Communication method and communication apparatus

Abstract

A communication method and a communication device, the method comprising: receiving, by a first device in a network device, first information, the first information being used to indicate first split information and / or first configuration information, the first split information being used to determine a function corresponding to the first device and a function corresponding to a second device in the network device, the first configuration information being used to indicate an artificial intelligence, AI, function corresponding to the first device and / or an AI function corresponding to the second device, and the AI function corresponding to the first device being different from the AI function corresponding to the second device, the AI function including one or more of: AI channel estimation, AI equalization, or AI demodulation. The method implements deployment of the AI function corresponding to the first device and / or the second device through the first information, and enables the network device to be combined with AI in a scenario of base station architecture separation, and to realize network intelligence.

Description

Technical Field

[0001] This application relates to the field of communication technology, and more specifically, to a communication method and a communication device. Background Technology

[0002] With the development of wireless communication technology, wireless networks can not only provide traditional wireless communication connectivity services, but also be deeply integrated with artificial intelligence (AI) to achieve network intelligence. AI or machine learning (ML) based on neural networks, when applied to wireless communication systems, can generally achieve accurate modeling and prediction of wireless data through data-driven training, enabling the completion of various wireless tasks, such as channel estimation, channel prediction, data traffic prediction, or beam prediction.

[0003] In future network architectures, base stations can be divided into primary and secondary devices. The primary device handles radio frequency (RF) and some lower-level physical layer processing functions, while the secondary device handles higher-level physical layer functions. In solutions that integrate wireless networks and AI, AI models are typically deployed on base stations. However, in scenarios with a separate base station architecture, how to deploy AI models on both the primary and secondary devices is currently a hot research topic. Summary of the Invention

[0004] This application provides a communication method and a communication device, which provides a method for deploying AI models in a base station separation architecture scenario to achieve network intelligence.

[0005] Firstly, a communication method is provided. This method can be executed by a first device in a network device. The first device can be the first device itself, or a component used in the first device (such as a chip or circuit, which can be a modem chip, also known as a baseband chip, or a system-on-a-chip (SoC) or system-in-package (SIP) chip containing a modem core, etc.), or a logic module or software capable of implementing some or all of the functions of the first device, etc., and this application does not limit this. The following description uses the first device in a network device as an example.

[0006] The method includes: a first device receiving first information, the first information being used to indicate first segmentation information and / or first configuration information, the first segmentation information being used to determine the function corresponding to the first device and the function corresponding to the second device, the first configuration information being used to indicate the artificial intelligence (AI) function corresponding to the first device and / or the AI ​​function corresponding to the second device, and the AI ​​function corresponding to the first device being different from the AI ​​function corresponding to the second device, the AI ​​function including one or more of the following: AI channel estimation, AI equalization, or AI demodulation.

[0007] For example, the first information could come from a second device within the network. Or the first information could come from other devices, such as the operation and maintenance (OAM) system.

[0008] For example, the first information can be used to indicate the first segmentation information, or the first information can be used to indicate the first configuration information, or the first information can be used to indicate both the first segmentation information and the first configuration information.

[0009] For example, the first segmentation information is used to determine the function corresponding to the first device and the function corresponding to the second device, or it can be understood that the first segmentation information is used to determine the segmentation position, which is the division position where the first device and the second device are respectively responsible for the functions of the network device.

[0010] For example, the AI ​​function in this application can be replaced by an AI model, that is, the first configuration information can be used to indicate the AI ​​model corresponding to the first device and / or the AI ​​model corresponding to the second device, and the AI ​​model corresponding to the first device is different from the AI ​​model corresponding to the second device. The AI ​​model may include one or more of the following: an AI model carried on the channel estimation unit, an AI model carried on the equalization unit, or an AI model carried on the demodulation unit.

[0011] For example, the AI ​​function corresponding to the first device can be deployed internally within the first device, or on other devices (or network elements) outside the first device, or in the cloud; similarly, the AI ​​function corresponding to the second device can be deployed internally within the second device, or on other devices (or network elements) outside the second device, or in the cloud. In other words, the specific deployment location of the AI ​​functions corresponding to the first and second devices is not limited here.

[0012] According to the method provided in this application, the network device may include a first device and a second device. The segmentation information (e.g., first segmentation information) corresponding to the first and second devices within the network device, and the AI ​​functions corresponding to the first device and / or the second device, can be indicated through the first information. This method utilizes the first information to deploy the AI ​​functions corresponding to the first and / or second devices, enabling the network device to integrate with AI in scenarios where the base station architecture is separated, thereby achieving network intelligence.

[0013] In addition, this method can dynamically and flexibly indicate the segmentation information and AI model deployment method of the first and second devices in the network through the first information.

[0014] In conjunction with the first aspect, in some possible implementations, the first configuration information belongs to at least one first candidate configuration information, one or more first candidate configuration information corresponds to one candidate segmentation information in at least one candidate segmentation information, each first candidate configuration information in at least one first candidate configuration information includes the AI ​​function corresponding to the first device and / or the AI ​​function corresponding to the second device, and at least one candidate segmentation information includes first segmentation information, which corresponds to the first configuration information.

[0015] In conjunction with the first aspect, in some possible implementations, each of the first candidate configuration information in at least one first candidate configuration information is different from the others.

[0016] In conjunction with the first aspect, in some possible implementations, the first configuration information is configuration information that satisfies a first condition among at least one first candidate configuration information, the first condition being associated with data transmission performance information and / or AI function information.

[0017] Based on the above scheme, the first configuration information is the configuration information that satisfies the first condition from at least one first candidate configuration information. It is evident that the deployment of AI functions corresponding to the first device and / or the second device in the first configuration information results in better performance in data transmission and / or AI function performance, thereby ensuring improved network communication performance when the first device and the second device have AI functions deployed.

[0018] In conjunction with the first aspect, in some possible implementations, the first segmentation information is associated with the transmission bandwidth between the first device and the second device and / or the computing power corresponding to the first device, and the first segmentation information corresponds to at least one second candidate configuration information in at least one first candidate configuration information, wherein the at least one second candidate configuration information includes the first configuration information.

[0019] Based on the above scheme, the selection of the first segmentation information is related to the transmission bandwidth and / or the computing power of the first device. That is, the first segmentation information can meet the transmission bandwidth and / or computing power of the first device between the first device and the second device, so that the first segmentation information can guarantee the communication quality between the first device and the second device.

[0020] In conjunction with the first aspect, in some possible implementations, where at least one second candidate configuration information includes multiple second candidate configuration information, the first configuration information is the configuration information among at least one second candidate configuration information that satisfies a first condition, the first condition being associated with data transmission performance information and / or AI function information.

[0021] Based on the above scheme, the first configuration information is the configuration information that satisfies the first condition among at least one second candidate configuration information. The at least first second candidate configuration information is the candidate configuration information corresponding to the first segmentation information. It is evident that the deployment of AI functions corresponding to the first device and / or the second device in the first configuration information exhibits better performance in data transmission and / or AI function performance among the multiple second candidate configuration information corresponding to the first segmentation information, thereby ensuring improved network communication performance for both the first and second devices when AI functions are deployed.

[0022] In conjunction with the first aspect, in some possible implementation methods, the AI ​​functions supported by the first device overlap with the AI ​​functions supported by the second device.

[0023] For example, the first configuration information is the configuration information that satisfies the first condition among at least one third candidate configuration information. The AI ​​functions included in each of the at least one third candidate configuration information are the same as the first set. The first set is the union of all AI functions supported by the first device and all AI functions supported by the second device. The AI ​​function corresponding to the first device in each third candidate configuration information belongs to a subset of all AI functions supported by the first device. The AI ​​function corresponding to the second device in each third candidate configuration information belongs to a subset of all AI functions supported by the second device. The first condition is associated with the performance information of data transmission and / or the information of the AI ​​function.

[0024] Based on the above scheme, this method can also be applied to situations where the AI ​​functions supported by the first device and the AI ​​functions supported by the second device have overlapping storage. For example, the AI ​​functions supported by the first device include AI channel estimation, and the AI ​​functions supported by the second device include AI channel estimation and AI equalization, meaning that at least one of the AI ​​functions supported by the first device and the AI ​​functions supported by the second device is the same.

[0025] In conjunction with the first aspect, in one possible implementation, the information of the AI ​​function associated with the first condition includes at least one of the following: performance information of the AI ​​function, priority information of the AI ​​function, or manufacturer information corresponding to the AI ​​function, etc.

[0026] In conjunction with the first aspect, among some possible implementation methods, the first condition is associated with at least one of the following: bit error rate, throughput, AI channel estimation performance, AI demodulation performance, AI equalization performance, priority of AI function, or vendor information corresponding to AI function.

[0027] For example, the priority of AI functions can be that each AI function has its own priority level. For instance, the priority of AI channel estimation is higher than that of AI equalization, and the priority of AI equalization is higher than that of AI demodulation.

[0028] For example, the priority of AI functions can be the combined priority of multiple AI functions versus the priority of a single AI function. For instance, the combined priority of multiple AI functions may be higher than the priority of a single AI function. For example, in AI channel estimation, AI equalization, and AI demodulation, the combined priority of at least two AI functions may be higher than the priority of each AI function in AI channel estimation, AI equalization, and AI demodulation.

[0029] In conjunction with the first aspect, in some possible implementations, before receiving the first information, the method further includes: sending a second information, the second information being used to indicate whether the first device supports AI functions, wherein, if the second information indicates that the first device supports AI functions, the second information also indicates the AI ​​functions supported by the first device.

[0030] For example, the second piece of information can indicate whether the first device supports AI functionality through one or more fields.

[0031] For example, if the first device supports AI functionality, the second information can indicate the AI ​​functionality supported by the first device through one or more fields.

[0032] In conjunction with the first aspect, in some possible implementations, where the second information indicates the AI ​​functions supported by the first device, the second information also indicates the manufacturer information corresponding to the AI ​​functions supported by the first device.

[0033] For example, the manufacturer information corresponding to an AI function can be the manufacturer identification information corresponding to that AI function.

[0034] In conjunction with the first aspect, among some possible implementations, the method further includes: sending first data to the second device based on the first information, wherein the first data is data processed by the first device based on the first configuration information in the case of the first segmentation information.

[0035] For example, the first data can be the data processed by the first device after receiving the air interface signal. For instance, the first data can be frequency domain signal data, and the processing of the air interface signal by the first device can include one or more operations such as Fast Fourier Transform, Cyclic Prefix Removal, and Precoding.

[0036] For example, the first data could be frequency domain symbol data; or frequency domain symbol data and channel data; or frequency domain symbol data after channel equalization; or log-likelihood ratio (LLR) data.

[0037] For example, the first data is data processed based on the first configuration information, which may be indicated by the first information or determined based on the first information. For instance, the first information is used to indicate the first segmentation information, and the first device determines the first configuration information based on the first segmentation information. Specific examples can be found in the description of the following embodiments.

[0038] Based on the above scheme, after receiving the first information, the first device processes the data to be transmitted according to the first configuration information and sends the processed data (e.g., the first data) to the second device, thereby realizing network-inherent intelligence and improving the performance of data transmission.

[0039] In conjunction with the first aspect, in some possible implementation methods, the first data includes the output result of the AI ​​function corresponding to the first device and the accuracy corresponding to the output result of the AI ​​function.

[0040] For example, the first data includes the output result of the first device after processing based on the AI ​​function corresponding to the first device indicated in the first configuration information, and the accuracy corresponding to the output result of the AI ​​function.

[0041] For example, the precision of the AI ​​function's output can be used to indicate the number of bytes or bits that the AI ​​function's output occupies in the first data.

[0042] In conjunction with the first aspect, in some possible implementations, the first data satisfies one or more of the following: When the AI ​​function corresponding to the first device includes AI channel estimation, the first data includes channel data and a first precision, where the channel data represents the output data of the AI ​​channel estimation corresponding to the first device, and the first precision indicates the precision of the AI ​​channel estimation result output by the first device; when the AI ​​function corresponding to the first device includes AI equalization, the first data includes symbol data and a second precision, where the symbol data represents the output data of the AI ​​equalization corresponding to the first device, and the second precision indicates the precision of the AI ​​equalization output result by the first device; or, when the AI ​​function corresponding to the first device includes AI demodulation, the first data includes log-likelihood ratio (LLR) data and a third precision, where the LLR data represents the output data of the AI ​​demodulation corresponding to the first device, and the third precision indicates the precision of the AI ​​demodulation output result by the first device.

[0043] For example, the AI ​​function corresponding to the first device indicated by the first configuration information is different, and the data results of the AI ​​function and the precision corresponding to the AI ​​function included in the first data are different.

[0044] For example, channel data can be the output data of AI channel estimation corresponding to the first device; symbol data can be the output data of AI equalization corresponding to the first device; LLR data can be the output data of AI demodulation corresponding to the first device.

[0045] For example, channel data can be a feature of the output data of AI channel estimation corresponding to the first device (e.g., one or more of the bandwidth, number of symbols, or frequency selectivity corresponding to the channel data); symbol data can be a feature of the output data of AI equalization corresponding to the first device (e.g., one or more of the signal-to-noise ratio, amplitude gain, etc. corresponding to the symbol data); LLR data can be a feature of the output data of AI demodulation corresponding to the first device (e.g., the mapping relationship between LLR data and bits).

[0046] In conjunction with the first aspect, in some possible implementations, the first segmentation information includes any one of the following: segmentation information 1, segmentation information 2, segmentation information 3, or segmentation information 4. Segmentation information 1 corresponds to: the second device including a channel estimation unit, an equalization unit, and a demodulation unit; segmentation information 2 corresponds to: the first device including a channel estimation unit, and the second device including an equalization unit and a demodulation unit; segmentation information 3 corresponds to: the first device including a channel estimation unit and an equalization unit, and the second device including a demodulation unit; segmentation information 4 corresponds to: the first device including a channel estimation unit, an equalization unit, and a demodulation unit.

[0047] For example, the first segmentation information can be any one of the segmentation information 1 to segmentation information 4 mentioned above. Different segmentation information results in different functional units corresponding to the first device and the second device. Furthermore, AI models are deployed on these functional units; therefore, the AI ​​functions corresponding to the first device and the second device differ depending on the segmentation information.

[0048] Secondly, a communication method is provided. This method can be executed by a second device in a network device. The second device can be the second device itself, or a component used in the second device (such as a chip or circuit, which can be a modem chip, also known as a baseband chip, or a system-on-a-chip or system-in-package chip containing a modem core, etc.), or a logic module or software capable of implementing some or all of the functions of the second device, etc., and this application does not limit this. The following description uses a second device in a network device as an example.

