Communication method and device

Abstract

The invention provides a communication method and device, belongs to the technical field of communication, and aims to meet higher data transmission requirements. In the method, an artificial intelligence (AI) / machine learning (ML) data set is obtained, the AI / ML data set comprises a first AI / ML data set and a second AI / ML data set, the first AI / ML data set and the second AI / ML data set are different in priority sequence number, and the different priority sequence numbers indicate that the transmission reliability and / or time delay levels of the first AI / ML data set and the second AI / ML data set are different; according to the priority sequence numbers of the first AI / ML data set and the second AI / ML data set, first control information and a first data channel are sent, the first control information is multiplexed in the first data channel, the first control information comprises the first AI / ML data set, and the first data channel further comprises the second AI / ML data set.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of communication, and in particular to a communication method and device. BACKGROUND

[0002] With the continuous development of the three driving forces of artificial intelligence (AI) / machine learning (ML) - computing power, algorithm and data related technologies, AI / ML has important application potential in many aspects such as modeling, learning, channel prediction, intelligent signal generation and processing, network state tracking and intelligent scheduling, network optimization deployment in complex unknown environments.

[0003] However, AI / ML involves a large amount of data, and the data types are also more, different data types put forward different transmission requirements for network transmission, and the current network transmission capacity may not be able to meet the transmission requirements of AI / ML data. SUMMARY

[0004] Embodiments of the present application provide a communication method and device to meet higher transmission requirements of data.

[0005] To achieve the above purpose, the technical scheme adopted by the present application is as follows:

[0006] In a first aspect, a communication method is provided. The method can be applied to a first communication device, can be executed by a module (such as a processor, a chip, or a chip system) applied to the first communication device, and can also be implemented by a logic node, a logic module, or software that can realize all or part of the functions of the first communication device. For convenience of description, the method is introduced below by taking the first communication device as an example. The method includes: obtaining an artificial intelligence (AI) / machine learning (ML) data set, the AI / ML data set being a first AI / ML data set and a second AI / ML data set, wherein the first AI / ML data set and the second AI / ML data set have different priority sequence numbers, and the different priority sequence numbers represent that the first AI / ML data set and the second AI / ML data set have different levels of transmission reliability and / or delay; and transmitting first control information and a first data channel according to the priority sequence numbers of the first AI / ML data set and the second AI / ML data set, wherein the first control information is multiplexed in the first data channel, the first control information contains the first AI / ML data set, and the first data channel also contains the second AI / ML data set.

[0007] Therefore, after obtaining the AI / ML data set, the first communication device does not directly send the AI / ML data set to the second communication device, but determines the priority sequence number of the plurality of data sets in the AI / ML data set, carries the data set with a high priority sequence number through the first control information, and carries the data set with a low priority sequence number through the first data channel. Since the transmission of the first control information is more reliable than the transmission of the data in the first data channel, the reliability of the transmission of the data set with a high priority sequence number can be ensured, the reporting error is avoided as much as possible, and the efficient use of transmission resources is achieved.

[0008] In a possible design scheme, the first AI / ML data set can include at least: a first AI / ML data subset and / or a second AI / ML data subset. That is, in this scheme, the number of data subsets included in the first AI / ML data set is not limited, and can be flexibly changed according to actual conditions.

[0009] Optionally, the first AI / ML data set, the first AI / ML data subset, and the second AI / ML data subset can include one or more of the following data types: monitoring information, training data, inference data, model management related information, model metadata and model auxiliary information, specific parameter information of a model, or any other possible data, which is not limited in particular

[0010] Optionally, if the first AI / ML data subset and the second AI / ML data subset have the same data type, the first AI / ML data subset corresponds to a first priority sequence number, and the second AI / ML data subset corresponds to a second priority sequence number, the first priority sequence number is the same as the second priority sequence number. That is, the priority relationship of the data subsets in the first AI / ML data set is determined based on the data type of each data subset. By determining the priority relationship, the data with the same priority sequence number can be merged / simultaneously processed, thereby saving overhead and reducing redundancy.

[0011] Optionally, if the first AI / ML data subset and the second AI / ML data subset have different data types, the first AI / ML data subset corresponds to a third priority sequence number, and the second AI / ML data subset corresponds to a fourth priority sequence number, the first priority sequence number is different from the second priority sequence number. That is, the priority relationship of the data subsets in the first AI / ML data set is determined based on the data type of each data subset. By determining the data with different priority sequence numbers, the data with a high priority sequence number is processed preferentially, so as to ensure the reliability of the transmission of the data set with a high priority sequence number.

[0012] Optionally, the data type can include one or more of the following features: the priority order of the monitoring data is greater than the priority order of the training data, or the priority order of the model management related information is greater than or equal to the priority order of the model metadata and the model auxiliary information, or the priority order of the model metadata and the model auxiliary information is greater than the priority order of the specific parameter information of the model. Based on this feature, the priority orders between the above-mentioned data types can be compared, and the data is processed according to the priority order of the data type.

[0013] Optionally, the multiplexing priority of the first AI / ML data subset and / or the second AI / ML data subset in the first data channel can include one or more of the following cases: the priority order of the first AI / ML data subset and / or the second AI / ML data subset is the same as the priority order of the HARQ-ACK; the priority order of the first AI / ML data subset and / or the second AI / ML data subset is the same as the priority order of the CSI part 1; the priority order of the first AI / ML data subset and / or the second AI / ML data subset is the same as the priority order of the CSI part 2; the priority order of the first AI / ML data subset and / or the second AI / ML data subset is different from the priority order of the HARQ-ACK; the priority order of the first AI / ML data subset and / or the second AI / ML data subset is different from the priority order of the CSI part 1; the priority order of the first AI / ML data subset and / or the second AI / ML data subset is different from the priority order of the CSI part 2. That is, the priority order of the data subset in the first AI / ML data set can be the same as or different from the priority order of the HARQ-ACK, the CSI part 1, and the CSI part 2. In the case of being the same, the data subset in the first AI / ML data set can be transmitted together with the signaling (such as HARQ-ACK) of the same priority order; in the case of being different, the data subset in the first AI / ML data set and the HARQ-ACK, the CSI part 1, and the CSI part 2 are sequentially mapped to the first data channel in the order of the priority order from high to low.

[0014] Optionally, the multiplexing priority is predefined by a protocol or indicated by physical layer or high layer signaling. The multiplexing priority predefined by a protocol is used in a scenario where the transmission reliability and / or delay level of the data types in the AI / ML data set is relatively certain, which helps to improve the efficiency, reliability and security of communication and reduce the communication delay. The multiplexing priority indicated by physical layer or high layer signaling is used in a scenario where the transmission reliability and / or delay level of the data types in the AI / ML data set is relatively uncertain, which directly indicates the priority relationship through a configured or protocol predefined priority relationship table, avoiding the situation that the priority sequence of the data types is ambiguous, resulting in the inability to determine the order of data multiplexing.

[0015] Optionally, if the first AI / ML data subset and the second AI / ML data subset are of the same data type, the data of the first AI / ML data subset and the second AI / ML data subset are jointly encoded and modulated. That is, the first communication device encodes the first AI / ML data set, and in the case where the first control information only contains the first AI / ML data set, the first AI / ML data set contains data subsets of the same type, one subset is directly and independently encoded, and multiple subsets are jointly encoded, thereby improving the utilization efficiency of resources and improving the reliability of transmission.

[0016] Optionally, if the first AI / ML data subset and the second AI / ML data subset are of different data types, the data of the first AI / ML data subset and the second AI / ML data subset are independently encoded and modulated. That is, the first communication device encodes the first AI / ML data set, and in the case where the first control information only contains the first AI / ML data set, the first AI / ML data set contains data subsets of different types, and multiple subsets are independently encoded, thereby avoiding the increase of processing complexity and time caused by joint encoding of different data types, and reducing the communication delay.

[0017] Optionally, if the data of the same type in the first AI / ML data set and the HARQ-ACK and CSI part 1, CSI part 2 and other signaling are jointly encoded and modulated, and the data of different types are independently encoded and modulated. Since HARQ-ACK and CSI part 1, CSI part 2 are all mapped to the first data channel for transmission, the data of the same type can also be jointly encoded, thereby improving the utilization efficiency of resources and improving the reliability of transmission. The data of different types can also be independently encoded, thereby reducing the processing complexity and reducing the communication delay.

[0018] In a possible design scheme, the second AI / ML data set can at least include a third AI / ML data subset and / or a fourth AI / ML data subset, that is, the first AI / ML data set in this scheme is not limited to include how many data subsets, which can be flexibly changed according to actual conditions.

[0019] Optionally, the second AI / ML dataset, and the third AI / ML data subset and the fourth AI / ML data subset can contain one or more of the following data types: monitoring information, training data, inference data, model management related information, model metadata and model auxiliary information, specific parameter information of the model, or any other possible data, without limitation.

[0020] Optionally, if the third AI / ML data subset and the fourth AI / ML data subset have the same data type, the third AI / ML data subset corresponds to a third priority sequence number, and the fourth AI / ML data subset corresponds to a fourth priority sequence number, the third priority sequence number is the same as the fourth priority sequence number. That is, the priority relationship of the data subsets in the first AI / ML dataset is determined based on the data type of each data subset. By determining the priority relationship, data with the same priority sequence number can be merged / simultaneously processed, saving overhead and reducing redundancy.

[0021] Optionally, if the third AI / ML data subset and the fourth AI / ML data subset have different data types, the third AI / ML data subset corresponds to a third priority sequence number, and the fourth AI / ML data subset corresponds to a fourth priority sequence number, the third priority sequence number is different from the fourth priority sequence number. That is, the priority relationship of the data subsets in the second AI / ML dataset is determined based on the data type of each data subset. By determining data with different priority sequence numbers, the data with a high priority sequence number is processed first when processing data, to ensure the reliability of the transmission of the data set with a high priority sequence number.

[0022] Further, the first communication device receives the priority sequence number of the data subset in the second AI / ML dataset, and transmits the first data channel according to the priority sequence number. According to the priority sequence number, the data subsets in the second AI / ML dataset are sequentially carried in the first data channel for transmission, ensuring that the data with a high priority sequence number is successfully transmitted and not lost, and improving the transmission reliability of the high-priority data.

[0023] Optionally, the priority sequence number of the data subset in the second AI / ML dataset is configured by higher layer signaling, or is implicitly indicated by the logical channel priority.

