, analysis information of UE communication characteristics or communication performance, and terminal energy consumption or energy efficiency analysis information), confidence (applicable to prediction information), applicable duration, usage area, etc.

[0472] S3. The AF entity (or AMF entity) sends the first AI / ML related information (and corresponding description information) of the terminal to the ADRF entity. The ADRF stores the first AI / ML related information (and corresponding description information) of the terminal, and assigns different index values ​​to different first AI / ML related information, for example, assigning a terminal data index value (UE dataindex, UDI) to the terminal data, assigning a terminal model index value (UE model index, UMI) to the AI / ML model of the terminal, and assigning a terminal analysis index value (UE analytics index, UAI) to the analysis information of the terminal.

[0473] S4. The ADRF entity sends a reply message to the AF entity (or AMF entity), which contains at least one of UDI, UMI and UAI.

[0474] Optionally, the AF entity sends a reply message to the terminal through the user plane (application layer) or the AMF entity, which includes at least one of UDI, UMI and UAI.

[0475] S5. The ADRF entity sends a message to the access network device to notify the access network device of the latest stored first AI / ML related information of the terminal. The message carries at least one of UDI, UMI and UAI, and corresponding description information.

[0476] The access network device (directly or through AMF) requests the ADRF entity of the core network to subscribe to the first AI / ML related information of at least one of the terminal, the access network device and the core network device, and receives an update notification of the first AI / ML related information of at least one of the terminal, the access network device and the core network device from the ADRF entity.

[0477] Example 2: Take the access network device / terminal as the first functional entity, the terminal / access network device / core network functional entity as the second functional entity, and the ADRF as the third functional entity.

[0478] In this example, if the first functional entity is access network device 2 and the second functional entity is access network device 1, access network device 1 and access network device 2 can be the centralized control unit (e.g., gNB-CU) and distributed unit (e.g., gNB-DU) of the access network, respectively, or access network device 1 and access network device 2 are two access network devices accessed by the terminal through dual access, or access network device 1 and access network device 2 are two adjacent access network devices.

[0479] In this example, if the first functional entity is terminal 2 and the second functional entity is terminal 1, terminal 1 and terminal 2 may be two different terminals. Terminal 2 can obtain the first AI / ML related information of terminal 1 only when terminal 1 authorizes terminal 2 to use the first AI / ML related information of terminal 1. In particular, terminal 1 and terminal 2 may be different terminals of the same user (e.g., mobile phone, computer, IoT device, etc.).

[0480] S1. Access network device 2 (or terminal 2) may send a sixth message to an ADRF entity.

[0481] (1) The sixth message may be used to request a subscription to first AI / ML related information of terminal 1, where the first AI / ML related information includes at least one of the following: data of terminal 1, an AI / ML model of terminal 1, and analysis information of terminal 1.

[0482] (2) The sixth message may also be used to request a subscription to first AI / ML related information of access network device 1, where the first AI / ML related information includes at least one of the following: data of access network device 1, an AI / ML model of access network device 1, and analysis information of access network device 1.

[0483] At this time, the sixth message may carry the following information:

[0484] a) Terminal identification, which may include: identification of one or more terminals, terminal group identification, information of terminals that meet certain conditions (for example, slice or slice instance information, indicating all / any terminals served by a specified slice or slice instance; or area information (for example, tracking area, cell or geographic area), indicating all / any terminals in a specified area).

[0485] b) a subscription type, used to indicate a request to subscribe to at least one of the data of access network device 1, the AI / ML model of access network device 1, and the analysis information of access network device 1;

[0486] c) Description or filtering information of the first AI / ML related information of the access network device 1 requested to be subscribed, for example:

[0487] - Data type (indicating what function / characteristic data is related to, such as data on terminal mobility characteristics or mobility trajectories, data on terminal communication characteristics or communication performance, access network equipment performance data, access network equipment load or resource usage data, access network equipment energy consumption or energy efficiency), data collection time (segment), data collection area, and data accuracy;

[0488] - AI / ML model type (indicating what function / feature the model is used for, such as a model of terminal mobility characteristics or mobility trajectory, a model of terminal communication characteristics or communication performance, an access network equipment performance model, an access network equipment load or resource usage model, an access network equipment energy consumption or energy efficiency model), model accuracy (characterizing the accuracy of the analysis results obtained using the model);

[0489] -Analysis identification (indicating what kind of function / characteristic analysis information, such as analysis information of terminal mobility characteristics or mobility trajectory, analysis information of terminal communication characteristics or communication performance, access network equipment performance analysis information, access network equipment load or resource usage analysis information, access network equipment energy consumption or energy efficiency analysis information), analysis information confidence level (applicable to prediction information), analysis information applicability time, analysis information applicability area, etc.

[0490] d) Information of the access network device 2, such as the ID or address of the access network device 2, a subscription association identifier, an address for receiving subscription information ( / notification or report), etc.

[0491] (3) The sixth message may also be used to request a subscription to first AI / ML related information of a core network function entity, where the first AI / ML related information includes at least one of the following: data of the core network function entity, an AI / ML model of the core network function entity, and analysis information of the core network function entity.

[0492] At this time, the sixth message may carry the following information:

[0493] a) Terminal identification, which may include: identification of one or more terminals, terminal group identification, information of terminals that meet certain conditions (for example, slice or slice instance information, indicating all / any terminals served by a specified slice or slice instance; or area information (for example, tracking area, cell or geographic area), indicating all / any terminals in a specified area).

[0494] b) a subscription type, used to indicate a request to subscribe to at least one of the data of a core network function entity, an AI / ML model of the core network function entity, and analysis information of the core network function entity;

[0495] c) Description or filtering information of the first AI / ML related information of the core network functional entity for which subscription is requested, for example:

[0496] - Data type (indicating what kind of function / characteristic data is related to, such as data on terminal mobility characteristics or movement trajectory, data on terminal communication characteristics or communication performance, core network performance data, core network load or resource usage data, core network energy consumption or energy efficiency), data collection time (segment), data collection area, and data accuracy;

[0497] - AI / ML model type (indicating what function / feature the model is used for, such as a model of terminal mobility characteristics or mobility trajectory, a model of terminal communication characteristics or communication performance, a core network performance model, a core network load or resource usage model, a core network energy consumption or energy efficiency model), model accuracy (characterizing the accuracy of the analysis results obtained using the model);

[0498] -Analysis identification (indicating what kind of function / characteristic analysis information, such as analysis information of terminal mobility characteristics or mobility trajectory, analysis information of terminal communication characteristics or communication performance, core network performance analysis information, core network load or resource usage analysis information, core network energy consumption or energy efficiency analysis information), analysis information confidence level (applicable to prediction information), analysis information applicability duration, analysis information applicability area, etc.

