Communication method, communication device, medium, and program product

By aligning data compression capabilities between O-RU and O-DU in 5G base stations and employing AI and block compression, the inefficiency of data compression configuration on the fronthaul interface is resolved, thereby improving communication performance and efficiency.

WO2026237637A1PCT designated stage Publication Date: 2026-11-19HUAWEI TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
PCT/CN2026/090814
Authority / Receiving Office
WO · WO
Patent Type
Applications
Current Assignee / Owner
Priority Date
2025-05-15
Filing Date
2026-04-15
Publication Date
2026-11-19

AI Technical Summary

Technical Problem

The lack of an effective data compression model configuration specification on the fronthaul interface between the O-RU and O-DU of 5G base stations results in high data transmission bandwidth requirements and low configuration efficiency.

Method used

The first device receives data compression capability information from the second device, determines a suitable compression method, and sends configuration information to align the capabilities of both devices. It then optimizes the data compression configuration by employing artificial intelligence (AI) compression and block compression methods.

Benefits of technology

It improves the suitability and accuracy of data compression configuration, reduces the possibility of reconfiguration, and enhances communication performance and efficiency.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN2026090814_19112026_PF_FP_ABST
    Figure CN2026090814_19112026_PF_FP_ABST
Patent Text Reader

Abstract

Embodiments of the present invention provide a communication method, a communication device, a computer-readable storage medium, and a computer program product. In the communication method, a first device receives, from a second device, capability information of the second device for data compression. On the basis of the capability information of the second device, the first device determines a data compression mode used by the second device, and sends a configuration for the data compression. The configuration is configuration information required by execution of the compression mode. In this way, the capabilities of the first device and the second device can be aligned, and the configuration can be standardized, thereby improving communication performance.
Need to check novelty before this filing date? Find Prior Art

Description

A communication method, communication device, medium, and program product

[0001] This application claims priority to Chinese Patent Application No. 202510633287X, filed on May 15, 2025, entitled "A Communication Method, Communication Device, Medium and Program Product", the entire contents of which are incorporated herein by reference. Technical Field

[0002] This disclosure generally relates to the field of communications, and more specifically to a communication method, communication apparatus, computer-readable storage medium, and computer program product. Background Technology

[0003] Fourth-generation (4G) base stations (eNodeBs) employ a bottom-layer segmentation approach, dividing the base station into two parts: a Baseband Unit (BBU) and a Remote Radio Unit (RRU). The BBU connects to one or more RRUs via fiber optic cables, metallic cabling, or microwave links. The BBU primarily handles centralized upper-layer processing of baseband signals, while the RRU primarily handles baseband signal reception and transmission, as well as radio frequency signal modulation / demodulation, data processing, and power amplification. The RRU, being closer to the antenna, experiences lower feeder loss and can also be called a Radio Unit (RU). This approach allows for highly centralized baseband signal processing by the BBU, enabling centralized deployment of computing resources, resulting in high resource utilization and low deployment costs. However, this bottom-layer segmentation places high demands on the fronthaul link bandwidth between the BBU and RRU, leading to high fiber optic deployment costs.

[0004] Therefore, to reduce the pressure on fronthaul link bandwidth and deployment costs caused by the underlying segmentation method, fifth-generation (5G) base stations (gNodeB, gNB) adopt an upper-layer segmentation approach, splitting the base station into two functional entities: a Central Unit (CU) and a Distributed Unit (DU). The midhaul link between the CU and DU has lower network bandwidth requirements. In the Open Radio Access Network (RAN), the DU can be further subdivided into an Open Distributed Unit (O-DU) and an Open Radio Unit (O-RU). For data transmission on the fronthaul interface between the O-RU and O-DU, the fronthaul data is typically compressed to reduce fronthaul bandwidth. However, some issues remain to be resolved regarding how to configure the data compression model used to compress fronthaul data. Summary of the Invention

[0005] Embodiments of this application provide a communication method, a communication device, and a computer-readable storage medium.

[0006] In a first aspect of this application, a communication method is provided. The method includes: receiving data compression capability information of a second device; determining a data compression method to be used by the second device based on the capability information of the second device; and sending configuration information for data compression, specifying the configuration required to execute the compression method. In this manner, a first device can configure data compression for the second device according to its capabilities. Therefore, this method improves the suitability and accuracy of the data compression configuration, thus reducing the likelihood of reconfiguration, improving the efficiency of data compression configuration, and ultimately improving communication performance.

[0007] In some embodiments, the aforementioned capability information may further include: the computing power of the second device or the compression methods supported by the second device. Thus, the capabilities of the second device and the first device can be aligned. For example, the data compression configuration can be determined based on the computing power of the second device, the supported compression methods, etc., improving the suitability and accuracy of the data compression configuration in terms of computing power and compression methods, and improving the efficiency of the data compression configuration.

[0008] In some embodiments, the compression method may further include: artificial intelligence (AI) compression, block compression, or both. Thus, the second device can obtain an appropriate compression method from the first device. For example, various different compression methods can be used to compress the data of the second device depending on the specific circumstances of the second device, thereby improving the efficiency of the compression model.

[0009] In some embodiments, the configuration may further include: the dimension of AI compression, the number of blocks in block compression, the number of indicator bits for the scaling factor of block compression, the number of indicator bits for the index parameter of block compression, the number of bits of compressed data in block compression, the transform domain of the data, or any combination thereof. Thus, the content of the inference configuration for data compression can be standardized, improving the efficiency of the inference configuration.

[0010] In some embodiments, the method further includes: sending first request information regarding the capability information of the second device, wherein the capability information is in response to the first request information. This initially aligns the capabilities of the second device and the first device, which improves the suitability and accuracy of the data compression configuration, thus reducing the likelihood of reconfiguration and improving the efficiency of the data compression configuration.

[0011] In some embodiments, the method further includes: sending second request information for AI compression condition information for the second device, and receiving AI compression condition information. Thus, the first device can obtain the applicable conditions of the second device, which helps improve the suitability and accuracy of the data compression configuration, thereby reducing the possibility of reconfiguration and improving the efficiency of data compression configuration.

[0012] In some embodiments, the condition information may include: radio frequency parameters or identifiers of the second device suitable for AI compression; temperature or identifiers of the second device suitable for AI compression; power consumption or identifiers of the second device suitable for AI compression; antenna array configuration or identifiers of the second device suitable for AI compression; time synchronization information or identifiers of time synchronization information suitable for AI compression; signal characteristics of external noise suitable for AI compression or identifiers of the signal characteristics of external noise; or any combination of the foregoing. Thus, aligning the applicable conditions of the model between the second and first devices improves the suitability and accuracy of the data compression configuration, thereby reducing the likelihood of reconfiguration and improving the efficiency of the data compression configuration.

[0013] In some embodiments, the second request information can be sent together with the first request information. This reduces signaling overhead.

[0014] In some embodiments, condition information and capability information can be received together, thereby reducing signaling overhead.

