Communication method and device

Abstract

The invention discloses a communication method and device, which can enable sequence sets generated by different devices to have better mutual ambiguity performance. In the method, an RAN node can obtain training conditions, such as an initialization sequence and a loss function, adopted when other RAN nodes generate a sequence set in an optimized manner from other equipment, so that training can be performed based on the training conditions to obtain the sequence set. Since a certain RAN node can acquire the training conditions adopted by other RAN nodes and determine the sequence set according to the same or similar training conditions, it can be ensured that a plurality of RAN nodes use the same or similar training conditions, and since the similar or same sequence set can be generated based on the same or similar training conditions, the accuracy of the sequence set can be improved. According to the technical scheme, different sequences in the same sequence set have relatively low mutual fuzzy side lobes, so that different sequences in the similar or same sequence set also have relatively low mutual fuzzy side lobes, and interference between terminals served by two RAN nodes can be reduced.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the field of communication, and in particular to a communication method and apparatus. BACKGROUND

[0002] In a communication, sensing or positioning scenario, a reference signal is usually generated based on a sequence with good correlation performance. The autocorrelation performance of the sequence can reflect the resolution capability of multipath or multi-target, and the cross-correlation performance between sequences can reflect the interference suppression capability between multiple devices.

[0003] At present, the sequences adopted in the 3rd generation partnership project (3GPP) standard include Zadoff-Chu sequences (ZC sequences) and Gold sequences, which are all obtained based on an analytical construction method. However, the ambiguity performance of these sequences is poor. The ambiguity performance of a sequence can be understood as the correlation performance of the sequence considering Doppler frequency offset. Therefore, in the case of high Doppler frequency offset, the influence of poor ambiguity performance of these sequences is more obvious. SUMMARY

[0004] In the current communication system, the sequences obtained based on the analytical construction method have poor ambiguity performance. In a possible design, in addition to determining the sequence based on the analytical construction method, a sequence set with good ambiguity performance can also be generated based on an artificial intelligence (AI) optimization method. However, if each device optimizes to obtain a sequence set respectively, it is difficult to ensure that the sequence sets obtained by different devices have good mutual ambiguity performance. Therefore, the present application provides a communication method and apparatus, which can enable the sequence sets generated by different devices to have good mutual ambiguity performance.

[0005] In a first aspect, a communication method is provided. The method can be executed by a first communication apparatus, or by a component of the first communication apparatus, such as a processor, a chip, or a chip system of the first communication apparatus, or by a logic module or software capable of realizing all or part of the functions of the first communication apparatus. Illustratively, the first communication apparatus can be a radio access network (RAN) node. Hereinafter, the first communication apparatus is taken as an example, and the method comprises: receiving first information indicating a first training condition, determining a first sequence set according to the first training condition, and transmitting and / or receiving a reference signal according to a first sequence in the first sequence set. The first training condition comprises a first initialization sequence and a first loss function.

[0006] Based on the scheme, the first communication device can obtain a certain training condition from other communication devices (such as the second communication device), so that the first communication device can determine a sequence set according to the training condition, and transmit and / or receive the reference signal according to the sequence in the sequence set. For example, in the case of the second communication device being a core network device, it can be considered that the core network device configures the training condition to the RAN node, so that the core network can configure the same or similar training condition for the adjacent RAN node; in the case of the second communication device being a RAN node, it can be considered that the training conditions are exchanged between multiple RAN nodes, so that the multiple RAN nodes can use the same or similar training condition. Wherein, the same training condition can mean that the initialization sequence and the loss function are the same, and the similar training condition can mean that the initialization sequence is the same and the loss function is similar. Since the same or similar training conditions can generate similar or identical sequence sets, and different sequences in the same sequence set have low mutual ambiguity sidelobes, different sequences in the similar or identical sequence sets also have low mutual ambiguity sidelobes, thereby realizing that multiple sequence sets generated by different devices have good mutual ambiguity performance, and the interference between devices using the multiple sequence sets can be reduced.

[0007] In a possible design, the method further includes: receiving second information, where the second information indicates a parameter of the first loss function.

[0008] In a possible design, the method further includes: receiving third information, where the third information indicates an expected value of the first loss function, and / or indicates an expected value of at least one index of the first loss function.

[0009] In a possible design, the first training condition further includes a first optimizer. The method further includes: receiving fourth information, where the fourth information indicates a parameter of the first optimizer.

[0010] In a possible design, the method further includes: sending fifth information, where the fifth information indicates a second training condition, and the second training condition is a recommended training condition for the first communication device.

[0011] In a possible design, the fifth information further indicates a training parameter associated with the second training condition; the training parameter associated with the second training condition includes a parameter of a second loss function and / or a parameter of a second optimizer, the second loss function being a loss function included in the second training condition, and the second optimizer being an optimizer included in the second training condition.

[0012] In a possible design, the method further includes: receiving sixth information, where the sixth information indicates a recommended training condition and / or a training parameter for a terminal; and determining, according to the sixth information, the second training condition and / or the training parameter associated with the second training condition.

[0013] In a possible design, the method further includes: sending seventh information, where the seventh information indicates the first training condition. Further, the seventh information also indicates a training parameter associated with the first training condition.

[0014] In a second aspect, a communication method is provided. The method can be performed by a second communication device, or by a component of the second communication device, e.g., a processor, a chip, or a chip system, etc. of the second communication device, or by a logic module or software that can implement all or part of the function of the second communication device. Exemplarily, the second communication device can be a core network device or a RAN node. The method includes: determining a first training condition, where the first training condition includes a first initialization sequence and a first loss function; and sending first information, where the first information indicates the first training condition.

[0015] Based on the scheme, the second communication device can indicate a training condition to the first communication device, so that the first communication device can determine a sequence set according to the training condition, and thus send and / or receive a reference signal according to a sequence in the sequence set. In the case where the second communication device is a core network device, it can be considered that the core network device configures a training condition to a RAN node, and thus the same or similar training condition can be configured to adjacent RAN nodes. In the case where the second communication device is a RAN node, it can be considered that multiple RAN nodes interact with each other to determine a training condition, and thus the multiple RAN nodes can use the same or similar training condition. Since the same or similar training condition can generate a similar or same sequence set, and different sequences in the same sequence set have a low mutual ambiguity sidelobe, different sequences in the similar or same sequence set also have a low mutual ambiguity sidelobe, and thus the interference between terminals served by multiple RAN nodes can be reduced.

[0016] In a possible design, the method further includes: sending second information, where the second information indicates a parameter of the first loss function.

[0017] In a possible design, the method further includes: sending third information, where the third information indicates an expected value of the first loss function, and / or indicates an expected value of at least one index of the first loss function.

[0018] In a possible design, the first training condition further includes a first optimizer; and the method further includes: sending fourth information, where the fourth information indicates a parameter of the first optimizer.

[0019] In a possible design, determining the first training condition includes: receiving fifth information, where the fifth information indicates a second training condition, and the second training condition is a recommended training condition for the first communication device; and determining the first training condition according to the fifth information.

[0020] In one possible design, the fifth message also indicates the training parameters associated with the second training condition. The method further includes: determining the training parameters associated with the first training condition based on the training parameters associated with the second training condition; and sending an eighth message indicating the training parameters associated with the first training condition.

[0021] In one possible design, determining the first training condition includes receiving a ninth message, which indicates the first training condition.

[0022] Thirdly, a communication method is provided. This method can be executed by a terminal, or by a component of the terminal, such as the terminal's processor, chip, or chip system, or by a logic module or software capable of implementing all or part of the terminal's functions. The following description uses a terminal as an example. The method includes: receiving seventh information indicating first training conditions; determining a first sequence set according to the first training conditions; and receiving and / or transmitting a reference signal according to the first sequence in the first sequence set. The first training conditions include a first initialization sequence and a first loss function.

[0023] Based on this scheme, the RAN node can instruct the terminal on training conditions, enabling the terminal to generate a sequence set based on these conditions. This allows both the RAN node and the terminal to generate similar or identical sequence sets based on the same or similar training conditions, thus facilitating subsequent sensing or communication. On one hand, since it's unnecessary to send the sequence set generated by the RAN node to the terminal, signaling overhead is reduced. On the other hand, because the RAN node and the terminal can generate similar or identical sequence sets based on the same or similar training conditions, they can use similar or identical sequences for sensing or communication, thereby reducing signaling overhead while minimizing the impact on sensing or communication performance.

[0024] In one possible design, the seventh piece of information also indicates the training parameters associated with the first training condition. The training parameters associated with the first training condition include the parameters of the first loss function and / or the parameters of the first optimizer.

[0025] In one possible design, the method further includes sending a sixth message indicating the training conditions and / or training parameters recommended by the terminal.