[0499] d) Information of the access network device 2, such as the ID or address of the access network device 2, a subscription association identifier, an address for receiving subscription information ( / notification or report), etc.

[0500] S2. Terminal 1 sends the first AI / ML related information of terminal 1 to access network device 1 through an access layer message. Optionally, the access layer message may also include description information corresponding to the first AI / ML related information of terminal 1, and the description information includes at least one of the following: terminal 1 data description information, terminal 1 model description information, and terminal 1 analysis description information. For the specific content of the description information, see step S1 of example 1.

[0501] S3. Access network device 1 sends the first AI / ML related information (and corresponding description information) of terminal 1 to the ADRF entity. The ADRF entity stores the first AI / ML related information (and corresponding description information) of terminal 1, and assigns index values ​​to different first AI / ML related information, for example, assigning UDI to the data of terminal 1, assigning UMI to the AI / ML model of terminal 1, and assigning UAI to the analysis information of terminal 1.

[0502] S4. The ADRF entity sends a reply message to the access network device 1, which includes at least one of UDI, UMI and UAI.

[0503] Note: The ADRF entity can send messages to or receive messages from the access network device through the AMF entity, or directly send messages to or receive messages from the access network device (for example: define a reference point or service interface between the access network device and the ADRF entity so that the access network device can communicate directly with the ADRF entity).

[0504] S5. Optionally, the access network device 1 sends a reply message to the terminal 1, which includes at least one of UDI, UMI and UAI.

[0505] S6. The ADRF entity sends a message to the access network device 2 (or terminal 2) to notify the access network device 2 (or terminal 2) of the latest stored information related to the first AI / ML of the terminal 1. The message carries at least one of UDI, UMI and UAI, and corresponding description information.

[0506] S7. Access network device 1 sends the first AI / ML related information of access network device 1 and the description information corresponding to the first AI / ML related information of access network device 1 to the ADRF entity; the description information includes at least one of the following: access network device 1 data description information, access network device 1 model description information, and access network device 1 analysis description information. For the specific content of the description information, see step S1 of Example 1.

[0507] ADRF stores the first AI / ML related information (and corresponding description information) of the access network device 1, and assigns index values ​​to different first AI / ML related information, for example, assigning an access network data index value (ANdata index, ADI) to the data of the access network device 1, assigning an access network model index value (AN model index, AMI) to the AI / ML model of the access network device 1, and assigning an access network analysis index value (AN analytics index, AAI) to the analysis information of the access network device 1.

[0508] S8. The ADRF entity sends a reply message to the access network device 1, which includes at least one of ADI, AMI and AAI.

[0509] S9. The ADRF entity sends a message to the access network device 2 (or terminal 2) to notify the access network device 2 (or terminal 2) of the latest stored information related to the first AI / ML of the access network device 1. The message carries at least one of ADI, AMI and AAI, and corresponding description information.

[0510] S10. The core network function entity (e.g., AMF entity, SMF entity, UPF entity, PCF entity, NEF entity, AF entity, NWDAF entity, DCCF entity) sends the first AI / ML related information of the core network function entity and the corresponding description information to the ADRF entity; the description information includes at least one of the following: core network function entity data description information, core network function entity model description information, core network function entity analysis description information. For the specific content of the description information, see step S1 of Example 1.

[0511] ADRF stores the first AI / ML related information (and corresponding description information) of the core network functional entity, and assigns index values ​​to different first AI / ML related information, for example, assigning a core network data index value (CN data index, CDI) to the data of the core network functional entity, assigning a core network model index value (CNmodel index, CMI) to the AI / ML model of the core network functional entity, and assigning a core network analysis index value (CN analyticsindex, CAI) to the analysis information of the core network functional entity.

[0512] Optionally, the ADRF entity sends a reply message to the core network function entity, which includes at least one of CDI, CMI and CAI.

[0513] S11. The ADRF entity sends a message to the access network device 2 (or terminal 2) to notify the access network device 2 (or terminal 2) of the latest stored first AI / ML related information of the core network function entity. The message carries at least one of CDI, CMI and CAI, and corresponding description information.

[0514] S12. Access network device 2 (or terminal 2) may subsequently send a request message to the ADRF entity, requesting first AI / ML related information of at least one of terminal 1, access network device 1 and core network function entity 1. The request message may carry at least one of UDI, UMI, UAI, ADI, AMI, AAI, CDI, CMI and CAI.

[0515] S13. The ADRF entity sends a reply message to the access network device 2 (or terminal 2), providing the access network device 2 (or terminal 2) with the first AI / ML related information of at least one of the terminal 1, the access network device 1, and the core network function entity 1. The reply message carries the file address of the first AI / ML related information of at least one of the terminal 1, the access network device 1, and the core network function entity 1.

[0516] S14. Access network device 2 (or terminal 2) obtains first AI / ML related information of at least one of terminal 1, access network device 1 and core network function entity 1 based on the file address of the received first AI / ML related information of at least one of terminal 1, access network device 1 and core network function entity 1.

[0517] S15. Access network device 2 (or terminal 2) uses the first AI / ML related information of at least one of terminal 1, access network device 1 and core network functional entity 1 to perform local AI calculation, processing and / or decision-making, such as access and mobility management based on terminal mobility characteristics (such as paging, switching, redirection, guiding the terminal to reselect a cell, roaming guidance, slice reselection, etc.), data bearer resource scheduling based on terminal communication characteristics, load balancing and / or energy efficiency control, target cell and / or target access network device selection based on access network device performance or load or energy consumption characteristics, core network functional entity (such as AMF, SMF) selection or slice instance selection based on core network performance or load or energy consumption characteristics, etc.

