Communication method and communication device

Abstract

The present application relates to a communication method and a communication device. The method may comprise: a first communication device receives or sends a reference signal, wherein the reference signal is used for acquiring training information, and the training information is used for training a constellation point-related scheme. Embodiments of the present application can improve the communication performance.

Description

Communication methods and communication equipment Technical Field

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

[0002] At the transmitting end, modulation algorithms can map multiple bits to a single constellation point. At the receiving end, demodulation algorithms corresponding to the modulation algorithms can be used to calculate the approximate point of the received signal on the constellation point. Regarding modulation and demodulation technologies, constellation point design in New Radio (NR) primarily uses rule-based mapping. Constellation points obtained through rule-based mapping are typically fixed and cannot be adapted to different channel conditions, resulting in low design flexibility. Using artificial intelligence (AI) and other methods, non-fixed constellation point distribution patterns can be designed more flexibly.

[0003] Summary of the Invention

[0004] This application provides a communication method and a communication device that can improve communication performance.

[0005] This application provides a communication method, including:

[0006] The first communication device receives or transmits a reference signal, which is used to acquire training information, and the training information is used to train constellation point related schemes.

[0007] This application provides a communication method, including:

[0008] The second communication device sends or receives a reference signal, which is used to acquire training information, and the training information is used to train constellation point related schemes.

[0009] This application provides a first communication device, including:

[0010] The transceiver unit is used to receive or send reference signals, which are used to acquire training information, and the training information is used to train constellation point correlation schemes.

[0011] This application provides a second communication device, including:

[0012] The transceiver unit is used to send or receive reference signals, which are used to acquire training information, which is used to train constellation point correlation schemes.

[0013] This application provides a communication device, including a transceiver, a processor, and a memory. The memory stores a computer program, the transceiver communicates with other devices, and the processor calls and runs the computer program stored in the memory to enable the communication device to perform the aforementioned communication method.

[0014] This application provides a chip for implementing the above-described communication method.

[0015] Specifically, the chip includes a processor for retrieving and running a computer program from memory, causing a device equipped with the chip to perform the aforementioned communication method.

[0016] This application provides a computer-readable storage medium for storing a computer program, which, when run by a device, causes the device to perform the aforementioned communication method.

[0017] This application provides a computer program product, including computer program instructions that cause a computer to execute the above-described communication method.

[0018] This application provides a computer program that, when run on a computer, causes the computer to perform the aforementioned communication method. Attached Figure Description

[0019] Figure 1 is a schematic diagram of an application scenario according to an embodiment of this application.

[0020] Figure 2 is an example diagram of 16QAM constellation points.

[0021] Figure 3 is a schematic flowchart of a communication method according to an embodiment of this application.

[0022] Figure 4 is a schematic flowchart of a communication method according to another embodiment of this application.

[0023] Figure 5 is a schematic flowchart of a communication method according to another embodiment of this application.

[0024] Figure 6 is a schematic flowchart of a communication method according to another embodiment of this application.

[0025] Figure 7 is a schematic flowchart of a communication method according to an embodiment of this application.

[0026] Figure 8 is a schematic flowchart of a communication method according to another embodiment of this application.

[0027] Figure 9 is a schematic flowchart of a communication method according to another embodiment of this application.

[0028] Figure 10 is a schematic flowchart of a communication method according to another embodiment of this application.

[0029] Figure 11 is a schematic diagram of the network-side model training and data collection method used for downlink transmission.

[0030] Figure 12 is a schematic diagram of model training and deployment.

[0031] Figure 13 is a schematic diagram of the network-side model training and data collection method used for uplink transmission.

[0032] Figure 14 is a schematic diagram of the user-side model training and data collection method used for downlink transmission.

[0033] Figure 15 shows the user-side model training and data collection methods used for uplink transmission.

[0034] Figure 16 is a schematic block diagram of a first communication device according to an embodiment of the present application.

[0035] Figure 17 is a schematic block diagram of a first communication device according to another embodiment of this application.

[0036] Figure 18 is a schematic block diagram of a second communication device according to an embodiment of the present application.

[0037] Figure 19 is a schematic block diagram of a second communication device according to another embodiment of this application.

[0038] Figure 20 is a schematic block diagram of a communication device according to an embodiment of this application.

[0039] Figure 21 is a schematic block diagram of a chip according to an embodiment of this application.

[0040] Figure 22 is a schematic block diagram of a communication system according to an embodiment of this application. Detailed Implementation

[0041] The technical solutions in the embodiments of this application will now be described with reference to the accompanying drawings.

[0042] The technical solutions of this application embodiment can be applied to various communication systems, such as: Long Term Evolution (LTE) systems, Advanced Long Term Evolution (LTE-A) systems, New Radio (NR) systems, evolution systems of NR systems, LTE-based access to unlicensed spectrum (LTE-U) systems, NR-based access to unlicensed spectrum (NR-U) systems, Non-Terrestrial Networks (NTN) systems, Universal Mobile Telecommunication System (UMTS), Wireless Local Area Networks (WLAN), Wireless Fidelity (WiFi), 5th-Generation (5G) systems, or other communication systems.

[0043] Traditional communication systems typically support a limited number of connections and are easy to implement. However, with the development of communication technology, mobile communication systems will not only support traditional communication but also, for example, device-to-device (D2D) communication, machine-to-machine (M2M) communication, machine-type communication (MTC), vehicle-to-vehicle (V2V) communication, or vehicle-to-everything (V2X) communication. The embodiments of this application can also be applied to these communication systems.

[0044] In one implementation, the communication system in this application embodiment can be applied to a carrier aggregation (CA) scenario, a dual connectivity (DC) scenario, or a standalone (SA) network deployment scenario.

[0045] In one embodiment, the communication system in this application can be applied to unlicensed spectrum, wherein the unlicensed spectrum can also be considered as shared spectrum; or, the communication system in this application can also be applied to licensed spectrum, wherein the licensed spectrum can also be considered as non-shared spectrum.

[0046] This application describes various embodiments in conjunction with network devices and terminal devices. The terminal device may also be referred to as user equipment (UE), access terminal, user unit, user station, mobile station, mobile station, remote station, remote terminal, mobile device, user terminal, terminal, wireless communication device, user agent, or user device, etc.

[0047] Terminal devices can be stations (STAION, ST) in WLANs, cellular phones, cordless phones, Session Initiation Protocol (SIP) phones, Wireless Local Loop (WLL) stations, Personal Digital Assistant (PDA) devices, handheld devices with wireless communication capabilities, computing devices or other processing devices connected to a wireless modem, in-vehicle devices, wearable devices, terminal devices in next-generation communication systems such as NR networks, or terminal devices in future evolved Public Land Mobile Network (PLMN) networks, etc.

[0048] In the embodiments of this application, the terminal device can be deployed on land, including indoor or outdoor, handheld, wearable or vehicle-mounted; it can also be deployed on water (such as ships); and it can also be deployed in the air (such as airplanes, balloons and satellites).

[0049] In the embodiments of this application, the terminal device may be a mobile phone, a tablet computer, a computer with wireless transceiver capabilities, a virtual reality (VR) terminal device, an augmented reality (AR) terminal device, a wireless terminal device in industrial control, a wireless terminal device in self-driving, a wireless terminal device in remote medical care, a wireless terminal device in a smart grid, a wireless terminal device in transportation safety, a wireless terminal device in a smart city, or a wireless terminal device in a smart home, etc.

[0050] By way of example and not limitation, in this embodiment, the terminal device can also be a wearable device. Wearable devices, also known as wearable smart devices, are a general term for devices that utilize wearable technology to intelligently design and develop everyday wearables, such as glasses, gloves, watches, clothing, and shoes. Wearable devices are portable devices that are worn directly on the body or integrated into the user's clothing or accessories. Wearable devices are not merely hardware devices, but also achieve powerful functions through software support, data interaction, and cloud interaction. Broadly speaking, wearable smart devices include those that are feature-rich, large in size, and can achieve complete or partial functions without relying on a smartphone, such as smartwatches or smart glasses, as well as those that focus on a specific type of application function and require the use of other devices such as smartphones, such as various smart bracelets and smart jewelry for vital sign monitoring.

[0051] In the embodiments of this application, the network device can be a device for communicating with mobile devices, such as an access point (AP) in a WLAN, an evolved Node B (eNB or eNodeB) in LTE, a relay station or access point, or a vehicle-mounted device, a wearable device, a network device (gNB) in an NR network, or a network device in a future evolved PLMN network or an NTN network, etc.

[0052] By way of example and not limitation, in this embodiment, the network device may have mobility characteristics; for example, the network device may be a mobile device. Optionally, the network device may be a satellite or a balloon station. For example, the satellite may be a low Earth orbit (LEO) satellite, a medium Earth orbit (MEO) satellite, a geostationary earth orbit (GEO) satellite, a high elliptical orbit (HEO) satellite, etc. Optionally, the network device may also be a base station located on land, water, or other similar locations.

[0053] In this embodiment, the network device can provide services to a cell. The terminal device communicates with the network device through the transmission resources (e.g., frequency domain resources, or spectrum resources) used by the cell. The cell can be the cell corresponding to the network device (e.g., a base station). The cell can belong to a macro base station or to a base station corresponding to a small cell. The small cell can include: metro cell, micro cell, pico cell, femto cell, etc. These small cells have the characteristics of small coverage area and low transmission power, and are suitable for providing high-speed data transmission services.

[0054] Figure 1 illustrates an exemplary communication system 100. The communication system includes a network device 110 and two terminal devices 120. In one embodiment, the communication system 100 may include multiple network devices 110, and the coverage area of ​​each network device 110 may include other numbers of terminal devices 120; this embodiment does not limit the scope of the present application.

[0055] In one embodiment, the communication system 100 may also include other network entities such as a Mobility Management Entity (MME) and an Access and Mobility Management Function (AMF), which are not limited in this application.

[0056] Network equipment can be further divided into access network equipment and core network equipment. That is, the wireless communication system also includes multiple core networks used to communicate with the access network equipment. Access network equipment can be evolved Node Bs (eNBs or e-NodeBs) in Long-Term Evolution (LTE), Next-Generation Radio (NR) (mobile communication system), or Authorized Auxiliary Access Long-Term Evolution (LAA-LTE) systems, such as macro base stations, micro base stations (also called "small base stations"), pico base stations, access points (APs), transmission points (TPs), or new generation Node Bs (gNodeBs).

[0057] It should be understood that devices with communication functions in the network / system of this application embodiment can be referred to as communication devices. Taking the communication system shown in Figure 1 as an example, the communication device may include network devices and terminal devices with communication functions. The network devices and terminal devices can be specific devices in this application embodiment, which will not be described in detail here. The communication device may also include other devices in the communication system, such as network controllers, mobility management entities, and other network entities. This application embodiment does not limit this.

[0058] It should be understood that the terms "system" and "network" are often used interchangeably in this document. The term "and / or" in this document merely describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. Furthermore, the character " / " in this document generally indicates that the preceding and following related objects have an "or" relationship.

[0059] It should be understood that the term "instruction" mentioned in the embodiments of this application can be a direct instruction, an indirect instruction, or an indication of a relationship. For example, A instructing B can mean that A directly instructs B, such as B being able to obtain information through A; it can also mean that A indirectly instructs B, such as A instructing C, so B can obtain information through C; or it can mean that there is a relationship between A and B.

[0060] In the description of the embodiments of this application, the term "correspondence" may indicate that there is a direct or indirect correspondence between two things, or that there is an association between two things, or that there is a relationship of instruction and being instructed, configuration and being configured, etc.

[0061] To facilitate understanding of the technical solutions of the embodiments of this application, the relevant technologies of the embodiments of this application are described below. The following relevant technologies are optional solutions and can be combined with the technical solutions of the embodiments of this application in any way, and they all fall within the protection scope of the embodiments of this application.

[0062] I. Modulation Techniques in NR

[0063] Modulation defines the number of bits a symbol can carry. For example, M-order modulation maps M bits to a given constellation point. At the transmitter, the signal to be modulated is typically a bit sequence of source bits after channel coding. NR supports Quadrature Phase Shift Keying (QPSK), Quadrature Amplitude Modulation (QAM), 64QAM, and 256QAM modulation. For example, QPSK carries 2 bits per constellation point, 16QAM carries 4 bits per constellation point (as shown in Figure 2), 64QAM carries 6 bits per constellation point, and 256QAM carries 8 bits per constellation point. The receiver needs to use the corresponding demodulation algorithm. Considering that channel decoding is usually required after demodulation, a soft demodulation algorithm is generally used to output the log-likelihood ratio (LLR) of the corresponding bit position at the received constellation point as the input to the channel decoder.

[0064] Generally, higher modulation orders can lead to higher throughput. However, under a given signal-to-noise ratio, higher-order modulation has a higher bit error rate because it makes the decisions between adjacent constellation points more susceptible to noise.

[0065] II. Wireless Communication and Artificial Intelligence

[0066] In recent years, artificial intelligence (AI) and machine learning (ML) technologies, relying on the development of different types of neural networks and machine learning algorithms, have been widely applied in various fields such as image, speech, and video processing. Typical neural network architectures include fully connected networks, convolutional neural networks (CNNs), recurrent neural networks (RNNs), and Transformer structures with self-attention mechanisms, which can accomplish different task objectives.

