Communication method, communication device, communication system, storage medium, and program product

Abstract

The present disclosure relates to a communication method, a communication device, a communication system, a storage medium, and a program product. The method comprises: sending first information to a second device, or receiving the first information sent by the second device, wherein the first information comprises a training sample, and the training sample is used for training or updating a demodulation model. In the method of the present disclosure, a first device and a second device negotiate, on the basis of communication interaction, a training sample used for model training or updating, so that an ideal training sample can be conveniently obtained during model application, thereby improving the accuracy and reliability of model training.

Description

Communication methods, communication equipment, communication systems, storage media and software products Technical Field

[0001] This disclosure relates to the field of communication technology, and in particular to a communication method, communication device, communication system, storage medium, and program product. Background Technology

[0002] To meet the service demands of high-speed data transmission, massive bandwidth, and reliable communication in mobile scenarios, wireless communication networks still need improvement and enhancement in many aspects. In wireless communication technology, the application of model prediction or learning techniques can effectively contribute to its development.

[0003] Summary of the Invention

[0004] For AI or ML-based models, training can be performed based on collected data, or the model can be trained or updated in real time or near real time during application. It is necessary to ensure the reliability of the model.

[0005] This disclosure provides a communication method, communication device, communication system, storage medium, and program product.

[0006] In a first aspect, embodiments of this disclosure provide a communication method, executed by a first device, the method comprising:

[0007] Sending first information to a second device, or receiving first information sent by the second device; wherein the first information includes training samples, which are used to train or update the demodulation model.

[0008] Secondly, embodiments of this disclosure provide a communication method executed by a second device, the method comprising:

[0009] Receive first information sent by a first device, or send first information to the first device; wherein the first information includes training samples, which are used to train or update the demodulation model.

[0010] Thirdly, embodiments of this disclosure provide a communication device, wherein the communication device is used to perform the method described in the first aspect or the second aspect.

[0011] Fourthly, embodiments of this disclosure provide a communication system, including a first device and a second device, wherein,

[0012] The first device is configured to implement the method as described in the first aspect;

[0013] The second device is configured to implement the method as described in the second aspect.

[0014] Fifthly, embodiments of this disclosure provide a storage medium storing instructions, wherein...

[0015] When the instructions are executed on the communication device, the communication device causes the communication device to perform the method described in the first aspect or the second aspect.

[0016] Sixthly, embodiments of this disclosure provide a program product, wherein,

[0017] When the program product is executed by a communication device, the communication device performs the method described in the first aspect or the second aspect.

[0018] In this embodiment of the disclosure, the first device and the second device negotiate training samples for model training or updating based on communication interaction, so that ideal training samples can be conveniently obtained during model application, thereby improving the accuracy and reliability of model training. Attached Figure Description

[0019] To more clearly illustrate the technical solutions in the embodiments of this disclosure, the accompanying drawings required for the description of the embodiments are introduced below. The following drawings are only some embodiments of this disclosure and do not impose specific limitations on the protection scope of this disclosure.

[0020] Figure 1A is an exemplary schematic diagram of the architecture of a communication system provided according to an embodiment of the present disclosure;

[0021] Figures 1B to 1D are schematic diagrams of model processing provided according to embodiments of the present disclosure;

[0022] Figures 2A and 2B are exemplary interactive schematic diagrams of the method provided according to embodiments of the present disclosure;

[0023] Figures 3A and 3B are exemplary interactive schematic diagrams of the method provided according to embodiments of the present disclosure;

[0024] Figure 4 is an exemplary interactive schematic diagram of the method provided according to an embodiment of the present disclosure;

[0025] Figure 5A is a schematic diagram of the structure of a communication device according to an embodiment of the present disclosure;

[0026] Figure 5B is a schematic diagram of the structure of a communication device according to an embodiment of the present disclosure;

[0027] Figure 6A is a schematic diagram of a communication device according to an embodiment of the present disclosure;

[0028] Figure 6B is a schematic diagram of a communication device according to an embodiment of the present disclosure. Detailed Implementation

[0029] This disclosure provides a communication method, communication device, communication system, storage medium, and program product.

[0030] In a first aspect, embodiments of this disclosure provide a communication method, executed by a first device, the method comprising:

[0031] Sending first information to a second device, or receiving first information sent by a second device; wherein the first information includes training samples, which are used to train or update the demodulation model.

[0032] In the above embodiments, the first device and the second device negotiate training samples for model training or updating based on communication interaction, so that ideal training samples can be easily obtained during model application, thereby improving the accuracy and reliability of model training.

[0033] In conjunction with the embodiments of the first aspect, in some embodiments, the training samples include: one or more target data;

[0034] The first piece of information also includes: the quantity of target data.

[0035] In the above embodiments, training samples define or indicate target data specifically used for model training or updating. The target data is the ideal output data required for model training or updating. Negotiating this through interaction between the communicating parties effectively solves the problem of the receiving end struggling to obtain ideal output data, thereby improving the accuracy of model training or updating. The quantity of target data can be used to indicate the number of training samples, facilitating multiple training iterations and improving model performance.

[0036] In conjunction with the embodiments of the first aspect, in some embodiments, the target data satisfies at least one of the following:

[0037] Generated based on a predefined method;

[0038] Use a predefined data sequence.

[0039] In the above embodiments, the target data can be simplified, and the model can be trained or updated based on the target data in different scenarios or situations, thereby improving the generalization of the model.

[0040] In conjunction with the embodiments of the first aspect, in some embodiments, the method further includes:

[0041] Receive second information sent by the second device, the second information including information modulated on the target data;

[0042] The input to the demodulation model is determined based on the second information, and the target data is used as the target output to train or update the demodulation model.

[0043] In the above embodiments, after receiving the second information for model training or updating, the receiving device can train or update the model based on the ideal output data in the first information, thereby improving the reliability of model training.

[0044] In conjunction with the embodiments of the first aspect, in some embodiments, receiving second information sent by the second device includes:

[0045] Receive second information sent by the second device under different conditions, wherein the conditions include channel environment and / or channel parameter configuration.

[0046] In the above embodiments, based on the same or different target data, the information sent by the sending end under different conditions can bring different training or update effects, thereby improving the adaptability and accuracy of the model in different scenarios.

[0047] In conjunction with the embodiments of the first aspect, in some embodiments, the second information transmitted under different conditions includes information modulated on the same target data.

[0048] In the above embodiments, the second information is sent under different conditions. Different transmission information can be generated due to changes in the channel environment or channel parameters. Therefore, training based on the same target data can improve the effect of model training or updating. The same target data can also simplify the operation of the sending end.

[0049] In conjunction with the embodiments of the first aspect, in some embodiments, receiving the second information sent by the second device includes:

[0050] The device receives N second messages sent by the second device, where N is the number of target data; wherein each of the N second messages includes information modulated on a target data.

[0051] In the above embodiments, training is performed based on multiple pieces of second information sent by the second device, thereby improving the model training effect and enhancing the robustness of the model.

[0052] In conjunction with the embodiments of the first aspect, in some embodiments, the method further includes:

[0053] Receive third information sent by the second device, the third information including information modulated from the communication data;

[0054] Based on the trained or updated demodulation model and third information, determine the demodulation data corresponding to the communication data.

[0055] In the above embodiments, after obtaining a reliable model, the receiving end can demodulate the received information based on the trained or updated model to obtain reliable and accurate demodulated data, thereby improving communication reliability.

[0056] In conjunction with the embodiments of the first aspect, in some embodiments, the method further includes:

[0057] Identify or select training samples.

[0058] In the above embodiments, the receiving device selects the training samples, which simplifies the operation of the transmitting device and helps to save energy in the transmitting device.

[0059] In conjunction with the embodiments of the first aspect, in some embodiments, the first device is a terminal or a network device.

[0060] Secondly, embodiments of this disclosure provide a communication method executed by a second device, the method comprising:

[0061] Receive first information sent by the first device, or send first information to the first device; wherein the first information includes training samples, which are used to train or update the demodulation model.

[0062] In the above embodiments, the second device and the first device negotiate training samples for model training or updating based on communication interaction, so that the receiving end can conveniently obtain ideal training samples during model application, thereby improving the accuracy and reliability of model training.

[0063] In conjunction with the embodiments of the second aspect, in some embodiments, the training samples include: one or more target data;

[0064] The first piece of information also includes: the quantity of target data.

[0065] In conjunction with the embodiments of the second aspect, in some embodiments, the target data satisfies at least one of the following:

[0066] Generated based on a predefined method;

[0067] Use a predefined data sequence.

[0068] In conjunction with the embodiments of the second aspect, in some embodiments, the method further includes:

[0069] Send second information to the first device, the second information including information modulated on the target data; wherein the second information and the target data are used by the first device to train or update the demodulation model.