[0015] In some embodiments, the method further includes receiving a response message for the configuration, the response message indicating whether the configuration can be used by the second device. Thus, the second device can provide feedback to the first device regarding the usage of the configuration, thereby improving the accuracy of the model configuration.

[0016] In some embodiments, the response message indicates that the configuration cannot be used on the second device, and the response message may also include a reason why the configuration cannot be used on the second device, such as a mismatch between the conditions indicated by the condition information and the configuration. Thus, the first device can obtain information about the usage of the configuration and can further adjust the model to improve its accuracy.

[0017] In some embodiments, the method further includes: updating the configuration for data compression based on the response message, and sending the updated configuration. Thus, the model can be further tuned to improve model performance.

[0018] In some embodiments, the method further includes receiving a response message for the updated configuration, the response message indicating whether the updated configuration can be used in the second device. Thus, the model can be further tuned to improve model performance.

[0019] In some embodiments, the second device may include an Open Radio Unit (O-RU), and the second device and the first device may form a Distributed Unit (DU); and the first device may include an Open Distributed Unit (O-DU). Thus, the method for distributing AI compressed bilateral model inference configurations for the fronthaul interface is standardized.

[0020] In a second aspect of this application, a communication method is provided. The method includes: transmitting capability information for data compression of a second device, and receiving configuration information for data compression, including configuration information required to perform a compression mode. In this manner, the second device can obtain a data compression configuration based on its capabilities. Therefore, this method improves the suitability and accuracy of the data compression configuration, thereby reducing the likelihood of reconfiguration, improving the efficiency of data compression configuration, and ultimately improving communication performance.

[0021] In some embodiments, the aforementioned capability information may further include: the computing power of the second device or the compression methods supported by the second device. Thus, the capabilities of the second device and the first device can be aligned. For example, the data compression configuration can be determined based on the computing power of the second device, the supported compression methods, etc., improving the suitability and accuracy of the data compression configuration in terms of computing power and compression methods, and improving the efficiency of the data compression configuration.

[0022] In some embodiments, the compression method may further include: artificial intelligence (AI) compression, block compression, or both. Thus, the second device can obtain an appropriate compression method from the first device. For example, various different compression methods can be used to compress the data of the second device depending on the specific circumstances of the second device, thereby improving the efficiency of the compression model.

[0023] In some embodiments, the configuration may further include: the dimension of AI compression, the number of blocks in block compression, the number of indicator bits for the scaling factor of block compression, the number of indicator bits for the index parameter of block compression, the number of bits of compressed data in block compression, the transform domain of the data, or any combination thereof. Thus, the content of the inference configuration for data compression can be standardized, improving the efficiency of the inference configuration.

[0024] In some embodiments, the method further includes: receiving first request information for capability information of the second device, wherein the capability information is sent in response to the first request information. This initially aligns the capabilities of the second device and the first device, which improves the suitability and accuracy of the data compression configuration, thus reducing the likelihood of reconfiguration and improving the efficiency of the data compression configuration.

[0025] In some embodiments, the method further includes: receiving second request information for AI compression condition information for the second device, and sending the AI ​​compression condition information if the second device is capable of performing AI compression. Thus, the first device can obtain the applicable conditions of the second device, which helps improve the suitability and accuracy of the data compression configuration, thereby reducing the possibility of reconfiguration and improving the efficiency of the data compression configuration.

[0026] In some embodiments, the condition information may include: radio frequency parameters or identifiers of the second device suitable for AI compression; temperature or identifiers of the second device suitable for AI compression; power consumption or identifiers of the second device suitable for AI compression; antenna array configuration or identifiers of the second device suitable for AI compression; time synchronization information or identifiers of time synchronization information suitable for AI compression; signal characteristics of external noise suitable for AI compression or identifiers of the signal characteristics of external noise; or any combination of the foregoing. Thus, aligning the applicable conditions of the model between the second and first devices improves the suitability and accuracy of the data compression configuration, thereby reducing the likelihood of reconfiguration and improving the efficiency of the data compression configuration.

[0027] In some embodiments, the second request information can be received together with the first request information. This reduces signaling overhead.

[0028] In some embodiments, AI-compressed condition information and capability information can be sent together, thereby reducing signaling overhead.

[0029] In some embodiments, the method further includes: determining whether the configuration can be used for a second device; and sending a response message for the configuration, the response message indicating whether the configuration can be used for the second device. Thus, the second device can provide feedback to the first device regarding the usage of the configuration, thereby improving the accuracy of the model configuration.

[0030] In some embodiments, the method further includes: receiving an updated configuration, determining whether the updated configuration can be used in the second device, and sending a response message for the updated configuration, the response message indicating whether the updated configuration can be used in the second device. Thus, the model can be further tuned to improve model performance.

[0031] In some embodiments, the second device may include an Open Radio Unit (O-RU), and the second device and the first device may form a Distributed Unit (DU), and the first device may include an Open Distributed Unit (O-DU). Thus, the method for distributing AI compressed bilateral model inference configurations for the fronthaul interface is standardized.

[0032] In a third aspect of this application, a communication device is provided. The communication device includes a processor and a memory storing instructions. When executed by the processor, the instructions cause the communication device to perform any method according to any one of the first to second aspects and their implementations.

[0033] In a fourth aspect of this application, a computer-readable storage medium is provided. The computer-readable storage medium stores instructions that, when executed by an electronic device, cause the electronic device to perform any method of any one of the first or second aspects and their implementations.

[0034] In a fifth aspect of this application, a chip is provided. The chip includes processing circuitry configured to perform any method of any one of the first to second aspects and their implementations.

[0035] In a sixth aspect of this application, a computer program product is provided. The computer program product includes instructions that, when executed by an electronic device, cause the electronic device to perform any method of any one of the first or second aspects and their implementations.

[0036] It should be understood that the description in the Summary Section is not intended to limit the key or essential features of this application, nor is it intended to restrict the scope of this application. Other features of this application will become readily apparent from the following description. Attached Figure Description

[0037] Figure 1A shows a schematic diagram of a communication system in which embodiments of the present disclosure may be implemented.

[0038] Figure 1B illustrates a schematic diagram of the CU / DU separation architecture of a gNB under a 5G Next Generation Radio Access Network (NG-RAN) architecture related to embodiments of the present disclosure.

[0039] Figure 1C shows the protocol stack distribution diagram under gNB-CU / DU separation and gNB-CU-CP / UP separation in relation to embodiments of this disclosure.

[0040] Figure 1D illustrates a schematic diagram of the relationship between DU and RU in relation to embodiments of this disclosure.

[0041] Figure 2 illustrates an interaction signaling diagram according to some embodiments of the present disclosure.

[0042] Figure 3 illustrates a first example process according to some embodiments of the present disclosure.

[0043] Figure 4 illustrates a second example process according to some embodiments of the present disclosure.