[0024] Optionally, when the third AI / ML data subset and the fourth AI / ML data subset are of different data types, the communication device further comprises one or more of the following features: the third AI / ML data subset corresponds to a first modulation and coding scheme (MCS) table, the fourth AI / ML data subset corresponds to a second MCS table, the first MCS table and the second MCS table are different; the third AI / ML data subset corresponds to a first multiple-input multiple-output (MIMO) layer number, the fourth AI / ML data subset corresponds to a second MIMO layer number, the first MIMO layer number and the second MIMO layer number are different; the third AI / ML data subset corresponds to a first demodulation reference signal (DMRS) mapping method, the fourth AI / ML data subset corresponds to a second DMRS mapping method, the first DMRS mapping method and the second DMRS mapping method are different. That is, the data in the second AI / ML data set corresponds to a priority order, and the priority order determines the processing manner of the data in the second AI / ML data set in the first data channel. Specifically, the processing manner of data with the same priority / priority order can be the same, and the processing manner of data with different priorities / priority orders can be different, so that each type of data can be processed in an appropriate manner, avoiding data loss caused by improper processing, and improving the reliability of communication.

[0025] In a second aspect, a communication device is provided. The communication device comprises modules for performing the method of the first aspect.

[0026] In a possible design, the communication device of the second aspect can further include a transceiver. The transceiver can be a transceiver circuit or an interface circuit. The transceiver can be used for the communication device of the second aspect to communicate with other communication devices.

[0027] In a possible design, the communication device of the second aspect can further include a memory. The memory can be integrated with the processor, or can be separately arranged. The memory can be used to store a computer program and / or data related to the method of the first aspect.

[0028] In embodiments of the present application, the communication device of the second aspect can be a terminal device, or can be a module (such as a processor, a chip, or a chip system) applied to a terminal device for execution, or can be a logic node, a logic module, or a software implementation capable of implementing all or part of the functions of a terminal device.

[0029] It can be understood that the technical effects of the device of the second aspect can also be referred to the above-mentioned related introduction of the first aspect, and will not be repeated here.

[0030] In a third aspect, a communication device is provided. The communication device comprises a processor coupled with a memory, and the processor is configured to execute instructions stored in the memory, so that the communication device performs the method of the first aspect.

[0031] In one possible design, the communication device of the third aspect may further include a transceiver. This transceiver can be a transceiver circuit or an interface circuit. The transceiver can be used for communication between the third aspect's communication device and other communication devices.

[0032] In the embodiments of this application, the communication device of the third aspect may be the terminal device of the first aspect, or a chip (system) or other component or assembly disposed in the terminal device, or a device containing the terminal device.

[0033] Furthermore, the technical effects of the communication device in the third aspect can be referenced from the technical effects of the method in the first aspect, and will not be elaborated here.

[0034] Fourthly, a communication device is provided, comprising: a processor and a memory; the memory is used to store instructions that, when executed by the processor, cause the communication device to perform the method as described in the first aspect.

[0035] In one possible design, the communication device of the fourth aspect may further include a transceiver. This transceiver can be a transceiver circuit or an interface circuit. The transceiver can be used by the communication device of the fourth aspect to communicate with other communication devices.

[0036] In the embodiments of this application, the communication device of the fourth aspect may be the terminal device of the first aspect, or a chip (system) or other component or assembly disposed in the terminal device, or a device containing the terminal device.

[0037] Furthermore, the technical effects of the communication device in the fourth aspect can be referenced from the technical effects of the method in the first aspect, and will not be elaborated here.

[0038] Fifthly, a chip is provided, comprising: a controller and an interface circuit, wherein the controller is configured to interact with other devices via the interface circuit to perform the method as described in the first aspect.

[0039] A sixth aspect provides a communication system. The communication system includes at least one of the following: means for performing the method of the first aspect.

[0040] A seventh aspect provides a computer-readable storage medium including storage of a computer program or instructions that, when executed, cause the method of the first aspect to be performed.

[0041] Eighthly, a computer program product is provided, including a computer program or instructions that, when executed, cause the method of the first aspect to be performed. Attached Figure Description

[0042] Figure 1 An architecture of a communication system provided by an embodiment of the present application Figure 1

[0043] Figure 2 An architecture of a communication system provided by an embodiment of the present application Figure 2

[0044] Figure 3 A flowchart of a communication method provided by an embodiment of the present application

[0045] Figure 4 An example diagram of a result of monitoring provided by an embodiment of the present application

[0046] Figure 5 An example diagram of auxiliary information of monitoring provided by an embodiment of the present application

[0047] Figure 6 A structure of a communication device provided by an embodiment of the present application Figure 1

[0048] Figure 2 A structure of a communication device provided by an embodiment of the present application Figure 2 DETAILED DESCRIPTION

[0049] The technical solutions of the embodiments of the present application can be applied to various communication systems, such as a wireless network (Wi-Fi) system, a vehicle to everything (V2X) communication system, a device to device (D2D) communication system, a vehicle networking communication system, a 4th generation (4G) mobile communication system such as a long term evolution (LTE) system, a worldwide interoperability for microwave access (WiMAX) communication system, a 5th generation (5G) mobile communication system such as a new radio (NR) system, and a future communication system such as a 5.5G, a 6th generation (6G) mobile communication system, etc.

[0050] For the convenience of understanding, the technical terms involved in the present application will be introduced first.

[0051] 1. Wireless communication system:

[0052] ​​​​Wireless communication systems have evolved from the first generation of analog communication to 5G NR and existing 6G technology. In this complex evolution process, high throughput and large connection are the core challenges of wireless communication networks. In order to cope with the above challenges, 5G communication proposes enhanced mobile broadband (eMBB), ultra-reliable, low latency communications (URLLC), massivemachine type communications (mMTC) and other applications as technical targets. And the future 6G wireless communication system will evolve towards larger throughput, lower latency, higher reliability, larger connection number, higher spectrum utilization, etc.

[0053] With the continuous development of AI / ML three driving forces-power, algorithm and data related technologies, AI / ML technology has triggered a new round of technological revolution in human society. Existing technology research shows that AI / ML has important application potential in many aspects such as modeling, learning, channel prediction, intelligent signal generation and processing, network state tracking and intelligent scheduling, network optimization deployment in complex unknown environment, and is expected to promote the evolution of future communication paradigm and the transformation of network architecture, which has very important significance and value for 6G technology research.

[0054] 2. AI terminology:

[0055] Model switching: deactivating the currently active AI / ML model and activating a different AI / ML model for a specific AI / ML enabled function;

[0056] Model activation: enabling an AI / ML model for a specific AI / ML function;

[0057] Model deactivation: disabling an AI / ML model for a specific AI / ML function;

[0058] Model fallback: fallback from an AI / ML model to a non-AI model;

[0059] Model selection: the process of selecting an AI / ML model for activation among multiple models for the same AI / ML function;

[0060] Model update: the process of updating model parameters and / or model structure;

[0061] Sub-model (sub-AI / ML model) switching: deactivating the currently active AI / ML sub-model and activating a different AI / ML sub-model for a specific function;

[0062] Sub-model activation: enabling an AI / ML sub-model for a specific AI / ML function;

[0063] Model deactivation: turning off a sub-AI / ML sub-model for a specific AI / ML function;

[0064] Sub-model fallback: fallback from an AI / ML sub-model to a non-AI sub-model;

[0065] Sub-model selection: a process of selecting one AI / ML sub-model for activation among multiple sub-models for the same function;

[0066] Sub-model update: a process of updating sub-model parameters and / or sub-model structure.

[0067] To solve the above technical problems, embodiments of the present application provide the following technical solutions.

[0068] The technical solutions in the present application will be described below with reference to the drawings.

[0069] In the embodiments of the present application, "indication" can include direct indication and indirect indication, and can also include explicit indication and implicit indication. The information indicated by a certain information is referred to as to-be-indicated information, and there are many ways to indicate the to-be-indicated information in the implementation process, for example, but not limited to, the to-be-indicated information itself or the index of the to-be-indicated information can be directly indicated. The to-be-indicated information can also be indirectly indicated by indicating other information, where the other information and the to-be-indicated information have an association relationship. The to-be-indicated information can also be indicated only by a part of the to-be-indicated information, and the other part of the to-be-indicated information is known or agreed in advance. For example, the indication of a specific information can also be achieved by means of the arrangement order of each information agreed in advance (for example, a protocol), thereby reducing the indication overhead to a certain extent. At the same time, the common part of each information can be identified and indicated uniformly, so as to reduce the indication overhead caused by separately indicating the same information.

[0070] In addition, the specific indication manner can also be various existing indication manners, for example, but not limited to, the above indication manners and various combinations thereof. The specific details of various indication manners can refer to the prior art, which will not be described herein. As can be seen from the above, for example, when multiple information of the same type needs to be indicated, the indication manners of different information can be different. In the implementation process, the required indication manner can be selected according to the specific needs, and the selected indication manner is not limited in the embodiments of the present application, so that the indication manner involved in the embodiments of the present application should be understood as covering various methods that can enable the to-be-indicated party to know the to-be-indicated information.

[0071] It should be understood that the to-be-indicated information can be sent together as a whole or can be sent separately in multiple sub-information, and the sending period and / or sending occasion of the sub-information can be the same or different. The specific sending method is not limited by the embodiments of the present application. The sending period and / or sending occasion of the sub-information can be predefined, for example, predefined according to a protocol, or can be configured by the sending end device by sending configuration information to the receiving end device.

[0072] In the present application, “sending information” can be understood as that a device sends information to another device, or can also be understood as that a logical module in a device sends information to another logical module. For example, “a network device sends information” can be understood as that the network device sends information to another device (such as a terminal or another network device), or can be understood as that a logical module 1 in the network device sends information to a logical module 2 in the network device.

[0073] In the present application, “receiving information” can be understood as that a device receives information from another device, or can also be understood as that a logical module in a device receives information from another logical module. For example, “a network device receives information” can be understood as that the network device receives information from another device (such as a terminal or another network device), or can be understood as that a logical module 1 in the network device receives information from a logical module 2 in the network device.

[0074] In the present application, “sending information to (for example, a terminal)” or related illustrations in the drawings can be understood as that the destination of the information is the terminal. It can include directly or indirectly sending information to the terminal. “Receiving information from (for example, a terminal)” or “receiving information sent by (for example, a terminal)” or “receiving information from (for example, a terminal)” or related illustrations in the drawings can be understood as that the source of the information is the terminal. It can include directly or indirectly receiving information from the terminal. The information can be processed as necessary between the source and the destination of the information, for example, format change, etc., but the destination can understand the valid information from the source. Similar expressions in the present application can be similarly understood, and will not be repeated here.

