Communication method, device, communication system and storage medium

Abstract

Provided in the present disclosure are a communication method, a device, a communication system and a storage medium. The method comprises: sending a sample bit sequence to a sending-end device; receiving a sample modulation symbol sent by the sending-end device; and receiving a sample symbol to be demodulated that is sent by a receiving-end device, wherein the sample symbol to be demodulated is determined by the receiving-end device on the basis of the sample modulation symbol sent by the sending-end device, and the sample modulation symbol and the sample symbol to be demodulated are used for training an intermediate model so as to obtain a trained intermediate model. In the present disclosure, the sample modulation symbol and the sample symbol to be demodulated can be determined by means of the interaction between a first device and the sending-end device and the receiving-end device, so as to train the intermediate model, thereby improving data transmission accuracy, improving the performance of a communication system, and achieving high availability.

Description

Communication methods, devices, systems and storage media Technical Field

[0001] This disclosure relates to the field of communications, and in particular to communication methods, devices, systems and storage media. Background Technology

[0002] To meet the service demands of high-speed data transmission, massive broadband traffic, and reliable communication in mobile scenarios, and ultimately realize future wireless communication visions such as smart cities and smart transportation, current wireless communication networks still require improvement and enhancement in many aspects. Among these, accurate signal 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. Summary of the Invention

[0003] To improve the performance of communication systems, embodiments of this disclosure provide a communication method, device, system, and storage medium.

[0004] According to a first aspect of the present disclosure, a communication method is provided, the method being performed by a first device, the method comprising:

[0005] Sending a sample bit sequence to the transmitting device; wherein the sample bit sequence is used to jointly train the modulation model and the demodulation model, the modulation model, the trained intermediate model and the demodulation model are connected in sequence, and the trained intermediate model is used to simulate at least the channel transmission process between the transmitting device and the receiving device;

[0006] Receive sample modulation symbols sent by the transmitting device;

[0007] The receiving end device receives sample demodulation symbols sent by the receiving end device; wherein the sample demodulation symbols are determined by the receiving end device based on the sample modulation symbols sent by the transmitting end device; wherein the sample modulation symbols and the sample demodulation symbols are used to train an intermediate model to obtain the trained intermediate model.

[0008] According to a second aspect of the present disclosure, a communication method is provided, the method being performed by a transmitting device, the method comprising:

[0009] Receive the sample bit sequence sent by the first device;

[0010] Perform a first operation on the sample bit sequence to obtain a sample modulation symbol; wherein the first operation includes at least a modulation operation;

[0011] The sample modulation symbol is sent to the first device.

[0012] According to a third aspect of the present disclosure, a communication method is provided, the method being performed by a receiving device, the method comprising:

[0013] The receiving end device receives sample modulation symbols transmitted through a channel to obtain a received signal; wherein, the sample modulation symbols are obtained by the receiving end device performing a first operation on the sample bit sequence after receiving the sample bit sequence transmitted by the first device, and the first operation includes at least a modulation operation;

[0014] A second operation is performed on the received signal to obtain sample symbols to be demodulated;

[0015] The sample to be demodulated symbol is sent to the first device.

[0016] According to a fourth aspect of the present disclosure, a first device is provided, comprising:

[0017] The transceiver module is configured to send a sample bit sequence to the transmitting device; wherein the sample bit sequence is used to jointly train the modulation model and the demodulation model, the modulation model, the trained intermediate model and the demodulation model are connected in sequence, and the trained intermediate model is used to simulate at least the channel transmission process between the transmitting device and the receiving device.

[0018] The transceiver module is also configured to receive sample modulation symbols sent by the transmitting device;

[0019] The transceiver module is further configured to receive sample demodulation symbols sent by the receiving device; wherein the sample demodulation symbols are determined by the receiving device based on the sample modulation symbols sent by the transmitting device; wherein the sample modulation symbols and the sample demodulation symbols are used to train an intermediate model to obtain the trained intermediate model.

[0020] According to a fifth aspect of the present disclosure, a transmitting end device is provided, comprising:

[0021] The transceiver module is configured to receive a sample bit sequence sent by the first device;

[0022] The processing module is configured to perform a first operation on the sample bit sequence to obtain a sample modulation symbol; wherein the first operation includes at least a modulation operation;

[0023] The transceiver module is further configured to send the sample modulation symbols to the first device. According to a sixth aspect of this disclosure, a receiving device is provided, comprising:

[0024] The transceiver module is configured to receive sample modulation symbols transmitted by the transmitting device through the channel to obtain a received signal; wherein the sample modulation symbols are obtained by the transmitting device performing a first operation on the sample bit sequence after receiving the sample bit sequence transmitted by the first device, and the first operation includes at least a modulation operation;

[0025] The processing module is configured to perform a second operation on the received signal to obtain sample symbols to be demodulated;

[0026] The transceiver module is also configured to send the sample demodulation symbols to the first device.

[0027] According to a seventh aspect of the present disclosure, a first device is provided, comprising:

[0028] One or more processors;

[0029] The processor is used to execute the method described in any one of the first aspects.

[0030] According to an eighth aspect of the present disclosure, a transmitting device is provided, comprising:

[0031] One or more processors;

[0032] The processor is used to execute the method described in any one of the second aspects.

[0033] According to a ninth aspect of the present disclosure, a receiving device is provided, comprising:

[0034] One or more processors;

[0035] The processor is used to execute the method described in any one of the third aspects.

[0036] According to a tenth aspect of the present disclosure, a communication system is provided, comprising:

[0037] A first device, the first device being configured to perform the method described in any one of the first aspects;

[0038] A transmitting device, the transmitting device being configured to perform the method described in any one of the second aspects;

[0039] A receiving device configured to perform the method described in any one of the third aspects.

[0040] According to an eleventh aspect of the present disclosure, a storage medium is provided that stores instructions that, when executed on a communication device, cause the communication device to perform a communication method as described in any one of the first, second, or third aspects.

[0041] According to a twelfth aspect of the present disclosure, a computer program product is provided, including a computer program that, when executed by a processor, is used to implement the communication method described in any one of the first, second, or third aspects.

[0042] In this embodiment of the disclosure, the sample modulation symbol and sample demodulation symbol can be determined through the interaction between the first device and the transmitting and receiving devices, so as to train the intermediate model. The trained intermediate model can be located between the modulation model and the demodulation model, so that the modulation model and the demodulation model can be jointly trained offline, which improves the accuracy of data transmission, improves the performance of the communication system, and has high availability.

[0043] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit this disclosure. Attached Figure Description

[0044] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0045] Figure 1A is an exemplary schematic diagram of the architecture of a communication system provided according to an embodiment of the present disclosure.

[0046] Figure 1B is an exemplary scenario diagram of an AI-based demodulation model provided according to an embodiment of the present disclosure.

[0047] Figure 1C is an exemplary schematic diagram of an AI demodulation scheme based on known modulation information provided in an embodiment of this disclosure.

[0048] Figure 1D is an exemplary schematic diagram of an AI demodulation scheme that does not require obtaining modulation scheme information according to an embodiment of the present disclosure.

[0049] Figure 1E is an exemplary schematic diagram of the mapping relationship between bit sequences and modulation symbols under the 16QAM modulation scheme provided in the embodiments of this disclosure.

[0050] Figure 1F is an exemplary scenario diagram of an AI-based modulation and demodulation model provided according to an embodiment of the present disclosure.

[0051] Figure 2A is one of the exemplary interactive schematic diagrams of a communication method provided according to an embodiment of the present disclosure.

[0052] Figure 2B is a second exemplary interactive schematic diagram of a communication method provided according to an embodiment of the present disclosure.

[0053] Figure 3A is one of the exemplary flowcharts of a communication method provided according to an embodiment of the present disclosure.

[0054] Figure 3B is a second exemplary flowchart of a communication method provided according to an embodiment of the present disclosure.

[0055] Figure 3C is a third exemplary flowchart of a communication method provided according to an embodiment of the present disclosure.

[0056] Figure 4 is an exemplary scenario diagram of joint training of modulation and demodulation models using an intermediate model according to an embodiment of the present disclosure.

[0057] Figure 5A is an exemplary block diagram of a first device provided according to an embodiment of the present disclosure.

[0058] Figure 5B is an exemplary block diagram of a transmitting device provided according to an embodiment of the present disclosure.

[0059] Figure 5C is an exemplary block diagram of a receiving device provided according to an embodiment of the present disclosure.

[0060] Figure 6A is an exemplary block diagram of a communication device provided according to an embodiment of the present disclosure.

[0061] Figure 6B is an exemplary block diagram of a chip provided according to an embodiment of the present disclosure. Detailed Implementation

[0062] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.

[0063] This disclosure provides a communication method, device, system, and storage medium.

[0064] In a first aspect, embodiments of this disclosure propose a communication method executed by a first device. The method includes: sending a sample bit sequence to a transmitting device; wherein the sample bit sequence is used to jointly train a modulation model and a demodulation model, the modulation model, the trained intermediate model, and the demodulation model are sequentially connected, and the trained intermediate model is used at least to simulate a channel transmission process between the transmitting device and a receiving device; receiving sample modulation symbols sent by the transmitting device; receiving sample demodulation symbols sent by the receiving device; wherein the sample demodulation symbols are determined by the receiving device based on the sample modulation symbols sent by the transmitting device; wherein the sample modulation symbols and the sample demodulation symbols are used to train the intermediate model to obtain the trained intermediate model.

[0065] In the above embodiments, the first device can acquire sample modulation symbols and sample demodulation symbols used to train the intermediate model, which improves the accuracy of data transmission, enhances the performance of the communication system, and increases its availability.

[0066] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes at least one of the following: randomly generating a set of sample bit sequences; setting the set of sample bit sequences according to rules; and receiving the set of sample bit sequences sent by the sending device.

[0067] In the above embodiments, the first device can determine the set of sample bit sequences in order to provide a training dataset for joint training, thereby improving the reliability of joint training.