[0070] In conjunction with embodiments of the second aspect, in some embodiments, sending second information to the first device includes:

[0071] The second information is sent to the first device under different conditions, wherein the conditions include channel environment and / or channel parameter configuration.

[0072] In conjunction with the embodiments of the second aspect, in some embodiments, the second information transmitted under different conditions includes information that has been modulated on the same target data.

[0073] In conjunction with embodiments of the second aspect, in some embodiments, sending second information to the first device includes:

[0074] N second messages are sent to the first device, where N is the number of target data; each of the N second messages includes information modulated on a target data.

[0075] In conjunction with the embodiments of the second aspect, in some embodiments, the method further includes:

[0076] The third information is sent to the first device, and the third information includes information after the communication data is modulated; wherein the first device is used to determine the demodulated data corresponding to the communication data based on the demodulation model after training or updating and the third information.

[0077] In conjunction with the embodiments of the second aspect, in some embodiments, the method further includes:

[0078] Identify or select training samples.

[0079] In conjunction with the embodiments of the second aspect, in some embodiments, the second device is a terminal or a network device.

[0080] Thirdly, embodiments of this disclosure provide a communication device, wherein the communication device is used to perform the method described in the first aspect or the second aspect.

[0081] Fourthly, embodiments of this disclosure provide a communication system, including a first device and a second device, wherein,

[0082] The first device is configured to implement the method as described in the first aspect;

[0083] The second device is configured to implement the method as described in the second aspect.

[0084] Fifthly, embodiments of this disclosure provide a storage medium storing instructions, wherein...

[0085] When the instructions are executed on the communication device, the communication device causes the communication device to perform the method described in the first aspect or the second aspect.

[0086] Sixthly, embodiments of this disclosure provide a program product, wherein,

[0087] When the program product is executed by a communication device, the communication device performs the method described in the first aspect or the second aspect.

[0088] In a seventh aspect, embodiments of this disclosure provide a communication device, including:

[0089] The transceiver module is used to send first information to the second device, or to receive first information sent by the second device; wherein the first information includes training samples, which are used to train or update the demodulation model.

[0090] Eighthly, embodiments of this disclosure provide a communication device, including:

[0091] The transceiver module is used to receive first information sent by the first device, or to send first information to the first device; wherein the first information includes training samples, which are used to train or update the demodulation model.

[0092] In a ninth aspect, embodiments of this disclosure provide a computer program that, when run on a computer, causes the computer to perform the methods described in alternative implementations of the first and second aspects.

[0093] In a tenth aspect, embodiments of this disclosure provide a chip or chip system. The chip or chip system includes processing circuitry configured to perform the methods described according to optional implementations of the first and second aspects above.

[0094] It is understood that the aforementioned communication devices, communication systems, storage media, program products, computer programs, chips, or chip systems are all used to execute the methods proposed in the embodiments of this disclosure. Therefore, the beneficial effects they can achieve can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.

[0095] This disclosure provides a communication method, a communication device, a communication system, a storage medium, and a program product. In some embodiments, the terms "communication method" and "information processing method," "information sending and receiving method," etc., can be used interchangeably.

[0096] This disclosure is not exhaustive, but merely illustrative of some embodiments, and is not intended to limit the scope of protection of this disclosure. Unless otherwise specified, each step in a particular embodiment can be implemented as an independent embodiment, and the steps can be arbitrarily combined. For example, a solution after removing some steps in a particular embodiment can also be implemented as an independent embodiment, and the order of the steps in a particular embodiment can be arbitrarily interchanged. Furthermore, the optional implementation methods in a particular embodiment can be arbitrarily combined; moreover, the embodiments can be arbitrarily combined, for example, some or all steps of different embodiments can be arbitrarily combined, and a particular embodiment can be arbitrarily combined with the optional implementation methods of other embodiments. In all embodiments of this disclosure, unless otherwise specified or logically conflicting, the terminology and / or descriptions between the embodiments are consistent and can be mutually referenced. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships.

[0097] The terminology used in the embodiments of this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the scope of this disclosure.

[0098] In this embodiment of the disclosure, unless otherwise stated, elements expressed in the singular form, such as "a," "an," "the," "the," "the," "the," "the," "the," "this," etc., can mean "one and only one," or "one or more," "at least one," etc. For example, when using articles such as "a," "an," "the," etc. in translation, the noun following the article can be understood as either a singular expression or a plural expression.

[0099] In the embodiments disclosed herein, "multiple" refers to two or more.

[0100] In some embodiments, the terms “at least one of A or B, at least one of A and B”, “one or more”, “a plurality of”, “multiple”, etc., may be used interchangeably.

[0101] In some embodiments, the notation "at least one of A and B", "A and / or B", "A in one case, B in another", "in response to one case A, in response to another case B", etc., may include the following technical solutions depending on the situation: in some embodiments, A (execute A regardless of whether there is a branch B); in some embodiments, B (execute B regardless of whether there is a branch A); in some embodiments, execution is selected from A and B (A and B are selectively executed); in some embodiments, both A and B are executed. The same applies when there are more branches such as A, B, C, etc.

[0102] In some embodiments, the notation "A or B" may include the following technical solutions, depending on the situation: in some embodiments, A (execute A regardless of whether a branch B exists); in some embodiments, B (execute B regardless of whether a branch A exists); in some embodiments, execution is selected from A and B (A and B are selectively executed). The same applies when there are more branches such as A, B, and C.

[0103] The prefixes "first," "second," etc., used in the embodiments of this disclosure are merely for distinguishing different descriptive objects and do not impose restrictions on the position, order, priority, quantity, or content of the descriptive objects. The description of the descriptive objects is found in the claims or the context of the embodiments, and the use of prefixes should not constitute unnecessary restrictions. For example, if the descriptive object is a "field," the ordinal numbers preceding "field" in "first field" and "second field" do not restrict the position or order of the "fields." "First" and "second" do not restrict whether the "fields" they modify are in the same message, nor do they restrict the order of "first field" and "second field." Similarly, if the descriptive object is a "level," the ordinal numbers preceding "level" in "first level" and "second level" do not restrict the priority between "levels." Furthermore, the number of descriptive objects is not limited by ordinal numbers and can be one or more. For example, in "first device," the number of "devices" can be one or more. Furthermore, the objects modified by different prefixes can be the same or different. For example, if the object being described is "device", then "first device" and "second device" can be the same device or different devices, and their types can be the same or different. Similarly, if the object being described is "information", then "first information" and "second information" can be the same information or different information, and their content can be the same or different.

[0104] In some embodiments, “including A,” “containing A,” “for indicating A,” and “carrying A” can be interpreted as directly carrying A or indirectly indicating A.

[0105] In some embodiments, terms such as "time / frequency" and "time-frequency domain" refer to the time domain and / or frequency domain.

[0106] In some embodiments, terms such as “in response to…”, “in response to determining…”, “in the case of…”, “when…”, “when…”, “if…”, etc. can be used interchangeably. These descriptions all refer to the device making a corresponding action under certain objective circumstances. They do not necessarily limit the time, nor do they require the device to make a judgment action when implementing it, nor do they mean that there must be other limitations.

[0107] In some embodiments, the terms “greater than,” “greater than or equal to,” “not less than,” “more than,” “more than or equal to,” “not less than,” “higher than,” “higher than or equal to,” “not lower than,” and “above” can be used interchangeably, as can the terms “less than,” “less than or equal to,” “not greater than,” “less than,” “less than or equal to,” “not more than,” “lower than,” “lower than or equal to,” “not higher than,” and “below”.

[0108] In some embodiments, devices, etc., may be interpreted as physical or virtual, and their names are not limited to those described in the embodiments. Terms such as “device,” “equipment,” “circuit,” “network element,” “network function,” “network device,” “function,” “node,” “unit,” “section,” “system,” “network,” “chip,” “chip system,” “entity,” and “subject” are interchangeable.

[0109] In some embodiments, "network" can be interpreted as devices included in a network (e.g., access network devices, core network devices, etc.).

[0110] In some embodiments, the terms "access network device (AN device)," "radio access network device (RAN device)," "base station (BS)," "radio base station," "fixed station," "node," "access point," "transmission point (TP)," "reception point (RP)," "transmission / reception point (TRP)," "panel," "antenna panel," "antenna array," "cell," "macro cell," "small cell," "femto cell," "pico cell," "sector," "cell group," "serving cell," "carrier," "component carrier," and "bandwidth part (BWP)" can be used interchangeably.

[0111] In some embodiments, the terms "terminal", "terminal device", "user equipment (UE)", "user terminal", "mobile station (MS)", "mobile terminal (MT)", "subscriber station", "mobile unit", "subscriber unit", "wireless unit", "remote unit", "mobile device", "wireless device", "wireless communication device", "remote device", "mobile subscriber station", "access terminal", "mobile terminal", "wireless terminal", "remote terminal", "handset", "user agent", "mobile client", and "client" can be used interchangeably.

