Communication method and communication apparatus

Abstract

Provided in the present application are a communication method and a communication apparatus, which can be applied to more scenarios. The communication method may be applied to a communication system. The method comprises: a first communication apparatus acquires a first sequence, wherein the first sequence is determined by means of an artificial intelligence (AI) model, and the first sequence is used for random access, or is used for synchronization, or is used for sensing a communication apparatus other than the first communication apparatus; and the first communication apparatus sends the first sequence.

Description

Communication method and communication apparatus

[0001] The present application claims priority from the Chinese patent application No. 202410826107.5 filed on June 24, 2024, and entitled "Communication method and communication apparatus", the content of which is incorporated herein by reference in its entirety. TECHNICAL FIELD

[0002] The present application relates to the field of communication technology, and in particular to a communication method and a communication apparatus. BACKGROUND

[0003] In the process of generating reference signals and sequences in a wireless communication system (such as a cellular system, a wireless fidelity (Wi-Fi) system, etc.), a sequence can be generated based on the type of the sequence and related sequence parameters, such as a sequence root index, a sequence length, a sequence cyclic shift, and a sequence initialization state value, a reference signal can be generated based on the sequence, and the reference signal can be used to implement corresponding functions, such as random access, synchronization, channel information estimation, or sensing, etc. The number of sequences generated in the current wireless communication system is limited by the sequence root index, the sequence length, and the sequence cyclic shift, etc. The number of available sequences is limited, which results in limited applicable scenarios. SUMMARY

[0004] Embodiments of the present application provide a communication method and a communication apparatus, which can be applied to more scenarios.

[0005] To achieve the above object, the present application adopts the following technical solutions:

[0006] In a first aspect, a communication method is provided. The communication method includes: a first communication apparatus obtaining a first sequence. The first sequence is determined by an artificial intelligence (AI) model, the first sequence is used for random access, or is used for synchronization, or is used for sensing a communication apparatus other than the first communication apparatus. The first communication apparatus sends the first sequence.

[0007] Based on the communication method provided in the first aspect, the first communication apparatus can obtain and send the first sequence. Since the first sequence is determined by the AI model, the problem that the available sequences are limited due to the sequence being limited by the sequence root index, the sequence length, and the sequence cyclic shift, etc. can be avoided, and the communication method can be applied to more scenarios.

[0008] It should be understood that, without special indication, the "first communication device" in the present application can refer to a terminal device, or a chip (system) or other components or assemblies (processors), or a device containing the terminal device, or a logic module or software capable of realizing all or part of the functions of the first communication device. The chip can be arranged in the terminal device.

[0009] In a possible implementation, the first sequence corresponds to the first model. The first model is used to detect at least the first sequence. Since the first sequence is determined or generated by the AI model, and the first sequence can be detected by the first model, the first sequence and the first model can be jointly trained and optimized, and the problem of inaccurate detection caused by large interference between sequences of different users in a multi-user scenario can be avoided, thereby improving the detection performance.

[0010] In a possible implementation, the first sequence can include a plurality of sub-sequences, different sub-sequences in the plurality of sub-sequences are carried on different air interface resources, and the values of the plurality of sub-sequences have a correlation. In this way, when detecting the first sequence, at least one of the time domain feature, the frequency domain feature, and the spatial domain feature of the channel can be better obtained based on the correlation between the plurality of sub-sequences in the first sequence, thereby improving the communication performance.

[0011] In a possible implementation, the first sequence is one sequence in a first sequence set, and the first sequence set can be determined according to a first condition met by the first communication device and a first correspondence relationship. The first correspondence relationship includes a correspondence relationship between each second sequence set in at least one second sequence set and an applicable condition. The first sequence set is one of the at least one second sequence set. That is, the sequence corresponding to the first condition can be determined as the first sequence according to the first correspondence relationship, so that the first sequence matches the first condition, that is, the first sequence matches the actual situation or condition of the first communication device.

[0012] In a possible implementation, the method provided in the first aspect can further include that the first communication device receives first information. The first information is used to indicate at least one third sequence set. The at least one third sequence set includes the at least one second sequence set. That is, the first communication device can be configured with at least one sequence set by the second communication device, so that it can be applicable to the scenario in which the first communication device cannot determine the sequence set by itself.

[0013] In a possible implementation, the first information can include one or more of the following: the at least one third sequence set, an identifier of each of the at least one third sequence set, or model information used to generate each of the at least one third sequence set. As can be seen, the first information can indicate the at least one third sequence set in different manners, which can improve flexibility. In addition, if the first information indicates the at least one third sequence set by using the identifier of each of the at least one third sequence set, the at least one third sequence set itself can be avoided from being indicated, and the model information of the third sequence set can be reduced, thereby reducing the overhead of the first information.

[0014] In a possible implementation, the first information can further be used to indicate a condition applicable to each of the at least one third sequence set. In this way, the AI sequence set and the detection model corresponding to the AI sequence set can be matched with the applicable condition, thereby improving communication performance.

[0015] In a possible implementation, the second sequence set in the at least one second sequence set is a third sequence set that has been activated in the at least one third sequence set. Before the first communication apparatus acquires the first sequence, the method provided by the first aspect can further include that the first communication apparatus receives second information. The second information is used to indicate a sequence set to be activated and / or a sequence set to be deactivated in the at least one third sequence set. That is, the first sequence is a sequence in a sequence set that has been activated, so that the situation that the second communication apparatus cannot correctly detect due to the transmission of a sequence that has not been activated can be avoided, and detection efficiency and performance can be improved.

[0016] In a possible implementation, the method provided by the first aspect can further include that the first communication apparatus transmits third information. The third information is used to indicate the first sequence set. In this way, the second communication apparatus can determine a detection model matched with the first sequence set, so that the second communication apparatus can avoid using a detection model that does not match to detect a sequence, reduce the amount of computation of the second communication apparatus, and improve detection efficiency.

[0017] In a possible implementation, the third information can further be used to indicate a validity time of the first sequence set. In this way, the first sequence set does not need to be indicated each time the first sequence is transmitted, and the amount of data of interaction is reduced, thereby reducing signaling overhead.

[0018] In a possible implementation, each of the at least one second sequence set corresponds to a time-frequency resource, and different second sequence sets in the at least one second sequence set correspond to different time-frequency resources, and the first communication device sending the first sequence can include: the first communication device sending the first sequence on the time-frequency resource corresponding to the first sequence set. In this way, the first sequence set can be implicitly indicated by the time-frequency resource, and the first sequence set can be avoided to be indicated separately, thereby reducing the overhead.

[0019] In a possible implementation, the method provided in the first aspect can further include: the first communication device receiving fourth information. The fourth information is used to indicate the time-frequency resource corresponding to each of the at least one second sequence set. That is, the time-frequency resource of each sequence set is configured by the second communication device, and in this way, the conflict between different first communication devices can be reduced. In addition, in this scenario, there is a corresponding relationship between the time-frequency resource and the sequence set, so that the second communication device can determine the model used to detect the sequence based on the time-frequency resource carrying the sequence, and the first communication device can avoid using separate signaling to indicate the sequence set corresponding to the first sequence, such as the first sequence set described above, thereby reducing the resource overhead.

[0020] In a possible implementation, the method provided in the first aspect can further include: the first communication device sending fifth information. The fifth information is used to indicate the first model. That is, the second communication device can be indicated to use the detection model matched with the first sequence, and in the case that the first sequence set and the detection model matched with the first sequence are determined by the first communication device, the second communication device can use the matched detection model, thereby improving the detection efficiency of the first sequence set.

[0021] In a possible implementation, the method provided in the first aspect can further include: the first communication device receiving sixth information. The sixth information is used to indicate the AI capability supported by the second communication device, and the AI capability includes one or more of the following: input, output, and computing power requirement of detecting the network. The first communication device obtaining the first sequence includes: the first communication device obtaining the first sequence according to the AI capability.

[0022] It should be understood that the AI capability can include the sequence length.

[0023] In a possible implementation, the method provided by the first aspect can further include: receiving, by the first communication device, seventh information. The seventh information can be used to indicate one or more of the following: a cyclic prefix of the first sequence, a cyclic prefix addition manner of the first sequence, a cyclic shift value of the first sequence, a subcarrier spacing corresponding to the first sequence, or a spacing between every two adjacent sub-sequences, a type of the first sequence, or a resource mapping manner of the first sequence. The first communication device can transmit the first sequence, including: transmitting, by the first communication device, the first sequence according to the seventh information. In this way, the first communication device can obtain information about how to generate a corresponding reference signal according to the sequence.

[0024] In a possible implementation, before the first communication device obtains the first sequence, the method provided by the first aspect can further include: receiving, by the first communication device, ninth information. The ninth information can be used to indicate switching of a sequence set. In this way, the sequence set can be managed by the second communication device, so that the activated sequence is more flexible.

[0025] In a possible implementation, the first sequence is a first-type sequence. The method provided by the first aspect can further include: receiving, by the first communication device, tenth information. The tenth information can be used to indicate that a priority of the first-type sequence is higher than a priority of a second-type sequence. The first-type sequence is a sequence determined by an AI model, and the second-type sequence is a sequence determined by a non-AI model. In this way, the first communication device can obtain a priority relationship between the first-type sequence and the second-type sequence, so that the first-type sequence can be preferentially selected in a case where the first-type sequence and the second-type sequence exist. Since the first-type sequence is a sequence obtained by an AI model, different AI sequences have lower ambiguity, that is, the cross-correlation between different AI sequences is lower, and therefore the first-type sequence can be applied to a scenario where more users send sequences in parallel, thereby improving detection efficiency.

[0026] The second aspect provides a communication method. The communication method includes: receiving, by a second communication device, a first sequence. The first sequence is determined by an artificial intelligence (AI) model, and the first sequence is used for random access, or is used for synchronization, or is used for sensing a communication device other than the first communication device. The second communication device detects the first sequence.

[0027] Based on the communication method provided by the second aspect, the second communication device can receive the first sequence. Since the first sequence is determined by an AI model, the first sequence can avoid the problem of limited available sequences caused by the limitation of parameters such as a root index of the sequence, a length of the sequence, and a cyclic shift of the sequence, and can be applied to more scenarios.

[0028] It should be understood that, without special indication, the "second communication device" in the present application can refer to a network device, or a chip (system) or other components or assemblies (processors), or a device containing the network device, or can also be a logical module or software capable of realizing all or part of the functions of the second communication device. Among them, the chip can be arranged in the network device.

[0029] In a possible implementation, the first sequence corresponds to a first model. The first model is used at least for detecting the at least first sequence.

[0030] In a possible implementation, the first sequence can include a plurality of sub-sequences, different sub-sequences in the plurality of sub-sequences are carried on different air interface resources, and there is a correlation between values of the plurality of sub-sequences.

[0031] In a possible implementation, the first sequence is one sequence in a first sequence set, and the first sequence set is determined according to a first condition satisfied by the first communication device and a first correspondence relationship. The first correspondence relationship includes a correspondence relationship between each second sequence set in at least one second sequence set and an applicable condition. The first sequence set is one of the at least one second sequence set.

[0032] In a possible implementation, the method provided by the second aspect can further include: the second communication device sending first information. The first information is used for indicating at least one third sequence set. The at least one third sequence set includes the at least one second sequence set.

[0033] In a possible implementation, the first information can include one or more of the following: the at least one third sequence set, or an identifier of each third sequence set in the at least one third sequence set, or model information used for generating each third sequence set in the at least one third sequence set.

[0034] In a possible implementation, the first information can further be used for indicating an applicable condition of each third sequence set in the at least one third sequence set.

[0035] In a possible implementation, a second sequence set in the at least one second sequence set is a third sequence set that has been activated in the at least one third sequence set. The method provided by the second aspect can further include: the second communication device sending second information. The second information is used for indicating a sequence set to be activated and / or a sequence set to be deactivated in the at least one third sequence set.

[0036] In a possible implementation, the method provided by the second aspect can further include: the second communication device receiving third information. The third information is used for indicating the first sequence set.

[0037] In a possible implementation, the third information can also be used to indicate a valid time of the first sequence set.

[0038] In a possible implementation, the method provided by the second aspect can further include: the second communication device sending fourth information. The fourth information is used to indicate time-frequency resources corresponding to each of the at least one second sequence set. Each of the at least one second sequence set corresponds to one time-frequency resource, and the time-frequency resources corresponding to different second sequence sets in the at least one second sequence set are different.

[0039] In a possible implementation, the method provided by the second aspect can further include: the second communication device receiving fifth information. The fifth information is used to indicate the first model.

[0040] In a possible implementation, the method provided by the second aspect can further include: the second communication device sending sixth information. The sixth information is used to indicate an AI capability supported by the second communication device, and the AI capability includes one or more of the following: input of detecting a network, output, and computing power requirement.

[0041] In a possible implementation, the method provided by the second aspect can further include: the second communication device sending seventh information. The seventh information is used to indicate one or more of the following: a cyclic prefix of the first sequence, a cyclic prefix addition manner of the first sequence, a cyclic shift value of the first sequence, a subcarrier spacing corresponding to the first sequence, or a spacing between every two adjacent sub-sequences, a type of the first sequence, and a resource mapping manner of the first sequence.

[0042] In a possible implementation, the method provided by the second aspect can further include: the second communication device sending ninth information. The ninth information is used to indicate switching the first sequence set.

[0043] In a possible implementation, the first sequence is a first type of sequence. The method provided by the second aspect can further include: the second communication device sending tenth information. The tenth information is used to indicate that a priority of the first type of sequence is higher than a priority of a second type of sequence. The first type of sequence is a sequence determined by an AI model, and the second type of sequence is a sequence determined by a non-AI model.

[0044] In addition, the technical effects of the communication method of the second aspect can refer to the technical effects of the communication method of the first aspect, which will not be described here.

[0045] In a third aspect, a communication device is provided. The communication device is configured to perform the communication method of any of the implementations of the first aspect to the second aspect.

[0046] In this application, the communication device described in the third aspect can be a terminal device or a network device, or a chip (system) or other component or assembly, or a device containing the terminal device or network device. The chip can be disposed within the terminal device or network device.

[0047] It should be understood that the communication apparatus described in the third aspect includes modules, units, or means that implement the communication methods described in any of the first to second aspects. These modules, units, or means can be implemented in hardware, software, or by hardware executing corresponding software. The hardware or software includes one or more modules or units for performing the functions involved in the aforementioned communication methods.