[0067] The rapid development of AI / ML technologies and the integration of artificial intelligence with wireless communication technologies have attracted widespread interest from both academia and industry. In the 18th and 19th releases (R18 and R19) of the 3rd Generation Partnership Project (3GPP), research, evaluation, and standardization work has been carried out on AI / ML-based Channel State Information (CSI) feedback, beam management, and positioning technologies. Furthermore, for the future development of wireless communication systems, the integration of AI / ML technologies may lead to more use cases for wireless AI / ML. For example, AI / ML-based channel estimation methods, AI / ML-based modulation and demodulation techniques, and AI / ML-based integrated receiver designs all demonstrate performance gains compared to traditional non-AI / ML algorithms. Therefore, the design of future 6th generation (6G) wireless communication systems may incorporate more AI / ML modules to enhance the overall system performance.

[0068] Specifically, for modulation and demodulation technologies, an AI-based constellation design method can be used to obtain the optimal constellation pattern and matching AI demodulation algorithm by optimizing the bit error rate performance of the link end-to-end. Constellation points designed based on A1 can achieve better performance than traditional regular constellation points in link performance indicators such as bit error rate, block error rate, and throughput, becoming a potential use case for combining 6G wireless communication systems with AI.

[0069] III. Zodiac Point Design in NR

[0070] In NR constellation design, the primary approach is to use constellation points based on regular mapping. For example, QPSK constellation points are evenly distributed on a unit circle, and all constellation points for QAM modulation schemes such as 16QAM, 64QAM, and 256QAM are arranged in a regular rectangular constellation pattern, as shown in Figure 1. This regular constellation point design facilitates standardization and simplifies the modulation algorithms for the transmitter and the demodulation algorithms for the receiver. Furthermore, regular constellation points facilitate the evolution from low-order to high-order modulation. For instance, when the system demands higher speeds, the introduction of 512QAM, 1024QAM, etc., allows for direct expansion based on QAM design rules, demonstrating good scalability.

[0071] However, fixed constellation points cannot be adapted to different channel conditions, such as different signal-to-noise ratios or different channel frequency-domain time selectivity. NR constellation points remain unchanged, which results in low design flexibility and may not achieve optimal performance in terms of bit error rate, block error rate, and throughput.

[0072] IV. AI-based constellation point design

[0073] The constellation point distribution patterns designed based on AI are irregular. Different equipment manufacturers and terminal manufacturers may design completely different constellation points based on different AI models and algorithms, making it difficult to standardize constellation point patterns.

[0074] Furthermore, constellation patterns may vary depending on channel and environmental characteristics. Different cells have different channel environments. Therefore, to obtain constellation patterns and matching demodulation models that are adapted to different channel and environmental characteristics, the network side and / or user side need to collect data to train the constellation patterns (or modulation models) and matching demodulation models.

[0075] The communication method described in this application can be used for training and data collection of modulation and / or demodulation models.

[0076] Figure 3 is a schematic flowchart of a communication method 300 according to an embodiment of this application. This method 300 can optionally be applied to the system shown in Figure 1, but is not limited thereto. The method includes at least a portion of the following:

[0077] S310. The first communication device receives or transmits a reference signal, which is used to acquire training information, and the training information is used to train the constellation point correlation scheme.

[0078] In this embodiment, constellation point correlation schemes can be trained on a first communication device or a second communication device. In some examples, the first communication device is a terminal device and the second communication device is a network device. If the first communication device receives a reference signal sent by the second communication device, it can collect training information based on the reference signal. Then, the constellation point correlation scheme can be trained on the first communication device; alternatively, the collected training information can be sent to the second communication device for training on the second communication device. If the first communication device sends a reference signal to the second communication device, the second communication device can collect training information based on the reference signal. Then, the second communication device can train the constellation point correlation scheme on the second communication device; alternatively, the collected training information can be sent to the first communication device for training on the first communication device.

[0079] In one implementation, the constellation points include irregular constellation points. Irregular constellation points can be constellation points generated based on artificial intelligence solutions. For example, irregular constellation points can be constellation points generated based on AI models and / or ML models. Alternatively, irregular constellation points can also be constellation points generated by adjusting the positions of regular constellation points (e.g., 16QAM, 64QAM, etc.) according to certain principles. In this embodiment, the model used to generate irregular constellation points can be deployed on a first communication device or a second communication device. If the model is deployed on the first communication device, the first communication device can send the constellation point information generated by the model to the second communication device. If the model is deployed on the second communication device, the second communication device can send the constellation point information generated by the model to the first communication device.

[0080] In one implementation, the constellation point correlation scheme includes a first scheme and / or a second scheme, wherein the first scheme is related to constellation point modulation and the second scheme is related to constellation point demodulation.

[0081] In the embodiments of this application, the first solution may include one or more of a first model, a first function, and a first feature. The first model, first function, and first feature may be a first AI and / or a first machine learning (ML) model. The first model may include a constellation point modulation model. The first function may include a constellation point modulation function. The first feature may include a constellation point modulation characteristic. For example, the first model may be an AI and / or ML-based constellation point modulation model. The first function may be an AI and / or ML-based constellation point modulation function. The first feature may be an AI and / or ML-based constellation point modulation characteristic.

[0082] In the embodiments of this application, the second solution may include one or more of a second model, a second function, and a second characteristic. One or more of the second model, second function, and second characteristic may be a second AI and / or a second ML model. The second model includes a constellation point demodulation model. The second function includes a constellation point demodulation function. The second characteristic includes a constellation point demodulation feature. For example, the second model may be an AI and / or ML-based constellation point demodulation model. The second function may be an AI and / or ML-based constellation point demodulation function. The second characteristic may be an AI and / or ML-based constellation point demodulation feature.

[0083] Figure 4 is a schematic flowchart of a communication method according to another embodiment of this application. The method 400 may include one or more features of the communication method described above.

[0084] In one embodiment, the method further includes: S410, the first communication device sends capability information, which includes the first communication device's ability to collect data. In this embodiment, the first communication device may send capability information to a second communication device. For example, a terminal device may report its ability to collect training information to a network device. The training information may include data used to train a constellation point correlation scheme.

[0085] In one implementation, during downlink transmission, the capability information reported by the first communication device to the second communication device includes one or more of the following:

[0086] The ability to support channel measurement and / or reporting on a maximum number of ports on a single downlink CC and / or BWP;

[0087] The ability to support channel measurement and / or reporting for a maximum duration on a downlink CC and / or BWP;

[0088] It also supports the ability to perform channel measurements and / or reporting for a second number of downlink CCs and / or BWPs.

[0089] In one embodiment, the method further includes: S420, the first communication device receives configuration information, the configuration information including reference signal resources configured based on the capability information.

[0090] In one implementation, the reference signal resource is used to receive or transmit the reference signal. In this embodiment, the first communication device can receive configuration information, such as RRC configuration information, sent by the second communication device. The reference signal resource may include downlink reference signal resources and / or uplink reference signal resources. For example, in downlink transmission, after receiving capability information reported by the terminal device, the network device can configure downlink reference signal resources for the terminal device based on the capability information. The terminal device can receive the reference signal based on the downlink reference signal resources. Similarly, in uplink transmission, after receiving capability information reported by the terminal device, the network device can configure uplink reference signal resources for the terminal device based on the capability information. The terminal device can transmit the reference signal based on the uplink reference signal resources.

[0091] In one implementation, in step S310, the first communication device receives a reference signal, including step S430, where the first communication device receives a downlink reference signal. For example, in downlink transmission, the terminal device can receive a downlink reference signal sent by the network device based on the downlink reference signal resources configured by the network device.

[0092] In one embodiment, the reference signal resources for carrying downlink reference signals include reference signal resources on one or more downlink carrier units (CCs) and / or downlink bandwidth parts (BWPs).

[0093] In the embodiments of this application, the first quantity, first duration, and second quantity are capability parameters reported by the first communication device. For example, a first quantity of 32 in the capability information reported by the first communication device can mean that the first communication device supports a maximum of 32 port channel measurements and reports on a downlink CC / downlink BWP. Similarly, the first duration can include the number of time slots for channel measurement and reporting; a first duration of 5 in the capability information reported by the first communication device can mean that the first communication device supports a maximum of 5 time slots for channel measurement and reporting on a downlink CC / downlink BWP. Furthermore, a second quantity of 8 in the capability information reported by the first communication device can mean that the first communication device simultaneously supports channel measurement and reporting on 8 downlink CC / BWPs.

[0094] In one implementation, the training information includes one or more of the following:

[0095] The downlink channel measurement sample is obtained by the first communication device based on the downlink reference signal;

[0096] Measure auxiliary information related to the sample;

[0097] Identification information for the dataset.

[0098] In this embodiment, the first communication device can obtain a measurement sample of the downlink channel based on the downlink reference signal received from the second communication device. For example, during downlink transmission, the terminal device can obtain the downlink channel measurement sample by measuring the received downlink reference signal on one or more of the downlink CC, downlink BWP, or port configured by the RRC. Then, the first communication device can use the downlink channel measurement sample to train a constellation point correlation scheme. The first communication device can also report training information including the downlink channel measurement sample to the second communication device, so that the second communication device can train the constellation point correlation scheme.

[0099] In this embodiment, the first communication device can report training information, including auxiliary information related to measurement samples, to the second communication device. The auxiliary information related to measurement samples can be used to describe and indicate the dataset required for training, as well as relevant information and features of the dataset acquisition process.

[0100] In one implementation, the auxiliary information associated with the measurement sample includes one or more of the following:

[0101] Information related to the region and / or location where the data was acquired;

[0102] Relevant information about the first communication device;

[0103] Data type association information;

[0104] Channel quality characteristics information.

[0105] In the embodiments of this application, the area and / or location of data acquisition can be used to describe the area and / or location where the terminal device acquires training information. For example, different cells, different sectors within a cell, different scenes within a cell (outdoor, indoor), etc.

[0106] In this embodiment, the relevant information of the first communication device can be used to describe auxiliary information describing the state of a terminal device, such as a UE. Examples include UE movement speed, UE geographic location information, and UE attitude information.

[0107] In the embodiments of this application, data type association information can be used to describe the data type. For example, it indicates whether the downlink channel being measured and reported is a frequency domain time domain channel, an angle domain delay domain channel, or a channel feature vector, etc.

[0108] In the embodiments of this application, channel quality characteristic information can be used to describe relevant measurement information describing downlink channel quality. For example, Channel Quality Indicator (CQI), Signal Noise Ratio (SNR), Signal to Interference plus Noise Ratio (SINR), Reference Signal Received Power (RSRP), etc.

[0109] In this embodiment, the first communication device can report training information, including the identification information of the dataset, to the second communication device. After receiving the identification information of the dataset, the second communication device can find the corresponding dataset based on the identification information and use the dataset to train the constellation point correlation scheme.

[0110] In one implementation, the identification information of the dataset includes one or more of the following:

[0111] Dataset identifier (ID) is used to associate a set of measurement samples and / or related auxiliary information of a group of channels;

[0112] Measurement Resource ID, used to associate a set of measurement resources and / or channel measurement samples.

[0113] For example, in downlink transmission, a Dataset ID can be used to associate a set of downlink channel measurement samples reported by the UE with related auxiliary information. Similarly, in downlink transmission, a Resource ID can be used to associate a set of configured downlink measurement resources with the downlink channel measurement samples reported by the UE on those downlink measurement resources.

[0114] In one implementation, the method further includes:

[0115] S440. The first communication device receives a second scheme, which includes one or more of a second model, a second function, and a second characteristic, wherein the second model includes a constellation point demodulation model, the second function includes a constellation point demodulation function, and the second characteristic includes a constellation point demodulation characteristic.

[0116] In this embodiment, if a first scheme and a second scheme are obtained by training a constellation point correlation scheme on a second communication device, the second communication device can send the second scheme to the first communication device during downlink transmission. The second communication device can use the first scheme to perform constellation point modulation, mapping the bit sequence to irregular constellation points, and send the irregular constellation points to the first communication device. The first communication device can demodulate the irregular constellation points based on the second scheme to obtain the log-likelihood ratio (LLR) of the corresponding bit positions on the irregular constellation points.

[0117] Figure 5 is a schematic flowchart of a communication method according to another embodiment of this application. The method 500 may include one or more features of the communication method described above. In one embodiment, the method further includes: S510, a first communication device transmits capability information, the capability information including the first communication device's ability to collect data. This step can be referred to in the relevant description of S410.

[0118] In one implementation, the capability information includes one or more of the following:

[0119] The ability to support up to a third number of ports for transmitting reference signals for data collection on an uplink CC and / or uplink BWP;

[0120] The ability to support the transmission of a reference signal for data collection for a maximum duration on an uplink CC and / or uplink BWP;

[0121] It also supports the ability to transmit reference signals for data collection on a fourth number of uplink CCs and / or uplink BWPs.

[0122] In one embodiment, the method further includes: S520, the first communication device receives configuration information, the configuration information including reference signal resources configured based on the capability information. This step can be referred to the relevant description of S420. In uplink transmission, the configuration information includes uplink reference signal resources configured based on the capability information.