[0112] In some embodiments, access network devices, core network devices, or network devices can be replaced by terminals. For example, embodiments of this disclosure can also be applied to structures where communication between access network devices, core network devices, or network devices and terminals is replaced by communication between multiple terminals (e.g., device-to-device (D2D), vehicle-to-everything (V2X), etc.). In this case, the structure can also be configured such that the terminal has all or part of the functions of the access network device. Furthermore, terms such as "uplink" and "downlink" can be replaced with terms corresponding to communication between terminals (e.g., "sidelink"). For example, uplink channel, downlink channel, etc., can be replaced with sidelink channel, and uplink link, downlink, etc., can be replaced with sidelink link.

[0113] In some embodiments, the terminal may be replaced by an access network device, a core network device, or a network device. In this case, the access network device, core network device, or network device may also be configured to have all or some of the functions of the terminal.

[0114] In some embodiments, the acquisition of data, information, etc., may comply with the laws and regulations of the country where the location is situated.

[0115] In some embodiments, data, information, etc., may be obtained with the user's consent.

[0116] Furthermore, each element, each row, or each column in the table of this disclosure can be implemented as an independent embodiment, and any combination of any element, any row, or any column can also be implemented as an independent embodiment.

[0117] Figure 1A is a schematic diagram of the architecture of a communication system according to an embodiment of the present disclosure.

[0118] As shown in Figure 1A, the communication system 100 includes a first device 101 and a second device 102.

[0119] In some embodiments, the second device 102 may refer to a transmitting end in communication interaction, or a communication transmitting device, which can perform data modulation and other processing, and send the processed signal or information to the receiving end. The first device 101 may refer to a receiving end in communication interaction, or a communication receiving device, which can receive the signal or information sent by the second device 102, and can demodulate the data in the signal or information to obtain the interactive data.

[0120] In some embodiments, the second device 102 may be a terminal or a network device. The first device 101 may be a network device or a terminal. For example, the first device 101 and the second device 102 may be different terminals or different network devices. For another example, the first device 101 may be a terminal and the second device 102 may be a network device; or, the first device 101 may be a network device and the second device 102 may be a terminal.

[0121] In some embodiments, the terminal includes, but is not limited to, at least one of the following: mobile phone, wearable device, Internet of Things device, car with communication function, smart car, tablet computer, computer with wireless transceiver function, virtual reality (VR) terminal device, augmented reality (AR) terminal device, wireless terminal device in industrial control, wireless terminal device in self-driving, wireless terminal device in remote medical surgery, wireless terminal device in smart grid, wireless terminal device in transportation safety, wireless terminal device in smart city, and wireless terminal device in smart home.

[0122] In some embodiments, the network device may include at least one of an access network device and a core network device.

[0123] In some embodiments, such as nodes or devices that connect terminals to a wireless network, the access network device may include at least one of the following in a 5G communication system: evolved Node B (eNB), next-generation eNB (ng-eNB), next-generation Node B (gNB), node B (NB), home node B (HNB), home evolved node B (HeNB), wireless backhaul device, radio network controller (RNC), base station controller (BSC), base transceiver station (BTS), base band unit (BBU), mobile switching center, base station in a 6G communication system, open RAN, cloud RAN, base station in other communication systems, and access node in a Wi-Fi system, but is not limited thereto.

[0124] In some embodiments, the technical solutions of this disclosure can be applied to the Open RAN architecture. In this case, the interfaces between or within access network devices involved in the embodiments of this disclosure can be transformed into internal interfaces of Open RAN. The processes and information interactions between these internal interfaces can be implemented by software or programs.

[0125] In some embodiments, the access network device may be composed of a central unit (CU) and a distributed unit (DU). The CU may also be called a control unit. The CU-DU structure can separate the protocol layer of the access network device. Some of the protocol layer functions are centrally controlled by the CU, while the remaining part or all of the protocol layer functions are distributed in the DU and centrally controlled by the CU. However, this is not the only possibility.

[0126] In some embodiments, a core network device may be a single device comprising one or more network elements, or it may be multiple devices or a group of devices, each comprising all or part of one or more network elements. Network elements may be virtual or physical. The core network may include, for example, at least one of the following: Evolved Packet Core (EPC), 5G Core Network (5GCN), and Next Generation Core (NGC).

[0127] In some embodiments, core network equipment includes network elements with specific functions, such as Access Management Function (AMF) and Service Management Function (SMF).

[0128] It is understood that the communication system described in this disclosure is for the purpose of more clearly illustrating the technical solutions of this disclosure, and does not constitute a limitation on the technical solutions proposed in this disclosure. As those skilled in the art will know, with the evolution of system architecture and the emergence of new business scenarios, the technical solutions proposed in this disclosure are also applicable to similar technical problems.

[0129] The following embodiments of this disclosure can be applied to the communication system 100 shown in FIG1A, or to some of the main bodies, but are not limited thereto. The main bodies shown in FIG1A are illustrative. The communication system may include all or some of the main bodies in FIG1A, or it may include other main bodies outside of FIG1A. The number and form of each main body are arbitrary. Each main body may be physical or virtual. The connection relationship between the main bodies is illustrative. The main bodies may not be connected or may be connected. The connection may be in any way, such as direct connection or indirect connection, wired connection or wireless connection.

[0130] The embodiments disclosed herein can be applied to Long Term Evolution (LTE), LTE-Advanced (LTE-A), LTE-Beyond (LTE-B), SUPER 3G, IMT-Advanced, 4th generation mobile communication system (4G), 5th generation mobile communication system (5G), 5G new radio (NR), Future Radio Access (FRA), New-Radio Access Technology (RAT), New Radio (NR), New radio access (NX), Future generation radio access (FX), Global System for Mobile communications (GSM), CDMA2000, Ultra Mobile Broadband (UMB), IEEE 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), and IEEE 802.20, Ultra-Wideband (UWB), Bluetooth (a registered trademark), Public Land Mobile Network (PLMN) networks, Device-to-Device (D2D) systems, Machine-to-Machine (M2M) systems, Internet of Things (IoT) systems, Vehicle-to-Everything (V2X) systems, systems utilizing other communication methods, and next-generation systems built upon them, etc. Furthermore, multiple systems can be combined (e.g., a combination of LTE or LTE-A with 5G).

[0131] In some implementations, to meet the service demands of mobile communication systems such as 5G or future 6G, including high-speed data transmission, massive bandwidth, and reliable communication in mobile scenarios, and to realize future wireless communication visions such as smart cities and smart transportation, current wireless communication networks still need improvement and enhancement in many aspects. Among these, accurate data demodulation is one of the fundamental modules for achieving low bit error rate and high-speed transmission in wireless communication systems, and it affects the overall performance of the communication system.

[0132] In some implementations, the demodulator is derived using methods derived from the Neyman-Pearson theorem and Bayes' theorem. Such demodulators typically require accurate channel state information and channel noise distribution, and their performance depends on the parameter settings of individual modules, such as filters, phase-locked loops, product modulators, or analog-to-digital converters. These demodulators may exhibit the following characteristics:

[0133] (1) It has a large time delay and is complex to implement.

[0134] (2) Unstable module performance: Due to factors such as vibration, acceleration, temperature fluctuation, aging, and instability of discrete components, the module performance will change, resulting in a decline in the overall performance of the receiver.

[0135] (3) Poor environmental adaptability: Wireless communication channels may suffer from undesirable factors such as multipath fading, impulse noise, clutter, or discrete interference, which significantly reduces demodulation accuracy. For example, some coherent demodulators require carrier synchronization, and the phase error and frequency offset present during the synchronization process will cause significant demodulation errors.

[0136] (4) It relies heavily on prior knowledge such as channel state information (CSI), but in communication, such as in fast fading scenarios, it is difficult to accurately estimate CSI. Therefore, the channel model may be unknown at the receiver.

[0137] (5) Prior waveform information and time series information were not fully utilized.

[0138] In some implementations, the increasing demand for wireless services such as smartphones, virtual reality, and the Internet of Things necessitates handling more complex and diverse communication requirements. Demodulators or mathematical models designed according to rigorous mathematical theory and precise system models may not be adequate for these needs. Therefore, AI or ML technologies, such as deep learning, can be applied to wireless communication systems.

[0139] In some implementations, the information of the modulated signal is represented by amplitude and phase. A crucial step in signal demodulation is feature extraction. Deep learning-based demodulators (or learning-based demodulators) can utilize neural networks to autonomously learn and extract important feature information from the received signal, thereby achieving data demodulation with higher accuracy and robustness. Deep learning-based demodulators include the following characteristics:

[0140] (1) Model training is performed using a dataset of a certain size under specific channel environment and parameter configuration. The demodulation model obtained under this environment and configuration has good flexibility and adaptability, which is conducive to improving the data demodulation accuracy.