[0044] Figure 5 shows a schematic flowchart of a method implemented at a first device according to an embodiment of the present disclosure.

[0045] Figure 6 shows a schematic flowchart of a method implemented at a second device according to an embodiment of the present disclosure.

[0046] Figure 7 is a block diagram of a device that can be used to implement some embodiments of this application.

[0047] Figure 8 is a schematic diagram of the structure of an apparatus according to some embodiments of this application.

[0048] Figure 9 is a schematic diagram of the structure of an apparatus according to some embodiments of this application.

[0049] Throughout all the accompanying drawings, the same or similar reference numerals are used to denote the same or similar components. Detailed Implementation

[0050] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0051] In the description of embodiments of this disclosure, the term "comprising" and similar terms should be understood as open-ended inclusion, i.e., "including but not limited to". The term "based on" should be understood as "at least partially based on". The term "one embodiment" or "the embodiment" should be understood as "at least one embodiment". The terms "first", "second", etc., may refer to different or the same objects. Other explicit and implicit definitions may also be included below.

[0052] Embodiments of this disclosure may be implemented according to any suitable communication protocol, including but not limited to cellular communication protocols such as 3rd Generation (3G), 4th Generation (4G), 5th Generation (5G) and future communication protocols, wireless local area network communication protocols such as Institute of Electrical and Electronics Engineers (IEEE) 802.11, and / or any other protocol currently known or to be developed in the future.

[0053] The technical solutions of the embodiments disclosed herein are applicable to communication systems that comply with any suitable communication protocol, such as: General Packet Radio Service (GPRS), Global System for Mobile Communications (GSM), Enhanced Data Rate for GSM Evolution (EDGE), Universal Mobile Telecommunications Service (UMTS), Long Term Evolution (LTE) systems, Wideband Code Division Multiple Access (WCDMA), Code Division Multiple Access 2000 (CDMA2000), Time Division-Synchronization Code Division Multiple Access (TD-SCDMA), Frequency Division Duplex (FDD) systems, Time Division Duplex (TDD), fifth-generation (5G) systems (e.g., New Radio (NR)), and future communication systems, etc.

[0054] For illustrative purposes, embodiments of this disclosure are described below with reference to 5G communication systems within the 3rd Generation Partnership Project (3GPP). However, it should be understood that embodiments of this disclosure are not limited to this communication system, but can be applied to any communication system with similar problems, such as wireless local area networks (WLANs), wired communication systems, or other communication systems developed in the future.

[0055] As used in this disclosure, the terms "network node" or "network device" refer to an entity or node that can be used to communicate with a terminal device, such as an access network device. An access network device can be a means deployed in a radio access network to provide wireless communication functionality for a mobile terminal, such as a Radio Access Network (RAN) network device. Access network devices can include various types of base stations. Base stations are used to provide radio access services to terminal devices. Specifically, each base station corresponds to a service coverage area, and terminal devices entering this area can communicate with the base station via wireless signals to receive the radio access services provided by the base station. The service coverage areas of base stations may overlap, and terminal devices in overlapping areas can receive wireless signals from multiple base stations, thus allowing multiple base stations to provide services to the terminal device simultaneously. Depending on the size of the provided service coverage area, access network devices can include macro base stations providing macro cells, micro base stations providing pico cells, pico base stations providing pico cells, and femto base stations providing femto cells. In addition, access network equipment can also include various forms of relay stations, access points, remote radio units (RRUs), radio heads (RHs), remote radio heads (RRHs), and so on. The names of access network equipment may differ in systems employing different radio access technologies; for example, in Long Term Evolution (LTE) networks it is called an evolved Node B (eNB or eNodeB), in 3G networks it is called a Node B (NB), and in 5G networks it may be called a g Node B (gNB) or NR Node B (NR NB), and so on. In some implementations, access network equipment can include satellites or high-altitude platform stations, and can be applied to scenarios such as Low Earth Orbit (LEO), Medium Earth Orbit (MEO), Geostationary Earth Orbiting (GEO) / Unmanned Aircraft System (UAS). For ease of description, in the subsequent embodiments of this disclosure, the devices that provide wireless communication functions for mobile terminals are collectively referred to as network devices, and the embodiments of this disclosure are no longer specifically limited.

[0056] Figure 1A illustrates a schematic diagram of a communication system 100 that can be implemented according to an embodiment of the present disclosure. As shown in Figure 1A, the communication system includes a first device 110 and a second device 120. The first device 110 and the second device 120 may have wireless transceiver capabilities, enabling them to communicate (e.g., wirelessly) with one or more devices of one or more communication systems. For example, the first device 110 may communicate with a CU 130, and the second device 120 may communicate with a terminal 140. This disclosure can be applied to scenarios where O-RU and O-DU are separated, for inference configuration distribution of fronthaul data AI compression. In some embodiments, the first device 110 may include an O-DU, and the second device 120 may include an O-RU, wherein the O-RU is connected to the O-DU via optical fiber. It should be understood that although the first device 110 is depicted as an O-DU in Figure 1A, the first device 110 may also be any other communication device capable of performing data compression / decompression. The second device 120 is depicted as an O-RU, but the second device 110 may also be any other communication device capable of performing data compression / decompression.

[0057] Furthermore, it should be understood that communication system 100 can be applied to various scenarios. For example, application scenarios of communication system 100 include, but are not limited to, existing communication systems or future evolved communication systems such as fifth-generation systems (5G), future communication systems, new radio (NR) communication systems, and non-terrestrial network (NTN) systems. In addition, it should be understood that the aforementioned communication can follow any appropriate communication technology and corresponding communication standards.

[0058] To reduce the pressure on fronthaul link bandwidth and deployment costs caused by the underlying splitting method, 5G base stations (gNBs) adopt an upper-layer splitting approach, dividing the base station into two functional entities: CU and DU. The midhaul link between the CU and DU has lower network bandwidth requirements. Figure 1B shows the overall architecture of the 3GPP 5G radio access network. Within the NG-RAN, a gNB can consist of two parts: gNB-CU and gNB-DU.

[0059] The functional decomposition between the CU and DU entities of a 5G base station adopts a static decomposition approach, with a fixed division based on the functional granularity of the protocol stack. Radio Link Control (RLC), Medium Access Control (MAC), and Physical Layer (PHY) protocols reside in the gNB-DU, while Radio Resource Control (RRC) and above (PDCP) and Service Data Adaptation Protocol (SDAP) protocols reside in the gNB-CU. Specifically, RRC implements air interface radio resource and air interface connection control and belongs to the Control Plane (CP) protocol. SDAP maps Quality of Service (QoS) flows to Data Radio Bearers (DRBs) and belongs to the User Plane (UP) protocol. QoS flows are service data flows with specific QoS requirements. RLC is a sublayer of Air Interface Layer 2, providing transparent data transmission as well as unacknowledged and acknowledged data transmission modes. The MAC layer, also a sublayer of the air interface layer 2, is primarily responsible for controlling and connecting the physical media of the physical layer. The PHY layer is responsible for transmitting bits or groups of bits over the physical media, including encoding and decoding the transmitted and received information. Figure 1C shows the protocol stack distribution in the case of gNB with CU / DU separation and gNB-CU further with control plane / user plane (CP / UP) separation. The PDCP layer protocol exists in both gNB-CU-CP and gNB-CU-UP units. The RRC layer is located above the PDCP layer in the gNB-CU-CP unit, and the SDAP layer is located above the PDCP layer in the gNB-CU-UP unit.