[0068] In some embodiments, in conjunction with the first aspect, the method further includes: inputting sample modulation symbols into an intermediate model to obtain a first demodulated symbol output by the intermediate model; determining a second loss function based on the difference between the sample demodulated symbol corresponding to the sample modulation symbol and the first demodulated symbol; and training the intermediate model based on the second loss function until a second stopping condition is met, thereby stopping the training of the intermediate model and obtaining a trained intermediate model.

[0069] In the above embodiments, the first device can pre-train the intermediate model, which is simple to implement and highly usable.

[0070] In conjunction with some embodiments of the first aspect, in some embodiments, the second stopping condition includes at least one of the following: reaching a second number of training epochs; the second loss function decreasing to a second fault tolerance range; and the accuracy of the first demodulated symbol reaching a second value.

[0071] In the above embodiments, the first device can stop training the intermediate model when the second stopping condition is met, which improves the reliability and feasibility of intermediate model training and has high availability.

[0072] In some embodiments, in conjunction with the first aspect, the method further includes: inputting a sample bit sequence into the modulation model to obtain a first bit sequence output by the demodulation model; determining a first loss function based on the difference between the sample bit sequence and the first bit sequence; jointly training the modulation model and the demodulation model based on the first loss function; stopping the joint training when a first stopping condition is met, thereby obtaining a trained modulation model and a trained demodulation model.

[0073] In the above embodiments, the first device can perform joint training offline, which improves the feasibility and reliability of joint training of the modulation model and the demodulation model.

[0074] In conjunction with some embodiments of the first aspect, in some embodiments, the first stopping condition includes at least one of the following: reaching a first number of training epochs; the first loss function decreasing to a first fault tolerance range; and the accuracy of the first bit sequence reaching a first value.

[0075] In the above embodiments, the first device can stop joint training when the first stopping condition is met, which improves the reliability and feasibility of the joint training process and has high availability.

[0076] In conjunction with some embodiments of the first aspect, in some embodiments, the trained intermediate model is further used to perform at least one of the following on the input data: layer mapping; precoding; channel estimation; channel equalization.

[0077] In the above embodiments, the mapping relationship between modulation symbols and demodulation symbols can be learned through intermediate models, which improves the feasibility of joint training and has high usability.

[0078] In conjunction with some embodiments of the first aspect, in some embodiments, the method further includes at least one of the following: sending first network parameters to the transmitting device; wherein the first network parameters are network parameters of a trained modulation model; and sending second network parameters to the receiving device; wherein the second network parameters are network parameters of a trained demodulation model.

[0079] In the above embodiments, after completing joint training, the first device directly provides the corresponding network parameters to the transmitting device and the receiving device, and the transmitting device and the receiving device deploy the modulation model and the demodulation model respectively, which improves the accuracy of data transmission, improves the performance of the communication system, and has high availability.

[0080] Secondly, embodiments of this disclosure provide a communication method executed by a transmitting device, the method comprising: receiving a sample bit sequence transmitted by a first device; performing a first operation on the sample bit sequence to obtain a sample modulation symbol; wherein the first operation includes at least a modulation operation; and transmitting the sample modulation symbol to the first device.

[0081] In conjunction with some embodiments of the second aspect, in some embodiments, the first operation further includes at least one of the following: a layer mapping operation; a precoding operation.

[0082] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes: transmitting the sample modulation symbols to a receiving device via a channel.

[0083] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes: sending a set of sample bit sequences to the first device.

[0084] In conjunction with some embodiments of the second aspect, in some embodiments, the method further includes: receiving first network parameters sent by the first device; wherein the first network parameters are network parameters of a trained modulation model; and deploying the modulation model based on the first network parameters.

[0085] Thirdly, embodiments of this disclosure propose a communication method, which is executed by a receiving device. The method includes: receiving sample modulation symbols transmitted by a transmitting device through a channel to obtain a received signal; wherein the sample modulation symbols are obtained by the transmitting device performing a first operation on the sample bit sequence after receiving a sample bit sequence transmitted by a first device, the first operation including at least a modulation operation; performing a second operation on the received signal to obtain sample demodulation symbols; and transmitting the sample demodulation symbols to the first device.

[0086] In conjunction with some embodiments of the third aspect, in some embodiments, the second operation includes at least one of the following: channel estimation operation; channel equalization operation.

[0087] In some embodiments, in conjunction with the third aspect, the method further includes: receiving second network parameters sent by a first device; wherein the second network parameters are network parameters of a trained demodulation model; and deploying the demodulation model based on the second network parameters.

[0088] Fourthly, embodiments of this disclosure propose a first device, comprising: a transceiver module configured to transmit a sample bit sequence to a transmitting device; wherein the sample bit sequence is used for joint training of a modulation model and a demodulation model, the modulation model, the trained intermediate model, and the demodulation model being sequentially connected, and the trained intermediate model being used at least to simulate the channel transmission process between the transmitting device and the receiving device; the transceiver module is further configured to receive sample modulation symbols transmitted by the transmitting device; the transceiver module is further configured to receive sample demodulation symbols transmitted by the receiving device; wherein the sample demodulation symbols are determined by the receiving device based on the sample modulation symbols transmitted by the transmitting device; wherein the sample modulation symbols and the sample demodulation symbols are used to train the intermediate model to obtain the trained intermediate model.

[0089] Fifthly, embodiments of this disclosure provide a transmitting end device, comprising: a transceiver module configured to receive a sample bit sequence transmitted by a first device; a processing module configured to perform a first operation on the sample bit sequence to obtain sample modulation symbols; wherein the first operation includes at least a modulation operation; the transceiver module is further configured to transmit the sample modulation symbols to the first device. Sixthly, embodiments of this disclosure provide a receiving end device, comprising: a transceiver module configured to receive sample modulation symbols transmitted by the transmitting end device through a channel to obtain a received signal; wherein the sample modulation symbols are obtained by the transmitting end device performing a first operation on the sample bit sequence after receiving it from the first device, the first operation including at least a modulation operation; a processing module configured to perform a second operation on the received signal to obtain sample demodulation symbols; the transceiver module is further configured to transmit the sample demodulation symbols to the first device.

[0090] In a seventh aspect, embodiments of this disclosure provide a first device comprising: one or more processors; wherein the processors are configured to perform the method described in any one aspect.

[0091] Eighthly, embodiments of this disclosure provide a transmitting device comprising: one or more processors; wherein the processors are configured to perform the method described in any one of the second aspects.

[0092] In a ninth aspect, embodiments of this disclosure provide a receiving device comprising: one or more processors; wherein the processors are configured to perform the method described in any one of the third aspects.

[0093] In a tenth aspect, embodiments of this disclosure provide a communication system comprising: a first device configured to perform the method described in any one aspect; a transmitting device configured to perform the method described in any one aspect; and a receiving device configured to perform the method described in any one aspect.

[0094] Eleventhly, embodiments of this disclosure provide a storage medium storing instructions that, when executed on a communication device, cause the communication device to perform a communication method as described in any one of the first, second, or third aspects.

[0095] In a twelfth aspect, embodiments of this disclosure provide a computer program product including a computer program that, when executed by a processor, is used to implement the communication method described in any one of the first, second, or third aspects.

[0096] It is understood that the aforementioned first device, transmitting device, receiving device, communication system, storage medium, program product, etc., are all used to execute the method proposed in the embodiments of this disclosure. Therefore, the beneficial effects that can be achieved can be referred to the beneficial effects in the corresponding methods, and will not be repeated here.

[0097] This disclosure provides a communication method, device, system, and storage medium. In some embodiments, the terms "communication method" and "neural network training method," "information transmission method," etc., may be used interchangeably.

[0098] 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.

[0099] 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.

[0100] 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.

[0101] In the embodiments disclosed herein, "multiple" refers to two or more.

[0102] 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.

[0103] 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.

[0104] 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.

[0105] 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.

[0106] In some embodiments, “including A,” “containing A,” “for indicating A,” and “carrying A” can be interpreted as directly carrying A or indirectly indicating A.

[0107] 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.

[0108] 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”.

[0109] 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.

[0110] In some embodiments, "network" can be interpreted as devices included in a network (e.g., access network devices, core network devices, etc.).

[0111] 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.

[0112] 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.

[0113] 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.

[0114] 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.

[0115] In some embodiments, the acquisition of data, information, etc., may comply with the laws and regulations of the country where the location is situated.

[0116] In some embodiments, data, information, etc., may be obtained with the user's consent.

[0117] 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.

[0118] Figure 1A is a schematic diagram of the architecture of a communication system according to an embodiment of the present disclosure.

[0119] As shown in Figure 1A, the communication system 100 includes at least one of a first device 101, a transmitting device 102, and a receiving device 103.

[0120] In some embodiments, the first device 101 can be used to train the modulation model and the demodulation model offline.

[0121] In one example, a modulation model can be used to modulate an input bit sequence to output a modulation symbol.

[0122] In one example, the modulation model can be subsequently deployed on the transmitting device 102 to modulate the encoded bit sequence obtained on the transmitting device 102 and output modulation symbols.

[0123] In one example, a demodulation model can be used to demodulate the input symbol to be demodulated, thereby outputting a demodulated symbol.

[0124] In one example, the demodulation model can be subsequently deployed on the receiving device 103 to demodulate the symbols to be demodulated on the receiving device 103 and output the demodulated symbols.

[0125] In some embodiments, the first device 101 may include at least one of a terminal, a network device, and a server, which is not limited in this disclosure.

[0126] In some embodiments, the transmitting device 102 can be used to transmit data and / or signals.

[0127] In some embodiments, the transmitting device 102 may include at least one of a terminal and a network device, which is not limited in this disclosure.

[0128] In some embodiments, the receiving device 103 may be used to receive data and / or signals.

[0129] In some embodiments, the receiving device 103 may include at least one of a network device and a terminal, which is not limited in this disclosure.

[0130] In some embodiments, the aforementioned terminals include, but are 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.

[0131] In some embodiments, the network devices described above include at least one of access network devices and core network devices.

[0132] In some embodiments, the access network device is, for example, a node or device that connects a terminal 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), radio 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.

[0133] 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.

[0134] 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.