[0026] In one possible design, combining the first, second, or third aspects, the first training condition is one of at least one predefined training condition.

[0027] Based on this possible design, at least one training condition is predefined, so that when subsequent devices interact with the training condition, they can indicate the training condition through the index of the training condition, thereby reducing signaling overhead.

[0028] In one possible design, combining the first, second, or third aspects, the first initialization sequence is one of the following: a ZC sequence, a sequence obtained by expanding the ZC sequence, a Gold sequence, or an M sequence.

[0029] Based on this possible design, the initial sequence can be set to a non-random, reproducible ZC sequence, Gold sequence, etc., thereby improving the reproducibility of the sequence set.

[0030] In one possible design, combining the first, second, or third aspect, the first initialization sequence is a Gold sequence, and the first information also indicates the initialization parameters of the Gold sequence; or, the first initialization sequence is an M sequence, and the first information also indicates the initialization parameters of the M sequence.

[0031] In combination with the first, second, or third aspect, in one possible design, the first loss function is associated with at least one of the following metrics: self-fuzzy peak sidelobe level (APSL), mutual-fuzzy peak sidelobe level (CPSL), self-fuzzy integrated sidelobe level (AISL), mutual-fuzzy integrated sidelobe level (CISL), or peak-to-average power ratio (PAPR).

[0032] Based on this possible design, using APSL, CPSL, AISL, CISL, or PAPR, which are related to fuzziness performance, to determine the loss function can enable different sequences in the final optimized sequence set to have good mutual fuzziness performance, thereby enabling similar sequence sets obtained based on the same or similar training conditions to also have good mutual fuzziness performance.

[0033] In one possible design, combining the first, second, or third aspects, the parameters of the first loss function include at least one of the following corresponding to at least one metric: weight, constraint value, Doppler frequency offset range, time delay range, or sequence transmission duration.

[0034] In one possible design, in conjunction with the first, second, or third aspect, the first information also indicates the parameters of the first loss function.

[0035] In one possible design, combining the first, second, or third aspects, the first training condition also includes a first optimizer.

[0036] In one possible design, combining the first, second, or third aspects, the parameters of the first optimizer include at least one of the following: learning rate, learning rate decay value, or momentum parameter.

[0037] In one possible design, in conjunction with the first, second, or third aspect, the first information also indicates the parameters of the first optimizer.

[0038] Fourthly, a communication method is provided. This method can be executed by a RAN node, or by a component of the RAN node, such as a processor, chip, or chip system of the RAN node, or by a logic module or software capable of implementing all or part of the functions of the RAN node. The following description uses a RAN node as an example. The method includes: receiving first information, the first information indicating training conditions and / or training parameters recommended by a terminal, the recommended training conditions including an initialization sequence and / or a loss function, and the recommended training parameters including parameters of the loss function; determining, based on the first information, first training conditions and / or training parameters associated with the first training conditions, the first training conditions including a first initialization sequence and a first loss function; and sending second information. Wherein, the second information indicates the first training conditions and / or training parameters associated with the first training conditions, or, the second information indicates a set of sequences obtained according to the first training conditions; or, the second information indicates a first sequence, the first sequence being a sequence from the set of sequences obtained according to the first training conditions.

[0039] Based on this scheme, the terminal can report its recommended or desired training conditions to the RAN node, enabling the RAN node to reasonably select training conditions to generate sequence sets, thereby improving the adaptability of the sequence sets and ultimately enhancing the performance of subsequent communication or sensing based on the sequences in the sequence sets. Furthermore, when the RAN node instructs the terminal on training conditions, the terminal can generate sequence sets based on those conditions. This allows the RAN node and the terminal to generate similar or identical sequence sets based on the same or similar training conditions (e.g., the first sequence set and the second sequence set are the same or similar), enabling subsequent sensing or communication based on these sequence sets. On one hand, since it is not necessary to send the first sequence set generated by the RAN node to the terminal, signaling overhead can be reduced. On the other hand, since the RAN node and the terminal can generate similar or identical sequence sets based on the same or similar training conditions, they can use similar or identical sequences for sensing or communication, thus reducing signaling overhead while having a minimal impact on sensing or communication performance.

[0040] Fifthly, a communication method is provided. This method can be executed by a terminal, or by a component of the terminal, such as a processor, chip, or chip system, or by a logic module or software capable of implementing all or part of the terminal's functions. The following description uses a terminal as an example. The method includes: sending first information, the first information indicating recommended training conditions and / or training parameters, the recommended training conditions including an initialization sequence and / or a loss function, and the recommended training parameters including parameters of the loss function; and receiving second information. The second information indicates the first training conditions and / or training parameters associated with the first training conditions, or the second information indicates a set of sequences obtained according to the first training conditions; or the second information indicates a first sequence, the first sequence being a sequence from the set of sequences obtained according to the first training conditions; the first training conditions include a first initialization sequence and a first loss function. The technical effects of this fifth aspect are similar to those of the first aspect described above, and will not be repeated here.

[0041] In conjunction with the fourth or fifth aspect, in one possible design, the training conditions recommended by the terminal are the same as or different from the first training conditions; or, the training parameters recommended by the terminal are the same as or different from the training parameters associated with the first training conditions.

[0042] Sixthly, a communication method is provided, comprising: a second communication device determining first training conditions and sending first information indicating the first training conditions to a first communication device. The first communication device receives the first information and, based on the first training conditions, determines a first sequence set, thereby sending and / or receiving reference signals based on the first sequence in the first sequence set. The first training conditions include a first initialization sequence and a first loss function. Exemplarily, the second communication device is a core network device or a RAN node, and the first communication device is a RAN node. The technical effects of this sixth aspect are analogous to those of the first aspect described above, and will not be repeated here.

[0043] In one possible design, the second communication device determines the first training condition by: the second communication device receiving fifth information from at least one first communication device, the fifth information from one of the first communication devices indicating training conditions recommended by that first communication device; and the second communication device determining the first training condition based on the fifth information from at least one first communication device.

[0044] In one possible design, the second communication device determines the first training condition by receiving ninth information from the fourth communication device, the ninth information indicating the first training condition. For example, the fourth communication device and the first communication device are different RAN nodes.

[0045] In a seventh aspect, a communication device is provided for implementing various methods. The communication device includes modules, units, or means corresponding to the implementation of the methods, wherein the 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 corresponding to the functions.

[0046] In some possible designs, the communication device may include a processing module and a transceiver module. The processing module can be used to implement the processing functions in any of the above aspects and any possible implementations thereof. The transceiver module may include a receiving module and a transmitting module, respectively used to implement the receiving function and the transmitting function in any of the above aspects and any possible implementations thereof.

[0047] In some possible designs, the transceiver module can consist of transceiver circuits, transceivers, transceivers, or communication interfaces.

[0048] Eighthly, a communication device is provided, comprising: a processor and a memory; the memory being used to store computer instructions that, when executed by the processor, cause the communication device to perform the method described in any of the preceding aspects and any possible design thereof.

[0049] A ninth aspect provides a communication device, comprising: a processor and a communication interface; the communication interface being used to communicate with a module outside the communication device; the processor being used to execute computer programs or instructions to cause the communication device to perform the methods described in any of the above aspects and any possible designs thereof.

[0050] A tenth aspect provides a communication device comprising: at least one processor; said processor being configured to execute a computer program or instructions stored in a memory to cause the communication device to perform the methods described in any of the foregoing aspects and any possible designs thereof. The memory may be coupled to the processor, or may be independent of the processor.

[0051] In an eleventh aspect, a communication device (e.g., the communication device may be a chip or a chip system) is provided, the communication device including a processor for implementing the functions involved in any of the above aspects and any possible designs thereof.

[0052] In some possible designs, the communication device includes a memory for storing necessary program instructions and data.

[0053] In some possible designs, when the device is a chip system, it can be composed of chips or contain chips and other discrete components.

[0054] The communication device described in aspects seven through eleven may be a first communication device in the first or sixth aspects, or a device included in the first communication device, such as a chip or chip system; or the communication device may be a second communication device in the second or sixth aspects, or a device included in the second communication device, such as a chip or chip system; or the communication device may be a terminal in the third or fifth aspects, or a device included in the terminal, such as a chip or chip system; or the communication device may be a RAN node in the fourth aspect, or a device included in the RAN node, such as a chip or chip system.

[0055] In a twelfth aspect, a communication device is provided, which may be a first communication device, or a module or unit (e.g., a chip, a chip system, or a circuit) in the first communication device that corresponds to the execution of the methods / operations / steps / actions described in the first aspect, or a module or unit that can be used in conjunction with the first communication device.