[0049] The method includes: a second device determining first information, the first information being used to indicate first segmentation information and / or first configuration information, the first segmentation information being used to determine the function corresponding to the first device and the function corresponding to the second device, the first configuration information being used to indicate the artificial intelligence (AI) function corresponding to the first device and / or the AI ​​function corresponding to the second device, wherein the AI ​​function corresponding to the first device is different from the AI ​​function corresponding to the second device, and the AI ​​function includes one or more of the following: AI channel estimation, AI equalization, or AI demodulation; and the second device sending the first information.

[0050] It should be understood that the second aspect corresponds to the first aspect mentioned above, and detailed descriptions and technical effects can be found in the description of the first aspect mentioned above.

[0051] In conjunction with the second aspect, in some possible implementations, the second device determines the first information, including: the second device determines the first information based on the second information, the second information being used to indicate whether the first device supports AI functions, wherein, if the second information indicates that the first device supports AI functions, the second information also indicates the AI ​​functions supported by the first device.

[0052] In conjunction with the second aspect, in some possible implementations, where the second information indicates the AI ​​functions supported by the first device, the second information also indicates the manufacturer information corresponding to the AI ​​functions supported by the first device.

[0053] In conjunction with the second aspect, in some possible implementations, the method further includes: a second device receiving first data, the first data being associated with first configuration information.

[0054] In conjunction with the second aspect, in some possible implementations, the first data satisfies one or more of the following: where the first configuration information indicates that, under the first segmentation information, the AI ​​function corresponding to the first device includes AI channel estimation, the first data includes channel data and a first precision, the channel data representing the output data of the AI ​​channel estimation corresponding to the first device, and the first precision indicating the precision of the AI ​​channel estimation result output by the first device; where the first configuration information indicates that, under the first segmentation information, the AI ​​function corresponding to the first device includes AI equalization, the first data includes symbol data and a second precision, the symbol data representing the output data of the AI ​​equalization corresponding to the first device, and the second precision indicating the precision of the AI ​​equalization output result by the first device; or, where the first configuration information indicates that, under the first segmentation information, the AI ​​function corresponding to the first device includes AI demodulation, the first data includes log-likelihood ratio (LLR) data and a third precision, the LLR data representing the output data of the AI ​​demodulation corresponding to the first device, and the third precision indicating the precision of the AI ​​demodulation output result by the first device.

[0055] In conjunction with the second aspect, in some possible implementation methods, the first configuration information belongs to at least one first candidate configuration information, one or more first candidate configuration information corresponds to one candidate segmentation information in at least one candidate segmentation information, each first candidate configuration information in at least one first candidate configuration information includes the AI ​​function corresponding to the first device and / or the AI ​​function corresponding to the second device, and at least one candidate segmentation information includes first segmentation information, which corresponds to the first configuration information.

[0056] In conjunction with the second aspect, in some possible implementations, each of the first candidate configuration information in at least one first candidate configuration information is different from the others.

[0057] In conjunction with the second aspect, in some possible implementations, the first configuration information is configuration information that satisfies a first condition among at least one first candidate configuration information, the first condition being associated with data transmission performance information and / or AI function information.

[0058] In conjunction with the second aspect, in some possible implementations, the first segmentation information is associated with the transmission bandwidth between the first device and the second device and / or the computing power corresponding to the first device, and the first segmentation information corresponds to at least one second candidate configuration information in at least one first candidate configuration information, wherein the at least one second candidate configuration information includes the first configuration information.

[0059] In conjunction with the second aspect, in some possible implementations, where at least one second candidate configuration information includes multiple second candidate configuration information, the first configuration information is the configuration information among at least one second candidate configuration information that satisfies a first condition, the first condition being associated with data transmission performance information and / or AI function information.

[0060] In conjunction with the second aspect, in some possible implementation methods, the AI ​​functions supported by the first device overlap with the AI ​​functions supported by the second device.

[0061] In conjunction with the second aspect, in some possible implementations, the first configuration information is configuration information that satisfies the first condition among at least one third candidate configuration information. The AI ​​functions included in each of the at least one third candidate configuration information are the same as the first set. The first set is the union of all AI functions supported by the first device and all AI functions supported by the second device. The AI ​​function corresponding to the first device in each third candidate configuration information belongs to a subset of all AI functions supported by the first device, and the AI ​​function corresponding to the second device in each third candidate configuration information belongs to a subset of all AI functions supported by the second device. The first condition is associated with the performance information of data transmission and / or the information of the AI ​​function.

[0062] In conjunction with the second aspect, in some possible implementation methods, the information of the AI ​​function associated with the first condition includes at least one of the following: performance information of the AI ​​function, priority information of the AI ​​function, or manufacturer information corresponding to the AI ​​function.

[0063] In conjunction with the second aspect, among some possible implementation methods, the first condition is associated with at least one of the following: bit error rate, throughput, AI channel estimation performance, AI demodulation performance, AI equalization performance, priority of AI function, or vendor information corresponding to AI function.

[0064] In conjunction with the second aspect, among some possible implementation methods, the first data includes the output results of the AI ​​function and the accuracy corresponding to the AI ​​function.

[0065] In conjunction with the second aspect, in some possible implementations, the first segmentation information includes any one of the following: segmentation information 1, segmentation information 2, segmentation information 3, or segmentation information 4. Segmentation information 1 corresponds to: the second device including a channel estimation unit, an equalization unit, and a demodulation unit; segmentation information 2 corresponds to: the first device including a channel estimation unit, and the second device including an equalization unit and a demodulation unit; segmentation information 3 corresponds to: the first device including a channel estimation unit and an equalization unit, and the second device including a demodulation unit; segmentation information 4 corresponds to: the first device including a channel estimation unit, an equalization unit, and a demodulation unit.

[0066] Thirdly, a communication device is provided, which has the functions of the first aspect above. For example, the communication device includes modules, units or means corresponding to the operations involved in the first aspect above. The modules, units or means can be implemented by software, or by hardware, or by a combination of software and hardware.

[0067] For example, the communication device may be the first device described above, such as a module or unit (e.g., a chip, a chip system, or a circuit) that corresponds to the method, operation, step, or action described in the first aspect above.

[0068] In one possible implementation, the communication device includes a transceiver unit (or communication module) and a processing unit (or processing module) connected to the transceiver unit.

[0069] For example, the transceiver unit is configured to receive first information, which is used to indicate first segmentation information and / or first configuration information. The first segmentation information is used to determine the function corresponding to the first device and the function corresponding to the second device. The first configuration information is used to indicate the artificial intelligence (AI) function corresponding to the first device and / or the AI ​​function corresponding to the second device. The AI ​​function corresponding to the first device is different from the AI ​​function corresponding to the second device. The AI ​​function includes one or more of the following: AI channel estimation, AI equalization, or AI demodulation.

[0070] Optionally, the communication device may further include a processing unit for performing other processing operations in the first aspect described above, besides the receiving and / or transmitting operations.

[0071] Fourthly, a communication device is provided, which has the functions of the aforementioned network device. For example, the communication device includes modules, units, or means that perform the operations involved in the second aspect. The modules, units, or means can be implemented by software, hardware, or a combination of software and hardware.

[0072] For example, the communication device may be the second device described above, such as a module or unit (e.g., a chip, a chip system, or a circuit) that corresponds one-to-one with the method, operation, step, or action described in the second aspect above.

[0073] In one possible implementation, the communication device includes a transceiver unit (or communication module) and a processing unit (or processing module) connected to the transceiver unit.

[0074] For example, the processing unit is configured to determine first information, which is used to indicate first segmentation information and / or first configuration information. The first segmentation information is used to determine the function corresponding to the first device and the function corresponding to the second device. The first configuration information is used to indicate the artificial intelligence (AI) function corresponding to the first device and / or the AI ​​function corresponding to the second device. The AI ​​function corresponding to the first device is different from the AI ​​function corresponding to the second device. The AI ​​function includes one or more of the following: AI channel estimation, AI equalization, or AI demodulation. The transceiver unit is configured to transmit the first information.

[0075] Fifthly, a communication device is provided. The communication device may be either the first device or the second device described above. The communication device includes a processor configured to retrieve and execute a computer program from a memory, causing the communication device to perform the methods in any of the possible implementations of the first to second aspects described above.

[0076] Optionally, the communication device further includes a transceiver and a memory. The processor controls the transceiver to send and receive signals, and the memory stores computer programs. The memory can be integrated into the processor or set up independently.

[0077] Optionally, there may be one or more processors and one or more memories.

[0078] Alternatively, the memory can be integrated with the processor, or the memory can be set separately from the processor.

[0079] Optionally, the transceiver includes a transmitter and a receiver.

[0080] In a sixth aspect, a communication device is provided, the communication device including one or more processors, the one or more processors being configured to execute computer programs or instructions, such that when the computer programs or instructions are executed, the communication device implements the methods in any possible design or implementation of the first to second aspects described above.

[0081] Optionally, the communication device further includes a memory for storing part or all of the computer program or instructions for implementing the functions involved in the first to fourth aspects described above.

[0082] In one possible design, the communication device may also include interface circuitry, wherein the processor is used to communicate with other devices or components via the interface circuitry.

[0083] The aforementioned communication device may be the first device, or the communication module in the first device, or the chip in the first device responsible for communication functions, such as an MDEM chip, or a SoC chip or system-in-a-package (SIP) chip containing a modem module.

[0084] The aforementioned communication device may be a first device / second device, or a communication module in the first device / second device, or a circuit or chip in the first device / second device responsible for communication functions, or a functional module in the first device / second device capable of calling and executing programs.

[0085] In a seventh aspect, a communication system is provided. The communication system includes a first device and / or a second device, wherein the first device is configured to perform the method in any possible implementation of the first aspect, and the second device is configured to perform the method in any possible implementation of the second aspect.

[0086] For example, the first device may be a chip or circuit used in the first device, or a functional module in the first device that can call and execute a program; or the second device may be a chip or circuit used in the second device, or a functional module in the second device that can call and execute a program.

[0087] For example, in an open RAN (O-RAN or ORAN) scenario, the first device can be a radio unit (RU) and the second device can be a distributed unit (DU).

[0088] Eighthly, a computer-readable storage medium is provided. This computer-readable storage medium stores computer program code or instructions to cause the methods in any of the possible implementations of the first to second aspects to be implemented. For example, when the computer program code or instructions are executed, the methods in any of the possible implementations of the first to second aspects are implemented.

[0089] A ninth aspect provides a computer program product. This computer program product includes computer program code or instructions to cause the methods in any of the possible implementations of the first to second aspects to be implemented. For example, when a computer reads and executes the computer program product, the methods in any of the possible implementations of the first to second aspects are implemented.

[0090] In a tenth aspect, a computer program is provided. When the computer program is run, it causes the method in any of the possible implementations of the first to second aspects to be implemented. Attached Figure Description

[0091] Figure 1 This is a schematic diagram of a communication system applicable to this application;

[0092] Figure 2This is a schematic diagram of another communication system applicable to this application;

[0093] Figure 3 This is a flowchart illustrating the communication method provided in the embodiments of this application;

[0094] Figure 4 This is a schematic diagram of a network architecture provided in an embodiment of this application;

[0095] Figure 5 This is a schematic diagram of the data format corresponding to the first data provided in the embodiments of this application;

[0096] Figure 6 This is a schematic block diagram of a communication device provided in an embodiment of this application;

[0097] Figure 7 This is a schematic block diagram of another communication device provided in the embodiments of this application;

[0098] Figure 8 This is a schematic diagram of the structure of an AI processor provided in an embodiment of this application. Detailed Implementation

[0099] To facilitate understanding of the above embodiments provided in this application, the following points are made:

[0100] 1) In this application, unless otherwise specified or in case of logical conflict, the terms and / or descriptions of different embodiments are consistent and can be referenced by each other. The technical features of different embodiments can be combined to form new embodiments according to their inherent logical relationship.

[0101] 2) In this application, "at least one" means one or more, and "more than one" means two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, or B exists alone, where A and B can be singular or plural. In the textual description of this application, the character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, and c can mean: a, or, b, or, c, or, a and b, or, a and c, or, b and c, or, a, b, and c. Here, a, b, and c can each be single or multiple.

[0102] 3) In this application, the terms "first," "second," and various numerical designations (e.g., #1, #2, etc.) indicate distinctions made for ease of description and are not intended to limit the scope of the embodiments of this application. For example, they may distinguish different messages, rather than describing a specific order or sequence. It should be understood that such descriptions can be interchanged where appropriate to describe solutions other than those in the embodiments of this application.

[0103] 4) In this application, descriptions such as “when…”, “under the circumstances of…” and “if” all refer to the fact that the device will make corresponding processing under certain objective circumstances. They are not time limits, nor do they require the device to make a judgment action when it is implemented, nor do they mean that there are other limitations.

[0104] 5) In this application, "instruction" or "for instruction" can include both direct and indirect instruction. When describing an instruction as being used to instruct A, it may include whether the instruction directly instructs A or indirectly instructs A, but does not necessarily mean that the instruction carries A.

[0105] The indication methods involved in the embodiments of this application should be understood to cover various methods that enable the party to be indicated to obtain the information to be indicated. The information to be indicated can be sent as a whole or divided into multiple sub-information and sent separately. Moreover, the sending period and / or sending time of these sub-information can be the same or different. This application does not limit the sending method, for example.

[0106] The "instruction information" in the embodiments of this application can be an explicit instruction, that is, a direct instruction through signaling, or an instruction obtained by combining other rules or parameters with the parameters indicated by the signaling, or by deduction. It can also be an implicit instruction, that is, an instruction obtained based on rules or relationships, or based on other parameters, or by deduction. This application does not specifically limit it in this regard.

[0107] 6) In this application, "communication" or "transmission" can also be described as "data transmission," "information transmission," "data processing," "signaling transmission," "broadcast channel transmission," etc. "Transmission" includes "sending" and / or "receiving." "Transmission" can be described as "output."

[0108] 7) In this application, "sending information to XX (device)" can be understood as the destination of the information being that device. This can include sending information directly or indirectly to that device. "Receiving information from XX (device), or receiving information from XX (device)" can be understood as the source of the information being that device, and can include receiving information directly or indirectly from that device. Information may undergo necessary processing between the source and destination, such as format changes, but the destination can understand the valid information from the source. Similar expressions in this application can be understood in a similar way, and will not be elaborated further here.

[0109] 8) In this application, the words “exemplary,” “example,” “for instance,” “e.g.,” are used to indicate examples, illustrations, or descriptions. Any embodiment or design described as an “example” in this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the word “example” is intended to present a concept in a concrete manner. In the embodiments of this application, “of,” “corresponding, relevant,” and “corresponding” may sometimes be used interchangeably, and it should be noted that their intended meanings are consistent unless their distinction is emphasized.