[0141] (2) During the training process, the model can learn the data distribution characteristics under various undesirable conditions. Therefore, the demodulator based on deep learning has stronger anti-noise and anti-interference capabilities.

[0142] (3) The requirements for prior knowledge (such as CSI and channel noise) can be relaxed or even eliminated.

[0143] Therefore, deep learning-based demodulators have great potential in dealing with complex wireless communication environments and improving communication performance.

[0144] In some implementations, the mapping between the raw data (data to be modulated) and constellation symbols differs depending on the modulation scheme, such as Quadrature Phase Shift Keying (QPSK), 16-Quadrature Amplitude Modulation (16QAM), or 64-Quadrature Amplitude Modulation (64QAM). At the receiver, one data symbol to be demodulated can correspond to data bits of different lengths. Therefore, for received data symbols using different modulation schemes, a matching demodulation scheme is required for data demodulation. Similarly, in AI-based demodulation implementations, different modulation schemes must also be considered.

[0145] In some implementations, training the AI ​​model requires input and output data of a defined dimension. The length of the demodulated data corresponding to a single data symbol differs depending on the modulation scheme. For example, in 16QAM modulation, a constellation point corresponds to 4 bits of data, while in 64QAM modulation, a constellation point corresponds to 6 bits of data. Therefore, the AI ​​demodulation model used for 16QAM modulation outputs 4 bits of data, and the AI ​​demodulation model used for 64QAM modulation outputs 6 bits of data. Consequently, the two models need to learn the mapping relationship between constellation points and data for each modulation scheme.

[0146] In one embodiment shown in Figure 1B, if the receiving end knows the modulation scheme information, for example, the modulation scheme information is indicated to the receiving end by the transmitting end during data transmission, the receiving end uses the modulation scheme information as auxiliary information for selecting the demodulation model, and the AI-based demodulation model realizes data demodulation under different modulation schemes.

[0147] In conjunction with another implementation shown in Figure 1C, when the transmitting end does not indicate modulation mode information, the data to be demodulated and the corresponding modulation mode information can be used as training data to train an AI modulation mode recognition model. This recognition model can determine the modulation mode of the corresponding transmitting end signal based on the features of the data to be demodulated, and then select the AI ​​demodulation model under the corresponding modulation mode for data demodulation.

[0148] In some implementations, the main application process of deep learning-based data demodulation is as follows: Model training is performed on an AI network model, such as an AI demodulation model, used for data demodulation. After model training is completed, the trained AI demodulation model is deployed on the signal receiving device, where model inference can be performed to complete the data demodulation task at the receiving end of the actual system.

[0149] In some implementations, different AI demodulation models are typically required because the mapping relationship between the data symbols to be demodulated and the demodulated data differs under different modulation schemes. For a given modulation scheme, one model can be used to implement data demodulation. However, due to device movement, changes in channel conditions, and the instability of the wireless environment, the distribution of the data to be demodulated input to the AI ​​demodulation model during inference applications may change significantly. In other words, the distribution of input data during model application differs from the distribution of input data during model training. This may cause the input-output mapping relationship learned by the AI ​​demodulation model based on the training dataset to no longer be entirely suitable for the test data, resulting in a decrease in the performance of the AI ​​demodulation model and a reduction in the generalization ability of the AI ​​model.

[0150] In some implementations, to improve the generalization problem of AI models in wireless communication system applications, the following three enhancement methods can be used to ensure the relative stability of the demodulation model's accuracy:

[0151] (1) Train a model using mixed datasets under different environments or configurations;

[0152] (2) Update the model using real-time data collected during the model application process;

[0153] (3) Train multiple models for different environments or configurations and select the appropriate model for inference during model application.

[0154] Referring to Figure 1D, during model updates, the training dataset collected under environment parameter i can be used to complete model training. When applying the model under environment parameter j, the training dataset collected under environment parameter j is used first to update the model, and then the updated model is used for model inference to complete data demodulation.

[0155] In some implementations, model training consumes more computational resources than model inference. Therefore, model updates require devices with high hardware computing resources to support low-latency online model training. Model updates require a certain number of ideally labeled data samples. However, data collection during model application incurs significant data collection costs and introduces latency, impacting the real-time performance of the model.

[0156] For data demodulation, the dataset used for AI demodulation model updates includes: model input (such as the data to be demodulated) and model target output (such as the original transmitted data). The data to be demodulated can be directly obtained by the receiver based on the received signal. However, due to real-time data transmission errors, the model target output is difficult for the receiver to obtain, such as ideal label data samples for model updates. Optionally, to address the generalization problem of AI-based data demodulation models, model updates are used to ensure model performance. However, model updates require a certain number of ideal label data samples, which are difficult to obtain in real-time model applications, thus posing challenges to model updates.

[0157] Figure 2A is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure. As shown in Figure 2A, the present disclosure relates to a communication method, which includes:

[0158] In step S2101, the first device 101 determines or selects training samples.

[0159] In some embodiments, the first device 101 may select training samples in accordance with the manner defined by the protocol or the principles of pre-configuration.

[0160] In some embodiments, the first device 101 may be a terminal or a network device. For example, the terminal or network device selects one or more sets of training samples for demodulating model training or model updating.

[0161] Optionally, the demodulation model can be an AI or ML-based model used to demodulate the model's input and output the demodulated information.

[0162] Optionally, the demodulation model can be deployed at the receiving end, such as the first device 101, for example, in a terminal and / or network device, to demodulate the received data.

[0163] Optionally, model training can include offline training or online training. Offline training can be based on a pre-collected dataset to train the demodulation model. Online training can be based on a dataset collected in real-time or near real-time to train the demodulation model.

[0164] Optionally, model updating can involve continuing online training of a pre-trained or trained demodulation model, thereby updating the model parameters of the pre-trained demodulation model. These model parameters can include the structure and weight parameters of the demodulation model. Model updating or online model training allows the demodulation model to better adapt to different environmental characteristics or channel environments, improving the model's generalization ability.

[0165] In some embodiments, training samples may refer to training datasets used to train or update demodulation models.

[0166] In some embodiments, the input to the demodulation model is the data to be demodulated, and the output is the demodulated data. When training the demodulation model, the training samples may include input training samples and output training samples.

[0167] Optionally, the input training samples can be based on the demodulated data received through communication, and the output training samples can be indicated by the first information.

[0168] In some embodiments, the training samples include:

[0169] One or more target data (Data);

[0170] Optionally, the target data can be the output training samples of the demodulation model, used for training or updating the demodulation model. In some embodiments, the target data satisfies at least one of the following:

[0171] Generated based on a predefined method;

[0172] Use a predefined data sequence.

[0173] Optionally, the target data is generated based on a predefined protocol method, for example, the first device 101 generates one or more target data in a random manner.

[0174] Optionally, the target data can use a predefined data sequence. For example, one or more target data can use a simple data sequence, such as Data1 using an all-zero sequence and Data2 using an all-one sequence.

[0175] In some embodiments, the target data can be used as data dedicated to demodulation model training or updating. Training with a simple data sequence can reduce processing operations at the sending or receiving end and reduce interference from the channel environment on the target data transmission.

[0176] In some embodiments, terms such as "certain," "preset," "default," "set," "indicated," "a certain," "any," and "first" can be used interchangeably. "Certain A," "preset A," "default A," "set A," "indicated A," "a certain A," "any A," and "first A" can be interpreted as A pre-defined in a protocol or the like, or as A obtained through setting, configuration, or instruction, or as specific A, a certain A, any A, or first A, but are not limited thereto.

[0177] In step S2102, the first device 101 sends the first information to the second device 102.

[0178] In some embodiments, the second device 102 may be a terminal or a network device. For example, the first device 101 may be a terminal and the second device 102 may be a network device; or, the first device 101 may be a network device and the second device 102 may be a terminal. As another example, the first device 101 and the second device 102 may be different terminals or different network devices.

[0179] In some embodiments, the first information may be indication information, or an indication carried in indication information, auxiliary information, or configuration information.

[0180] Optionally, when the first device 101 is a terminal and the second device 102 is a network device, the first information can be sent via Radio Resource Control (RRC) messages.

[0181] Optionally, when the first device 101 is a network device and the second device 102 is a terminal, the first information can be sent via downlink control information (DCI) or RRC messages.

[0182] In some embodiments, the first information includes training samples used to train or model the demodulation model. The description of the training samples can be found in the description of step S2101, such as including one or more target data.

[0183] Optionally, the target data can be the output training samples of the demodulation model, and the first information can indicate the content of one or more target data.