[0060] As mentioned earlier, in an open RAN, the DU can be further subdivided into O-DU and O-RU, as shown in Figure 1D. CU 130 has high-level protocol processing functions, such as Radio Resource Control (RRC) and Packet Data Convergence Protocol (PDCP). The O-DU has baseband processing functions and complete protocol layer functions, primarily responsible for high-level protocol functions such as data encryption and integrity protection, and also has high-level physical layer processing functions. The O-RU has low-level physical layer signal processing functions, primarily responsible for the transmission and reception of radio frequency signals. The O-RU and O-DU are connected via optical fiber, and their interface is called the fronthaul interface. There are two types of functional separation between the O-RU and O-DU: Type A and Type B. The main difference between Type A and Type B functional separation is that in Type A separation, the O-RU does not support precoding, while in Type B separation, the O-RU supports precoding. It should be understood that in some embodiments of this disclosure, the O-RU can be referred to as RU, and the O-DU can be referred to as DU.

[0061] With the growth of mobile data, the data transmitted on the fronthaul interface is also constantly increasing, but the capacity of the fronthaul link is limited. Therefore, the protocol supports compression of fronthaul data to reduce fronthaul bandwidth. Artificial Intelligence (AI) compression is an efficient compression method. AI compression is generally a two-end model, which includes an encoder and a decoder. The encoder compresses the data, and the decoder restores the data. However, the current fronthaul interface does not support AI compression, and there are no relevant specifications on how to distribute the configuration of the two-end AI compression model. More generally, regarding data compression-based communication between communication devices, how to determine the configuration information used for data compression and how to send this configuration information requires further research and clarification.

[0062] In view of this, embodiments of the present disclosure provide a communication method. In this method, a first device receives data compression capability information of a second device from the second device. Based on the capability information of the second device, the first device determines a data compression method to be used by the second device and sends a configuration for data compression. This configuration consists of configuration information required to execute the compression method. In this way, the capabilities of the first and second devices can be aligned, and the configuration can be standardized. Therefore, this method improves the suitability and accuracy of the data compression configuration, thereby reducing the possibility of reconfiguration, improving the efficiency of data compression configuration, and ultimately improving communication performance.

[0063] Figure 2 illustrates an interaction signaling diagram according to some embodiments of the present disclosure. For clarity and without limitation, the communication process 200 depicted in Figure 2 will be discussed in conjunction with Figure 1A.

[0064] In process 200, the second device 120 sends 210 data compression capability information 215 of the second device 120 to the first device 110. Correspondingly, the first device 110 receives 220 the data compression capability information 215 of the second device from the second device 120. In some examples, the first device 110 may include an O-DU, the second device 120 may include an O-RU, and the second device 120 and the first device 110 constitute a DU.

[0065] In some embodiments, capability information 215 may include the computing power of the second device 120 or the compression methods supported by the second device 120. Additionally, the compression methods may include artificial intelligence (AI) compression, block compression, or a combination of both. It should be understood that in some embodiments, it is optional for the second device 120 to send capability information 215 to the first device 110. In this way, the capabilities of the second device 120 and the first device 110 can be aligned. For example, the data compression configuration can be determined based on the computing power of the second device, the supported compression methods, etc., thereby improving the adaptability and accuracy of the data compression configuration in terms of computing power and compression methods, and improving the efficiency of the data compression configuration.

[0066] Alternatively or additionally, the first device 110 may send a first request message for capability information 215 of the second device 120 to the second device 120, wherein the capability information 215 is in response to the first request message. In some examples, the first request message may be a capability query message. For example, the DU (i.e., the first device 110) may send a capability or function query to the RU (i.e., the second device 120). The DU may request the computing power of the RU, such as floating-point operations per second (FLPOS), or request the compression methods supported by the RU, such as AI compression, block compression, etc.

[0067] Correspondingly, the second device 120 can receive a first request message for capability information of the second device 120 from the first device 110, wherein the capability information is sent in response to the first request message.

[0068] Referring again to Figure 2, based on the capability information 215 of the second device 120, the first device 110 determines 225 the data compression method to be used by the second device 120. The first device 110 sends 230 a data compression configuration 235 to the second device 120, whereby the configuration 235 is the configuration information required to execute the compression method. For example, the configuration 235 could be a model inference configuration. Correspondingly, the second device 120 receives the data compression configuration 235 from the first device 110. In other words, the first device 110 determines the compression method to be used based on the capabilities or functions of the second device 120 and indicates the compression method to be used to the second device 120. In this way, the second device 120 can obtain a data compression configuration based on its capabilities. Therefore, this method improves the suitability and accuracy of the data compression configuration, thus reducing the possibility of reconfiguration, improving the efficiency of the data compression configuration, and ultimately improving communication performance.

[0069] In some embodiments, configuration 235 may further include the dimension of AI compression, the number of blocks in block compression, the number of indicator bits for the scaling factor of block compression, the number of indicator bits for the index parameter of block compression, the number of bits of compressed data in block compression, the transform domain of the data, or a combination of one or more of the above. In some examples, the transform domain of the data may be the frequency domain. In other embodiments, the transform domain of the data may also be any suitable transform domain other than the frequency domain.

[0070] Alternatively or additionally, the first device 110 may send a second request message for conditional information regarding AI compression for the second device 120. The first device 110 may then receive the conditional information for AI compression. In some examples, the conditional information may be applicable conditions for the AI ​​model, and the second request message may be a query message for the applicable conditions. For example, if AI compression is to be adopted by the RU (i.e., the second device 120), the DU (i.e., the first device 110) may also send a query message to the RU (i.e., the second device 120) regarding the applicable conditions of the AI ​​model on the RU side.

[0071] In some embodiments, the condition information may include radio frequency parameters or identifiers of radio frequency parameters of the second device for AI compression, temperature or identifiers of the second device for AI compression, power consumption or identifiers of the second device for AI compression, configuration of the antenna array of the second device for AI compression or identifiers of the antenna array configuration, time synchronization information or identifiers of time synchronization information for AI compression, signal characteristics of external noise or identifiers of external noise for AI compression, or a combination of one or more of the above.