[0048] Fourthly, a communication device is provided. The communication device includes a processor configured to execute the communication method described in any of the possible implementations of the first to second aspects.

[0049] In one possible design, the communication device described in the fourth aspect may further include a transceiver. This transceiver may be a transceiver circuit or an interface circuit. The transceiver can be used for communication between the communication device described in the fourth aspect and other communication devices.

[0050] In one possible design, the communication device described in the fourth aspect may further include a memory. This memory may be integrated with the processor or disposed separately. The memory may be used to store computer programs and / or data related to the communication method described in any of the first to second aspects.

[0051] In this application, the communication device described in the fourth aspect can be a terminal device or a network device, or a chip (system) or other component or assembly, or a device containing the terminal device or network device. The chip can be disposed within the terminal device or network device.

[0052] Fifthly, a communication device is provided. The communication device includes a processor coupled to a memory, the processor executing a computer program stored in the memory, such that the communication device performs the communication method described in any possible implementation of the first to second aspects.

[0053] In one possible design, the communication device described in the fifth aspect may further include a transceiver. This transceiver may be a transceiver circuit or an interface circuit. The transceiver can be used for communication between the communication device described in the fifth aspect and other communication devices.

[0054] In the present application, the communication apparatus of the fifth aspect can be a terminal device or a network device, or a chip (system) or other components or assemblies, or an apparatus containing the terminal device or the network device. The chip can be arranged in the terminal device or the network device.

[0055] The sixth aspect provides a communication apparatus, including a processor and a memory; the memory is used to store a computer program, when the processor executes the computer program, to make the communication apparatus execute the communication method of any one of the implementation manners of the first aspect to the second aspect.

[0056] In a possible design, the communication apparatus of the sixth aspect can further include a transceiver. The transceiver can be a transceiver circuit or an interface circuit. The transceiver can be used for the communication apparatus of the sixth aspect to communicate with other communication apparatuses.

[0057] In the present application, the communication apparatus of the sixth aspect can be a terminal device or a network device, or a chip (system) or other components or assemblies, or an apparatus containing the terminal device or the network device. The chip can be arranged in the terminal device or the network device.

[0058] The seventh aspect provides a communication apparatus, including a processor; the processor is used to be coupled with a memory, and read a computer program in the memory, and then execute the communication method of any one of the implementation manners of the first aspect to the second aspect according to the computer program.

[0059] In a possible design, the communication apparatus of the seventh aspect can further include a transceiver. The transceiver can be a transceiver circuit or an interface circuit. The transceiver can be used for the communication apparatus of the seventh aspect to communicate with other communication apparatuses.

[0060] In the present application, the communication apparatus of the seventh aspect can be a terminal device or a network device, or a chip (system) or other components or assemblies, or an apparatus containing the terminal device or the network device. The chip can be arranged in the terminal device or the network device.

[0061] The eighth aspect provides a processor. The processor is used to execute the communication method of any one of the implementation manners of the first aspect to the second aspect.

[0062] The ninth aspect provides a communication system. The communication system includes one or more terminal devices, and one or more network devices.

[0063] In a tenth aspect, a computer-readable storage medium is provided, including a computer program or instructions, and when the computer program or instructions are run on a computer, the computer is caused to perform the communication method in any possible implementation of the first aspect to the second aspect.

[0064] In an eleventh aspect, a computer program product is provided, including a computer program or instructions, and when the computer program or instructions are run on a computer, the computer is caused to perform the communication method in any possible implementation of the first aspect to the second aspect.

[0065] In addition, the technical effects of the communication apparatus in the third aspect to the eleventh aspect can refer to the technical effects of the communication method in the first aspect to the second aspect, which will not be repeated here. BRIEF DESCRIPTION OF DRAWINGS

[0066] FIG. 1 is an AI lifecycle management schematic diagram provided by an embodiment of the present application;

[0067] FIG. 2 is an architecture schematic diagram of a communication system provided by an embodiment of the present application;

[0068] FIG. 3 is a flow schematic diagram of a communication method provided by an embodiment of the present application;

[0069] FIG. 4 is a schematic diagram of intervals between sub-sequences provided by an embodiment of the present application;

[0070] FIG. 5 is a flow schematic diagram of another communication method provided by an embodiment of the present application;

[0071] FIG. 6 is a flow schematic diagram of another communication method provided by an embodiment of the present application;

[0072] FIG. 7 is a flow schematic diagram of model training provided by an embodiment of the present application;

[0073] FIG. 8 is a flow schematic diagram of model training provided by an embodiment of the present application;

[0074] FIG. 9 is a flow schematic diagram of another communication method provided by an embodiment of the present application;

[0075] FIG. 10 is a flow schematic diagram of another communication method provided by an embodiment of the present application;

[0076] FIG. 11 is a flow schematic diagram of another communication method provided by an embodiment of the present application;

[0077] FIG. 12 is a flow schematic diagram of another communication method provided by an embodiment of the present application;

[0078] FIG. 13 is a flow schematic diagram of another communication method provided by an embodiment of the present application;

[0079] FIG. 14 is a structural schematic diagram of a communication apparatus according to an embodiment of the present application;

[0080] FIG. 15 is a structural schematic diagram of a communication apparatus according to an embodiment of the present application. DETAILED DESCRIPTION

[0081] The related technologies in the present application will be described below with reference to the accompanying drawings.

[0082] 1. Air interface artificial intelligence (AI), dual-end model, and air interface AI lifecycle management.

[0083] In the 3rd generation partnership project (3GPP) protocol release 18 (R18), air interface AI is introduced, that is, part of the air interface functions or links in the cellular network system can be implemented using AI. Some air interface AI use cases can be implemented using the architecture of a dual-end AI model.

[0084] In the architecture of the dual-end AI model, for a corresponding air interface function, the receiving end and the sending end use two parts of an AI model to cooperatively complete the function. For example, for channel state information (CSI) feedback, the receiving end and the sending end can use two parts of an AI model to complete the feedback of the channel state information. For example, the sending end uses part 1 of the AI model to complete the compression of the CSI, and feeds back the output result of part 1 of the AI model to the receiving end, and the receiving end uses part 2 of the AI model to complete the information recovery of the CSI.

[0085] In the air interface AI, a network device can manage an AI model or an AI function used by the network device and / or a terminal device, that is, air interface AI life cycle management (LCM). The granularity of the LCM can be an AI model or an AI function, that is, the difference between the AI model and the AI function is that the management granularity is different. The AI function can be at the use case level, for example, CSI feedback based on AI can be an AI function, and AI beam management can be another AI function. An AI function can also be a configuration under a specific use case, for example, in AI beam management, predicting the beam quality at a future time based on the measured beam quality can be an AI function, and predicting the beam quality at two future times based on the measured beam quality can be another AI function. It can be understood that for the LCM management of the AI function, one AI function corresponds to at least one AI model, wherein each AI model corresponding to the AI function can implement the AI function. That is, one AI function can also be implemented by multiple AI models, wherein multiple AI models can cooperate to implement the AI function, and at this time, the network device can manage the AI function. In an AI function, which AI model is specifically used can be determined by the implementation of the terminal device. In the subsequent description of the embodiments of the present application, the part related to the LCM will be described by taking the granularity of the AI model as an example. It can be understood that the corresponding process and description can also be applicable to the case of taking the AI function as the granularity. The LCM process of the AI can include operations such as activating, deactivating, switching, or falling back the AI model. As shown in FIG. 1, the LCM process of the air interface AI can be implemented through the following links: a data collection link, a model inference link, a model management link, a model training link, a model storage link, and a model tracking link. The data collection link can be used to collect one or more of the following data: data for model training (also referred to as training data), data for tracking model performance (also referred to as monitoring data), and data for model inference (also referred to as inference data or model inference input). In the model training link, the device for model training can perform model training according to the training data, and the model can also be updated in the model training link.The trained model or the updated model can be stored through a model storage link. The node for model storage can be a network side device, a terminal side device, an over the top (OTT) server device or an application server device of the network side or the terminal side or a third party.

[0086] Before the model inference link, a device requiring model inference can obtain the model from the node for model storage, and input inference input data as input data of the model, so as to obtain a model inference result. In the model management link, a device managing the model can manage the existing model according to the data for model tracking and / or the model inference result, such as triggering the model training module to update the model, and / or performing activation, deactivation or switching operation on the model stored in the model storage link. In addition, the device managing the model in the model management link can also transmit one or more of the following information to the model inference device: information for model activation, information for model deactivation or information for model switching.

[0087] 2. Reference signal

[0088] The generation process of the reference signal includes generation of a sequence (also referred to as a reference signal sequence) adopted by the reference signal, and resource mapping of the sequence. In addition, the generated sequence can also be modulated before resource mapping. In an orthogonal frequency division multiplexing (OFDM) system, after resource mapping is completed, the mapping result of the reference signal on the frequency domain resource (for example, a resource block (RB), or a resource element (RE), or it can be considered as the mapping result of the reference signal on different subcarriers) can be obtained. Further, the reference signal mapped on the frequency domain resource, and the frequency domain signal mapped on other REs or subcarriers in the same OFDM symbol, are subjected to inverse fast Fourier transform (IFFT), and the time domain signal containing the reference signal can be obtained. Further, a cyclic prefix (CP) is added to the time domain signal to form a baseband signal in the time domain, and the baseband signal in the time domain is sent out after digital-to-analog conversion and subsequent radio frequency link processing. At the receiving end, the received time domain signal expression form or frequency domain signal expression form of the reference signal can be obtained through the inverse process of the above process. Different types of reference signals can be used to implement different functions. Among them, the reference signal can be generated by using different types of reference signal sequences according to the functions to be implemented. For example, when the reference signal is used for random access, the reference signal can be generated by using a sequence for random access, such as a zadoff-chu (ZC) sequence; when the reference signal is used for synchronization, the reference signal can be generated by using a synchronization signal sequence for synchronization, such as an m sequence or a gold sequence; when the reference signal is used for channel measurement, the reference signal can be generated by using a channel state information reference signal (CSI-RS) sequence or a sounding reference signal (SRS) sequence, such as an m sequence or a ZC sequence; when the reference signal is used for data demodulation, the reference signal can be generated by using a demodulation reference signal (DMRS) sequence for data demodulation, such as an m sequence or a ZC sequence; when the reference signal is used for sensing a terminal device or a network device, the reference signal can be generated by using a sequence for sensing a terminal device or a network device, such as an m sequence, a ZC sequence, or a gold sequence.It should be understood that the reference signal herein is only for example, and in actual implementation, the reference signal can also be a reference signal for implementing other functions, and correspondingly, the sequence for generating the reference signal can also be other sequences, which are not described herein.

[0089] It should be noted that in the current long term evolution (LTE) or new radio (NR) protocol, the physical random access channel (PRACH) carries a random access preamble. Since the random access preamble is also generated by the network device and the terminal device in a conventional manner, for the purpose of description, the random access preamble is also described as a reference signal in the embodiments of the present application, that is, the reference signal described in the random access in the embodiments of the present application refers to the random access preamble.

[0090] For a cellular network communication system, such as an NR and / or LTE system, the reference signal can be predefined by a protocol. In some scenarios, the type of the reference signal, the generation manner of the reference signal, the resource mapping manner of the reference signal, and the generation manner of the time domain baseband signal containing the reference signal can be predefined by the protocol, so as to determine the predefined reference signal. For example, the protocol can define at least one configuration information for determining the reference signal. Each configuration information in the at least one configuration information can be used to determine one reference signal or one reference signal set. Each configuration information in the at least one configuration information can include one or more of the following: the sequence type of the reference signal, the generation manner of the sequence of the reference signal, the resource mapping manner of the reference signal, and the generation manner of the time domain baseband signal containing the reference signal. In actual communication, the reference signal sent by the terminal device can be one of one or more reference signals determined according to one configuration information in the at least one configuration information. For example, in a random access (RA) process, the reference signal sent by the terminal device is one of a plurality of reference signals determined according to one configuration information indicated by the network device.

[0091] For the purpose of understanding, the following illustrates the sequence detection process in combination with a random access process, such as a random access process (such as a four-step random access process or a two-step random access process) defined in NR release 15 (R15) or release 16 (R16).

[0092] In the RA process, the reference signal can be considered as a random access preamble (preamble), and the subsequent is simply referred to as a preamble. Among them, the random access process can include: (1) The network device sends a broadcast message, such as a system information block (system information block, SIB) indicating a preamble set, which includes a plurality of preambles in the preamble set. Specifically, the configuration information indicating the preamble set in the SIB, according to the configuration information and the generation method of the corresponding preamble sequence in the protocol, a preamble sequence set is determined, wherein the preamble sequence is a ZC sequence. (2) The terminal device can select a preamble sequence from the preamble sequence set determined from the information indicated by the broadcast message, and after resource mapping of the preamble sequence, send a random access request. Correspondingly, the network device can receive the random access request. Among them, in the four-step random access, the random access request can also be called the first message or message 1 (message 1, Msg1), and in the two-step random access, the random access request can also be called the first message or message A (message A, MsgA). Among them, the first message carries a preamble in the preamble set, and the preamble carried in the first message can be selected (such as randomly selected) by the terminal device from the preamble set. (3) Since the network device is pre-configured with the preambles in the preamble set, the network device can detect the preamble in the first message based on all preambles in the preamble set, and send a random access response (random access response, RAR) based on the detected preamble, for responding to the first message of the terminal device. Among them, in the four-step random access, the RAR can also be called the second message, or message two (message 2, Msg2). In the two-step random access, the RAR can also be called the second message or message B (message B, MsgB).

[0093] In a system such as a 4th generation (4G) mobile communication system, a 5th generation (5G) mobile communication system, and the like, a network device (such as a base station or a cell) can configure a time-frequency resource used for random access, which can also be referred to as a rach occasion (RO) resource. The network device can indicate the RO resource by indicating a position of a resource block (RB) occupied in a frequency domain, a position of a subframe (or a symbol) occupied in a time domain, and a period of the RO resource. A preamble can be transmitted on the RO resource indicated by the network device. Within a coverage of the network device, the network device allocates a preamble set to a terminal device, and the preamble set includes a plurality of preambles, such as 64 preambles. The terminal device within the coverage of the network device shares the preambles in the preamble set. The terminal device that has not accessed the network can randomly select a preamble to be transmitted by the terminal device, and attempts to access the network by transmitting the preamble, which can be carried in a random access request.