[0184] In some embodiments, the first information may further include the number (n) of target data.

[0185] Optionally, the amount of target data can be based on protocol definition, terminal determination, or network device configuration. The amount of target data can be indicated in the first information.

[0186] Optionally, the amount of target data can be used to measure the number of training samples, or to verify the amount of target data received that matches the amount of target data received.

[0187] In one example, the first information includes the number of target data points, n, and the training samples, such as one or more target data points, for example, Data. i , where i = 1, 2, ..., n.

[0188] In this example, the first device 101 and / or the second device 102 can easily determine the data used for model training or updating. For example, referring to the description of step S2103, if the second device 102 sends information modulated on the target data, the first device 101 can determine whether the second information has been completely sent, i.e., whether the modulation information corresponding to the target data has been completely sent, based on the reception of the first information. Thus, the first device 101 can perform training or updating in a timely manner. As another example, if the second information also includes other data, or if there is other information sent synchronously with the second information, the first device 101 can receive a corresponding amount of second information (including information modulated on the target data) based on the quantity of target data.

[0189] In another example, the first information includes the target data, such as Data. i Where i = 1, 2, ..., n, the number of target data n can be determined by the device performing training or updating, such as by the first device 101. For example, in conjunction with the description of step S2103, if the second device 102 sends information modulated on the target data, the first device 101 can determine the number of second information used for training or updating, that is, the number of modulation information corresponding to the target data.

[0190] In some embodiments, the second device 102 receives first information to obtain target data for demodulating model training or updating.

[0191] It is worth noting that, in conjunction with the description of the foregoing embodiments, due to changes in device location, channel environment, or configuration, real-time data transmission may contain errors. The first device 101, relying solely on demodulation of the received information, may struggle to obtain ideal output training samples. However, based on the first information of this embodiment, the first device 101 and the second device 102 can determine the training samples, such as target data, for model training or updating before model training or updating. This ensures that the demodulated model has ideal output labels during training or updating, thereby improving the accuracy of model training or updating.

[0192] In some embodiments, the names of information, etc., are not limited to the names described in the embodiments. Terms such as "information", "message", "signal", "signaling", "report", "configuration", "indication", "instruction", "command", "channel", "parameter", "domain", and "field" can be used interchangeably.

[0193] In some embodiments, terms such as “send,” “transmit,” “report,” “distribute,” “transmit,” “bidirectional transmission,” “send and / or receive” can be used interchangeably.

[0194] In some embodiments, the terms “downlink control information (DCI),” “downlink (DL) assignment,” “DL DCI,” “uplink (UL) grant,” and “UL DCI” can be used interchangeably.

[0195] In some embodiments, "acquire," "get," "obtain," "receive," "transmit," "bidirectional transmission," and "send and / or receive" can be used interchangeably and can be interpreted as receiving from other entities, acquiring from protocols, acquiring from higher layers, obtaining through self-processing, or autonomous implementation. Protocols include, for example, at least one of the 3GPP protocol, Wi-Fi protocol, and audio and / or video protocols.

[0196] In step S2103, the second device 102 sends the second information to the first device 101.

[0197] In some embodiments, the second information is information sent during the model training or update phase of the demodulation model.

[0198] In some embodiments, the second information includes information modulated on the target data, used to carry data related to demodulation model training.

[0199] In some embodiments, the second information may be transmission information or transmission signal, which is modulation information in model training or updating.

[0200] In some embodiments, after obtaining the first information, the second device 102 learns the target data specifically used for demodulating model training or updating.

[0201] In some embodiments, during the model update process, the second device 102 uses the target data as the original transmission data, such as preprocessing and modulation of the target data to obtain modulated data, and carries the modulated information of the target data through the second information carrier, such as the modulated data.

[0202] In some embodiments, the second device 102 may transmit the second information under different conditions. These conditions include channel environment and / or channel parameter configuration.

[0203] For example, the second device 102 transmits the second information multiple times under different conditions. Each transmission of the second information corresponds to a condition, such as a channel environment or a channel parameter configuration.

[0204] Optionally, the target data involved in the second information transmitted under different conditions may be the same or different, or the target data corresponding to different second information may be the same or different. For example, it may include information modulated from the same or different target data. Thus, based on a limited number of target data, more input training samples can be obtained, for example, in conjunction with the description of step S2104, the first device 101 can obtain more input in model training or updating.

[0205] Optionally, the second information transmitted under different conditions may include information modulated from the same target data. Thus, based on the same target data, and combined with variations in conditions such as channel environment and / or channel parameter configuration, multiple input training samples can be obtained.

[0206] In one example, taking the same target data corresponding to different second information as an example, the second device 102 can send the second information multiple times under different channel environments and / or different channel parameter configurations. Each second information includes information modulated on the same target data. Under different conditions, each second information transmitted through the channel will be different.

[0207] For example, the second information includes information modulated from Data1. The second device 102 can transmit this second information multiple times under different channel environments. For instance, the second device 102 can transmit the second information under channel environments with certain physical characteristics, such as indoors, outdoors, at a set altitude, or at a set latitude and longitude. In these different channel environments, Data1 remains unchanged, but the information modulated from Data1 changes during transmission, resulting in different demodulated data obtained by the first device 101, i.e., different input training samples.

[0208] For example, the second information includes information modulated from Data1. The second device 102 can transmit this second information multiple times under different channel parameter configurations. For instance, in an indoor channel environment, the second device 102 can transmit the second information multiple times, adjusting one or more environmental or channel parameter configurations each time it transmits the second information. In this case, Data1 remains unchanged under different parameter configurations, but the information modulated from Data1 changes during transmission, resulting in different demodulated data obtained by the first device 101, i.e., different input training samples.

[0209] In this example, by changing the channel environment or channel parameter configuration, the same target data can obtain multiple different input training samples, thereby using a limited amount of target data and saving signaling resources for the first information.

[0210] In some embodiments, the second device 102 may send N second messages under the same or different conditions, where N is the number of target data; wherein each of the N second messages includes information modulated on a target data.

[0211] In one example, the second device 102 sends N second messages, wherein the first second message includes information modulated onto Data1, the second second message includes information modulated onto Data2, ..., and the Nth second message includes information modulated onto Data1. n The modulated information.

[0212] In some embodiments, the n target data can be repeatedly sent in the manner described in the above example, such as repeatedly sending one or more of the n target data, or repeatedly sending the n target data N times, to obtain n*N training samples.

[0213] In some embodiments, the first device 101 receives second information.

[0214] In step S2104, the first device 101 determines the input of the demodulation model based on the second information, and trains or updates the demodulation model using the target data as the target output.

[0215] In some embodiments, after receiving the second information, the first device 101 may perform preprocessing such as equalization or detection on the second information to obtain the data to be demodulated in the second information.

[0216] Optionally, the data to be demodulated can be information such as constellation symbols.

[0217] In some embodiments, the input to the demodulation model can be the aforementioned data to be demodulated, or the input training samples can be the aforementioned data to be demodulated. Based on the demodulation model, the output is the demodulated data from the training or update phase.

[0218] Optionally, the demodulated data is either soft bit data to be decoded of the log-likelihood ratio type or the original bit data corresponding to the target data.

[0219] In some embodiments, the target data (Data) is used at the transmitting end to obtain modulated data and at the receiving end to serve as the target output for training or updating the demodulation model in order to adjust the output accuracy of the demodulation model.

[0220] In some embodiments, if the second device 102 sends the second information under different conditions or sends the second information multiple times, for example, the target data corresponding to the different second information sent multiple times may be the same or different.

[0221] Optionally, the first device 101 can receive second information under different conditions. Due to changes in the channel environment and / or channel parameter configuration, the first device 101 can obtain different data to be demodulated each time it receives second information, thereby obtaining more input training samples.

[0222] In some embodiments, training or updating of the demodulation model may be stopped when any of the following conditions are met:

[0223] The training or update time reaches a first duration, which can be defined by the protocol or determined by the first device 101 and the second device 102;

[0224] The number of iterations for training or updating the demodulation model reaches a predetermined number, which can be defined by the protocol or determined by the first device 101 and the second device 102;

[0225] The trained or updated demodulation model has reached a convergence metric, such as the output of the demodulation model meeting a predefined performance metric.

[0226] Optionally, the predefined performance metrics include, but are not limited to, a predefined error, which indicates that the training or update of the demodulation model is complete when the error between the output of the demodulation model and the ideal target output (such as target data) is less than or equal to the predefined error.

[0227] Optionally, if any of the above conditions are met, the training or update of the demodulation model is considered complete, and inference or application can be performed based on the demodulation model.

[0228] In step S2105, the second device 102 sends third information to the first device 101.

[0229] In some embodiments, the third information is information sent during the model inference or application phase of the demodulation model.