[0123] In one implementation, in S310, the first communication device transmits a reference signal, including in S530, the first communication device transmits an uplink reference signal. For example, in uplink transmission, the terminal device can transmit an uplink reference signal, such as a sounding reference signal (SRS), to the network device based on the uplink reference signal resources configured by the network device.

[0124] In one implementation, the reference signal resources used to carry the uplink reference signal include reference signal resources on one or more uplink CCs and / or uplink BWPs. For example, the first communication device transmits the uplink reference signal resources on the configured port of the uplink CC / uplink BWP configured by the RRC.

[0125] In the embodiments of this application, the third quantity, second duration, and fourth quantity are capability parameters reported by the first communication device. For example, a third quantity of 8 in the capability information reported by the first communication device can mean that the first communication device supports the transmission of reference signals for data collection on a maximum of 8 ports on one uplink CC / uplink BWP. Similarly, the second duration can include the number of time slots for channel measurement and reporting; a second duration of 5 in the capability information reported by the first communication device can mean that the first communication device supports a maximum of 5 time slots for transmitting reference signals for data collection on one uplink CC / uplink BWP. Furthermore, a fourth quantity of 8 in the capability information reported by the first communication device can mean that the first communication device simultaneously supports the transmission of reference signals for data collection on 8 uplink CC / BWPs.

[0126] In one implementation, the training information includes one or more of the following:

[0127] The uplink channel measurement sample is obtained by the second communication device based on the uplink reference signal;

[0128] Measure auxiliary information related to the sample;

[0129] Identification information for the dataset.

[0130] In this embodiment, the second communication device can obtain uplink channel measurement samples based on uplink reference signals received from the first communication device. For example, during uplink transmission, the terminal device can obtain uplink channel measurement samples by measuring the received uplink reference signals on one or more of the uplink CC, uplink BWP, or port. Then, the second communication device can use the uplink channel measurement samples to train a constellation point correlation scheme. Alternatively, the second communication device can report training information including the uplink channel measurement samples to the first communication device, allowing the first communication device to train the constellation point correlation scheme.

[0131] In one implementation, the auxiliary information associated with the measurement sample includes one or more of the following:

[0132] Information related to the region and / or location of the data acquisition; information related to the first communication device; data type association information; channel quality characteristic information.

[0133] In this embodiment, the auxiliary information related to the uplink transmission measurement samples reported by the first communication device to the second communication device may be similar to the auxiliary information related to the downlink transmission measurement samples, as detailed in the descriptions of the above embodiments. A network device, such as a base station, can obtain uplink channel measurement samples through SRS measurements. The base station can also bind data type association information and channel quality characteristic information from the auxiliary information related to the measurement samples to the uplink channel measurement samples. The area and / or location-related information of the data acquisition, as well as the relevant information of the first communication device, such as the UE, can be indicated by the first communication device to the second communication device.

[0134] In one implementation, the identification information of the dataset includes one or more of the following:

[0135] Dataset ID, used to associate a set of channel measurement samples and / or related auxiliary information;

[0136] Measurement Resource ID, used to associate a set of measurement resources and / or channel measurement samples.

[0137] For example, in uplink transmission, a Dataset ID can be used to associate a set of uplink channel measurement samples and related auxiliary information. Similarly, in uplink transmission, a Resource ID can be used to associate a set of uplink measurement resources and / or uplink channel measurement samples. The uplink Dataset ID and Resource ID can be associated by the UE and indicated to the base station, or the base station can associate them.

[0138] In one embodiment, the method further includes: S540, the first communication device receives a first scheme, the first scheme including one or more of a first model, a first function, and a first characteristic, wherein the first model includes a constellation point modulation model, the first function includes a constellation point modulation function, and the first characteristic includes a constellation point modulation characteristic.

[0139] In this embodiment, if a first scheme and a second scheme are obtained by training a constellation point correlation scheme on a second communication device, the second communication device can send the first scheme to the first communication device during uplink transmission. The first communication device can use the first scheme to perform constellation point modulation, mapping the bit sequence to irregular constellation points, and send the irregular constellation points to the second communication device. The second communication device can demodulate the irregular constellation points based on the second scheme to obtain the log-likelihood ratio (LLR) of the corresponding bit positions on the irregular constellation points.

[0140] Figure 6 is a schematic flowchart of a communication method according to another embodiment of this application. The method 600 may include one or more features of the above-described communication method. In one embodiment, the method further includes:

[0141] S610, The first communication device trains the constellation point correlation scheme based on the training information.

[0142] In downlink transmission, the first communication device can obtain measurement samples of the downlink channel based on the downlink reference signal. The first communication device can then train a constellation point correlation scheme based on training information, including these downlink channel measurement samples. In uplink transmission, the second communication device can obtain measurement samples of the uplink channel based on the downlink reference signal and send these uplink channel measurement samples to the first communication device. The first communication device can then train a constellation point correlation scheme based on this uplink channel measurement samples and other training information.

[0143] In one implementation, the capability information reported by the first communication device further includes model training capability. For example, the UE may have local model training capability, such as the ability to transmit collected data to the UE side or the UE manufacturer's server for model training. If the capability information reported by the first communication device supports model training capability, the first communication device can continue to execute subsequent processes such as receiving configuration information, receiving or transmitting reference signals, and training. For example, after steps S410, S420, and S430, step S610 can be executed. Similarly, after steps S510, S520, and S530, step S610 can be executed. Furthermore, if the capability information reported by the first communication device does not support model training capability, subsequent processes will not continue.

[0144] In one implementation, step S610, where the first communication device trains the constellation point correlation scheme based on the training information, includes:

[0145] The first input information is input into the first scheme to be trained, and the first output information is output. The first input information includes a bit sequence, and the first output information includes modulated constellation points.

[0146] After resource mapping and channel model transmission of the first output information, channel estimation and equalization are performed to obtain the received symbol. The channel model is constructed based on the training information.

[0147] The second input information is input into the second scheme to be trained to output the second output information, the second input information including the received symbol, and the second output information including the log-likelihood ratio (LLR) sequence;

[0148] The loss function constructed based on the first input information and the second output information is used to adjust the first scheme and / or the second scheme to obtain the trained first scheme and / or second scheme.

[0149] In the embodiments of this application, the channel model can be a downlink channel model in downlink transmission. In uplink transmission, the channel model can be an uplink channel model. The following description uses a first scheme as the first model and a second scheme as the second model as examples.

[0150] The model training process for downlink transmission can include: inputting a bit sequence as the first input information into a first model (e.g., a constellation point modulation model) to be trained, and using the output modulated constellation points as the first output information. After resource mapping and downlink channel model transmission of the first output information, channel estimation and equalization are performed to obtain the received symbols. Then, inputting a bit sequence as the second input information into a second model (e.g., a constellation point demodulation model), and using the output LLR sequence as the second output information. Based on the loss function constructed from the first input information and the second output information, adjusting the first model and / or the second model to obtain the trained first model and / or the second model. After training, the first model can be deployed on the second communication device side, and the second model can be deployed on the first communication device side.

[0151] The model training process for uplink transmission may include: inputting a bit sequence as the first input information into a first model to be trained, and using the output modulated constellation points as the first output information. After resource mapping and uplink channel model transmission of the first output information, channel estimation and equalization are performed to obtain the received symbols. Then, inputting a bit sequence as the second input information into a second model to be trained, and using the output LLR sequence as the second output information. Based on the loss function constructed from the first input information and the second output information, the first model and / or the second model are adjusted to obtain the trained first model and / or the second model. After training, the first model can be deployed on the first communication device side, and the second model can be deployed on the second communication device side.

[0152] There are various types of loss functions, such as cross-entropy loss, MSE loss, and similarity loss. The length of the first input information is variable, and the order of the first scheme can be preset.

[0153] In one embodiment, the first communication device trains the constellation point correlation scheme based on the training information, and further includes using channel quality feature information as third input information for the first scheme and / or the second scheme.

[0154] For example, the first and third input information are input together into a first scheme to be trained to output the first output information. After resource mapping and channel model transmission of the first output information, channel estimation and equalization are performed to obtain the received symbols. Then, the received symbols are used as the second and third input information to input together into a second scheme to be trained to output the second output information. Based on the loss function constructed from the first and second input information, the first and / or second schemes are adjusted to obtain the trained first and / or second schemes.

[0155] In one implementation, the method for establishing the channel model includes one or more of the following:

[0156] A channel model is established based on the noise characteristics of the channel, and the channel quality characteristic information is used as the noise reference range during the training process of the first scheme and / or the second scheme.

[0157] A channel model is established based on complete channel characteristics, and the first scheme and / or the second scheme are trained using measurement samples of the downlink channel.

[0158] A channel model is established based on complete channel characteristics, and the first scheme and / or the second scheme are trained using uplink channel measurement samples.

[0159] In the first method, if the channel model is built solely based on the noise characteristics of the channel, these noise characteristics do not depend on specific channel features, such as AWGN or colored noise at different frequencies. In this case, the channel quality feature information from the first information report can be incorporated into the model training as a reference range for noise during the training process.

[0160] In the second method, a channel model can be established based on complete channel characteristics. For downlink transmission, downlink channel measurement samples (or downlink channel data samples) from the first information reporting can be used for training. For uplink transmission, uplink channel measurement samples (or uplink channel data samples) can be used for training. Furthermore, certain channel estimation and equalization methods, such as minimum mean square estimation (MMSE) channel estimation and equalization, and least squares channel estimation and equalization, can be used for end-to-end training.

[0161] In one embodiment, the method further includes: the first communication device transmitting a first scheme, the first scheme including one or more of a first model, a first function, and a first characteristic, wherein the first model includes a constellation point modulation model, the first function includes a constellation point modulation function, and the first characteristic includes a constellation point modulation characteristic.

[0162] In this embodiment, if a first scheme and a second scheme are obtained by training a constellation point correlation scheme on the first communication device, during downlink transmission, after S610, the first communication device can send the first scheme to the second communication device. The second communication device can use the first scheme to perform constellation point modulation, mapping the bit sequence to irregular constellation points, and send the irregular constellation points to the first communication device. The first communication device can demodulate the irregular constellation points based on the second scheme to obtain the log-likelihood ratio (LLR) of the corresponding bit positions on the irregular constellation points.

[0163] In one embodiment, the method further includes: the first communication device transmitting a second scheme, the second scheme including one or more of a second model, a second function, and a second characteristic, wherein the second model includes a constellation point demodulation model, the second function includes a constellation point demodulation function, and the second characteristic includes a constellation point demodulation characteristic.

[0164] In this embodiment, if a first scheme and a second scheme are obtained by training a constellation point correlation scheme on the first communication device, during uplink transmission, after S610, the first communication device can send the second scheme to the second communication device. The first communication device can use the first scheme to perform constellation point modulation, mapping the bit sequence to irregular constellation points, and send the irregular constellation points to the second communication device. The second communication device can demodulate the irregular constellation points based on the second scheme to obtain the log-likelihood ratio (LLR) of the corresponding bit positions on the irregular constellation points.

[0165] Figure 7 is a schematic flowchart of a communication method according to an embodiment of this application. This method 700 can optionally be applied to the system shown in Figure 1, but is not limited thereto. The method includes at least a portion of the following:

[0166] S710, the second communication device sends or receives a reference signal, which is used to acquire training information, and the training information is used to train the constellation point related scheme.

[0167] In one implementation, the constellation point correlation scheme includes a first scheme and / or a second scheme, wherein the first scheme is related to constellation point modulation and the second scheme is related to constellation point demodulation.

[0168] Figure 8 is a schematic flowchart of a communication method according to another embodiment of this application. The method 800 may include one or more features of the above-described communication method. In one embodiment, the method further includes: S810, the second communication device receives capability information, the capability information including the first communication device's ability to collect data.

[0169] In one embodiment, the method further includes: S820, the second communication device sends configuration information, the configuration information including reference signal resources configured based on the capability information, the reference signal resources being used to receive or transmit the reference signal.

[0170] In one embodiment, the second communication device transmits a reference signal, including: S830, the second communication device transmits a downlink reference signal.

[0171] In one embodiment, the reference signal resources for carrying downlink reference signals include reference signal resources on one or more downlink carrier units (CC) and / or downlink bandwidth portions (BWP).

[0172] In one implementation, the training information includes one or more of the following:

[0173] The downlink channel measurement sample, obtained by the first communication device based on the downlink reference signal; auxiliary information related to the measurement sample;

[0174] Identification information for the dataset.

[0175] In one implementation, the capability information includes one or more of the following:

[0176] The ability to support channel measurement and / or reporting on a maximum number of ports on a single downlink CC and / or BWP;

[0177] The ability to support channel measurement and / or reporting for a maximum duration on a downlink CC and / or BWP;

[0178] It also supports the ability to perform channel measurements and / or reporting for a second number of downlink CCs and / or BWPs.

[0179] In one embodiment, the method further includes: S840, the second communication device transmits a second scheme, the second scheme including one or more of a second model, a second function, and a second characteristic, wherein the second model includes a constellation point demodulation model, the second function includes a constellation point demodulation function, and the second characteristic includes a constellation point demodulation characteristic.