[0094] In the 4G mobile communication system or the 5G mobile communication system described above, a preamble sequence used for random access is a Zadoff-chu (ZC) sequence. In the 5G mobile communication system, for example, the network device can determine the ZC sequence according to the following formulas (1) and (2): x u,v (n)=x u (n+C v )mod L RA ); (2)

[0095] wherein u is a root index of the sequence (also referred to as a root exponent), x u (i) represents an i-th element in the sequence with the root u, i = 0, 1, …, L RA -1, x u,v (n) represents a sequence obtained by cyclically shifting the root sequence each time, C v is a cyclic shift value of the sequence, and L RA is a length of the root sequence. The root index, the cyclic shift value, and the length of the sequence of the ZC sequence described above can be indicated by information in a system information block (SIB).

[0096] It should be understood that the formulas (1) and (2) described above can be preconfigured, such as being agreed by a protocol, and are not limited in this regard.

[0097] For the specific determination process of the preamble and the preamble set, please refer to the relevant introduction in the NR protocol of 3GPP (such as technical specification (TS) 38, i.e. the technical specification of TS 38 series), which will not be repeated here.

[0098] It should be understood that the above x u,v (n) can be a time domain sequence (a time domain representation of the sequence), x u,v (n) can be converted to the frequency domain (i.e. converted to a frequency domain sequence) by a discrete fourier transform (DFT) to obtain a frequency domain sequence, so as to perform mapping of the frequency domain position. Wherein, the frequency domain sequence can satisfy the relationship shown in the following formula (3):

[0099] The ZC sequence has autocorrelation characteristics, and the sequences generated by the same root index are mutually orthogonal after cyclic shift. In addition, the ZC sequence also has good cross-correlation characteristics, and the cross-correlation values of the sequences generated by different root indexes are the inverse of the square root of the sequence length L RA , that is, the longer the ZC sequence, the better the cross-correlation. Based on the autocorrelation characteristics and cross-correlation characteristics of the ZC sequence, the detection of the ZC sequence can be performed.

[0100] Optionally, the detection manner of the ZC sequence is as follows: the network device performs correlation processing on the received signal and the sequence preconfigured in the network device (the correlation processing can be performed in the time domain, or the time domain signal can be converted to the frequency domain and then the correlation processing is performed in the frequency domain), and determines whether the received signal contains the preconfigured sequence or whether it contains the reference signal corresponding to the preconfigured sequence according to the result of the correlation between the received signal and the preconfigured sequence in the network device. If the result of the correlation between a preconfigured sequence and the received signal exceeds a first threshold, it can be determined that the network device detects the preconfigured sequence, or it can be determined that the terminal device transmits the preconfigured sequence. The first threshold can be determined by the network device through simulation traversal. Optionally, the first threshold can also be determined in combination with the false alarm requirement at the time of detection (such as requiring a false alarm probability less than a certain value). It should be understood that the first threshold can be different in different scenarios. For example, in the case of a small number of users transmitting at the same time, the first threshold can be low, and in the case of a large number of users transmitting at the same time, the first threshold can be high. For example, in the coverage range of the network device, the number of terminal devices transmitting reference signals in the same time period is different, the interference between different terminal devices is different, and the corresponding first threshold is different. In the embodiments of the present application, the correlation processing of two signals can be the conjugate multiplication of the two signals. It should be understood that the conjugate multiplication is only used as an example, and other possible correlation processing manners can also exist.

[0101] In the above scheme, the generated sequence needs to satisfy the relationship of formula (1) and formula (2), the number of available sequences (i.e. the generated sequence) is limited by the root index of the sequence, the length of the sequence and the cyclic shift of the sequence and other parameters, the number of available sequences is limited, and in the scenario of large-scale random access, the number of available sequences may not meet the demand of a large number of terminals simultaneously accessing, for example, the selected sequence may collide or conflict, thereby causing the application scenario to be limited.

[0102] In addition, in random access, the preamble sequences generated by different root sequences are non-orthogonal. Therefore, in the case that multiple terminal devices in the coverage range of the network device transmit different preamble sequences on the same time-frequency resource (such as the same RO resource), the interference between these different preamble sequences is large, thereby causing the problem of low detection performance.

[0103] It should be understood that in the embodiments of the present application, the RO resource can also be referred to as RO, which will not be described in detail hereinafter.

[0104] In the same time period, different terminal devices may also select the same preamble code for random access, which will cause different terminal devices to send the same content and cause collision and conflict, thereby causing the problem that different terminal devices cannot be distinguished in detection.

[0105] It can be learned from the above analysis of the preamble in the random access process that the preamble detection performance is low in the above random access process.

[0106] It should be understood that the above reference signal is a preamble for example only, and in the case where the reference signal has other functions, the reference signal can be other reference signals, and the implementation of other types of reference signals and sequence detection are similar to the preamble. For example, the other reference signals can also be used for one or more functions of synchronization detection, channel estimation, channel state information detection, perception detection of other devices, phase noise information estimation, etc. The above terminal device is an example of a device that transmits a reference signal, and the above network device is an example of a device that receives a reference signal. Therefore, in the scheme of detecting the reference signal, there is a problem of low detection efficiency or poor detection performance.

[0107] In addition, in the above scheme, the network device needs to determine which sequence is detected based on the threshold, and it is difficult to determine the optimal threshold, and the implementation complexity is high under the optimal performance condition.

[0108] The technical solutions in the present application will be described below with reference to the accompanying drawings.

[0109] The technical solutions of the embodiments of the present application can be applied to various communication systems, such as a wireless fidelity (WiFi) system, a vehicle to everything (V2X) communication system, a device-to-device (D2D) communication system, a vehicle networking communication system, a 4th generation (4G) mobile communication system such as an LTE system, a worldwide interoperability for microwave access (WiMAX) communication system, a 5th generation (5G) mobile communication system such as a new radio (NR) system, and a future communication system, an open RAN (O-RAN) system, etc.

[0110] The present application will present various aspects, embodiments or features around a system that can include a plurality of devices, components, modules, etc. It should be understood and appreciated that each system can include additional devices, components, modules, etc., and / or can not include all of the devices, components, modules, etc. discussed in conjunction with the accompanying drawings. In addition, combinations of these solutions can also be used.

[0111] In addition, the terms "exemplary," "for example," and the like are used as adjectives to indicate certain examples or instances, but not necessarily as a determination or limitation as to the merits of the elements being described. In the present disclosure, any embodiment or design solution described as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments or design solutions.

[0112] First, in the present disclosure, "for indicating" can include for directly indicating and for indirectly indicating. When describing that certain "information" is for indicating A, it can include that the information directly indicates A or indirectly indicates A, and it does not mean that A must be carried in the information.

[0113] The information indicated by one information is referred to as to-be-indicated information. In the implementation process, there are many ways to indicate the to-be-indicated information, for example, but not limited to, the to-be-indicated information can be directly indicated, such as the to-be-indicated information itself or an index of the to-be-indicated information. The to-be-indicated information can also be indirectly indicated by indicating other information, where the other information and the to-be-indicated information have an association relationship. The to-be-indicated information can also be only indicated in part, and the other part of the to-be-indicated information is known or agreed in advance. For example, the indication of a specific information can also be achieved by means of the arrangement order of each information agreed in advance (for example, a protocol stipulates), thereby reducing the indication overhead to a certain extent. At the same time, the common part of each information can be identified and uniformly indicated, so as to reduce the indication overhead caused by separately indicating the same information.

[0114] In addition, the specific indication manner can also be various existing indication manners, for example, but not limited to, the above-mentioned indication manners and various combinations thereof. The specific details of various indication manners can refer to the prior art, and will not be described herein. As can be seen from the above, for example, when multiple information of the same type needs to be indicated, the indication manner of different information can not be the same. In the implementation process, the required indication manner can be selected according to the specific needs, and the selected indication manner is not limited in the embodiments of the present disclosure. In this way, the indication manner involved in the embodiments of the present disclosure should be understood as covering various methods that can enable the to-be-indicated party to know the to-be-indicated information.

[0115] The to-be-indicated information can be sent as a whole or can be divided into multiple sub-information and sent separately, and the sending period and / or sending occasion of the sub-information can be the same or different. The specific sending method is not limited in the present application. The sending period and / or sending occasion of the sub-information can be predefined, for example, predefined according to a protocol, or configured by the transmitting end device to the receiving end device through sending configuration information. The configuration information can include, for example but not limited to, one or a combination of at least two of non-access layer signaling (NAS), radio resource control (RRC) signaling, medium access control (MAC) layer signaling and physical layer signaling. The MAC layer signaling can include, for example, MAC control element (CE), and the physical (PHY) layer signaling can include, for example, downlink control information (DCI).

[0116] Second, in the embodiments shown below, the first, second and various numbers are only distinguished for convenience of description, and do not limit the scope of the embodiments of the present application. For example, different indication information is distinguished.

[0117] Third, "preset" or "predefined" or "preconfigured" can be realized by pre-saving corresponding codes, tables or other ways that can be used to indicate related information in devices (for example, including terminals and network devices), and can also be pre-specified in a protocol. The specific implementation method is not limited in the present application. The "saving" can mean saving in one or more memories. The one or more memories can be separately set or integrated in the encoder or decoder, processor or communication device. The one or more memories can be part of the separately set and part of the integrated in the decoder, processor or communication device. The type of memory can be any form of storage medium, which is not limited in the present application.

[0118] Fourth, the "protocol" involved in the embodiments of the present application can refer to a standard protocol in the communication field, which can include, for example, the LTE protocol of 3GPP, the NR protocol and the related protocol applied to the future communication system, which is not limited in the present application.

[0119] The network architecture and service scenarios described in the embodiments of the present application are for more clearly illustrating the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. It can be known by those skilled in the art that, with the evolution of network architecture and the appearance of new service scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0120] The network architecture and service scenarios described in the embodiments of the present application are for more clearly illustrating the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. It can be known by those skilled in the art that, with the evolution of network architecture and the appearance of new service scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0121] To facilitate understanding of the embodiments of the present application, first, a communication system shown in FIG. 2 is taken as an example to illustrate the communication system applicable to the embodiments of the present application in detail. Exemplarily, FIG. 2 is a schematic diagram of the architecture of a communication system applicable to the method provided by the embodiments of the present application.

[0122] As shown in FIG. 2, the communication system includes at least one access network device (network device 201a to network device 201c) and at least one terminal device (such as terminal device 202a to terminal device 202f in FIG. 2).

[0123] The communication system can also include a core network device 203. The terminal device is connected to the access network device in a wireless manner, and the access network device is connected to the core network device in a wireless or wired manner. The core network device and the access network device can be independent and different physical devices, can be integrated into the same physical device with the functions of the core network device and the logical functions of the access network device, or can be a physical device integrated with part of the functions of the core network device and part of the functions of the access network device. The terminal device and the terminal device, and the access network device and the access network device can be connected to each other in a wired or wireless manner. FIG. 2 is only a schematic diagram, and the communication system can also include other network devices, such as wireless relay devices and wireless backhaul devices, which are not shown in FIG. 2.

[0124] The terminal device can be a terminal having a transceiver function, or can also be a chip or chip system provided in the terminal device. The terminal device can also be referred to as a user equipment (UE), an access terminal, a subscriber unit, a subscriber station, a mobile station (MS), a mobile station, a remote station, a remote terminal, a mobile device, a user terminal, a terminal, a wireless communication device, a user agent, or a user device. The terminal in the embodiments of the present application can be a mobile phone, a cellular phone, a smart phone, a Pad, a wireless data card, a personal digital assistant (PDA), a wireless modem, a handset, a laptop computer, a machine type communication (MTC) terminal, a computer with a wireless transceiver function, a virtual reality (VR) terminal, an augmented reality (AR) terminal, a smart home device (for example, a refrigerator, a television, an air conditioner, an electricity meter, etc.), a smart robot, a mechanical arm, a plant device, a wireless terminal in a self-driving vehicle, a wireless terminal in industrial control, a wireless terminal in self-driving, a wireless terminal in telemedicine, a wireless terminal in a smart grid, a wireless terminal in transportation safety, a wireless terminal in a smart city, a wireless terminal in a smart home, a vehicle-mounted terminal, a roadside unit (RSU) with a terminal function, etc., a flight device (for example, a smart robot, a hot air balloon, a drone, an airplane), etc. The terminal device of the present application can also be a vehicle-mounted module, a vehicle-mounted module, a vehicle-mounted component, a vehicle-mounted chip, or a vehicle-mounted unit built into a vehicle as one or more components or units. The terminal device can also be other devices with terminal functions, for example, the terminal device can also be a device with terminal functions in D2D communication. The embodiments of the present application do not limit the device form of the terminal device, and the device for realizing the function of the terminal device can be a terminal device; it can also be a device capable of supporting the terminal device to realize the function, such as a chip system. The device can be installed in the terminal or used with the terminal. In the embodiments of the present application, the chip system can be composed of a chip, or can include a chip and other discrete devices.

[0125] The access network device can be a device with wireless transceiver function, or also can be a chip or chip system arranged in the device, located in an access network (AN) of a communication system, and used to provide access services for terminals. For example, the access network device can be referred to as a radio access network (RAN) device, and specifically can be an access network device of a future communication system, for example, a base station of a future communication system, or in a future communication system, the access network device can also have other naming ways, which are all included in the protection scope of the embodiments of the present application, and the present application does not make any limitation on this. Alternatively, the access network device can also include a gNB in a 5G, such as a new radio (NR) system, or one or a group (including multiple antenna panels) of antenna panels of a base station in a 5G, or can also be a network node constituting a gNB, a transmission and reception point (TRP or transmission point, TP), or a transmission measurement function (TMF), such as a centralized unit (CU), a distributed unit (DU), a CU-control plane (CP), a CU-user plane (UP), or a radio unit (RU), an RSU with base station function, or a wired access gateway, or a core network element of a 5G, and the like. Alternatively, the access network device can also include an access point (AP) in a wireless fidelity (WiFi) system, a wireless relay node, a wireless backhaul node, various forms of macro base stations, micro base stations (also referred to as small stations), relay stations, access points, wearable devices, vehicle-mounted devices, and the like.