[0072] In one example, the condition information may include RU-side RF parameters, RU-side temperature status, RU-side power consumption status, antenna array status (e.g., antenna orientation, angle, and array configuration), time synchronization information, and characteristics of unprocessed external noise signals. In another example, the condition information may include IDs of applicable conditions, such as identifiers of RU-side RF parameters, RU-side temperature status, RU-side power consumption status, antenna array status (e.g., antenna orientation, angle, and array configuration), time synchronization information, and characteristics of unprocessed external noise signals.

[0073] Correspondingly, the second device 120 can receive a second request message for AI compression condition information for the second device 120 from the first device 110, and send the AI ​​compression condition information to the first device 110.

[0074] In some embodiments, the second request information may be sent together with the first request information. Additionally, condition information may be received together with capability information. For example, a query message for applicable conditions may be sent during a capability query, instructing the RU to report applicable conditions when reporting support for AI compression. Furthermore, if an applicable condition query is received when a capability query message is received, the RU reports the applicable conditions of the AI ​​model to the DU.

[0075] Alternatively or additionally, upon receiving configuration 235, the second device 120 may determine whether configuration 235 is applicable to the second device 120 and send a response message for configuration 235. The response message indicates whether configuration 235 is applicable to the second device 120. For example, after receiving configuration from DU, RU may infer whether the configuration was successfully or unsuccessfully applied at RU.

[0076] Correspondingly, the first device 110 can receive a response message for configuration 235, which indicates whether configuration 235 can be used in the second device 120. Additionally, the response message can indicate that configuration 235 cannot be used in the second device 120, and the response message can also include a reason why configuration 235 cannot be used in the second device 120, which may include a condition indicated by condition information that does not match configuration 235.

[0077] In some embodiments, the first device 110 may also update the configuration for data compression based on a response message and send the updated configuration to the second device 120. For example, the DU may reconfigure the inference configuration based on feedback from the RU. Upon receiving the updated configuration, the second device 120 may determine whether the updated configuration is usable by the second device 120 and send a response message for the updated configuration. The response message indicates whether the updated configuration is usable by the second device 120. Additionally, the first device 110 may receive the response message for the updated configuration, indicating whether the updated configuration is usable by the second device 120.

[0078] In this manner, the first device 110 sends AI capability query information to the second device 120, and distributes the model's inference configuration based on the query results. This achieves model alignment between the first device 110 and the second device 120, thereby reducing unnecessary overhead and significantly improving communication efficiency.

[0079] To gain a more thorough and complete understanding of this disclosure, two more specific implementations of the communication method provided herein will be described with reference to Figures 3 and 4. It should be noted that each part of Figures 3 and 4 can be used individually or in any combination, and is for illustrative purposes only and is not intended to limit the scope of this disclosure.

[0080] Figure 3 illustrates a first example process 300 according to some embodiments of the present disclosure, which can be considered a specific implementation of process 200 of Figure 2. DU 301 in Figure 3 can correspond to the first device 110 of Figure 2, and RU 302 in Figure 3 can correspond to the second device 120 of Figure 2.

[0081] At 310, DU 301 sends a function / capability query message to RU 302. This function / capability query message can correspond to one implementation of the first request information in procedure 200; see procedure 200 for a specific example, which will not be repeated here. It should be understood that sending the function / capability query is optional.

[0082] At 320, RU 302 feeds back the corresponding function / capability to DU 301. This function / capability corresponds to one implementation of capability information 215 in process 200; see process 200 for a specific example, which will not be repeated here. It should be understood that feeding back the corresponding capability or function is also optional.

[0083] At 330, if AI compression is used, DU 301 can send an RU 302-side applicability query message to RU 302, such as query information on the applicability conditions of the AI ​​model. The RU 302-side applicability query message corresponds to one implementation of the second request information in process 200; a specific example is provided in process 200 and will not be repeated here. Furthermore, the applicability query information can also be sent when querying capabilities at 310.

[0084] At 340, RU 302 can report the applicability conditions of the AI ​​model to DU 301. If the query information for the applicability conditions is received at 310, RU 302 will then report the applicability conditions at 320. The applicability conditions here correspond to one implementation of the condition information in process 200; see process 200 for a specific example, which will not be repeated here.

[0085] At 350, DU 301 determines the compression method to be used based on the capabilities or functions of RU 302 and instructs RU 302 on the compression method to be used, i.e., issues the inference configuration. Additionally, DU 301 also issues the inference configuration based on information fed back by RU 302. The inference configuration in Figure 3 corresponds to one implementation of configuration 235 for data compression in process 200. For a specific example, please refer to process 200, which will not be repeated here.

[0086] At 360, after receiving the configuration from DU 301, RU 302 sends an inference configuration response to DU 301 to indicate whether the inference configuration application was successful or failed. This inference configuration response corresponds to one implementation of the response message for configuration 235 in process 200; see process 200 for a specific example, which will not be elaborated here.

[0087] In this way, the DU sends AI capability query information to the RU, and distributes the model's inference configuration based on the query results. The DU can configure the model for the RU based on the RU's capabilities, thereby improving model performance and thus increasing communication efficiency.

[0088] Figure 4 illustrates a second example process 400 according to some embodiments of the present disclosure, which can be considered as a specific implementation of process 200 of Figure 2. DU 401 in Figure 4 can correspond to the first device 110 of Figure 2, and RU 402 in Figure 4 can correspond to the second device 120 of Figure 2.

[0089] At 410, DU 401 issues an inference configuration to RU 402. The inference configuration can be determined based on the information and capability information fed back by the RU. Furthermore, the inference configuration can include the dimension of AI compression, the number of blocks for block compression, the number of indicator bits, the number of bits, and the applicable conditions for the AI ​​model. The inference configuration in Figure 4 corresponds to one implementation of configuration 235 for data compression in process 200. See process 200 for additional examples, which will not be repeated here.

[0090] At 420, after receiving the configuration from DU 401, RU 402 sends an inference configuration response to DU 401 to indicate whether the inference configuration was successfully or unsuccessfully applied on the RU 402 side. If the inference configuration response indicates application failure, the feedback information (i.e., the inference configuration response) may also include the reason for the failure, such as the applicable conditions not being applicable. This inference configuration response corresponds to one implementation of the response message for configuration 235 in procedure 200; see procedure 200 for an additional example, which will not be repeated here.

[0091] Optionally, at 430, RU 402 can also feed back the applicable conditions of the AI ​​model to DU 401. Specifically, the applicable conditions may include RF parameters on the RU 402 side, temperature status on the RU 402 side, power consumption status on the RU 402 side, antenna array status (such as antenna orientation, angle, and array configuration), time synchronization information, and characteristics of unprocessed external noise signals. Furthermore, the reported applicable conditions can also be the ID of the applicable conditions. The applicable conditions here correspond to one implementation of the condition information in process 200; see process 200 for additional examples, which will not be repeated here.