[0180] Figure 9 is a schematic flowchart of a communication method according to another embodiment of this application. The method 900 may include one or more features of the communication method described above. In one embodiment, the method further includes: S910, the second communication device receives capability information, the capability information including the data collection capabilities of the first communication device.

[0181] In one embodiment, the method further includes: S920, the second communication device sends configuration information, the configuration information including reference signal resources configured based on the capability information, the reference signal resources being used to receive or transmit the reference signal.

[0182] In one embodiment, the second communication device receives a reference signal, including: S930, the second communication device receives an uplink reference signal.

[0183] In one implementation, the reference signal resources for carrying uplink reference signals include reference signal resources on one or more uplink CCs and / or uplink BWPs.

[0184] In one implementation, the training information includes one or more of the following:

[0185] The uplink channel measurement sample is obtained by the second communication device based on the uplink reference signal;

[0186] Measure auxiliary information related to the sample;

[0187] Identification information for the dataset.

[0188] In one implementation, the capability information includes one or more of the following:

[0189] The ability to support up to a third number of ports for transmitting reference signals for data collection on an uplink CC and / or uplink BWP;

[0190] The ability to support the transmission of a reference signal for data collection for a maximum duration on an uplink CC and / or uplink BWP;

[0191] It also supports the ability to transmit reference signals for data collection on a fourth number of uplink CCs and / or uplink BWPs.

[0192] In one embodiment, the method further includes: S940, the second communication device transmits a first scheme, the first scheme including one or more of a first model, a first function, and a first characteristic, wherein the first model includes a constellation point modulation model, the first function includes a constellation point modulation function, and the first characteristic includes a constellation point modulation characteristic.

[0193] In one implementation, the auxiliary information associated with the measurement sample includes one or more of the following:

[0194] Information related to the region and / or location of the data acquisition; information related to the first communication device; data type association information; channel quality characteristic information.

[0195] In one implementation, the identification information of the dataset includes one or more of the following:

[0196] Dataset ID, used to associate a set of channel measurement samples and / or related auxiliary information;

[0197] Measurement Resource ID, used to associate a set of measurement resources and / or channel measurement samples.

[0198] Figure 10 is a schematic flowchart of a communication method according to another embodiment of this application. The method may include one or more features of the above-described communication method. In one embodiment, the method further includes:

[0199] S1010 The second communication device trains the constellation point correlation scheme based on the training information.

[0200] In this embodiment, the capability information reported by the first communication device received by the second communication device may further include: model training capability. If the capability information reported by the first communication device supports model training capability, the second communication device can continue to execute subsequent processes such as sending configuration information, receiving or sending reference signals, and training. The model training process can be performed at the base station, on a server on the network side, on other network elements in the core network, or on other network-side entity units. For example, after steps S810, S820, and S830, S1010 can be executed, followed by S840. Similarly, after steps S910, S920, and S930, S1010 can be executed, followed by S940. Furthermore, if the capability information reported by the first communication device does not support model training capability, the second communication device will not continue to execute subsequent processes.

[0201] In one implementation, the second communication device trains the constellation point correlation scheme based on the training information, including:

[0202] The first input information is input into the first scheme to be trained, and the first output information is output. The first input information includes a bit sequence, and the first output information includes modulated constellation points.

[0203] After resource mapping and channel model transmission of the first output information, channel estimation and equalization are performed to obtain the received symbol. The channel model is constructed based on the training information.

[0204] The second input information is input into the second scheme to be trained, and the second output information is output. The second input information includes the received symbol, and the second output information includes the LLR sequence.

[0205] The loss function constructed based on the first input information and the second output information is used to adjust the first scheme and / or the second scheme to obtain the trained first scheme and / or second scheme.

[0206] In one embodiment, the second communication device trains the constellation point correlation scheme based on the training information, and further includes:

[0207] Channel quality characteristic information is used as the third input information for the first scheme and / or the second scheme.

[0208] In one implementation, the method for establishing the channel model includes one or more of the following:

[0209] A channel model is established based on the noise characteristics of the channel, and the channel quality characteristic information is used as the noise reference range during the training process of the first scheme and / or the second scheme.

[0210] A channel model is established based on complete channel characteristics, and the first scheme and / or the second scheme are trained using measurement samples of the downlink channel.

[0211] A channel model is established based on complete channel characteristics, and the first scheme and / or the second scheme are trained using uplink channel measurement samples.

[0212] In one embodiment, if the first communication device trains the constellation point correlation scheme, the method further includes: the second communication device receiving a first scheme, the first scheme including one or more of a first model, a first function, and a first characteristic, wherein the first model includes a constellation point modulation model, the first function includes a constellation point modulation function, and the first characteristic includes a constellation point modulation characteristic. In downlink transmission, if the first communication device trains and obtains a first scheme and a second scheme, after steps S810, S820, and S830, the second communication device can receive the first scheme sent by the first communication device.

[0213] In one embodiment, if the first communication device trains the constellation point correlation scheme, the method further includes: the second communication device receiving a second scheme, the second scheme including one or more of a second model, a second function, and a second characteristic, wherein the second model includes a constellation point demodulation model, the second function includes a constellation point demodulation function, and the second characteristic includes a constellation point demodulation characteristic. In uplink transmission, if the first communication device trains and obtains both the first and second schemes, after steps S910, S920, and S930, the second communication device can receive the second scheme sent by the first communication device.

[0214] Specific examples of the second communication device executing methods 700 to 1000 in this embodiment can be found in the relevant descriptions of the second communication device in methods 300 to 600 above, which will not be repeated here for the sake of brevity.

[0215] The communication method in this application includes a network-side or user-side data collection and model training method. Through terminal capability reporting, RRC configuration, information indication and reporting processes, and possible model transmission processes, the network side and / or the user side can respectively deploy a first and / or a second model / function / feature to realize AI / ML-based modulation and demodulation functions and enhance downlink and uplink performance.

[0216] Example 1: A method for network-side data collection and model training

[0217] Sub-example 1.1: Downlink Example

[0218] This embodiment provides a method for data collection and model training on the network side. The constellation points (or modulation model) and demodulation model trained by this method can be used for downlink transmission. Specifically, the process shown in Figure 11 may include one or more of the following steps:

[0219] S1101. Terminal Capability Reporting. Different user terminals (hereinafter referred to as users or terminals), such as UEs, have different data collection capabilities. Therefore, UEs need to report their ability to collect data for the network. This capability includes, but is not limited to, one or more of the following:

[0220] (1) The maximum number of ports that can be supported for channel measurement and reporting on a single downlink CC / BWP. For example, if the UE reports this capability parameter as 32, it means that the UE can support a maximum of 32 ports for channel measurement and reporting on a single downlink CC / BWP.

[0221] (2) The maximum duration of channel measurement and reporting capability supported on a downlink CC / BWP. For example, this duration can be the number of time slots for channel measurement and reporting. If the UE reports this capability parameter as 10, it means that the UE can support a maximum of 10 time slots for channel measurement and reporting on a downlink CC / BWP.

[0222] (3) The ability to simultaneously support channel measurement and reporting on how many downlink CC / BWPs. For example, if the UE reports this capability parameter as 16, it means that the UE simultaneously supports channel measurement and reporting on 16 downlink CC / BWPs.

[0223] S1102, RRC Configuration Information. Based on the relevant capabilities reported by the UE, the network configures one or more measurement resources and reporting resources on the downlink CC / BWP for the UE. The number of configured measurement resources and reporting resources shall not exceed the corresponding capability parameters reported by the UE.

[0224] S1103. The network sends a downlink reference signal to the user side. This downlink reference signal can be transmitted on the RRC configuration resources in step S1102, that is, on the configured downlink CC / BWP and on the configured port. Examples of this downlink reference signal may include CSI-RS, in which case step S1103 can reuse the relevant CSI-RS configuration and transmission methods, without needing to be specifically designed for this embodiment. Alternatively, it can be a downlink reference signal specifically used for downlink channel measurement and data collection in this embodiment.

[0225] S1104. The user reports first information to the base station, which includes at least one or more of the following:

[0226] (1) Measurement sample of downlink channel: The measurement sample of downlink channel is obtained by measuring the downlink reference signal in step S1103 on the port configured on the downlink CC / BWP configured by the UE in the RRC.

[0227] (2) Auxiliary information related to the measurement samples: relevant information and characteristics used to describe and indicate the dataset and the dataset acquisition process, which may include, but are not limited to, one or more of the following:

[0228] a) Data acquisition area and location information: This describes the area and location where the UE acquires data. For example, different cells (identified by cell ID or Physical Cell Identifier (PCI), different sectors within a cell, or different scenarios within a cell (outdoor, indoor), etc.

[0229] b) User-related information: auxiliary information used to describe the state of the UE, such as user movement speed, user geographical location information, user posture information, etc.

[0230] c) Data type association information: used to describe the data type. For example, it indicates whether the downlink channel being measured and reported is a frequency domain / time domain channel, an angle domain / delay domain channel, or a channel feature vector, etc.

[0231] d) Channel quality characteristics: Relevant measurement information used to describe downlink channel quality. Examples include CQI, SNR, SINR, and RSRP.

[0232] (3) Dataset identification information: Optional, the UE also reports the representation information of the data set. It can be in the form of Dataset ID, which is used to associate a group of downlink channel measurement samples and related auxiliary information reported by the UE; or it can be a measurement resource ID, which is used to associate a group of configured downlink measurement resources and the downlink channel measurement samples reported by the UE on that resource.

[0233] The first information report in step S1104 can be based on a single transmission and bearer method. For example, it can be carried by physical layer signaling such as Uplink Control Information (UCI) and reported through the Physical Uplink Control Channel (PUCCH) or the Physical Uplink Shared Channel (PUSCH); it can also be uplink messages during random access procedures, such as MsgA and Msg3; it can be based on higher-layer signaling, such as Minimization of Drive Test (MDT); or it can be based on other dedicated uplink channels used for AI / ML data collection. This first information report can also be based on a combination of the above signaling. For example, downlink channel measurement samples, which have a large data volume, can be carried using MDT; other parts, such as auxiliary information and dataset identification information, have lower overhead and can be carried through physical layer signaling.

[0234] S1105. The network trains a model based on the first information reported by the UE. This model training requires obtaining one or more of a first model, a first function, or a first feature (which can be referred to as the first model / function / feature), and one or more of a second model, a second function, or a second feature (which can be referred to as the second model / function / feature), as shown in Figure 12:

[0235] The first model / function / feature performs modulation, taking the bit sequence as the first input information and outputting the modulated constellation points as the first output information. After resource mapping and downlink channel transmission, the received symbols are obtained at the receiving end through channel estimation and equalization modules. This downlink channel can be obtained through modeling, the modeling method of which is described in detail below. The estimated received symbols are used as the second input information, and processed by the second model / function / feature to output the LLR sequence as the second output information. This second model / function / feature performs demodulation. Optionally, the first model / function / feature and / or the second model / function / feature can both use information characterizing channel quality (e.g., CQI, SNR, SINR, RSRP, or noise power) as the third input information, enabling the first model / function / feature and / or the second model / function / feature to adapt to different channel qualities. After training, the first model / function / feature can be deployed on the network side, and the second model / function / feature can be deployed on the user side.

[0236] In this training process, a bit sequence of a certain length is randomly generated as the first input information. A loss function is established between the first input information and the second output information, and this loss function is optimized to complete the model training. As an example, the cross-entropy loss function is primarily considered. Optionally, loss functions such as MSE and similarity loss functions can also be used.

[0237] The length of the first input information is variable, and the order of the first model / function / feature is preset. Specifically, if the preset first model / function / feature performs M-order modulation, then the trainable parameters of the first model / function / feature are 2. M The real and imaginary parts of the constellation points (considering that AI / ML models generally use real parameters, there are a total of 2...) M+1 (2 trainable real parameters), or amplitude and phase values ​​(2 in total). M+1 (Number of trainable real parameters). Correspondingly, the second model / function / feature performs M-order demodulation. Both the first and second models / functions / features can be adapted to first input information sequences of different lengths, and the models (including model framework, model structure, etc.) can adopt any implementation method that satisfies the above description.

[0238] The model training process can be performed at the base station, on a network-side server, on other network elements in the core network, or on other network-side entities. Based on Figure 12, it is necessary to model the impact of the channel and channel estimation equalization during the training process, including two modeling methods:

[0239] The first method models only the noise impact of the channel, which is independent of specific channel characteristics, such as AWGN or colored noise at different frequencies. In this case, model training only needs to incorporate the channel quality feature information from the first information report as a reference range for noise during training.

[0240] The second method involves modeling complete channel characteristics, which requires incorporating downlink channel data samples from the first information report into the training. Simultaneously, certain channel estimation and equalization methods can be employed, such as MMSE channel estimation and equalization, least squares channel estimation and equalization, etc., to participate in end-to-end training.