[0110] 9) In this application, "predefined" can mean a standard protocol predefined, or it can mean something pre-agreed upon or negotiated between devices. Here, "protocol" can refer to a standard protocol in the field of communications, such as a fourth-generation (4G) protocol. th Generation 4G network, fifth generation (5G) network th This application does not limit the scope to network protocols such as 5G (generation, 5G), New Radio (NR), 5.5G, and related protocols applied in future communication networks. "Predefined" may include "preconfiguration," which can be achieved by pre-storing corresponding codes, tables, or other methods that can indicate relevant information in the device.

[0111] 10) In this application, "identifier" can also be replaced with: index, number, sequence number, etc. For example, the identifier corresponding to the segmentation position in the embodiments of this application can be replaced with index, number, or sequence number.

[0112] 11) In this application, the configuration can be signaling configuration, such as radio resource control (RRC) messages, control information (such as uplink control information (UCI)), or medium access control (MAC) signaling (e.g., MAC control element (MAC CE / MAC-CE)). As an example, the signaling configuration can be configured by signaling to the first device and / or the second device. For example, the second device configures the correspondence between candidate segmentation information and candidate configuration information for the first device. This can be understood as the second device instructing the first device to communicate this correspondence via signaling.

[0113] The technical solutions in this application will now be described with reference to the accompanying drawings.

[0114] The technical solutions of this application can be applied to various communication systems, such as: Long Term Evolution (LTE) systems, LTE Frequency Division Duplex (FDD) systems, LTE Time Division Duplex (TDD) systems, 5G systems, or New Radio (NR) and future communication systems. The technical solutions provided in this application can also be applied to device-to-device (D2D) communication, vehicle-to-everything (V2X) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), and Internet of Things (IoT) communication systems.

[0115] Furthermore, the embodiments of this application are applicable to both homogeneous and heterogeneous network scenarios, and there are no restrictions on the transmission points. They can be applied to systems such as multi-point collaborative transmission between macro base stations, micro base stations, and macro base stations. The embodiments of this application are applicable to both low-frequency and high-frequency scenarios, including terahertz and optical communications.

[0116] In a communication system, a device can send signals to or receive signals from another device. These signals may include reference signals, information, signaling, or data. In this application, "device" can be replaced by an entity, network entity, communication equipment, communication module, node, or communication node.

[0117] Figure 1 This is a schematic diagram of a communication system applicable to an embodiment of this application. For example... Figure 1 As shown, the communication system 10 includes a radio access network (RAN) 100 and a core network (CN) 200. RAN 100 includes at least one RAN node (e.g., Figure 1 110a and 110b (collectively referred to as 110) and at least one terminal (such as Figure 1 RAN100, denoted as RAN100, comprises RAN nodes 120a-120j, collectively referred to as RAN120. RAN100 may also include other RAN nodes, such as wireless relay equipment and / or wireless backhaul equipment. Figure 1(Not shown in the image). Terminal 120 is connected to RAN node 110 wirelessly. RAN node 110 is connected to core network 200 wirelessly or via wired connection. The core network equipment in core network 200 and RAN node 110 in RAN 100 can be different physical devices, or they can be the same physical device integrating core network logical functions and radio access network logical functions.

[0118] RAN 100 can be a cellular system related to the 3rd Generation Partnership Project (3GPP), such as a 4G mobile communication system, a 5G mobile communication system, or a future-oriented evolution system. RAN 100 can also be O-RAN, a cloud radio access network (CRAN), or a wireless fidelity (WiFi) system. RAN 100 can also be a communication system that integrates two or more of the above systems.

[0119] RAN node 110, sometimes also referred to as network equipment, 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 the 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 1 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 1 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.

[0120] In one possible scenario, a RAN node can be a base station (BS), an evolved NodeB (eNodeB), an access point (AP), a transmission reception point (TRP), a base station in a future mobile communication system, or an access node in a WiFi system, etc. Figure 1 110a), micro base stations or indoor stations (such as Figure 1In CRAN scenarios, RAN nodes can be 110b), relay nodes or donor nodes, or wireless controllers. Optionally, RAN nodes can also be servers, wearable devices, vehicles, or in-vehicle equipment. For example, in vehicle-to-everything (V2X) technology, the access network equipment can be a roadside unit (RSU).

[0121] In another possible scenario, multiple RAN nodes collaborate to assist the terminal in achieving wireless access, with different RAN nodes each implementing some of the base station's functions. For example, RAN nodes can be central units (CUs), distributed units (DUs), CU-control planes (CU-CPs), CU-user planes (CU-UPs), radio units (RUs), or CU-radio units (CU-RUs), etc. CUs and DUs can be set up separately or included in the same network element, such as a baseband unit (BBU). RUs can be included in radio frequency equipment or radio frequency units, such as remote radio units (RRUs), active antenna units (AAUs), or remote radio heads (RRHs).

[0122] In different systems, CU (including open CU-CP (O-CU-CP) and open CU-UP (O-CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an ORAN system, CU can also be called an open central unit (O-CU), DU can also be called an open distributed unit (O-DU), CU-CP can also be called O-CU-CP, CU-UP can also be called O-CU-UP, and RU can also be called O-RU. For ease of description, this application uses CU, CU-CP, CU-UP, DU, and RU as examples. Any of the CU (or CU-CP, CU-UP), DU, and RU in this application can be implemented through software modules, hardware modules, or a combination of software and hardware modules.

[0123] Terminal 120 can be a device or module that accesses the aforementioned communication system and has corresponding communication functions. A terminal can also be referred to as user equipment (UE), terminal, user device, access terminal, user unit, user station, mobile station, mobile station (MS), remote station, remote terminal, mobile device, user terminal, terminal unit, terminal station, terminal device, wireless communication equipment, user agent, or user device. A terminal typically contains a communication module, circuit, or chip that performs the corresponding communication functions. The terminal may also be configured with program instructions for performing these communication functions.

[0124] For example, the terminal in this application embodiment can be a mobile phone, a personal digital assistant (PDA) computer, a laptop computer, a tablet computer, a drone, a computer with wireless transceiver capabilities, a machine type communication (MTC) terminal, a virtual reality (VR) terminal, an augmented reality (AR) terminal, an Internet of Things (IoT) terminal, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in remote medical care, a wireless terminal in a smart grid, a wireless terminal in transportation safety, a wireless terminal in a smart city, a wireless terminal in a smart home (e.g., game consoles, smart TVs, smart speakers, smart refrigerators, and fitness equipment), a transport vehicle with wireless communication capabilities, a communication module, or a roadside unit (RSU) with terminal capabilities.

[0125] RAN 100 and terminal 120 can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; they can also be deployed on water; and they can also be deployed in the air on aircraft, balloons, and satellites. The embodiments of this application do not limit the scenarios in which RAN 100 and terminal 120 are located.

[0126] Communication between access network devices and terminal devices follows a specific protocol layer structure. This protocol layer may include a control plane protocol layer and a user plane protocol layer. The control plane protocol layer may include at least one of the following: radio resource control (RRC) layer, packet data convergence protocol (PDCP) layer, radio link control (RLC) layer, media / medium access control (MAC) layer, or physical (PHY) layer, etc. The user plane protocol layer may include at least one of the following: service data adaptation protocol (SDAP) layer, PDCP layer, RLC layer, MAC layer, or physical layer, etc.

[0127] The correspondence between network elements and their achievable protocol layer functions in the ORAN system can be found in Table 1 below.

[0128] Table 1

[0129] ORAN network elements 3GPP protocol layer functions O-CU-CP RRC+PDCP-Control Plane (PDCP-C) O-CU-UP SDAP+PDCP - User Plane (PDCP-U) O-DU RLC+MAC+PHY-high O-RU PHY-low

[0130] CN 200 can be a 5G core network or an evolved 5G core network. Taking a 5G core network as an example, CN 200 includes access and mobility management (AMF) network elements responsible for mobility management and access management services; session management (SMF) network elements responsible for session management; user plane (UPF) network elements responsible for user plane packet routing and forwarding and quality of service (QoS) control; and policy control (PCF) network elements. These core network elements can operate independently or be combined to implement certain control functions; for example, AMF, SMF, and PCF can be combined into a single core network device.

[0131] The communication system 10 provided in this application may further include AI network elements for implementing some or all AI-related operations. AI network elements may also be referred to as AI nodes, AI devices, AI entities, AI modules, AI models, or AI units, etc. The AI ​​network elements may be built into the network elements of the communication system. For example, an AI network element may be an AI module built into access network equipment, core network equipment, cloud servers, or operation, administration and maintenance (OAM) management systems to implement AI-related functions. The OAM may be the management system for core network equipment and / or the management system for access network equipment. Alternatively, the AI ​​network element may be an independently configured network element in the communication system. Optionally, the terminal or its built-in chip may also include an AI entity for implementing AI-related functions.

[0132] Figure 2 This is a schematic diagram of a possible application framework in a communication system applicable to embodiments of this application. For example... Figure 2 As shown, network elements in a communication system are connected via interfaces (e.g., NG, Xn) or air interfaces. These network element nodes, such as core network equipment, access network nodes (RAN nodes), terminals, or one or more devices in the OAM, are equipped with one or more AI modules (for clarity, ...). Figure 2 (Only one is shown in the image). The access network node can be a single RAN node or can include multiple RAN nodes, such as RU, CU, and DU. One or more of the RU, CU, or DU can also be equipped with one or more AI modules. Optionally, the CU can also be split into CU-CP and CU-UP. One or more AI modules are provided in CU-CP and / or CU-UP.

[0133] AI modules are used to implement corresponding AI functions. AI modules deployed in different network elements can be the same or different. Depending on the parameter configuration, the AI ​​module can implement different functions. The AI ​​module model can be configured based on one or more of the following parameters: structural parameters (e.g., at least one of the following: number of neural network layers, neural network width, inter-layer connections, neuron weights, neuron activation function, or biases in the activation function), input parameters (e.g., the type and / or dimension of the input parameters), or output parameters (e.g., the type and / or dimension of the output parameters). The biases in the activation function can also be referred to as the neural network biases.

[0134] An AI module can have one or more models. A model can infer an output, which includes one or more parameters. The learning, training, or inference processes of different models can be deployed on different nodes or devices, or they can be deployed on the same node or device.

[0135] It should be understood that the above naming is defined solely for the purpose of distinguishing different functions and should not constitute any limitation on this application. This application does not preclude the possibility of using other naming conventions in 5G networks and other future networks. For example, in future networks, some or all of the above-mentioned network elements may use the terminology from 5G, or they may use other names, etc.

[0136] Understandable. Figure 1 or Figure 2 This is merely an example and does not constitute a limitation on the scope of protection of this application. The communication method provided in the embodiments of this application may also involve... Figure 1 The network elements not shown in the diagram may also include, of course, the communication method provided in this application embodiment, only network elements not shown in the diagram. Figure 1 Some of the network elements are shown.

[0137] To facilitate understanding of the embodiments of this application, the basic concepts involved in this application will be explained first.

[0138] 1. AI: AI enables machines to possess human-like intelligence, for example, allowing machines to use computer hardware and software to simulate certain intelligent human behaviors. To achieve artificial intelligence, machine learning methods can be employed. In machine learning, machines learn (or train) models using training data. This model represents the mapping between inputs and outputs. The learned model can be used for reasoning (or prediction), that is, it can be used to predict the output corresponding to a given input. This output can also be called the reasoning result (or prediction result).

[0139] This document explains some basic concepts in the field of AI, which does not limit the scope of protection of the embodiments of this application.

[0140] (1) Machine learning (ML):

[0141] Machine learning is a crucial technological approach to achieving AI. AI endows machines with human-like intelligence, using computer hardware and software to simulate certain intelligent human behaviors, including machine learning and other methods. Machine learning refers to learning models or rules from raw data, such as neural networks, decision trees, and support vector machines. Machine learning can be categorized into supervised learning, unsupervised learning, and reinforcement learning.

[0142] Supervised learning, based on collected sample values ​​and labels, uses machine learning algorithms to learn the mapping relationship between sample values ​​and labels, and expresses this learned mapping relationship using a machine learning model. The process of training the machine learning model is the process of learning this mapping relationship. For example, in signal detection, the noisy received signal is the sample, and the corresponding real constellation point is the label. Machine learning aims to learn the mapping relationship between samples and labels through training, that is, to enable the machine learning model to learn a signal detector. During training, the model parameters are optimized by calculating the error between the model's predicted values ​​and the real labels. Once the mapping relationship is learned, it can be used to predict the sample label of each new sample. The mapping relationship learned in supervised learning can include linear mappings and nonlinear mappings. Based on the type of label, the learning task can be divided into classification tasks and regression tasks.

[0143] Unsupervised learning relies solely on collected sample values, using algorithms to discover inherent patterns within the samples. One type of unsupervised learning algorithm uses the samples themselves as supervisory signals; that is, the model learns the mapping relationship from sample to sample, which is called self-supervised learning. During training, model parameters are optimized by calculating the error between the model's predictions and the samples themselves. Self-supervised learning can be used for signal compression and decompression recovery applications; common algorithms include autoencoders and generative adversarial networks.

[0144] Reinforcement learning, unlike supervised learning, is a type of algorithm that learns problem-solving strategies through interaction with the environment. Unlike supervised and unsupervised learning, reinforcement learning problems do not have explicit "correct" action labels. The algorithm needs to interact with the environment to obtain reward signals from the environment, and then adjust its decision actions to obtain a larger reward signal value. For example, in downlink power control, the reinforcement learning model adjusts the downlink transmission power of each terminal device based on the total system throughput feedback from the wireless network, aiming to achieve a higher system throughput. The goal of reinforcement learning is also to learn the mapping relationship between the environment state and the optimal / near-optimal decision actions. However, because the label of the "correct action" cannot be obtained in advance, the network cannot be optimized by calculating the error between the action and the "correct action." Reinforcement learning training is achieved through iterative interaction with the environment.

[0145] Deep neural networks (DNNs) are a specific implementation of machine learning. According to the general approximation theorem, neural networks can theoretically approximate any continuous function, thus enabling them to learn arbitrary mappings. Traditional communication systems rely on extensive expert knowledge to design communication modules, while DNN-based deep learning communication systems can automatically discover hidden pattern structures from large datasets, establish mapping relationships between data, and achieve performance superior to traditional modeling methods.

[0146] Based on their construction method, DNNs can be divided into feedforward neural networks (FNNs), convolutional neural networks (CNNs), and recurrent neural networks (RNNs). FNNs can be neural networks where neurons in adjacent layers are completely connected pairwise, which makes FNNs typically require a large amount of storage space and have high computational complexity.