[0075] The predefinition or pre-configuration can be realized by pre-storing corresponding codes, tables or other means for indicating relevant information in the device, and the embodiments of the present application do not limit the specific implementation manner. The storage can be in one or more memories. The one or more memories can be separately arranged or integrated in the encoder or decoder, processor or communication device. The one or more memories can be partially separately arranged and partially integrated in the decoder, processor or communication device. The memory can be any form of storage medium, and the embodiments of the present application do not limit the same.

[0076] The protocol referred to in the embodiments of the present application can refer to a protocol family in the communication field, a standard protocol similar to the protocol family frame structure, or a relevant protocol applied to a future communication system, and the embodiments of the present application do not limit the same.

[0077] In the embodiments of the present application, the descriptions such as "when", "in the case of", "if" and "whether" all refer to that the device will make corresponding processing under certain objective condition, and are not limited in time, and do not require the device to have a judgment action when implemented, nor mean that there are other limitations.

[0078] In the description of the embodiments of the present application, unless otherwise specified, " / " represents that the objects before and after the " / " are in an "or" relationship, for example, A / B can represent A or B; "and / or" in the embodiments of the present application is only a description of the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone, where A and B can be singular or plural. In addition, in the description of the embodiments of the present application, unless otherwise specified, "multiple" means two or more than two. "At least one of the following" or the like means any combination of the items, including any combination of single item or multiple items. For example, at least one of a, b or c can represent: a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple. In addition, in order to clearly describe the technical solutions of the embodiments of the present application, in the embodiments of the present application, "first", "second", and the like are used to distinguish the functions and effects of the same items or similar items. Those skilled in the art can understand that "first", "second", and the like do not limit the quantity and execution order, and "first", "second", and the like do not necessarily mean different. At the same time, in the embodiments of the present application, "exemplary" or "for example" means to serve as an example, illustration or description. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as more preferred or more advantageous than other embodiments or design schemes. Rather, "exemplary" or "for example" is used to present the relevant concept in a specific manner, for understanding.

[0079] The network architecture and service scenarios described in the embodiments of the present application are used to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art can know that, with the evolution of network architecture and the appearance of new service scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0080] In order to understand the embodiments of the present application, first, a communication system suitable for the embodiments of the present application is described in detail. For example, as shown in the figure, the communication system mainly includes at least one of the following: a first communication device and a second communication device. Figure 2

[0081] ​The first communication device can be a terminal-side device, such as a terminal device, or the first communication device can also be a network-side device, such as a network device, such as an access network device, or a network element of a core network, or can also be a network element of a management domain on the network side. Similarly, the second communication device can also be a terminal-side device, such as a terminal device, or the second communication device can also be a network-side device, such as a network device, such as an access network device, or a network element of a core network, or can also be a network element of a management domain on the network side. In other words, the interaction between the first communication device and the second communication device in the communication system can be an interaction between a terminal and a network side, or an interaction between network elements on the network side, and the specific implementation is not limited.

[0082] For example, a possible, non-limiting architecture of the communication system can be as shown in Figure 2 As shown in Figure 2 The communication system 10 includes a radio access network (RAN) 100, a core network (CN) 200, and an Internet 300. The RAN 100 includes at least one RAN node (such as 110a and 110b in Figure 2 , collectively referred to as 110) and at least one terminal (such as 120a-120j in Figure 2 , collectively referred to as 120). The RAN 100 can further include other RAN nodes, such as wireless relay devices and / or wireless backhaul devices (not shown in Figure 2 ), etc. The terminals 120 are connected to the RAN nodes 110 in a wireless manner. The RAN nodes 110 are connected to the core network 200 in a wireless or wired manner. The core network devices in the core network 200 and the RAN nodes 110 in the RAN 100 can be different physical devices, respectively, or can be the same physical device integrated with the logical functions of the core network and the logical functions of the radio access network.

[0083] The RAN 100 can be a 3GPP related cellular system, such as a 4G, 5G mobile communication system, or a future-oriented evolution system (such as a 6G mobile communication system). The RAN 100 can also be an open radio access network (O-RAN or ORAN), a cloud radio access network (CRAN), or a wireless fidelity (WiFi) system. The RAN 100 can also be a communication system that combines two or more of the above systems.

[0084] RAN node 110, sometimes also referred to as access network equipment, RAN entity, or access node, constitutes part of the communication system and is used to help terminals achieve wireless access. Multiple RAN nodes 110 in communication system 10 can be of the same type or different types. In some scenarios, the roles of RAN node 110 and terminal 120 are relative, for example... Figure 2 Network element 120i can be a helicopter or a drone, and it can be configured as a mobile base station. For terminals 120j that access RAN 100 through network element 120i, network element 120i is a base station; however, for base station 110a, network element 120i is a terminal. RAN node 110 and terminal 120 are sometimes referred to as communication devices, for example... Figure 3 Network elements 110a and 110b can be understood as communication devices with base station functions, while network elements 120a-120j can be understood as communication devices with terminal functions.

[0085] In one possible scenario, a RAN node can be a base station, an evolved NodeB (eNodeB), an access point (AP), a transmission reception point (TRP), a next-generation NodeB (gNB), a next-generation base station in a 6th-generation (6G) mobile communication system, a base station in a future mobile communication system, or an access node in a WiFi system, etc. A RAN node can also be a macro base station (such as...) Figure 3 110a), micro base stations or indoor stations (such as Figure 4 The RAN node can be a relay node or donor node (as described in section 110b), or a wireless controller in a CRAN scenario. Optionally, the RAN node can also be a server, wearable device, vehicle, or in-vehicle equipment. For example, the access network equipment in vehicle-to-everything (V2X) technology can be a roadside unit (RSU). All or part of the functions of the RAN node in this application can also be implemented through software functions running on hardware, or through virtualization functions instantiated on a platform (e.g., a cloud platform). The RAN node in this application can also be a logical node, logical module, or software capable of implementing all or part of the RAN node functions.

[0086] In another possible scenario, a terminal is assisted by multiple RAN nodes to implement wireless access, and different RAN nodes respectively implement part of functions of a base station. For example, a RAN node can be a central unit (CU), a distributed unit (DU), a CU-control plane (CP), a CU-user plane (UP), or a radio unit (RU), etc. The CU and the DU can be separately arranged, or can be included in the same network element, for example, in a baseband unit (BBU). The RU can be included in a radio frequency device or a radio frequency unit, for example, in a remote radio unit (RRU), an active antenna unit (AAU), or a remote radio head (RRH).

[0087] In different systems, the CU (or CU-CP and CU-UP), DU or RU can also have different names, but those skilled in the art can understand their meanings. For example, in an ORAN system, the CU can also be referred to as an O-CU (open CU), the DU can also be referred to as an O-DU, the CU-CP can also be referred to as an O-CU-CP, the CU-UP can also be referred to as an O-CU-UP, and the RU can also be referred to as an O-RU. For the convenience of description, the CU, CU-CP, CU-UP, DU and RU are taken as examples for description in this application. Any one of the CU (or CU-CP, CU-UP), DU and RU in this application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0088] It can be understood that the RAN node described above can be a newly defined name, and the RAN node can also have different expressions, such as an access node, a network device, a wireless access node, etc., without limitation. In this application, the network device is used for description hereinafter without special description.

[0089] The terminal can also be referred to as a terminal device, user equipment (UE), mobile station, mobile terminal, etc. The terminal can be widely applied to various scenarios, such as device-to-device (D2D), vehicle-to-everything (V2X) communication, machine-type communication (MTC), internet of things (IOT), virtual reality, augmented reality, industrial control, automatic driving, remote medical treatment, smart power grid, smart furniture, smart office, smart wear, smart transportation, smart city, etc. The terminal can be a mobile phone, tablet computer, computer with wireless transceiver function, wearable device, vehicle, unmanned aerial vehicle, helicopter, airplane, ship, robot, mechanical arm, smart home device, etc. Embodiments of the present application do not limit the device form of the terminal.

[0090] In the communication system, after obtaining the AI / ML data set, the first communication device does not directly send the AI / ML data set to the second communication device, but determines the priority order of the plurality of data sets in the AI / ML data set, and carries the data set with high priority order by the first control information, and carries the data set with low priority order by the first data channel. Since the transmission of the first control information is more reliable than the transmission of the data in the first data channel, the reliability of the transmission of the data set with high priority order can be ensured, the reporting error is avoided as much as possible, and the efficient use of transmission resources is realized.

[0091] The communication method will be further described below with reference to the accompanying drawings. It can be understood that the present application is exemplified by taking the first communication device and the second communication device as the execution subject of the interaction, but the present application does not limit the execution subject of the interaction. For example, the methods executed by the first communication device and the second communication device in the present application can also be executed by the modules (such as processors, chips, or chip systems, etc.) of the communication device, and can also be realized by logical nodes, logical modules or software which can realize all or part of the functions of the communication device.

[0092] The interaction process between the communication devices in the communication system will be specifically described below by means of method embodiments with reference to the accompanying drawings. The communication method provided by the embodiments of the present application can be applied to the above-mentioned communication system and specifically applied to various scenarios mentioned in the above-mentioned communication system. The following will be specifically described.

[0093] Figure 5 A flowchart of a communication method according to the embodiments of the application is shown. The communication method is applied to the above-mentioned communication system, and mainly involves the interaction between the first communication device and the second communication device.

[0094] AsOrder of priority relationship As shown, the flow of the communication method is as follows:

[0095] S301, the first communication device acquires an artificial intelligence AI / machine learning ML data set.

[0096] The AI / ML data set is data that needs to be transmitted between the first communication device and the second communication device, and can be used for steps related to AI / ML life cycle management, such as model supervision, model management, model training, model inference, etc.

[0097] The AI / ML data set can be one or more, such as one AI / ML data set, such as multiple AI / ML data sets, such as a first AI / ML data set and a second AI / ML data set, and such as a first AI / ML data set, a second AI / ML data set, and a third AI / ML data set. For ease of understanding, two AI / ML data sets are introduced below as an example, and more than two AI / ML data sets can be understood by reference, which will not be described here.

[0098] The first AI / ML data set can include data of the same type (which can also be replaced by category / dimension, etc.) or different types, and the priorities of the different types of data are different, which can be represented by their respective priority numbers (which can also be replaced by priority / priority index, etc.). For example, it can contain one or more of the following data types: monitoring information, training data, inference data, model management related information, model metadata and model auxiliary information, and specific parameter information of the model. For example, it can contain one or more of the following data types: channel state, link performance, air interface overhead, throughput, latency, and other communication data, or any other possible data type, which is not limited. The following will be introduced respectively.

[0099] 1) Monitoring information, training data, and inference data are dimension-related data collected by the first communication device, or in other words, these data are collected by the first communication device and sent to the second communication device, and the second communication device determines whether to perform model switching or rollback, etc. The following will be introduced respectively.