[0092] At 440, DU 401 reconfigures the inference configuration based on feedback from RU 402 and sends the reconfigured inference configuration to RU 402. The reconfigured inference configuration may specifically include the AI ​​compression dimension, block compression, number of blocks, number of indicator bits, number of bits, and change domain. For example, the reconfigured inference configuration corresponds to one implementation of the updated configuration in process 200; see process 200 for additional examples, which will not be repeated here.

[0093] At 450, after receiving the configuration from DU 401, RU 402 sends an inference configuration response to DU 401 to indicate whether the inference configuration reception was successful or failed. If the response fails, the feedback information may also include the reason for the failure, such as a change in applicable conditions. The inference configuration response in Figure 4 corresponds to one implementation of the response message for the updated configuration in process 200, which will not be described further here.

[0094] In this way, DU 401 issues inference configuration based on feedback from RU 402. RU 402 determines whether the issued inference configuration is applicable and sends feedback to DU 401. DU 401 then adjusts the inference configuration based on the feedback from RU 402, achieving model alignment between DU 401 and RU 402. This improves model performance and, consequently, communication efficiency.

[0095] In summary, this disclosure relates to the inference configuration of how the RU receives data sent by the DU after the fronthaul interface is opened, where data between the DU and RU is compressed using an AI model. First, consider the RU reporting capability information to the DU, including the RU's computing power and supported compression methods. Based on the information reported by the RU, the DU can further query the applicability conditions of the AI ​​model. The RU then reports the applicability conditions, which may include RU-side RF parameters, RU-side temperature status, RU-side power consumption status, antenna array status (such as antenna direction, angle, and array configuration), time synchronization information, and characteristics of unprocessed external noise signals. The DU then sends the inference configuration based on the RU's applicability conditions.

[0096] Furthermore, in some embodiments, the DU can also directly issue inference configurations based on the RU's capabilities. After receiving the inference configuration, the RU determines whether the inference configuration is applicable. If it is not applicable, it feeds back the applicable conditions to the DU, and the DU reconfigures the applicable conditions based on the RU's feedback.

[0097] Figure 5 illustrates a schematic flowchart of a method 500 implemented at a first device according to an embodiment of the present disclosure. For clarity and without limitation, the process 500 will be discussed in conjunction with Figure 1A. In one possible implementation, method 500 may be implemented by the first device 110 in communication system 100. In other possible implementations, method 500 may also be implemented by other communication devices independent of communication system 100. As an example, method 500 will be described below assuming it is implemented by the first device 110 in communication system 100.

[0098] In block 510, the first device 110 receives data compression capability information from the second device. In block 520, the first device 110 determines, based on the second device's capability information, a data compression method to be used by the second device. In block 530, the first device 110 sends a configuration for data compression, including configuration information required to execute the compression method.

[0099] In some embodiments, the capability information may further include at least one of the following: the computing power of the second device, or the compression method supported by the second device. In some embodiments, the compression method may further include at least one of the following: AI compression, or block compression.

[0100] In some embodiments, the configuration may further include at least one of the following: the dimension of AI compression, the number of blocks in block compression, the number of indicator bits for the scaling factor of block compression, the number of indicator bits for the index parameter of block compression, the number of bits of the compressed data in block compression, or the transform domain of the data.

[0101] In some embodiments, the first device may send a first request for capability information of the second device, wherein the capability information is in response to the first request. In some embodiments, the first device may send a second request for conditional information regarding AI compression of the second device, and receive conditional information regarding AI compression.

[0102] In some embodiments, the condition information may include at least one of the following: radio frequency parameters or identifiers of the second device for AI compression, temperature or identifiers of the second device for AI compression, power consumption or identifiers of the second device for AI compression, configuration of the antenna array of the second device for AI compression or identifiers of the antenna array configuration, time synchronization information or identifiers of time synchronization information for AI compression, or signal characteristics of external noise or identifiers of external noise for AI compression.

[0103] In some embodiments, the second request information and the first request information may be sent together. In some embodiments, condition information and capability information may be received together.

[0104] In some embodiments, the first device may receive a response message for the configuration, the response message indicating whether the configuration can be used by the second device. In some embodiments, the response message indicates that the configuration cannot be used by the second device, and the response message may also include a reason why the configuration cannot be used by the second device, including a mismatch between the conditions indicated by condition information and the configuration.

[0105] In some embodiments, the first device may update the configuration for data compression and send the updated configuration based on a response message. In some embodiments, the first device may receive a response message for the updated configuration, the response message indicating whether the updated configuration can be used by the second device.

[0106] In some embodiments, the second device may include an O-RU, and the second device and the first device may form a DU; and the first device may include an O-DU.

[0107] Figure 6 illustrates a schematic flowchart of a method 600 implemented at a second device according to an embodiment of the present disclosure. For clarity and without limitation, the process 600 will be discussed in conjunction with Figure 1A. In one possible implementation, method 600 may be implemented by a second device 120 in communication system 100. In other possible implementations, method 600 may also be implemented by other communication devices independent of communication system 100. As an example, method 600 will be described below as being implemented by the second device 120 in communication system 100.

[0108] In block 610, the second device 120 sends data compression capability information. In block 620, the second device 120 receives configuration information for data compression, which is the configuration information required to perform the compression method.

[0109] In some embodiments, the capability information may include at least one of the following: the computing power of the second device, or the compression method supported by the second device. In some embodiments, the compression method may include at least one of the following: AI compression, or block compression.

[0110] In some embodiments, the configuration may further include at least one of the following: the dimension of AI compression, the number of blocks in block compression, the number of indicator bits for the scaling factor of block compression, the number of indicator bits for the index parameter of block compression, the number of bits of compressed data in block compression, or the transform domain of the data.

[0111] In some embodiments, the second device may receive a first request for capability information of the second device, wherein the capability information is sent in response to the first request. In some embodiments, the second device may receive a second request for conditional information regarding AI compression of the second device, and, if the second device is capable of performing AI compression, send the conditional information regarding AI compression.

[0112] In some embodiments, the condition information may include at least one of the following: radio frequency parameters or identifiers of the second device for AI compression, temperature or identifiers of the second device for AI compression, power consumption or identifiers of the second device for AI compression, configuration of the antenna array of the second device for AI compression or identifiers of the antenna array configuration, time synchronization information or identifiers of time synchronization information for AI compression, or signal characteristics of external noise or identifiers of external noise for AI compression.

[0113] In some embodiments, the second request information and the first request information may be received together. In some embodiments, the condition information and capability information of AI compression may be sent together.

[0114] In some embodiments, the second device may determine whether a configuration is usable for the second device; and send a response message for the configuration, the response message indicating whether the configuration is usable for the second device. In some embodiments, the second device may receive an updated configuration, determine whether the updated configuration is usable for the second device, and send a response message for the updated configuration, the response message indicating whether the updated configuration is usable for the second device.

[0115] In some embodiments, the second device may include an O-RU, the second device and the first device may form a DU, and the first device may include an O-DU.