[0135] In some embodiments, the core network equipment may be a single device comprising multiple network elements, or it may be multiple devices or a group of devices, each comprising some or all of the multiple network elements. Network elements may be virtual or physical. The core network may include, for example, at least one of the Evolved Packet Core (EPC), 5G Core Network (5GCN), and Next Generation Core (NGC).

[0136] 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.

[0137] 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 can be in any way, it can be a direct connection or an indirect connection, it can be a wired connection or a wireless connection.

[0138] 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).

[0139] In some embodiments, the optimal demodulator in a traditional wireless communication system is generally implemented by classical methods such as maximum likelihood estimation and Bayes' theorem. These demodulators typically require accurate Channel State Information (CSI) and channel noise distribution, and their performance depends on the parameter settings of each module, including filters, phase-locked loops, product modulators, analog-to-digital converters, etc.

[0140] The main limitations of traditional demodulators include:

[0141] 1. Large latency and complex implementation: The use of traditional demodulators usually causes significant latency, and the implementation process is relatively complex.

[0142] 2. Unstable module performance: Due to factors such as vibration, acceleration, temperature fluctuation, aging, and instability of discrete components, the module performance may change, resulting in a decrease in the overall performance of the receiver.

[0143] 3. Poor environmental adaptability: Real-world wireless communication channels may suffer from multipath fading, impulse noise, clutter, or discrete interference, which can significantly degrade demodulation performance. For example, some coherent demodulators require carrier synchronization, and phase errors and frequency offsets during synchronization can lead to demodulation errors.

[0144] 4. High dependence on prior knowledge such as CSI: Traditional demodulation methods usually have a high dependence on prior knowledge. However, in actual communication, especially in fast fading scenarios, it is difficult to accurately estimate CSI. Therefore, the channel model may be unknown at the receiver.

[0145] 5. Traditional demodulation methods do not make full use of prior waveform information and time series information.

[0146] Traditional wireless communication systems are generally designed based on rigorous mathematical theories and precise system models. However, with the increasing demands of wireless services such as smartphones, virtual reality, and the Internet of Things (IoT), these systems need to handle more complex and diverse communication requirements, and traditional mathematical models may not be able to adequately address these challenges. In this context, deep learning has been introduced into wireless communication systems as a powerful solution.

[0147] Since the information of a modulated signal is represented by its amplitude and phase, feature extraction is crucial for signal demodulation. Deep learning-based demodulators (or learning-based demodulators) can automatically learn and extract important features from signals using techniques such as neural networks, thereby achieving more accurate and robust demodulation. Their main advantages are:

[0148] 1. By learning from massive datasets, it possesses greater flexibility and adaptability. Compared to traditional methods, it requires less or even completely eliminates the need for prior knowledge;

[0149] 2. Because the model learns features under various undesirable conditions during training, the deep learning-based demodulator has stronger noise resistance.

[0150] 3. The requirements for prior knowledge (such as CSI and channel noise) can be relaxed or even eliminated.

[0151] Therefore, deep learning-based demodulators have great potential in dealing with complex wireless communication environments and improving communication performance.

[0152] In some embodiments, the demodulation model enhancement scheme based on Artificial Intelligence (AI) can use a neural network model to implement data demodulation, as shown in Figure 1B. This demodulation model takes the data to be demodulated (or the symbols to be demodulated) at the receiving end as input and outputs demodulated symbols (i.e., bit sequence b). During communication, the demodulated bit sequence output by this demodulation model is used... The error between the coded bit sequence b at the transmitting end and the output of the demodulation model is used as a loss function to update the model parameters of each layer, so that the output of the demodulation model is close to the target output.

[0153] In some embodiments, various modulation schemes are currently available, such as Quadrature Phase Shift Keying (QPSK), 16 Quadrature Amplitude Modulation (16QAM), and 64 Quadrature Amplitude Modulation (64QAM). The mapping between constellation symbols and data differs, and one data symbol to be demodulated corresponds to different lengths of data bits. For example, in QPSK, 16QAM, and 64QAM, one data symbol to be demodulated corresponds to 2, 4, and 6 demodulated data bits, respectively. Therefore, for received symbols using different modulation schemes, a matching demodulation scheme is required for data demodulation. For demodulation schemes based on AI models, different modulation schemes also need to be considered.

[0154] Training an AI model requires input and output data of a defined dimension. The length of the demodulated data corresponding to a symbol to be demodulated may differ depending on the modulation scheme. For example, in 16QAM modulation, a symbol to be demodulated corresponds to 4 bits of demodulated data, while in 64QAM modulation, a symbol to be demodulated corresponds to 6 bits of demodulated data. Therefore, the output length of the AI ​​demodulation model used for 16QAM and 64QAM should be 4 bits and 6 bits respectively, and it needs to learn the mapping relationship between constellation points and data under the two modulation schemes respectively.

[0155] Therefore, AI-based demodulation schemes can demodulate data under different modulation schemes, but they require known modulation scheme information. This modulation scheme information can be indicated to the receiving device by the transmitting device during data transmission as auxiliary information for selecting the demodulation model, as shown in Figure 1C. The input data of the AI ​​demodulation model consists of n data symbols to be demodulated, and the output data consists of n×M 0 / 1 bits, where M is the modulation order.

[0156] Furthermore, when the transmitting device does not indicate modulation scheme information, it is possible to explore modulation scheme recognition based on AI models. That is, using the data to be demodulated and the corresponding modulation scheme information as training data, the AI ​​modulation scheme recognition model obtained through training can determine the corresponding modulation scheme of the transmitting signal based on the features of the data to be demodulated, and then select the AI ​​demodulation model under the corresponding modulation scheme to demodulate the data, thus realizing an AI demodulation scheme that does not require indication of modulation information, as shown in Figure 1D.

[0157] In digital communication systems, constellation design is an important research direction. The transmitting device can map bit data to appropriate constellation points to complete data modulation, and the receiving device can demodulate the data according to the corresponding decision regions to recover the bit data. The AI-based data demodulation scheme described above only enhances the receiving end's data demodulation function and does not modify the transmitting end's modulation function. That is, the transmitting device still uses 16QAM, 64QAM, etc., to complete the data modulation of coded bits, using fixed rules to map the coded bit sequence to the corresponding constellation points. Taking 16QAM as an example, the mapping relationship between the bit sequence to be modulated and the modulation symbols can be shown in Figure 1E.

[0158] In typical channel environments, standard modulation schemes such as 16QAM and 64QAM can achieve high-precision data transmission, basically meeting the system's operational requirements. However, in real-world applications, the channel environment is often more complex, and the actual channel conditions are unknown, making it impossible to design constellation diagrams mathematically. In such cases, using a fixed data modulation scheme may not achieve optimal data transmission performance. For example, when the signal-to-noise ratio (SNR) is low, i.e., when channel noise is high, using constellation points that are further apart to perform data modulation can reduce the impact of signal distortion caused by noise, allowing the receiving equipment to perform data demodulation with higher accuracy.

[0159] Therefore, using AI models to simultaneously enhance both the modulation and demodulation models is beneficial for further improving data transmission accuracy and enhancing the overall performance of the communication system. An AI-based modulation and demodulation enhancement scheme can be illustrated as shown in Figure 1F. The input to the modulation model at the transmitting end is the coded bit b, and the output is the modulation symbol x; the input to the demodulation model at the receiving end is the symbol y to be demodulated, and the output is the demodulated bit. In the application of the model, a neural network model is used to implement the data modulation function. The modulation model maps the encoded bits b to constellation points x suitable for the current channel environment, and the demodulation model processes the data symbols y to be demodulated, which are affected by factors such as channel conditions and noise, to obtain the demodulated bits.

[0160] Since the transmitting modulation model does not have its own target output, joint training of the models at both ends is required to calculate the demodulated bits output by the demodulation model. The loss function between the modulated and coded bits b is used to update the parameters of the modulation and demodulation models. The impact on signal transmission from the transmitting modulation model to the receiving demodulation model is reflected in the demodulated bits. In the distortion, the demodulated output bits are suppressed by training the modulation and demodulation models. The error between the target bit b and the target bit b.

[0161] The modulation symbol x output by the modulation model needs to be processed by other modules (such as layer mapping, precoding, etc.) after the modulation model at the transmitting end to obtain the transmitted signal s. transmit =f transmit (x). The transmitted signal reaches the receiver after being transmitted through the channel, and the received signal s receive =f channel (s transmit Affected by channel propagation, noise, and interference, the signal is further processed by other modules (such as channel estimation and equalization) before the receiver's demodulation model to obtain the demodulated symbol y = f. receive (s receive ).

[0162] While conventional offline communication methods can acquire the modulation symbol x at the transmitting end and the demodulation symbol y at the receiving end during data acquisition, communication requires adding other modules between the modulation and demodulation models, as well as the channel transmission process, between them. These other modules, such as transmitting-end layer mapping and receiving-end channel estimation, can be considered as computational operations with fixed rules. However, channel transmission is affected by noise and interference in the actual channel environment, and the channel state is uncertain, making it impossible to accurately implement using fixed computational methods. Consequently, joint training of the modulation and demodulation models cannot be completed.

[0163] To achieve joint training of the modulation and demodulation models and improve data transmission accuracy, this disclosure provides the following communication methods, devices, systems, and storage media.

[0164] 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 embodiments of the present disclosure relate to a communication method, which includes:

[0165] Step S2100: The first device 101 initializes the intermediate model.

[0166] In some embodiments, the first device 101 can be used to jointly train the modulation model and the demodulation model.

[0167] In some embodiments, the modulation model can be used to modulate the input bit sequence to output a modulation symbol.

[0168] In some embodiments, the demodulation model can be used to demodulate the input symbols to be demodulated, thereby outputting demodulated symbols.

[0169] In some embodiments, the first device 101 may be, for example, a terminal, network device, server, or other device that supports the above-described joint training.

[0170] In some embodiments, the modulation model, the trained intermediate model, and the demodulation model can be connected sequentially, and the trained intermediate model can at least be used to simulate the channel transmission process between the transmitting device 102 and the receiving device 103.