[0100] The monitoring information can include data related to the results of monitoring and the auxiliary results of monitoring.

[0101] The result of the monitoring is information that can be used to directly describe the performance of the model, and can include at least one of: an intermediate key performance indicator (KPI), or a final KPI. For example, the intermediate KPI can be an accuracy related KPI, such as a channel state information (CSI) compression accuracy related KPI: a squared generalized cosine similarity (SGCS), a normalized mean square error (NMSE), etc.; or a beam prediction accuracy related KPI: a beam prediction accuracy, a channel quality difference of predicted beams, etc.; or a positioning accuracy related KPI: a percentile in a cumulative distribution function (CDF) of horizontal accuracy, a vertical accuracy, a horizontal and vertical accuracy, etc.; or a radio frequency map (RF map) predicted accuracy of a channel / power / modulation and coding scheme (MCS) / interference / beam index / ul time advance, etc. task, a difference between a RF map predicted wireless channel parameter (such as a multipath channel parameter, i.e. power, delay, horizontal / vertical angle of arrival, angle of departure of each path) and a true value of the wireless channel parameter, etc.

[0102] The final KPI can be a communication function related data, such as a link performance, an air interface overhead, an inference / training complexity, a storage overhead, a latency, a UE throughput, a reference signal overhead; or a communication data related indicator, such as a data distribution, a data frequency shift, a performance bias, etc.

[0103] For example Priority relationshipAs shown, the second communication device (e.g., network side or base station) has a RF MAP, which is an AI model, the RF MAP can predict the channel condition and select a proper modulation and coding scheme (MCS), the second communication device sends the MCS index to the first communication device (e.g., UE), i.e., indicates the MCS, the first communication device demodulates and decodes the received link data based on the MCS, and obtains the link performance, such as the indication of link decoding error (i.e., negative acknowledgment (NACK)), throughput, and the link error rate in a period of time. The throughput or the link error rate in a period of time can be used as the supervision result of the AI model, and the supervision result is fed back, e.g., the first communication device sends the indication of whether the link is decoded correctly and the supervision result to the second communication device. The second communication device manages the supervision model based on the supervision result, e.g., when the throughput of the link is lower than expected, the second communication device can perform model management, such as model switching, model rollback, and the like. In the above example, the supervision data is related to the management of the model, and the reliability requirement is high, therefore the supervision result obtained by the first communication device can be transmitted in the first control channel.

[0104] The supervised auxiliary result is usually information used to assist in describing the performance of the model, e.g., can include at least one of: actual measurement result, or actual channel state, or ground truth label. The actual measurement result can also be actual test result, actual measurement feedback, or actual feedback response, etc. The actual channel condition can be actual precoding matrix, actual CSI feedback, actual channel measurement condition, actual measured wireless channel parameter, etc. The ground truth label can be actual user position, actual channel map, etc.

[0105] For example HARQ-ACK, CSI part 1, CSI part 2, AI-part1, PUSCHAs shown, the second communication device (such as a network side or a base station) has an RF MAP, which is an AI model. The RF MAP can predict the channel condition and select a suitable MCS. The second communication device sends the MCS index to the first communication device (such as a UE), i.e., indicates the MCS. The first communication device demodulates and decodes the received link data based on the MCS to obtain a decoding result, such as a current link decoding error, i.e., a negative acknowledgement. The first communication device can also obtain parameters of the actual channel state through other means (such as a sensing module or a sensing communication). The first communication device sends the negative acknowledgement and the parameters of the actual channel state to the second communication device. The second communication device supervises based on the negative acknowledgement and the actual channel state and judges the reason for the current communication link decoding error. For example, the actual channel condition reflects that the current channel state is very good. The second communication device can understand that the link decoding error is a problem of the MCS index output by the AI model. Therefore, the second communication device starts model management, such as model switching or model rollback, and the like. For another example, the actual channel condition reflects that a sudden interference occurs in the current channel. The second communication device can understand that the link decoding error is a channel reason and is irrelevant to the MCS index output by the AI model. Therefore, the second communication device does not perform any processing. In the above examples, the supervision data is related to the management of the model and has high reliability requirements. Therefore, the first communication device can transmit the supervision result in the first control channel.

[0106] The training data is a set of input data required for the AI / ML model training function, which can include at least one of the following: structured data, image data, time series data, text data, channel data of multiple areas, communication data, historical data, sensing data, and the like.

[0107] The inference data is a set of input data required for the AI / ML inference function, which can include at least one of the following: signal quality related data, location related data, Qos related data, busy green degree related data, time related data, and the like.

[0108] 2) Model management related information, model metadata and model auxiliary information, and specific parameter information of the model are dimension related data of the model data, or in other words, these data are data that play an important role in the life cycle of the model.

[0109] Among them, the model management related information is capable of being used to manage and distinguish different models, which can include at least one of the following: model identities, dataset identities, functionality identities, sub-model identities, sub-dataset identities, sub-functionality identities, model switching, model activation, model deactivation, model rollback, model selection, model update, sub-model switching, sub-model activation, model deactivation, sub-model rollback, sub-model selection, sub-model update.

[0110] The model metadata and model auxiliary information can be understood as key information for assisting model management, model identification, or key information in AI / ML life cycle management, which can include at least one of the following: applicable scenario information, application / applicable conditions, information of an agent, input of a model, data of a model, auxiliary information for inference, applicable features / functions, etc.

[0111] The specific parameters of the model can be understood as at least one of the following: structure of the model, parameters of the model (such as gradient, weight, etc.), hyperparameters of the model, etc.

[0112] Embodiments of the present application do not limit the acquisition method of the model management related information, the model metadata and the model auxiliary information, and the specific parameter information of the model, which can be pre-configured to the communication device in the model construction process, and the communication device can directly obtain, or the communication device can obtain based on other modules.

[0113] Since the first AI / ML dataset described above contains different types of data, such as monitoring information, training data, etc., and the model management related information, model metadata, etc., the subsets can also be divided according to the type of data, such as each type of data in the first AI / ML dataset being an AI / ML data subset, which will be described in detail below.

[0114] If the first AI / ML dataset contains the same type of data, the first AI / ML dataset can no longer be subdivided into subsets, or the first AI / ML dataset can be directly considered as belonging to one subset of the AI / ML dataset set, such as the first AI / ML data subset / second AI / ML data subset, for example, the first AI / ML data subset or the second AI / ML data subset both contain monitoring information, or training data, or one or more of the other various types of data described above, which are not listed one by one here. In addition, in the case where the first AI / ML dataset contains the same type of data, two or more subsets can also be provided, but each subset contains the same type of data and the same priority sequence number, for example, the first AI / ML data subset and the second AI / ML data subset can be monitoring information, the first AI / ML data subset corresponds to the first priority sequence number, and the second AI / ML data subset corresponds to the second priority sequence number, at this time, the first priority sequence number is the same as the second priority sequence number.

[0115] If the first AI / ML dataset contains different types of data, the first AI / ML dataset can be subdivided into more subsets, such as the first AI / ML data subset and the second AI / ML data subset. At this time, the first AI / ML data subset corresponds to the first priority sequence number, and the second AI / ML data subset corresponds to the second priority sequence number, and the first priority sequence number is different from the second priority sequence number. For example, the data type of the first AI / ML data subset is monitoring information, and the data type of the second AI / ML data subset is training data, the first AI / ML data subset corresponds to the first priority sequence number, and the second AI / ML data subset corresponds to the second priority sequence number, and the first priority sequence number is greater than the second priority sequence number. For example, the data type of the first AI / ML data subset is related data of model management, and the data type of the second AI / ML data subset is metadata and auxiliary information of the model, the first AI / ML data subset corresponds to the first priority sequence number, and the second AI / ML data subset corresponds to the second priority sequence number, and the first priority sequence number is greater than or equal to the second priority sequence number. For example, the data type of the first AI / ML data subset is metadata and auxiliary information of the model, and the data type of the second AI / ML data subset is specific parameter information of the model, the first AI / ML data subset corresponds to the first priority sequence number, and the second AI / ML data subset corresponds to the second priority sequence number, and the first priority sequence number is greater than or equal to the second priority sequence number.

[0116] It can be understood that in the embodiments of the present application, the larger the priority sequence number is, the higher the priority is, that is, the higher the reliability requirement or the delay requirement is, or the higher the multiplexing priority is, such as the priority of priority sequence number 1 is higher than that of priority sequence number 0. Of course, it can also be that the smaller the priority sequence number is, the higher the priority is, that is, the higher the reliability requirement or the delay requirement is, such as the priority of priority sequence number 0 is higher than that of priority sequence number 1. The value of the specific priority sequence number can also not determine the priority relationship of the data, and the priority relationship of the data can be predefined by the protocol or configured by the higher layer. In addition, the above-mentioned priority sequence number can also be replaced by priority, multiplexing priority sequence number, priority index and other possible expressions, which are not limited here.

[0117] The second AI / ML data set can include the same type of data, or different types of data, and the different types of data correspond to a priority sequence number (which can also be replaced by priority / priority index, etc.), for example, it can contain one or more of the following data types: monitoring information, training data, inference data, model management related information, model metadata and model auxiliary information, specific parameter information of the model, or any other possible data type, which is not limited here, which will be introduced below. The specific second AI / ML data set can include one or more data types of specific content, which is not repeated here, please refer to the related introduction in the first AI / ML data set.

[0118] Since the above-mentioned second AI / ML data set contains different types of data, such as monitoring information, training data, and model management related information, model metadata, etc., it can also be divided into subsets according to the type of data, such as each type of data in the second AI / ML data set is an AI / ML data subset, which will be introduced in detail below.

[0119] If the second AI / ML data set contains the same type of data, the second AI / ML data set can no longer be subdivided, or the second AI / ML data set can be directly considered as belonging to a subset of the AI / ML data set, such as a third AI / ML data subset or a fourth AI / ML data subset, for example, the third AI / ML data subset or the fourth AI / ML data subset contains monitoring information, or training data, or one or more of the other types of data described above, which will not be listed one by one here. In addition, in the case where the second AI / ML data set contains the same type of data, two or more subsets can also be provided, but each subset contains the same type of data and the same priority sequence number, for example, the third AI / ML data subset and the fourth AI / ML data subset can be monitoring information, the third AL / ML data subset corresponds to the third priority sequence number, and the fourth AL / ML data subset corresponds to the fourth priority sequence number, at this time, the third priority sequence number and the fourth priority sequence number are the same.