[0241] S1106. The network transmits a second model / function / feature to the UE, enabling the UE to perform demodulation and downlink data reception based on the second model / function / feature. Step S1106 is optional; that is, the model transmission process is not mandatory. If the UE does not receive the second model / function / feature transmitted by the network, the UE can obtain the corresponding second model / function / feature locally based on its implementation. This model transmission can be based on physical layer signaling, such as transmission over the PDCCH via DCI; it can be transmitted via RRC configuration; it can also be based on higher-layer signaling, such as MDT; or it can be transmitted via other dedicated model transmission signaling and channels. Additionally, this second model / function / feature transmission can transmit model-related indication information, such as the model ID or associated ID, used to indicate additional condition information associated with the model or base station. For example, a set of associated IDs may include the modulation order M corresponding to the model, whether the training includes third input information, or some information related to base station configuration (such as base station identifier, base station port configuration, etc.).

[0242] Sub-example 1.2: Uplink Example

[0243] This embodiment provides a method for data collection and model training on the network side. The constellation points (or modulation model) and demodulation model obtained by this method can be used for uplink transmission. Specifically, the process shown in Figure 13 may include one or more of the following steps:

[0244] S1301. Terminal Capability Reporting. Different UEs have different capabilities for data collection from the auxiliary network. Therefore, the UE needs to report the auxiliary network's data collection capabilities. These capabilities include, but are not limited to, one or more of the following:

[0245] (1) The maximum number of ports that can be used to transmit reference signals for data collection on an uplink CC / BWP. For example, if the UE reports this capability parameter as 4, it means that the UE can support a maximum of 4 ports for transmitting reference signals for data collection on an uplink CC / BWP;

[0246] (2) The maximum duration of data collection reference signal transmission supported on an uplink CC / BWP. For example, this duration can be the number of time slots for data collection reference signal transmission. If the UE reports this capability parameter as 10, it means that the UE can support a maximum of 10 time slots for data collection reference signal transmission on an uplink CC / BWP.

[0247] (3) The ability to simultaneously support the number of uplink CC / BWPs for transmitting data collection reference signals. For example, if the UE reports this capability parameter as 16, it means that the UE simultaneously supports 16 uplink CC / BWPs for transmitting data collection reference signals.

[0248] S1302, RRC Configuration Information. Based on the relevant capabilities reported by the UE, the network configures one or more reference signal resources on the uplink CC / BWP for the UE. The number of reference signal resources configured shall not exceed the corresponding capability parameters reported by the UE.

[0249] S1303: The user sends an uplink reference signal and a second information report to the network. This uplink reference signal is transmitted on the RRC configuration resources in step S1302, specifically on the configured uplink CC / BWP and on the configured port. Examples of this uplink reference signal may include SRS, in which case step S1303 can reuse the relevant SRS configuration and transmission methods, without needing to be specifically designed for this embodiment; or it may be an uplink reference signal specifically used for uplink channel measurement and data collection in this embodiment.

[0250] The second piece of information to be reported may optionally include one or more of the following:

[0251] (1) Auxiliary information related to the measurement sample: relevant information and characteristics used to describe and indicate the reference signal transmission and data acquisition process, which may include, but are not limited to, the following:

[0252] a) Data acquisition area, location and other related information: used to describe the area and location of the UE transmitting reference signals, such as different cells (identified by cell ID, or PCI, etc.), different sectors within the cell, or different scenarios within the cell (outdoor, indoor, etc.);

[0253] b) User-related information: auxiliary information used to describe the state of the UE, such as user movement speed, user geographical location information, user posture information, etc.

[0254] (2) Dataset identification information: Optionally, it can be in the form of a Dataset ID, used to associate a set of uplink channel measurement samples and related auxiliary information; or it can be a Measurement Resource ID, used to associate a set of configured uplink measurement resources and the uplink channel measurement samples of that resource. The uplink Dataset ID and Measurement Resource ID can be associated by the UE and indicated to the base station, or the base station can associate them.

[0255] S1304, Model Training. The model training process is similar to that of the downlink embodiment 1.1, except that the second method for channel modeling uses uplink channel samples obtained from uplink reference signal measurements, which will not be described in detail here.

[0256] S1305. The network transmits a first model / function / feature to the UE, enabling the UE to perform modulation and uplink data transmission based on the first model / function / feature. This step S1305 is optional; the model transmission process is not mandatory. If the UE does not receive the first model / function / feature transmitted by the network, the UE can obtain the corresponding first model / function / feature locally. This model transmission can be based on physical layer signaling, such as transmission over the PDCCH via DCI; it can be transmitted via RRC configuration; it can also be based on higher-layer signaling, such as MDT; or it can be transmitted via other dedicated model transmission signaling and channels. Additionally, the first model / function / feature transmission can transmit model-related indication information, such as the model ID or associated ID, similar to the above sub-implementation, and will not be repeated here.

[0257] Based on the method and process of this embodiment, the network side can complete data collection and model training, enabling the network and UE to obtain the first and second models / functions / features respectively, realize AI / ML-based modulation and demodulation, and enhance the performance of downlink and uplink bit error rate, block error rate and throughput.

[0258] Example 2: A method for user-side data collection and model training

[0259] Sub-example 2.1: Downlink Example

[0260] This embodiment provides a method for data collection and model training on the user side. The constellation points (or modulation model) and demodulation model obtained by this method can be used for downlink transmission. Specifically, the process shown in Figure 14 may include one or more of the following steps:

[0261] S1401. Terminal Capability Reporting. Different UEs have different capabilities in data collection and model training; therefore, UEs need to report their data collection and model training capabilities. These capabilities include, but are not limited to, one or more of the following:

[0262] (1) Model training capability, which refers to the UE's local ability to train models, or the UE's ability to transmit collected data to the UE side or the UE manufacturer's server for model training. If this capability is not included in the UE capability report, the subsequent processes in this embodiment are not supported.

[0263] (2) The maximum number of ports that can be used for channel measurement on a single downlink CC / BWP. For example, if the UE reports this capability parameter as 32, it means that the UE can support a maximum of 32 ports for channel measurement on a single downlink CC / BWP.

[0264] (3) The maximum duration of channel measurement capability supported on a downlink CC / BWP. For example, this duration can be the number of time slots for channel measurement. If the UE reports this capability parameter as 10, it means that the UE can support a maximum of 10 time slots for channel measurement on a downlink CC / BWP.

[0265] (4) The ability to simultaneously support channel measurements on a number of downlink CC / BWPs. For example, if the UE reports this capability parameter as 16, it means that the UE simultaneously supports channel measurements on 16 downlink CC / BWPs.

[0266] S1402, RRC configuration information: Based on the relevant capabilities reported by the UE, the network configures one or more measurement resources on the downlink CC / BWP for the UE. The number of configured measurement resources shall not exceed the corresponding capability parameters reported by the UE.

[0267] S1403. The network sends a downlink reference signal to the user side, which is the same as the downlink sub-implementation in Embodiment 1, and will not be described again.

[0268] S1404 The model training is completed by the UE local, the UE side, or the UE manufacturer's server. The model training process is the same as the downlink sub-implementation of Implementation Example 1, and will not be described again here.

[0269] S1405. The UE transmits a first model / function / feature to the network, which allows the network to perform modulation based on the first model / function / feature. This step S1405 is optional; that is, the model transmission process is not mandatory. If the UE does not send the first model / function / feature to the network, the network can obtain the corresponding first model / function / feature locally. This model transmission can be based on physical layer signaling, such as transmission via UCI carried on PUCCH or PUSCH, or uplink messages during random access procedures, such as MsgA and Msg3; it can also be based on higher layer signaling, such as MDT; or other dedicated uplink channels for AI / ML model transmission. The first model / function / feature transmission may additionally transmit model-related indication information, such as the model ID or associated ID. Unlike the sub-implementation described above, the associated ID here indicates additional condition information associated with the model or the UE. For example, a set of associated IDs may include the modulation order M corresponding to the model, whether the training includes third input information, UE measurement data, the UE's current state, or some communication related to UE configuration. Optionally, this additional condition information includes, but is not limited to, one or more of the following:

[0270] (1) Auxiliary information related to the measurement sample: relevant information and characteristics used to describe and indicate the dataset and the dataset acquisition process, which may include, but are not limited to, the following:

[0271] a) Data acquisition area, location and other related information: used to describe the area and location where the UE acquires data, such as different cells (identified by cell ID, or PCI, etc.), different sectors within a cell, or different scenarios within a cell (outdoor, indoor, etc.);

[0272] b) User-related information: auxiliary information used to describe the state of the UE, such as user movement speed, user geographical location information, user posture information, etc.

[0273] c) Data type association information: used to describe the data type, for example, indicating whether the downlink channel being measured and reported is a frequency domain time domain channel, an angle domain time delay domain channel, or a channel feature vector, etc.

[0274] d) Channel quality characteristic information: Relevant measurement information used to describe downlink channel quality, such as CQI, SNR, SINR, RSRP, etc.

[0275] (2) Identification information of dataset: Optionally, the UE may also report the identification information of the dataset used for model training. It may be in the form of dataset ID, which is used to associate a set of downlink channel measurement samples and related auxiliary information measured by the UE; or measurement resource ID, which is used to associate a set of configured downlink measurement resources.

[0276] Sub-example 2.2: Uplink Example

[0277] This embodiment provides a method for data collection and model training on the UE side. The constellation points (or modulation model) and demodulation model obtained by this method can be used for uplink transmission. Specifically, the process shown in Figure 15 may include one or more of the following steps:

[0278] S1501. Terminal Capability Reporting. Different UEs have different capabilities in data collection and model training; therefore, UEs need to report their data collection and model training capabilities. These capabilities include, but are not limited to, one or more of the following:

[0279] (1) Model training capability, which refers to the UE's ability to receive datasets sent by the network side and the ability to train models, or the UE's ability to transmit collected data to the UE side or the UE manufacturer's server for model training. If this capability is not included in the UE capability report, the subsequent processes in this embodiment are not supported.

[0280] (2) The maximum number of ports that can be supported for transmitting reference signals for data collection on an uplink CC / BWP. For example, if the UE reports this capability parameter as 4, it means that the UE can support the transmission of reference signals for data collection on a maximum of 4 ports on an uplink CC / BWP.

[0281] (3) The maximum duration of the ability to transmit reference signals for data collection on an uplink CC / BWP. For example, the duration can be the number of time slots for transmitting reference signals for data collection. If the UE reports this capability parameter as 10, it means that the UE can support a maximum of 10 time slots for transmitting reference signals for data collection on an uplink CC / BWP.

[0282] (4) The ability to support the number of uplink CC / BWPs for data collection at the same time. For example, if the UE reports this capability parameter as 16, it means that the UE supports the data collection of uplink CC / BWPs at the same time.

[0283] S1502, RRC configuration information: Based on the relevant capabilities reported by the UE, the network configures one or more reference signal resources on the uplink CC / BWP for the UE. The number of reference signal resources configured shall not exceed the corresponding capability parameters reported by the UE.

[0284] S1503. The user sends an uplink reference signal to the network. This uplink reference signal is transmitted on the RRC configuration resources in step S1502, that is, on the configured uplink CC / BWP and on the configured port. This uplink reference signal can refer to SRS. In this case, step S1503 can reuse the relevant SRS configuration and transmission methods, and does not need to be specially designed for this embodiment; or it can be an uplink reference signal specifically used for uplink channel measurement and data collection in this embodiment.

[0285] S1504, Third Information Indication, which includes at least uplink channel samples obtained from network measurements. This set of uplink channel samples may be obtained based on the user's uplink reference signal, or based on the uplink reference signals of all users under the user's vendor, or based on the uplink reference signals of all users within the cell.

[0286] The model training is completed by the S1505, the UE local machine, the UE side, or the UE manufacturer's server. The model training process is the same as the aforementioned process and will not be repeated here.

[0287] S1506, the UE transmits a second model / function / feature to the network, so that the network side can complete demodulation and uplink data reception based on the second model / function / feature. This step S1506 is optional; that is, the model transmission process is not mandatory. If the network does not receive the second model / function / feature transmitted by the UE, the network side can obtain the corresponding second model / function / feature locally based on its implementation. The model transmission and additional model-related indication information and additional condition information are the same as in sub-example 2.1 and will not be repeated here.

[0288] Based on the method and process of this embodiment, the UE side can complete data collection and model training, enabling the network and UE to obtain the first and second models / functions / features respectively, realize AI / ML-based modulation and demodulation, and enhance the performance of downlink and uplink bit error rate, block error rate and throughput.

[0289] In this embodiment of the application, by implementing data collection and model training on the network side and the UE side, the network and the UE can respectively obtain the first and second models / functions / characteristics, realize AI / ML-based modulation and demodulation, and enhance the performance of downlink and uplink bit error rate, block error rate and throughput.

[0290] Figure 16 is a schematic block diagram of a first communication device 1600 according to an embodiment of the present application. The first communication device 1600 may include:

[0291] The transceiver unit 1610 is used to receive or transmit a reference signal, which is used to acquire training information, and the training information is used to train a constellation point correlation scheme.

[0292] In one implementation, the constellation point correlation scheme includes a first scheme and / or a second scheme, wherein the first scheme is related to constellation point modulation and the second scheme is related to constellation point demodulation.

[0293] In one embodiment, the transceiver unit 1610 is also used to transmit capability information, which includes the first communication device's ability to collect data.