[0230] In some embodiments, the third information includes information modulated from the communication data. The communication data represents data that needs to be transmitted or demodulated by the first device 101 in actual communication.

[0231] Optionally, the third information may be modulation information in model inference or application.

[0232] In some embodiments, third information can be used to determine the actual input to the demodulation model in model inference or application.

[0233] In some embodiments, the first device 101 receives the aforementioned third information.

[0234] In step S2106, the first device 101 determines the demodulation data based on the trained or updated demodulation model and the third information.

[0235] In some embodiments, the first device 101 may perform preprocessing such as equalization or detection on the received third information to obtain the communication data to be demodulated in the third information.

[0236] In some embodiments, the communication data to be demodulated is taken as input, and the demodulated data corresponding to the communication data is output using the demodulation model.

[0237] In some embodiments, the demodulation model trained or updated by the model has good generalization and robustness and can accurately obtain demodulated data.

[0238] The communication method involved in the embodiments of this disclosure may include at least one of steps S2101 to S2106.

[0239] For example, step S2102 can be implemented as an independent embodiment, steps S2102 to S2104 can be implemented as an independent embodiment, and steps S2102, S2105 to S2106 can be implemented as an independent embodiment, but are not limited thereto.

[0240] In some embodiments, steps S2101, S2105, and S2106 are optional, and one of them may be performed in different embodiments, or one or more of these steps may be omitted or substituted in different embodiments.

[0241] In some embodiments, steps S2101, S2103, and S2104 are optional, and one of them may be performed in different embodiments, or one or more of these steps may be omitted or substituted in different embodiments.

[0242] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0243] Figure 2B is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure. As shown in Figure 2B, the present disclosure relates to a communication method, which includes:

[0244] In step S2201, the second device 102 determines or selects training samples.

[0245] In some embodiments, the second device 102 may be a terminal or a network device.

[0246] In some embodiments, the implementation of step S2201 can be referred to the implementation of step S2101 in FIG2A, and will not be repeated here. For example, the training samples or the method of selecting training samples can be referred to the description of step S2101.

[0247] In step S2202, the second device 102 sends the first information to the first device 101.

[0248] In some embodiments, the implementation of step S2202 can be referred to the implementation of step S2102 in FIG2A, and will not be repeated here. For example, the first information or the method of sending the first information can be referred to the description of step S2102.

[0249] In step S2203, the second device 102 sends the second information to the first device 101.

[0250] In some embodiments, the implementation of step S2203 can be referred to the implementation of step S2103 in FIG2A, and will not be repeated here.

[0251] In step S2204, the first device 101 determines the input of the demodulation model based on the second information, and trains or updates the demodulation model using the target data as the target output.

[0252] In some embodiments, the implementation of step S2204 can be referred to the implementation of step S2104 in FIG2A, and will not be repeated here.

[0253] In step S2205, the second device 102 sends third information to the first device 101.

[0254] In some embodiments, the implementation of step S2205 can be referred to the implementation of step S2105 in FIG2A, and will not be repeated here.

[0255] In step S2206, the first device 101 determines the demodulation data based on the trained or updated demodulation model and the third information.

[0256] In some embodiments, the implementation of step S2206 can be found in the implementation of step S2106 in FIG2A, and will not be repeated here.

[0257] The communication method involved in the embodiments of this disclosure may include at least one of steps S2201 to S2206.

[0258] For example, step S2202 can be implemented as an independent embodiment, steps S2202 to S2204 can be implemented as an independent embodiment, and steps S2202, S2205 to S2206 can be implemented as independent embodiments, but are not limited thereto.

[0259] In some embodiments, steps S2201, S2205, and S2206 are optional, and one of them may be performed in different embodiments, or one or more of these steps may be omitted or substituted in different embodiments.

[0260] In some embodiments, steps S2201, S2203, and S2204 are optional, and one of them may be performed in different embodiments, or one or more of these steps may be omitted or substituted in different embodiments.

[0261] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0262] Figure 3A is an interactive schematic diagram illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 3A, this embodiment of the present disclosure relates to a communication method, which includes:

[0263] In step S3101, the first device 101 and the second device 102 transmit the first information.

[0264] For example, the first device 101 sends the first information to the second device 102, or the second device 102 sends the first information to the first device 101.

[0265] In some embodiments, the first information includes training samples used to train or update the demodulation model.

[0266] In some embodiments, the training samples include at least one of the following:

[0267] One or more target data;

[0268] The amount of target data.

[0269] In some embodiments, the target data satisfies at least one of the following:

[0270] Generated based on a predefined method;

[0271] Use a predefined data sequence.

[0272] In some embodiments, the first device 101 may determine or select training samples on its own.

[0273] In some embodiments, the first device 101 is a terminal or network device.

[0274] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0275] Figure 3B is an interactive schematic diagram illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 3B, this embodiment of the present disclosure relates to a communication method, which includes:

[0276] In step S3201, the first device 101 and the second device 102 transmit the first information.

[0277] For example, the first device 101 sends the first information to the second device 102, or the second device 102 sends the first information to the first device 101.

[0278] In some embodiments, the implementation of step S3201 can be referred to the implementation of step S3101 in FIG3A, and will not be repeated here.

[0279] In step S3202, the second device 102 sends the second information to the first device 101.

[0280] In some embodiments, the implementation of step S3202 can be referred to the implementation of step S2103 in FIG2A, and will not be repeated here.

[0281] In some embodiments, the second device 102 may send second information under different conditions, wherein the conditions include channel environment and / or channel parameter configuration.

[0282] In some embodiments, the second information transmitted under different conditions includes information modulated from the same target data.

[0283] In step S3203, the first device 101 determines the input of the demodulation model based on the second information, and trains or updates the demodulation model using the target data as the target output.

[0284] In some embodiments, the implementation of step S3203 can be referred to the implementation of step S2104 in FIG2A, and will not be repeated here.

[0285] In some embodiments, the first device 101 can perform model inference or application phases based on a trained or updated demodulation model.

[0286] For example, in some embodiments, the method may further include: the second device 102 sending third information to the first device 101, the third information including information after modulation of the communication data; the first device 101 determining the demodulated data corresponding to the communication data based on the trained or updated demodulation model and the third information.

[0287] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0288] Figure 4 is an interactive schematic diagram of a communication method according to an embodiment of the present disclosure. As shown in Figure 4, the communication method involved in this embodiment of the present disclosure includes:

[0289] Step S4101: Data interaction between the receiving end and the sending end for model update.

[0290] In some embodiments, the transceiver devices perform data information exchange for AI demodulation model updates: that is, the sender or receiver selects one or more sets of data for AI demodulation model performance updates and sends an indicator to the other party.

[0291] Optionally, the indicator includes the number of data samples n used for model updates, and the data sample Data per data point. i Let i = 1, 2, ..., n. If model updates are required during model application, they will be performed based on this set of data; this set of data can be randomly generated or use simple data sequences such as all 0s or all 1s.

[0292] The main purpose of this step is to determine the data specifically used for model updates during subsequent model applications, similar to the pilot data used in channel transmission and reception. In this way, during model updates, the transmitter uses this data as the original transmission data, and the receiver uses it as the target output for model training, thus achieving model updates.

[0293] In some embodiments, the receiving end corresponds to the first device 101 in the foregoing embodiments, and the sending end corresponds to the second device in the foregoing embodiments.

[0294] In some embodiments, the Indicator corresponds to the first information in the foregoing embodiments.

[0295] In some embodiments, step S4101 corresponds to step S2102 or step S2202 in the foregoing embodiments.

[0296] In step S4102, the transmitting end completes data modulation and other processing.

[0297] In some embodiments, the transmitting end uses the Data for model performance monitoring determined in step S4101 as the original transmission data, completes data modulation and other processing, and generates a data signal to be transmitted.

[0298] In some embodiments, the data signal to be transmitted corresponds to the second information in the foregoing embodiments.

[0299] Step S4103: The sending end transmits real-time data for model updating to the receiving end.

[0300] In some embodiments, data transmission can be performed in this step, such as the sending end sending the data signal to be transmitted to the receiving end.

[0301] In some embodiments, the real-time data corresponds to the second information used in the model training or update process in the foregoing embodiments.

[0302] In step S4104, the receiving end completes data demodulation and other processing.

[0303] In some embodiments, the receiving end acquires the received signal and acquires the data to be demodulated.

[0304] Step S4105: The receiving end updates the AI ​​demodulation model.

[0305] In some embodiments, due to real-time changes in the channel environment, the same original transmitted data will result in different demodulated data received by the receiver after channel transmission. Therefore, the transmitter can repeatedly transmit n sample data, and the receiver can reuse the data for model updates. The receiver processes the received signal to obtain the demodulated data. The model is updated by using the data to be demodulated as input to the AI ​​demodulation model and using the data used for model updating as the target output.