[0056] Alternatively, the communication device may be a second communication device, or a module or unit (e.g., a chip, a chip system, or a circuit) in the second communication device that corresponds one-to-one with the methods / operations / steps / actions described in the second aspect, or a module or unit that can be used in conjunction with the second communication device.

[0057] Alternatively, the communication device may be a RAN node, or a module or unit (e.g., a chip, or a chip system, or a circuit) in the RAN node that corresponds one-to-one with the methods / operations / steps / actions described in the fourth aspect, or a module or unit that can be matched with the RAN node.

[0058] Alternatively, the communication device may be a terminal, or a module or unit (e.g., a chip, chip system, or circuit) in the terminal that corresponds one-to-one with the methods / operations / steps / actions described in the third or fifth aspect, or a module or unit that can be matched with the terminal.

[0059] It is understandable that when the communication device provided in any of the seventh to twelfth aspects is a chip, the transmitting action / function of the communication device can be understood as outputting information, and the receiving action / function of the communication device can be understood as inputting information.

[0060] In a thirteenth aspect, a computer-readable storage medium is provided that stores a computer program or instructions that, when executed on a communication device, enable the communication device to perform the methods described in any of the preceding aspects and any possible designs thereof.

[0061] In a fourteenth aspect, a computer program product containing instructions is provided that, when run on a communication device, enables the communication device to perform the methods described in any of the foregoing aspects and any possible design thereof.

[0062] In a fifteenth aspect, a communication system is provided, comprising a first communication device and a second communication device. Further, a terminal may also be included. The first communication device can be used to implement the method described in the first aspect and any possible design thereof, the second communication device can be used to implement the method described in the second aspect and any possible design thereof, and the terminal can be used to implement the method described in the third aspect and any possible design thereof.

[0063] The technical effects of any of the design methods in aspects seven through fifteen can be found in the technical effects of different design methods in aspects one through six, and will not be repeated here. Attached Figure Description

[0064] Figure 1 A schematic diagram of a scene perception provided for this application;

[0065] Figure 2 A schematic diagram of another sensing scenario provided for this application;

[0066] Figure 3 A schematic diagram of the structure of a communication system provided in this application;

[0067] Figure 4 This application provides a schematic diagram of the structure of an O-RAN system;

[0068] Figure 5 A flowchart illustrating a communication method provided in this application;

[0069] Figure 6 This application provides a phase comparison map of sequence m in two sequence sets generated under different training conditions;

[0070] Figure 7 This application provides a phase comparison map of sequence m in two sequence sets generated under the same training conditions;

[0071] Figure 8 A flowchart illustrating another communication method provided in this application;

[0072] Figure 9 A schematic diagram illustrating the correlation results of a sequence provided in this application;

[0073] Figures 10-12 A schematic diagram of the communication device provided in this application. Detailed Implementation

[0074] In the description of this application, unless otherwise stated, " / " indicates that the objects before and after are in an "or" relationship. For example, A / B can mean A or B. "And / or" in this application is merely a description of the relationship between the related objects, indicating that there can be three relationships. For example, A and / or B can mean: A exists alone, A and B exist simultaneously, and B exists alone. A and B can be singular or plural.

[0075] In the description of this application, unless otherwise stated, "multiple" means two or more. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can mean: a, b, c, a and b, a and c, b and c, a and b and c, where a, b, and c can be single or multiple.

[0076] Furthermore, to facilitate a clear description of the technical solutions in the embodiments of this application, the terms "first" and "second" are used in the embodiments of this application to distinguish identical or similar items with substantially the same function and effect. Those skilled in the art will understand that the terms "first" and "second" do not limit the quantity or execution order, and the terms "first" and "second" are not necessarily different.

[0077] In the embodiments of this application, the terms "exemplary" or "for example" are used to indicate that something is an example, illustration, or description. Any embodiment or design that is described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or design. Specifically, the use of terms such as "exemplary" or "for example" is intended to present the relevant concepts in a specific manner to facilitate understanding.

[0078] It is understood that the term "embodiment" used throughout the specification means that a specific feature, structure, or characteristic related to an embodiment is included in at least one embodiment of this application. Therefore, various embodiments throughout the specification do not necessarily refer to the same embodiment. Furthermore, these specific features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. It is understood that in the various embodiments of this application, the sequence number of each process does not imply the order of execution; the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0079] It is understood that in this application, "...when" and "if" both refer to the corresponding processing that will be carried out under certain objective circumstances, and are not limited to a specific time, nor do they require a judgment action to be performed during implementation, nor do they imply any other limitations.

[0080] It is understood that some optional features in the embodiments of this application can be implemented independently in certain scenarios without relying on other features, such as the current solution on which they are based, to solve the corresponding technical problems and achieve the corresponding effects. Alternatively, they can be combined with other features as needed in certain scenarios. Correspondingly, the apparatus given in the embodiments of this application can also implement these features or functions, which will not be elaborated here.

[0081] In this application, unless otherwise specified, the same or similar parts between the various embodiments can be referred to each other. In the various embodiments of this application, unless otherwise specified or there is a logical conflict, the terminology and / or descriptions between different embodiments are consistent and can be mutually referenced. Technical features in different embodiments can be combined to form new embodiments based on their inherent logical relationships. The following descriptions of the embodiments of this application do not constitute a limitation on the scope of protection of this application. Before introducing the embodiments, some terms involved in this application are explained.

[0082] To facilitate understanding of the technical solutions of the embodiments of this application, a brief introduction to the relevant technologies of this application is given below.

[0083] 1. Wireless sensing, sensing signals:

[0084] The technical principles of wireless sensing differ somewhat from those of wireless communication. For example, in wireless communication, the transmitting end modulates information onto radio waves and sends it to the receiving end, which then demodulates the signal carried on the radio waves to obtain the information. In a sensing scenario, the transmitting device radiates electromagnetic waves into the surrounding environment to send sensing signals. The receiving device receives the sensing signals reflected from the surrounding environment and analyzes and compares them with the transmitted sensing signals to perceive relevant information about the surrounding environment, such as the presence of the target, the number of targets, and the location of each target. For instance, the reflected sensing signals can also be called echo signals or echoes of sensing signals; these terms are interchangeable and not limited to one another.

[0085] A sensing signal can be understood as a signal used to sense (or detect) a target. The target can also be understood as a target object, such as a scatterer or reflector. The sensing signal can be a detection signal, a linear frequency modulated signal, a radar signal, a radar sensing signal, a radar detection signal, an environmental sensing signal, a pulse signal, or a signal in a wireless communication system. The sensing signal can be a reference signal; for example, its initial amplitude and phase information can be pre-configured to the receiver through a configuration sequence. The sensing signal can also be a data signal; the receiver can calculate the initial amplitude and phase of each data signal using known modulation methods such as data verification. The sensing signal can also have other names, which are not specifically limited in this application.

[0086] Generally, sensing can be categorized into single-site sensing and dual-site sensing. In single-site sensing mode, the transmitting and receiving ends of the sensing signal are the same device. In terms of the sensing process, this station must both transmit and receive the reflected signals from the target surface; therefore, single-site sensing mode can also be called a self-transmitting and self-receiving mode.

[0087] In dual-station sensing mode, the transmitting and receiving ends of the sensing signals are two different devices. From the sensing process perspective, station A transmits the sensing signal, and the reflected signal from the target surface is received by station B. Therefore, dual-station sensing mode can also be called self-transmitting and other-receiving or A-transmitting and B-receiving mode.

[0088] 2. Integrated communication and sensing:

[0089] In the evolution of fifth-generation (5G) wireless communication technology towards 5G-Advanced (5G-A) and future communication technologies, integrated communication and sensing technology is considered one of the key technologies for expanding the service capabilities of mobile communication networks. The core idea of ​​this technology is to add sensing capabilities to the mobile communication network, building capabilities such as target detection, imaging, and identification, thereby integrating communication and sensing capabilities into a single network to achieve harmonious coexistence and even mutual benefit.

[0090] For example, in integrated communication and sensing technology, the sensing mode can include... Figure 1 The six sensing scenarios are shown. Among them, sensing scenarios (1) and (4) are single-site sensing modes. In sensing scenario (1), the base station transmits and receives data automatically, and in sensing scenario (4), the terminal transmits and receives data automatically. Sensing scenarios (2), (3), (5), and (6) are dual-site sensing modes. In sensing scenario (2), base station A transmits data and base station B receives data. In sensing scenario (3), the base station transmits data and the terminal receives data. In sensing scenario (5), the terminal transmits data and the base station receives data. In sensing scenario (6), terminal A transmits data and terminal B receives data. Among them, sensing scenarios (3)-(6) can also be called UE-assisted sensing scenarios.