[0120] If the second AI / ML dataset contains different types of data, the second AI / ML dataset can be further subdivided into more subsets, such as a third AI / ML data subset and a fourth AI / ML data subset. At this time, the third AL / ML data subset corresponds to a third priority sequence number, and the fourth AL / ML data subset corresponds to a fourth priority sequence number, and the third priority sequence number is different from the fourth priority sequence number. For example, the data type of the third AI / ML data subset is monitoring information, the data type of the fourth AI / ML data subset is training data, the third AL / ML data subset corresponds to a third priority sequence number, the fourth AL / ML data subset corresponds to a fourth priority sequence number, and the third priority sequence number is greater than the fourth priority sequence number. For another example, the data type of the third AI / ML data subset is related data of model management, the data type of the fourth AI / ML data subset is metadata and auxiliary information of the model, the third AL / ML data subset corresponds to a third priority sequence number, the fourth AL / ML data subset corresponds to a fourth priority sequence number, and the third priority sequence number is greater than or equal to the fourth priority sequence number. For another example, the data type of the third AI / ML data subset is metadata and auxiliary information of the model, the data type of the fourth AI / ML data subset is specific parameter information of the model, the third AL / ML data subset corresponds to a third priority sequence number, the fourth AL / ML data subset corresponds to a fourth priority sequence number, and the third priority sequence number is greater than or equal to the fourth priority sequence number.

[0121] In addition, the first AI / ML dataset and the second AI / ML dataset can contain the same (or similar / near) data types, but in practice, the data types contained by the two are required to be different to avoid redundancy. For example, when the first AI / ML dataset is monitoring information, the second AI / ML dataset can be training data, or inference data, or other possible data types, which are not limited here.

[0122] As can be seen from the above introduction, the data types contained by the two are different, the priority sequence numbers corresponding to the data types can be different, and the priority sequence numbers of the first AI / ML dataset and the second AI / ML dataset can be different, indicating that the transmission reliability and / or delay levels of the first AI / ML dataset and the second AI / ML dataset are different, that is, the transmission modes of the two can be different, which will be introduced below.

[0123] S302, the first communication device sends the first control information and the first data channel according to the priority sequence numbers of the first AI / ML dataset and the second AI / ML dataset.

[0124] The first control information can be downlink control information (DCI), uplink control information (UCI), sidelink control information (SCI), or can also be future new signaling, and the specific limitation is not made. The first control information can contain the first AI / ML data set, and optionally, the first control information can also contain other fields / information elements, such as existing fields / information elements, such as hybrid automatic repeat request-acknowledgement (HARQ-ACK), channel state information (CSI) part 1, CSI part 2, etc.

[0125] The first data channel can be a physical downlink shared channel (PDSCH), a physical downlink control channel (PDCCH), a physical sidelink shared channel (PSSCH), or can also be a future new channel, and the specific limitation is not made. The first data channel can contain the second AI / ML data set described above, and the first control information can also be multiplexed in the first data channel, so that the reliability of the first AI / ML data set transmission with high priority order number is higher.

[0126] Wherein, after the first AI / ML data set (optionally, other fields / information elements) is carried into the first control information, the first communication device can encode the first control information according to the priority relationship (or multiplexing priority) of the first AI / ML data set, obtain the encoded information, and then multiplex (or map) the encoded information to the first data channel according to the priority relationship (or multiplexing priority) of the first AI / ML data set. Details are as follows.

[0127] In a possible case, when the first control information only contains the first AI / ML data set, the priority relationship of the first AI / ML data set can be the priority relationship between the same or different data / data subsets of the first AI / ML data set itself. The priority relationship can be dynamically determined or defined by protocol, which is described as follows.

[0128] Case 1: Protocol predefinition:

[0129] The multiplexing rule predefined by the protocol is mainly applicable to the scenario where the transmission reliability and / or latency level of the data types in the AI / ML data set is relatively determined. For example, the protocol can predefine the priority relationship of each of the same / different types of AI / ML data / data subset. In this case, the first communication device can determine the priority relationship of the data / data subset in the first AI / ML data set according to the data type of the data / data subset in the first AI / ML data set according to the definition of the protocol.

[0130] For example, the first AI / ML data set contains a data subset of one data type, such as the first AI / ML data subset and the second AI / ML data subset both contain monitoring data of a communication task. At this time, the priority relationship of the first AI / ML data subset and the second AI / ML data subset is the same priority, at this time, the same priority can be represented by the same priority sequence number of the first AI / ML data subset and the second AI / ML data subset, or the same value of the priority sequence number, such as the value of the first priority sequence number is 0, denoted as priority sequence number 0, and the value of the second priority sequence number is also 0, also denoted as priority sequence number 0, and the two are the same priority.

[0131] For another example, the first AI / ML data set contains multiple data types, such as the first AI / ML data set includes the data types of the first AI / ML data subset and the second AI / ML data subset, such as the first AI / ML data subset is model management related parameters, and the second AI / ML data subset is metadata and auxiliary information of the model, then the priority relationship of the first AI / ML data subset and the second AI / ML data subset can be that the priority of the first AI / ML data subset is greater than the priority of the second AI / ML data subset, that is, the priority of the model management related parameters is greater than the priority of the metadata and auxiliary information of the model. For example, the value of the first priority sequence number of the first AI / ML data subset is 0, denoted as priority sequence number 0, and the value of the second priority sequence number of the second AI / ML data subset is 1, denoted as priority sequence number 1, the priority of the priority sequence number 0 is greater than the priority of the priority sequence number 1, or the opposite can also be implemented, such as the priority of the priority sequence number 1 is greater than the priority of the priority sequence number 0, which is not limited.

[0132] Of course, if the first AI / ML data set contains a data subset, at this time, the priority relationship can not be considered, and the corresponding processing can be directly performed on the data subset, such as the encoding, mapping and the like described above.

[0133] Case 2: Dynamic indication

[0134] The dynamic indication of the multiplexing priority relationship is mainly applicable to a scenario in which the transmission reliability and / or latency level of the data types in the AI / ML data set is relatively uncertain. For example, the second communication device / or any other possible device can pre-configure a priority relationship table item for the first communication device through signaling (such as high-layer or physical-layer signaling), which can indicate the priority relationship between different same / different types of AI / ML data / data subsets in the AI / ML data set, and different priority relationships correspond to different sequence numbers in the priority relationship table item. For another example, the above-mentioned priority relationship table item can also be protocol predefined. Subsequently, the second communication device / or any other possible device can send the corresponding sequence number to the first communication device through signaling (such as high-layer or physical-layer signaling), and the first communication device can determine which priority relationship it needs to use according to the sequence number, such as whether the priority of the first AI / ML data subset is higher than that of the second AI / ML data subset or vice versa.

[0135] In another possible case, when the first control information contains not only the first AI / ML data set but also other fields / information elements, the priority relationship of the first AI / ML data set can be the priority relationship between the first AI / ML data set and the other fields / information elements, which can be dynamically determined or protocol predefined, which will be introduced respectively below.

[0136] Case A: Protocol predefined:

[0137] The protocol predefined multiplexing rule is mainly applicable to a scenario in which the transmission reliability and / or latency level of the data types in the AI / ML data set is relatively certain. The protocol can predefine the respective priority relationships of the same / different types of AI / ML data / data subsets and the above-mentioned fields / information elements (such as HARQ-ACK, CSI, etc.), and different priority relationships can be defined. In this case, the first communication device can determine the priority relationship of the data / data subsets and the fields / information elements according to the respective data types of the data / data subsets and the fields / information elements in the first AI / ML data set, according to the definition of the protocol.

[0138] For example, the above-mentioned fields / information elements include HARQ-ACK, CSI part 1, and CSI part 2, and the first AI / ML data set includes a data subset, such as the first AI / ML data subset.

[0139] For example, the protocol predefines the first AI / ML data subset as a soft value reflecting the link performance, such as user throughput, historical information of user throughput, and the like, which is subsequently sent in combination with HARQ-ACK, providing more link information, and the protocol predefines the priority between the first AI / ML data subset and the above-mentioned fields / cells from high to low in turn as: HARQ-ACK, the first AI / ML data subset, CSI part 1, and CSI part 2, or in other words, the priority sequence numbers corresponding to HARQ-ACK, the first AI / ML data subset, CSI part 1, and CSI part 2 are: priority sequence number 0, priority sequence number 0, priority sequence number 1, and priority sequence number 2. It can be understood that the specific values of the above-mentioned priority sequence numbers are only one example, and for example, other values such as priority sequence number 4, priority sequence number 5,..., priority sequence number 10, priority sequence number 11,..., priority sequence number 20, priority sequence number 21, and the like can also be used; the priority sequence numbers can also be, or priority sequence number 0, priority sequence number 1, priority sequence number 2, and priority sequence number 3; for another example, the values of the priority sequence numbers can only be used to distinguish different priority sequence numbers, and the values do not represent the priority, and the priority represented by the priority sequence numbers can also be indicated in other ways, such as the arrangement order between different priority sequence numbers, such as in the order from left to right as: priority sequence number 1, priority sequence number 3, and priority sequence number 2, representing the priority from high to low or from low to high. The priority sequence numbers involved below can also be understood in this way, and will not be described one by one below.

[0140] For another example, the protocol predefines the first AI / ML data subset as actual channel information related to the actual situation, such as a real label, which is subsequently sent in combination with CSI part 1, providing more link information, and the protocol predefines the priority between the first AI / ML data subset and the above-mentioned fields / cells from high to low in turn as: HARQ-ACK, CSI part 1, the first AI / ML data subset, and CSI part 2, or in other words, the priority sequence numbers corresponding to HARQ-ACK, CSI part 1, the first AI / ML data subset, and CSI part 2 are: priority sequence number 0, priority sequence number 1, priority sequence number 1, and priority sequence number 2. It can be understood that the specific values of the above-mentioned priority sequence numbers are only one example, and the present application is not limited thereto.

[0141] For another example, the protocol predefines the first AI / ML data subset as time delay insensitive information (such as auxiliary information belonging to the next moment: metadata of the future model), and predefines the priority between the first AI / ML data subset and the above-mentioned fields / cells from high to low as: HARQ-ACK, CSI part 1, CSI part 2, the first AI / ML data subset, or the priority sequence numbers corresponding to HARQ-ACK, CSI part 1, CSI part 2, the first AI / ML data subset are: priority sequence number 0, priority sequence number 1, priority sequence number 2, and priority sequence number 2, respectively. It can be understood that the specific value of the above-mentioned priority sequence number is only an example, and the present application is not limited thereto.

[0142] In addition, the protocol can also predefine the first AI / ML data subset as other data content, and then predefine the relationship with the above-mentioned fields / cells, which is not limited herein.