[0126] The CU and the DU can be separately arranged, or can also be included in the same network element, such as a baseband unit (BBU). The RU can be included in a radio frequency device or a radio frequency unit, such as a remote radio unit (RRU), an active antenna unit (AAU), or a remote radio head (RRH). It can be understood that the access network device can be a CU node, or a DU node, or a device including a CU node and a DU node. In addition, the CU can be divided into an access network device in the access network RAN, or the CU can be divided into an access network device in the core network CN, which is not limited here. In different systems, the CU (or CU-CP and CU-UP), the DU, or the RU can also have different names, but those skilled in the art can understand their meanings.

[0127] In the communication system provided in FIG. 2, the access network device can be an open RAN (O-RAN), in which case the CU can also be referred to as an open centralized unit (O-CU) or gNB-CU, the DU can also be referred to as an open distributed unit (O-DU) or gNB-DU, the CU-CP can also be referred to as an O-CU-CP, the CU-UP can also be referred to as an O-CU-UP, and the RU can also be referred to as an open radio unit (O-RU). In addition, in the O-RAN, an O-RAN radio intelligent controller (RIC) can also be included. The RIC can obtain information of the network side and / or the terminal device from the RAN node (such as the CU, the CU-CP, the CU-UP, the DU, and / or the RU) and / or the terminal device, and the RIC performs optimization tasks based on the information. For example, the RIC collects the configuration of the network device and / or the terminal device, and updates / optimizes the configuration of the network device and / or the terminal device. For another example, the RIC collects data of the network device and / or the terminal device for model training and inference, and accordingly, the RIC can submit the inference result to the network device and / or the terminal device. The RIC communicates with the O-CU and the O-DU through an E2 interface, that is, the O-RIC can control the gNB-DU.

[0128] For the convenience of description, in this application, CU, CU-CP, CU-UP, DU and RU are taken as examples for description. Any one of the CU (or CU-CP, CU-UP), DU and RU in this application can be implemented by a software module, a hardware module, or a combination of a software module and a hardware module. In the embodiments of this application, the form of the access network device is not limited, and the device for implementing the function of the access network device can be the access network device; or can be a device capable of supporting the access network device to implement the function, such as a chip system. The device can be installed in the access network device or used in matching with the access network device.

[0129] The core network device can be a core network equipment including an access and mobility management function (AMF), or a core network equipment including a network data analytics function (NWDAF), or an operations, administration and maintenance (OAM) equipment, etc., or can also be a chip or chip system, module, or component, etc. provided in the equipment.

[0130] It should be understood that in the embodiments of this application, the access network device and the core network device can be referred to as network devices, or devices on the network side. In some possible implementations, the chip or system or component for implementing the function of the access network device or the core network device can also be referred to as a network device.

[0131] It should be noted that the communication method provided by the embodiments of this application can be applied between the terminal device and the network device as shown in FIG. 2, or between the terminal device and the terminal device. The specific implementation can refer to the following method embodiments, which will not be described here.

[0132] It should be pointed out that the scheme in the embodiments of this application can also be applied to other communication systems, and the corresponding names can also be replaced by the names of the corresponding functions in other communication systems.

[0133] It should be understood that FIG. 2 is only a simplified schematic diagram for easy understanding, and other network devices and / or other terminal devices can also be included in the communication system, which are not shown in FIG. 2.

[0134] To solve the problems in the embodiments of the present application, the embodiments of the present application provide a communication method, in which a first communication device can obtain a first sequence and send the first sequence, wherein the first sequence is an AI sequence, which can be understood as a sequence determined by an AI model. In this way, the sending of the sequence can be implemented based on AI. On the one hand, the number of sequences can be limited by the root index of the sequence, the length of the sequence, and the cyclic shift of the sequence, thereby causing the problem of limited available sequences. On the other hand, the sequence detection performance can be improved by the low interference characteristics between AI sequences.

[0135] The first communication device can be a terminal device in the communication system provided in FIG. 2, and the second communication device can be an access network device in the communication system provided in FIG. 2. Alternatively, the first communication device can be a terminal device in the communication system provided in FIG. 2, and the second communication device can be a terminal device in the communication system provided in FIG. 2.

[0136] The communication method provided in the embodiments of the present application will be described in detail below with reference to FIGS. 3-13.

[0137] Exemplarily, FIG. 3 is a flowchart of a communication method provided in the embodiments of the present application. The communication method can be applied to the communication between any two devices shown in FIG. 2.

[0138] As shown in FIG. 3, the communication method includes the following steps:

[0139] S301, the first communication device obtains a first sequence. It can also be understood that the first communication device determines the first sequence.

[0140] The first sequence is determined by an AI model, and the sequence determined by the AI model is an AI sequence. Therefore, the first sequence is an AI sequence. The AI model can also be referred to as an AI network, which can be a model implemented based on one or more of the following ways, or a mapping relationship between input parameters and output parameters: neural network, deep learning, reinforcement learning, machine learning, federated learning, distributed learning, etc. The AI model can be a first AI model.

[0141] In one possible implementation, the first sequence is a set of trainable parameters in the AI model. Optionally, after the first AI model is determined (for example, after the AI model is trained), a part or all of the model parameters or the model weight parameter set of the first AI model can be determined as a set of sequences, and the set of sequences can include the first sequence.

[0142] In another possible implementation, the first sequence is an output result of the AI model according to a specific input, that is, an inference output result of the AI model. Optionally, the first sequence can be generated by a part of sub-models of the first AI model after the first AI model is determined (for example, after the AI model is trained), or the first sequence can be generated based on a second AI model determined by the first AI model, or a set composed of the first sequence.

[0143] In a possible implementation, the first AI model is a double-end model. In another possible implementation, the first AI model is a single-end model.

[0144] In a possible implementation, the first sequence is used for random access, or is used for synchronization, or is used for sensing a communication device other than the first communication device.

[0145] In the case where the first sequence is used for random access, the first sequence can be a sequence related to a ZC sequence, for example, a sequence used for initialization in a training process for training the first sequence is a ZC sequence. Alternatively, in the case where the first sequence is used for synchronization, the first sequence can be a sequence related to an m sequence, or a ZC sequence, or a gold sequence, for example, a sequence used for initialization in a training process for training the first sequence corresponds to an m sequence, or a ZC sequence, or a gold sequence. Alternatively, in the case where the first sequence is used for sensing a communication device other than the first communication device, the first sequence can be a sequence related to a ZC sequence or a gold sequence, for example, a sequence used for initialization in a training process for training the first sequence corresponds to a ZC sequence or a gold sequence.

[0146] In other possible implementations, the first sequence can be used for demodulating a signal (or can be used for channel estimation and demodulation), in which case, the reference signal can be a demodulation reference signal (DMRS). Alternatively, the first sequence can be used for measuring channel quality (or can be used for channel estimation), in which case, the reference signal can be a channel state information-reference signal (CSI-RS). The above signals can be generated based on an m sequence, a gold sequence, or a ZC sequence.

[0147] It should be understood that the first sequence listed in the embodiments of the present application is used as an example, and in actual implementation, the first sequence can also be other possible sequences.

[0148] In a possible implementation, the first sequence can include a plurality of sub-sequences, different sub-sequences in the plurality of sub-sequences are carried on different air interface resources, or different sub-sequences in the plurality of sub-sequences are mapped on different air interface resources, and the plurality of sub-sequences have correlation. The air interface resources can include one or more of the following: time domain resources, frequency domain resources, or space domain resources.

[0149] The different sub-sequences in the plurality of sub-sequences can be carried on different air interface resources, which can refer to the following one or more of the different sub-sequences carrying the plurality of sub-sequences: time domain resources, frequency domain resources, and space domain resources. Different sub-sequences corresponding to different space domain resources means that the sequence values of the sub-sequences sent on different antenna ports are different, or different sub-sequences are mapped on different antenna ports, for example, the sub-sequences on antenna port 1 are {x1, x2, …, xn}, the sub-sequences on antenna port 2 are {y1, y2, …, yn}, and {x1, x2, …, xn} is not completely the same as {y1, y2, …, yn}. Different sub-sequences corresponding to different time domain resources means that the sequence values of the sub-sequences carried on different time domain resources (such as time domain symbols, time slots, etc.) are different, or different sub-sequences are mapped on different time domain resources (such as time domain symbols, time slots, etc.). Different sub-sequences corresponding to different frequency domain resources means that the sequence values of the sub-sequences carried in different frequency domain ranges (such as subcarrier intervals) are different, or different sub-sequences are mapped on different frequency domain ranges (such as subcarrier intervals).

[0150] The plurality of sub-sequences have correlation, which means that the detection results of the plurality of sub-sequences can be jointly detected or combined for detection. In a possible case, each sub-sequence in the plurality of sub-sequences can be referred to as a sequence channel, and therefore the first sequence can be referred to as a multi-channel sequence. For example, in the case of a time domain multi-channel sequence, the first sequence can occupy a plurality of consecutive time domain symbols (such as OFDM symbols) in the time domain, and each symbol carries a sequence channel, that is, each symbol carries a sub-sequence. Different sequence channels can occupy the same or different resources in the frequency domain or the space domain in addition to different time domain resources. At the receiving end, the correlation operation can be performed on the received signal on each symbol and the preconfigured sub-sequence carried on the corresponding symbol, and the correlation result is a complex number. In the case where the plurality of sub-sequences have correlation, the complex number results after correlation on each symbol can be directly added, so as to realize the superposition of the amplitudes and phases of the correlation results on different time domain symbols. According to whether the amplitude or phase parameter of the superimposed result exceeds a certain threshold, it is determined whether the preconfigured sequence (such as the first sequence) is included in the received signal.

[0151] In a possible implementation, the first sequence corresponds to a first model. The first model is used to detect at least the first sequence. It should be understood that the first model is also determined by the AI model. In other words, the first sequence and the first model are determined by joint training as a whole. In a possible implementation, the first model is part of the first AI model. Alternatively, the first AI model includes the first model and a set of trainable parameters.

[0152] Since the first sequence is determined or generated by the AI model, and the first sequence can be detected by the first model, the first sequence and the first model can be jointly trained and optimized, which can avoid the problem of inaccurate detection caused by interference between sequences of different users in a multi-user scenario, thereby improving the detection performance.

[0153] Alternatively, the first model can also be used to determine channel information, which includes one or more of the following: timing advance (TA), frequency offset, time offset, channel state information, and the like. The channel state information can include channel quality indicator (CQI), rank indicator (RI), layer indicator (LI), precoding matrix indicator (PMI), signal to interference plus noise ratio (SINR), reference signal receiving power (RSRP), reference signal received quality (RSRQ), or received signal strength indication (RSSI). In actual implementation, the channel information can also be other channel-related information, which is not described herein.

[0154] In a possible implementation, the first sequence is one sequence in a first sequence set. The first sequence set includes at least one sequence, each sequence in the first sequence set is an AI sequence, and the sequences in the first sequence set are determined by the same AI model. It should be understood that the sequences in the first sequence set can also be referred to as AI sequences, and each sequence in the first sequence set has the same function as the first sequence. For example, the first sequence is a sequence for random access, and each sequence in the first sequence set is a sequence for random access. The AI model used to determine each sequence in the first sequence set is the same AI model. In addition, the sequences in the first sequence set correspond to the first model. In other words, the sequences in the first sequence set can be detected by the first model. Alternatively, the first model can detect each sequence in the first sequence set.

[0155] In a possible implementation, the number of sub-sequences included in each sequence in the first sequence set is the same as the number of sub-sequences included in the first sequence. In other words, each sequence in the first sequence set can include a plurality of sub-sequences, different sub-sequences in each sequence are carried on different air interface resources, or in other words, different sub-sequences in each sequence are mapped on different air interface resources, and the plurality of sub-sequences have a correlation. In this way, when detecting the first sequence, at least one of the time domain feature, the frequency domain feature, and the spatial domain feature of the channel can be better obtained based on the correlation between the plurality of sub-sequences in the first sequence, thereby improving the communication performance.

[0156] For the implementation of each sequence in the first sequence set, refer to the related description of the first sequence, which is not repeated here.

[0157] In the embodiments of this application, S301 can include that the first communication device determines the first sequence from the first sequence set.

[0158] In a possible implementation, the first sequence set is one of at least one second sequence set. The at least one second sequence set includes a sequence set available to the first communication device, that is, the first sequence set is one of the sequence sets available to the first communication device. Each second sequence set in the at least one second sequence set includes at least one sequence, each sequence in the second sequence set is an AI sequence, and the sequences in the same second sequence set are determined by the same AI model. In the case where the first sequence includes a plurality of sub-sequences, the sequences in the second sequence set can also include a plurality of sub-sequences. Each second sequence set in the at least one second sequence set corresponds to a model (also referred to as a detection model), and each sequence in the second sequence set can be detected by the model corresponding to the second sequence set, or in other words, the model corresponding to the second sequence set can detect the sequences in the second sequence set.

[0159] The first sequence set can be a sequence set determined by the first communication device from the at least one second sequence set, or the first sequence set can be a sequence set indicated by the second communication device from the at least one second sequence set. It should be understood that if the at least one second sequence set includes a second sequence set, the second sequence set is the first sequence set.

[0160] In a possible implementation, each of the at least one second sequence set is a sequence set in the at least one third sequence set. Each of the at least one third sequence set corresponds to a model, and the sequences in each of the at least one third sequence set can be detected by the model corresponding to the third sequence set, or in other words, the model corresponding to the third sequence set can be used to detect the sequences in the third sequence set. It can be understood that the number of sequence sets in the at least one second sequence set is less than or equal to the number of sequence sets in the at least one third sequence set. Alternatively, the at least one third sequence set can be indicated by the second communication device. Alternatively, the at least one third sequence set can be generated by the first communication device through an AI model.