[0147] CNNs are neural networks specifically designed to process data with a grid-like structure. For example, time-series data (discrete sampling along the time axis) and image data (two-dimensional discrete sampling) can both be considered grid-like data. CNNs do not use all the input information at once for computation; instead, they use a fixed-size window to extract a portion of the information for convolution operations, which significantly reduces the computational cost of model parameters. Furthermore, depending on the type of information extracted by the window (such as people and objects in an image representing different types of information), each window can use different convolution kernels, allowing CNNs to better extract features from the input data.

[0148] Recurrent Neural Networks (RNNs) are a type of distributed neural network (DNN) that utilizes feedback time-series information. Their input includes the current input value and their own output value from the previous time step. RNNs are well-suited for acquiring temporally correlated sequence features, and are particularly applicable to applications such as speech recognition and channel coding / decoding.

[0149] AI models refer to function models that map a certain-dimensional input to a certain-dimensional output, and their parameters can be obtained through machine learning training. For example, f(X) = aX² + b is a quadratic function model, which can be viewed as an AI model. a and b correspond to the model's parameters and can be obtained through machine learning training. Data used for model training, validation, and / or testing in machine learning can form datasets or training datasets. The quantity and / or quality of data in these datasets or training datasets will affect the effectiveness of machine learning. Model training involves selecting an appropriate loss function (which measures the difference between the model's predictions and the true values) and using optimization algorithms to train the model parameters to minimize the loss function value. Model testing involves evaluating the model's performance using test data after training. Model application involves using the trained model to solve real-world problems.

[0150] A neural network, or artificial neural network, is a mathematical model that mimics the behavioral characteristics of animal neural networks to perform distributed parallel information processing. It is a special form of AI model.

[0151] (2) Model training:

[0152] Model training involves selecting an appropriate function (such as a loss function) and using optimization algorithms to train the model parameters so that the difference between the model's predicted values ​​and the ground truth (or target values, labels) tends to be minimized.

[0153] For example, model training methods include, but are not limited to, supervised learning, self-supervised learning, and knowledge distillation.

[0154] (3) Model file and model parameters:

[0155] Model files and / or model parameters can be used to determine the model. Optionally, the model in this application may refer to the model itself, or it may refer to the model files and / or model parameters used to determine the model.

[0156] The model file can be used to indicate the model structure, which may include, but is not limited to, FNN, CNN, or RNN. The model file can have a fixed format, such as a standard predefined format, or a format pre-negotiated by both ends of the connection. Model parameters can refer to the parameters in the neural network model, such as, but not limited to, the number of layers in the neural network, the type and weights of neurons in each layer, etc. This application does not limit the method of distributing model parameters.

[0157] Take DNN as an example. The idea behind DNN comes from the neuronal structure of the brain. Each neuron can perform a weighted summation operation on its inputs and then use the result of the weighted summation operation to generate the output through a non-linear function. For example, the input of a neuron is x = [x0, x1, ..., x...]. N-1 The weights corresponding to the inputs are w = [w0, w1, ..., w] N-1 The bias of the weighted summation is b. The nonlinear function f() can take many forms; for example, the nonlinear function f() can be the maximum value function max{0, x}. Then the effect of a neuron's execution is... Where N is a positive integer, and n is a positive integer greater than or equal to 0 and less than or equal to (N-1). The weights of the weighted summation operation of neurons in a neural network and the nonlinear function are called the parameters of the neural network. The parameters of all neurons in a neural network constitute the parameters of the neural network.

[0158] A DNN typically has multiple neural network layers, including an input layer, one or more hidden layers, and an output layer. Generally, the first layer is the input layer, the last layer is the output layer, and the layers in between are hidden layers. Each layer contains multiple neurons. Layers are fully connected; that is, any neuron in the i-th layer is connected to any neuron in the (i+1)-th layer. The input layer processes the received values ​​(i.e., the DNN's input) through neurons and then passes them to the hidden layers. Similarly, the hidden layers pass the computation results to the final output layer, producing the DNN's output. This application does not limit the structure and parameters used in the AI ​​model.

[0159] One of the model structure or model parameters can be predefined, while the other can be sent by the sender (e.g., the network side). Alternatively, both the model structure and model parameters can be sent by the sender (e.g., the network side). This application does not impose any restrictions on this.

[0160] Sending a model can refer to sending a model file and / or model parameters, while receiving a model can refer to receiving a model file and / or model parameters.

[0161] With the development of wireless communication technology, intelligence will further evolve at the wireless network architecture level. AI and wireless networks will be further deeply integrated to achieve network intelligence. In network intelligence scenarios, in addition to providing traditional communication connectivity services, the network can also combine with AI to provide AI services, realizing the inclusiveness, real-time nature, and high security of network intelligence.

[0162] To achieve network intelligence, AI models can be deployed in base stations. These AI models can then be used to implement physical layer functions within network devices. In future network architectures, the separation of base station architecture is likely to be a common design. For example, in a separated base station architecture scenario, the base station can be divided into multiple parts; in other words, a base station can include multiple parts, or a base station can be composed of multiple parts, or multiple parts can constitute a single base station. How to deploy AI models in base stations under this separated base station architecture scenario is currently a hot research topic.

[0163] Based on the above description, this application provides a communication method to provide a method for deploying AI models in scenarios where base station architectures are separated, thereby achieving network intelligence.

[0164] In this application embodiment, the method provided by this application is described using a scenario where the network device (e.g., a base station) architecture is separated, with the network device comprising two parts as an example. Of course, the method provided by this application also applies to cases where the network device includes multiple parts (e.g., a third part, or a fourth part, etc.). For example, the network device is divided into two parts, which may include a first device and a second device. The first device may be responsible for radio frequency and some lower-level physical layer processing functions in the network device, while the second device may be responsible for some higher-level physical layer functions in the network device, and may further include one or more of the following: higher-level protocol stack processing and control functions. Considering a scenario where the architecture is separated, the first device carries a portion of the functions in the network device, and the second device carries another portion of the functions in the network device. Alternatively, it can be understood that the functions included in the network device can be divided (or segmented) into two parts, with one part carried by the first device and the other by the second device. It is evident that the functions carried by the first device and the second device may differ depending on the division location (or segmentation location).

[0165] It should be understood that in some scenarios, the first device may be referred to as the first part, the first unit, the first module, or the baseband low (BBL) unit. The second device may be referred to as the second part, the second unit, the second module, or the baseband high (BBH) unit. In O-RAN scenarios, the first device may also be a RU in O-RAN, and the second device may also be a DU in O-RAN. The RU and DU in O-RAN are also applicable to the method provided in this application. For example, the AI ​​function included in the first device may be deployed on the RU, or on other devices (or network elements) besides the RU, or on the cloud, etc.; the AI ​​function included in the second device may be deployed on the DU, or on other devices (or network elements) besides the DU, or on the cloud, etc.

[0166] The communication method provided in the embodiments of this application will be described in detail below with reference to the accompanying drawings, and can be applied to the above-mentioned... Figure 1 or Figure 2 The communication system shown. It should be understood that the embodiments of this application can be applied to scenarios where the sending end and the receiving end communicate.

[0167] It should also be understood that the embodiments shown below do not specifically limit the structure of the execution subject of the method provided in the embodiments of this application, as long as it is possible to communicate according to the method provided in the embodiments of this application by running the code or program that records the method provided in the embodiments of this application. For example, the method provided in the embodiments of this application can be executed by a first device or a second device in a network device. Unless otherwise specified, the "first device" in this application can refer to the first device itself, or a component in the first device (e.g., a communication module, processor, circuit, chip (such as a modem chip, also known as a baseband chip, or a SoC chip or SIP chip containing a modem core, or a chip system, etc.), or it can be a logic module or software that can implement all or part of the functions of the first device. The "second device" in this application can refer to the second device itself, or a component in the second device (e.g., a communication module, processor, circuit, chip, or chip system, etc.), or it can be a logic module or software that can implement all or part of the functions of the second device.

[0168] For ease of description, in the following embodiments, in a base station separation scenario, the base station is divided into a first device and a second device as an example, where the first device is exemplified by BBL and the second device by BBH, to introduce the method provided in this application. Currently, BBL in the following embodiments can also be replaced by devices (or units, modules) with other names, which can be used to handle radio frequency and some underlying physical functions in the base station; BBH in the embodiments can also be replaced by devices (or units, modules) with other names, which can be used to handle some higher-level physical functions of the base station. The following uses the information interaction between BBL and BBH as an example to exemplarily describe the method provided in this application.

[0169] It should be understood that the method provided in this application is applicable to uplink transmission scenarios.

[0170] Figure 3 This is a flowchart illustrating a communication method provided in an embodiment of this application. For example... Figure 3 As shown, the method 300 may include the following multiple steps.

[0171] 301, The third device determines the first information.

[0172] It should be understood that the third device can be the second device (such as BBH); or, the third device can be other devices (or network elements) besides the first device (such as BBL) and the second device (such as BBH) that have the function of determining the first information. For example, the third device can be OAM.

[0173] Optionally, the third device determines the first information based on the AI ​​functions supported by BBH and / or BBL.

[0174] The first information is used to indicate the first segmentation information and / or the first configuration information. The first segmentation information is used to determine the function corresponding to BBL and the function corresponding to BBH. The first configuration information is used to indicate the AI ​​function corresponding to BBL and / or the AI ​​function corresponding to BBH, and the AI ​​function corresponding to BBL is different from the AI ​​function corresponding to BBH.

[0175] In this application, the AI ​​function is described using one or more of the following as examples: AI channel estimation, AI equalization, and AI demodulation.

[0176] For example, assuming the AI ​​function supported by BBH includes AI channel estimation, the third device can determine first information based on the AI ​​function supported by BBH. This first information is used to indicate first segmentation information and / or first configuration information. The first segmentation information is used to determine or indicate the function corresponding to BBH, wherein the function corresponding to BBH includes channel estimation. The first configuration information is used to determine or indicate that the AI ​​function corresponding to BBH includes AI channel estimation.

[0177] For another example, suppose the AI ​​functions supported by BBL include AI channel estimation, and the AI ​​functions supported by BBH include AI equalization and AI demodulation. The third device can determine first information based on the AI ​​functions supported by BBH and BBL. This first information is used to indicate first segmentation information and / or first configuration information. The first segmentation information is used to determine or indicate the functions corresponding to BBL and / or BBH, where the function corresponding to BBL includes channel estimation, and the function corresponding to BBH includes equalization and demodulation. The first configuration information indicates that the AI ​​functions corresponding to BBL include AI channel estimation, and the AI ​​functions corresponding to BBH include AI equalization and AI demodulation.

[0178] The following will provide an exemplary description of AI channel estimation, AI equalization, and AI demodulation. It is understood that other methods may also be used for AI channel estimation, AI equalization, and AI demodulation, and this application does not limit them.

[0179] For example, the input data for AI channel estimation can include signals on multiple resource units (e.g., resource elements, REs), some of which carry known pilot signals. The output data for AI channel estimation can include channel estimates (or estimated channel values) for all REs. The training data for AI channel estimation can include input features and label data. Input features can be the input data for AI channel estimation (e.g., channel observations corresponding to multiple pilot REs) and the location information corresponding to the pilots. Label data can be the actual channel values ​​(or channel responses, ideal channel estimates, or channel values ​​obtained from actual measurements) at all RE locations. AI channel estimation can be further optimized using the error between the predicted channel and the actual channel (e.g., the parameters in AI channel estimation can be iteratively optimized based on the backpropagation algorithm). The error between the predicted channel parameters and the actual channel parameters can be represented by one or more of the following: mean squared error (MSE), root mean square error, normalized mean square error, or similarity-guided channel selection (SGCS). The smaller the error or the higher the similarity, the higher the accuracy and reliability of the AI ​​channel estimation, and the better the performance.

[0180] For example, the input data for AI equalization can include the received signals from Nr antennas, and the output data can include equalized symbols from Nt data streams, where Nr and Nt are both positive integers. The training data for AI equalization can include input features and label data. The input features can be the AI ​​equalization input data (distorted data containing noise), and the label data can be the original transmitted data (noise-free / distortion-free data). The training data can include input data affected by channel distortion and noise, and the corresponding original transmitted data. The training objective can be to minimize the error between the equalized data output by the model and the original transmitted symbols (e.g., MSE, cross-entropy loss) and optimize the parameters (e.g., neural network weights, biases, etc.) in AI equalization through backpropagation (e.g., gradient descent). The evaluation metric for AI equalization can be determined by the error between the equalized data and the original transmitted data. A smaller error indicates better equalization performance, and the recovered symbols are closer to the true values.

[0181] For example, the input data for AI demodulation can include equalized data, and the output data can include the bit depth or log-likelihood ratio (LLR) corresponding to the equalized data. The training data for AI demodulation can include the equalized output data, and the training objective can include bit decision or LLR output. The performance of AI demodulation can be evaluated using bit error rate or LLR accuracy. A lower bit error rate indicates better AI demodulation performance, and a closer LLR distribution to the Shannon limit results in higher decoding gain and better AI demodulation performance.

[0182] It should be understood that the AI ​​channel estimation, AI equalization, and AI demodulation described above can also be obtained using the training methods illustrated in the following example. Taking a neural network as an example, this neural network can be any one of the AI ​​channel estimation, AI equalization, and AI demodulation methods:

[0183] For example, a neural network can be understood as a mapping from an input data set to an output data set. Generally, the initialization of a neural network can be random; the process of obtaining a mapping from existing data using random weights w and biases b can be called neural network training. Specifically, training can be implemented by using a loss function to evaluate the output of the neural network, backpropagating the error, and iteratively optimizing w and b using gradient descent until the loss function is less than or equal to a certain threshold. The loss function can be represented by the cross-entropy or MSE between the output data and the real data of the neural network. For example, the function of a neural network includes AI channel estimation; the loss function corresponding to this AI channel estimation can be represented by the cross-entropy or MSE between the output data of the AI ​​channel estimation and the real data (e.g., real channel data). The loss functions for AI equalization and AI demodulation are similar to the loss function for AI channel estimation, and will not be listed here. The gradient descent process can be represented as... θ represents the parameters to be optimized (e.g., w and b), L is the loss function, and η is the learning rate used to control the step size of gradient descent. The backpropagation process can utilize the chain rule for partial derivatives; for example, the gradient of the parameters in the previous layer can be recursively calculated from the gradient of the parameters in the next layer. The specific expression can be given as: Where w ij Let s be the weight of the connection between node j and node i. i The weighted sum of the inputs at node i.