[0143] For another example, the above-mentioned fields / cells include HARQ-ACK, CSI part 1, and CSI part 2, and the first AI / ML data set includes multiple data subsets, such as the first AI / ML data subset and the second AI / ML data subset.

[0144] For example, the protocol predefines the first AI / ML data subset as the parameters of model management, and the second AI / ML data subset as the metadata of the model (such as the position of the first communication device). The second communication device needs to determine whether the current data packet is transmitted correctly first, and then update the next round of period model. During the model updating process, data such as channel environment and position of the first communication device are also needed, which is similar to the type of CSI part 1. Based on this, the protocol predefines the priority between the first AI / ML data subset and the above-mentioned fields / cells from high to low as: HARQ-ACK, the first AI / ML data subset, CSI part 1, the second AI / ML data set, and CSI part 2, or the priority sequence numbers corresponding to HARQ-ACK, the first AI / ML data subset, CSI part 1, the second AI / ML data set, and CSI part 2 are: priority sequence number 0, priority sequence number 1, priority sequence number 1, priority sequence number 2, and priority sequence number 3, or priority sequence number 0, priority sequence number 1, priority sequence number 2, priority sequence number 3, and priority sequence number 4. It can be understood that the specific value of the above-mentioned priority sequence number is only an example, and the present application is not limited thereto.

[0145] For another example, the protocol predefines the first AI / ML data subset as monitoring information, the second AI / ML data subset as metadata or auxiliary information of the model, and the second communication device needs to monitor whether the model is suitable, and then update a new round of periodic model, and the metadata or auxiliary information is needed in the model updating process. Based on this, the protocol predefines the priority between the first AI / ML data subset and the above-mentioned fields / cells from high to low as follows: HARQ-ACK, the first AI / ML data subset, the second AI / ML data set, CSI part 1, and CSI part 2, or the priority sequence numbers corresponding to HARQ-ACK, the first AI / ML data subset, the second AI / ML data set, CSI part 1, and CSI part 2 are 0, 1, 2, 3, and 4, respectively. It can be understood that the specific value of the above-mentioned priority sequence number is only an example, and the present application is not limited thereto.

[0146] In addition, the first communication device can encode the first control information according to the priority relationship of the first AI / ML data set to obtain encoded information, and then multiplex (or map) the encoded information to the first data channel according to the priority relationship of the first AI / ML data set. After the process, the first communication device carries the second AI / ML data set in the first data channel for transmission.

[0147] Case B: dynamic indication

[0148] The dynamic indication of the multiplexing priority relationship is mainly applicable to the scenario where the transmission reliability and / or latency level of the data types in the AI / ML data set are relatively uncertain. For example, the second communication device / or any other possible device can preconfigure a priority relationship table item for the first communication device through signaling (such as high-layer signaling or physical-layer signaling), which can indicate the priority relationship between the same / different types of AI / ML data / data subsets in the AI / ML data set and other fields / cells, and different priority relationships correspond to different sequence numbers in the priority relationship table item. For example, the preconfigured table 1 includes only one type of multiplexing priority of the first AI / ML data subset (denoted as AI-part1) in the first AI / ML data set, and the preconfigured table 2 includes two types of multiplexing priority of the first AI / ML data subset (denoted as AI-part1type1) and the second AI / ML data subset (denoted as AI-part1type2) in the first AI / ML data set. For another example, the above-mentioned priority relationship table item can also be pre-defined by the protocol.

[0149] Subsequently, the second communication device, or any other possible device, can send the corresponding serial number to the first communication device through signaling (such as high layer signaling or physical layer signaling), and the first communication device can determine which priority relationship it needs to use according to the serial number by traversing the priority relationship table.

[0150] The priority relationship corresponding to serial number 1 in Table 1 is HARQ-ACK, CSI part 1, CSI part 2, AI-part1, PUSCH, or in other words, the priority serial numbers corresponding to HARQ-ACK, CSI part 1, CSI part 2, AI-part1, PUSCH are priority serial number 0, priority serial number 1, priority serial number 2, priority serial number 3, and priority serial number 4. The corresponding priority serial numbers can not be in increasing or decreasing order, and more consideration can be given to the second communication device, or any other possible device, preconfiguring the priority relationship table item to the first communication device through signaling (such as high layer signaling or physical layer signaling). For example, the priority relationship corresponding to serial number 5 in Table 1 is (AI-part1, HARQ-ACK), CSI part 1, CSI part 2, PUSCH, or in other words, the priority serial numbers corresponding to (AI-part1, HARQ-ACK), CSI part 1, CSI part 2, PUSCH are priority serial number 0, priority serial number 0, priority serial number 1, priority serial number 2, and priority serial number 3. The corresponding priority serial numbers can not be in increasing or decreasing order, and more consideration can be given to the second communication device, or any other possible device, preconfiguring the priority relationship table item to the first communication device through signaling (such as high layer signaling or physical layer signaling). In addition, AI-part1 and HARQ-ACK in the priority relationship corresponding to serial number 5 in Table 1 have the same priority, which is indicated by adding parentheses. In addition, the priority relationship indicated by adding parentheses is only one example, and the priority relationship can also be indicated by adding special symbols, such as AI-part1*, HARQ-ACK*, or any other possible expression, which is not limited here.

[0151] For example, the priority relationship corresponding to the sequence number 1 in Table 2 is HARQ-ACK, CSI part 1, CSI part 2, AI-part1 type1, AI-part1 type2, PUSCH, or in other words, the priority sequence numbers corresponding to HARQ-ACK, CSI part 1, CSI part 2, AI-part1 type1, AI-part1 type2, and PUSCH are priority sequence number 0, priority sequence number 1, priority sequence number 2, priority sequence number 3, priority sequence number 4, and priority sequence number 5, respectively. The corresponding priority sequence numbers can also not be in ascending or descending order. More consideration can be given to the fact that the second communication device and / or any other possible device can preconfigure the priority relationship table item for the first communication device through signaling (such as high-layer signaling or physical-layer signaling). In addition, the priority relationship in Table 2 can also be represented by adding parentheses to indicate the priority relationship between the AI / ML data / data subset and / or other fields / information elements in the parentheses. The specific implementation can be referred to the related description of Table 1, and will not be repeated here.

[0152] The high-layer signaling can be radio resource control (RRC), MAC-control element (MAC-CE), or other possible signaling. The physical-layer signaling can be DCI, SCI, UCI, etc., which is not limited here.

[0153] Table 1

[0154] HARQ-ACK, CSI part 1, AI-part1, CSI part 2, PUSCH HARQ-ACK, AI-part1, CSI part 1, CSI part 2, PUSCH 1 AI-part1, HARQ-ACK, CSI part 1, CSI part 2, PUSCH 2 (AI-part1, HARQ-ACK), CSI part 1, CSI part 2, PUSCH 3 Figure 6 4 Figure 1 5 Figure 6

[0155] Table 2

[0156]

[0157] According to the above content, in the embodiments of the present application,

[0158] First, the first communication device can encode (such as independently or jointly encode) the first control information according to the priority relationship of the first AI / ML data set, to obtain the encoded information.

[0159] In the first possible scenario, the first control information can only contain the first AI / ML data set.

[0160] If the first AI / ML dataset contains the same (or similar) type of data, the first communication device can independently encode one subset or jointly encode multiple subsets. For example, if the first AI / ML dataset includes a first AI / ML data subset, the first AI / ML data subset can be directly independently encoded to obtain the encoded information, i.e., the encoded first AI / ML dataset. If the first AI / ML dataset includes a first AI / ML data subset and a second AI / ML data subset of the same type, the first communication device can determine that the two subsets are of the same type according to the same priority order (or the same priority relationship) of the first AI / ML data subset and the second AI / ML data subset, and then jointly encode the data of the first AI / ML data subset and the second AI / ML data subset to obtain the encoded information. For example, the first AI / ML data subset includes monitoring auxiliary information of monitoring data, and the second AI / ML data subset also includes monitoring auxiliary information of monitoring data. The two subsets are of the same type, and the data of the first AI / ML data subset and the second AI / ML data subset are jointly encoded.

[0161] If the first AI / ML dataset contains different (or dissimilar) types of data, the first communication device can independently encode different subsets. For example, the first AI / ML data subset is monitoring auxiliary information of monitoring data, and the second AI / ML data subset is metadata of a model. The different types of data make the priority order of the two subsets different (or the priority relationship indicates different priorities), and thus the first communication device can determine that the two subsets are of different types according to the priority order relationship of the first AI / ML data subset and the second AI / ML data subset, and then independently encode the data of the first AI / ML data subset and the second AI / ML data subset to obtain the encoded information.

[0162] In the second possible scenario, the first control information not only includes the first AI / ML dataset, but also includes other information elements (or control information elements) such as HARQ-ACK and CSI part 1, CSI part 2, etc. The first communication device can determine whether to independently or jointly encode according to whether the data type in the first AI / ML dataset matches / similar to the other information elements in the first control information.

[0163] If one data subset in the first AI / ML data set is of the same type as other information elements / fields, the same type can be encoded as a whole, and different types are independently encoded. For example, the data type of the first AI / ML data subset in the first AI / ML data set is link performance, and the data type of HARQ-ACK is also link performance. The data type of the first AI / ML data subset is the same as that of HARQ-ACK, and the first communication device can jointly encode and modulate to obtain encoded information, such as the encoded first AI / ML data subset and HARQ-ACK. For another example, the data type of the second AI / ML data subset in the first AI / ML data set is channel state, and the data type of CSI part 1 is also channel state. The data type of the second AI / ML data subset is the same as that of CSI part 1, and the first communication device can jointly encode and modulate to obtain encoded information, such as the encoded second AI / ML data subset and CSI part 1.

[0164] It can be understood that each subset data type and / or other information elements / fields are independently encoded or jointly encoded, and the same data type can be understood as the same or similar communication function (such as link performance, channel state, etc.) of a communication task; it can also be understood as the same or similar communication task (such as beam management, positioning, CSI prediction, etc.); it can also be understood as the same or similar dimension of data collection in the AI / ML life cycle management (such as supervised data, training data, inference data), or the dimension of model data (such as model metadata, model management related data, auxiliary information), or the same or similar AI / ML process (such as model supervision, model training, model inference). The present application does not limit the interpretation of the same data type, and any granularity (such as network, granularity, or device granularity, etc.) of the same or similar or similar can be understood as the same as defined in the embodiments of the present application.