[0161] Alternatively, the at least one second sequence set includes at least one third sequence set that has been activated. The at least one third sequence set that has been activated is a sequence set in an activated state, which is a usable sequence set for the first communication device, or in other words, a sequence set that can be used immediately. It should be understood that there can also be a sequence set that has not been activated in the at least one third sequence set. For the first communication device, the sequence set that has not been activated is a sequence set that has been disabled, or in other words, a sequence set that cannot be used immediately. For different communication devices, the activation state of the same sequence set can be the same or different. In addition, for different functions implemented by the same communication device, the activation state of the same sequence set can be the same or different. Taking a random access procedure as an example, if an initial random access procedure corresponds to a sequence set A and a schedule request (SR) procedure corresponds to a sequence set B, then in the initial random access procedure, the sequence set A is in an activated state and the sequence set B is in a deactivated state. When switching from the initial random access procedure to the schedule request procedure, the sequence set A is in a deactivated state and the sequence set B is in an activated state.

[0162] The first communication device can determine the sequence set in the active state according to the sequence set to be activated and / or the sequence set to be deactivated in the at least one third sequence set, so as to determine the activated sequence set. The sequence set to be activated and / or the sequence set to be deactivated in the at least one third sequence set can be determined by a protocol or can be indicated by the second communication device. In the embodiments of the present application, the sequence set to be activated refers to the sequence set that needs to be activated, and the sequence set to be deactivated refers to the sequence set that needs to be deactivated. After the sequence set is activated, the sequence set can become in the active state. After the sequence set is deactivated, the sequence set can become in the deactivated state. In addition, when one activated sequence set becomes in the deactivated state and another sequence set in the deactivated state becomes in the activated state, it can be considered as the switching of the activated sequence set, or the switching of the sequence set. It should be understood that, in the embodiments of the present application, the sequence set to be activated refers to the sequence set that needs to be activated before S301 is performed. The sequence set to be deactivated refers to the sequence set that needs to be deactivated before S301 is performed.

[0163] In some possible implementations, the first sequence can be one of a plurality of sequences, and the plurality of sequences can include the sequences in the at least one second sequence set. It should be understood that, in the embodiments of the present application, the at least one second sequence set can be obtained according to the plurality of sequences. For example, the plurality of sequences are divided according to the number of channels, and the sequences with the same number of channels are divided into the same sequence set, so as to obtain the at least one second sequence set. For another example, the plurality of sequences are divided according to the scenes corresponding to the sequences, and the sequences corresponding to the same scene are divided into the same sequence set, so as to obtain the at least one second sequence set. Here, the manner of dividing the plurality of sequences is only used for example, and other dividing manners can also exist, which will not be described hereinafter.

[0164] In some possible implementations, the first sequence can be one of a plurality of sequences, and the plurality of sequences can include the sequences in the at least one third sequence set. It should be understood that, in the embodiments of the present application, the at least one third sequence set can be obtained according to the plurality of sequences, and the specific implementation of obtaining the at least one third sequence set according to the plurality of sequences is similar to that of obtaining the at least one second sequence set according to the plurality of sequences, which will not be described hereinafter.

[0165] S302, the first communication device sends the first sequence. Correspondingly, the second communication device receives the first sequence.

[0166] The first communication device sending the first sequence means that the first communication device sends a reference signal generated by the first sequence, and the reference signal is mapped to a time-frequency resource. For example, in an OFDM system, after the reference signal completes the mapping of the time-frequency resource (for example, resource element mapping, RE mapping), it can be further converted into a time-domain signal through an IFFT operation, and then further converted into a time-domain baseband signal by adding a cyclic prefix CP, and then sent out through digital-to-analog conversion and radio frequency processing. It should be understood that, in the case that the first sequence is a frequency domain sequence, the first communication device can directly map the first sequence (frequency domain sequence) to the time-frequency resource. In the case that the first sequence is a time domain sequence, the first sequence can be converted into a frequency domain sequence first, and then the frequency domain sequence is mapped to the time-frequency resource.

[0167] It should be understood that if the resource to which the reference signal is mapped (which can also be referred to as the resource carrying the reference signal) further includes a space domain, such as a port resource, a space-time-frequency resource can be formed, that is, the reference signal can also be mapped to a space-time-frequency resource including a space domain resource. For the sake of simplicity, the following examples are only given with reference to the mapping of the reference signal to the time-frequency resource.

[0168] The second communication device receiving the first sequence means that the second communication device receives the reference signal after the mapping of the first sequence. For example, in an OFDM system, after the second communication device performs analog-to-digital conversion on the received signal, a time-domain baseband signal is obtained, and then further de-cyclic prefixing and FFT operation are performed to obtain a frequency domain signal, and then the corresponding frequency domain received signal containing the reference signal is obtained according to the time-frequency resource position of the reference signal mapping.

[0169] Optionally, in a random access scenario, there is a corresponding relationship between the sequence set and the rach occasion (RO) resource. The first sequence is carried on the RO resource corresponding to the first sequence set. That is, the first communication device sends the first sequence on the RO resource corresponding to the first sequence set. Correspondingly, the second communication device receives the first sequence on the RO resource corresponding to the first sequence set. In this way, the first communication device can implicitly indicate the information of the first sequence set through the time-frequency resource, and can avoid the first communication device separately indicating the information of the first sequence set, thereby reducing the overhead. The information of the first sequence set can be identification information such as the ID, index, name, etc. of the first sequence set. The information indicating the first sequence set can also be understood as indicating the first sequence set.

[0170] It should be understood that there can be no corresponding relationship between the sequence set and the RO resource.

[0171] S303, the second communication device detects the first sequence.

[0172] As an example, the second communication device at least correlates the reference signal obtained in S302 with each sequence in the first sequence set, so as to determine the detected sequence.

[0173] In a possible implementation, in a case where the second communication device can determine the first sequence set, the second communication device at least correlates the reference signal obtained in S302 with each sequence in the first sequence set, and inputs into a detection model (i.e., the first model), where each sequence in the first sequence set corresponds to a probability, and if there is a sequence in the first sequence set corresponding to a probability greater than a second threshold, it can be determined that the second communication device detects the sequence, or it can be determined that the first communication device transmits the sequence. For the first sequence, if the first sequence is detected, the probability corresponding to the first sequence is greater than the second threshold. It should be understood that the implementation of the second threshold can refer to the related description of the first threshold, and will not be repeated.

[0174] In another possible implementation, in a case where the second communication device cannot determine the first sequence set, the second communication device correlates the reference signal obtained in S302 with each sequence in at least one second sequence set, and inputs into a detection model (i.e., a detection model corresponding to each sequence set in the at least one second sequence set), where each sequence in the first sequence set corresponds to a probability, and if there is a sequence in the at least one second sequence set corresponding to a probability greater than a third threshold, it can be determined that the second communication device detects the sequence, or it can be determined that the first communication device transmits the sequence. For the first sequence, if the first sequence is detected, the probability corresponding to the first sequence is greater than the third threshold. The implementation of the third threshold can refer to the related description of the first threshold, and will not be repeated. It should be understood that the second communication device can also correlate the reference signal obtained in S302 with each sequence in at least one third sequence set, and will not be repeated.

[0175] It should be understood that the reference signal obtained in S302 can also be directly input into the detection model for detection, or the reference signal obtained in S302 can also be processed in other possible ways before being detected by the detection model. The principle is similar to the information obtained by correlating the model detected reference signal and the sequence in S303, and will not be repeated. In the embodiments of the present application, the probability corresponding to the sequence can refer to the probability for indicating the possibility of the existence of the sequence.

[0176] Based on the communication method provided in FIG. 3, the first communication device can obtain and transmit the first sequence. Since the first sequence is determined by the AI model, the number of sequences can be avoided to be limited by the root index of the sequence, the length of the sequence, and the cyclic shift of the sequence, thereby avoiding the problem that the available sequences are limited, and the method can be applied to more scenarios.

[0177] In addition, the sequence detection performance can be improved by the low interference characteristics between AI sequences.

[0178] S304, the second communication device sends information #1. Correspondingly, the first communication device receives the information #1.

[0179] The information #1 is used to indicate the generation mode information of the reference signal.

[0180] For example, when the reference signal is a preamble in random access, the information #1 is used to indicate the sequence used according to the preamble (which can also be referred to as a preamble sequence), and determine the generation, resource mapping, baseband signal generation, etc. of the preamble.

[0181] In a possible implementation, the information #1 can indicate the generation mode of the preamble by indicating one or more of the following: cyclic prefix (CP), cyclic shift of the sequence used by the preamble, and subcarrier spacing (SCS).

[0182] Among them, for the implementation of the CP of the first sequence, reference can be made to the related introduction of the CP in the prior art. The cyclic shift can be the cyclic shift value of the sequence used by the preamble. It should be understood that if the terminal device supports the sequence generated by formula (1) and formula (2), the length of the CP of the sequence in the first sequence set can be the same as the CP length of the sequence generated by formula (1) and formula (2). For the implementation of the cyclic shift and the SCS, reference can be made to the related introduction in the prior art.

[0183] It should be understood that in the embodiments of the present application, on the premise that the second communication device indicates the generation mode information of the reference signal in the non-AI mode, for example, in the case that the second communication device indicates the generation mode of the preamble based on the ZC sequence in the SIB message in the random access process, it can be predefined by the protocol that one or more of the CP, the cyclic shift or the SCS used by the first sequence is the same as the parameter (such as the zeroCorrelationZoneConfig parameter) in the generation mode of the preamble in the non-AI mode. At this time, it can also be understood that the information #1 is used to indicate one or more of the following: the cyclic prefix of the first sequence, the cyclic prefix addition mode of the first sequence, the cyclic shift value of the first sequence, the subcarrier spacing corresponding to the first sequence, or the interval between every two adjacent sub-sequences, the type of the first sequence, and the resource mapping mode of the first sequence.

[0184] In a possible implementation, if the first sequence includes multiple sub-sequences and the multiple sub-sequences are mapped on different time domain resources, optionally, information #1 can further include time lengths of intervals between every two adjacent sub-sequences in the multiple sub-sequences. The time lengths can be represented by symbols or sampling points. The time lengths of intervals between different two sub-sequences can be the same or different. As shown in (a) of FIG. 4, assuming that the length of one symbol is 4096k, the length of one symbol CP is 2048k, and the length of the sub-sequence is the length of the sub-sequence except the length of the CP in one symbol. The first sequence includes sub-sequence 1 to sub-sequence 4, sub-sequence 1 and sub-sequence 2 are adjacent, sub-sequence 2 and sub-sequence 3 are adjacent, and sub-sequence 3 and sub-sequence 4 are adjacent. The time length of the first sequence is 16384k, that is, 0.28 milliseconds (ms), the time lengths of intervals between sub-sequence 1 and sub-sequence 2, between sub-sequence 2 and sub-sequence 3, and between sub-sequence 3 and sub-sequence 4 are the same, for example, the length of one CP, that is, the different sub-sequences are separated by the CP. It can be understood that the time length of the interval between the adjacent two sub-sequences can also be greater than the length of the CP, for example, the time length of the interval between the adjacent two sub-sequences can be 4096k.

[0185] Alternatively, information #1 can further comprise a time length of interval between two adjacent sub-sequences in the plurality of sub-sequences after frequency domain resource mapping, which is applicable to the case that the plurality of sub-sequences are mapped on different OFDM symbols. The time length of interval between the frequency domain sequences of the two adjacent sub-sequences in the plurality of sub-sequences can be in units of symbols. The time length of interval between the two different sub-sequences can be the same or different. For example, the time length of interval between the frequency domain sequences of the two adjacent sub-sequences in the plurality of sub-sequences can be 0 symbol, in which case the two adjacent sub-sequences are each mapped on one symbol, and the two symbols are adjacent. As shown in (b) of FIG. 4, taking a first sequence comprising 4 sub-sequences as an example, sub-sequence 1 and sub-sequence 2 are adjacent, sub-sequence 2 and sub-sequence 3 are adjacent, and sub-sequence 3 and sub-sequence 4 are adjacent, then sub-sequence 1 is mapped on symbol n, sub-sequence 2 is mapped on symbol n+1, sub-sequence 3 is mapped on symbol n+2, and sub-sequence 4 is mapped on symbol n+3. Alternatively, the time length of interval between the frequency domain sequences of the two adjacent sub-sequences in the plurality of sub-sequences can also be 1 or more symbols. For example, as shown in (c) of FIG. 4, taking a first sequence comprising 4 sub-sequences, i.e., sub-sequence 1 to sub-sequence 4, as an example, sub-sequence 1 and sub-sequence 2 are adjacent, sub-sequence 2 and sub-sequence 3 are adjacent, and sub-sequence 3 and sub-sequence 4 are adjacent, then sub-sequence 1 is mapped on symbol n, sub-sequence 2 is mapped on symbol n+2, sub-sequence 3 is mapped on symbol n+4, and sub-sequence 4 is mapped on symbol n+7. n is a positive integer.

[0186] The two adjacent sub-sequences in the plurality of sub-sequences refer to that there is no other sub-sequence in the plurality of sub-sequences between the two sub-sequences. For example, in the case that the plurality of sub-sequences are time domain sequences, there is no other sub-sequence in the plurality of sub-sequences between the two adjacent sub-sequences in the time domain. For another example, in the case that the plurality of sub-sequences are frequency domain sequences, there is no other sub-sequence in the plurality of sub-sequences between the two adjacent sub-sequences in the frequency domain.

[0187] The information #1 can be carried in broadcast information, such as SIB. It should be understood that the information #1 can also be carried in other possible information and / or signaling.

[0188] The information #1 can also be referred to as seventh information.

[0189] In a possible implementation, in the case that the sequence set to be activated and / or deactivated is indicated by the second communication device, in combination with FIG. 3, as shown in FIG. 5, the method provided by the embodiments of the present application can further comprise: S501.

[0190] S501, the second communication device sends information #2. Correspondingly, the first communication device receives the information #2.

[0191] The information #2 is used to indicate the sequence set to be activated and / or the sequence set to be deactivated in the at least one third sequence set. Optionally, the information #2 can be used to indicate the activated third sequence set in the at least one third sequence set. Alternatively, the information #2 can be used to indicate the deactivated third sequence set in the at least one third sequence set. Alternatively, the information #2 can be used to indicate the activated and / or deactivated third sequence set in the at least one third sequence set.

[0192] That is, the first sequence is the sequence in the activated sequence set, so that the situation that the second communication device cannot correctly detect due to the transmission of the unactivated sequence can be avoided, and the detection efficiency and performance are improved.