[0184] It should be understood that the AI ​​functions supported by BBH in this application refer to the AI ​​functions that BBH can provide, and the deployment location of these AI functions can be one or more of the following: within BBH, on other devices, or in the cloud. Similarly, the AI ​​functions supported by BBL refer to the AI ​​functions that BBL can provide, and the deployment location of these AI functions can be one or more of the following: within BBL, on other devices, or in the cloud.

[0185] The method by which the third device determines the first information based on the AI ​​functions supported by BBH and / or BBL is not limited. In one possible implementation, the third device may determine the first information from the correspondence between at least one candidate configuration information and at least one candidate segmentation information, based on the AI ​​functions supported by BBH and / or BBL.

[0186] The correspondence between the at least one candidate configuration information and the at least one candidate segmentation information can be predefined, configured, or indicated, and this application does not limit this. The correspondence between the candidate configuration information and the candidate segmentation information can be represented by language, tables, diagrams, or other means (such as storage and / or transmission). The correspondence between candidate segmentation information and candidate configuration information is described below in tabular form as shown in Tables 2 and 3.

[0187] Table 2

[0188]

[0189]

[0190] Based on Table 2 above, segmentation information 1 corresponds to seven candidate configuration information, specifically configuration information 1-0 to 1-6. In configuration information 1-0, the AI ​​function corresponding to BBH can include AI channel estimation. Segmentation information 2 corresponds to four candidate configuration information, specifically configuration information 2-0 to 2-3. In configuration information 2-0, the AI ​​function corresponding to BBL can include AI channel estimation; in configuration information 2-1, the AI ​​function corresponding to BBL can include AI channel estimation, and the AI ​​function corresponding to BBH can include AI equalization; in configuration information 2-2, the AI ​​function corresponding to BBL can include AI channel estimation, and the AI ​​function corresponding to BBH can include AI demodulation; in configuration information 2-3, the AI ​​function corresponding to BBL can include AI channel estimation, and the AI ​​function corresponding to BBH can include both AI equalization and AI demodulation. The candidate configuration information corresponding to segmentation information 3 and segmentation information 4 will not be detailed here.

[0191] It should be understood that in practical applications, the correspondence between candidate segmentation information and candidate configuration information can also be obtained by various transformations of Table 2 above. For example, a certain number of rows can be added or removed from Table 2, or Table 2 can be split into multiple tables, each including some rows and columns from Table 2. For instance, Table 2 can be split into two tables (Table #2-1 and Table #2-2). Table #2-1 can include the first, second, and third columns of Table 2, and Table #2-2 can include the first, second, and fourth columns of Table 2. Table 2#1 and Table 2#2 can be composed of one or more rows from Table 2. The following will illustrate this with reference to Table 3. Of course, Table 3 is not limiting, and the specific correspondence can also include other rows or columns from Table 2 above.

[0192] Table 3

[0193]

[0194]

[0195] Based on Table 3 above, segmentation information 1 corresponds to two candidate configuration information sets, specifically configuration information 1-0 to 1-1. Segmentation information 2 corresponds to one candidate configuration information set, specifically configuration information 2-1. Segmentation information 3 corresponds to two candidate configuration information sets, specifically configuration information 3-1 and 3-2. Segmentation information 4 corresponds to two candidate configuration information sets, specifically configuration information 4-0 and 4-2.

[0196] As can be seen from Tables 2 and 3 above, a candidate segmentation information can correspond to one or more candidate configuration information.

[0197] For example, the correspondence between at least one segmentation information and at least one candidate configuration information is shown in Table 3 above. Assuming the AI ​​function supported by BBH includes AI channel estimation, the third device can determine first information based on the AI ​​function supported by BBH. This first information is used to indicate the first segmentation information and / or the first configuration information. The first segmentation information can be segmentation information 1 in Table 3 above, used to determine the function corresponding to BBH, where the function corresponding to BBH includes channel estimation. The first configuration information can be configuration information 1-0 in Table 3 above, used to indicate that the AI ​​function corresponding to BBH includes AI channel estimation.

[0198] For another example, the correspondence between at least one segmentation information and at least one candidate configuration information is shown in Table 3 above. Assuming the AI ​​function supported by BBL includes AI channel estimation, and the AI ​​function supported by BBH includes AI equalization, the third device can determine first information based on the AI ​​functions supported by BBH and BBL. This first information is used to indicate first segmentation information and / or first configuration information. The first segmentation information can be segmentation information 2 in Table 3 above. This first segmentation information is used to determine the functions corresponding to BBL and BBH, where the function corresponding to BBL includes channel estimation, and the function corresponding to BBH includes equalization and demodulation. The first configuration information can be configuration information 2-1 in Table 3 above. This first configuration information is used to indicate that the AI ​​function corresponding to BBL includes AI channel estimation, and the AI ​​function corresponding to BBH includes AI equalization.

[0199] In summary, when there is a one-to-one correspondence between the first segmentation information and the first configuration information, the first information can indicate the first segmentation information, or the first configuration information, or both the first segmentation information and the first configuration information. When the first segmentation information corresponds to one or more candidate first configuration information, the first information can indicate the first segmentation information, and the first configuration information can be determined by the first device from the one or more candidate first configuration information corresponding to the first segmentation information. Alternatively, the first information can indicate the first configuration information, and the first configuration information can implicitly indicate the first segmentation information. The first device can determine the first configuration information based on the first information, and can also determine the first segmentation information. Alternatively, the first information can indicate both the first segmentation information and the first configuration information. In this way, the first device can more clearly understand the functions and AI functions corresponding to the BBL. When the first configuration information corresponds to one or more candidate first segmentation information, the first information can indicate the first configuration information. The first segmentation information can be determined by the first device from one or more candidate first segmentation information corresponding to the first configuration information. Alternatively, the first information can indicate the first segmentation information, and the first segmentation information can implicitly indicate the first configuration information. The first device can determine the first segmentation information and the first configuration information based on the first information. Or, the first information can indicate both the first segmentation information and the first configuration information. In this way, the first device can clearly know the functions and AI functions corresponding to BBL. Furthermore, it is understood that the first configuration information can indicate one or more of the AI ​​functions corresponding to the first device (BBL) or the second device (BBH). Thus, the first device can determine the AI ​​function corresponding to the first device based on the first configuration information, and further, it can also determine the AI ​​function corresponding to the second device. Since there is also a correspondence between the AI ​​functions corresponding to the first device (BBL) or the AI ​​functions corresponding to the second device (BBH), one can determine the candidate value of the other through one of them.

[0200] The following section details the relevant schemes for the first handover information.

[0201] The first segmentation information is used to determine the functions corresponding to the BBL and the BBH; in other words, different first segmentation information results in different functions for the corresponding BBL and / or BBH. For example, the first segmentation information includes one of the following: segmentation information 1, segmentation information 2, segmentation information 3, or segmentation information 4. Segmentation information 1 corresponds to: BBH including a channel estimation unit, an equalization unit, and a demodulation unit. Segmentation information 2 corresponds to: BBL including a channel estimation unit, and BBH including an equalization unit and a demodulation unit. Segmentation information 3 corresponds to: BBL including a channel estimation unit and an equalization unit, and BBL including a demodulation unit. Segmentation information 4 corresponds to: BBL including a channel estimation unit, an equalization unit, and a demodulation unit.

[0202] It should be understood that the segmentation information shown above is merely an example. The functional units included in BBH and BBL differ depending on the segmentation information. Furthermore, BBH and BBL also include other functional units, not limited to the three functional units shown above (e.g., channel estimation unit, equalization unit, and demodulation unit). For ease of description, this application embodiment exemplarily combines the segmentation position corresponding to the segmentation information with the channel estimation unit, equalization unit, and demodulation unit. It can be understood that BBL and BBH also include other functional units, which are not shown here. For example, in the case of segmentation information 1, in addition to the channel estimation unit, equalization unit, and demodulation unit, BBH may also include one or more of the following: a descrambling unit, a rate matching unit, a decoding unit (or decryption unit), and a cyclic redundancy check (CRC) unit; BBL may include one or more of the following: a radio frequency unit, a fast Fourier transform / cyclic prefix removal unit, etc.

[0203] The format of the first segmentation information is not limited. As an example, the first segmentation information includes the identifier corresponding to the segmentation position, that is, the identifier corresponding to the segmentation method.

[0204] The identifier corresponding to the splitting position can be used to identify the splitting position. The splitting position indicates the location where the functions in the network device are divided into BBL and BBH. For example, if the functions in the network device are split at a certain position, resulting in two parts, one part of the function is handled by BBL and the other part by BBH, this position is referred to as the splitting position for ease of description. Furthermore, the term "splitting" is mentioned multiple times in the embodiments of this application; this "splitting" can be a logical division of the functions in the network device.

[0205] It should also be understood that, in conjunction with the above-mentioned segmentation information 1 to segmentation information 4, the corresponding segmentation positions in the network device can be found in [reference needed]. Figure 4 Examples are shown in the text. Among them, Figure 4 The segmentation positions corresponding to each segmentation information are only examples and are not limitations.

[0206] It should also be understood that the embodiments of this application mainly provide illustrative examples of the specific locations of the channel estimation unit, equalization unit, and demodulation unit. The combination of network devices and AI can be understood as combining functional units within the network device with AI models. For example, one or more units of the channel estimation unit, equalization unit, or demodulation unit in the network device can be combined with AI functions. That is, the network device can possess one or more of the following: AI channel estimation, AI equalization, or AI demodulation. For example, AI functions may include one or more of the following: AI channel estimation, AI equalization, or AI demodulation. The AI ​​functions in the embodiments of this application can be replaced with AI models.

[0207] It should also be understood that the same AI function can correspond to one or more AI models, and each of these models can be combined with the functional unit to achieve the corresponding AI function. The accuracy, manufacturer information, or certain parameters of these one or more AI models may differ.

[0208] The following section details the relevant solutions for the first configuration information.

[0209] The first configuration information is used to determine the AI ​​function corresponding to BBL and / or the corresponding AI function to BBH, and the AI ​​function corresponding to BBL is different from the AI ​​function corresponding to BBH. In other words, when the first configuration information is different, the AI ​​function corresponding to BBL and / or the AI ​​function corresponding to BBH are different.

[0210] The format in which the first configuration information is presented is not limited. As an example, the first configuration information includes the identifier corresponding to the configuration information.

[0211] For example, the first configuration information can be used to indicate the AI ​​function corresponding to BBL and / or the AI ​​function corresponding to BBH through one or more fields. The specific form of the first configuration information is not limited here.

[0212] Optionally, the first configuration information belongs to at least one first candidate configuration information. Alternatively, it can be understood that at least one first candidate configuration information includes the first configuration information, or that the first configuration information indicated by the first information is determined from at least one first candidate configuration information.

[0213] For example, a third device can determine the first configuration information from at least one first candidate configuration information. For instance, the third device can determine the first configuration information from at least one first candidate configuration information based on AI functions supported by BBL and / or AI functions supported by BBH; or the third device can determine the first configuration information from at least one first candidate configuration information based on a first condition. The first condition is associated with data transmission performance information and / or AI function information. Optionally, the AI ​​function information includes one or more of the following: AI function performance information, AI function priority information, or vendor information corresponding to the AI ​​function, etc.

[0214] For example, BBL supports AI channel estimation and AI equalization, while BBH does not support AI functions. Therefore, the third device obtains at least one first candidate configuration information from the candidate configuration information shown in Table 3. This at least one candidate configuration information includes configuration information 3-2. At least one candidate configuration information includes one configuration information, meaning that configuration information 3-2 can be used as the first configuration information.

[0215] For another example, the AI ​​function supported by BBL includes AI channel estimation. The third device obtains at least one first candidate configuration information from multiple candidate configuration information in Table 3 based on the AI ​​function supported by BBL. This at least one candidate configuration information may include configuration information 1-0, configuration information 1-1, configuration information 2-1, and configuration information 4-0. The third device can determine the first configuration information from configuration information 1-0, configuration information 1-1, configuration information 2-1, and configuration information 4-0. In cases where at least one first candidate configuration information includes multiple candidate configuration information, the third device can determine one candidate configuration information as the first configuration information from the multiple candidate configuration information based on a certain condition (e.g., a first condition). An explanation of the first condition can be found in the exemplary description in the following assumptions.

[0216] For example, BBL supports AI channel estimation and AI equalization, while BBH supports AI equalization. The third device can select configuration information 2-1, 3-1, 3-2, and 4-0 from multiple candidate configuration information in Table 3 as at least one first candidate configuration information. Where at least one first candidate configuration information includes multiple candidate configurations, the third device can select one configuration information from at least one first candidate configuration information (configuration information 2-1, 3-1, 3-2, and 4-0) as the first configuration information. For example, the third device can determine the first configuration information from at least one first candidate configuration information based on a first condition. Optionally, the first condition can be associated with one or more of the following: bit error rate, throughput, AI channel estimation performance, AI demodulation performance, AI equalization performance, priority of AI functions, or vendor information corresponding to AI functions.

[0217] Wherein, when the first condition is associated with bit error rate or throughput, the third device may determine the first configuration information from at least one first candidate configuration information using one of the following methods:

[0218] Method 1: Online Assessment

[0219] For example, for configuration information 2-1, configuration information 3-1, configuration information 3-2, and configuration information 4-0, the third device can set a running time to run the AI ​​function corresponding to BBL and the AI ​​function corresponding to BBH in configuration information 2-1, configuration information 3-1, configuration information 3-2, and configuration information 4-0 respectively. The third device calculates the bit error rate and / or throughput of data transmission under each candidate configuration information. Based on the statistical results, the third device can select the candidate configuration information whose bit error rate and / or throughput meet a certain threshold or condition as the first configuration information.

[0220] Method 2: Offline Assessment

[0221] For example, for configuration information 2-1, configuration information 3-1, configuration information 3-2 and configuration information 4-0, the third device can query the AI ​​model performance information of each candidate configuration information under a specific configuration. The third device can select the candidate configuration information whose model performance information meets a certain threshold or condition as the first configuration information by comparing the model performance of the same AI model under different candidate configuration information and / or the overall model performance of the AI ​​model corresponding to different candidate configuration information.

[0222] In both Method 1 and Method 2, the thresholds or conditions can be predefined, configured, or indicated. The size of the thresholds and the content of the conditions are not limited in this application.

[0223] For example, the third device obtains at least one first candidate configuration information from Table 3 based on the AI ​​functions supported by BBL and / or BBH. This at least one first candidate configuration information may include configuration information 1-0, configuration information 1-1, configuration information 2-1, configuration information 3-1, configuration information 3-2, configuration information 4-0, and configuration information 4-2. The third device can select one configuration information from configuration information 1-0, configuration information 1-1, configuration information 2-1, configuration information 3-1, configuration information 3-2, configuration information 4-0, and configuration information 4-2 as the first configuration information based on a first condition.