[0171] In some embodiments, the first device 101 may determine the initialization parameters of the intermediate model and initialize the intermediate model based on the initialization parameters.

[0172] In one example, the initialization parameters may include, but are not limited to, at least one of the following: the structural parameters of the intermediate model; the training parameters of the intermediate model.

[0173] In one example, the structural parameters of the intermediate model depend on the parameter configuration used in the actual application, the complexity of the channel environment, and so on.

[0174] In one example, the training parameters of the intermediate model include, but are not limited to, at least one of the following: the loss function type of the intermediate model; the learning rate of the intermediate model; the optimizer type of the intermediate model; the maximum number of training epochs of the intermediate model; and the output accuracy of the intermediate model.

[0175] The loss function types for intermediate models include, but are not limited to, L1 and L2 functions. The L1 function can refer to the minimum absolute value bias function, and the L2 function can refer to the minimum squared error function.

[0176] The learning rate of the intermediate model is the speed at which the model updates its knowledge or parameters during training, and its value can be in the range of (0, 1).

[0177] The optimizer for the intermediate model can be used to optimize the weights and / or biases of the model. The optimizer type can include, but is not limited to, at least one of the following: stochastic gradient descent optimizer; adaptive learning rate optimizer; adaptive learning rate and momentum optimizer; gradient normalization optimizer.

[0178] The maximum number of training cycles for the intermediate model can refer to the maximum number of training rounds for the intermediate model.

[0179] The output accuracy of the intermediate model refers to the degree of accuracy of the model's output data relative to the labels (training reference data).

[0180] The above is merely an illustrative example, and this disclosure does not limit the content of the initialization parameters.

[0181] In some embodiments, the first device 101 may determine the initialization parameters in the following manner:

[0182] Method 1-1: Determine the initialization parameters based on the instructions from the network device.

[0183] In one example, the network device could be a network-side functional unit used for AI model management.

[0184] In one example, the network device can configure the initialization parameters of the intermediate model and send indication information to the first device 101. This indication information indicates the initialization parameters. The first device 101 can determine the initialization parameters based on the indication information.

[0185] Method 1-2: Determine initialization parameters based on instructions from transmitting device 102 and / or receiving device 103.

[0186] In one example, the receiving device 103 can configure the initialization parameters of the intermediate model and send them to the first device 101.

[0187] In one example, the initialization parameters of the intermediate model can be configured by the sending device 102 and sent to the first device 101.

[0188] Methods 1-3 determine the initialization parameters based on predefined rules.

[0189] In one example, the initialization parameters can be determined by the first device 101 itself based on predefined rules. These predefined rules can be configured by the network device and / or agreed upon by the protocol, and this disclosure does not limit their scope.

[0190] The above is merely an illustrative example, and this disclosure does not limit the method by which the first device 101 determines the initialization parameters of the intermediate model.

[0191] In some embodiments, the first device 101 may initialize an intermediate model based on the initialization parameters.

[0192] In one example, the first device 101 can initialize the network structure of the intermediate model based on the structural parameters of the intermediate model.

[0193] In one example, the first device 101 can set relevant parameters during the training process of the intermediate model based on the training parameters of the intermediate model.

[0194] In one example, initializing the intermediate model may also include initializing the network parameters of the intermediate model, which may include, but is not limited to, at least one of the following methods: zero initialization; random initialization; Xavier initialization; Kaiming initialization.

[0195] Zero initialization can refer to setting the network parameters to 0 when initializing the intermediate model.

[0196] Random initialization can refer to assigning random values ​​to the network parameters when initializing the intermediate model.

[0197] Xavier initialization can maintain signal stability during forward and backward propagation by setting appropriate initial values ​​for weights and biases, ensuring that the output variance of each neuron is approximately the same as its input variance.

[0198] Kaiming initialization maintains consistent variance of activation values ​​in deep networks by adjusting the initial values ​​of weights, thereby preventing gradient vanishing and making the network easier to train.

[0199] The above is merely an illustrative example, and this disclosure does not limit the scheme for the first device 101 to initialize the intermediate model. Step S2101: The first device 101 obtains a set of sample bit sequences.

[0200] In some embodiments, the sample bit sequence set may include at least one sample bit sequence b.

[0201] In one example, the sample bit sequence b can be a sequence of "1" and "0" with a length greater than or equal to 1. For example, the sample bit sequence can be "100010" or "111110000".

[0202] In one example, the sample bit sequence b can be used as input data for the modulation model.

[0203] In one example, the sample bit sequence b is the bit sequence obtained after encoding the sample data. The sample data is the data that the transmitting device 102 wants to send to the receiving device 103.

[0204] In some embodiments, the first device 101 may determine the sample bit sequence set in at least one of the following ways: Method 2-1, randomly generating the sample bit sequence set.

[0205] In one example, the first device 101 may use a random algorithm to generate the set of sample bit sequences.

[0206] Method 2-2: Set up the sample bit sequence set according to the rules.

[0207] In one example, the rules may be agreed upon by a protocol, and / or the rules may be set by the network device and provided to the first device 101, which is not limited in this disclosure.

[0208] In one example, the rule may include at least one of the following: the number of sample bit sequence sets; the number of sample bit sequences included in each sample bit sequence set; the length value of each sample bit sequence; and the algorithm for setting the sample bit sequences.

[0209] In one example, the first device 101 can set the sample bit sequence set according to rules.

[0210] Method 2-3: Receive the set of sample bit sequences sent by the sending device 102.

[0211] In one example, the sending device 102 can generate or set the sample bit sequence set and then send it to the first device 101. The way the sending device 102 generates or sets the sample bit sequence set is similar to that of methods 2-1 and 2-2, and will not be described again here.

[0212] The above is merely an illustrative example. The first device 101 may also determine the sample bit sequence set in other ways, and this disclosure does not limit this.

[0213] In step S2102, the first device 101 sends a sample bit sequence to the sending device 102.

[0214] In some embodiments, the transmitting device 102 receives a sample bit sequence.

[0215] In some embodiments, the first device 101 may select one from the set of sample bit sequences and send it to the sending device 102 each time.

[0216] In step S2103, the transmitting device 102 obtains the sample modulation symbol.

[0217] In some embodiments, the transmitting device 102 may perform a first operation on the sample bit sequence to obtain the sample modulation symbol.

[0218] In one example, the first operation includes at least a modulation operation.

[0219] For example, the transmitting device 102 can modulate the sample bit sequence using a modulation module.

[0220] In one example, the first operation may also include at least one of a layer mapping operation and a precoding operation.

[0221] For example, the transmitting device 102 can perform layer mapping on the input data through a layer mapping module. The input data of the layer mapping module may include sample modulation symbols output by the modulation model.

[0222] For example, the transmitting device 102 can precode the input data using a precoding module. The input data to the precoding module may include the output data of the layer mapping module. The precoding module can output sample modulation symbols.

[0223] For example, the sample modulation symbols can be processed by the layer mapping module and / or the precoding module to obtain the transmitted signal, which can also be called the sample modulation symbols.

[0224] In step S2104, the transmitting device 102 sends sample modulation symbols to the first device 101.

[0225] In some embodiments, the first device 101 receives sample modulation symbols.

[0226] In step S2105, the transmitting device 102 sends sample modulation symbols to the receiving device 103.

[0227] In some embodiments, the receiving device 103 receives sample modulation symbols to obtain a received signal.

[0228] In some embodiments, the transmitting device 102 transmits the sample modulation symbols to the receiving device 103 via a channel.

[0229] In some embodiments, the receiving device 103 receives sample modulation symbols transmitted through the channel to obtain the received signal.

[0230] In step S2106, the receiving device 103 obtains the sample symbol to be demodulated.

[0231] In some embodiments, the receiving device 103 may perform a second operation on the received signal to obtain sample symbols to be demodulated.

[0232] In one example, the second operation may include at least one of channel estimation and channel equalization.

[0233] For example, the receiving device 103 can perform channel estimation on the input data through the channel estimation module, wherein the input data of the channel estimation module can be the received signal.

[0234] For example, the receiving device 103 can perform channel equalization on the input data through the channel equalization module, wherein the input data of the channel equalization module can be the output data of the channel estimation module, and the output data of the channel equalization module can be the sample symbols to be demodulated.

[0235] In step S2107, the receiving device 103 sends the sample demodulation symbol to the first device 101.

[0236] In some embodiments, the first device 101 receives sample symbols to be demodulated.

[0237] In step S2108, the first device 101 acquires the first symbol to be demodulated.

[0238] In some embodiments, the first device 101 can input the sample modulation symbol provided by the transmitting device 102 into the intermediate model to obtain the first demodulated symbol output by the intermediate model.

[0239] In step S2109, the first device 101 determines the second loss function.

[0240] In some embodiments, the first device 101 may determine the second loss function based on the difference between the first demodulated symbol output by the intermediate model and the sample demodulated symbol sent by the receiving device 103.

[0241] In step S2110, the first device 101 trains the intermediate model.

[0242] In some embodiments, the first device 101 can use the sample symbols to be demodulated as labels and update and adjust the network parameters of the intermediate model based on the second loss function to complete supervised communication.

[0243] In step S2111, the first device 101 obtains the trained intermediate model.

[0244] In some embodiments, the first device 101 may stop training the intermediate model when a second stopping condition is met, thereby obtaining a trained intermediate model.

[0245] In one example, the second stopping condition is the condition for stopping the training of the intermediate model.

[0246] In one example, the second stopping condition may include at least one of the following: reaching a second number of training epochs; the second loss function decreasing to a second tolerance range; and the accuracy of the first demodulated symbol reaching a second value.

[0247] The above is merely an illustrative example, and this disclosure does not limit the content of the second stopping condition.

[0248] Understandably, the trained intermediate model does not ultimately need to be deployed to the sending or receiving devices.

[0249] 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", "field", "symbol", "symbol", "codebook", "codeword", "codepoint", "bit", "data", "program", and "chip" can be used interchangeably.

[0250] 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.