[0518] The access network device or terminal uses the first AI / ML related information of at least one of the terminal, the access network device and the core network functional entity to perform local AI calculation, processing and / or decision-making.

[0519] Example 3: Take the access network device as the first functional entity, the terminal as the second functional entity, and the ADRF as the third functional entity as an example.

[0520] S1. The access network device determines, based on a trigger condition, that first AI / ML related information of the terminal needs to be obtained, where the first AI / ML related information includes at least one of the following: data of the terminal, an AI / ML model of the terminal, and analysis information of the terminal.

[0521] Trigger conditions include any of the following:

[0522] 1a. The access network device receives a request or command message related to terminal access and mobility management sent by the AMF entity;

[0523] 1b. The access network device receives a request or command message related to terminal session management sent by the SMF entity;

[0524] 1c. The access network device receives a request or command message related to terminal policy (eg, proximity service-related policy) control sent by the PCF entity;

[0525] 1d. The access network device receives an air interface message sent by the terminal, such as an access request or a measurement report;

[0526] 1e. The access network device determines that the terminal data is needed to train the AI / ML model;

[0527] 1f. The access network device determines that the terminal’s AI / ML model is needed to train the access network device’s local AI / ML model (e.g., federated learning, transfer learning).

[0528] In the above cases 1a-1d, the access network device determines that the analysis information of the terminal is needed to determine the terminal behavior and assist in decision making (eg, access or resource management of the terminal).

[0529] S2. The access network device sends a request message to the ADRF entity to request the first AI / ML related information of the terminal. The request message carries an index value of the first AI / ML related information of the terminal requested by the access network device, for example, at least one of UDI, UMI and UAI.

[0530] S3. The ADRF entity sends a reply message to the access network device, providing the access network device with the first AI / ML related information of the terminal. The reply message carries the file address of the first AI / ML related information of the terminal requested by the access network device, for example, at least one of the file address of the terminal data, the file address of the terminal AI / ML model, and the file address of the terminal analysis information.

[0531] S4. The access network device obtains the first AI / ML related information of the terminal according to the file address of the first AI / ML related information of the terminal in the reply message.

[0532] The access network device uses the first AI / ML related information of the terminal to perform local AI calculation, processing and / or decision-making, such as access and mobility management based on terminal mobility characteristics (such as paging, switching, redirection, guiding the terminal to perform cell reselection, roaming guidance, slice reselection, etc.), data bearer resource scheduling based on terminal communication characteristics, load balancing and / or energy efficiency control, etc.

[0533] If the access network device determines to send an air interface message to the terminal based on step S4 to perform access layer control on the terminal, the following steps S5 to S7 are executed:

[0534] S5. The access network device sends an air interface reply or request message to the terminal, which carries the index value of the first AI / ML related information of the terminal. For example, if the UMI is carried, it indicates that the AI / ML model corresponding to the UMI is used between the terminal and the access network device for access layer processing (such as encoding and decoding, channel control, and resource configuration).

[0535] S6. The terminal sends an air interface confirmation or reply message to the access network device, which carries the UMI, to confirm to the access network device that the AI / ML model corresponding to the UMI will be used for access layer processing.

[0536] S7. The AI / ML model corresponding to the UMI is used between the terminal and the access network device for access layer processing.

[0537] If the access network device determines to send a terminal-related reply or request to the core network based on step 4 or step 7, the access network device performs one of the following operations:

[0538] S8a, the access network device sends a reply or request message related to terminal access and mobility management to the AMF entity;

[0539] S8b, the access network device sends a reply or request message related to terminal session management to the SMF entity;

[0540] S8c. The access network device sends a terminal policy (eg, proximity service-related policy) control-related reply or request message to the PCF entity.

[0541] Based on the trigger condition, the access network device requests the ADRF entity to obtain first AI / ML related information of at least one of the terminal, the access network device and the core network device.

[0542] Example 4: Take the access network device as the first functional entity, the terminal as the second functional entity, and the ADRF as the third functional entity as an example.

[0543] S1. The terminal sends an air interface message to the access network device, which carries the UMI, to request the terminal and the access network device to use the AI / ML model corresponding to the UMI for access layer processing (such as encoding and decoding, channel control, and resource configuration).

[0544] S2. After the access network device receives the air interface message, if the access network device does not locally store the UMI or the AI / ML model of the terminal corresponding to the UMI, the access network device decides to request the AI / ML model of the terminal from the ADRF entity ( / other core network functional entities).

[0545] S3. The access network device sends a request message to the ADRF entity, where the message carries the UMI, for requesting the AI / ML model of the terminal corresponding to the UMI.

[0546] S4. The ADRF entity sends a reply message to the access network device, and the reply message carries the file address of the AI / ML model of the terminal corresponding to the UMI.

[0547] S5. The access network device obtains the AI / ML model corresponding to the UMI according to the file address of the AI / ML model of the terminal in the reply message. The access network device sends an air interface reply message to the terminal, which carries the UMI, to confirm to the terminal that the AI / ML model corresponding to the UMI will be used for access layer processing.

[0548] S6. The AI / ML model corresponding to the UMI is used between the terminal and the access network device for access layer processing.

[0549] The terminal and the access network device use the information (index / identification) of the AI / ML model stored in the ADRF entity to negotiate the AI / ML model to be used.

[0550] An embodiment of the present application provides a method for an access network device to obtain first AI / ML related information of at least one of a terminal, an access network device and a core network device through an ADRF entity, thereby improving the efficiency of the access network device in obtaining input data, models and analysis information from terminals and other network elements, improving the accuracy and real-time performance of local AI calculations, processing or decision-making of the access network device, and realizing AI-based access layer processing using a unified model between the terminal.

[0551] Fig.13 Schematic diagram of the structure of the communication device 1300 provided in the embodiment of the present application. Fig.13 As shown, the device 1300 includes: a memory 1310 , a transceiver 1320 , and a processor 1330 .