[0224] Wherein, when the first condition is associated with one or more of the AI ​​channel estimation performance, AI demodulation performance, or AI equalization performance, the third device can determine the performance information of each AI function in each of the first candidate configuration information in at least one first candidate configuration information through the above method 1 or method 2, and select the candidate configuration that satisfies the AI ​​performance (one or more of the AI ​​channel estimation performance, AI demodulation performance, or AI equalization performance) supported by the first condition as the first configuration information.

[0225] Wherein, when the first condition is associated with the priority of the AI ​​function, the third device can determine the first configuration information from at least one first candidate configuration information according to the priority of the AI ​​function.

[0226] For example, the priority of AI functions in the first condition can include: the priority corresponding to AI channel estimation (i.e., the priority of AI channel estimation) > the priority corresponding to AI equalization (i.e., the priority of AI equalization) > the priority corresponding to AI demodulation (i.e., the priority of AI demodulation). If at least one first candidate configuration information determined by the third device includes configuration information 3-1 and configuration information 4-2 in Table 3, then the third device can select the configuration information with the higher priority of AI functions from configuration information 3-1 and configuration information 4-2 as the first configuration information; that is, the third device can use configuration information 3-1 as the first configuration information.

[0227] For example, the priority of AI function in the first condition can include: the priority of both BBL and BBH having AI function is greater than the priority of only one of BBL and BBH having AI function. If the third device determines at least one first candidate configuration information including configuration information 1-1, configuration information 2-1 and configuration information 4-0 in Table 3, then the third device can select the configuration information with the higher priority from configuration information 1-1, configuration information 2-1 and configuration information 4-0 as the first configuration information, that is, the third device can use configuration information 2-1 as the first configuration information.

[0228] When the first condition is associated with the manufacturer information of the AI ​​function, the third device can determine the first configuration information from at least one first candidate configuration information based on the manufacturer information corresponding to the AI ​​function.

[0229] For example, in the first condition, the priority of the same manufacturer for the AI ​​function can be higher than the priority of different manufacturers for the AI ​​function. BBL supports AI channel estimation and AI equalization, where the manufacturer corresponding to AI channel estimation and AI equalization supported by BBL is manufacturer #1. BBH supports AI equalization, where the manufacturer corresponding to AI equalization supported by BBH is manufacturer #2. Manufacturer #1 and manufacturer #2 are different manufacturers. Based on the AI ​​functions supported by BBL and BBH, and combined with the candidate configuration information in Table 3, the third device determines at least one first candidate configuration information, including configuration information 1-1, configuration information 2-1, configuration information 3-1, configuration information 3-2, and configuration information 4-0. The third device then selects the configuration information with the same manufacturer for the AI ​​function included in the candidate configuration information from the first condition configuration information 1-1, configuration information 2-1, configuration information 3-1, configuration information 3-2, and configuration information 4-0 as the first configuration information; that is, the third device can use configuration information 3-2 as the first configuration information.

[0230] There is no limitation on how the first configuration information is determined from at least one first candidate configuration information. In one possible implementation, the first configuration information can be determined from at least one second candidate configuration information among at least one first candidate configuration information. In other words, the first configuration information belongs to at least one second candidate configuration information among at least one first candidate configuration information.

[0231] In this configuration, at least one second candidate configuration information corresponds to the first segmentation information. At least one second candidate configuration information belongs to at least one first candidate configuration information. Alternatively, the first segmentation information corresponds to at least one second candidate configuration information among the at least one first candidate configuration information. The first segmentation information is determined based on the transmission bandwidth between BBL and BBH and / or the computing power capability corresponding to BBL. Alternatively, the first segmentation information is associated with the transmission bandwidth between BBL and BBH and / or the computing power capability of BBL.

[0232] For example, the third device can determine the first segmentation information from at least one candidate segmentation information based on the transmission bandwidth between BBL and BBH and / or the computing power corresponding to BBL.

[0233] Combination Figure 4The segmentation information shown corresponds to different segmentation positions. It can be seen that: different segmentation information and different segmentation positions result in different functions for BBL and BBH, different amounts of data transmitted between BBH and BBL, different transmission bandwidths between BBH and BBL, and different computing power for BBL.

[0234] For example, for segmentation information 1, the data transmitted between BBL and BBH may include frequency domain symbol data at the antenna dimension; for segmentation information 2, the data transmitted between BBL and BBH may include frequency domain symbol data and channel data at the antenna dimension; for segmentation information 3, the data transmitted between BBL and BBH may include frequency domain symbol data obtained after channel equalization at the layer dimension; for segmentation information 4, the data transmitted between BBL and BBH may include LLR data at the layer dimension.

[0235] Among them, the transmission bandwidths corresponding to BBL and BBH may be different depending on the segmentation information. The transmission bandwidths corresponding to segmentation information 1 to segmentation information 4 can satisfy the following order: segmentation information 2 > segmentation information 1 > segmentation information 4 > segmentation information 3.

[0236] The computing power of BBL may vary depending on the segmentation information. The computing power of BBL corresponding to segmentation information 1 to segmentation information 4 can satisfy the following order: segmentation information 4 > segmentation information 3 > segmentation information 2 > segmentation information 1.

[0237] For example, BBL supports AI channel estimation and AI equalization, while BBH supports AI equalization. The third device can select configuration information 1-1, 2-1, 3-1, and 3-2 as first candidate configuration information from the candidate configuration information shown in Table 3. The segmentation information corresponding to this first candidate configuration information can include segmentation information 1, segmentation information 2, and segmentation information 3. Assuming that the transmission bandwidth between BBL and BBH can support the transmission of LLR data or frequency domain symbol data at the antenna dimension, the third device can use segmentation information 3 as the first segmentation information. Therefore, at least one second candidate configuration information corresponding to the first segmentation information can include configuration information 3-1 and configuration information 3-2. The third device can select configuration information 3-2 as the first configuration information from configuration information 3-1 and configuration information 3-2 based on a first condition (e.g., the priority of AI functions).

[0238] For another example, BBL supports AI channel estimation and AI equalization, while BBH supports AI equalization. The third device can select configuration information 1-1, 2-1, 3-1, and 3-2 as the first candidate configuration information from the candidate configuration information shown in Table 3. The segmentation information corresponding to this first candidate configuration information can include segmentation information 1, segmentation information 2, and segmentation information 4. Assuming that BBL's computing power can support the computational capability when the segmentation information is segmentation information 4, the candidate segmentation information between BBL and BBH can include segmentation point 1, segmentation information 2, and segmentation information 3. The third device can determine segmentation information 3 as the first segmentation information from the candidate segmentation information. Therefore, at least one second candidate configuration information corresponding to the first segmentation information can include configuration information 3-1 and configuration information 3-2. The third device can select configuration information 3-2 as the first configuration information based on a first condition (e.g., the priority of AI functions).

[0239] In one possible implementation, assuming the third device is the second device (i.e., BBH), the method may further include, prior to step 301:

[0240] BBL sends a second message to BBH. BBH then receives the second message from BBL.

[0241] The second information is used to indicate whether BBL supports AI functions. Where the second information indicates that BBL supports AI functions, it also indicates the AI ​​functions supported by BBL.

[0242] For example, if the second information supports AI functionality in BBL, the second information can also indicate the manufacturer information corresponding to the AI ​​functionality supported by BBL.

[0243] As an example, the second information can indicate whether BBL supports AI functionality through one or more fields. Suppose that the second information indicates whether BBL supports AI functionality through one field (e.g., field #1). When field #1 is "0", it indicates that BBL supports AI functionality; when field #1 is "1", it indicates that BBL does not support AI functionality.

[0244] As an example, when the second information indicates that the BBL supports AI functions, the second information can also use one or more fields to indicate the AI ​​functions supported by the BBL. For example, the second information indicates the AI ​​functions supported by the BBL through two fields (e.g., field #2 and field #3). When the value of field #2 and field #3 is "00", it can indicate that the BBL supports the AI ​​function of AI channel estimation. When the value of field #2 and field #3 is "01", it can indicate that the BBL supports the AI ​​function of AI equalization. Or when the value of field #2 and field #3 is "11", it can indicate that the BBL supports the AI ​​function of AI demodulation.

[0245] As an example, when the second information indicates that BBL supports AI functions, the second information can also use one or more fields to indicate the vendor information corresponding to the AI ​​functions supported by BBL. Assuming the vendor information corresponding to the AI ​​functions can be a vendor identifier or index, one or more fields in the second information are used to indicate the vendor identifier or index corresponding to the AI ​​functions supported by BBL.

[0246] In another possible implementation, assuming the third device is a device other than the second device (i.e., BBH) and the first device (i.e., BBL) (e.g., OAM), the method may further include the following before step 301:

[0247] BBL sends a second message to BBH, which forwards it to OAM. OAM then receives the second message. BBH then sends a third message to OAM, which OAM receives from BBH.

[0248] The second and third information can be carried in the same signaling message or in different signaling messages, and this application does not limit this.

[0249] It should be understood that the second piece of information can be found in the description above.

[0250] The third information is used to indicate whether BBH supports AI functionality. If the third information indicates that BBH supports AI functionality, it can further indicate the specific AI functionality supported by BBH. Alternatively, if the third information indicates that BBH supports AI functionality, then it can be assumed that the third information indicates that BBH supports AI functionality.

[0251] For example, if the third information indicates that BBH supports AI functions, the third information can also indicate the vendor information corresponding to the AI ​​functions supported by BBH.

[0252] It should be understood that the third information is similar to the second information mentioned above. Specific examples of the third information can be obtained by replacing the second information with the third information, such as replacing BBL with BBH, etc., which will not be elaborated here.

[0253] It should be understood that step 301 above can be an internal operation of the third device, that is, in the specific implementation process, step 301 is an optional step.

[0254] 302, the third device sends the first message. Correspondingly, the BBL receives the first message.

[0255] For example, after the third device determines the first information, it sends the first information. Accordingly, the BBL receives the first information. Assuming the third device and the second device are the same device, for example, the third device is BBH, BBH can send the first information to the BBL. Accordingly, the BBL receives the first information from BBH. Assuming the third device is a different device from the first and second devices, for example, the third device is OAM, OAM can send the first information to BBH, and BBH forwards the first information to the BBL.

[0256] For example, after receiving the first information, the BBL determines the data processing method based on the first information. This data can be data sent by the BBL to the BBH. For instance, the data sent by the BBL to the BBH can be frequency domain signal data; or frequency domain signal data and channel data; or frequency domain symbol data after channel equalization; or LLR data.

[0257] The first information is used to indicate the first segmentation information and / or the first configuration information. It should be understood that a detailed description of the first information can be found in the description of step 301 above, and will not be repeated here.

[0258] For example, when the first information is used to indicate the first segmentation information, the BBL can determine the first configuration information corresponding to the first segmentation information based on the correspondence between candidate configuration information and candidate segmentation information (e.g., Table 2 or Table 3 mentioned above); or, when the first information is used to indicate the first configuration information, the BBL can determine the first segmentation information corresponding to the first configuration information based on the correspondence between candidate configuration information and candidate segmentation information (e.g., Table 2 or Table 3 mentioned above). The BBL can determine the AI ​​function corresponding to the BBL based on the first information, and determine the data processing method based on the AI ​​functions it supports.

[0259] The following will provide an exemplary description of a scheme for using the first information to indicate the first segmentation information and / or the first configuration information.

[0260] In one possible implementation, the first information is used to indicate the first segmentation information. The BBL can determine the candidate configuration information corresponding to the first segmentation information based on the correspondence between candidate configuration information and candidate segmentation information (e.g., Table 2 or Table 3 above). The BBL determines the processing method for the transmitted data based on the candidate configuration information corresponding to the first segmentation information.

[0261] For example, the correspondence between candidate configuration information and candidate segmentation information is shown in Table 3. The segmentation information indicated by the first information is segmentation information 2 in Table 3. Therefore, the BBL determines that its corresponding AI function includes AI channel estimation based on candidate configuration 2-1 (the first configuration information) corresponding to segmentation information 2. When the AI ​​function supported by the BBL includes AI channel estimation, the BBL processes the transmitted data using AI channel estimation according to the first configuration information and sends the processed data to the BBH. Where the BBL supports AI channel estimation and the AI ​​channel estimation corresponds to multiple different AI models, the BBL can select one AI model from these multiple AI models to process the transmitted data according to a first rule. The first rule can be predefined, configured, or indicated, and can be related to the accuracy of the AI ​​model or other parameters of the AI ​​model. When the AI ​​function supported by the BBL does not include AI channel estimation, the BBL processes the transmitted data using a non-AI channel estimation functional unit (e.g., a channel estimation unit supported by the BBL itself) according to the first configuration information and sends the processed data to the BBH.

[0262] For example, the correspondence between candidate configuration information and candidate segmentation information is illustrated in Table 3. The segmentation information indicated by the first information is segmentation information 3 in Table 3. Based on candidate configuration information 3-1 and candidate configuration information 3-2 corresponding to segmentation information 3, the BBL can select one candidate configuration information from candidate configuration 3-1 and candidate configuration information 3-2 as the first configuration information, according to the first condition and / or the AI ​​functions supported by the BBL. When the AI ​​functions supported by the BBL include AI channel estimation and AI equalization, the BBL determines one candidate configuration information from candidate configuration 3-1 and candidate configuration information 3-2 as the first configuration information based on the first condition. A detailed description of the first condition can be found in step 301 above. Assuming that the BBH determines configuration information 3-2 as the first condition, the data sent by the BBL to the BBH is data processed by AI channel estimation and AI equalization. When the AI ​​function supported by BBL includes AI equalization but does not include AI channel estimation, then BBL determines candidate configuration information 3-1 as the first configuration information from candidate configuration information 3-1 and candidate configuration information 3-2. The data sent by BBL to BBH is the data after AI equalization processing.

[0263] In one possible implementation, the first information is used to indicate the first configuration information, which in turn indicates the AI ​​function corresponding to BBL and / or the AI ​​function corresponding to BBH, and the AI ​​function corresponding to BBL is different from the AI ​​function corresponding to BBH.

[0264] For example, the first configuration information can be used to indicate the AI ​​function corresponding to the BBL. When the first configuration information is used to indicate the AI ​​function corresponding to the BBL, the BBL can determine the processing method for the transmitted data based on the AI ​​function corresponding to the BBL indicated by the first configuration information and the AI ​​functions supported by the BBL itself.