[0251] In some embodiments, terms such as “send,” “transmit,” “report,” “distribute,” “transmit,” “bidirectional transmission,” “send and / or receive” can be used interchangeably.

[0252] 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.

[0253] In some embodiments, the information transmission method involved in this disclosure may include at least one of steps S2100 to S2111. For example, step S2100 may be implemented as an independent embodiment, step S2101 may be implemented as an independent embodiment, step S2102 may be implemented as an independent embodiment, steps S2101+S2102 may be implemented as an independent embodiment, step S2103 may be implemented as an independent embodiment, steps S2101+S2102+S2103 may be implemented as an independent embodiment, step S2104 may be implemented as an independent embodiment, and steps S2101 to S2104 may be implemented as independent embodiments. The steps S2105, S2101-S2105, S2106+S2107, S2108+S2109+S2110, S2111, and S2100-S2111 can be implemented as independent embodiments, but are not limited thereto. In some embodiments, steps S2101 to S2111 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0254] In some embodiments, the execution order of steps S2101 to S2111 is not limited.

[0255] In the above embodiments, the first device can learn the mapping relationship between modulation symbols and demodulation symbols through an intermediate model, thereby improving the feasibility of joint training and increasing its usability.

[0256] 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 embodiments of the present disclosure relate to a communication method, which includes:

[0257] Step S2200: The first device 101 initializes the modulation model and the demodulation model.

[0258] In some embodiments, the first device 101 can be used to jointly train the modulation model and the demodulation model.

[0259] In some embodiments, the modulation model can be used to modulate the input bit sequence to output a modulation symbol.

[0260] In some embodiments, the demodulation model can be used to demodulate the input symbols to be demodulated, thereby outputting demodulated symbols.

[0261] In some embodiments, the first device 101 may be, for example, a terminal, network device, server, or other device that supports the above-described joint training.

[0262] In some embodiments, the modulation model, the trained intermediate model, and the demodulation model can be connected sequentially, and the trained intermediate model can at least be used to simulate the channel transmission process between the transmitting device 102 and the receiving device 103.

[0263] In some embodiments, the first device 101 may determine initialization parameters for at least one of the modulation model and the demodulation model, and initialize the model based on the initialization parameters.

[0264] In one example, initialization parameters may include, but are not limited to, at least one of the following: structural parameters of the model; training parameters of the model.

[0265] The model can be at least one of a modulation model and a demodulation model.

[0266] In one example, the model's structural parameters depend on the parameter configuration used in the actual application, the complexity of the channel environment, and so on.

[0267] In one example, the training parameters of the model include, but are not limited to, at least one of the following: the type of loss function of the model; the learning rate of the model; the type of optimizer of the model; the maximum number of training epochs of the model; and the output accuracy of the model.

[0268] The loss function types of the model include, but are not limited to, L1 and L2 functions. The L1 function can refer to the minimum absolute value bias function, and the L2 function can refer to the minimum squared error function.

[0269] The learning rate of a model is the speed at which the model updates its knowledge or parameters during training, and its value can be in the range of (0, 1).

[0270] The optimizer of the model can be used to optimize the weights and / or biases of the model. The optimizer type can include, but is not limited to, at least one of the following: stochastic gradient descent optimizer; adaptive learning rate optimizer; adaptive learning rate and momentum optimizer; gradient normalization optimizer.

[0271] The maximum number of training cycles for a model can refer to the maximum number of training rounds for the model.

[0272] The model's output accuracy refers to the degree of precision of the model's output data relative to the labels (training reference data).

[0273] The above is merely an illustrative example, and this disclosure does not limit the content of the initialization parameters.

[0274] In some embodiments, the first device 101 may determine the initialization parameters in the following manner:

[0275] Method 3-1: Determine the initialization parameters based on the instructions from the network device.

[0276] In one example, the network device could be a network-side functional unit used for AI model management.

[0277] In one example, the network device can configure the initialization parameters of the model and send indication information to the first device 101. This indication information indicates the initialization parameters. The first device 101 can determine the initialization parameters based on the indication information.

[0278] Method 3-2: Determine the initialization parameters based on the instructions of the transmitting device 102 and / or the receiving device 103.

[0279] In one example, the initialization parameters of the model can be configured by the receiving device 103 and sent to the first device 101.

[0280] In one example, the initialization parameters of the model can be configured by the sending device 102 and sent to the first device 101.

[0281] In one example, the initialization parameters of the demodulation model can be configured by the receiving device 103, the initialization parameters of the modulation model can be configured by the transmitting device 102, and the receiving device 103 and the transmitting device 102 can send the corresponding initialization parameters to the first device 101.

[0282] Method 3-3 determines the initialization parameters based on predefined rules.

[0283] In one example, the initialization parameters can be determined by the first device 101 itself based on predefined rules. These predefined rules can be configured by the network device and / or agreed upon by the protocol, and this disclosure does not limit their scope.

[0284] Methods 3-4 determine the initialization parameters based on the combination method.

[0285] In one example, the network device can determine the initialization parameters of one model, while the initialization parameters of another model are determined by the sending device 102 and sent to the first device 101.

[0286] In one example, the initialization parameters of one model can be determined by the network device, while the initialization parameters of another model are determined by the receiving device 103 and sent to the first device 101.

[0287] In one example, the initialization parameters of one model can be determined by a network device, while the initialization parameters of another model are determined by a first device 101 based on predefined rules.

[0288] In one example, the initialization parameters of one model can be determined by a network device, while the initialization parameters of another model are determined by a first device 101 based on predefined rules.

[0289] The above is merely an illustrative example, and this disclosure does not limit the method by which the first device 101 determines the initialization parameters.

[0290] In some embodiments, the first device 101 may initialize the corresponding model based on the initialization parameters.

[0291] In one example, the first device 101 can initialize the network structure of the model based on the model's structural parameters.

[0292] In one example, the first device 101 can set relevant parameters during the model training process based on the model's training parameters.

[0293] In one example, initializing the model may also include initializing the network parameters of the model, which may include, but is not limited to, at least one of the following methods: zero initialization; random initialization; Xavier initialization; Kaiming initialization.

[0294] Zero initialization can refer to setting the network parameters to 0 when initializing the model.

[0295] Random initialization can refer to assigning random values ​​to the network parameters when initializing the model.

[0296] Xavier initialization can maintain signal stability during forward and backward propagation by setting appropriate initial values ​​for weights and biases, ensuring that the output variance of each neuron is approximately the same as its input variance.

[0297] Kaiming initialization maintains consistent variance of activation values ​​in deep networks by adjusting the initial values ​​of weights, thereby preventing gradient vanishing and making the network easier to train.

[0298] The above is merely an illustrative example, and this disclosure does not limit the scheme for initializing the modulation model and the demodulation model of the first device 101.

[0299] Step S2201: The first device 101 acquires the sample bit sequence set.

[0300] In some embodiments, step S2201 is implemented in a similar manner to step S2101, and will not be described again here.

[0301] Step S2202: The first device 101 acquires the first bit sequence.

[0302] In some embodiments, the first device 101 inputs at least one sample bit sequence b from the sample bit sequence set into the modulation model to obtain the first bit sequence output by the demodulation model corresponding to each sample bit sequence b.

[0303] In some embodiments, the modulation model, the trained intermediate model, and the demodulation model are connected sequentially, as shown in Figure 4.

[0304] In one example, the trained intermediate model can at least be used to simulate the channel transmission process between the transmitting device 102 and the receiving device 103.

[0305] In one example, the trained intermediate model can also be used to implement the functions of other modules deployed on the transmitting device 102 and the receiving device 103. The trained intermediate model can also be used to perform at least one of the following on the input data: layer mapping; precoding; channel estimation; channel equalization.

[0306] In one example, the trained intermediate model can be used to infer the mapping relationship between the modulation symbol x and the demodulation symbol y.

[0307] For example, the input data of the trained intermediate model can be the output data of the modulation model.

[0308] For example, the trained intermediate model can be used to perform layer mapping and precoding on the input data to obtain the transmitted signal, and simulate the channel transmission process between the transmitting device 102 and the receiving device 103 to transmit the transmitted signal through the channel. Channel estimation and channel equalization can be performed on the signal received through the channel (i.e., the received signal) to obtain the output data of the trained intermediate model.

[0309] For example, the output data of the trained intermediate model can be used as the input data of the demodulation model.

[0310] For example, layer mapping can refer to passing data from the upper layer to the lower layer and ensuring effective communication and coordination between different layers.

[0311] For example, precoding can improve the reliability and stability of a signal by transforming and optimizing the data at the transmitting end, thereby reducing noise interference and multipath fading during signal transmission.

[0312] For example, channel estimation can be used to identify and estimate the characteristics and effects of wireless channels, and can be used to assess or detect channel conditions.

[0313] For example, channel equalization can compensate for channel-induced distortion by adjusting the phase and amplitude of the received signal based on channel estimation, so that the output signal is as close as possible to the original input signal.

[0314] For example, the training process of the intermediate model has been described in the foregoing embodiments and will not be repeated here.

[0315] Understandably, to improve the efficiency and reliability of joint training, the network parameters of the intermediate model are no longer adjusted (or updated) during joint training after the intermediate communication is completed. In other words, during the joint training of the modulation and demodulation models, the trained intermediate model is set to be untrainable, and its network parameters are no longer updated during joint training. The joint training process can be used to adjust (or update) the network parameters of the modulation model and / or the demodulation model.

[0316] In step S2203, the first device 101 determines the first loss function.

[0317] In some embodiments, the first device 101 can be based on the first bit sequence output by the demodulation model. The difference between sample bit sequences b determines the first loss function.

[0318] Step S2204: The first device 101 performs joint training on the modulation model and the demodulation model.

[0319] In some embodiments, the first device 101 can use the sample bit sequence b as a label and, based on a first loss function, update and adjust the network parameters of the modulation model and the demodulation model to complete supervised model training. During this joint training process, the intermediate model can be set to be untrainable, meaning that the network parameters of the intermediate model will not be updated or adjusted.

[0320] In step S2205, the first device 101 obtains the trained modulation model and the trained demodulation model.