[0091] Furthermore, in an integrated communication and sensing system, the base station has the ability to communicate with terminals and also possesses sensing capabilities. For example, such as... Figure 2 As shown in (a), the base station can communicate with the terminal and can perform self-transmitting and self-receiving sensing, such as sending sensing signals and receiving echo signals; or, as... Figure 2 As shown in (b), base station A can communicate with the terminal and can perform self-transmitting and receiving sensing, such as sending sensing signals and having base station B receive the echo signals.

[0092] Currently, in scenarios such as communication, sensing, or positioning, reference signals are typically generated based on sequences with good correlation properties. The correlation properties of a sequence can include its autocorrelation performance and the cross-correlation performance between sequences.

[0093] For example, in a communication scenario, the reference signal may include, but is not limited to: a demodulation reference signal (DMRS), a sounding reference signal (SRS), and a preamble carried in a physical random access channel (PRACH). In a sensing scenario, the reference signal may be a sensing signal. In a positioning scenario, the reference signal may include, but is not limited to: a positioning reference signal (PRS) or a sidelink PRS (SL-PRS).

[0094] The autocorrelation performance of a sequence can reflect the multipath or multitarget resolution capability, while the cross-correlation performance between sequences can reflect the interference suppression capability or interference level between multiple devices.

[0095] For example, a sequence consisting of L elements can be represented in the time domain as [x0, x1, x2, ..., x...]. L-1 For example, the (periodic) autocorrelation function of this sequence can be expressed as:

[0096]

[0097] Where τ = 0, 1, ..., L-1, τ represents the time-domain offset, also known as the cyclic shift. * represents the conjugate operation, and % represents the modulo operation. x l The table shows the elements in the sequence. From the above formula, we can see that each correlation value R[τ] in the autocorrelation function of the sequence is obtained by performing a correlation operation on the sequence after cyclically shifting it by τ. A single correlation operation can be understood as: multiplying corresponding elements by their conjugates and then adding them together.

[0098] For example, a sequence can be represented in the time domain as x = [x0, x1, x2, ..., x...]. L-1 The other sequence is represented in the time domain as y = [y0, y1, y2, ..., y]. L-1 Taking [a specific example] as an example, the (periodic) cross-correlation function of sequence x and sequence y can be expressed as:

[0099]

[0100] The meaning of each parameter can be found in the explanation of the corresponding parameter in the autocorrelation function above, and will not be repeated here.

[0101] Generally, good autocorrelation performance of a sequence can be understood as follows: when τ≠0, the amplitude of R[τ] is as low as possible compared to R[0] (i.e., the autocorrelation function value at τ=0). Good cross-correlation performance between sequences can be understood as follows: for τ=0,1,…,L-1, R… x,y The amplitude of [τ] should be kept as low as possible.

[0102] Specifically, in mobile scenarios, such as when the transmitting or receiving end is in motion, or when the target to be sensed is in motion, there is a Doppler frequency offset between the reference signal received by the receiver and the reference signal transmitted by the transmitter. This Doppler frequency offset causes a phase rotation in the received reference signal, meaning the original transmitted sequence is multiplied by the phase rotation caused by the Doppler frequency offset. In this scenario, the self-ambiguity or cross-ambiguity performance of the sequence usually needs to be considered. Ambiguity is a performance indicator extended from correlation. The autocorrelation or cross-correlation of a sequence is obtained by performing a correlation operation after cyclically shifting one sequence with another; the self-ambiguity or cross-ambiguity of a sequence further considers multiplying one sequence by the phase rotation caused by Doppler and then performing a correlation operation with the cyclic shift of another sequence. Therefore, self-ambiguity or cross-ambiguity when Doppler is 0 can be understood as autocorrelation / cross-correlation.

[0103] For example, the self-fuzzy function of a sequence can be expressed as:

[0104]

[0105] The mutual ambiguity function between sequences can be expressed as:

[0106]

[0107] Where u represents the Doppler frequency and T represents the transmission duration of the sequence.

[0108] Understandably, the autocorrelation function can be understood as a self-ambiguity function when the Doppler frequency is 0, and the cross-correlation function can be understood as a cross-ambiguity function when the Doppler frequency is 0. In the following embodiments of this application, self-ambiguity functions and cross-ambiguity functions are used as examples for illustration.

[0109] As one possible implementation, the reference signal uses a sequence obtained analytically. For example, the sequence can be a traditional Zadoff-Chu sequence (ZC sequence), a sequence obtained by extending a ZC sequence, a Gold sequence, an M sequence, etc. For instance, DMRS, PRS, or SL-PRS are generated based on Gold sequences, and the preamble in SRS or PRACH is generated based on ZC sequences.

[0110] For example, the ZC sequence can be expressed as:

[0111]

[0112] Where l = 0, 1, ..., L zc -1,L zc Let represent the length of the ZC sequence, and q represent the root of the ZC sequence, with different roots corresponding to different sequences. Furthermore, the existing protocol TR 38.211 groups the ZC sequences, and q can be determined jointly based on the group index μ and the intra-group index v, for example... L zc The ZC sequence is usually a prime number. To generate a sequence of non-prime length, the ZC sequence can be extended. For example, to generate an M sequence... zc Long sequences can be generated in the following way:

[0113] r u,v [n] = x q [nmodL zc ]

[0114] Where mod represents the modulo operation, n = 0, 1, ..., N zc -1,L zc For less than N zc The largest prime number.

[0115] For example, the sequence obtained after expanding the ZC sequence can be: a sequence obtained by cyclic expansion, zero-padding expansion, or repeating the last few elements of the sequence. In addition, other expansions can be performed on the ZC sequence to obtain the expanded sequence, and this application does not specifically limit the expansion method.

[0116] For example, both the Gold sequence and the M sequence are pseudo-random sequences. The M sequence is also known as the longest linear shift register sequence. The Gold sequence is generated by combining two preferred pairs of M sequences of equal order. Taking the 31-order Gold sequence specified in the existing protocol TR 38.211 as an example, its expression can be:

[0117] c[n]=(x1[n+N c ]+x2[n+N c mod2

[0118] The first M-sequence, x1(n+31) = (x1[n+3] + x1[n]) mod 2, is initialized with x1[1] = 1 and x1[n] = 0 (n = 1, 2, ..., 30). The second M-sequence, x2(n+31) = (x2[n+3] + x2[n+2] + x2[n+1] + x2[n]) mod 2, has initialization parameters that can be expressed as follows: Its specific value can be configured during use. N c For example, N is a constant. c =1600.

[0119] However, the sequences obtained by the above analytical construction method have poor ambiguity performance, with high auto-ambiguity peak sidelobe level (APSL) and cross-ambiguity peak sidelobe level (CPSL) of the self-ambiguity function, especially when considering high Doppler frequency offset.

[0120] As another possible implementation, sequences can be obtained through optimization, such as artificial intelligence (AI) optimization, to generate a set of sequences with good self-fuzziness and mutual fuzziness performance. For example, model parameters / training variables can be defined as individual sequence elements of the sequence set, with the loss function / objective function being minimizing the APSL of each sequence and the CPSL between any two sequences. The values ​​of the sequence elements are then updated until the loss value tends to stabilize or falls below a certain threshold.

[0121] For example, in the embodiments of this application, the sequence obtained by the optimization method can also be understood as the sequence obtained by the computer search method, the sequence obtained by the AI ​​method, or as an optimized sequence, computer search sequence, AI sequence, etc. This application does not specifically limit its name.

[0122] However, sequences obtained through AI optimization cannot be represented analytically like ZC or Gold sequences. Defining these sequences directly in the protocol would require a significant amount of documentation. In particular, longer sequences contain a larger number of elements, making it easy for multiple solutions with similar performance to emerge during optimization. For example, there might be several completely different sequences with similar fuzzy performance. In such cases, deciding which of these similar solutions to include in the protocol can easily lead to disputes.

[0123] However, if each device is allowed to optimize and obtain its own sequence set, it is difficult to guarantee good mutual ambiguity performance between the sequence sets obtained by different devices. For example, if adjacent base stations 1 and 2 obtain sequence set 1 and sequence set 2 respectively through their own optimization methods, it is easy for the sequences in sequence set 1 and the sequences in sequence set 2 to have high CPSL, resulting in severe interference between the terminals served by the two base stations.

[0124] Based on this, this application provides a communication method in which a base station can obtain training conditions, such as initialization sequences and loss functions, used by other base stations or core network equipment when generating sequence sets through optimization. This allows the base station to train based on these training conditions to obtain the sequence set. Since a base station can obtain the training conditions used by other base stations and determine the sequence set accordingly, it can ensure that multiple base stations use the same or similar training conditions. Furthermore, since similar or identical sequence sets can be generated based on the same or similar training conditions, and different sequences within the same sequence set have low mutual ambiguity sidelobes, different sequences within similar or identical sequence sets also have low mutual ambiguity sidelobes, thereby reducing interference between terminals served by two base stations. The specific implementation of this method will be described in detail in subsequent embodiments and will not be repeated here.