[0306] In some embodiments, step S4105 corresponds to step S2104 or S2204 in the foregoing embodiments.

[0307] Step S4106: The sending end transmits real-time data to the receiving end.

[0308] In some embodiments, step S4106 corresponds to step S2105 or S2205 in the foregoing embodiments.

[0309] Step S4107: The receiving end performs real-time data demodulation.

[0310] In some embodiments, the receiving end completes subsequent real-time data demodulation based on the updated AI demodulation model.

[0311] In some embodiments, step S4107 corresponds to step S2106 or S2206 in the foregoing embodiments.

[0312] In some embodiments of this disclosure, when the application environment or parameter configuration of the AI-based data demodulation model differs from that during model training in actual system applications, it is necessary to consider the generalization ability of the AI ​​demodulation model and apply common generalization enhancement methods to ensure model application performance. Model updating is a common method to enhance the generalization ability of AI models, and ideal label data collection is a key step in the model updating process. It is necessary to clarify the data collection methods used for updating the AI ​​demodulation model in the actual system to effectively update the model and ensure its stable operation.

[0313] In some embodiments, the method of this disclosure, which is a method for using model updates to ensure the generalization of AI demodulation models, can be used for data collection for AI demodulation model updates, effectively obtaining ideal label data for model updates, enabling the model to process real-time data under actual application environments or parameter configurations, thereby ensuring better AI demodulation model performance.

[0314] In some embodiments, for data transmission in a real communication system, the original data from the transmitting end is transmitted to the receiving end via a wireless channel after modulation and other steps. Due to factors such as channel noise and non-ideal device characteristics, the data obtained by the receiving end after demodulation and other steps has a certain error compared to the original data sent by the transmitting end. Updating the AI ​​demodulation model requires ideal tag data, including the data to be demodulated and the corresponding ideal demodulation data. In conventional signal transmission and reception processes, ideal demodulation data is difficult to obtain. The method of this disclosure can be used as a data collection method for AI demodulation model updates, enabling the receiving end to obtain ideal demodulation data corresponding to the data to be demodulated and identical to the original data sent by the transmitting end for AI demodulation model updates.

[0315] In some embodiments, the method of this disclosure can effectively obtain ideal label data for model updates, enabling the model to process real-time data under actual application environments or parameter configurations, thereby ensuring better AI demodulation model performance.

[0316] In some embodiments, the present disclosure can address the generalization problem of AI demodulation models in actual system applications, realize data collection for model updates during model system applications, help achieve efficient AI demodulation model updates to ensure the demodulation accuracy of AI demodulation model data, and thus effectively improve the practicality of AI-based demodulation schemes.

[0317] The communication method involved in the embodiments of this disclosure may include at least one of steps S4101 to S4106. For example, step S4101 may be implemented as a standalone embodiment, but is not limited thereto.

[0318] In some embodiments, the steps and their optional implementations in other embodiments described before or after this embodiment, as well as other related parts in the specification, can be referred to, and will not be repeated here.

[0319] This disclosure also proposes an apparatus (also referred to as a communication device, etc.) for implementing any of the above methods. For example, an apparatus is proposed that includes units or modules for implementing the steps performed by the terminal in any of the above methods. Furthermore, another apparatus is proposed that includes units or modules for implementing the steps performed by a network device (e.g., an access network device, a core network functional node, a core network device, etc.) in any of the above methods.

[0320] It should be understood that the division of units or modules in the above device is only a logical functional division. In actual implementation, they can be fully or partially integrated into a single physical entity, or they can be physically separated. Furthermore, the units or modules in the device can be implemented by a processor calling software: for example, the device includes a processor connected to a memory containing instructions. The processor calls the instructions stored in the memory to implement any of the above methods or to implement the functions of the units or modules in the above device. The processor can be, for example, a general-purpose processor, such as a Central Processing Unit (CPU) or a microprocessor, and the memory can be internal or external to the device. Alternatively, the units or modules in the device can be implemented in the form of hardware circuits. The functionality of some or all of the units or modules can be achieved through the design of these hardware circuits, which can be understood as one or more processors. For example, in one implementation, the hardware circuit is an application-specific integrated circuit (ASIC). The functionality of some or all of the units or modules is achieved through the design of the logical relationships between the components within the circuit. In another implementation, the hardware circuit can be implemented using a programmable logic device (PLD). Taking a field-programmable gate array (FPGA) as an example, it can include a large number of logic gates. The connection relationships between the logic gates are configured through configuration files, thereby achieving the functionality of some or all of the units or modules. All units or modules of the above device can be implemented entirely through processor-called software, entirely through hardware circuits, or partially through processor-called software with the remaining parts implemented through hardware circuits.

[0321] In this embodiment, the processor is a circuit with signal processing capabilities. In one implementation, the processor can be a circuit with instruction read and execute capabilities, such as a Central Processing Unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), or a digital signal processor (DSP). In another implementation, the processor can implement certain functions through the logical relationships of hardware circuits. The logical relationships of the aforementioned hardware circuits are fixed or reconfigurable. For example, the processor is a hardware circuit implemented using an application-specific integrated circuit (ASIC) or a programmable logic device (PLD), such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document and configuring the hardware circuit can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units or modules. Furthermore, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as a Neural Network Processing Unit (NPU), a Tensor Processing Unit (TPU), or a Deep Learning Processing Unit (DPU).

[0322] Figure 5A is a schematic diagram of a communication device proposed in an embodiment of this disclosure. The communication device 5100 is used to perform any of the above methods. In some embodiments, as shown in Figure 5A, the communication device 5100 may include at least one of a transceiver module 5101, a processing module 5102, etc. In some embodiments, the transceiver module 5101 is used to send first information to a second device, or to receive first information sent by the second device; wherein the first information includes training samples for training or updating the demodulation model. Optionally, the transceiver module 5101 is used to perform at least one of the communication steps (e.g., step S2102, but not limited thereto) performed by the first device 101 in any of the above methods, which will not be described in detail here. Optionally, the processing module 5102 is used to perform at least one of the other steps (e.g., steps S2101, S2104, S2106, but not limited thereto) performed by the first device 101 in any of the above methods, which will not be described in detail here.

[0323] Figure 5B is a schematic diagram of the structure of a communication device proposed in an embodiment of this disclosure. The communication device 5200 is used to execute any of the above methods. In some embodiments, as shown in Figure 5B, the communication device 5200 may include at least one of a transceiver module 5201, a processing module 5202, etc. In some embodiments, the transceiver module 5201 is used to receive first information sent by a first device, or to send first information to the first device; wherein the first information includes training samples for training or updating the demodulation model. Optionally, the transceiver module 5201 is used to execute at least one of the communication steps (e.g., steps S2103 or S2105, but not limited thereto) executed by the second device 102 in any of the above methods, which will not be elaborated here. Optionally, the processing module 5202 is used to execute at least one of other steps (e.g., step S2201, but not limited thereto) executed by the second device 102 in any of the above methods, which will not be elaborated here.

[0324] In some embodiments, the transceiver module may include a transmitting module and / or a receiving module, which may be separate or integrated. Optionally, the transceiver module may be interchangeable with a transceiver.

[0325] In some embodiments, the processing module may be a single module or may include multiple sub-modules. Optionally, the multiple sub-modules may each perform all or part of the steps required by the processing module.

[0326] In some embodiments, the processing module can be replaced by the processor, and the transceiver module can be replaced by the transceiver.

[0327] Figure 6A is a schematic diagram of the structure of the communication device 6100 proposed in an embodiment of this disclosure. The communication device 6100 can be a network device (e.g., access network device, core network device, etc.), a terminal (e.g., user equipment, etc.), a chip, chip system, or processor that supports the network device in implementing any of the above methods, or a chip, chip system, or processor that supports the terminal in implementing any of the above methods. The communication device 6100 can be used to implement the methods described in the above method embodiments; for details, please refer to the descriptions in the above method embodiments.

[0328] As shown in Figure 6A, the communication device 6100 is used to execute any of the above methods. In some embodiments, the communication device 6100 includes one or more processors 6101. The processor 6101 may be a general-purpose processor or a special-purpose processor, such as a baseband processor or a central processing unit. The baseband processor may be used to process communication protocols and communication data, and the central processing unit may be used to control communication devices (e.g., base stations, baseband chips, terminal devices, terminal device chips, DUs or CUs, etc.), execute programs, and process program data. Optionally, the communication device 6100 is used to execute any of the above methods. Optionally, one or more processors 6101 are used to invoke instructions to cause the communication device 6100 to execute any of the above methods.