[0321] In some embodiments, the first device 101 may stop joint training when a first stopping condition is met, thereby obtaining a trained modulation model and a trained demodulation model.

[0322] In one example, the first stopping condition is the condition for stopping joint training.

[0323] In one example, the first stopping condition may include at least one of the following: reaching a first number of training epochs; the first loss function decreasing to a first tolerance range; and the accuracy of the first bit sequence reaching a first value.

[0324] In this process, the first device 101 updates and adjusts the network parameters of the modulation model and the demodulation model in one round, which can increment the number of training cycles by 1. The number of training cycles can be accumulated from 0 until it is equal to the first number of training cycles, at which point the first stopping condition is met, and the first device 101 can stop the joint training process.

[0325] The number of the first training cycles can be a positive integer, such as 1, 2, 3, etc. This number of the first training cycles can be agreed upon by the protocol and / or provided to the first device 101 by the network device, and this disclosure does not limit it.

[0326] The first device 101 can determine that the first stopping condition is met when the first loss function is reduced to a certain range, such as within the first fault tolerance range, and at this time the joint training process can be stopped.

[0327] The first device 101 can determine that the first stopping condition is met when the accuracy of the first bit sequence output by the demodulation model reaches a first value, and at this time the joint training process can be stopped.

[0328] The first device 101 may also determine that the first stopping condition is met under other circumstances, such as when the learning rates of the modulation model and the demodulation model reach a second value, which is not limited in this disclosure.

[0329] In step S2206, the first device 101 sends the first network parameters to the sending device 102.

[0330] In some embodiments, the sending device 102 receives a first network parameter.

[0331] In some embodiments, the first network parameters are the network parameters of a trained modulation model.

[0332] In some embodiments, the transmitting device 102 is a device for transmitting signals and / or data.

[0333] Step S2207: The transmitting device 102 deploys the modulation model.

[0334] In some embodiments, the transmitting device 102 updates the network parameters of the modulation model based on the first network parameters to complete the deployment of the modulation model.

[0335] In step S2208, the first device 101 sends the second network parameters to the receiving device 103.

[0336] In some embodiments, the receiving device 103 receives a second network parameter.

[0337] In some embodiments, the second network parameters are the network parameters of the trained demodulation model.

[0338] In some embodiments, the receiving device 103 is a device for receiving signals and / or data.

[0339] Step S2209: The receiving device 103 deploys the demodulation model.

[0340] In some embodiments, the receiving device 103 updates the network parameters of the demodulation model based on the second network parameters to complete the deployment of the demodulation model.

[0341] In some embodiments, the information transmission method involved in this disclosure may include at least one of steps S2201 to S2209. For example, step S2201 may be implemented as an independent embodiment, step S2202 may be implemented as an independent embodiment, step S2201+S2202 may be implemented as an independent embodiment, step S2203 may be implemented as an independent embodiment, step S2201+S2202+S2203 may be implemented as an independent embodiment, step S2204 may be implemented as an independent embodiment, steps S2201 to S2204 may be implemented as independent embodiments, step S2205 may be implemented as an independent embodiment, steps S2201 to S2205 may be implemented as independent embodiments, steps S2206+S2207 may be implemented as independent embodiments, steps S2208+S2209 may be implemented as independent embodiments, and steps S2201 to S2209 may be implemented as independent embodiments, but are not limited thereto.

[0342] In some embodiments, steps S2201 to S2209 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0343] In some embodiments, the execution order of steps S2201 to S2209 is not limited.

[0344] In the above embodiments, the modulation model and demodulation model can be jointly trained offline, which improves the accuracy of data transmission, enhances the performance of the communication system, and increases its availability.

[0345] In some embodiments, the intermediate model, modulation model, and / or demodulation model described above may include at least one of the following layers: an input layer; a convolutional layer; a pooling layer; an activation function layer; a fully connected layer; and an output layer. The intermediate model, modulation model, and / or demodulation model may employ any of the following models as the backbone network: a residual network, a Visual Geometry Group (VGG) network, or GoogleNet, and the deployment of the corresponding model is completed based on the network parameters provided by the first device 101.

[0346] In some embodiments, the first device 101 can jointly train the modulation model, intermediate model, and demodulation model. The first device 101 acquires a set of sample bit sequences, inputs at least one of these sample bit sequences into the modulation model, acquires the first bit sequence output by the demodulation model, determines a first loss function based on the difference between the first bit sequence and the sample bit sequences, performs supervised training using the sample bit sequences as labels and the first loss function, and obtains the trained modulation model, the trained intermediate model, and the trained demodulation model when a first stopping condition is met. It is understood that the intermediate model does not ultimately need to be deployed; the first device 101 can deploy the trained modulation model to the transmitting device 102 and the trained demodulation model to the receiving device 103.

[0347] In some embodiments, the first device 101 can first train the intermediate model. After training, the modulation model, intermediate model, and demodulation model can be jointly trained. During the joint training process, the intermediate model can be set to be trainable, meaning the joint training process can be used to adjust (or update) the network parameters of at least one of the modulation model, intermediate model, and demodulation model. Specifically, the first device 101 can train the intermediate model using steps S2201 to S2211. After training, the electronic device 101 can acquire a set of sample bit sequences, input at least one of the sample bit sequences into the modulation model, obtain the first bit sequence output by the demodulation model, determine a first loss function based on the difference between the first bit sequence and the sample bit sequence, use the sample bit sequence as a label, and perform supervised training based on the first loss function until a first stopping condition is met, resulting in a trained modulation model, a trained intermediate model, and a trained demodulation model. It is understood that the intermediate model does not ultimately need to be deployed. The first device 101 can deploy the trained modulation model to the transmitting device 102 and the trained demodulation model to the receiving device 103.

[0348] In the above embodiments, the modulation model, intermediate model and demodulation model can be jointly trained offline, which improves the accuracy of data transmission, improves the performance of the communication system and has high availability.

[0349] Figure 3A is a flowchart 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 can be executed by a first device 101 and includes the following steps:

[0350] Step S3101: Send the sample bit sequence.

[0351] In some embodiments, the first device 101 sends a sample bit sequence to the transmitting device 102.

[0352] In some embodiments, the transmitting device 102 receives a sample bit sequence.

[0353] In some embodiments, step S3101 may refer to steps in other embodiments described before or after this embodiment, such as step S2102 in FIG2A and its optional implementation, and other related parts in the specification, which will not be repeated here.

[0354] Step S3102: Obtain the sample modulation symbol.

[0355] In some embodiments, the first device 101 receives sample modulation symbols sent by the transmitting device 102, but is not limited thereto. The first device 101 may also receive sample modulation symbols sent by other entities, such as relay devices or other terminals, in which case step S3102 may be omitted.

[0356] In some embodiments, the first device 101 acquires sample modulation symbols as specified by the protocol, in which case step S3102 is omitted.

[0357] In some embodiments, the first device 101 obtains sample modulation symbols from the upper layer(s), in which case step S3102 is omitted.

[0358] In some embodiments, the first device 101 processes the data to obtain sample modulation symbols, in which step S3102 is omitted.

[0359] In some embodiments, the first device 101 autonomously implements the function indicated by the sample modulation symbol, or the above function is default or default, in which case step S3102 is omitted.

[0360] In some embodiments, step S3102 may refer to steps in other embodiments described before or after this embodiment, such as step S2104 in FIG2A and its optional implementation, as well as other related parts in the specification, which will not be repeated here.

[0361] Step S3103: Obtain the sample symbols to be demodulated.

[0362] In some embodiments, the first device 101 receives sample demodulation symbols sent by the receiving device 103, but is not limited thereto. The first device 101 may also receive sample demodulation symbols sent by other execution entities, such as relay devices or other terminals, in which case step S3103 may be omitted.

[0363] In some embodiments, the first device 101 acquires the sample symbols to be demodulated as specified by the protocol, in which case step S3103 is omitted.

[0364] In some embodiments, the first device 101 obtains sample symbols to be demodulated from the upper layer(s), in which case step S3103 is omitted.

[0365] In some embodiments, the first device 101 processes the sample to obtain the demodulated symbol, in which step S3103 is omitted.

[0366] In some embodiments, the first device 101 autonomously implements the function indicated by the sample demodulation symbol, or the above function is default or default, in which case step S3103 is omitted.

[0367] In some embodiments, step S3103 may refer to steps in other embodiments described before or after this embodiment, such as step S2106 in FIG2A and its optional implementation, as well as other related parts in the specification, which will not be repeated here.

[0368] In some embodiments, steps S3101 to S3103 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0369] In some embodiments, the execution order of steps S3101 to S3103 is not limited.

[0370] In the above embodiments, sample modulation symbols and sample demodulation symbols used for training intermediate models can be obtained through interaction with the transmitting and receiving devices, which improves the reliability of intermediate model training, enhances the performance of the communication system, and increases its availability.

[0371] Figure 3B is a flowchart illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 3B, this embodiment of the disclosure relates to a communication method, which can be executed by a sending device 102, and includes the following steps:

[0372] Step S3201: Obtain the sample bit sequence.

[0373] In some embodiments, the transmitting device 102 receives a sample bit sequence sent by the first device 101, but is not limited thereto. The transmitting device 102 may also receive a sample bit sequence sent by other entities, such as relay devices or other terminals, in which case step S3201 may be omitted.

[0374] In some embodiments, the transmitting device 102 acquires the sample bit sequence specified by the protocol, in which case step S3201 is omitted.

[0375] In some embodiments, the transmitting device 102 obtains the sample bit sequence from the upper layer(s), in which case step S3201 is omitted.

[0376] In some embodiments, the transmitting device 102 processes the data to obtain a sample bit sequence, in which case step S3201 is omitted.

[0377] In some embodiments, the transmitting device 102 autonomously implements the function indicated by the sample bit sequence, or the above function is default or default, in which case step S3201 is omitted.

[0378] In some embodiments, step S3201 may refer to steps in other embodiments described before or after this embodiment, such as step S2102 in FIG2A and its optional implementation, and other related parts in the specification, which will not be repeated here.

[0379] Step S3202: Determine the sample modulation symbol.