[0552] The memory 1310 is used to store computer programs; the transceiver 1320 is used to send and receive data under the control of the processor 1330; the processor 1330 is used to read the computer program stored in the memory 1310 and perform the following operations:

[0553] Obtain index information of first artificial intelligence AI / machine learning ML related information of the second functional entity, where the index information of the first AI / ML related information is used to indicate the first AI / ML related information stored by the second functional entity in the third functional entity, where the first AI / ML related information includes at least one of the following: first data information for AI / ML model training or analysis, first AI / ML model information, and first analysis information;

[0554] Acquire the first AI / ML related information according to the index information of the first AI / ML related information;

[0555] Use the first AI / ML related information to communicate with the second functional entity.

[0556] In one implementation, the processor 1330 is specifically configured to perform the following operations:

[0557] A first message sent by the second functional entity is received, where the first message carries index information of first AI / ML related information.

[0558] In one implementation, the processor 1330 is further configured to perform the following operations:

[0559] A second message is sent to the second functional entity, where the second message is used to request the first AI / ML related information.

[0560] In one implementation, the processor 1330 is specifically configured to perform the following operations:

[0561] Based on any one of the following triggering conditions, a second message is sent to the second functional entity:

[0562] Determine that data or AI / ML models of a second functional entity are required for AI / ML model training or analysis;

[0563] receiving a third message sent by the second functional entity, where the third message is used to request processing by the access layer, the non-access layer, or the application layer;

[0564] A fourth message sent by a fourth functional entity is received, where the fourth message is used to request access layer, non-access layer, or application layer control of the second functional entity.

[0565] In one implementation, the processor 1330 is specifically configured to perform the following operations:

[0566] Using the index information of the first AI / ML related information, obtaining the first AI / ML related information from the third functional entity; or,

[0567] The first AI / ML related information is determined according to the locally stored AI / ML related information and the index information of the first AI / ML related information, where the locally stored AI / ML related information is the AI / ML related information obtained by the first functional entity from the third functional entity and stored locally, and the locally stored AI / ML related information includes the index information of the first AI / ML related information.

[0568] In one implementation, the processor 1330 is specifically configured to perform the following operations:

[0569] receiving a fifth message sent by a fifth functional entity, where the fifth message carries index information of the first AI / ML related information and / or information of the third functional entity, and the fifth message is used to request switching or to provide terminal context;

[0570] Obtain the first AI / ML related information from the third functional entity using the index information of the first AI / ML related information and / or the information of the third functional entity;

[0571] The second functional entity is the second terminal, the first functional entity is the functional entity currently serving the second functional entity, and the fifth functional entity is the functional entity that previously served the second functional entity.

[0572] In one implementation, the processor 1330 is further configured to perform the following operations:

[0573] Send a sixth message to the third functional entity, where the sixth message is used to request to subscribe to the first AI / ML related information of the second functional entity;

[0574] Receive index information of the first AI / ML related information sent by the third functional entity.

[0575] In one implementation, the processor 1330 is further configured to perform the following operations:

[0576] Send index information of the first AI / ML related information to the second functional entity.

[0577] In one implementation, the first AI / ML related information is first data information, and the processor 1330 is specifically configured to perform the following operations:

[0578] Using the first data information to perform AI / ML model training to obtain a second AI / ML model; or using the first data information to perform analysis to obtain second analysis information;

[0579] Use the second AI / ML model or the second analysis information to communicate with the second functional entity.

[0580] In one implementation, the first AI / ML related information is first AI / ML model information, and the processor 1330 is specifically configured to perform the following operations:

[0581] Determining a first AI / ML model according to the first AI / ML model information;

[0582] The first AI / ML model is used to communicate with the second functional entity.

[0583] In one implementation, the processor 1330 is specifically configured to perform the following operations:

[0584] Perform access layer processing with the second functional entity;

[0585] The first functional entity and the second functional entity meet one of the following conditions:

[0586] The first functional entity is a first access network device, and the second functional entity is a second terminal;

[0587] The first functional entity is a first terminal, and the second functional entity is a second terminal;

[0588] The first functional entity is a first terminal, and the second functional entity is a second access network device.

[0589] In one implementation, the processor 1330 is specifically configured to perform the following operations:

[0590] Performing non-access layer or application layer processing with the second functional entity;

[0591] The first functional entity and the second functional entity meet one of the following conditions:

[0592] The first functional entity is a first core network functional entity, and the second functional entity is a second terminal;

[0593] The first functional entity is a first terminal, and the second functional entity is a second terminal;

[0594] The first functional entity is a first terminal, and the second functional entity is a second core network functional entity.

[0595] Among them, Fig.13 In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically one or more processors represented by processor 1330 and various circuits of memory represented by memory 1310 are linked together. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 1320 may be a plurality of components, namely, a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium, which transmission medium may include a wireless channel, a wired channel, an optical cable, and other transmission media. The processor 1330 is responsible for managing the bus architecture and general processing, and the memory 1310 may store data used by the processor 1330 when performing operations.

[0596] Optionally, processor 1330 can be a central processing unit (CPU), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or a complex programmable logic device (CPLD), and the processor can also adopt a multi-core architecture.

[0597] When the communication device 1300 is a terminal, it may also include a user interface. For different terminals, the user interface may also be an interface that can connect to required external or internal devices. The connected devices include but are not limited to a keypad, display, speaker, microphone, joystick, etc.

[0598] The processor 1330 is used to execute all method steps of the first functional entity of the embodiment of the present application according to the obtained executable instructions by calling the computer program stored in the memory 1310. The processor 1330 and the memory 1310 can also be arranged physically separately.

[0599] It should be noted here that the above-mentioned communication device 1300 provided in the present application can implement all the method steps implemented by the first functional entity in the above-mentioned method embodiment, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0600] Fig.14 Schematic diagram of the structure of the communication device 1400 provided in the embodiment of the present application. Fig.14 As shown, the device 1400 includes: a memory 1410 , a transceiver 1420 , and a processor 1430 .