[0265] For example, if the AI ​​function corresponding to the BBL indicated by the first configuration information is an AI function supported by the BBL, then the BBL will process the transmitted data using the AI ​​function indicated by the first configuration information based on the first information. Specifically, the AI ​​function corresponding to the BBL indicated by the first configuration information may correspond to multiple different AI models on the BBL side. The BBL can select one AI model from these multiple AI models to process the transmitted data according to certain rules (such as the first rule mentioned above).

[0266] For another example, if the AI ​​function corresponding to the BBL indicated by the first configuration information is not an AI function supported by the BBL, then the BBL cannot process the transmitted data according to the AI ​​function indicated by the first configuration information. In this case, the BBL can use a non-AI function unit to process the transmitted data.

[0267] Referring to Table 3 above, assuming the first configuration information indicates that the AI ​​function corresponding to BBL is AI equalization, BBL determines the data processing method based on the AI ​​equalization indicated by the first configuration information and the AI ​​functions it supports. If BBL supports AI equalization, it will use AI equalization to process the transmitted data according to the first configuration information. If the AI ​​equalization supported by BBL corresponds to multiple AI models, BBL can select one AI model from these models according to a rule (e.g., the first rule) to implement AI equalization and process the transmitted data. Alternatively, if BBL does not support AI equalization, it will use a non-AI function equalization unit to process the transmitted data.

[0268] For example, the first configuration information can be used to indicate the AI ​​function corresponding to the BBH. When the first configuration information indicates the AI ​​function corresponding to the BBH, the BBL determines the AI ​​function corresponding to the BBH based on the first configuration information indicated by the first information, and determines the first segmentation information. The BBL determines the functional unit corresponding to the BBL based on the first segmentation information, and determines the AI ​​function corresponding to the BBL based on the AI ​​functions it supports. The BBL can determine the data transmission processing method based on the AI ​​functions it supports.

[0269] For example, there is a correspondence between the first configuration information and the first segmentation information. In other words, knowing either the first configuration information or the first segmentation information allows us to determine the other information. The correspondence between the first configuration information and the first segmentation information can be predefined, configured, or indicated. This correspondence can be represented through language, illustrations, tables, or other forms; the specific form of representation is not limited.

[0270] For example, BBL determines the first segmentation information based on the AI ​​function corresponding to BBH indicated by the first configuration information, and then determines the AI ​​function corresponding to BBL based on this first segmentation information. The AI ​​function corresponding to BBL determined by the first segmentation information is an AI function supported by BBL. BBL activates this AI function and uses it to process the transmitted data. Furthermore, the AI ​​function determined by BBL based on the first segmentation information corresponds to multiple AI models with different levels of precision on the BBL side. BBL can select one AI model from these multiple AI models to process the transmitted data according to a first rule. The first rule is similar to the first rule in the example above and will not be repeated here.

[0271] For another example, the BBL determines the first segmentation information based on the AI ​​function corresponding to the BBH indicated by the first configuration information, and then determines the AI ​​function corresponding to the BBL based on the first segmentation information. If the AI ​​function corresponding to the BBL determined by the first segmentation information is not one of the AI ​​functions supported by the BBL, then the BBL cannot process the transmitted data based on the AI ​​function determined by the first segmentation information. In this case, the BBL can use a non-AI function unit to process the transmitted data.

[0272] Referring to Table 3 above, assuming the first configuration information is used to indicate that the AI ​​function corresponding to BBH is AI channel estimation, then BBL can determine the first configuration information (e.g., configuration information 1-0) and the first segmentation information (e.g., segmentation information 1) based on Table 3. BBL then determines the functional unit corresponding to BBL based on segmentation information 1, i.e., as shown... Figure 4The functional unit corresponding to BBL at the segmentation position corresponding to segmentation information 1 is shown in the figure; BBL determines the AI ​​function corresponding to BBL according to configuration information 1-0, that is, as shown in Table 3, BBL does not include AI channel estimation, AI equalization and AI demodulation.

[0273] For example, the first configuration information can be used to indicate the AI ​​functions corresponding to BBH and BBL. When the first configuration information is used to indicate the AI ​​functions corresponding to BBH and BBL, BBL determines the data transmission processing method based on the AI ​​functions corresponding to BBL indicated by the first configuration information and the AI ​​functions supported by BBL itself.

[0274] For example, if the AI ​​function corresponding to the BBL indicated by the first configuration information is one of the AI ​​functions supported by the BBL, then the BBL will process the transmitted data using the AI ​​function indicated by the first configuration information based on the first information. Specifically, the AI ​​function corresponding to the BBL indicated by the first configuration information may correspond to multiple different AI models on the BBL side. The BBL can select one AI model from these multiple AI models to process the transmitted data based on the AI ​​function corresponding to the BBH and a second rule. The second rule can be predefined, configured, or indicated, and it can be related to the accuracy, manufacturer information, or other information of the AI ​​model.

[0275] For another example, if the AI ​​function corresponding to the BBL indicated by the first configuration information is not an AI function supported by the BBL, then the BBL cannot process the transmitted data according to the AI ​​function indicated by the first configuration information. In this case, the BBL can use a non-AI function unit to process the transmitted data.

[0276] Referring to Table 3 above, assuming the first configuration information indicates that the AI ​​function corresponding to BBH and the AI ​​function corresponding to BBL are AI channel estimation, where the AI ​​function corresponding to BBL is AI channel estimation and the AI ​​function corresponding to BBH is AI equalization, then this first configuration information is configuration information 2-1 in Table 3 above. BBL determines the processing method for transmitted data based on the AI ​​function corresponding to BBL indicated by the first configuration information and the AI ​​functions it supports. When the AI ​​function supported by BBL includes AI channel estimation, BBL processes the transmitted data corresponding to AI channel estimation. If the AI ​​function supported by BBL includes AI channel estimation, and there are multiple AI models corresponding to this AI channel estimation, BBL can select an AI model based on a certain rule (e.g., the second rule mentioned above) to implement AI channel estimation and process the transmitted data.

[0277] In one possible implementation, the first information is used to indicate first segmentation information and first configuration information. The BBL can determine the functional units corresponding to the BBL and BBH, as well as the AI ​​function corresponding to the BBL and / or the AI ​​function corresponding to the BBH, based on the first segmentation information. The BBL can determine the processing method for the transmitted data based on the first configuration information.

[0278] It should be understood that, for a specific example of how the first information is used to indicate the first segmentation information and the first configuration information, please refer to the example above where the first information is used to indicate the first configuration information, and BBL determines the processing method of the transmitted data, which will not be repeated here.

[0279] 303, BBL sends the first data to BBH based on the first information.

[0280] For example, after receiving the first information, BBL sends the first data to BBH based on the first information. Correspondingly, BBH receives the first data from BBL. This first data is the data processed by BBL based on the first configuration information, in the case of the first segmentation information. For details on how BBL determines the first segmentation information and / or the first configuration information based on the first information, please refer to the description in step 302 above.

[0281] For example, the first data may include the output of the AI ​​function corresponding to BBL, and the precision of the AI ​​function output. The precision of the AI ​​function output can be used to determine the number of bytes or bits occupied by the AI ​​function output in the first data.

[0282] As an example, the first data satisfies one or more of the following: When the AI ​​function corresponding to the first device includes AI channel estimation, the first data includes channel data and a first precision, where the channel data represents the output data of the AI ​​channel estimation corresponding to the first device, and the first precision indicates the precision of the output result of the AI ​​channel estimation corresponding to the first device; when the AI ​​function corresponding to the first device includes AI equalization, the first data includes symbol data and a second precision, where the symbol data represents the output data of the AI ​​equalization corresponding to the first device, and the second precision indicates the precision of the output result of the AI ​​equalization corresponding to the first device; or, when the AI ​​function corresponding to the first device includes AI demodulation, the first data includes log-likelihood ratio (LLR) data and a third precision, where the LLR data represents the output data of the AI ​​demodulation corresponding to the first device, and the third precision indicates the precision of the output result of the AI ​​demodulation corresponding to the first device.

[0283] Here, channel data represents the output data of AI channel estimation corresponding to the first device. It can be understood that channel data can be used to embody (or reflect) the output data of AI channel estimation corresponding to the first device. For example, the channel data can be the output data of AI channel estimation corresponding to the first device, or the channel data can be used to represent the characteristics of the output data of AI channel estimation corresponding to the first device (such as one or more of the following: bandwidth, number of symbols, or frequency selectivity of the channel data).

[0284] Here, symbolic data represents the output data of the AI ​​equalization corresponding to the first device. It can be understood that symbolic data can be used to represent (or reflect) the output data of the AI ​​equalization corresponding to the first device. For example, symbolic data can be the output data of the AI ​​equalization corresponding to the first device, or the symbolic data can be used to represent the characteristics of the output data of the AI ​​equalization corresponding to the first device (e.g., one or more of the signal-to-noise ratio, amplitude gain, etc. corresponding to the symbolic data).

[0285] In this context, LLR data represents the output data of the AI ​​demodulation corresponding to the first device. It can be understood that LLR data can be used to represent (or reflect) the output data of the AI ​​demodulation corresponding to the first device. For example, LLR data can be the output data of the AI ​​demodulation corresponding to the first device, or it can be used to represent the characteristics of the output data of the AI ​​demodulation corresponding to the first device (e.g., the mapping relationship between LLR data and bits). The following example illustrates the transmission format of the first data, using channel data as the output data of AI channel estimation, symbol data as the output data of AI equalization, and LLR data as the output data of AI demodulation:

[0286] For example, assuming the first segmentation information is segmentation information 2, the AI ​​function corresponding to BBL in the first configuration information includes AI channel estimation, and BBL supports AI channel estimation. The first data sent by BBL to BBH includes the output data of the AI ​​channel estimation supported by BBL and the precision of the AI ​​channel estimation output result (or the first precision), where the first precision can be used to indicate the number of bytes or bits occupied by the AI ​​channel estimation output data in the first data. The specific format of the first data is as follows: Figure 5 As shown in (1), the first data includes frequency domain symbol data, channel data, and a first precision. The frequency domain symbol data is as follows: Figure 5 The in-phase and quadrature (IQ) frequency domain data shown in (1) is channel data processed by AI channel estimation. The first precision can be used to indicate the number of bytes occupied by the channel data in the first data. Among them, "i Sample(1 st"RE in PRE)" can represent the sampled value of the in-phase component on the first resource element; "qSample(1 st "RE in PRE)" can represent the sampled value of the orthogonal component on the first resource element; ... "i Sample(12 st "REin PRE)" can represent the sampled value of the in-phase component on the twelfth resource element; "q Sample(12)" can represent the sampled value of the in-phase component on the twelfth resource element. st "RE in PRE)" can represent the sampled value of the orthogonal component on the twelfth resource element. Among them, "Channel est i Sample(1)" represents the sampled value of the orthogonal component on the twelfth resource element. st "REin PRE)" can represent the channel estimate of the in-phase component on the first resource element; "Channel est qSample(1 st "RE in PRE)" can represent the channel estimate of the orthogonal component on the first resource element; ... "Channel est i Sample(12)" st "RE in PRE)" can represent the channel estimate of the in-phase component on the twelfth resource element; "Channel est q Sample(12)" st "RE in PRE" can represent the channel estimate of the orthogonal component on the twelfth resource element.

[0287] For example, assuming the first segmentation information is segmentation information 4, the AI ​​function corresponding to BBL in the first configuration information includes AI demodulation, and BBL supports AI demodulation. The first data sent by BBL to BBH includes the output data of the AI ​​demodulation supported by BBL and the precision (or third precision) of the AI ​​channel estimation output result, where the third precision can be used to indicate the number of bytes or bits occupied by the output result in the first data during AI demodulation. The specific format of the first data is as follows: Figure 5 As shown in (2), the first data includes LLR data and a third precision. The LLR data is the data after AI demodulation processing, and the third precision can be used to indicate the number of bytes occupied by the LLR data in the first data. Optionally, the first data may also include the modulation order corresponding to AI demodulation, for example... Figure 5 The Mod order shown in (2) is as follows. Among them, "LLR sample(bit 1 of 1" is a mod order that is not explicitly defined in the original text. st "RE inPRE" means targeting the first resource element (e.g., 1). st The LLR sample value of the first bit (e.g., bit 1) on the RE); "LLR sample (bit 2 of 1) st"RE in PRE" indicates that the first resource element (e.g., 1) is being targeted. st The LLR sample value of the second bit (e.g., bit 2) on RE); ... "LLR sample (bit 1 of 12 st "RE in PRE" indicates that the twelfth resource element (e.g., 12) is being targeted. st The LLR sample value of the first bit (e.g., bit 1) on RE); "LLR sample (bit mof 12)" st "RE in PRE" indicates that the twelfth resource element (e.g., 12) is being targeted. st The LLR sample value of the m-th bit (e.g., bitm) on RE).

[0288] For example, BBL sends the first data, and correspondingly, BBH receives the first data from BBL. BBH determines the corresponding functional unit and AI function based on the first segmentation information and / or the first configuration information, and processes the received first data.

[0289] For example, the first segmentation information indicates segmentation information 2, the first configuration information indicates that the AI ​​function corresponding to BBL is AI channel estimation, and the AI ​​function corresponding to BBH is AI equalization. BBL supports AI channel estimation, BBH supports AI equalization, and the segmentation positions corresponding to BBL and BBH are as follows: Figure 4 The segmentation information 2 corresponds to the segmentation position. BBL sends the first data to BBH, which includes the output result of AI channel estimation and the accuracy of AI channel estimation output. After receiving the first data, BBH uses the received first data as the input of AI equalization. The first data is input into the AI ​​equalization and processed to obtain the AI ​​equalized first data. Further, the AI ​​equalized first data can be processed sequentially by the functional units of BBH, including the descrambling unit, derate matching unit, decoding unit, and CRC check unit, to obtain the output bitstream.

[0290] The above text combined Figures 1 to 5 The communication method embodiments of this application are described in detail below, and will be combined with... Figure 6 and Figure 8 This application describes in detail the communication device-side embodiments. It should be understood that the descriptions of the device embodiments correspond to the descriptions of the method embodiments; therefore, any parts not described in detail can be found in the preceding method embodiments.

[0291] Figure 6 This is a schematic block diagram of the communication device 1000 provided in an embodiment of this application. Figure 6As shown, the communication device 1000 includes a processing module 1010 and a communication module 1020. The communication device 1000 can be a transmitting device (e.g., the one described above). Figure 3 The first device in the process (i.e., BBL) can also be a communication device applied to or used in conjunction with a transmitting device to implement a method executed by the transmitting device, such as a chip, chip system, or circuit; or, the communication device 1000 can be a receiving device (e.g., the one described above). Figure 3 The second device in the context (i.e., BBH) can also be a communication device applied to or used in conjunction with the receiving device to enable the methods executed by the receiving device, such as a chip, chip system, or circuit.