[0380] In some embodiments, step S3202 may refer to steps in other embodiments described before or after this embodiment, such as step S2103 in FIG2A and its optional implementation, as well as other related parts in the specification, which will not be repeated here.

[0381] Step S3203: Send sample modulation symbols.

[0382] In some embodiments, the transmitting device 102 transmits sample modulation symbols to the first device 101.

[0383] In some embodiments, the first device 101 receives sample modulation symbols.

[0384] In some embodiments, step S3203 may refer to steps in other embodiments described before or after this embodiment, such as step S2104 in FIG2A and its optional implementation, as well as other related parts in the specification, which will not be repeated here.

[0385] In some embodiments, steps S3201 to S3203 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0386] In some embodiments, the execution order of steps S3201 to S3203 is not limited.

[0387] In the above embodiments, the transmitting device can send sample modulation symbols to the first device so that the first device can prepare sample modulation symbols for training the intermediate model, thereby improving the accuracy of intermediate model training, improving the performance of the communication system, and increasing availability.

[0388] Figure 3C is a flowchart illustrating a communication method according to an embodiment of the present disclosure. As shown in Figure 3C, this embodiment of the present disclosure relates to a communication method, which can be executed by a receiving device 103, and includes the following steps:

[0389] Step S3301: Determine the received signal.

[0390] In some embodiments, step S3301 may refer to steps in other embodiments described before or after this embodiment, such as step S2105 in FIG2A and its optional implementation, as well as other related parts in the specification, which will not be repeated here.

[0391] Step S3302: Determine the sample signal to be demodulated.

[0392] In some embodiments, step S3302 may refer to steps in other embodiments described before or after this embodiment, such as step S2106 in FIG2A and its optional implementation, and other related parts in the specification, which will not be repeated here.

[0393] Step S3303: Send sample symbols to be demodulated.

[0394] In some embodiments, the receiving device 103 sends sample symbols to be demodulated to the first device 101.

[0395] In some embodiments, the first device 101 receives sample symbols to be demodulated.

[0396] In some embodiments, steps S3301 to S3303 are optional, and one or more of these steps may be omitted or substituted in different embodiments.

[0397] In some embodiments, the execution order of steps S3301 to S3303 is not limited.

[0398] In the above embodiments, the receiving device can determine the sample demodulation symbols and send them to the first device so that the first device can prepare sample demodulation symbols for training the intermediate model, thereby improving the accuracy of intermediate model training, improving the performance of the communication system, and increasing availability.

[0399] The above process is further illustrated with examples below.

[0400] Applying AI technology to both data transmitters and receivers has broad application and research value. Data modulation and demodulation, as fundamental and crucial modules in both ends, directly impact data transmission accuracy and communication system throughput. While neural network models can enhance the data demodulation function at the receiver and improve demodulation accuracy, using AI models to simultaneously enhance both modulation and demodulation models further improves data transmission accuracy and overall communication system performance, thus possessing significant research and application value.

[0401] The modulation model is deployed at the transmitting end (device), and the demodulation model is deployed at the receiving end (device). The two models require processing by other modules at the transmitting end, channel transmission, and further processing by other modules at the receiving end. To jointly train the modulation and demodulation models, the output of the modulation model needs to be processed by other modules, transmitted through the channel, and then input into the demodulation model. However, during communication, fixed data processing or computation methods cannot replicate the impact of channel transmission on the data; therefore, conventional offline communication methods cannot be used to complete the joint training of the modulation and demodulation models.

[0402] In this embodiment of the disclosure, for the joint training of models in the AI-based data modulation and demodulation enhancement technology scheme, a joint training method for modulation and demodulation models using an intermediate model is proposed. The processing of other modules between the modulation and demodulation models and the channel transmission are approximated using a neural network model. This model is used to simulate the transmission process between modulated data x and the data to be demodulated y. Then, this model is used to connect the modulation and demodulation models, thereby completing modulation and demodulation communication, as shown in Figure 4, including the following steps:

[0403] (1) Data preparation.

[0404] A set of data Data is randomly generated or manually set. Each sample data b in this set of data is a bit data sequence, which is used as the bit data to be modulated and encoded at the sending end to complete subsequent communication.

[0405] The dataset used for model training supports (2) intermediate model training and (3) joint training of modulation and demodulation models; the data can be determined by the first device used to complete the model training, in which case the first device needs to send the data to the sending end; the data can also be determined by the sending end, in which case the sending end needs to send the data to the first device.

[0406] (2) Intermediate communication.

[0407] In an existing communication system that does not use an AI model, data sample b in the dataset Data is sequentially processed by the modulation module and other modules at the transmitting end, the actual channel transmission, and the other modules and demodulation module at the receiving end. During this process, the modulation data x at the transmitting end and the demodulation data y at the receiving end are collected to form a dataset for intermediate communication. The intermediate model is trained using this dataset so that the intermediate model learns the mapping relationship from x to y. The trained model is then placed between the modulation model and the demodulation model, and its model parameters are fixed.

[0408] The dataset used for training the intermediate model includes x and y, where x needs to be sent from the transmitter to the first device, and y needs to be sent from the receiver to the first device to support the training of the intermediate model. Each data point in x and y consists of multiple coordinate points, which are the constellation point coordinates of the modulation symbol at the transmitter and the demodulation symbol at the receiver.

[0409] (3) Joint training of modulation and demodulation models.

[0410] Initialize the modulation and demodulation model parameters, and sequentially pass data sample b from the dataset Data through the modulation model, intermediate model, and demodulation model to obtain demodulated bits. Minimize model output The error between the target output b and the target output b is used to update the modulation and demodulation model parameters, thus completing the communication.

[0411] The datasets used for joint training of modulation and demodulation models include b and Where b is determined by the first device or sent to the first device by the transmitter to support joint training of the modulation and demodulation models.

[0412] (4) Application of modulation and demodulation models.

[0413] In practical model applications, modulation and demodulation models are deployed, and intermediate models are no longer used. The encoded bit b is processed by the modulation model, then processed by other transmitting and receiving modules in the actual system, and transmitted through the channel. Finally, the demodulated bit is obtained through the demodulation model.

[0414] The first device deploys a modulation model to the transmitting end and a demodulation model to the receiving end.

[0415] In the above embodiments, for technical solutions based on AI models to achieve modulation at the transmitting end and demodulation at the receiving end, a method for joint training of modulation and demodulation models using an intermediate model is proposed to address the situation where channel transmission cannot be reflected during the joint training of the modulation and demodulation models. This method uses the modulation data from the transmitting end and the demodulation data from the receiving end to train the intermediate model to simulate the impact of other modules at the transmitting and receiving ends and channel transmission on the data during modulation and demodulation. This serves as a connection between the modulation and demodulation models during the model training process, thereby completing the joint training of the modulation and demodulation models. This helps to promote the application of AI-based modulation and demodulation schemes in practical communication systems and improve the accuracy of data transmission and the overall performance of the communication system.

[0416] This disclosure also provides an apparatus (also referred to as a communication device, etc.) for implementing any of the above methods. For example, an apparatus is provided that includes units or modules for implementing the steps performed by the first device in any of the above methods. Furthermore, another apparatus is provided that includes units or modules for implementing the steps performed by the transmitting or receiving device in any of the above methods.

[0417] 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.

[0418] 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).

[0419] Figure 5A is a schematic diagram of the structure of a first device according to an embodiment of this disclosure. The first device 5100 is used to perform any of the above methods. In some embodiments, as shown in Figure 5A, the first device 5100 may include a transceiver module 5101.

[0420] In some embodiments, the transceiver module 5101 is used to send a sample bit sequence to a transmitting device; wherein the sample bit sequence is used to jointly train a modulation model and a demodulation model, the modulation model, the trained intermediate model, and the demodulation model are sequentially connected, and the trained intermediate model is used at least to simulate the channel transmission process between the transmitting device and the receiving device; receiving sample modulation symbols sent by the transmitting device; receiving sample demodulation symbols sent by the receiving device; wherein the sample demodulation symbols are determined by the receiving device based on the sample modulation symbols sent by the transmitting device; wherein the sample modulation symbols and the sample demodulation symbols are used to train the intermediate model to obtain the trained intermediate model.

[0421] Optionally, the transceiver module 5101 is used to perform at least one of the communication steps such as receiving and / or sending performed by the first device 5100 in any of the above methods (e.g., steps S2102, S2104, S2107, S2206, S2208, but not limited thereto), which will not be elaborated here.

[0422] Figure 5B is a schematic diagram of the structure of the transmitting device according to an embodiment of this disclosure. The transmitting device 5200 is used to perform any of the above methods. In some embodiments, as shown in Figure 5B, the transmitting device 5200 may include at least one of a transceiver module 5201 and a processing module 5202.

[0423] In some embodiments, the transceiver module 5201 is used to receive a sample bit sequence sent by the first device.

[0424] In some embodiments, the processing module 5202 is used to perform a first operation on the sample bit sequence to obtain a sample modulation symbol; wherein the first operation includes at least a modulation operation.

[0425] In some embodiments, the transceiver module 5201 is further configured to send the sample modulation symbols to the first device.

[0426] Optionally, the transceiver module 5201 is used to perform at least one of the communication steps such as receiving and / or sending performed by the transmitting device 5200 in any of the above methods (e.g., steps S2102, S2104, S2105, S2206, but not limited thereto), which will not be described in detail here.

[0427] Optionally, the processing module 5202 is used to execute at least one of the other steps (such as step S2103, step S2207, but not limited thereto) executed by the transmitting device 5200 in any of the above methods, which will not be described in detail here.

[0428] Figure 5C is a schematic diagram of the structure of the receiving device according to an embodiment of this disclosure. The receiving device 5300 is used to perform any of the above methods. In some embodiments, as shown in Figure 5C, the receiving device 5300 may include at least one of a transceiver module 5301 and a processing module 5302.

[0429] In some embodiments, the transceiver module 5301 is used to receive sample modulation symbols transmitted by the transmitting device through the channel to obtain a received signal; wherein, the sample modulation symbols are obtained by the transmitting device performing a first operation on the sample bit sequence after receiving the sample bit sequence transmitted by the first device, and the first operation includes at least a modulation operation.