[0125] The technical solutions of this application embodiment can be used in various communication systems, including third-generation partnership project (3GPP) communication systems, such as fourth-generation (4G) systems like Long Term Evolution (LTE), fifth-generation (5G) systems like New Radio (NR), LTE and 5G hybrid networking systems, sensing systems, integrated communication and sensing systems, non-terrestrial networks (NTN), device-to-device (D2D) communication systems, vehicle-to-everything (V2X) communication systems, machine-type communication (MTC) systems, Internet of Things (IoT) systems, or other future communication systems. The communication system can also be a non-3GPP communication system; there is no limitation on this.

[0126] The communication systems described above are merely illustrative examples, and are not limited to those described herein. The communication systems provided in this application do not impose any limitations on the solutions described herein. This will be explained uniformly here and will not be repeated below.

[0127] Figure 3 A possible, non-limiting system schematic diagram is shown. For example... Figure 3 As shown, the communication system 30 includes a radio access network (RAN) 300. Optionally, it may also include a core network (CN) 400 and / or the Internet. Figure 3 (Not shown in the image). RAN 300 includes at least one RAN node (e.g., ...). Figure 3 310a and 310b (collectively referred to as 310) and at least one terminal (such as Figure 3 The 320a-320j series, collectively referred to as 320, are core network devices. The core network 400 includes at least one core network device.

[0128] Optionally, RAN 300 may also include other RAN nodes, such as wireless relay equipment and / or wireless backhaul equipment. Figure 3 (Not shown in the image). Terminal 320 connects to RAN node 310 wirelessly (e.g., via air interface communication). RAN node 310 connects to core network 400 wirelessly or via wired connection. The core network equipment in core network 400 and RAN node 310 in RAN 300 can be different physical devices, or they can be the same physical device integrating core network logical functions and radio access network logical functions.

[0129] In one possible implementation, RAN 300 can be a 3GPP-related cellular system, such as a 4G or 5G mobile communication system, an NTN system (e.g., an NTN supporting pass-through mode and / or regenerative mode, or an NTN supporting eye-fixed cell mode and / or eye-moving cell mode), or a future-oriented evolution system. RAN 300 can also be an open RAN (O-RAN or ORAN), a cloud radioaccess network (CRAN), or a wireless fidelity (WiFi) system. RAN 300 can also be a communication system integrating two or more of the above systems.

[0130] In some scenarios, the roles of RAN node 310 and terminal 320 are relative, for example, Figure 3The network element 320i can be a helicopter or a drone, and it can be configured as a mobile base station. For the terminal 320j accessing the RAN 300 via the network element 320i, the network element 320i is a base station; however, for the base station 310a, the network element 320i is a terminal. RAN node 310 and terminal 320 are sometimes referred to as communication devices, for example... Figure 3 Network elements 310a and 310b can be understood as communication devices with base station functions, while network elements 320a-320j can be understood as communication devices with terminal functions.

[0131] In one possible implementation, RAN node 310 is a network-side device with wireless transceiver capabilities. RAN nodes, sometimes also referred to as RAN entities or access nodes, constitute part of the communication system and are used to assist terminals in achieving wireless access. Multiple RAN nodes 310 in the communication system 30 can be of the same type or different types.

[0132] As one possible implementation, RAN node 310 can be an access network device, such as a base station, an evolved NodeB (eNodeB), an access point (AP), a transmission reception point (TRP), a next-generation NodeB (gNB) in a 5G mobile communication system, a base station evolved by 3GPP, a base station in a future mobile communication system, an access node in a WiFi system, a wireless relay node, a wireless backhaul node, etc.

[0133] For example, a RAN node can be a macro base station (such as...) Figure 3 310a), micro base stations or indoor stations (such as Figure 4 RAN nodes can be 310b, relay nodes or donor nodes, or wireless controllers in CRAN scenarios. Optionally, RAN nodes can also be servers, wearable devices, vehicles or in-vehicle equipment, etc. For example, in V2X technology, the RAN node can be a roadside unit (RSU).

[0134] As another possible implementation, multiple RAN nodes collaborate to assist terminal devices in achieving wireless access, with different RAN nodes each implementing some of the functions of the access network equipment. For example, RAN nodes can be central units (CU), distributed units (DU), CU-control plane (CP), CU-user plane (UP), radio units (RU), or sensing units (SU), etc.

[0135] For example, the CU and DU can be configured separately or included in the same network element, such as in the baseband unit (BBU). The RU can be included in radio frequency equipment or radio frequency units, such as in a remote radio unit (RRU), an active antenna unit (AAU), or a remote radio head (RRH).

[0136] Optionally, the CU can be connected to the core network and one or more DUs. The CU may have some of the core network's functions. Furthermore, access network equipment may include one or more CUs, one or more DUs, and one or more RUs.

[0137] For example, the CU can be used to perform layer 2 (L2) and layer 3 (L3) functions. Furthermore, the CU can also have some of the core network functions. The DU can be used to perform layer 1 (L1) and some L2 functions, and the RU can be used to perform L1 computing and radio frequency (RF) digital functions.

[0138] like Figure 3 As shown, a CU can connect to the core network and one or more DUs. A backhaul interface exists between the CU and the core network to carry traffic between them. A midhaul interface exists between the CU and the DU to carry traffic between them. A DU can connect to one or more RUs. A fronthaul interface exists between the DU and the RU to carry traffic between them.

[0139] In terms of hardware, CU and DU can include a chassis platform, motherboard, peripheral devices, and cooling equipment. The motherboard contains processing units, memory, internal input / output (I / O) interfaces, and external connection ports. Its hardware accelerator is designed with interfaces, and hardware functional components include: storage for software, hardware, and system debugging interfaces, and a single-board management controller.

[0140] DUs are typically implemented using multi-core processors and one or more hardware accelerators. Parts of the DU protocol stack can be implemented in software running on a multi-core processor, while computationally intensive L1 and L2 functions can be offloaded to a field-programmable gate array (FPGA) / graphics processing unit (GPU)-based hardware accelerator; or all L1 functions can be offloaded to an FPGA / GPU-based hardware accelerator, while other protocol stack components are implemented in software running on the processor; or the entire protocol stack can be implemented in software running on the processor. Hardware accelerators support interconnection with x86 or non-x86 processors. Similarly, accelerators have a multi-channel peripheral component interconnect express (PCIe) interface pointing to the central processing unit (CPU) and external connections via GbE.

[0141] An RU may include an O-RAN processing unit (OPU), a digital processing unit (DPU), and an RF processing unit.

[0142] The OPU is used to receive Enhanced Common Public Radio Interface (eCPRI) frames from the O-RAN fronthaul and perform fronthaul interface, L1 layer (coding, scrambling, modulation, layer mapping, precoding), synchronization, beamforming, and resource unit mapping. The OPU can be implemented as a CPU, FPGA, or application-specific integrated circuit (ASIC).

[0143] The DPU is used to perform synchronization, uplink (UL) digital downconversion (DDC), downlink (DL) digital upconversion (DUC), channel failure ratio (CFR), and digital pre-distortion (DPD) processing. It improves power amplifier efficiency by reducing the peak-to-average power ratio (PAPR) / adjacent channel leakage ratio (ACLR) of the RF front-end. The DPU can be implemented as an FPGA or ASIC.

[0144] The RF processing unit includes a transceiver module, up / down converters, power amplifiers (PA), low-noise amplifiers (LNA), and Tx / Rx filters. Analog-to-digital conversions (such as digital-to-analog converters (DACs), analog-to-digital converters (ADCs), RF sampling, and frequency conversion) can be performed within the transceiver module. Note that physical and logical partitions within the RF processing unit do not require specific boundaries.

[0145] In different systems, CU (or CU-CP and CU-UP), DU, or RU may have different names, but those skilled in the art will understand their meaning. For example, in an ORAN system, CU can also be called an O-RAN central unit (O-CU), DU can also be called an O-RAN distributed unit (O-DU), CU-CP can also be called an O-RAN central unit control plane (O-CU-CP), CU-UP can also be called an O-RAN central unit user plane (O-CU-UP), and RU can also be called an O-RAN radio unit (O-RU).

[0146] As another possible implementation, the RAN node can also be a non-real time RAN intelligent controller (Non-RT RIC or NRT RIC) and / or a near-real time RAN intelligent controller (Near-RT RIC or nRT RIC).