[0165] The first communication device can also multiplex (or map) the encoded information to the first data channel according to the priority relationship of the first AI / ML data set, specifically to the physical time-frequency resource, which can be mapped according to the following rules:

[0166] 1) The priority relationship or multiplexing priority of the first AI / ML data set, HARQ-ACK, CSI part 1, and CSI part 2 in the first control information is that the priority sequence number of the first AI / ML data set is lower than that of HARQ-ACK, CSI part 1, and CSI part 2, the mapping rule of the first AI / ML data set is the same as the mapping method of the second AI / ML data set transmitted in the first data channel, and at this time, after the mapping of the encoded HARQ-ACK, the encoded CSI part 1, and the encoded CSI part 2 is completed, the encoded first AI / ML data set and the encoded second AI / ML data set are sequentially mapped on the remaining resources.

[0167] 2) The priority relationship or multiplexing priority of each element or data in the first control information is that the priority sequence number of the first AI / ML data set is the same as that of HARQ-ACK and / or CSI part 1 and / or CSI part 2. Therefore, the mapping rule of the first AI / ML data set is the same / similar to that of HARQ-ACK and / or CSI part 1 and / or CSI part 2, such as the priority sequence number of the first AI / ML data set being the same as or similar to that of CSI part 1, and the mapping being similar to that of CSI part 1, such as the first AI / ML data set being mapped on the first OFDM symbol without transmitting DMRS to improve transmission reliability. For example, the priority sequence number of the first AI / ML data set is the same as or similar to that of HARQ-ACK, and the mapping is similar to that of HARQ-ACK, such as the first AI / ML data set being mapped on the first OFDM symbol after the first DMRS to improve transmission reliability. Of course, if the priority sequence number of the first AI / ML data set is different / similar to that of HARQ-ACK and / or CSI part 1 and / or CSI part 2, the first AI / ML data set can be directly mapped and transmitted on the OFDM symbol with DMRS to improve transmission reliability.

[0168] 3) Different subsets of the first AI / ML data set with different data types can use different mapping methods, such as the mapping methods in 1 or 2 above, or new defined mapping methods, and the specific implementation method is not limited.

[0169] Optionally, the second communication device can indicate the transmission of the first control information and the first data channel of the first communication device through signaling (such as high-layer or physical-layer signaling), flexibly schedule data transmission, and improve communication performance. Wherein, when there is only one type of data in the first AI / ML data set during the transmission of the first control information of the first communication device, the second communication device can indicate the number of transmission bits required by the first AI / ML data set through signaling; or when there are multiple types of data (such as the first AI / ML data subset and the second AI / ML data subset) in the first AI / ML data set, the second communication device can indicate the number of transmission bits required by each type of data in the first AI / ML data set through signaling; or when there is only one type of data in the first AI / ML data set, the second communication device can indicate the expansion factor of the first AI / ML data set through signaling, and the first communication device calculates the number of bits according to the expansion factor. Similarly, when there are multiple types of data (such as the first AI / ML data subset and the second AI / ML data subset) in the first AI / ML data set, the second communication device can indicate the expansion factor of each type of data in the first AI / ML data set through signaling.

[0170] Optionally, when the uplink transmission resource is insufficient, the first communication device can also discard part or all of the first AI / ML data subset and / or the second AI / ML data subset according to the priority relationship of the first AI / ML data set. For example, the priority defined by the protocol is from high to low in turn HARQ-ACK, CSI part 1, CSI part 2, first AI / ML data subset, second AI / ML data set. When the uplink transmission resource is insufficient, the first communication device can discard part or all of the second AI / ML data set, the first AI / ML data subset, the CSI part 2, the CSI part 1, and the HARQ-ACK in turn.

[0171] The above introduces how the first AI / ML data set is mapped, and the following specifically introduces how the second AI / ML data set is carried to the first data channel.

[0172] The first data channel corresponds to one or more LCs / LC groups / LC sets. The second AI / ML data set can contain data of the same type or data of different types. Different types of data correspond to different priority sequence numbers, and data of the same type correspond to the same priority sequence number.

[0173] Since the data in the second AI / ML data set corresponds to the data priority sequence number, the data priority sequence number can also determine the processing manner of the data in the second AI / ML data set in the first data channel. Specifically, the processing manner of data with the same priority / priority sequence number can be the same, and the processing manner of data with different priority / priority sequence number can be different. The different processing manners can be using different MCS tables, different number of layers of corresponding MIMO systems, different mapping methods of demodulation reference signals (DMRS), and different channel quality indicators (CQI).

[0174] For example, the second AI / ML data set includes a third AI / ML data subset and a fourth AI / ML data subset. The third AI / ML data subset and the fourth AI / ML data subset include the same type of data. The third AI / ML data subset corresponds to a third priority sequence number, and the fourth AI / ML data subset corresponds to a fourth priority sequence number. The third priority sequence number and the fourth priority sequence number are the same, and correspondingly, the data processing manner of the third AI / ML data subset and the fourth AI / ML data subset is the same. Alternatively, the third AI / ML data subset and the fourth AI / ML data subset include different types of data. The third AI / ML data subset corresponds to a third priority sequence number, and the fourth AI / ML data subset corresponds to a fourth priority sequence number. The third priority sequence number and the fourth priority sequence number are different, and correspondingly, the third AI / ML data subset can correspond to a first modulation and coding scheme (MCS) table, the fourth AI / ML data subset can correspond to a second MCS table, the first MCS table and the second MCS table are different; the third AI / ML data subset can correspond to a first multiple-input multiple-output (MIMO) layer number, the fourth AI / ML data subset can correspond to a second MIMO layer number, the first MIMO layer number and the second MIMO layer number are different; the third AI / ML data subset can correspond to a first demodulation reference signal (DMRS) mapping method, the fourth AI / ML data subset can correspond to a second DMRS mapping method, the first DMRS mapping method and the second DMRS mapping method are different; the third AI / ML data subset can correspond to a first channel quality indicator (CQI) method, and the fourth AI / ML data subset can correspond to a second CQI method, the first CQI method and the second CQI method are different.

[0175] Additionally, the different priority sequence number data subsets correspond to different MCS tables, which can be configured by high layer signaling or pre-defined by protocol. For example, by high layer signaling configuration or protocol pre-definition, the data subset with high priority sequence number is configured with a high reliability MCS table, and the data subset with low priority sequence number is configured with a low reliability MCS table.

[0176] Additionally, the data subsets of different priority orders correspond to different MIMO layers, and further, the different MIMO layers can be bound to the bit allocation of different priority orders.

[0177] In one possible way, the priority order of the data in the second AI / ML data set can be independent of the priority of the LC / LC group / LC set, i.e., the priority order of the data in the second AI / ML data set can be maintained independently by the first communication device and the second communication device. In this case, the first communication device and the second communication device can additionally maintain a table of data priorities, so that when the first communication device transmits data through the logical channel, the processing manner of the data in the logical channel is determined according to the priority defined by the priority table, or the priority order of the data in the second AI / ML data set can be indicated by a high-layer signaling configuration, such as a radio resource control (RRC), a medium access control-control element (MAC-CE), or any other possible signaling, such as a newly defined message in the future, so that when the first communication device transmits data through the logical channel, the processing manner of the data in the logical channel is determined according to the priority defined by the priority table.

[0178] In another possible way, the priority order of the data in the second AI / ML data set can be associated with the priority of the LC / LC group / LC set, i.e., when the first communication device transmits the data in the second AI / ML data set through the LC / LC group / LC set, the second AI / ML data subset of high priority order can be transmitted in the high-priority LC / LC group / LC set, and the second AI / ML data subset of low priority order can be transmitted in the low-priority LC / LC group / LC set, thereby implicitly indicating the processing manner of the data corresponding to the second AI / ML data subset.

[0179] Additionally, a signaling (such as the second AI / ML data set) dedicated to the AI / ML data set multiplexed to the first data channel can also be defined, such as a DCI format, which is a DCI scrambled by a special RNTI. The signaling can indicate at least one of the following: time-frequency resources of the first data channel, proportion of information bits of AI / ML data subsets of different priorities (or priority orders) multiplexed to the first data channel, allocation criteria of CB / TBs corresponding to different priority AI / ML data subsets multiplexed to the first data channel (these CB / TBs are also referred to as CB / TBs of different priorities), or MCS information corresponding to different priority CB / TBs.

[0180] Additionally, during the first data channel transmission of the first communication device, the second communication device can also indicate the time-frequency resources used by the second AI / ML dataset and the scheduling information such as the MCS and RV versions via signaling.

[0181] In summary, after acquiring the AI / ML dataset, the first communication device does not directly send the AI / ML dataset to the second communication device. Instead, it determines the priority number of multiple datasets in the AI / ML dataset and carries the high-priority datasets through the first control information, while carrying the low-priority datasets through the first data channel. Since the first control information is more reliable than the data transmission in the first data channel, the reliability of the transmission of the high-priority datasets can be guaranteed, reporting errors can be minimized, and efficient use of transmission resources can be achieved.

[0182] It is understood that the embodiments of this application are illustrated using the example of a first AI / ML dataset being transmitted within first control information, a second AI / ML dataset being transmitted within a first data channel, and the first control information being multiplexed within the first data channel. However, the scenarios described in this application are not limited to this. For example, the first AI / ML dataset may be transmitted within the first control information, and the first control information may be transmitted within the first control channel; and / or the second AI / ML dataset may be transmitted within the first data channel. The specific principles can be understood by referring to the method described in the first aspect above, and will not be repeated here.

[0183] Figure 6 This is a schematic diagram of the structure of the communication device provided in the embodiments of this application. Figure 6 For example, such as Figure 6 As shown, the communication device 600 includes a transceiver module 601 and a processing module 602. For ease of explanation, Figure 6 Only the main components of the communication device are shown.

[0184] The transceiver module 601 is used to perform the transceiver function of the above communication method, and the processing module 602 is used to perform other functions of the above communication method besides the transceiver function.

[0185] Optionally, the transceiver module 601 may include a transmitting module ( Figure 4 (not shown in the image) and receiving module ( Figure 3 (Not shown in the diagram). The transmitting module implements the transmitting function of the communication device 600, and the receiving module implements the receiving function of the communication device 600.

[0186] Optionally, the communication device 600 may also include a storage module. Figure 7The storage module stores programs or instructions. When the processing module 602 executes the programs or instructions, the communication device 600 can perform the methods described above Figure 7 The functions of the terminal in the methods described above.

[0187] It can be understood that the communication device 600 can be a terminal or a network device, or a chip (system) or other components or assemblies that can be arranged in the terminal or the network device, or a device containing the terminal or the network device, and the present application does not limit this.