[0193] S501 is an optional step, which is performed when the second communication device indicates the sequence set to be activated and / or the sequence set to be deactivated. When the sequence set to be activated and / or the sequence set to be deactivated in the at least one third sequence set is determined by the protocol, S501 is not needed to be performed. For example, according to the protocol, when the sequence set ID is in the range of 0-5, the corresponding sequence set is the activated sequence set. For another example, according to the protocol, the third sequence set is the activated sequence set in the default state.

[0194] In the embodiments of the present application, the sequence set to be activated, the sequence set to be deactivated, the activated state of the sequence set or the deactivated state of the sequence set are all for the first communication device unless otherwise specified. The sequence set to be activated refers to the sequence set that needs to be activated when S501 is performed. The sequence set to be deactivated refers to the sequence set that needs to be deactivated when S501 is performed.

[0195] The information #2 can also be referred to as the second information.

[0196] In a possible implementation, when the at least one third sequence set is indicated by the second communication device, the first communication device can obtain the at least one third sequence set from the second communication device. In this case, in combination with FIG. 3, as shown in FIG. 6, the method provided by the embodiments of the present application can further include S601.

[0197] S601, the second communication device sends information #3. Correspondingly, the first communication device receives the information #3.

[0198] The information #3 is used to indicate at least one third sequence set. The information #3 can include one or more of the following: the at least one third sequence set, or an identifier of each third sequence set in the at least one third sequence set, or model information used to generate each third sequence set in the at least one third sequence set. The information #3 can directly indicate the at least one third sequence set, or indirectly indicate the at least one third sequence set. The information #3 can also be referred to as first information.

[0199] In the case that the information #3 directly indicates the at least one third sequence set, the information #3 can optionally include each sequence set in the at least one third sequence set. Taking the case that the first sequence set includes a plurality of sub-sequences as an example, the first sequence set can be a three-dimensional matrix, such as a matrix of [N, M, L] (dimension N*M*L), and the information #3 can include the matrix. Wherein N represents N sequences, each sequence includes M sub-sequences, and each sub-sequence has a length of L. For example, each sub-sequence can be represented as [m_1, m_2, …, m_L], where the sequence values m_1, …, m_L are all complex numbers. M, N, and L are positive integers greater than or equal to 1. If the first sequence does not include a plurality of sub-sequences, the first sequence set can be a two-dimensional matrix, such as a matrix of [N, L] (dimension N*L).

[0200] In the case that the information #3 indirectly indicates the at least one third sequence set, the information #3 can optionally indicate an identifier of each third sequence set in the at least one third sequence set. In this case, the first communication device and the second communication device can each be preconfigured with a correspondence between each sequence set in the at least one third sequence set and an identifier of the sequence set. For example, a plurality of sequence sets can be predefined by a protocol, each sequence set in the plurality of sequence sets can be represented by an identifier, and the plurality of sequence sets can include the at least one third sequence set. In this case, the information #3 can include the identifier of each third sequence set in the at least one third sequence set. The first communication device can obtain the corresponding sequence set in the protocol by the identifier of each third sequence set in the at least one third sequence set. For another example, the plurality of sequence sets can be stored on a public website or server, the plurality of sequence sets can include the at least one third sequence set, and the protocol can refer to the website or server. The first communication device can obtain the at least one third sequence set in the plurality of sequence sets stored on the public website or server by the identifier of each third sequence set in the at least one third sequence set.

[0201] Alternatively, information #3 can include information for generating the model of each sequence set in the at least one third sequence set. For example, information #3 can include the model structure, model parameters, model identifier, etc. of the model corresponding to each sequence set in the at least one third sequence set, which are not described herein. The model corresponding to each sequence set can be stored in the second communication device, or in an OTT server or application server of the second communication device, or can be defined by a protocol, or stored in a public website or server. In the case where the model corresponding to each sequence set is stored in the second communication device, information #3 can include at least one of the model structure and model parameters, i.e. the second communication device indicates the model to the first communication device by model transmission or model delivery; in the case where the model corresponding to each sequence set is defined by a protocol, or stored in a public website or server, information #3 can include model identifier information, and the first communication device obtains the model structure and parameters, etc. by the model identifier and by protocol description, or by the public website or server.

[0202] It should be understood that the above example of information #3 indicating the at least one third sequence set is only for illustration, and other implementation manners can also be used in actual implementation, which are not described herein.

[0203] In the embodiments of the present application, information #3 can be carried in a broadcast message, such as a system information block (SIB). Alternatively, information #3 can be carried in a radio resource control (RRC) message, or information #3 can be carried in a non-access stratum (NAS) message. It should be understood that the SIB, RRC and NAS messages herein are only for illustration, and information #3 can also be carried in other possible information in actual implementation. For example, information #3 can also be carried in a dedicated radio bearer (DRB).

[0204] In the embodiments of the present application, information #3 can be carried in a broadcast message, such as a system information block (SIB). Alternatively, information #3 can be carried in a radio resource control (RRC) message, or information #3 can be carried in a non-access stratum (NAS) message. It should be understood that the SIB, RRC and NAS messages herein are only for illustration, and information #3 can also be carried in other possible information in actual implementation. For example, information #3 can also be carried in a dedicated radio bearer (DRB).

[0205] It can be seen that the first information can indicate the at least one third sequence set in different ways, which can improve flexibility. In addition, if the first information indicates the at least one third sequence set by the identifier of each third sequence set in the at least one third sequence set, the model information of the third sequence set and the at least one third sequence set itself can be avoided, and the overhead of the first information can be reduced.

[0206] For each third sequence set in the at least one third sequence set and the model corresponding to each third sequence set, one or two training methods can be used.

[0207] In one method, the AI sequence is a set of parameters that can be trained in the part of the double-end AI model. The double-end AI model refers to a double-end AI model including AI sequence sending and detection.

[0208] In this case, the double-end AI model includes a set of trainable parameters (which can also be referred to as a trainable matrix, a trainable vector, a plurality of trainable parameters, and can also be understood as model A) and two parts of model B. Taking the AI sequence as an example of a single-channel sequence, that is, the AI sequence does not include a subsequence, in this case, the trainable parameter matrix A is an N*L two-dimensional matrix, where N can be considered as the number of AI sequences to be trained, that is, the number of AI sequences to be trained includes AI sequence 1 to AI sequence N, and L is the length of the AI sequence to be trained. In the training stage, k column vectors are selected from model A as true value labels (or the identification of the k column vectors is taken as the true value label) for representing k AI sequences sent by the device sending sequence, and k channel state information (channel state information H1 to channel state information Hk) is taken as training data, where each channel state information is used to represent the channel between the device sending an AI sequence and the receiving device, and each channel state information includes at least L elements in the dimension, for example, the channel state information can be a P*L matrix, in the case of using the channel state information to represent the frequency domain channel, L can be the number of subcarriers, and P can be the number of transmitting antennas or the number of receiving antennas. The training data is input into model A, and the output result of model A can be considered as the received signal containing the sent AI sequence received at the receiving end. The result output by model A is taken as the input data of model B, or, optionally, the result output by model A is superimposed with random noise or interference and taken as the input data of model B, which is used to train model B. In one possible case, the output result of model B is the identification of k' sequences, which can be considered as the identification of the sent AI sequence inferred or detected by model B. According to the identification of the k' sequences and the identification of the actually sent k sequences, a loss error can be obtained. Optionally, model A and / or model B can also be adjusted (i.e., gradient back propagation) according to the loss error, until the error of model A and / or model B is less than an error threshold, or the number of training times reaches a certain number. Thus, model A, that is, the sequence set, can be obtained. It should be pointed out that the above training process is only an example, and in some cases, it can also be extended based on the training process, for example, the data amount of each training batch is K (the number of k cases to be generated in each iteration), and parallel training is performed, and for another example, the number of AI sequences selected (such as the value of k) can be dynamically changed each time the training is performed. In addition, the above channel state information H can be used to represent the frequency domain channel, and the trained AI sequence is the frequency domain form of the AI sequence, or is considered as the form of the AI sequence mapped on the frequency domain. If the trained AI sequence is required to be in the time domain form, the channel state information used can represent the time domain channel. The principle of determining at least one third sequence set in mode 1 is illustrated below by taking FIG. 7 as an example. As shown in FIG. 7, model A includes sequence 1 to sequence N.For example, sequence 1 and sequence n are selected from sequence 1 to sequence N, sequence 1 is multiplied by channel H1 and superimposed with random noise or interference to obtain received signal 1; sequence n is multiplied by channel H2 and superimposed with random noise or interference to obtain received signal 2. Received signal 1 and received signal 2 are input into model B, so that detected sequence 1' and sequence 2' can be obtained. Model A and / or model B are adjusted based on the error of the sequence detected by model B until the error of model A and / or model B is less than the error threshold or the number of training reaches a certain number, so that trained model A and trained model B can be obtained. Adjusting model A can also be understood as adjusting the parameters in the trainable parameter set.

[0209] In the second mode, at least one third sequence set is determined by an AI sub-model. For example, a specific value, such as the identification of a sequence, is input into the AI sub-model, and at least one sequence in the at least one third sequence set can be obtained. At this time, the at least one third sequence set is the inference output result set of the AI sub-model. In this case, the double-end model includes model C and model D. The training process of model C and model D can refer to the first mode, and the difference is that the model A in the first mode is a trainable parameter matrix, while the model C in the second mode can be a neural network. The principle of determining at least one third sequence set in the second mode is illustrated below with reference to FIG. 8. As shown in FIG. 8, the identification of sequence 1 to the identification of sequence N is input into model C, and model C can obtain sequence 1 to sequence N. For example, sequence 1 and sequence n are selected from sequence 1 to sequence N, sequence 1 is multiplied by channel H1 and superimposed with random noise or interference to obtain received signal 1; sequence n is multiplied by channel H2 and superimposed with random noise or interference to obtain received signal H2. Received signal 1 and received signal 2 are input into model D, so that detected sequence 1' and sequence 2' can be obtained. Model C and / or model D are adjusted based on the error of the sequence detected by model D until the error of model C and / or model D is less than the error threshold or the number of training reaches a certain number, so that trained model C and trained model D can be obtained.

[0210] It should be understood that after the double-end model is trained by the first mode, the AI sequence determined by model A can be detected using model B, and model B is the detection model corresponding to the sequence set. It can be considered that the AI sequence set is determined by the double-end AI model, and after model A (or the trainable parameter set A) is obtained, the AI sequence (which is a column in the trainable parameter matrix) can be directly determined. After the double-end model is trained by the second mode, the AI sequence determined by model C can be detected using model D, and model D is the detection model corresponding to the sequence set. The AI sequence set is determined by the double-end AI model, and after model C is obtained, the AI sequence can be generated by model C.

[0211] It should be understood that the first and second manners are only used for example, and in actual implementation, other possible manners can also be used to train the at least one third sequence set and the detection model corresponding to each third sequence set in the at least one third sequence set.

[0212] In the case where the at least one third sequence set indicated in information #3 is determined by the second communication device through an AI model, the principle of determining the at least one third sequence set by the second communication device through the AI model can refer to the related description of determining the at least one third sequence set by the first communication device through the AI model, and will not be described herein.

[0213] In the case where the at least one third sequence set indicated in information #3 is determined by the third communication device through an AI model and then sent to the second communication device, the method provided in the embodiments of the present application can further include S602.

[0214] S602, the third communication device sends information #4. Correspondingly, the second communication device receives information #4.

[0215] Information #4 is used to indicate the at least one third sequence set. As an example, the first communication device can be a terminal device, the second communication device can be an access network device, and the third communication device can be a core network device, such as the core network device in the communication system provided in FIG. 2.

[0216] It should be understood that in the embodiments of the present application, the different third sequence sets and the models corresponding to the third sequence sets in the at least one third sequence set can be obtained by different communication devices. For example, the sequence set A and the model corresponding to the sequence set A are obtained by the second communication device, and the sequence set B and the model corresponding to the sequence set B can be obtained by the fourth communication device, where the second communication device and the fourth communication device can be access network devices. In the case where the second communication device is a first access network device and the fourth communication device is a second access network device, in the embodiments of the present application, the interference between each sequence set in the at least one third sequence set and the sequence set corresponding to the second access network device is less than or equal to the interference threshold, where the interference between two sequence sets can be measured by the correlation result between the sequences, for example, using the absolute value or the square of the absolute value of the correlation result, and the interference between the sets can be measured by the maximum or average of the correlation result of the sequences in set A and the sequences in set B. Wherein, the interference threshold can be determined according to the actual situation. In this way, two sequence sets with low correlation can correspond to different access network devices, so as to reduce the correlation between the sequence sets of different access network devices and reduce the interference between different access network devices. In a possible implementation, the first access network device and the second access network device can communicate directly, such as through X2 interface or N2, the first access network device can calculate the interference between the sequence set of the first access network device and the sequence set of the second access network device, and determine the sequence set with low correlation. In another possible implementation, the third communication device can calculate the correlation between the sequence sets of the first access network device and the second access network device, and indicate or send the sequence set with low correlation to the first access network device and the second access network device, where the first access network device and the second access network device can communicate directly with the third communication device, such as through S1 interface or N2 interface.

[0217] In another possible implementation, in the case where the at least one third sequence set is determined by the first communication device through the AI model, the method provided by the embodiments of the present application can further include: the first communication device determines the at least one third sequence set through the AI model. For the implementation of determining the at least one third sequence set through the AI model by the first communication device, reference can be made to the related description of determining the at least one third sequence set through the AI model by the second communication device, which will not be repeated here. In this case, as shown in FIG. 9, the method provided by the embodiments of the present application can further include S901 to S903 in combination with FIG. 3:

[0218] S901, the second communication device sends information #5. Correspondingly, the first communication device receives the information #5.

[0219] The information #5 is used to indicate the capability of the second communication device. Wherein, the capability of the second communication device includes the input, output, and computing power requirement of the model provided by the second communication device for detecting the sequence. For example, the input requirement of the model can be a constraint on the dimension of the model input, such as the model receiving at most X input values, the output of the model can be a constraint requirement on the dimension of the model output, such as the model outputting at most Y values, and the computing power requirement can be a maximum computing complexity requirement of the model, such as Z floating point (Z FLOPs) number calculation.

[0220] The information #5 can also be referred to as the sixth information.

[0221] In the case where there is a model in the model in the first communication device that matches the capability of the second terminal device, the following S902 is performed. Wherein, there is a model in the model in the first communication device that matches the capability of the second terminal device can include: there is a model in the model in the first communication device that meets the model input requirement, model output requirement, computing power requirement, etc. of the second communication device.