[0601] The memory 1410 is used to store computer programs; the transceiver 1420 is used to send and receive data under the control of the processor 1430; the processor 1430 is used to read the computer program stored in the memory 1410 and perform the following operations:

[0602] Sending first artificial intelligence AI / machine learning ML related information to the third functional entity, where the first AI / ML related information includes at least one of the following: first data information for AI / ML model training or analysis, first AI / ML model information, and first analysis information;

[0603] receiving index information of the first AI / ML related information sent by the third functional entity, where the index information of the first AI / ML related information is used to indicate the first AI / ML related information stored in the third functional entity by the second functional entity;

[0604] Use the first AI / ML related information to communicate with the first functional entity.

[0605] In one implementation, the processor 1430 is further configured to perform the following operations:

[0606] A first message is sent to the first functional entity, where the first message carries index information of first AI / ML related information.

[0607] In one implementation, the processor 1430 is specifically configured to perform the following operations:

[0608] Performing access layer processing with the first functional entity;

[0609] The first functional entity and the second functional entity meet one of the following conditions:

[0610] The first functional entity is a first access network device, and the second functional entity is a second terminal;

[0611] The first functional entity is a first terminal, and the second functional entity is a second terminal;

[0612] The first functional entity is a first terminal, and the second functional entity is a second access network device.

[0613] In one implementation, the processor 1430 is specifically configured to perform the following operations:

[0614] Performing non-access layer or application layer processing with the first functional entity;

[0615] The first functional entity and the second functional entity meet one of the following conditions:

[0616] The first functional entity is a first core network functional entity, and the second functional entity is a second terminal;

[0617] The first functional entity is a first terminal, and the second functional entity is a second terminal;

[0618] The first functional entity is a first terminal, and the second functional entity is a second core network functional entity.

[0619] Among them, Fig.14In the embodiment, the bus architecture may include any number of interconnected buses and bridges, specifically one or more processors represented by processor 1430 and various circuits of memory represented by memory 1410 are linked together. The bus architecture may also link together various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The bus interface provides an interface. The transceiver 1420 may be a plurality of components, namely, a transmitter and a receiver, providing a unit for communicating with various other devices on a transmission medium, which transmission medium may include a wireless channel, a wired channel, an optical cable, and other transmission media. The processor 1430 is responsible for managing the bus architecture and general processing, and the memory 1410 may store data used by the processor 1430 when performing operations.

[0620] Optionally, the processor 1430 may be a CPU, an ASIC, an FPGA or a CPLD, and the processor may also adopt a multi-core architecture.

[0621] When the communication device 1400 is a terminal, it may also include a user interface. For different terminals, the user interface may also be an interface that can connect to required external or internal devices. The connected devices include but are not limited to a keypad, display, speaker, microphone, joystick, etc.

[0622] The processor 1430 is used to execute all method steps of the second functional entity of the embodiment of the present application according to the obtained executable instructions by calling the computer program stored in the memory 1410. The processor 1430 and the memory 1410 can also be arranged physically separately.

[0623] It should be noted here that the above-mentioned communication device 1400 provided in the present application can implement all the method steps implemented by the second functional entity in the above-mentioned method embodiment, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0624] Fig.15 Schematic diagram of the structure of the communication device 1500 provided in the embodiment of the present application. Fig.15 As shown, the device 1500 includes:

[0625] A first acquisition unit 1510 is configured to acquire index information of first artificial intelligence AI / machine learning ML related information of a second functional entity, where the index information of the first AI / ML related information is used to indicate the first AI / ML related information stored by the second functional entity in a third functional entity, where the first AI / ML related information includes at least one of the following: first data information for AI / ML model training or analysis, first AI / ML model information, and first analysis information;

[0626] The second acquisition unit 1520 is configured to acquire the first AI / ML related information according to the index information of the first AI / ML related information;

[0627] The processing unit 1530 is configured to perform communication processing with the second functional entity using the first AI / ML related information.

[0628] In one implementation, the first acquiring unit 1510 is specifically configured to:

[0629] A first message sent by the second functional entity is received, where the first message carries index information of first AI / ML related information.

[0630] In one implementation, the apparatus 1500 further includes a first sending unit, and the first sending unit is configured to:

[0631] A second message is sent to the second functional entity, where the second message is used to request the first AI / ML related information.

[0632] In one implementation, the first sending unit is specifically configured to:

[0633] Based on any one of the following triggering conditions, a second message is sent to the second functional entity:

[0634] Determine that data or AI / ML models of a second functional entity are required for AI / ML model training or analysis;

[0635] receiving a third message sent by the second functional entity, where the third message is used to request processing by the access layer, the non-access layer, or the application layer;

[0636] A fourth message sent by a fourth functional entity is received, where the fourth message is used to request access layer, non-access layer, or application layer control of the second functional entity.

[0637] In one implementation, the second obtaining unit 1520 is specifically configured to:

[0638] Using the index information of the first AI / ML related information, obtaining the first AI / ML related information from the third functional entity; or,

[0639] The first AI / ML related information is determined according to the locally stored AI / ML related information and the index information of the first AI / ML related information, where the locally stored AI / ML related information is the AI / ML related information obtained by the first functional entity from the third functional entity and stored locally, and the locally stored AI / ML related information includes the index information of the first AI / ML related information.

[0640] In one implementation, the first acquiring unit 1510 is specifically configured to:

[0641] receiving a fifth message sent by a fifth functional entity, where the fifth message carries index information of the first AI / ML related information and / or information of the third functional entity, and the fifth message is used to request switching or to provide terminal context;

[0642] The second acquisition unit 1520 is specifically configured to:

[0643] Obtain the first AI / ML related information from the third functional entity using the index information of the first AI / ML related information and / or the information of the third functional entity;

[0644] The second functional entity is the second terminal, the first functional entity is the functional entity currently serving the second functional entity, and the fifth functional entity is the functional entity that previously served the second functional entity.

[0645] In one implementation, the apparatus 1500 further includes a second sending unit and a receiving unit, wherein:

[0646] A second sending unit is configured to send a sixth message to the third functional entity, where the sixth message is used to request to subscribe to first AI / ML related information of the second functional entity;

[0647] The receiving unit is configured to receive index information of the first AI / ML related information sent by the third functional entity.

[0648] In one implementation, the first sending unit is further configured to:

[0649] Send index information of the first AI / ML related information to the second functional entity.