[0147] Non-RT RIC is used to implement non-real-time intelligent management of the RAN, enabling AI / machine learning (ML) including model training and updates, and guiding applications / functions within the Near-RT RIC based on policies. Near-RT RIC is used to implement near real-time intelligent management of the RAN, achieving near real-time control and optimization of O-RAN modules and resources through data collection and related operations on the E2 interface. The E2 interface can be understood as an open interface between two nodes (or endpoints).

[0148] All or part of the functions of the RAN node in this application can also be implemented through software functions running on hardware, or through virtualization functions instantiated on a platform (e.g., a cloud platform), or through software modules, hardware modules, or a combination of software and hardware modules. The RAN node in this application can also be a logical node, logical module, or software capable of implementing all or part of the functions of the access network equipment, or a device with some access network equipment functions, such as a chip system, which can be installed in the access network equipment.

[0149] In one possible implementation, core network equipment can refer to equipment in the core network 400 that provides service support to terminals. In this embodiment, the core network equipment in the core network 400 includes sensing function (SF) network elements. SF network elements are primarily responsible for sensing services and are used to implement sensing functions. Sensing functions include, for example, sensing control functions and / or sensing computing functions. Furthermore, SF network elements can also support sensing billing functions when terminals and / or RAN nodes perform sensing operations.

[0150] In one possible scenario, the functionality of the SF network element can be implemented by the network data analytics function (NWDAF) network element, or the SF network element and the NWDAF network element can be co-located. Alternatively, the SF network element can be deployed integrated with the core network or deployed independently.

[0151] Optionally, in addition to SF network elements, the core network equipment in Core Network 400 may also include at least one of the following: access and mobility management function (AMF) network elements, session management function (SMF) network elements, user plane function (UPF) network elements, policy control function (PCF) network elements, unified data management (UDM) network elements, application function (AF) network elements, network exposure function (NEF) network elements, and location management function (LMF) network elements. Of course, Core Network 400 may also include other core network equipment without limitation.

[0152] In one possible implementation, terminal 320 is a user-side device with wireless transceiver capabilities. It can be a fixed device, mobile device, handheld device (e.g., mobile phone), wearable device, in-vehicle device, or a wireless device (e.g., communication module, modem, or chip system, etc.) built into the aforementioned devices. The terminal is used to connect people, objects, and machines, and can be widely used in various scenarios, such as: cellular communication, device-to-device (D2D) communication, V2X communication, MTC communication, IoT, virtual reality (VR), augmented reality (AR), industrial control, self-driving, remote medical care, smart grid, smart furniture, smart office, smart wearables, smart transportation, smart city, drones, robots, etc. For example, a terminal can be a handheld terminal in cellular communication, a communication device in D2D, an IoT device in MTC, a camera in intelligent transportation and smart cities, or a communication device on a drone; or, a terminal can be a mobile phone, tablet computer, computer with wireless transceiver capabilities, wearable device, vehicle, drone, helicopter, airplane, ship, robot, robotic arm, smart home device, etc. The embodiments of this application do not limit the device form of the terminal. A terminal may sometimes be referred to as a UE, user terminal, user device, user unit, user station, terminal, access terminal, access station, UE station, remote station, mobile device, or wireless communication device, etc.

[0153] It should be noted that the system described in the embodiments of this application is for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and does not constitute a limitation on the technical solutions provided in the embodiments of this application. As those skilled in the art will know, with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of this application are also applicable to similar technical problems.

[0154] The following is combined with Index The communication system shown uses the interaction between RAN nodes, terminals, and core network equipment as an example to describe the communication method provided in the embodiments of this application. It should be noted that in the following embodiments of this application, the message names, parameter names, or information names between RAN nodes and terminals are just examples, and other names may be used in other embodiments. The method provided in this application is not specifically limited in this regard.

[0155] It is understood that in the embodiments of this application, the RAN node, terminal, or core network device may execute some or all of the steps in the embodiments of this application. These steps or operations are merely examples, and the embodiments of this application may also perform other operations or variations thereof. Furthermore, the various steps may be executed in different orders as presented in the embodiments of this application, and it is not necessarily necessary to execute all the operations in the embodiments of this application.

[0156] It is understood that this application uses RAN nodes, terminals, and core network equipment as examples to illustrate the execution of the interaction, but this application does not limit the execution subject of the interaction. For example, the method executed by the RAN node in this application can also be executed by a module (e.g., chip, chip system, or processor) applied to the RAN node, or by a logical node, logical module, or software that can implement all or part of the RAN node's functions; the method executed by the terminal in this application can also be executed by a module (e.g., chip, chip system, or processor) applied to the terminal, or by a logical node, logical module, or software that can implement all or part of the terminal's functions; the method executed by the core network equipment in this application can also be executed by a module (e.g., chip, chip system, or processor) applied to the core network equipment, or by a logical node, logical module, or software that can implement all or part of the core network functions.

[0157] Before describing the method and flow provided in this application, the training conditions in this method will be explained first.

[0158] In one possible implementation, the training conditions in the embodiments of this application can be understood as: the training conditions used when obtaining the sequence set in an optimized manner, such as factors affecting the fuzzy performance of the sequence. Furthermore, training conditions can also be called optimization conditions, etc., and this application does not specifically limit the name of the training conditions.

[0159] As one possible implementation, obtaining the sequence set based on optimization can be understood as generating the sequence set by solving an optimization problem. The optimization problem can be related to at least one of the following: APSL, CPSL, auto-ambiguity integrated sidelobe level (AISL), cross-ambiguity integrated sidelobe level (CISL), or peak to average power ratio (PAPR).

[0160] For example, APSL represents the maximum value among the maximum self-blurred sidelobes of all sequences in the sequence set. Assume X = {x 0 ,x 1 ,……,x M-1} represents a set of sequences of size M (i.e., the set of sequences contains M sequences), where a sequence is represented as . If the sequence length is L, or the sequence contains L elements, then APSL can be represented as:

[0161]

[0162] in, Represents sequence x m The maximum self-blurring sidelobe. u represents the Doppler frequency, and τ represents the cyclic shift.

[0163] For example, CPSL represents the maximum value of the largest mutually blurred sidelobes between any two sequences in a sequence set. Based on the sequence set X as assumed above, CPSL can be expressed as:

[0164]

[0165] in, Represents a sequence and sequence The maximum cross-ambiguity sidelobe between them. u represents the Doppler frequency, and τ represents the cyclic shift.

[0166] For example, AISL represents the sum or average of the self-fuzzy sidelobes of all sequences in the sequence set. CISL represents the sum or average of the mutual fuzzy sidelobes between any two sequences in the sequence set.

[0167] For example, PAPR represents the maximum time-domain signal envelope power (P0). peak ) and average power (P) avg The ratio of ) is expressed in decibels (dB), that is:

[0168]

[0169] PAPR can be understood as a value that measures the degree of envelope fluctuation of a signal; the higher the PAPR, the greater the envelope fluctuation. A higher PAPR will degrade the performance of the communication system. Wireless communication systems typically require power amplification before transmission. Due to technological and equipment cost limitations, power amplifiers often amplify linearly within a certain range; exceeding this range will lead to signal distortion. Signal distortion may prevent the receiving end from correctly interpreting the signal. To ensure that the signal peak remains within the linear range of the power amplifier's amplification capability, the average power of the transmitted signal needs to be reduced. This approach results in lower power amplifier efficiency, or equivalently, a smaller coverage area. Therefore, when designing sequences, the PAPR of the transmitted signal carrying the sequence can be maintained at a low level, for example, below 3dB, by optimizing sequence elements.

[0170] As one possible implementation, considering the complexity of the optimization problem, it can be solved using methods such as AI. For example, the optimization problem can be used as the loss function of a neural network to generate a set of sequences.

[0171] For example, each element in the sequence set can be used as the model parameters / output of the neural network, and the optimization problem can be used as the loss function, such as the loss function being related to at least one of APSL, CPSL, AISL, CISL, or PAPR. The neural network can be a single-layer 1×ML fully connected neural network, where M is the number of sequences in the sequence set, L is the length of the sequence, and M and L are positive integers. Since no training data is required when generating sequences based on AI, the input of the neural network can be defaulted to 1, and the model parameters of the neural network are also the output of the neural network.

[0172] For example, suppose we need to generate a set of sequences by solving the following optimization problem: Then you can As the loss function, a sequence set is generated based on an AI method. Here, w can be understood as the weight.

[0173] Furthermore, when generating sequences using an optimization-based approach, constraints can be imposed on the elements of the sequence. For example, constraining each element to be constant modulus allows for optimization of the phase of the sequence elements, such as using the phase of the sequence elements as model parameters. Here, "constant modulus" can be understood as the sequence elements being constant modulus in the time domain, or constant modulus in the frequency domain. This can be understood as time-domain sequence elements, and the corresponding frequency-domain sequence can be obtained by performing a Discrete Fourier Transform (DFT) on the time-domain sequence. Alternatively, as described above... It can be understood as frequency domain sequence elements. The inverse discrete fourier transform (IDFT) can be performed on the frequency domain sequence to obtain its corresponding time domain sequence.