[0294] In one embodiment, the transceiver unit 1610 is further configured to receive configuration information, which includes reference signal resources configured based on the capability information, and the reference signal resources are used to receive or transmit the reference signal.

[0295] In one embodiment, the transceiver unit 1610 is also used to receive downlink reference signals.

[0296] In one embodiment, the reference signal resources for carrying downlink reference signals include reference signal resources on one or more downlink carrier units (CC) and / or downlink bandwidth portions (BWP).

[0297] In one implementation, the training information includes one or more of the following:

[0298] The downlink channel measurement sample is obtained by the first communication device based on the downlink reference signal;

[0299] Measure auxiliary information related to the sample;

[0300] Identification information for the dataset.

[0301] In one implementation, the capability information includes one or more of the following:

[0302] The ability to support channel measurement and / or reporting on a maximum number of ports on a single downlink CC and / or BWP;

[0303] The ability to support channel measurement and / or reporting for a maximum duration on a downlink CC and / or BWP;

[0304] It also supports the ability to perform channel measurements and / or reporting for a second number of downlink CCs and / or BWPs.

[0305] In one embodiment, the transceiver unit 1610 is further configured to receive a second scheme, the second scheme including one or more of a second model, a second function, and a second characteristic, wherein the second model includes a constellation point demodulation model, the second function includes a constellation point demodulation function, and the second characteristic includes a constellation point demodulation characteristic.

[0306] In one embodiment, the transceiver unit 1610 is also used to transmit an uplink reference signal.

[0307] In one implementation, the reference signal resources for carrying uplink reference signals include reference signal resources on one or more uplink CCs and / or uplink BWPs.

[0308] In one implementation, the training information includes one or more of the following:

[0309] The uplink channel measurement sample is obtained by the second communication device based on the uplink reference signal;

[0310] Measure auxiliary information related to the sample;

[0311] Identification information for the dataset.

[0312] In one implementation, the capability information includes one or more of the following:

[0313] The ability to support up to a third number of ports for transmitting reference signals for data collection on an uplink CC and / or uplink BWP;

[0314] The ability to support the transmission of a reference signal for data collection for a maximum duration on an uplink CC and / or uplink BWP;

[0315] It also supports the ability to transmit reference signals for data collection on a fourth number of uplink CCs and / or uplink BWPs.

[0316] In one embodiment, the transceiver unit 1610 is further configured to receive a first scheme, the first scheme including one or more of a first model, a first function, and a first characteristic, wherein the first model includes a constellation point modulation model, the first function includes a constellation point modulation function, and the first characteristic includes a constellation point modulation characteristic.

[0317] In one implementation, the auxiliary information associated with the measurement sample includes one or more of the following:

[0318] Information related to the region and / or location where the data was acquired;

[0319] Relevant information about the first communication device;

[0320] Data type association information;

[0321] Channel quality characteristics information.

[0322] In one implementation, the identification information of the dataset includes one or more of the following:

[0323] Dataset identifier (ID) is used to associate a set of measurement samples and / or related auxiliary information for a group of channels;

[0324] Measurement Resource ID, used to associate a set of measurement resources and / or channel measurement samples.

[0325] Figure 17 is a schematic block diagram of a first communication device 1700 according to another embodiment of this application. The first communication device may include one or more features of the first communication device described above. In one embodiment, the first communication device further includes:

[0326] The processing unit 1710 is used to train the constellation point correlation scheme based on the training information.

[0327] In one embodiment, the processing unit 1710 is further configured to:

[0328] The first input information is input into the first scheme to be trained, and the first output information is output. The first input information includes a bit sequence, and the first output information includes modulated constellation points.

[0329] After resource mapping and channel model transmission of the first output information, channel estimation and equalization are performed to obtain the received symbol. The channel model is constructed based on the training information.

[0330] The second input information is input into the second scheme to be trained to output the second output information, the second input information including the received symbol, and the second output information including the log-likelihood ratio (LLR) sequence;

[0331] The loss function constructed based on the first input information and the second output information is used to adjust the first scheme and / or the second scheme to obtain the trained first scheme and / or second scheme.

[0332] In one embodiment, the processing unit 1710 is further configured to use channel quality feature information as third input information for the first scheme and / or the second scheme.

[0333] In one implementation, the method for establishing the channel model includes one or more of the following:

[0334] A channel model is established based on the noise characteristics of the channel, and the channel quality characteristic information is used as the noise reference range during the training process of the first scheme and / or the second scheme.

[0335] A channel model is established based on complete channel characteristics, and the first scheme and / or the second scheme are trained using measurement samples of the downlink channel.

[0336] A channel model is established based on complete channel characteristics, and the first scheme and / or the second scheme are trained using uplink channel measurement samples.

[0337] In one embodiment, the transceiver unit 1610 is further configured to transmit a first scheme, the first scheme including one or more of a first model, a first function, and a first characteristic, wherein the first model includes a constellation point modulation model, the first function includes a constellation point modulation function, and the first characteristic includes a constellation point modulation characteristic.

[0338] In one embodiment, the transceiver unit 1610 is further configured to transmit a second scheme, the second scheme including one or more of a second model, a second function, and a second characteristic, wherein the second model includes a constellation point demodulation model, the second function includes a constellation point demodulation function, and the second characteristic includes a constellation point demodulation characteristic.

[0339] The first communication devices 1600 and 1700 in this application embodiment can realize the corresponding functions of the first communication devices in the aforementioned method embodiments. The processes, functions, implementation methods, and beneficial effects of each module (sub-module, unit, or component, etc.) in the first communication devices 1600 and 1700 can be found in the corresponding descriptions in the above method embodiments, and will not be repeated here. It should be noted that the functions described for each module (sub-module, unit, or component, etc.) in the first communication devices 1600 and 1700 in the application embodiments can be implemented by different modules (sub-modules, units, or components, etc.) or by the same module (sub-module, unit, or component, etc.).

[0340] Figure 18 is a schematic block diagram of a second communication device 1800 according to an embodiment of the present application. The second communication device 1800 may include:

[0341] The transceiver unit 1810 is used to send or receive a reference signal, which is used to acquire training information, and the training information is used to train a constellation point correlation scheme.

[0342] In one implementation, the constellation point correlation scheme includes a first scheme and / or a second scheme, wherein the first scheme is related to constellation point modulation and the second scheme is related to constellation point demodulation.

[0343] In one embodiment, the transceiver unit 1810 is further configured to receive capability information, which includes the capability of the first communication device to collect data.

[0344] In one embodiment, the transceiver unit 1810 is further configured to transmit configuration information, which includes reference signal resources configured based on the capability information, and the reference signal resources are used to receive or transmit the reference signal.

[0345] In one embodiment, the transceiver unit 1810 is also used to transmit a downlink reference signal.

[0346] In one embodiment, the reference signal resources for carrying downlink reference signals include reference signal resources on one or more downlink carrier units (CC) and / or downlink bandwidth portions (BWP).

[0347] In one implementation, the training information includes one or more of the following:

[0348] The downlink channel measurement sample is obtained by the first communication device based on the downlink reference signal;

[0349] Measure auxiliary information related to the sample;

[0350] Identification information for the dataset.

[0351] In one implementation, the capability information includes one or more of the following:

[0352] The ability to support channel measurement and / or reporting on a maximum number of ports on a single downlink CC and / or BWP;

[0353] The ability to support channel measurement and / or reporting for a maximum duration on a downlink CC and / or BWP;

[0354] It also supports the ability to perform channel measurements and / or reporting for a second number of downlink CCs and / or BWPs.

[0355] In one embodiment, the transceiver unit 1810 is further configured to transmit a second scheme, the second scheme including one or more of a second model, a second function, and a second characteristic, wherein the second model includes a constellation point demodulation model, the second function includes a constellation point demodulation function, and the second characteristic includes a constellation point demodulation characteristic.

[0356] In one embodiment, the transceiver unit 1810 is also used to receive an uplink reference signal.

[0357] In one implementation, the reference signal resources for carrying uplink reference signals include reference signal resources on one or more uplink CCs and / or uplink BWPs.

[0358] In one implementation, the training information includes one or more of the following:

[0359] The uplink channel measurement sample is obtained by the second communication device based on the uplink reference signal;

[0360] Measure auxiliary information related to the sample;

[0361] Identification information for the dataset.

[0362] In one implementation, the capability information includes one or more of the following:

[0363] The ability to support up to a third number of ports for transmitting reference signals for data collection on an uplink CC and / or uplink BWP;

[0364] The ability to support the transmission of a reference signal for data collection for a maximum duration on an uplink CC and / or uplink BWP;

[0365] It also supports the ability to transmit reference signals for data collection on a fourth number of uplink CCs and / or uplink BWPs.

[0366] In one embodiment, the transceiver unit 1810 is further configured to transmit a first scheme, the first scheme including one or more of a first model, a first function, and a first characteristic, wherein the first model includes a constellation point modulation model, the first function includes a constellation point modulation function, and the first characteristic includes a constellation point modulation characteristic.

[0367] In one implementation, the auxiliary information associated with the measurement sample includes one or more of the following:

[0368] Information related to the region and / or location where the data was acquired;

[0369] Relevant information about the first communication device;

[0370] Data type association information;

[0371] Channel quality characteristics information.

[0372] In one implementation, the identification information of the dataset includes one or more of the following:

[0373] Dataset identifier (ID) is used to associate a set of measurement samples and / or related auxiliary information for a group of channels;

[0374] Measurement Resource ID, used to associate a set of measurement resources and / or channel measurement samples.

[0375] Figure 19 is a schematic block diagram of a second communication device 1900 according to another embodiment of this application. The second communication device may include one or more features of the second communication device described above. In one embodiment, the second communication device further includes:

[0376] The processing unit 1910 is used for the second communication device to train the constellation point correlation scheme based on the training information.

[0377] In one embodiment, the processing unit 1910 is used to:

[0378] The first input information is input into the first scheme to be trained, and the first output information is output. The first input information includes a bit sequence, and the first output information includes modulated constellation points.

[0379] After resource mapping and channel model transmission of the first output information, channel estimation and equalization are performed to obtain the received symbol. The channel model is constructed based on the training information.

[0380] The second input information is input into the second scheme to be trained to output the second output information, the second input information including the received symbol, and the second output information including the log-likelihood ratio (LLR) sequence;

[0381] The loss function constructed based on the first input information and the second output information is used to adjust the first scheme and / or the second scheme to obtain the trained first scheme and / or second scheme.

[0382] In one embodiment, the processing unit is further configured to use channel quality feature information as third input information for the first scheme and / or the second scheme.

[0383] In one implementation, the method for establishing the channel model includes one or more of the following:

[0384] A channel model is established based on the noise characteristics of the channel, and the channel quality characteristic information is used as the noise reference range during the training process of the first scheme and / or the second scheme.

[0385] A channel model is established based on complete channel characteristics, and the first scheme and / or the second scheme are trained using measurement samples of the downlink channel.

[0386] A channel model is established based on complete channel characteristics, and the first scheme and / or the second scheme are trained using uplink channel measurement samples.

[0387] In one embodiment, the transceiver unit 1810 is further configured to receive a first scheme, the first scheme including one or more of a first model, a first function, and a first characteristic, wherein the first model includes a constellation point modulation model, the first function includes a constellation point modulation function, and the first characteristic includes a constellation point modulation characteristic.

[0388] In one embodiment, the transceiver unit 1810 is further configured to receive a second scheme, the second scheme including one or more of a second model, a second function, and a second characteristic, wherein the second model includes a constellation point demodulation model, the second function includes a constellation point demodulation function, and the second characteristic includes a constellation point demodulation characteristic.

[0389] The second communication devices 1800 and 1900 in this application embodiment can realize the corresponding functions of the second communication devices in the aforementioned method embodiments. The processes, functions, implementation methods, and beneficial effects of each module (sub-module, unit, or component, etc.) in the second communication devices 1800 and 1900 can be found in the corresponding descriptions in the above method embodiments, and will not be repeated here. It should be noted that the functions described for each module (sub-module, unit, or component, etc.) in the second communication devices 1800 and 1900 in the application embodiments can be implemented by different modules (sub-modules, units, or components, etc.) or by the same module (sub-module, unit, or component, etc.).

[0390] Figure 20 is a schematic structural diagram of a communication device 2000 according to an embodiment of this application. The communication device 2000 includes a processor 2010, which can call and run computer programs from memory to enable the communication device 2000 to implement the methods in the embodiments of this application.

[0391] In one embodiment, the communication device 2000 may further include a memory 2020. The processor 2010 can retrieve and run computer programs from the memory 2020 to enable the communication device 2000 to implement the methods described in the embodiments of this application.

[0392] The memory 2020 can be a separate device independent of the processor 2010, or it can be integrated into the processor 2010.

[0393] In one embodiment, the communication device 2000 may further include a transceiver 2030, which the processor 2010 may control to communicate with other devices. Specifically, it may send information or data to other devices or receive information or data sent by other devices.

[0394] The transceiver 2030 may include a transmitter and a receiver. The transceiver 2030 may further include an antenna, and the number of antennas may be one or more.