[0222] S902, the first terminal device sends information #6. Correspondingly, the second terminal device receives the information #6.

[0223] Wherein, the information #6 is used to indicate the first model, and the information #6 can also be used to indicate the input form and output form of the first model. For example, the input form can include that the information input into the model is the received signal. The output form can be that the information output from the model is the detected sequence identifier, or the time offset, or the frequency offset. It should be pointed out that the above input form and output form are only examples, and there can be other input forms and output forms, depending on the implementation of the first model.

[0224] Optionally, the information #6 can also include the processing manner of the information before the input model (which can also be referred to as the pre-processing manner) or the processing manner of the information output from the model (which can also be referred to as the post-processing manner). For example, the pre-processing manner can include performing frequency domain correlation processing or time domain correlation processing on the received signal and the sequences in the first sequence set. The post-processing manner can include performing inverse normalization processing on the result of the existence of the normalized output.

[0225] Optionally, the information #6 can also be used to indicate the first sequence set.

[0226] In this way, the second communication device can be indicated that the detection model matching the first sequence can be in the first sequence set, and the detection model matching the first sequence is determined by the first communication device, so that the second communication device can adopt the matching detection model, and the detection efficiency for the first sequence set is improved.

[0227] The information #6 can also be referred to as the fifth information.

[0228] In the embodiments of the present application, if the first communication device is a terminal device and the second communication device is a terminal device, before performing S901, the method provided by the embodiments of the present application can further include S903.

[0229] S903, the first communication device and the second communication device access the network through the fourth communication device.

[0230] The fourth communication device can be an access network device. In this way, the first communication device and the second communication device can obtain resources for sidelink communication.

[0231] It should be understood that in the embodiments of the present application, when performing S901 and S902, the first communication device and the second communication device can be in a connected state or a non-connected state with the network device.

[0232] In some possible implementations, there is a corresponding relationship between the sequence set and the scenario, or the sequence set applicable in different scenarios is different, or the applicable conditions of different sequence sets are different. In this case, the first sequence set can be determined according to the first condition met by the first communication device and the first corresponding relationship. The first corresponding relationship includes a corresponding relationship between each of the at least one second sequence set and the applicable condition. The first sequence set is one of the at least one second sequence set. That is, the sequence corresponding to the first condition can be determined as the first sequence according to the first corresponding relationship, so that the first sequence matches the first condition, that is, the first sequence matches the actual situation or condition of the first communication device.

[0233] The applicable condition can be related to a state of the communication device. The applicable condition can also be divided into a network-side applicable condition and a terminal-side applicable condition. For example, the applicable condition can be determined according to the state of the communication device. The state of the communication device includes one or more of the following: a speed of the communication device, a signal to interference plus noise ratio (SINR) of the communication device, a signal to noise ratio (SNR) of the communication device, a location of the communication device, an antenna angle of the communication device, a beam pattern, and the like. The applicable condition can also be referred to as an applicable scenario, or a scenario corresponding to the sequence set. For example, the speed of the communication device can include a first speed range, a second speed range, and a third speed range, where the first speed range can be a speed range less than or equal to a first speed threshold, the second speed range can be a speed range greater than the first speed threshold and less than or equal to a second speed threshold, and the third speed range can be a speed range greater than the second speed threshold. The SNR of the communication device can include a high signal to noise ratio and a low signal to noise ratio, where the high signal to noise ratio refers to a signal to noise ratio greater than a signal to noise ratio threshold, and the low signal to noise ratio refers to a signal to noise ratio less than the signal to noise ratio threshold. Similarly, the SINR of the communication device can include a high signal to interference plus noise ratio and a low signal to interference plus noise ratio, where the high signal to interference plus noise ratio refers to a signal to interference plus noise ratio greater than a signal to interference plus noise ratio threshold, and the low signal to interference plus noise ratio refers to a signal to interference plus noise ratio less than the signal to interference plus noise ratio threshold. The location of the communication device can include indoor and outdoor, and the like. The antenna angle of the communication device can include a first angle range, a second angle range, a third angle range, and the like. The beam pattern of the communication device can include a first beam pattern, a second beam pattern, and the like. The above-mentioned states of the communication device and ranges are only examples, and other states of the communication device or division ranges can also exist in actual implementation.

[0234] The first condition satisfied by the first communication device is an applicable condition corresponding to one of the at least one second sequence set.

[0235] For example, assuming that the at least one second sequence set includes sequence set 1 to sequence set 3, the first correspondence relationship includes a correspondence relationship between each of sequence set 1 to sequence set 3 and an applicable condition, and the first correspondence relationship is shown in Table 1 as follows:

[0236] Table 1

[0237] It should be understood that the at least one second sequence set in the above Table 1 is only for example, and in actual implementation, other sequence sets can be included in the at least one second sequence set. The first correspondence can further include a correspondence between a sequence set other than the at least one second sequence set and an applicable condition, such as a correspondence between a sequence set other than the at least one second sequence set in the at least one third sequence set and an applicable condition.

[0238] Optionally, in embodiments of the present application, the first correspondence can be agreed by a protocol, or the first correspondence can be indicated by a device at a network side. For example, when the second communication apparatus is a device at a network side, the first correspondence can be indicated by the second communication apparatus. In the case where the first correspondence is indicated by the second communication apparatus, in combination with FIG. 3, as shown in FIG. 10, the method provided by embodiments of the present application can further include S1001.

[0239] S1001, the second communication apparatus sends information #7. Correspondingly, the first communication apparatus receives the information #7.

[0240] The information #7 is used to indicate the first correspondence.

[0241] It should be understood that S1001 is an optional step, and in the case where the first correspondence is indicated by the second communication apparatus, S1001 is performed. In the case where the first correspondence is agreed by a protocol, S1001 need not be performed.

[0242] It should be understood that in the case where the at least one third sequence set is indicated by the second communication apparatus, the information #7 and the information #2 can be carried in a same message, in which case, the information #2 and the information #7 are collectively referred to as first information. In other words, the first information can be further used to indicate the applicable condition of each third sequence set in the at least one third sequence set.

[0243] That is, the second communication apparatus can configure at least one sequence set for the first communication apparatus, so that the at least one sequence set can be applicable to a scenario where the first communication apparatus cannot determine the sequence set by itself.

[0244] In a possible implementation, in a case where the first sequence set is determined by the first communication device from at least one second sequence set, the first communication device can indicate the first sequence set to the second communication device, for example, in a scenario where the sequence is dedicated to the first communication device, such as in a non-random access procedure, the first communication device can indicate the first sequence set to the second communication device in an explicit indication manner. In this way, the second communication device can select a model corresponding to the first sequence set for sequence detection, avoid blind detection, and thus reduce the processing complexity on the second communication device. The first communication device can indicate the first sequence set to the second communication device in an explicit indication manner. Alternatively, the first communication device can indicate the first sequence set to the second communication device in an implicit indication manner. The explicit indication and the implicit indication are described below.

[0245] Optionally, in a case where the first communication device indicates the first model to the second communication device in an explicit indication manner, as shown in FIG. 11, the method provided in the embodiments of the present application can further include S1101.

[0246] S1101, the first communication device sends information #8. Correspondingly, the second communication device receives the information #8.

[0247] The information #8 is used to indicate the first sequence set.

[0248] Optionally, the information #8 can also be used to indicate a valid time length of the first sequence set, that is, a time length during which the first communication device can select a sequence from the first sequence set. In this way, the UE does not have to indicate the set to which the first sequence belongs each time the first sequence is sent.

[0249] In this way, the second communication device can determine a detection model matched with the first sequence set, so as to avoid using a detection model that does not match to detect the sequence, reduce the calculation amount of the second communication device, and improve the detection efficiency.

[0250] The information #8 can also be referred to as third information.

[0251] In a case where the method provided in the embodiments of the present application includes S1101, the method provided in the embodiments of the present application can further include S1102.

[0252] S1102, a connection is established between the first communication device and the second communication device.

[0253] Alternatively, in a case that there is a correspondence between the sequence set and the random access occasion (RO) resource in the random access scenario, the first communication device indicates the first model to the second communication device in a manner of implicit indication. In this case, as shown in FIG. 12, the method provided by the embodiment of the application can further include S1201.

[0254] S1201, the second communication device sends information #9. Correspondingly, the first communication device receives the information #9.

[0255] The information #9 is used to indicate the correspondence between the RO resource and the sequence set. That is, there is a correspondence between the sequence set and the RO resource. In this case, the second communication device can determine the model for detecting the sequence according to the resource of the received reference signal. For example, the second communication device can determine the model for detecting the sequence as the first model according to the reference signal corresponding to the first sequence.

[0256] That is, the time-frequency resource of each sequence set is configured by the second communication device, so that the conflict between different first communication devices can be reduced. In addition, in this scenario, there is a correspondence between the time-frequency resource and the sequence set, so that the second communication device can determine the model for detecting the sequence based on the time-frequency resource carrying the sequence, avoiding the first communication device indicating the sequence set corresponding to the first sequence, such as the above-mentioned first sequence set, by using separate signaling, so that the resource overhead can be reduced.

[0257] In a possible implementation, the information #9 is a SIB message.

[0258] The information #9 can also be referred to as fourth information.

[0259] In another possible implementation, in a case that the first sequence set is a fourth sequence set configured by the second communication device, as shown in FIG. 13, the method provided by the embodiment of the application can further include S1301 in combination with FIG. 3:

[0260] S1301, the second communication device sends information #10. Correspondingly, the first communication device receives the information #10.

[0261] The information #10 is used to indicate the fourth sequence set.

[0262] It should be understood that, in the embodiment of the application, the first sequence is a first type of sequence, and the method provided by the embodiment of the application can further include that the second communication device sends information #11. Correspondingly, the first communication device receives the information #11.

[0263] The information #11 is used to indicate that the priority of the first type of sequence is higher than the priority of the second type of sequence. The first type of sequence is a sequence determined by an AI model, and the second type of sequence is a sequence determined by a non-AI model. For example, the second type of sequence can be a sequence determined in a manner of an existing standard, such as a manner in NR protocol TS 38.211, for example, a ZC sequence. It should be understood that the second type of sequence is a ZC sequence for example, and in actual implementation, the second type of sequence can also be other possible sequences, such as an m sequence or a gold sequence, which are not described herein. The priority of the first type of sequence is higher than the priority of the second type of sequence, which means that in a case where the first type of sequence and the second type of sequence exist on the first communication device and are used to implement the same function, the first type of sequence is used to implement the function.

[0264] It should be understood that in another implementation, the information #11 is used to indicate that the priority of the first type of sequence is lower than the priority of the second type of sequence.

[0265] It should be understood that the priority relationship between the first type of sequence and the second type of sequence can also be determined in a pre-defined manner, for example, determined in a manner of a protocol, and in this case, the second communication device can send the information #11, and the first communication device determines the priority of the first type of sequence and the second type of sequence according to the pre-defined priority relationship.

[0266] In this way, the first communication device can obtain the priority relationship between the first type of sequence and the second type of sequence, so that the first type of sequence can be preferentially selected in a case where the first type of sequence and the second type of sequence exist. Since the first type of sequence is a sequence obtained by an AI model, it can be suitable for more user scenarios, thereby improving detection efficiency.

[0267] The information #11 can also be referred to as tenth information.

[0268] In a possible implementation, before S301, the method provided by the embodiment of the present application can include: the second communication device sends information #12. Correspondingly, the first communication device receives the information #12. The information #12 is used to indicate switching of a first sequence set.

[0269] In this way, the second communication device can manage the sequence set, so that the activated sequence is more flexible.

[0270] The information #12 can also be referred to as ninth information.

[0271] The communication method provided by the embodiment of the present application is described in detail above in combination with FIGS. 3-13. The communication device used to execute the communication method provided by the embodiment of the present application is described in detail below in combination with FIGS. 14-15.

[0272] Exemplarily, FIG. 14 is a structural schematic diagram I of a communication apparatus provided in the embodiments of the present application. As shown in FIG. 14, the communication apparatus 1400 includes a processing module 1401 and a transceiver module 1402. For ease of illustration, FIG. 14 only shows the main components of the communication apparatus 1400.

[0273] In some embodiments, the communication apparatus 1400 can be applicable to the communication system shown in FIG. 2, and perform the functions of the first communication apparatus 1400 in the communication method shown in FIG. 3.

[0274] The processing module 1401 is configured to obtain a first sequence. The first sequence is determined by an artificial intelligence (AI) model, and the first sequence is used for random access, or is used for synchronization, or is used for sensing a communication apparatus 1400 other than the first communication apparatus 1400.

[0275] The transceiver module 1402 is configured to send the first sequence.

[0276] Optionally, the transceiver module 1402 can include a receiving module and a sending module (not shown in FIG. 14). The transceiver module 1402 is configured to implement the sending function and the receiving function of the communication apparatus 1400.

[0277] Optionally, the communication apparatus 1400 can further include a storage module (not shown in FIG. 14), which stores a program or instructions. When the processing module 1401 executes the program or instructions, the communication apparatus 1400 can perform the functions of the first communication apparatus 1400 in any one of the communication methods shown in FIG. 3.

[0278] It should be understood that the processing module 1401 involved in the communication apparatus 1400 can be implemented by a processor or a processor-related circuit component, and can be a processor or a processing unit; and the transceiver module 1402 can be implemented by a transceiver or a transceiver-related circuit component, and can be a transceiver or a transceiving unit.

[0279] It should be noted that the communication apparatus 1400 is a terminal device or a network device, or a chip (system) or other components or assemblies, or an apparatus containing the terminal device or the network device. The chip can be arranged in the terminal device or the network device.

[0280] In addition, the technical effects of the communication apparatus 1400 can refer to the technical effects of any one of the communication methods shown in FIG. 3, which will not be described herein again.

[0281] In other embodiments, the communication apparatus 1400 can be applicable to the communication system shown in FIG. 2, and perform the functions of the second communication apparatus in the communication method shown in FIG. 3.

[0282] The transceiver module 1402 is configured to receive the first sequence. The first sequence is determined by an artificial intelligence (AI) model, and the first sequence is used for random access, or is used for synchronization, or is used for sensing a communication device 1400 other than the first communication device 1400.