[0292] The communication module can also be called a transceiver module, transceiver, transceiver unit, or transceiver device. The processing module can also be called a processor, processing board, processing unit, or processing device. Optionally, the communication module is used to execute the sending and receiving operations of the sending and receiving devices in the above method. The device in the communication module that implements the receiving function can be considered a receiving unit, and the device in the communication module that implements the sending function can be considered a sending unit; that is, the communication module includes a receiving unit and a sending unit.

[0293] Optionally, the communication device 1000 may further include a storage module 1030 for storing device program code and / or data.

[0294] In one example, when the communication device 1000 is applied to the first device, the processing module 1010 can be used to implement the first device in the above embodiments (e.g., Figure 3 The BBL (Browser-Based Booth) processing function in the above embodiment is used to implement the transmit and receive functions of the first device.

[0295] In another example, when the communication device 1000 is applied to the second device, the processing module 1010 can be used to implement the second device in the above embodiments (e.g., Figure 3 The BBH processing function in the above embodiment is used to implement the transmit and receive function of the second device.

[0296] In another example, when the communication device 1000 is applied to a third device, the processing module 1010 can be used to implement the third device in the above embodiments (e.g., Figure 3 The communication module 1020 can be used to implement the transmit and receive functions of the third device in the above embodiments, and can also be used to implement the transmit and receive functions of the third device in the above embodiments.

[0297] Furthermore, it should be noted that the aforementioned communication module and / or processing module can be implemented through virtual modules. For example, the processing module can be implemented through software functional units or virtual devices, and the communication module can be implemented through software functions or virtual devices. Alternatively, the processing module or communication module can also be implemented through physical devices, such as chips / circuits (e.g., integrated circuits or logic circuits). The communication module can be an input / output circuit and / or a communication interface, performing input operations (corresponding to the aforementioned receiving operation) and output operations (corresponding to the aforementioned sending operation); the processing module is an integrated processor, microprocessor, or circuit (e.g., integrated circuits or logic circuits).

[0298] The module division in this application is illustrative and represents only one logical functional division. In actual implementation, other division methods are possible. Furthermore, the functional modules in the various examples of this application can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0299] In one example, the functional unit in any of the above devices may be one or more integrated circuits configured to implement the above methods, such as: one or more application-specific integrated circuits (ASICs), or one or more central processing units (CPUs), one or more microcontroller units (MCUs), one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0300] In one example, storage module 1030 may include random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory and / or registers, etc.

[0301] Figure 7 This is a schematic block diagram of a communication device 2000 provided in an embodiment of this application. Optionally, the communication device 2000 may be a chip or a chip system. Optionally, in this application, the chip system may be composed of chips or may include chips and other discrete devices.

[0302] like Figure 7As shown, the communication device 2000 can be used to implement the functions of any device (e.g., terminal device, network device) in the communication system described in the foregoing examples. The communication device 2000 may include at least one processor 2010. Optionally, the processor 2010 is coupled to a memory, which may be located within the device, integrated with the processor, or located outside the device. For example, the communication device 2000 may also include at least one memory 2020. The memory 2020 stores the computer programs, computer programs or instructions, and / or data necessary for implementing any of the above examples; the processor 2010 may execute the computer programs stored in the memory 2020 to complete the methods in any of the above examples.

[0303] The communication device 2000 may also include a communication interface 2030, through which the communication device 2000 can interact with other devices. Exemplarily, the communication interface 2030 may be a transceiver, circuit, bus, module, pin, or other type of communication interface. When the communication device 2000 is a chip-based device or circuit, the communication interface 2030 in the device 2000 may also be an input / output circuit, capable of inputting information (or receiving information) and outputting information (or sending information). The processor 2010 may be an integrated processor, microprocessor, integrated circuit, or logic circuit, etc., and the processor can determine the output information based on the input information.

[0304] In one example, when the communication device 2000 is applied to the first device (e.g., BBL), the processor 2010 can be used to implement the processing function of the first device in the above embodiments, and the communication interface 2030 can be used to implement the sending and receiving function of the first device in the above embodiments.

[0305] In another example, when the communication device 2000 is applied to the second device (e.g., BBH), the processor 2010 can be used to implement the processing function of the second device in the above embodiments, and the communication interface 2030 can be used to implement the sending and receiving function of the second device in the above embodiments.

[0306] In another example, when the communication device 2000 is applied to a third device (e.g., BBH or OAM), the processor 2010 can be used to implement the processing function of the third device in the above embodiments, and the communication interface 2030 can be used to implement the sending and receiving function of the third device in the above embodiments.

[0307] The coupling in this application refers to indirect coupling or communication connection between devices, units, or modules, which can be electrical, mechanical, or other forms, used for information exchange between devices, units, or modules. The processor 2010 may operate in conjunction with the memory 2020 and the communication interface 2030. This application does not limit the specific connection medium between the processor 2010, the memory 2020, and the communication interface 2030.

[0308] Optionally, such as Figure 7 As shown, the processor 2010, the memory 2020, and the communication interface 2030 are interconnected via a bus 2040. Optionally, the bus may include buses of the types such as address bus, data bus, and control bus. Furthermore, for ease of illustration, Figure 7 The diagram shows a bus 2040, but does not imply that there is only one bus or one type of bus.

[0309] It should be understood that the processor mentioned in the embodiments of this application can be one of the following devices or a portion of the circuitry used for processing functions: a central processing unit (CPU), a processor for AI, or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or any combination thereof. A general-purpose processor can be a microprocessor or any conventional processor.

[0310] For example, the processor used for AI can be one or more of the following: graphics processing unit (GPU), neural processing unit (NPU), tensor processing unit (TPU), and data processing unit (DPU).

[0311] For example, one possible implementation of a processor for AI could be... Figure 8 The AI ​​processor 2100 shown can be understood to be used in many other possible ways, which are not limited in this application. Figure 8 This is a schematic diagram of the structure of the AI ​​processor provided in the embodiments of this application.

[0312] like Figure 8 As shown, the AI ​​processor 2100 may include one or more of the following: an AI core, a digital vision pre-processing (DVPP) module, a task scheduler (TS), an L3 cache, an AI CPU, a control CPU, an L2 cache, a universal serial bus (USB) interface, a network interface card (NIC), a peripheral component interconnect express (PCIe) interface (PCIe is a high-speed serial computer expansion bus standard), a double data rate (DDR) / high bandwidth memory (HBM) interface, a general purpose input / output (GPIO) / inter-integrated circuit (I2C) bus, etc. It is understood that the specific meanings of these terms are well known to those skilled in the art and will not be elaborated upon here.

[0313] It should also be understood that the memory mentioned in the embodiments of this application can be volatile memory and / or non-volatile memory. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM). For example, RAM can be used as an external cache. By way of example and not limitation, RAM includes the following forms: static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous linked dynamic random access memory (SLDRAM), and direct rambus RAM (DR RAM).

[0314] It should be noted that when the processor is a general-purpose processor, DSP, ASIC, FPGA, or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, the memory (storage module) can be integrated into the processor.

[0315] It should also be noted that the memory described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0316] This application also provides a computer-readable storage medium storing computer instructions for implementing the methods executed by a communication device (e.g., a first device and / or a second device) in the above-described method embodiments.

[0317] This application also provides a computer program product comprising instructions which, when executed by a computer, implement the methods performed by a communication device (e.g., a first device and / or a second device) in the above-described method embodiments.

[0318] This application also provides a communication system, which includes the first device and / or the second device described in the above embodiments.

[0319] Optionally, the communication system may further include the first device and / or the second device described in the above embodiments.

[0320] The explanations and beneficial effects of the relevant contents in any of the devices provided above can be found in the corresponding method embodiments provided above, and will not be repeated here.

[0321] In the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0322] This application will present various aspects, embodiments, or features relating to systems that may include multiple devices, components, modules, etc. It should be understood and appreciated that individual systems may include additional devices, components, modules, etc., and / or may not include all the devices, components, modules, etc. discussed in conjunction with the accompanying drawings. Furthermore, combinations of these approaches are also possible.

[0323] In this application, examples may reference each other without logical contradiction. For example, methods and / or terms between method embodiments may reference each other, functions and / or terms between device embodiments may reference each other, and functions and / or terms between device examples and method examples may reference each other.

[0324] It should be understood that the above embodiments are mainly illustrated using devices in existing network architectures as examples, and the specific form of the devices is not limited in the embodiments of this application. For example, any device that can achieve the same function in the future is applicable to the embodiments of this application.

[0325] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0326] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be described again here.

[0327] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0328] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0329] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0330] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to existing solutions, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, external hard drives, ROM, RAM, magnetic disks, or optical disks.

[0331] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A communication method, characterized in that, The network device includes a first device and a second device, the method is applied to the first device or to a chip in the first device, the method includes: The system receives first information, which is used to indicate first segmentation information and / or first configuration information. The first segmentation information is used to determine the function corresponding to the first device and the function corresponding to the second device. The first configuration information is used to indicate the artificial intelligence (AI) function corresponding to the first device and / or the AI ​​function corresponding to the second device. The AI ​​function corresponding to the first device is different from the AI ​​function corresponding to the second device. The AI ​​function includes one or more of the following: AI channel estimation, AI equalization, or AI demodulation.

2. The method according to claim 1, characterized in that, The first configuration information belongs to at least one first candidate configuration information. One or more first candidate configuration information corresponds to one candidate segmentation information in at least one candidate segmentation information. Each first candidate configuration information in the at least one first candidate configuration information includes the AI ​​function corresponding to the first device and / or the AI ​​function corresponding to the second device. The at least one candidate segmentation information includes the first segmentation information, and the first segmentation information corresponds to the first configuration information.

3. The method according to claim 2, characterized in that, The first configuration information is the configuration information that satisfies the first condition among the at least one first candidate configuration information, and the first condition is associated with the performance information of data transmission and / or the information of AI function.

4. The method according to claim 1 or 2, characterized in that, The first segmentation information is associated with the transmission bandwidth between the first device and the second device and / or the computing power corresponding to the first device. The first segmentation information corresponds to at least one second candidate configuration information in at least one first candidate configuration information, and the at least one second candidate configuration information includes the first configuration information.

5. The method according to claim 4, characterized in that, When the at least one second candidate configuration information includes multiple second candidate configuration information, The first configuration information is the configuration information that satisfies the first condition among the at least one second candidate configuration information, and the first condition is associated with the performance information of data transmission and / or the information of AI function.

6. The method according to any one of claims 1 to 5, characterized in that, The AI ​​functions supported by the first device overlap with those supported by the second device.

7. The method according to any one of claims 3 to 6, characterized in that, The first condition is associated with at least one of the following: Bit error rate, throughput, AI channel estimation performance, AI demodulation performance, AI equalization performance, priority of AI functions, or vendor information corresponding to AI functions.

8. The method according to any one of claims 1 to 7, characterized in that, Before receiving the first information, the method further includes: Send a second message, which indicates whether the first device supports AI functionality. Wherein, if the second information indicates the AI ​​functions supported by the first device, the second information also indicates the AI ​​functions supported by the first device.

9. The method according to claim 8, characterized in that, In cases where the second information indicates the AI ​​functions supported by the first device, the second information also indicates the manufacturer information corresponding to the AI ​​functions supported by the first device.

10. The method according to any one of claims 1 to 9, characterized in that, The method further includes; Based on the first information, first data is sent to the second device. The first data is data processed by the first device based on the first configuration information under the first segmentation information.

11. The method according to claim 10, characterized in that, The first data includes the output result of the AI ​​function corresponding to the first device and the accuracy corresponding to the output result of the AI ​​function corresponding to the first device.

12. The method according to claim 11, characterized in that, The first data satisfies one or more of the following: When the AI ​​function corresponding to the first device includes AI channel estimation, the first data includes channel data and a first precision. The channel data represents the output data of the AI ​​channel estimation corresponding to the first device, and the first precision is used to indicate the precision of the output of the AI ​​channel estimation result corresponding to the first device. When the AI ​​function corresponding to the first device includes AI equalization, the first data includes symbolic data and a second precision. The symbolic data represents the output data of the AI ​​equalization corresponding to the first device, and the second precision indicates the precision of the AI ​​equalization output result corresponding to the first device; or... When the AI ​​function corresponding to the first device includes AI demodulation, the first data includes log-likelihood ratio (LLR) data and third precision. The LLR data represents the output data of the AI ​​demodulation corresponding to the first device, and the third precision is used to indicate the precision of the AI ​​demodulation output result corresponding to the first device.

13. The method according to any one of claims 1 to 12, characterized in that, The first segmentation information includes any one of the following: segmentation information 1, segmentation information 2, segmentation information 3, or segmentation information 4. Segmentation information 1 corresponds to: The second device includes a channel estimation unit, an equalization unit, and a demodulation unit; Segmentation information 2 corresponds to: the first device includes a channel estimation unit, and the second device includes an equalization unit and a demodulation unit; Segmentation information 3 corresponds to: the first device includes a channel estimation unit and an equalization unit, and the second device includes a demodulation unit; Segmentation information 4 corresponds to: The first device includes a channel estimation unit, an equalization unit, and a demodulation unit.

14. A communication method, characterized in that, The network device includes a first device and a second device, the method is applied to the second device or used in a chip in the second device, the method includes: First information is determined, which is used to indicate first segmentation information and / or first configuration information. The first segmentation information is used to determine the function corresponding to the first device and the function corresponding to the second device. The first configuration information is used to indicate the artificial intelligence (AI) function corresponding to the first device and / or the AI ​​function corresponding to the second device. The AI ​​function corresponding to the first device is different from the AI ​​function corresponding to the second device. The AI ​​function includes one or more of the following: AI channel estimation, AI equalization, or AI demodulation. Send the first message.

15. The method according to claim 14, characterized in that, The determination of the first information includes: Based on the second information, the first information is determined, wherein the second information is used to indicate whether the first device supports AI functions. Wherein, if the second information indicates that the first device supports AI functions, the second information also indicates the AI ​​functions supported by the first device.

16. The method according to claim 15, characterized in that, In cases where the second information indicates the AI ​​functions supported by the first device, the second information also indicates the manufacturer information corresponding to the AI ​​functions supported by the first device.

17. The method according to any one of claims 14 to 16, characterized in that, The method further includes: Receive first data, which is associated with first configuration information.

18. A communication device, characterized in that, Includes modules for implementing the method as described in any one of claims 1 to 17.

19. A communication device, characterized in that, Includes a processor for executing a computer program or instructions in memory to cause the method as described in any one of claims 1 to 17 to be performed.

Images