[0395] In one embodiment, the communication device 2000 may be the first communication device in the embodiments of this application, and the communication device 2000 may implement the corresponding processes implemented by the first communication device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0396] In one embodiment, the communication device 2000 may be the second communication device in the embodiments of this application, and the communication device 2000 may implement the corresponding processes implemented by the second communication device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0397] Figure 21 is a schematic structural diagram of a chip 2100 according to an embodiment of this application. The chip 2100 includes a processor 2110, which can call and run computer programs from memory to implement the methods in the embodiments of this application.

[0398] In one embodiment, chip 2100 may further include memory 2120. Processor 2110 can retrieve and run computer programs from memory 2120 to implement the methods executed by a terminal device or network device in this embodiment.

[0399] The memory 2120 can be a separate device independent of the processor 2110, or it can be integrated into the processor 2110.

[0400] In one embodiment, the chip 2100 may further include an input interface 2130. The processor 2110 can control the input interface 2130 to communicate with other devices or chips; specifically, it can acquire information or data sent by other devices or chips.

[0401] In one embodiment, the chip 2100 may further include an output interface 2140. The processor 2110 can control the output interface 2140 to communicate with other devices or chips; specifically, it can output information or data to other devices or chips.

[0402] In one implementation, the chip can be applied to the first communication device in the embodiments of this application, and the chip can implement the corresponding processes implemented by the first communication device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0403] In one implementation, the chip can be applied to the second communication device in the embodiments of this application, and the chip can implement the corresponding processes implemented by the second communication device in the various methods of the embodiments of this application. For the sake of brevity, it will not be described in detail here.

[0404] The chips used in the first communication device and the second communication device can be the same chip or different chips.

[0405] It should be understood that the chip mentioned in the embodiments of this application may also be referred to as a system-on-a-chip, system chip, chip system, or system-on-a-chip, etc.

[0406] The processors mentioned above can be general-purpose processors, digital signal processors (DSPs), field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), or other programmable logic devices, transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processors mentioned above can be microprocessors or any conventional processor.

[0407] The aforementioned memory can be volatile memory or non-volatile memory, or a combination of both. 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).

[0408] It should be understood that the above-described memory is exemplary and not a limiting description. For example, the memory in the embodiments of this application may also be 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 link dynamic random access memory (SLDRAM), and direct memory bus RAM (DR RAM), etc. That is to say, the memory in the embodiments of this application is intended to include, but is not limited to, these and any other suitable types of memory.

[0409] Figure 22 is a schematic block diagram of a communication system 2200 according to an embodiment of the present application. The communication system 2200 includes a first communication device 2210 and a second communication device 2220.

[0410] The first communication device 2210 is used to receive or transmit a reference signal, which is used to acquire training information, and the training information is used to train a constellation point correlation scheme.

[0411] The second communication device 2220 is used to send or receive reference signals.

[0412] The first communication device 2210 can be used to implement the corresponding functions implemented by the first communication device in the above method, and the second communication device 2220 can be used to implement the corresponding functions implemented by the first communication device in the above method. For the sake of brevity, further details are omitted here.

[0413] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented in software, it can be implemented, in whole or in part, as a computer program product. This computer program product includes one or more computer instructions. When these computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device such as a server or data center that integrates one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives (SSDs)).

[0414] It should be understood that 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.

[0415] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0416] 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 method of communication, comprising: The first communication device receives or transmits a reference signal, which is used to acquire training information, and the training information is used to train constellation point related schemes.

2. The method of claim 1, wherein, The constellation point related scheme includes a first scheme and / or a second scheme, wherein the first scheme is related to constellation point modulation and the second scheme is related to constellation point demodulation.

3. The method of claim 1 or 2, wherein, The method further includes: The first communication device sends capability information, which includes the first communication device's ability to collect data.

4. The method of claim 3, wherein, The method further includes: The first communication device receives configuration information, which includes reference signal resources configured based on the capability information. The reference signal resources are used to receive or transmit the reference signal.

5. The method of claim 4, wherein, The first communication device receives a reference signal, including: the first communication device receives a downlink reference signal.

6. The method of claim 5, wherein, Reference signal resources used to carry downlink reference signals include reference signal resources on one or more downlink carrier units (CC) and / or downlink bandwidth portions (BWP).

7. The method of claim 5 or 6, wherein, The training information includes one or more of the following: The downlink channel measurement sample is obtained by the first communication device based on the downlink reference signal; Measure auxiliary information related to the sample; Identification information for the dataset.

8. The method of any one of claims 5-7, wherein, The capability information includes one or more of the following: The ability to support channel measurement and / or reporting on a maximum number of ports on a single downlink CC and / or BWP; The ability to support channel measurement and / or reporting for a maximum duration on a downlink CC and / or BWP; It also supports the ability to perform channel measurements and / or reporting for a second number of downlink CCs and / or BWPs.

9. The method of any one of claims 5-8, wherein, The method further includes: the first communication device receiving a second scheme, the second scheme including one or more of a second model, a second function, and a second characteristic, wherein the second model includes a constellation point demodulation model, the second function includes a constellation point demodulation function, and the second characteristic includes a constellation point demodulation characteristic.

10. The method of claim 4, wherein, The first communication device transmits a reference signal, including: The first communication device sends an uplink reference signal.

11. The method of claim 10, wherein, Reference signal resources used to carry uplink reference signals include reference signal resources on one or more uplink CCs and / or uplink BWPs.

12. The method of claim 10 or 11, wherein, The training information includes one or more of the following: The uplink channel measurement sample is obtained by the second communication device based on the uplink reference signal; Measure auxiliary information related to the sample; Identification information for the dataset.

13. The method of any one of claims 10 to 12, wherein, The capability information includes one or more of the following: The ability to support up to a third number of ports for transmitting reference signals for data collection on an uplink CC and / or uplink BWP; The ability to support the transmission of a reference signal for data collection for a maximum duration on an uplink CC and / or uplink BWP; It also supports the ability to transmit reference signals for data collection on a fourth number of uplink CCs and / or uplink BWPs.

14. The method of any one of claims 10 to 13, wherein, The method further includes: the first communication device receiving a first scheme, the first scheme including one or more of a first model, a first function, and a first characteristic, wherein the first model includes a constellation point modulation model, the first function includes a constellation point modulation function, and the first characteristic includes a constellation point modulation characteristic.

15. The method of claim 7 or 12, wherein, The auxiliary information related to the measurement sample includes one or more of the following: Information related to the region and / or location where the data was acquired; Relevant information about the first communication device; Data type association information; Channel quality characteristics information.

16. The method of claim 7, 12, or 15, wherein, The identification information of the dataset includes one or more of the following: Dataset identifier (ID) is used to associate a set of measurement samples and / or related auxiliary information for a group of channels; Measurement Resource ID, used to associate a set of measurement resources and / or channel measurement samples.

17. The method of any one of claims 1 to 16, wherein, The method further includes: the first communication device training the constellation point correlation scheme based on the training information.

18. The method of claim 17, wherein, The first communication device trains the constellation point correlation scheme based on the training information, including: The first input information is input into the first scheme to be trained, and the first output information is output. The first input information includes a bit sequence, and the first output information includes modulated constellation points. After resource mapping and channel model transmission of the first output information, channel estimation and equalization are performed to obtain the received symbol. The channel model is constructed based on the training information. The second input information is input into the second scheme to be trained, and the second output information is output. The second input information includes the received symbol, and the second output information includes the log-likelihood ratio (LLR) sequence. Based on the loss function constructed from the first input information and the second output information, the first scheme and / or the second scheme are adjusted to obtain the trained first scheme and / or the second scheme.

19. The method of claim 18, wherein, The first communication device trains the constellation point correlation scheme based on the training information, and further includes: using channel quality feature information as third input information for the first scheme and / or the second scheme.

20. The method of claim 18 or 19, wherein, The methods for establishing the channel model include one or more of the following: A channel model is established based on the noise characteristics of the channel, and the channel quality characteristic information is used as the reference range of noise during the training process of the first scheme and / or the second scheme. A channel model is established based on complete channel characteristics, and the first scheme and / or the second scheme are trained using measurement samples of the downlink channel. A channel model is established based on complete channel characteristics, and the first scheme and / or the second scheme are trained using uplink channel measurement samples.

21. The method of any one of claims 17-20, wherein, The method further includes: the first communication device transmitting a first scheme, the first scheme including one or more of a first model, a first function, and a first characteristic, wherein the first model includes a constellation point modulation model, the first function includes a constellation point modulation function, and the first characteristic includes a constellation point modulation characteristic.

22. The method of any one of claims 17-20, wherein, The method further includes: the first communication device sending a second scheme, the second scheme including one or more of a second model, a second function, and a second characteristic, wherein the second model includes a constellation point demodulation model, the second function includes a constellation point demodulation function, and the second characteristic includes a constellation point demodulation characteristic.

23. A method of communication, comprising: The second communication device sends or receives reference signals, which are used to acquire training information, and the training information is used to train constellation point related schemes.

24. The method of claim 23, wherein, The constellation point related scheme includes a first scheme and / or a second scheme, wherein the first scheme is related to constellation point modulation and the second scheme is related to constellation point demodulation.

25. The method of claim 23 or 24, wherein, The method further includes: the second communication device receiving capability information, the capability information including the first communication device's ability to collect data.

26. The method of claim 25, wherein, The method further includes: the second communication device sending configuration information, the configuration information including reference signal resources configured based on the capability information, the reference signal resources being used to receive or send the reference signal.

27. The method of claim 26, wherein, The second communication device transmits a reference signal, including: the second communication device transmits a downlink reference signal.

28. The method of claim 27, wherein, Reference signal resources used to carry downlink reference signals include reference signal resources on one or more downlink CCs and / or downlink BWPs.

29. The method of claim 27 or 28, wherein, The training information includes one or more of the following: The downlink channel measurement sample is obtained by the first communication device based on the downlink reference signal; Measure auxiliary information related to the sample; Identification information for the dataset.

30. The method of any one of claims 27-29, wherein, The capability information includes one or more of the following: The ability to support channel measurement and / or reporting on a maximum number of ports on a single downlink CC and / or BWP; The ability to support channel measurement and / or reporting for a maximum duration on a downlink CC and / or BWP; It also supports the ability to perform channel measurements and / or reporting for a second number of downlink CCs and / or BWPs.

31. The method of any one of claims 27-30, wherein, The method further includes: the second communication device sending a second scheme, the second scheme including one or more of a second model, a second function, and a second characteristic, wherein the second model includes a constellation point demodulation model, the second function includes a constellation point demodulation function, and the second characteristic includes a constellation point demodulation characteristic.

32. The method of claim 26, wherein, The second communication device receives a reference signal, including: the second communication device receives an uplink reference signal.

33. The method of claim 32, wherein, Reference signal resources used to carry uplink reference signals include reference signal resources on one or more uplink CCs and / or uplink BWPs.

34. The method of claim 32 or 33, wherein, The training information includes one or more of the following: The uplink channel measurement sample is obtained by the second communication device based on the uplink reference signal; Measure auxiliary information related to the sample; Identification information for the dataset.

35. The method of any one of claims 32 to 34, wherein, The capability information includes one or more of the following: The ability to support up to a third number of ports for transmitting reference signals for data collection on an uplink CC and / or uplink BWP; The ability to support the transmission of a reference signal for data collection for a maximum duration on an uplink CC and / or uplink BWP; It also supports the ability to transmit reference signals for data collection on a fourth number of uplink CCs and / or uplink BWPs.

36. The method of any one of claims 32 to 35, wherein, The method further includes: the second communication device transmitting a first scheme, the first scheme including one or more of a first model, a first function, and a first characteristic, wherein the first model includes a constellation point modulation model, the first function includes a constellation point modulation function, and the first characteristic includes a constellation point modulation characteristic.

37. The method of claim 29 or 34, wherein, The auxiliary information related to the measurement sample includes one or more of the following: Information related to the region and / or location where the data was acquired; Relevant information about the first communication device; Data type association information; Channel quality characteristics information.

38. The method of claim 29, 34, or 37, wherein, The identification information of the dataset includes one or more of the following: Dataset identifier (ID) is used to associate a set of measurement samples and / or related auxiliary information for a group of channels; Measurement Resource ID, used to associate a set of measurement resources and / or channel measurement samples.

39. The method of any one of claims 23 to 38, wherein, The method further includes: the second communication device training the constellation point correlation scheme based on the training information.

40. The method of claim 39, wherein, The second communication device trains the constellation point correlation scheme based on the training information, including: The first input information is input into the first scheme to be trained, and the first output information is output. The first input information includes a bit sequence, and the first output information includes modulated constellation points. After resource mapping and channel model transmission of the first output information, channel estimation and equalization are performed to obtain the received symbol. The channel model is constructed based on the training information. The second input information is input into the second scheme to be trained, and the second output information is output. The second input information includes the received symbol, and the second output information includes the LLR sequence. Based on the loss function constructed from the first input information and the second output information, the first scheme and / or the second scheme are adjusted to obtain the trained first scheme and / or the second scheme.

41. The method of claim 40, wherein, The second communication device trains the constellation point correlation scheme based on the training information, and further includes: using channel quality feature information as third input information for the first scheme and / or the second scheme.