[0650] In one implementation, the first AI / ML related information is first data information, and the processing unit 1530 is specifically configured to:

[0651] Using the first data information to perform AI / ML model training to obtain a second AI / ML model; or using the first data information to perform analysis to obtain second analysis information;

[0652] Use the second AI / ML model or the second analysis information to communicate with the second functional entity.

[0653] In one implementation, the first AI / ML related information is first AI / ML model information, and the processing unit 1530 is specifically configured to:

[0654] Determining a first AI / ML model according to the first AI / ML model information;

[0655] The first AI / ML model is used to communicate with the second functional entity.

[0656] In one implementation, the processing unit 1530 is specifically configured to:

[0657] Perform access layer processing with the second functional entity;

[0658] The first functional entity and the second functional entity meet one of the following conditions:

[0659] The first functional entity is a first access network device, and the second functional entity is a second terminal;

[0660] The first functional entity is a first terminal, and the second functional entity is a second terminal;

[0661] The first functional entity is a first terminal, and the second functional entity is a second access network device.

[0662] In one implementation, the processing unit 1530 is specifically configured to:

[0663] Performing non-access layer or application layer processing with the second functional entity;

[0664] The first functional entity and the second functional entity meet one of the following conditions:

[0665] The first functional entity is a first core network functional entity, and the second functional entity is a second terminal;

[0666] The first functional entity is a first terminal, and the second functional entity is a second terminal;

[0667] The first functional entity is a first terminal, and the second functional entity is a second core network functional entity.

[0668] It should be noted here that the above-mentioned communication device 1500 provided in the present application can implement all the method steps implemented by the first functional entity in the above-mentioned method embodiment, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0669] Fig.16 Schematic diagram of the structure of the communication device 1600 provided in the embodiment of the present application. Fig.16 As shown, the device 1600 includes:

[0670] The sending unit 1610 is configured to send first artificial intelligence AI / machine learning ML related information to the third functional entity, where the first AI / ML related information includes at least one of the following: first data information for AI / ML model training or analysis, first AI / ML model information, and first analysis information;

[0671] The receiving unit 1620 is configured to receive index information of the first AI / ML related information sent by the third functional entity, where the index information of the first AI / ML related information is used to indicate the first AI / ML related information stored in the third functional entity by the second functional entity;

[0672] The processing unit 1630 is configured to perform communication processing with the first functional entity using the first AI / ML related information.

[0673] In one implementation, the sending unit 1610 is further configured to:

[0674] A first message is sent to the first functional entity, where the first message carries index information of first AI / ML related information.

[0675] In one implementation, the processing unit 1630 is specifically configured to:

[0676] Performing access layer processing with the first functional entity;

[0677] The first functional entity and the second functional entity meet one of the following conditions:

[0678] The first functional entity is a first access network device, and the second functional entity is a second terminal;

[0679] The first functional entity is a first terminal, and the second functional entity is a second terminal;

[0680] The first functional entity is a first terminal, and the second functional entity is a second access network device.

[0681] In one implementation, the processing unit 1630 is specifically configured to:

[0682] Performing non-access layer or application layer processing with the first functional entity;

[0683] The first functional entity and the second functional entity meet one of the following conditions:

[0684] The first functional entity is a first core network functional entity, and the second functional entity is a second terminal;

[0685] The first functional entity is a first terminal, and the second functional entity is a second terminal;

[0686] The first functional entity is a first terminal, and the second functional entity is a second core network functional entity.

[0687] It should be noted here that the above-mentioned communication device 1600 provided in the present application can implement all the method steps implemented by the second functional entity in the above-mentioned method embodiment, and can achieve the same technical effect. The parts and beneficial effects of this embodiment that are the same as the method embodiment will not be described in detail here.

[0688] It should be noted that the division of units in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional unit in each embodiment of the present application may be integrated into a processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0689] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a processor-readable storage medium. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) or a processor (processor) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0690] An embodiment of the present application also provides a non-transitory readable storage medium, which stores a computer program, and the computer program is used to enable a processor to execute all method steps of the first functional entity in the above method embodiment.

[0691] An embodiment of the present application also provides a non-transitory readable storage medium, which stores a computer program, and the computer program is used to enable a processor to execute all method steps of the second functional entity in the above method embodiment.

[0692] Non-transitory readable storage media can be any available media or data storage devices that can be accessed by a computer, including but not limited to magnetic storage (such as floppy disks, hard disks, magnetic tapes, magneto-optical disks (MO), etc.), optical storage (such as CD, DVD, BD, HVD, etc.), and semiconductor storage (such as ROM, EPROM, EEPROM, non-volatile memory (NAND FLASH), solid-state drive (SSD)), etc.

[0693] An embodiment of the present application also provides a computer program product, including a computer program, which implements the method described in any one of the above method embodiments when the computer program is executed by a processor.

[0694] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage and optical storage, etc.) that contain computer-usable program code.

[0695] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer executable instructions. These computer executable instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0696] These processor executable instructions may also be stored in a processor readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the processor readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0697] These processor-executable instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0698] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is also intended to include these modifications and variations.

Claims

1. A communication method, characterized in that: Applied to the first functional entity, the method comprises: Obtain index information of first artificial intelligence AI / machine learning ML related information of the second functional entity, where the index information of the first AI / ML related information is used to indicate the first AI / ML related information stored by the second functional entity in the third functional entity, where the first AI / ML related information includes at least one of the following: first data information for AI / ML model training or analysis, first AI / ML model information, and first analysis information; Acquire the first AI / ML related information according to the index information of the first AI / ML related information; Use the first AI / ML related information to communicate with the second functional entity.

2. The method according to claim 1, characterized in that The obtaining of index information of the first AI / ML related information of the second functional entity includes: A first message sent by the second functional entity is received, where the first message carries index information of the first AI / ML related information.

3. The method according to claim 2, characterized in that Before the receiving the first message sent by the second functional entity, the method further includes: Send a second message to the second functional entity, where the second message is used to request the first AI / ML related information.