[0188] In addition, the technical effects of the communication device 600 can refer to the technical effects of the methods described above, and will not be repeated here. Figure 7

[0189] The following will be described in detail Figure 7 The various constituent components of the communication device 700 will be specifically introduced:

[0190] The processor 701 is the control center of the communication device 700, which can be one processor or a collective term of multiple processing elements. For example, the processor 701 is one or more central processing units (CPU), which can also be an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application, such as one or more digital signal processors (DSP), or one or more field programmable gate arrays (FPGA).

[0191] Optionally, the processor 701 can perform various functions of the communication device 700 by running or executing software programs stored in the memory 702 and calling data stored in the memory 702, such as performing the communication method in the embodiments of the present application.

[0192] In a specific implementation, as an embodiment, the processor 701 can include one or more CPUs, such as the CPU0 and CPU1 shown in Figure 7

[0193] In a specific implementation, as an embodiment, the communication device 700 can also include multiple processors, such as the CPU0 and CPU1 shown in Figure 7 ​​The processors 701 and 704 shown in FIG. 7 can each be a single-CPU or a multi-CPU. The processor herein can refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0194] The memory 702 is configured to store a software program for implementing the solutions of the present application, and the processor 701 is configured to control the execution of the software program. The specific implementation can refer to the above-mentioned method embodiments, and will not be repeated here.

[0195] Alternatively, the memory 702 can be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disk storage, a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to this. The memory 702 can be integrated with the processor 701 or exist independently, and is coupled to the processor 701 through the interface circuit (not shown in FIG. 7) of the communication device 700. The embodiments of the present application are not limited in this regard. Figure 7

[0196] The transceiver 703 is configured to communicate with other communication devices. For example, the communication device 700 is a terminal, and the transceiver 703 can be configured to communicate with a network device or another terminal. For another example, the communication device 700 is a network device, and the transceiver 703 can be configured to communicate with a terminal or another network device.

[0197] Optionally, the transceiver 703 can include a receiver and a transmitter (not shown separately in FIG. 7). The receiver is configured to implement the receiving function, and the transmitter is configured to implement the transmitting function. ​

[0198] Optionally, the transceiver 703 can be integrated with the processor 701 or exist independently, and is coupled to the processor 701 through the interface circuit (not shown in FIG. 7) of the communication device 700. The embodiments of the present application are not limited in this regard. ​ ​​The communication device 700 shown in FIG. 7 is not intended to limit the communication device. The actual communication device can include more or less components than those shown in the figure, or combine some components, or arrange the components differently.

[0199] It can be understood that, ​ The structure of the communication device 700 shown in FIG. 7 does not constitute a limitation on the communication device. The actual communication device can include more or less components than those shown in the figure, or combine some components, or arrange the components differently.

[0200] In addition, the technical effects of the communication device 700 can refer to the technical effects of the methods described in the above method embodiments, which will not be described here.

[0201] It should be understood that the processor in the embodiments of the present application can be a central processing unit (CPU). The processor can also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic components, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0202] It should also be understood that the memory in the embodiments of the present application can be a volatile memory or a nonvolatile memory, or can include both volatile and nonvolatile memory. Among them, the nonvolatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically EPROM (EEPROM), or a flash memory. The volatile memory can be a random access memory (RAM) used as an external cache. By way of example, and not limitation, many forms of random access memory (RAM) are available, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM), and direct rambus RAM (DR RAM).

[0203] The above-described embodiments can be implemented in part or in whole through software, hardware (e.g., circuitry), firmware, or any combination thereof. When implemented in software, the above-described embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When loaded and executed by a computer, the computer instructions or computer programs can produce the processes or functions described above in accordance with the embodiments of the present application. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable apparatus. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, such as from a website site, a computer, a server, or a data center to another website site, a computer, a server, or a data center through a wired (e.g., infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium or a collection of medium accessible by a computer or a data storage device such as a server, a data center, etc. containing one or more available medium. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state disk.

[0204] It should be understood that the term "and / or" in this document is merely used to describe an associated relationship between associated objects, and can represent three relationships, for example, A and / or B can represent three cases of A alone, A and B together, and B alone, where A and B can be singular or plural. In addition, the character " / " in this document generally represents an "or" relationship between the front and rear associated objects, but can also represent an "and / or" relationship. The specific meaning can be understood according to the context before and after.

[0205] In this application, "at least one" means one or more, and "multiple" means two or more. "At least one of the following" or similar expressions means any combination of the items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple.

[0206] It should be understood that in various embodiments of the present application, the size of the sequence number of the above-described processes does not mean the order of execution, and the execution order of the processes should be determined according to their functions and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0207] Those skilled in the art can clearly understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0208] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0209] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the above-described device embodiments are merely schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0210] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0211] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically independently, or two or more units can be integrated into one unit.

[0212] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0213] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A communication method characterized by comprising: The method comprises: obtaining an artificial intelligence (AI) / machine learning (ML) data set, the AI / ML data set being a first AI / ML data set and a second AI / ML data set, wherein the first AI / ML data set and the second AI / ML data set have different priority orders, and the different priority orders represent that the first AI / ML data set and the second AI / ML data set have different levels of transmission reliability and / or latency; sending first control information and a first data channel according to the priority orders of the first AI / ML data set and the second AI / ML data set, wherein the first control information is multiplexed in the first data channel, the first control information includes the first AI / ML data set, and the first data channel further includes the second AI / ML data set.

2. The method of claim 1, wherein, The first AI / ML data set at least includes a first AI / ML data subset and / or a second AI / ML data subset.

3. The method of claim 2, wherein, The first AI / ML data set, the first AI / ML data subset, and the second AI / ML data subset include one or more of the following data types: monitoring information, training data, inference data, model management related information, model metadata and model auxiliary information, and specific parameter information of a model.

4. The method of claim 3, wherein, If the first AI / ML data subset and the second AI / ML data subset have the same data type, the first AI / ML data subset corresponds to a first priority order, and the second AI / ML data subset corresponds to a second priority order, the first priority order is the same as the second priority order.

5. The method of claim 3, wherein, If the first AI / ML data subset and the second AI / ML data subset have different data types, the first AI / ML data subset corresponds to a third priority order, and the second AI / ML data subset corresponds to a fourth priority order, the first priority order is different from the second priority order.

6. The method of claim 3, wherein, The data type includes one or more of the following features: The priority order of the monitoring data is greater than the priority order of the training data, or the priority order of the model management related information is greater than or equal to the priority order of the model metadata and model auxiliary information, or the priority order of the model metadata and model auxiliary information is greater than the priority order of the specific parameter information of the model.

7. The method according to any one of claims 2 to 6, characterized in that, The multiplexing priority of the first AI / ML data subset and / or the second AI / ML data subset multiplexed into the first data channel includes one or more of the following ways: The priority order of the first AI / ML data subset and / or the second AI / ML data subset is the same as the priority order of HARQ-ACK. The priority order of the first AI / ML data subset and / or the second AI / ML data subset is the same as the priority order of CSI part 1. The priority order of the first AI / ML data subset and / or the second AI / ML data subset is the same as the priority order of CSI part 2. The priority order of the first AI / ML data subset and / or the second AI / ML data subset is different from the priority order of HARQ-ACK. The priority order of the first AI / ML data subset and / or the second AI / ML data subset is different from the priority order of CSI part 1. The priority order of the first AI / ML data subset and / or the second AI / ML data subset is different from the priority order of CSI part 2.

8. The method of claim 7, wherein, The multiplexing priority is protocol predefined or indicated by physical layer or high layer signaling.

9. The method of claim 4, wherein, If the first AI / ML data subset and the second AI / ML data subset have the same data type, the first AI / ML data subset and the second AI / ML data subset are jointly encoded and modulated.

10. The method of claim 5, wherein, If the first AI / ML data subset and the second AI / ML data subset have different data types, the first AI / ML data subset and the second AI / ML data subset are independently encoded and modulated.

11. The method according to any one of claims 1 to 10, characterized in that, In the first AI / ML data subset, the data with the same data type as HARQ-ACK and CSI part 1 and CSI part 2 signaling is jointly encoded and modulated, and the data with different data types is independently encoded and modulated.

12. The method of claim 1, wherein, The second AI / ML data set at least includes a third AI / ML data subset and / or a fourth AI / ML data subset.

13. The method of claim 12, wherein, The second AI / ML data set and the third AI / ML data subset and the fourth AI / ML data subset include one or more of the following data types: Monitoring information, training data, inference data, model management related information, model metadata and model auxiliary information, and specific parameter information of the model.

14. The method of claim 13, wherein, If the third AI / ML data subset and the fourth AI / ML data subset have the same data type, the third AI / ML data subset corresponds to a third priority order, and the fourth AI / ML data subset corresponds to a fourth priority order, the third priority order is the same as the fourth priority order.

15. The method of claim 13, wherein, If the third AI / ML data subset and the fourth AI / ML data subset have different data types, the third AI / ML data subset corresponds to a third priority order, and the fourth AI / ML data subset corresponds to a fourth priority order, the third priority is different from the fourth priority order.

16. The method according to any one of claims 12-15, characterized in that, The method comprises: Receiving the priority order of the data subset in the second AI / ML data set, and transmitting the first data channel according to the priority order.

17. The method of claim 16, wherein, The priority order of the data subset in the second AI / ML data set is configured by high layer signaling or implicitly indicated by logical channel priority.

18. The method of claim 15, wherein, When the third AI / ML data subset and the fourth AI / ML data subset have different data types, the following one or more features are further included: The third AI / ML data subset corresponds to a first modulation and coding scheme (MCS) table, the fourth AI / ML data subset corresponds to a second MCS table, and the first MCS table and the second MCS table are different. The third AI / ML data subset corresponds to a first multiple-input multiple-output (MIMO) layer number, and the fourth AI / ML data subset corresponds to a second MIMO layer number, the first MIMO layer number and the second MIMO layer number being different. The third AI / ML data subset corresponds to a first demodulation reference signal (DMRS) mapping method, and the fourth AI / ML data subset corresponds to a second DMRS mapping method, the first DMRS mapping method and the second DMRS mapping method being different.

19. A communications device, characterized by The apparatus includes means for performing the method of any of claims 1-18.

20. A communications device, characterized by The communication apparatus includes a processor and a memory, the memory is configured to store computer instructions, when the processor executes the instructions, the communication apparatus performs the method of any of claims 1-18.

21. A computer-readable storage medium, characterized in that, The computer readable storage medium includes storing computer programs or instructions, when the computer programs or instructions are executed, the method of any of claims 1-18 is performed.

22. A computer program product, characterised in that, The computer readable storage medium includes storing computer programs or instructions, when the computer programs or instructions are executed, the method of any of claims 1-18 is performed.

Images