[0116] Figure 7 is a block diagram of a device 700 that can be used to implement some embodiments of the present application. In some embodiments, device 700 may be an element of a communication network infrastructure, such as a base station (e.g., NodeB, evolved NodeB (eNodeB or eNB), next-generation NodeB (sometimes referred to as gNodeB or gNB), Home Subscriber Server (HSS), gateway (GW), such as a packet gateway (PGW) or serving gateway (SGW), or various other nodes or functions within a core network (CN) or public land mobile network (PLMN). In other embodiments, device 700 may be a device connected to network infrastructure via a wireless interface, such as a mobile phone, smartphone, or other such device that can be classified as user equipment (UE). In some embodiments, device 700 may be a machine-type communication (MT) device. C) Device (also known as machine-to-machine (M2M) device), or another such device that can be classified as a UE even though it does not provide direct service to a user. In some embodiments, device 700 may be a roadside unit (RSU), vehicle UE (V-UE), pedestrian UE (P-UE), or infrastructure UE (I-UE). In some scenarios, device 700 may also be referred to as a mobile device, a term intended to reflect a device connected to a mobile network, regardless of whether the device itself is designed for or capable of being mobile. A particular device may utilize all or only a subset of the components shown, and the level of integration may vary depending on the device. Furthermore, device 700 may contain multiple instances of components, such as multiple processors, memory, transmitters, receivers, etc.

[0117] Device 700 typically includes a processor 702, such as a central processing unit (CPU), and may further include a dedicated processor, such as a graphics processing unit (GPU) or other such processor, memory 704, a network interface 706, and a bus 708 for connecting the components of device 700. Optionally, device 700 may also include components such as a mass storage device 710, a video adapter 712, and an I / O interface 716 (shown in dashed lines).

[0118] Memory 704 may include any type of non-transitory system memory readable by processor 702, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous DRAM (SDRAM), read-only memory (ROM), or combinations thereof. In one embodiment, memory 704 may include more than one type of memory, such as ROM used at startup and DRAM used for program and data storage during program execution. Bus 708 may be one or more of a plurality of bus architectures of any type, including a memory bus or memory controller, a peripheral bus, or a video bus.

[0119] Device 700 may also include one or more network interfaces 706, which may include at least one of wired network interfaces and wireless network interfaces. As shown in FIG7, network interface 706 may include a wired network interface for connecting to network 722, and may also include a wireless access network interface 720 for connecting to other devices via a wireless link. When device 700 is a network infrastructure element, the wireless access network interface 720 may be omitted for nodes or functions that are elements of a PLMN rather than elements at the wireless edge (e.g., eNB). When device 700 is infrastructure at the wireless edge of the network, it may include both wired and wireless network interfaces. When device 700 is a wirelessly connected device, such as a user equipment, the wireless access network interface 720 may be present and may be supplemented by other wireless interfaces such as a WiFi network interface. Network interface 706 allows device 700 to communicate with remote entities such as those connected to network 722.

[0120] Mass storage 710 may include any type of non-transitory storage device configured to store data, programs, and other information and make the data, programs, and other information accessible via bus 708. Mass storage 710 may include, for example, one or more of a solid-state drive, hard disk drive, disk drive, or optical disk drive. In some embodiments, mass storage 710 may be located remotely from device 700 and may be accessed using a network interface such as interface 706. In the illustrated embodiment, mass storage 710 is distinct from the memory 704 that includes it, and mass storage 710 typically performs storage tasks compatible with higher latency but typically provides low or no fluctuation. In some embodiments, mass storage 710 may be integrated with heterogeneous memory 704.

[0121] Optional video adapter 712 and I / O interface 716 (shown in dashed lines) provide interfaces for coupling device 700 to external input and output devices. Examples of input and output devices include a display 66 coupled to video adapter 712 and an I / O device 718, such as a touchscreen, coupled to I / O interface 716. Other devices may be coupled to device 700 and may utilize additional or fewer interfaces. For example, a serial interface such as Universal Serial Bus (USB) (not shown) may be used to provide interfaces for external devices. Those skilled in the art will understand that in embodiments where device 700 is part of a data center, I / O interface 716 and video adapter 712 may be virtualized and provided via network interface 706.

[0122] Figure 8 is a schematic diagram of the structure of a device 800 according to some embodiments of this application. As shown in Figure 8, the device 800 includes a receiving unit 802, a determining unit 804, and a transmitting unit 806. The device 800 can be applied to the communication system shown in Figure 1A and can implement any of the methods provided in the foregoing embodiments. Optionally, the physical manifestation of the device 800 can be a communication device, such as a network device or a UE. Alternatively, the device 800 can be other devices capable of implementing the functions of a communication device, such as a processor or chip inside the communication device. Specifically, the device 800 can be a programmable chip, such as a field-programmable gate array (FPGA), a complex programmable logic device (CPLD), an application-specific integrated circuit (ASIC), or a system on a chip (SOC).

[0123] In some embodiments, the receiving unit 802 may be configured to receive data compression capability information of the second device. The determining unit 804 may be configured to determine, based on the capability information of the second device, a data compression method to be used by the second device. The sending unit 806 may be configured to send configuration information for data compression, including configuration information required to execute the compression method.

[0124] In some other embodiments, apparatus 800 may include various other units or modules that can be configured to perform the various operations or functions described with respect to the foregoing method embodiments. Specific details can be obtained by referring to the detailed description of the foregoing method embodiments, and will not be repeated here.

[0125] Figure 9 is a schematic diagram of the structure of a device 900 according to some embodiments of this application. As shown in Figure 9, the device 900 includes a transmitting unit 902 and a receiving unit 904. The device 900 can be applied to the communication system shown in Figure 1A and can implement any of the methods provided in the foregoing embodiments. Optionally, the physical manifestation of the device 900 can be a communication device, such as a network device or a UE. Alternatively, the device 900 can be other devices capable of implementing the functions of a communication device, such as a processor or chip inside the communication device. Specifically, the device 900 can be a programmable chip, such as a field-programmable gate array (FPGA), a complex programmable logic device (CPLD), an application-specific integrated circuit (ASIC), or a system on a chip (SOC).

[0126] In some embodiments, the transmitting unit 902 may be configured to transmit data compression capability information of the second device. The receiving unit 904 may be configured to receive configuration information for data compression, which is configuration information required to perform the compression method.

[0127] In some other embodiments, the apparatus 900 may include various other units or modules that can be configured to perform the various operations or functions described with respect to the foregoing method embodiments. Specific details can be obtained by referring to the detailed description of the foregoing method embodiments, and will not be repeated here.

[0128] It should be noted that the module division in the above embodiments of this application is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods. Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, exist as separate physical units, or be integrated into one unit by two or more units. The integrated units described above can be implemented in hardware or as software functional units.

[0129] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, or all or part of it, 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.) or processor to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0130] Based on the above embodiments, this application also provides a computer program that, when run on a computer, causes the computer to execute any of the methods provided in the above embodiments.