4. The method according to claim 3, characterized in that The sending the second message to the second functional entity comprises: Sending the second message to the second function entity based on any one of the following triggering conditions: Determining that data or an AI / ML model of the second functional entity is required for AI / ML model training or analysis; receiving a third message sent by the second functional entity, where the third message is used to request access layer, non-access layer or application layer processing; A fourth message sent by a fourth functional entity is received, where the fourth message is used to request access layer, non-access layer, or application layer control of the second functional entity.

5. The method according to any one of claims 1 to 4, characterized in that: The acquiring the first AI / ML related information according to the index information of the first AI / ML related information includes: Using the index information of the first AI / ML related information, obtaining the first AI / ML related information from a third functional entity; or, The first AI / ML related information is determined according to locally stored AI / ML related information and index information of the first AI / ML related information, where the locally stored AI / ML related information is AI / ML related information obtained by the first functional entity from the third functional entity and stored locally, and the locally stored AI / ML related information includes index information of the first AI / ML related information.

6. The method according to claim 1, characterized in that The obtaining of index information of the first AI / ML related information of the second functional entity includes: receiving a fifth message sent by a fifth functional entity, where the fifth message carries index information of the first AI / ML related information and / or information of the third functional entity, and the fifth message is used to request switching or to provide terminal context; The acquiring the first AI / ML related information according to the index information of the first AI / ML related information includes: obtaining the first AI / ML related information from the third functional entity using the index information of the first AI / ML related information and / or the information of the third functional entity; The second functional entity is a second terminal, the first functional entity is a functional entity currently serving the second functional entity, and the fifth functional entity is a functional entity that previously served the second functional entity.

7. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: Sending a sixth message to the third functional entity, where the sixth message is used to request a subscription to the first AI / ML related information of the second functional entity; Receive index information of the first AI / ML related information sent by the third functional entity.

8. The method according to claim 1, characterized in that Before using the first AI / ML related information to communicate with the second functional entity, the method further includes: Send index information of the first AI / ML related information to the second functional entity.

9. The method according to claim 1, characterized in that: The first AI / ML related information is the first data information, and the using the first AI / ML related information to perform communication processing with the second functional entity includes: Using the first data information to perform AI / ML model training to obtain a second AI / ML model; or using the first data information to perform analysis to obtain second analysis information; Use the second AI / ML model or the second analysis information to communicate with the second functional entity.

10. The method according to claim 1, characterized in that The first AI / ML related information is first AI / ML model information, and the using the first AI / ML related information to perform communication processing with the second functional entity includes: Determining a first AI / ML model according to the first AI / ML model information; Use the first AI / ML model to communicate with the second functional entity.

11. The method according to any one of claims 1 to 10, characterized in that: The performing communication processing with the second functional entity includes: performing access layer processing with the second functional entity; The first functional entity and the second functional entity meet one of the following conditions: The first functional entity is a first access network device, and the second functional entity is a second terminal; The first functional entity is a first terminal, and the second functional entity is a second terminal; The first functional entity is a first terminal, and the second functional entity is a second access network device.

12. The method according to any one of claims 1 to 10, characterized in that: The performing communication processing with the second functional entity includes: Performing non-access layer or application layer processing with the second functional entity; The first functional entity and the second functional entity meet one of the following conditions: The first functional entity is a first core network functional entity, and the second functional entity is a second terminal; The first functional entity is a first terminal, and the second functional entity is a second terminal; The first functional entity is a first terminal, and the second functional entity is a second core network functional entity.

13. A communication method, characterized in that: Applied to the second functional entity, the method comprises: Sending first artificial intelligence AI / machine learning ML related information to the third functional entity, where the first AI / ML related information includes at least one of the following: first data information for AI / ML model training or analysis, first AI / ML model information, and first analysis information; receiving index information of the first AI / ML related information sent by the third functional entity, where the index information of the first AI / ML related information is used to indicate the first AI / ML related information stored in the third functional entity by the second functional entity; Use the first AI / ML related information to communicate with the first functional entity.

14. The method according to claim 13, characterized in that After receiving the index information of the first AI / ML related information sent by the third functional entity, and before using the first AI / ML related information to perform communication processing with the first functional entity, the method further includes: A first message is sent to the first functional entity, where the first message carries index information of the first AI / ML related information.

15. The method according to claim 13 or 14, characterized in that The communication processing with the first functional entity includes: Performing access layer processing with the first functional entity; The first functional entity and the second functional entity meet one of the following conditions: The first functional entity is a first access network device, and the second functional entity is a second terminal; The first functional entity is a first terminal, and the second functional entity is a second terminal; The first functional entity is a first terminal, and the second functional entity is a second access network device.

16. The method according to claim 13 or 14, characterized in that The communication processing with the first functional entity includes: Performing non-access layer or application layer processing with the first functional entity; The first functional entity and the second functional entity meet one of the following conditions: The first functional entity is a first core network functional entity, and the second functional entity is a second terminal; The first functional entity is a first terminal, and the second functional entity is a second terminal; The first functional entity is a first terminal, and the second functional entity is a second core network functional entity.

17. A communication device, characterized in that: Applied to a first functional entity, the device comprises: A first acquisition unit is used to acquire index information of first artificial intelligence AI / machine learning ML related information of a second functional entity, where the index information of the first AI / ML related information is used to indicate the first AI / ML related information stored by the second functional entity in a third functional entity, where the first AI / ML related information includes at least one of the following: first data information for AI / ML model training or analysis, first AI / ML model information, and first analysis information; a second acquiring unit, configured to acquire the first AI / ML related information according to the index information of the first AI / ML related information; A processing unit is configured to perform communication processing with the second functional entity using the first AI / ML related information.

18. A communication device, characterized in that: Applied to the second functional entity, the device includes: A sending unit, configured to send first artificial intelligence AI / machine learning ML related information to a third functional entity, where the first AI / ML related information includes at least one of the following: first data information for AI / ML model training or analysis, first AI / ML model information, and first analysis information; a receiving unit, configured to receive index information of the first AI / ML related information sent by the third functional entity, where the index information of the first AI / ML related information is used to indicate the first AI / ML related information stored in the third functional entity by the second functional entity; A processing unit is configured to perform communication processing with a first functional entity using the first AI / ML related information.