[0174] In one possible implementation, the training conditions in this application embodiment, i.e., the factors affecting the sequence fuzzing performance, may include the initialization sequence and the loss function. Optionally, the training conditions may also include an optimizer.

[0175] As one possible implementation, the initialization sequence can be a non-random, reproducible sequence. For example, the initialization sequence can be a ZC sequence, a sequence obtained by expanding a ZC sequence, a Gold sequence, an M sequence, etc. Implementations of each sequence can be found in the relevant descriptions above, and will not be repeated here. Furthermore, the initialization sequence can also be called the initialization value, and of course, it can have other names; this application does not specifically limit its usage.

[0176] As one possible implementation, the loss function is related to at least one of the following metrics: APSL, CPSL, AISL, CISL, or PAPR. The implementations of each metric can be found in the descriptions above and will not be repeated here. For example, the loss function being related to at least one of APSL, CPSL, AISL, CISL, or PAPR can be understood as the form of the loss function being related to at least one of APSL, CPSL, AISL, CISL, or PAPR.

[0177] Furthermore, there are parameters for the loss function. The parameters of the loss function include at least one of the following: weight corresponding to at least one of the above-mentioned indicators, constraint value, Doppler frequency offset range (also known as Doppler frequency range), time delay range, or sequence transmission duration.

[0178] For example, the weight corresponding to a certain indicator can represent the degree of influence of that indicator on the loss function; the constraint value corresponding to a certain indicator can be understood as the maximum allowed value of that indicator after optimization, or the expected value of that indicator after optimization; the Doppler frequency offset range, delay range, or sequence transmission duration corresponding to a certain indicator can be understood as the Doppler frequency offset range, delay range, or sequence transmission duration used when calculating that indicator. The Doppler frequency offset range can be understood as the range of values ​​of u in the above APSL / CPSL / AISL / CISL expressions, the delay range can be understood as the range of values ​​of τ in the APSL / CPSL / AISL / CISL expressions, and the sequence transmission duration can be understood as T in the fuzzy function.

[0179] For example, APSL / CPSL / AISL / CISL can correspond to at least one of weights, constraint values, Doppler frequency offset range (also known as Doppler frequency range), time delay range, or sequence transmission duration, and PAPR can correspond to weights and / or constraint values.

[0180] For example, the parameters of the loss function can remain unchanged during model optimization (i.e., during the generation of the sequence set), and they do not need to be optimized. The parameters of the loss function can also be called the hyperparameters of the loss function, and they can be interchanged.

[0181] For example, the loss function may include, but is not limited to: wAPSL+(1-w)CPSL, w1APSL+w2CPSL+w3PAPR,

[0182] wAPSL + (1-w)CPSL + max(PAPR, p). Here, w and w1 can be understood as the weights corresponding to APSL, (1-w) and w2 as the weights of CPSL, w3 as the weight of PAPR, and p as the constraint value of PAPR. w, w1, w2, and w3 are all greater than or equal to 0 and less than or equal to 1, and p is a positive number.

[0183] As one possible implementation, the optimizer may include, but is not limited to, stochastic gradient descent (SGD), adaptive moment estimation (Adam), and root mean square propagation (RMSProp). Furthermore, the optimizer's parameters may include, but are not limited to, the learning rate, learning decay value, and momentum parameter.

[0184] For example, the optimizer's parameters can remain unchanged during model optimization (i.e., during the generation of the sequence set), and they do not need to be optimized. The optimizer's parameters can also be called the optimizer's hyperparameters, and they can be interchanged.

[0185] As one possible implementation, one possible way to use the training conditions is to use the initial sequence as the initial model parameters / initial output of the neural network. Subsequently, the model parameters of the neural network are continuously updated based on the loss function, or based on the loss function and the optimizer, so that the value of the loss function generally shows a decreasing trend, and finally the sequence set is obtained.

[0186] In one possible implementation, the protocol may predefine at least one training condition, each training condition may have a corresponding index or identifier. For example, the at least one training condition may include some or all of the training conditions shown in Table 1.

[0187] Table 1

[0188] Initialization sequence Loss function Optimizer [optional] ZC sequence 0 wAPSL + (1 - w)CPSL SGD ZC sequence 1 Adam w1APSL + w2CPSL + w3PAPR ZC sequence 2 wAPSL + (1 - w)CPSL + max(PAPR, p) Adam Gold sequence 3 wAPSL + (1 - w)CPSL RMSProp Gold sequence 4 RMSProp w1APSL + w2CPSL + w3PAPR Index 5 …… …… ……

[0189] For example, the ZC sequences and Gold sequences in Table 1 can be understood as specific sequences, rather than sequence types. For instance, the protocol can define which ZC sequence is included in the training conditions, such as defining parameters used to determine the ZC sequence, like the value of the root of the ZC sequence. Similarly, the protocol can define which Gold sequence / M sequence is included in the training conditions, such as defining parameters used to determine the Gold sequence / M sequence, like the initialization parameters of the Gold sequence / M sequence.

[0190] For example, the parameters of the loss function, such as the weights of each metric, constraint values, Doppler range, delay range, and sequence transmission duration considered when calculating APSL / CPSL / AISL / CISL, can be predefined default values ​​by the protocol; or they can be configurable and unrestricted.

[0191] For example, the optimizer's parameters, such as learning rate, learning decay value, momentum parameter, etc., can be default values ​​predefined by the protocol; or they can be configurable and unrestricted.

[0192] It should be noted that Table 1 is only an exemplary illustration of training conditions. The initialization sequence, loss function, or optimizer shown in Table 1 can be arbitrarily combined to form new training conditions, or the initialization sequence, loss function, or optimizer can have other values ​​or combinations. Table 1 does not impose any limitation on the scheme of this application, nor does this application limit the specific form of the training conditions.

[0193] Table 1 illustrates the protocol's predefined initialization sequences and loss functions as examples. Furthermore, the protocol may also employ the following three implementation methods:

[0194] As a first possible implementation, the protocol can define an initialization sequence and multiple loss functions. Each loss function and the initialization sequence can serve as a set of training conditions. For example, the training conditions defined by the protocol can be shown in Table 2. Referring to Table 2, the protocol defines an initialization sequence of ZC sequence, and also defines three loss functions.

[0195] Table 2

[0196] Initialization sequence Loss function Optimizer [optional] ZC sequence 0 wAPSL + (1 - w)CPSL SGD ZC sequence 1 Adam w1APSL + w2CPSL + w3PAPR ZC sequence 2 wAPSL + (1 - w)CPSL + max(PAPR, p) Adam Index

[0197] Optionally, since the initialization sequences corresponding to the three loss functions are the same, the indices in Table 2 can also be understood as indices of the loss functions. Alternatively, Table 2 can exclude the initialization sequences and define them separately.

[0198] As a second possible implementation, the protocol can define an initialization sequence and a loss function, which serve as a set of training conditions. For example, the protocol can define the initialization sequence as the ZC sequence and the loss function as wAPSL+(1-w)CPSL, or define the initialization sequence as the Gold sequence and the loss function as w1APSL+w2CPSL+w3PAPR, without restriction.

[0199] As a third possible implementation, the protocol can define multiple initialization sequences and a loss function. Each initialization sequence and the loss function can serve as a set of training conditions. For example, the training conditions defined by the protocol can be shown in Table 3. Referring to Table 3, the protocol defines one loss function as wAPSL+(1-w)CPSL, and in addition, three other loss functions are defined.

[0200] Table 3

[0201] Initialization sequence Loss function Optimizer [optional] ZC sequence 0 wAPSL + (1 - w)CPSL SGD Gold sequence 1 wAPSL + (1 - w)CPSL Adam M sequence 2 wAPSL + (1 - w)CPSL Adam Figure 5

[0202] Optionally, since the loss function is the same for the three initialization sequences, the indices in Table 3 can also be understood as indices for the initialization sequences. Alternatively, Table 3 can omit the loss function and define a separate loss function.

[0203] Optionally, the protocol can also predefine the expected values ​​of each loss function, such as the expected values ​​after optimization, for example, defining the expected value of wAPSL+(1-w)CPSL. Alternatively, the protocol can predefine the expected values ​​of at least one metric of the loss function, for example, defining the expected value of APSL as -13.5dB, the expected value of CPSL as -20dB, or the expected value of PAPR as 3dB, etc.