[0283] The processing module 1401 is configured to detect the first sequence.

[0284] Optionally, the transceiver module 1402 can include a receiving module and a sending module (not shown in FIG. 14). The transceiver module 1402 is configured to implement the sending function and the receiving function of the communication device 1400.

[0285] Optionally, the communication device 1400 can further include a storage module (not shown in FIG. 14), which stores a program or instructions. When the processing module 1401 executes the program or instructions, the communication device 1400 can perform the functions of the second communication device 1400 in any one of the communication methods shown in FIG. 3.

[0286] It should be understood that the processing module 1401 involved in the communication device 1400 can be implemented by a processor or a processor-related circuit component, and can be a processor or a processing unit; the transceiver module 1402 can be implemented by a transceiver or a transceiver-related circuit component, and can be a transceiver or a transceiving unit.

[0287] It should be noted that the communication device 1400 is a terminal device or a network device, or a chip (system) or other components or assemblies, or a device containing the terminal device or the network device. The chip can be arranged in the terminal device or the network device.

[0288] In addition, the technical effects of the communication device 1400 can refer to the technical effects of any one of the communication methods shown in FIG. 3, which will not be described here.

[0289] Exemplarily, FIG. 15 is a structural schematic diagram of a communication device provided by an embodiment of the present application. The communication device can be a terminal device or a network device, or a chip (system) or other components or assemblies that can be arranged in the terminal device or the network device. As shown in FIG. 15, the communication device 1500 can include a processor 1501. Optionally, the communication device 1500 can further include a memory 1502 and / or a transceiver 1503. The processor 1501 is coupled with the memory 1502 and the transceiver 1503, for example, through a communication bus.

[0290] The various constituent components of the communication device 1500 will be specifically introduced below in combination with FIG. 15:

[0291] The processor 1501 is a control center of the communication device 1500, which can be one processor or collectively refer to multiple processing elements. For example, the processor 1501 is one or more central processing units (CPUs), application specific integrated circuits (ASICs), or one or more integrated circuits configured to perform the functions of the embodiments of the present application, such as one or more digital signal processors (DSPs), or one or more field programmable gate arrays (FPGAs).

[0292] Optionally, the processor 1501 can perform various functions of the communication device 1500 by running or executing software programs stored in the memory 1502 and calling data stored in the memory 1502.

[0293] In a specific implementation, as an embodiment, the processor 1501 can include one or more CPUs, such as CPU0 and CPU1 shown in FIG. 15.

[0294] In a specific implementation, as an embodiment, the communication device 1500 can also include multiple processors, such as the processor 1501 and the processor 1504 shown in FIG. 15. Each of these processors can be a single-CPU or a multi-CPU. The processor here can refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0295] The memory 1502 is used to store software programs for executing the schemes of the present application, and is controlled by the processor 1501 to perform the execution. The specific implementation can refer to the above method embodiments, which will not be repeated here.

[0296] Optionally, the memory 1502 can be a read-only memory (ROM) or other type of static storage device that can store static information and instructions, a random access memory (RAM) or other type of dynamic storage device that can store information and instructions, an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disk storage, a magnetic disk storage or other magnetic storage devices, or any other medium capable of storing desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited to this. The memory 1502 can be integrated with the processor 1501 or exist independently and be coupled to the processor 1501 through the interface circuit (not shown in FIG. 15) of the communication apparatus 1500, and the embodiments of the present application do not make a specific limitation in this regard.

[0297] The transceiver 1503 is configured to communicate with other communication apparatuses. For example, the communication apparatus 1500 is a terminal device, and the transceiver 1503 can be configured to communicate with a network device or another terminal device. For another example, the communication apparatus 1500 is a network device, and the transceiver 1503 can be configured to communicate with a terminal device or another network device.

[0298] Optionally, the transceiver 1503 can include a receiver and a transmitter (not shown separately in FIG. 15). The receiver is configured to implement the receiving function, and the transmitter is configured to implement the transmitting function.

[0299] Optionally, the transceiver 1503 can be integrated with the processor 1501 or exist independently and be coupled to the processor 1501 through the interface circuit (not shown in FIG. 15) of the communication apparatus 1500, and the embodiments of the present application do not make a specific limitation in this regard.

[0300] It should be noted that the structure of the communication apparatus 1500 shown in FIG. 15 does not constitute a limitation on the communication apparatus, and the actual communication apparatus can include more or fewer components than those shown, or combine certain components, or have a different arrangement of components.

[0301] In addition, the technical effects of the communication apparatus 1500 can refer to the technical effects of the communication method described in the above method embodiments, which will not be described here again.

[0302] It is to be understood that the processor in the present application can be a CPU, and can also be other general-purpose processors, DSPs, ASICs, FPGAs or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor.

[0303] It should also be understood that the memory in the present application can be a volatile memory or a nonvolatile memory, or can include both volatile and nonvolatile memory. Among them, the nonvolatile memory can be a ROM, a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an EEPROM or a flash memory. The volatile memory can be a RAM used as an external cache. By way of example, but not limitation, many forms of RAM can be used, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchlink DRAM (SLDRAM) and direct rambus RAM (DR RAM).

[0304] The above-described embodiments can be implemented in part or in whole through software, hardware (e.g., circuitry), firmware, or any combination thereof. When implemented in software, the above-described embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When loaded and executed by a computer, the computer instructions or computer programs can produce the processes or functions described above in accordance with the embodiments of the present application. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable apparatus. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, such as from a website site, a computer, a server, or a data center to another website site, a computer, a server, or a data center through a wired (e.g., infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium or a collection of medium accessible by a computer or a data storage device such as a server, a data center, etc. containing one or more available medium. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state disk.

[0305] It should be understood that the term "and / or" in this document is merely used to describe an associated relationship between associated objects, and can represent three relationships, for example, A and / or B can represent three cases of A alone, A and B together, and B alone, where A and B can be singular or plural. In addition, the character " / " in this document generally represents an "or" relationship between the front and rear associated objects, but can also represent an "and / or" relationship. The specific meaning can be understood according to the context before and after.

[0306] In this application, "at least one" means one or more, and "multiple" means two or more. "At least one of the following" or similar expressions means any combination of the items, including any combination of single or multiple items. For example, at least one of a, b, or c can represent a, b, c, a-b, a-c, b-c, or a-b-c, where a, b, and c can be single or multiple.

[0307] It should be understood that in various embodiments of the present application, the size of the sequence number of the above-described processes does not mean the order of execution, and the execution order of the processes should be determined according to their functions and inherent logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0308] Those skilled in the art can clearly understand that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0309] Those skilled in the art can clearly understand that, for the convenience and brevity of the description, the specific working processes of the above-described system, device and unit can refer to the corresponding processes in the foregoing method embodiments, which will not be repeated here.

[0310] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the above-described device embodiments are only schematic, for example, the division of the units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units shown or discussed can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0311] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on a plurality of network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0312] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically independently, or two or more units can be integrated into one unit.

[0313] If the functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer readable storage medium. Based on this understanding, the technical solutions of the present application essentially or the parts that contribute to the prior art or parts of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage medium includes various media that can store program codes, such as a U disk, a mobile hard disk, a ROM, a RAM, a magnetic disk or an optical disk, etc.

[0314] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A communication method, characterized in that, The method includes: Obtain a first sequence; wherein the first sequence is determined by an artificial intelligence (AI) model, and the first sequence is used for random access, or for synchronization, or for sensing communication devices other than the first communication device; Send the first sequence.

2. The method according to claim 1, characterized in that, The first sequence corresponds to the first model; the first model is used to detect at least the first sequence.

3. The method according to claim 1 or 2, characterized in that, The first sequence includes multiple subsequences, and different subsequences are carried on different air interface resources, and the values ​​of the multiple subsequences are correlated.

4. The method according to any one of claims 1-3, characterized in that, The first sequence is a sequence in a first sequence set, which is determined based on a first condition satisfied by the first communication device and a first correspondence; wherein, the first correspondence includes the correspondence between each of the at least one second sequence set and the applicable condition; the first sequence set is one of the at least one second sequence set.

5. The method according to claim 4, characterized in that, The method further includes: Receive first information; wherein the first information is used to indicate at least one third sequence set; the at least one third sequence set includes the at least one second sequence set.

6. The method according to claim 5, characterized in that, The first information includes one or more of the following: the at least one third sequence set, or the identifier of each third sequence set in the at least one third sequence set, or model information used to generate each third sequence set in the at least one third sequence set.

7. The method according to claim 5 or 6, characterized in that, The first information is also used to indicate the applicable conditions for each of the at least one third sequence set.

8. The method according to claim 5, characterized in that, The second sequence set in the at least one second sequence set is the activated third sequence set in the at least one third sequence set; before obtaining the first sequence, the method further includes: Receive second information; wherein the second information is used to indicate the set of sequences to be activated and / or the set of sequences to be deactivated in the at least one third sequence set.

9. The method according to any one of claims 4-8, characterized in that, The method further includes: Send a third message; wherein the third message is used to indicate the first sequence set.

10. The method according to claim 9, characterized in that, The third piece of information is also used to indicate the effective time of the first sequence set.

11. The method according to any one of claims 5-8, characterized in that, Each of the at least one second sequence set corresponds to a time-frequency resource, and different second sequence sets in the at least one second sequence set correspond to different time-frequency resources. Sending the first sequence includes: The first sequence is transmitted on the time-frequency resources corresponding to the first sequence set.

12. The method according to claim 11, characterized in that, The method further includes: Receive fourth information; wherein the fourth information is used to indicate the time-frequency resources corresponding to each of the at least one second sequence set.

13. The method according to claim 2, characterized in that, The method further includes: Send a fifth message; wherein the fifth message is used to instruct the first model.

14. The method according to any one of claims 1-13, characterized in that, The method further includes: Receive sixth information; wherein the sixth information is used to indicate the AI ​​capabilities supported by the second communication device, the AI ​​capabilities including one or more of the following: detecting the input, output, and computing power requirements of the network; The process of obtaining the first sequence includes: The first sequence is obtained based on the AI ​​capability.

15. The method according to claim 3, characterized in that, The method further includes: Receive seventh information; wherein the seventh information is used to indicate one or more of the following: the cyclic prefix of the first sequence, the cyclic prefix addition method of the first sequence, the cyclic shift value of the first sequence, the subcarrier interval corresponding to the first sequence, or the interval between every two adjacent subsequences, the type of the first sequence, and the resource mapping method of the first sequence. Sending the first sequence includes: The first sequence is sent according to the seventh information.

16. A communication method, characterized in that, The method includes: Receive a first sequence; wherein the first sequence is determined by an artificial intelligence (AI) model, and the first sequence is used for random access, or for synchronization, or for sensing communication devices other than the first communication device; Detect the first sequence.

17. The method according to claim 16, characterized in that, The first sequence corresponds to the first model; the first model is used to detect at least the first sequence.

18. The method according to claim 16 or 17, characterized in that, The first sequence includes multiple subsequences, and different subsequences are carried on different air interface resources; and the values ​​of the multiple subsequences are correlated.

19. The method according to any one of claims 16-18, characterized in that, The first sequence is a sequence in a first sequence set, which is determined based on a first condition satisfied by the first communication device and a first correspondence; wherein, the first correspondence includes the correspondence between each of the at least one second sequence set and the applicable condition; the first sequence set is one of the at least one second sequence set.

20. The method according to claim 19, characterized in that, The method further includes: Send a first message; wherein the first message is used to indicate at least one third sequence set; the at least one third sequence set includes the at least one second sequence set.

21. The method according to claim 20, characterized in that, The first information includes one or more of the following: the at least one third sequence set, or the identifier of each third sequence set in the at least one third sequence set, or model information used to generate each third sequence set in the at least one third sequence set.

22. The method according to claim 20 or 21, characterized in that, The first information is also used to indicate the applicable conditions for each of the at least one third sequence set.

23. The method according to claim 20, characterized in that, The second sequence set in the at least one second sequence set is the third sequence set that has been activated in the at least one third sequence set; the method further includes: Send a second message; wherein the second message is used to indicate the set of sequences to be activated and / or the set of sequences to be deactivated in the at least one third sequence set.

24. The method according to any one of claims 19-23, characterized in that, The method further includes: Receive third information; wherein the third information is used to indicate the first sequence set.

25. The method according to claim 24, characterized in that, The third piece of information is also used to indicate the effective time of the first sequence set.

26. The method according to any one of claims 19-23, characterized in that, The method further includes: Send a fourth message; wherein the fourth message is used to indicate the time-frequency resource corresponding to each of the at least one second sequence set, each of the at least one second sequence set corresponds to a time-frequency resource, and the time-frequency resources corresponding to different second sequence sets in the at least one second sequence set are different.

27. The method according to claim 17, characterized in that, The method further includes: Receive fifth information; wherein the fifth information is used to indicate the first model.

28. The method according to any one of claims 16-27, characterized in that, The method further includes: Send a sixth message; wherein the sixth message is used to indicate the AI ​​capabilities supported by the second communication device, the AI ​​capabilities including one or more of the following: detecting the input, output, and computing power requirements of the network.

29. The method according to claim 18, characterized in that, The method further includes: Send a seventh message; wherein the seventh message is used to indicate one or more of the following: the cyclic prefix of the first sequence, the cyclic prefix addition method of the first sequence, the cyclic shift value of the first sequence, the subcarrier interval corresponding to the first sequence, or the interval between every two adjacent subsequences, the type of the first sequence, and the resource mapping method of the first sequence.

30. A communication device, characterized in that, The communication device is used to perform the communication method as described in any one of claims 1-29.

31. A communication device, characterized in that, include: Processor, the processor being coupled to memory; The processor is configured to execute a computer program stored in the memory, so that the communication device performs the communication method as described in any one of claims 1-29.

32. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a computer program or instructions that, when executed on a computer, cause the computer to perform the communication method as described in any one of claims 1-29.

33. A computer program product, characterized in that, The computer program product includes: a computer program or instructions that, when executed on a computer, cause the computer to perform the communication method as described in any one of claims 1-29.

34. A chip system, characterized in that, include: At least one processor and a communication interface, the at least one processor being coupled to a memory via the communication interface, such that when the at least one processor executes a computer program or instructions in the memory, the method of any one of claims 1-29 is performed.

Images