19. A communication device, characterized in that: Applied to the first functional entity, the device includes a memory, a transceiver, a processor, The memory is used to store a computer program; the transceiver is used to send and receive data under the control of the processor; the processor is used to read the computer program in the memory and perform the following operations: Obtain index information of first artificial intelligence AI / machine learning ML related information of the second functional entity, where the index information of the first AI / ML related information is used to indicate the first AI / ML related information stored by the second functional entity in the third functional entity, where the first AI / ML related information includes at least one of the following: first data information for AI / ML model training or analysis, first AI / ML model information, and first analysis information; Acquire the first AI / ML related information according to the index information of the first AI / ML related information; Use the first AI / ML related information to communicate with the second functional entity.

20. The device according to claim 19, characterized in that The processor is specifically configured to perform the following operations: A first message sent by the second functional entity is received, where the first message carries index information of the first AI / ML related information.

21. The device according to claim 20, characterized in that The processor is further configured to perform the following operations: Send a second message to the second functional entity, where the second message is used to request the first AI / ML related information.

22. The device according to claim 21, characterized in that The processor is specifically configured to perform the following operations: Sending the second message to the second function entity based on any one of the following triggering conditions: Determining that data or an AI / ML model of the second functional entity is required for AI / ML model training or analysis; receiving a third message sent by the second functional entity, where the third message is used to request access layer, non-access layer or application layer processing; A fourth message sent by a fourth functional entity is received, where the fourth message is used to request access layer, non-access layer, or application layer control of the second functional entity.

23. The device according to any one of claims 19 to 22, characterized in that The processor is specifically configured to perform the following operations: Using the index information of the first AI / ML related information, obtaining the first AI / ML related information from a third functional entity; or, The first AI / ML related information is determined according to locally stored AI / ML related information and index information of the first AI / ML related information, where the locally stored AI / ML related information is AI / ML related information obtained by the first functional entity from the third functional entity and stored locally, and the locally stored AI / ML related information includes index information of the first AI / ML related information.

24. The device according to claim 19, characterized in that The processor is specifically configured to perform the following operations: receiving a fifth message sent by a fifth functional entity, where the fifth message carries index information of the first AI / ML related information and / or information of the third functional entity, and the fifth message is used to request switching or to provide terminal context; obtaining the first AI / ML related information from the third functional entity using the index information of the first AI / ML related information and / or the information of the third functional entity; The second functional entity is a second terminal, the first functional entity is a functional entity currently serving the second functional entity, and the fifth functional entity is a functional entity that previously served the second functional entity.

25. The device according to any one of claims 19 to 24, characterized in that The processor is further configured to perform the following operations: Sending a sixth message to the third functional entity, where the sixth message is used to request a subscription to the first AI / ML related information of the second functional entity; Receive index information of the first AI / ML related information sent by the third functional entity.

26. The device according to claim 19, characterized in that The processor is further configured to perform the following operations: Send index information of the first AI / ML related information to the second functional entity.

27. The device according to claim 19, characterized in that The first AI / ML related information is the first data information, and the processor is specifically configured to perform the following operations: Using the first data information to perform AI / ML model training to obtain a second AI / ML model; or using the first data information to perform analysis to obtain second analysis information; Use the second AI / ML model or the second analysis information to communicate with the second functional entity.

28. The device according to claim 19, characterized in that The first AI / ML related information is first AI / ML model information, and the processor is specifically configured to perform the following operations: Determining a first AI / ML model according to the first AI / ML model information; Use the first AI / ML model to communicate with the second functional entity.

29. The device according to any one of claims 19 to 28, characterized in that The processor is specifically configured to perform the following operations: performing access layer processing with the second functional entity; The first functional entity and the second functional entity meet one of the following conditions: The first functional entity is a first access network device, and the second functional entity is a second terminal; The first functional entity is a first terminal, and the second functional entity is a second terminal; The first functional entity is a first terminal, and the second functional entity is a second access network device.

30. The device according to any one of claims 19 to 28, characterized in that The processor is specifically configured to perform the following operations: Performing non-access layer or application layer processing with the second functional entity; The first functional entity and the second functional entity meet one of the following conditions: The first functional entity is a first core network functional entity, and the second functional entity is a second terminal; The first functional entity is a first terminal, and the second functional entity is a second terminal; The first functional entity is a first terminal, and the second functional entity is a second core network functional entity.

31. A communication device, characterized in that: Applied to the second functional entity, the device includes a memory, a transceiver, a processor, The memory is used to store a computer program; the transceiver is used to send and receive data under the control of the processor; the processor is used to read the computer program in the memory and perform the following operations: Sending first artificial intelligence AI / machine learning ML related information to the third functional entity, where the first AI / ML related information includes at least one of the following: first data information for AI / ML model training or analysis, first AI / ML model information, and first analysis information; receiving index information of the first AI / ML related information sent by the third functional entity, where the index information of the first AI / ML related information is used to indicate the first AI / ML related information stored in the third functional entity by the second functional entity; Use the first AI / ML related information to communicate with the first functional entity.

32. The device according to claim 31, characterized in that The processor is further configured to perform the following operations: A first message is sent to the first functional entity, where the first message carries index information of the first AI / ML related information.

33. The device according to claim 31 or 32, characterized in that The processor is specifically configured to perform the following operations: Performing access layer processing with the first functional entity; The first functional entity and the second functional entity meet one of the following conditions: The first functional entity is a first access network device, and the second functional entity is a second terminal; The first functional entity is a first terminal, and the second functional entity is a second terminal; The first functional entity is a first terminal, and the second functional entity is a second access network device.

34. The device according to claim 31 or 32, characterized in that The processor is specifically configured to perform the following operations: Performing non-access layer or application layer processing with the first functional entity; The first functional entity and the second functional entity meet one of the following conditions: The first functional entity is a first core network functional entity, and the second functional entity is a second terminal; The first functional entity is a first terminal, and the second functional entity is a second terminal; The first functional entity is a first terminal, and the second functional entity is a second core network functional entity.

35. A non-transitory readable storage medium, characterized in that The non-transitory readable storage medium stores a computer program, and the computer program is used to enable a processor to execute the method according to any one of claims 1 to 12, or the method according to any one of claims 13 to 16.

Images