[0430] In some embodiments, the processing module 5302 is used to perform a second operation on the received signal to obtain sample symbols to be demodulated.

[0431] In some embodiments, the transceiver module 5301 is further configured to send the sample demodulation symbol to the first device.

[0432] Optionally, the transceiver module 5301 is used to perform at least one of the communication steps such as receiving and / or sending performed by the receiving device 5300 in any of the above methods (e.g., steps S2105, S2107, and S2208, but not limited thereto), which will not be described in detail here.

[0433] Optionally, the processing module 5302 is used to execute at least one of the other steps (such as step S2106, step S2209, but not limited thereto) executed by the receiving device 5300 in any of the above methods, which will not be described in detail here.

[0434] 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.

[0435] 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.

[0436] In some embodiments, the processing module can be replaced by the processor, and the transceiver module can be replaced by the transceiver.

[0437] 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 first device, a transmitting device, or a receiving device, or it can be a chip, chip system, or processor that supports the first device, transmitting device, or receiving device in implementing any of the above methods. The communication device 6100 can be used to implement the methods described in the above method embodiments, and for details, please refer to the description in the above method embodiments.

[0438] 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.

[0439] 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 transceivers 6102 perform at least one of the communication steps such as sending and / or receiving in the above method (e.g., steps S2102, S2104, S2105, S2107, S2206, S2208, but not limited thereto), and the processor 6101 performs at least one of other steps (e.g., steps S2100, S2101, S2103, S2106, S2108, S2109, S2110, S2111, S2200, S2201, S2202, S2203, S2204, S2205, S2207, S2209, but not limited thereto). In optional embodiments, the transceiver may include a receiver and / or a transmitter, which may be separate or integrated. 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.

[0440] 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 an optional embodiment, 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 send the data and / or instructions to the processor 6101.

[0441] 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.

[0442] 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.

[0443] Chip 6200 includes one or more processors 6201. Chip 6200 is used to perform any of the methods described above.

[0444] 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.

[0445] In some embodiments, the interface circuit 6202 performs at least one of the communication steps such as sending and / or receiving in the above method (e.g., steps S2102, S2104, S2105, S2107, S2206, S2208, but not limited thereto). For example, the interface circuit 6202 performing the communication steps such as sending and / or receiving in the above method means that the interface circuit 6202 performs 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 S2100, S2101, S2103, S2106, S2108, S2109, S2110, S2111, S2200, S2201, S2202, S2203, S2204, S2205, S2207, S2209, but is not limited thereto).

[0446] 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.

[0447] This disclosure also proposes a storage medium storing instructions that, when executed on a communication device, cause the communication device 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.

[0448] This disclosure also proposes a program product, including a program and / or instructions, which, when executed by a communication device, cause the communication device 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.

[0449] This disclosure also proposes a computer program that, when run on a computer, causes the computer to perform any of the above methods.

[0450] Other embodiments of this disclosure will readily occur to those skilled in the art upon consideration of the specification and practice of the invention disclosed herein. This disclosure is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not disclosed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this disclosure are indicated by the following claims.

[0451] It should be understood that this disclosure is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this disclosure is limited only by the appended claims.

Claims

1. A communication method, characterized in that, The method is performed by a first device, and the method includes: Sending a sample bit sequence to the transmitting device; wherein the sample bit sequence is used to jointly train the modulation model and the demodulation model, the modulation model, the trained intermediate model and the demodulation model are connected in sequence, and the trained intermediate model is used to simulate at least the channel transmission process between the transmitting device and the receiving device; Receive sample modulation symbols sent by the transmitting device; The receiving end device receives sample demodulation symbols sent by the receiving end device; wherein the sample demodulation symbols are determined by the receiving end device based on the sample modulation symbols sent by the transmitting end device; wherein the sample modulation symbols and the sample demodulation symbols are used to train an intermediate model to obtain the trained intermediate model.

2. The method according to claim 1, characterized in that, The method further includes at least one of the following: Randomly generate a set of sample bit sequences; According to the rules, set up a set of sample bit sequences; Receive the set of sample bit sequences sent by the sending device.

3. The method according to claim 1 or 2, characterized in that, The method further includes: Input the sample modulation symbol into the intermediate model, and obtain the first demodulated symbol output by the intermediate model; The second loss function is determined based on the difference between the sample to be demodulated symbol corresponding to the sample modulation symbol and the first to be demodulated symbol; Based on the second loss function, the intermediate model is trained until the second stopping condition is met, at which point the training of the intermediate model is stopped, and a trained intermediate model is obtained.

4. The method according to claim 3, characterized in that, The second stopping condition includes at least one of the following: Reach the second training cycle number; The second loss function is reduced to within the second fault tolerance range; The accuracy of the first demodulated symbol reaches the second value.

5. The method according to any one of claims 1-4, characterized in that, The method further includes: Input the sample bit sequence into the modulation model to obtain the first bit sequence output by the demodulation model; Based on the difference between the sample bit sequence and the first bit sequence, a first loss function is determined; Based on the first loss function, the modulation model and the demodulation model are jointly trained; Once the first stopping condition is met, the joint training is stopped, and the trained modulation model and the trained demodulation model are obtained.

6. The method according to claim 5, characterized in that, The first stopping condition includes at least one of the following: Reach the first training cycle number; The first loss function is reduced to within the first fault tolerance range; The accuracy of the first bit sequence reaches the first value.

7. The method according to any one of claims 1-6, characterized in that, The trained intermediate model is also used to perform at least one of the following on the input data: Layer mapping; Precoding; Channel estimation; Channel equalization.

8. The method according to any one of claims 1-7, characterized in that, The method further includes at least one of the following: The first network parameters are sent to the transmitting device; wherein, the first network parameters are the network parameters of the trained modulation model; The second network parameters are sent to the receiving device; wherein, the second network parameters are the network parameters of the trained demodulation model.

9. A communication method, characterized in that, The method is executed by the sending device, and the method includes: Receive the sample bit sequence sent by the first device; Perform a first operation on the sample bit sequence to obtain a sample modulation symbol; wherein the first operation includes at least a modulation operation; The sample modulation symbol is sent to the first device.

10. The method according to claim 9, characterized in that, The first operation further includes at least one of the following: Layer mapping operations; Precoding operation.

11. The method according to claim 9 or 10, characterized in that, The method further includes: The sample modulation symbols are transmitted to the receiving device through the channel.

12. The method according to any one of claims 9-11, characterized in that, The method further includes: Send a set of sample bit sequences to the first device.

13. The method according to any one of claims 9-12, characterized in that, The method further includes: Receive the first network parameters sent by the first device; wherein, the first network parameters are the network parameters of the trained modulation model; Based on the first network parameters, a modulation model is deployed.

14. A communication method, characterized in that, The method is executed by the receiving device, and the method includes: The receiving end device receives sample modulation symbols transmitted through a channel to obtain a received signal; wherein, the sample modulation symbols are obtained by the receiving end device performing a first operation on the sample bit sequence after receiving the sample bit sequence transmitted by the first device, and the first operation includes at least a modulation operation; A second operation is performed on the received signal to obtain sample symbols to be demodulated; The sample to be demodulated symbol is sent to the first device.

15. The method according to claim 14, characterized in that, The second operation includes at least one of the following: Channel estimation operation; Channel equalization operation.

16. The method according to claim 14 or 15, characterized in that, The method further includes: Receive the second network parameters sent by the first device; wherein, the second network parameters are the network parameters of the trained demodulation model; Based on the second network parameters, a demodulation model is deployed.

17. A first device, characterized in that, include: The transceiver module is configured to send a sample bit sequence to the transmitting device; wherein the sample bit sequence is used to jointly train the modulation model and the demodulation model, the modulation model, the trained intermediate model and the demodulation model are connected in sequence, and the trained intermediate model is used to simulate at least the channel transmission process between the transmitting device and the receiving device. The transceiver module is also configured to receive sample modulation symbols sent by the transmitting device; The transceiver module is further configured to receive sample demodulation symbols sent by the receiving device; wherein the sample demodulation symbols are determined by the receiving device based on the sample modulation symbols sent by the transmitting device; wherein the sample modulation symbols and the sample demodulation symbols are used to train an intermediate model to obtain the trained intermediate model.

18. A transmitting device, characterized in that, include: The transceiver module is configured to receive a sample bit sequence sent by the first device; The processing module is configured to perform a first operation on the sample bit sequence to obtain a sample modulation symbol; wherein the first operation includes at least a modulation operation; The transceiver module is also configured to send the sample modulation symbols to the first device.

19. A receiving device, characterized in that, include: The transceiver module is configured to receive sample modulation symbols transmitted by the transmitting device through the channel to obtain a received signal; wherein the sample modulation symbols are obtained by the transmitting device performing a first operation on the sample bit sequence after receiving the sample bit sequence transmitted by the first device, and the first operation includes at least a modulation operation; The processing module is configured to perform a second operation on the received signal to obtain sample symbols to be demodulated; The transceiver module is also configured to send the sample demodulation symbols to the first device.

20. A first device, characterized in that, include: One or more processors; The processor is used to execute the method according to any one of claims 1-8.

21. A transmitting device, characterized in that, include: One or more processors; The processor is used to execute the method according to any one of claims 9-13.

22. A receiving device, characterized in that, include: One or more processors; The processor is used to execute the method according to any one of claims 14-16.

23. A communication system, characterized in that, include: A first device, the first device being configured to perform the method according to any one of claims 1-8; A transmitting device configured to perform the method of any one of claims 9-12; A receiving device configured to perform the method of any one of claims 14-16.

24. A storage medium storing instructions, characterized in that, When the instruction is executed on the communication device, the communication device performs the communication method as described in any one of claims 1-8, 9-13, or 14-16.

25. A computer program product, comprising a computer program, characterized in that, When executed by a processor, the computer program is used to implement the communication method according to any one of claims 1-8, 9-13, or 14-16.

Images