[0131] Based on the above embodiments, this application also provides a computer-readable storage medium storing a computer program. When executed by a computer, the computer program causes the computer to perform any of the methods provided in the above embodiments. The storage medium can be any available medium that can be accessed by a computer. By way of example, but not limited to, a computer-readable medium may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code having the form of instructions or data structures and that can be accessed by a computer.

[0132] Based on the above embodiments, this application also provides a chip for reading a computer program stored in a memory and implementing any of the methods provided in the above embodiments.

[0133] Based on the above embodiments, this application provides a chip system including a processor for supporting a computer device in implementing the functions involved in the communication devices in the above embodiments. In one possible design, the chip system further includes a memory for storing necessary programs and data of the computer device. This chip system may be composed of chips or may include chips and other discrete components.

[0134] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0135] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in one or more blocks of the flowchart illustrations and / or one or more blocks of the block diagrams.

[0136] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means that implement the functions specified in one or more flowcharts and / or one or more block diagrams.

[0137] These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer-implemented process, such that the instructions, which execute on the computer or other programmable apparatus, provide steps for implementing the functions specified in one or more flowcharts and / or one or more block diagrams.

[0138] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the scope of protection of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A communication method, comprising: Receive data compression capability information from the second device; Based on the capability information of the second device, determine the compression method for data used by the second device; as well as Send configuration for the data compression, the configuration being the configuration information required to execute the compression method.

2. The method of claim 1, wherein the capability information includes at least one of the following: The computing power of the second device; or The compression methods supported by the second device.

3. The method according to claim 2, wherein the compression method includes at least one of the following: Artificial intelligence (AI) compression; or Block compression.

4. The method of claim 3, wherein the configuration further comprises at least one of the following: The dimensions of the AI ​​compression; The number of blocks in the block compression; The number of bits indicating the scaling factor of the block compression; The number of indicator bits for the index parameter of the block compression; The number of bits of the compressed data in the block compression; or The transform domain of the data.

5. The method according to any one of claims 1 to 4, further comprising: Send a first request message for the capability information of the second device, wherein the capability information is in response to the first request message.

6. The method according to any one of claims 1 to 5, further comprising: Send a second request message for conditional information regarding AI compression for the second device; as well as Receive the condition information compressed by the AI.

7. The method of claim 6, wherein the condition information includes at least one of the following: Radio frequency parameters or identifiers of the second device applicable to the AI ​​compression; The temperature of the second device used for AI compression, or an identifier of the temperature; The power consumption of the second device applicable to the AI ​​compression, or an identifier of the power consumption; The configuration of the antenna array of the second device applicable to the AI ​​compression, or an identifier of the configuration of the antenna array; Information applicable to time synchronization of the AI ​​compression or an identifier of the time synchronization information; or The signal characteristics of the external noise applicable to the AI ​​compression or the identification of the signal characteristics of the external noise.

8. The method of claim 6, wherein the second request information is sent together with the first request information.

9. The method of claim 8, wherein the condition information is received together with the capability information.

10. The method according to any one of claims 1 to 9, further comprising: Receive a response message for the configuration, the response message indicating whether the configuration can be used in the second device.

11. The method of claim 10, wherein the response message indicates that the configuration cannot be used for the second device, and the response message further includes a reason why the configuration cannot be used for the second device, the reason including a mismatch between the conditions indicated by the condition information and the configuration.

12. The method according to any one of claims 1 to 10, further comprising: Based on the response message, update the configuration for the data compression; as well as Send the updated configuration.

13. The method according to claim 12, further comprising: Receive a response message for the updated configuration, the response message indicating whether the updated configuration can be used in the second device.

14. The method according to any one of claims 1 to 13, wherein: The second device includes an open radio frequency unit (O-RU), and the second device and the first device form a distributed unit (DU); and The first device includes an Open Distributed Unit (O-DU).

15. A communication method, comprising: Send information about the second device's data compression capabilities; as well as Receive configuration for the data compression, the configuration being configuration information required to execute the compression method.

16. The method of claim 15, wherein the capability information includes at least one of the following: The computing power of the second device; or The compression methods supported by the second device.

17. The method of claim 16, wherein the compression method comprises at least one of the following: Artificial intelligence (AI) compression; or Block compression.

18. The method of claim 17, wherein the configuration further comprises at least one of the following: The dimensions of the AI ​​compression; The number of blocks in the block compression; The number of bits indicating the scaling factor of the block compression; The number of indicator bits for the index parameter of the block compression; The number of bits of the compressed data in the block compression; or The transform domain of the data.

19. The method according to any one of claims 15 to 18, further comprising: Receive a first request message for the capability information of the second device, wherein the capability information is sent in response to the first request message.

20. The method according to any one of claims 15 to 19, further comprising: Receive a second request message for conditional information regarding AI compression for the second device; as well as If the second device is capable of performing AI compression, the condition information for the AI ​​compression is sent.

21. The method of claim 20, wherein the condition information comprises at least one of the following: Radio frequency parameters or identifiers of the second device applicable to the AI ​​compression; The temperature of the second device used for AI compression, or an identifier of the temperature; The power consumption of the second device applicable to the AI ​​compression, or an identifier of the power consumption; The configuration of the antenna array of the second device applicable to the AI ​​compression, or an identifier of the configuration of the antenna array; Information applicable to time synchronization of the AI ​​compression or an identifier of the time synchronization information; or The signal characteristics of the external noise applicable to the AI ​​compression or the identification of the signal characteristics of the external noise.

22. The method of claim 20, wherein the second request information is received together with the first request information.

23. The method of claim 22, wherein the AI-compressed condition information is sent together with the capability information.

24. The method according to any one of claims 15 to 23, further comprising: Determine whether the configuration can be used for the second device; as well as Send a response message for the configuration, the response message indicating whether the configuration can be used in the second device.

25. The method according to any one of claims 15 to 24, further comprising: Receive the updated configuration; Determine whether the updated configuration can be used in the second device; as well as Send a response message for the updated configuration, the response message indicating whether the updated configuration can be used in the second device.

26. The method according to any one of claims 15 to 25, wherein: The second device includes an open radio frequency unit (O-RU), and the second device and the first device form a distributed unit (DU); and The first device includes an Open Distributed Unit (O-DU).

27. A communications device comprising: A processor and a memory storing instructions, which, when executed by the processor, cause the communication device to perform the method according to any one of claims 1 to 14 or any one of claims 15 to 26.

28. A chip comprising processing circuitry configured to perform the method according to any one of claims 1 to 14 or any one of claims 15 to 26.

29. A computer-readable storage medium storing instructions that, when executed by a communication device, cause the communication device to perform the method according to any one of claims 1 to 14 or any one of claims 15 to 26.

30. A computer program product tangibly stored on a computer-readable medium and comprising computer-executable instructions that, when executed, cause a communication device to perform the method according to any one of claims 1 to 14 or any one of claims 15 to 26.