42. The method of claim 40 or 41, wherein, The methods for establishing the channel model include one or more of the following: A channel model is established based on the noise characteristics of the channel, and the channel quality characteristic information is used as the reference range of noise during the training process of the first scheme and / or the second scheme. A channel model is established based on complete channel characteristics, and the first scheme and / or the second scheme are trained using measurement samples of the downlink channel. A channel model is established based on complete channel characteristics, and the first scheme and / or the second scheme are trained using uplink channel measurement samples.

43. The method of any one of claims 23 to 38, wherein, The method further includes: the second communication device receiving a first scheme, the first scheme including one or more of a first model, a first function, and a first characteristic, wherein the first model includes a constellation point modulation model, the first function includes a constellation point modulation function, and the first characteristic includes a constellation point modulation characteristic.

44. The method of any one of claims 23 to 38, wherein, The method further includes: the second communication device receiving a second scheme, the second scheme including one or more of a second model, a second function, and a second characteristic, wherein the second model includes a constellation point demodulation model, the second function includes a constellation point demodulation function, and the second characteristic includes a constellation point demodulation characteristic.

45. A first communication device comprising: The transceiver unit is used to receive or send reference signals, which are used to acquire training information, and the training information is used to train constellation point correlation schemes.

46. The first communication device of claim 45, wherein, The constellation point related scheme includes a first scheme and / or a second scheme, wherein the first scheme is related to constellation point modulation and the second scheme is related to constellation point demodulation.

47. A first communications device according to claim 45 or 46, wherein, The transceiver unit is also used to send capability information, which includes the first communication device's ability to collect data.

48. A first communications device according to Claim 47, wherein, The transceiver unit is also used to receive configuration information, which includes reference signal resources configured based on the capability information. The reference signal resources are used to receive or transmit the reference signal.

49. The first communication device of claim 48, wherein, The transceiver unit is also used to receive downlink reference signals.

50. The first communication device of claim 49, wherein, Reference signal resources used to carry downlink reference signals include reference signal resources on one or more downlink carrier units (CC) and / or downlink bandwidth portions (BWP).

51. A first communications device according to claim 49 or 50, wherein, The training information includes one or more of the following: The downlink channel measurement sample is obtained by the first communication device based on the downlink reference signal; Measure auxiliary information related to the sample; Identification information for the dataset.

52. A first communications device according to any one of claims 49 to 51, wherein, The capability information includes one or more of the following: The ability to support channel measurement and / or reporting on a maximum number of ports on a single downlink CC and / or BWP; The ability to support channel measurement and / or reporting for a maximum duration on a downlink CC and / or BWP; It also supports the ability to perform channel measurements and / or reporting for a second number of downlink CCs and / or BWPs.

53. A first communications device according to any one of claims 49 to 52, wherein, The transceiver unit is also used to receive a second scheme, which includes one or more of a second model, a second function, and a second characteristic, wherein the second model includes a constellation point demodulation model, the second function includes a constellation point demodulation function, and the second characteristic includes a constellation point demodulation characteristic.

54. The first communication device of claim 48, wherein, The transceiver unit is also used to send uplink reference signals.

55. A first communications device according to Claim 54, wherein, Reference signal resources used to carry uplink reference signals include reference signal resources on one or more uplink CCs and / or uplink BWPs.

56. A first communications device according to claim 54 or 55, wherein, The training information includes one or more of the following: The uplink channel measurement sample is obtained by the second communication device based on the uplink reference signal; Measure auxiliary information related to the sample; Identification information for the dataset.

57. A first communications device according to any one of claims 54 to 56, wherein, The capability information includes one or more of the following: The ability to support up to a third number of ports for transmitting reference signals for data collection on an uplink CC and / or uplink BWP; The ability to support the transmission of a reference signal for data collection for a maximum duration on an uplink CC and / or uplink BWP; It also supports the ability to transmit reference signals for data collection on a fourth number of uplink CCs and / or uplink BWPs.

58. A first communications device according to any one of claims 54 to 57, wherein, The transceiver unit is further configured to receive a first scheme, the first scheme including one or more of a first model, a first function, and a first characteristic, wherein the first model includes a constellation point modulation model, the first function includes a constellation point modulation function, and the first characteristic includes a constellation point modulation characteristic.

59. The first communication device of claim 51 or 56, wherein, The auxiliary information related to the measurement sample includes one or more of the following: Information related to the region and / or location where the data was acquired; Relevant information about the first communication device; Data type association information; Channel quality characteristics information.

60. The first communication device of claim 51, 56, or 59, wherein, The identification information of the dataset includes one or more of the following: Dataset ID, used to associate a set of channel measurement samples and / or related auxiliary information; Measurement Resource ID, used to associate a set of measurement resources and / or channel measurement samples.

61. A first communications device according to any one of claims 45 to 60, wherein, The first communication device further includes: The processing unit is used to train the constellation point correlation scheme based on the training information.

62. The first communication device of claim 61, wherein, The processing unit is also used for: The first input information is input into the first scheme to be trained, and the first output information is output. The first input information includes a bit sequence, and the first output information includes modulated constellation points. After resource mapping and channel model transmission of the first output information, channel estimation and equalization are performed to obtain the received symbol. The channel model is constructed based on the training information. The second input information is input into the second scheme to be trained, and the second output information is output. The second input information includes the received symbol, and the second output information includes the log-likelihood ratio (LLR) sequence. Based on the loss function constructed from the first input information and the second output information, the first scheme and / or the second scheme are adjusted to obtain the trained first scheme and / or the second scheme.

63. The first communication device of claim 62, wherein, The processing unit is further configured to use channel quality feature information as third input information for the first scheme and / or the second scheme.

64. A first communications device according to claim 62 or 63, wherein, The methods for establishing the channel model include one or more of the following: A channel model is established based on the noise characteristics of the channel, and the channel quality characteristic information is used as the reference range of noise during the training process of the first scheme and / or the second scheme. A channel model is established based on complete channel characteristics, and the first scheme and / or the second scheme are trained using measurement samples of the downlink channel. A channel model is established based on complete channel characteristics, and the first scheme and / or the second scheme are trained using uplink channel measurement samples.

65. A first communications device according to any one of claims 61 to 64, wherein, The transceiver unit is further configured to transmit a first scheme, the first scheme including one or more of a first model, a first function, and a first characteristic, wherein the first model includes a constellation point modulation model, the first function includes a constellation point modulation function, and the first characteristic includes a constellation point modulation characteristic.

66. The first communication device of any one of claims 61 to 64, wherein, The transceiver unit is also used to transmit a second scheme, the second scheme including one or more of a second model, a second function, and a second characteristic, wherein the second model includes a constellation point demodulation model, the second function includes a constellation point demodulation function, and the second characteristic includes a constellation point demodulation characteristic.

67. A second communication device, comprising: The transceiver unit is used to send or receive reference signals, which are used to acquire training information, and the training information is used to train constellation point correlation schemes.

68. The second communication device of claim 67, wherein, The constellation point related scheme includes a first scheme and / or a second scheme, wherein the first scheme is related to constellation point modulation and the second scheme is related to constellation point demodulation.

69. A second communications device according to claim 67 or 68, wherein, The transceiver unit is also used to receive capability information, which includes the first communication device's ability to collect data.

70. A second communications device according to Claim 69, wherein, The transceiver unit is also used to send configuration information, which includes reference signal resources configured based on the capability information. The reference signal resources are used to receive or send the reference signal.

71. The second communication device of claim 70, wherein, The transceiver unit is also used to transmit downlink reference signals.

72. The second communication device of claim 71, wherein, Reference signal resources used to carry downlink reference signals include reference signal resources on one or more downlink carrier units (CC) and / or downlink bandwidth portions (BWP).

73. A second communications device according to claim 71 or 72, wherein, The training information includes one or more of the following: The downlink channel measurement sample is obtained by the first communication device based on the downlink reference signal; Measure auxiliary information related to the sample; Identification information for the dataset.

74. A second communications device according to any one of claims 71 to 73, wherein, The capability information includes one or more of the following: The ability to support channel measurement and / or reporting on a maximum number of ports on a single downlink CC and / or BWP; The ability to support channel measurement and / or reporting for a maximum duration on a downlink CC and / or BWP; It also supports the ability to perform channel measurements and / or reporting for a second number of downlink CCs and / or BWPs.

75. A second communications device according to any one of claims 71 to 74, wherein, The transceiver unit is also used to transmit a second scheme, the second scheme including one or more of a second model, a second function, and a second characteristic, wherein the second model includes a constellation point demodulation model, the second function includes a constellation point demodulation function, and the second characteristic includes a constellation point demodulation characteristic.

76. The second communication device of claim 70, wherein, The transceiver unit is also used to receive uplink reference signals.

77. The second communication device of claim 76, wherein, Reference signal resources used to carry uplink reference signals include reference signal resources on one or more uplink CCs and / or uplink BWPs.

78. A second communications device according to claim 76 or 77, wherein, The training information includes one or more of the following: The uplink channel measurement sample is obtained by the second communication device based on the uplink reference signal; Measure auxiliary information related to the sample; Identification information for the dataset.

79. A second communications device according to any one of claims 76 to 78, wherein, The capability information includes one or more of the following: The ability to support up to a third number of ports for transmitting reference signals for data collection on an uplink CC and / or uplink BWP; The ability to support the transmission of a reference signal for data collection for a maximum duration on an uplink CC and / or uplink BWP; It also supports the ability to transmit reference signals for data collection on a fourth number of uplink CCs and / or uplink BWPs.

80. A second communications device according to any one of claims 76 to 79, wherein, The transceiver unit is further configured to transmit a first scheme, the first scheme including one or more of a first model, a first function, and a first characteristic, wherein the first model includes a constellation point modulation model, the first function includes a constellation point modulation function, and the first characteristic includes a constellation point modulation characteristic.

81. The second communication device of claim 73 or 78, wherein, The auxiliary information related to the measurement sample includes one or more of the following: Information related to the region and / or location where the data was acquired; Relevant information about the first communication device; Data type association information; Channel quality characteristics information.

82. The second communication device of claim 73, 78, or 81, wherein, The identification information of the dataset includes one or more of the following: Dataset identifier (ID) is used to associate a set of measurement samples and / or related auxiliary information for a group of channels; Measurement Resource ID, used to associate a set of measurement resources and / or channel measurement samples.

83. A second communications device according to any one of claims 67 to 82, wherein, The second communication device also includes: The processing unit is used by the second communication device to train the constellation point correlation scheme based on the training information.

84. A second communications device according to Claim 83 wherein, The processing unit is used for: The first input information is input into the first scheme to be trained, and the first output information is output. The first input information includes a bit sequence, and the first output information includes modulated constellation points. After resource mapping and channel model transmission of the first output information, channel estimation and equalization are performed to obtain the received symbol. The channel model is constructed based on the training information. The second input information is input into the second scheme to be trained, and the second output information is output. The second input information includes the received symbol, and the second output information includes the log-likelihood ratio (LLR) sequence. Based on the loss function constructed from the first input information and the second output information, the first scheme and / or the second scheme are adjusted to obtain the trained first scheme and / or the second scheme.

85. The second communication device of claim 84, wherein, The processing unit is further configured to use channel quality feature information as third input information for the first scheme and / or the second scheme.

86. A second communications device according to claim 84 or 85, wherein, The methods for establishing the channel model include one or more of the following: A channel model is established based on the noise characteristics of the channel, and the channel quality characteristic information is used as the reference range of noise during the training process of the first scheme and / or the second scheme. A channel model is established based on complete channel characteristics, and the first scheme and / or the second scheme are trained using measurement samples of the downlink channel. A channel model is established based on complete channel characteristics, and the first scheme and / or the second scheme are trained using uplink channel measurement samples.

87. A second communications device according to any one of claims 67 to 82, wherein, The transceiver unit is further configured to receive a first scheme, the first scheme including one or more of a first model, a first function, and a first characteristic, wherein the first model includes a constellation point modulation model, the first function includes a constellation point modulation function, and the first characteristic includes a constellation point modulation characteristic.

88. The second communication device of any one of claims 67 to 82, wherein, The transceiver unit is also used to receive a second scheme, which includes one or more of a second model, a second function, and a second characteristic, wherein the second model includes a constellation point demodulation model, the second function includes a constellation point demodulation function, and the second characteristic includes a constellation point demodulation characteristic.

89. A communication device, comprising: A transceiver, a processor, and a memory, wherein the memory is used to store a computer program, the transceiver is used to communicate with other devices, and the processor is used to invoke and run the computer program stored in the memory to cause the communication device to perform the method as described in any one of claims 1 to 44.

90. A chip comprising: A processor for retrieving and running a computer program from memory, causing a device on which the chip is mounted to perform the method as described in any one of claims 1 to 44.

91. A computer-readable storage medium for storing a computer program that, when run by a device, causes the device to perform the method as described in any one of claims 1 to 44.

92. A computer program product comprising computer program instructions that cause a computer to perform the method as described in any one of claims 1 to 44.

93. A computer program that causes a computer to perform the method as described in any one of claims 1 to 44.

94. A communication system, comprising: A first communication device is configured to perform the method as described in any one of claims 1 to 22; A second communication device is used to perform the method as described in any one of claims 23 to 44.

Images