[0329] In some embodiments, the communication device 6100 further includes one or more transceivers 6102. When the communication device 6100 includes one or more transceivers 6102, the transceiver 6102 performs at least one of the communication steps such as sending and / or receiving in the above method (e.g., steps S2102, S2103, or S2105, but not limited thereto), and the processor 6101 performs at least one of the other steps (e.g., steps S2101, S2104, or S2106, but not limited thereto). In optional embodiments, the transceiver may include a receiver and / or a transmitter, which may be separate or integrated together. Optionally, the terms transceiver, transceiver unit, transceiver, transceiver circuit, interface circuit, interface, etc., can be used interchangeably; the terms transmitter, transmitting unit, transmitter, transmitting circuit, etc., can be used interchangeably; the terms receiver, receiving unit, receiver, receiving circuit, etc., can be used interchangeably.

[0330] In some embodiments, the communication device 6100 further includes one or more memories 6103 for storing data and / or instructions. Optionally, one or more processors 6101 are used to invoke instructions stored in the memory 6103 to cause the communication device 6100 to perform any of the above methods. Optionally, all or part of the memory 6103 may also be located outside the communication device 6100. In optional embodiments, the communication device 6100 may include one or more interface circuits 6104. Optionally, the interface circuit 6104 is connected to the memory 6103 and can be used to receive data and / or instructions from the memory 6103 or other devices, and can be used to send data and / or instructions to the memory 6103 or other devices. For example, the interface circuit 6104 can read data and / or instructions stored in the memory 6103 and can be used to send data and / or instructions to the memory 6103 or other devices. For example, the interface circuit 6104 can read data and / or instructions stored in the memory 6103 and send the data and / or instructions to the processor 6101.

[0331] The communication device 6100 described in the above embodiments may be a network device or a terminal, but the scope of the communication device 6100 described in this disclosure is not limited thereto, and the structure of the communication device 6100 may not be limited by FIG. 6A. The communication device may be a standalone device or a part of a larger device. For example, the communication device may be: (1) a standalone integrated circuit IC, or chip, or chip system or subsystem; (2) a collection of one or more ICs, optionally, the IC collection may also include storage components for storing data, programs and / or instructions; (3) an ASIC, such as a modem; (4) a module that can be embedded in other devices; (5) a receiver, terminal device, smart terminal device, cellular phone, wireless device, handheld device, mobile unit, vehicle device, network device, cloud device, artificial intelligence device, etc.; (6) others, etc.

[0332] Figure 6B is a schematic diagram of the structure of chip 6200 according to an embodiment of this disclosure. For cases where the communication device 6100 can be a chip or a chip system, please refer to the schematic diagram of chip 6200 shown in Figure 6B, but it is not limited thereto.

[0333] Chip 6200 includes one or more processors 6201. Chip 6200 is used to perform any of the methods described above.

[0334] In some embodiments, chip 6200 further includes one or more interface circuits 6202. Optionally, terms such as interface circuit, interface, and transceiver pin can be used interchangeably. In some embodiments, chip 6200 further includes one or more memories 6203 for storing data and / or instructions. Optionally, all or part of the memories 6203 may be located outside of chip 6200. Optionally, interface circuit 6202 is connected to memory 6203, and interface circuit 6202 can be used to receive data and / or instructions from memory 6203 or other devices, and interface circuit 6202 can be used to send data and / or instructions to memory 6203 or other devices. For example, interface circuit 6202 can read data and / or instructions stored in memory 6203 and send the data and / or instructions to processor 6201.

[0335] In some embodiments, the interface circuit 6202 performs at least one of the communication steps such as sending and / or receiving in the above-described method (e.g., steps S2102, S2103, or S2105, but not limited thereto). The interface circuit 6202 performing the communication steps such as sending and / or receiving in the above-described method refers, for example, to the interface circuit 6202 performing data and / or instruction interaction between the processor 6201, the chip 6200, the memory 6203, or the transceiver device. In some embodiments, the processor 6201 performs at least one of other steps (e.g., steps S2101, S2104, or S2106, but not limited thereto).

[0336] The modules and / or devices described in the various embodiments, such as virtual devices, physical devices, and chips, can be combined or separated arbitrarily as needed. Optionally, some or all steps can also be performed collaboratively by multiple modules and / or devices, which is not limited here.

[0337] This disclosure also proposes a storage medium storing instructions that, when executed on the communication device 6100, cause the communication device 6100 to perform any of the above methods. Optionally, the storage medium is an electronic storage medium. Optionally, the storage medium is a computer-readable storage medium, but not limited thereto; it may also be a storage medium readable by other devices. Optionally, the storage medium may be a non-transitory storage medium, but not limited thereto; it may also be a temporary storage medium.

[0338] This disclosure also proposes a program product, including a program and / or instructions, which, when executed by the communication device 6100, cause the communication device 6100 to perform any of the above methods. Optionally, the program product is a computer program product. Optionally, the program product is stored on the storage medium.

[0339] This disclosure also proposes a computer program that, when run on a computer, causes the computer to perform any of the above methods. Industrial applicability

[0340] The first and second devices communicate and negotiate training samples for model training or updates, thereby facilitating the acquisition of ideal training samples during model application and improving the accuracy and reliability of model training.

Claims

1. A communication method, performed by a first device, the method comprising: Sending first information to a second device, or receiving first information sent by the second device; wherein the first information includes training samples, which are used to train or update the demodulation model.

2. The method as described in claim 1, wherein, The training samples include: one or more target data; The first information also includes: the quantity of the target data.

3. The method as described in claim 2, wherein, The target data satisfies at least one of the following: Generated based on a predefined method; Use a predefined data sequence.

4. The method as described in claim 2 or 3, wherein, The method further includes: Receive second information sent by the second device, the second information including information modulated on the target data; The input to the demodulation model is determined based on the second information, and the target data is used as the target output to train or update the demodulation model.

5. The method of claim 4, wherein, The receipt of the second information sent by the second device includes: The second information is received from the second device under different conditions, wherein the conditions include at least one of the following: channel environment and channel parameter configuration.

6. The method of claim 5, wherein, The second information transmitted under different conditions includes information modulated from the same target data.

7. The method of claim 4, wherein, The receipt of the second information sent by the second device includes: The device receives N second messages sent by the second device, where N is the number of target data; wherein each of the N second messages includes information modulated on a target data.

8. The method according to any one of claims 1 to 7, wherein, The method further includes: Receive third information sent by the second device, the third information including information modulated from the communication data; Based on the trained or updated demodulation model and the third information, the demodulation data corresponding to the communication data is determined.

9. The method according to any one of claims 1 to 8, wherein, The method further includes: Determine or select the training samples.

10. The method according to any one of claims 1 to 9, wherein, The first device is a terminal or network device.

11. A communication method performed by a second device, the method comprising: Receive first information sent by a first device, or send first information to the first device; wherein the first information includes training samples, which are used to train or update the demodulation model.

12. The method of claim 11, wherein, The training samples include: one or more target data; The first information also includes: the quantity of target data.

13. The method of claim 12, wherein, The target data satisfies at least one of the following: Generated based on a predefined method; Use a predefined data sequence.

14. The method of claim 12 or 13, wherein, The method further includes: Send a second message to the first device, the second message including information modulated on the target data; wherein the second message and the target data are used by the first device to train or update the demodulation model.

15. The method of claim 14, wherein, Sending the second information to the first device includes: The second information is sent to the first device under different conditions, wherein the conditions include at least one of the following: channel environment, channel parameter configuration.

16. The method of claim 15, wherein, The second information transmitted under different conditions includes information after the same modulation of the same target data.

17. The method of claim 14, wherein, Sending the second information to the first device includes: N second messages are sent to the first device, where N is the number of target data; wherein each of the N second messages includes information modulated on a target data.

18. The method as claimed in any one of claims 11 to 17, wherein, The method further includes: Send a third message to the first device, the third message including information modulated from the communication data; wherein, the first device... It is used to determine the demodulated data corresponding to the communication data based on the trained or updated demodulation model and the third information.

19. The method as claimed in any one of claims 11 to 18, wherein, The method further includes: Determine or select the training samples.

20. The method of any one of claims 11 to 19, wherein, The second device is a terminal or network device.

21. A communication device, wherein, The communication device is used to perform the method according to any one of claims 1 to 10 or any one of claims 11 to 20.

22. A communication system, comprising a first device and a second device, wherein, The first device is configured to implement the method as described in any one of claims 1 to 10; The second device is configured to implement the method as described in any one of claims 11 to 20.

23. A storage medium storing instructions, wherein, When the instructions are executed on the communication device, the communication device performs the method as described in any one of claims 1 to 10 or any one of claims 11 to 20.

24. A program product comprising at least one of a program and instructions, wherein, When at least one of the programs or instructions is executed by a communication device, it implements the method as described in any one of claims 1 to 10 or any one of claims 11 to 20.

Images