[0204] For example, each device can determine whether it has the ability to generate AI sequences / optimize sequences based on the expected value of a loss function predefined in the protocol, or the expected value of at least one metric of the loss function. For instance, if a device cannot reach the expected value no matter how it optimizes, it means that the device does not have the ability to generate AI sequences; if the device can reach the expected value after optimization, it means that the device has the ability to generate AI sequences.

[0205] Once a device determines whether it has the capability to generate AI sequences, it can report this capability to the RAN or core network. The RAN or core network can then determine whether to configure training conditions for that device based on this capability. For example, if the device does not have the capability to generate AI sequences, training conditions will not be configured for it, because even if configured, the device will not be able to generate AI sequences; if the device does have the capability to generate AI sequences, training conditions can be configured for it. Optionally, if a device does not have the capability to generate AI sequences, it may be denied access to the network.

[0206] In one possible implementation, the sequence set obtained using the optimization-based approach described above can be a single-channel sequence set, i.e., the sequence set includes M sequences, each with a length of L, such as each sequence being represented as [x0, x1, x2, ..., x...]. L-1 ].

[0207] Alternatively, the sequence set obtained using the optimization-based approach described above can also be a multi-channel sequence set, which includes at least one multi-channel sequence. A multi-channel sequence can be understood as a group of sequences comprising multiple channel sequences of equal length, with the total length of the multi-channel sequence being the sum of the lengths of the individual channel sequences. The number of sequences included in a multi-channel sequence can be called the number of channels in that multi-channel sequence. For example, a K-channel sequence of length L comprising L×K elements can be represented as:

[0208] [[x 0,0 ,x 1,0 ,x 2,0 ,…,x L-1,0 ],……,[x 0,k ,x 1,k ,x2,k ,…,x L-1,k ],……,[x 0,K-1 ,x 1,K-1 ,x 2,K-1 ,…,x L-1,K-1 ]]

[0209] In this context, the correlation / fuzziness result of a multi-channel sequence can be understood as the superposition of each channel sequence after independent correlation. The fuzzy sidelobes of each channel sequence may cancel each other out to achieve better fuzziness characteristics than a single-channel sequence. A multi-channel sequence can also be understood as a sequence that requires independent correlation of sequence segments, and the number of channels can be understood as the number of segments in the sequence when performing correlation.

[0210] When optimizing multi-channel sequences, the metrics APSL / CPSL / AISL / CISL of the aforementioned loss function are obtained based on the fuzzy function of the multi-channel sequence, while PAPR is obtained considering the transmission of all channel sequences. The parameters of the aforementioned loss function may also include the number of channels in the multi-channel sequence and the transmission interval between two adjacent channel sequences. It can be understood that the transmission duration of a multi-channel sequence is equal to the number of channels multiplied by the transmission interval between two adjacent channel sequences.

[0211] The communication method provided in the embodiments of this application will be described below based on the above introduction. For example... Figure 6 As shown, the communication method may include the following steps:

[0212] S501, The second communication device determines the first training conditions.

[0213] As one possible implementation, the second communication device can be a core network device. This core network device can be an existing network element deployed in the core network, such as an AMF network element; that is, it adds the functionality implemented by the second communication device in this application to an existing core network element. Alternatively, the core network device can be a new, independently deployed core network element, such as an SF network element; this application does not specifically limit this.

[0214] As another possible implementation, the second communication device can be a RAN node. In this case, the first training condition can be the training condition used by the RAN node when generating the sequence set.

[0215] The first training condition includes a first initialization sequence and a first loss function. Optionally, the first training condition may also include a first optimizer.

[0216] As one possible implementation, the first initialization sequence can be one of the following: a ZC sequence, a sequence obtained by extending a ZC sequence, a Gold sequence, or an M sequence. Refer to the above description of the initialization sequence; further details will not be repeated here.

[0217] As one possible implementation, the first loss function is associated with at least one of the metrics APSL, CPSL, AISL, CISL, or PAPR. The parameters of the first loss function include at least one of the following: the weights corresponding to each metric, constraint values, Doppler frequency offset range, time delay range, or sequence transmission duration. Refer to the above description of loss functions; further details will not be repeated here.

[0218] As one possible implementation, the first optimizer can be one of SGD, Adam, or RMSProp. The parameters of the first loss function include at least one of the following: learning rate, learning rate decay value, or momentum parameter. Please refer to the above description of the optimizers, which will not be repeated here.

[0219] As one possible implementation, the first training condition is one of at least one predefined training conditions. For example, the protocol may predefine at least one training condition, which includes the first training condition. The way the protocol predefines training conditions can be referred to the foregoing relevant descriptions, and will not be repeated here.

[0220] As one possible implementation, the second communication device determines the first training conditions, which may include the second communication device determining the first initialization sequence, the form of the first loss function, and the parameters of the first loss function. For example, the first initialization sequence is determined to be a ZC sequence, the form of the first loss function is wAPSL+(1-w)CPSL, and the parameter w of the first loss function is 0.4.

[0221] S502, the second communication device sends first information to the first communication device. Correspondingly, the first communication device receives the first information from the second communication device.

[0222] As one possible implementation, the first communication device is a RAN node. In the case where the second communication device is also a RAN node, the first and second communication devices are different RAN nodes.

[0223] The first information indicates the first training conditions. The first training conditions include a first initialization sequence and a first loss function. Optionally, the first training conditions may also include a first optimizer. The first training conditions can be referred to the relevant description in step S501 above, and will not be repeated here.

[0224] As a first possible implementation, in the case where the protocol defines multiple initialization sequences and multiple loss functions, the first information may include the index of the first training condition in the at least one training condition. In this case, the first information can be considered to indicate the form of the first loss function. For example, taking at least one predefined training condition as shown in Table 1, assuming the first training condition is the training condition corresponding to index 0, the first information may include index 0, the form of the first loss function is wAPSL+(1-w)CPSL, and the parameter w of the first loss function may be predefined by the protocol or may be indicated by the second communication device.

[0225] Alternatively, training conditions can be associated with business processes or business scenarios. For example, business scenario 1 can be associated with training condition 1, and business scenario 2 can be associated with training condition 2. That is, training condition 1 is used in business scenario 1, and training condition 2 is used in business scenario 2. In this case, the first information may include the identifier or index of the business scenario associated with the first training condition.

[0226] As a second possible implementation, if the protocol defines an initialization sequence and multiple loss functions, the first information may include the index of the first loss function among the multiple loss functions. Since the protocol defines only one initialization sequence, the communication device in the network, after determining the first loss function, can determine that the first training condition includes the first loss function and an initialization sequence predefined by the protocol. Therefore, in this implementation, the first information can also be considered to indicate the first training condition. Furthermore, the first information can also be considered to indicate the form of the first loss function, whose parameters can be predefined by the protocol or indicated by the second communication device.

[0227] As a third possible implementation, if the protocol defines an initialization sequence and a loss function, the initialization sequence is the first initialization sequence and the loss function is the first loss function. In this case, the first information may include the parameters of the first loss function, or it can be considered that the first information indicates the parameters of the first loss function.

[0228] Alternatively, if the protocol defines an initialization sequence and a loss function, and predefines the parameters of the loss function, then steps S501 and S502 above may not be executed. Each communication device in the network generates a sequence set based on the protocol definition and using the same fixed training conditions.

[0229] As a fourth possible implementation, where the protocol defines multiple initialization sequences and a loss function, the first information may include the index of the first initialization sequence within these multiple initialization sequences. Since the protocol defines only one loss function, the communication devices in the network can determine that the first training condition includes the first initialization sequence and a loss function predefined by the protocol after determining the first initialization sequence. Therefore, in this implementation, the first information can also be considered to indicate the first training condition.

[0230] As one possible implementation, if the first initialization sequence is a Gold sequence, the first information also indicates the initialization parameters of the Gold sequence. If the first initialization sequence is an M sequence, the first information also indicates the initialization parameters of the M sequence.

[0231] As one possible implementation, the second communication device can send first information to multiple first communication devices. For example, if the second communication device is a core network device, the core network device can send the first information to multiple RAN nodes it manages or serves; if the second communication device is a RAN node, the RAN node can send the first information to multiple RAN nodes adjacent to it.

[0232] As one possible implementation, under the first, second, or fourth possible implementation described above, the second communication device may also indicate the parameters of the first loss function to the first communication device. For example, the second communication device may indicate the parameters of the first loss function through first information, that is, the first information also indicates the parameters of the first loss function; or, the second communication device may send second information to the first communication device, which indicates the parameters of the first loss function, and correspondingly, the first communication device receives the second information from the second communication device to obtain the parameters of the first loss function.

[0233] For example, the second information and the first information may be carried in the same message or in different messages, and this application does not specifically limit this.

[0234] For example, if the second communication device does not indicate the parameters of the first loss function to the first communication device, or indicates only part of the parameters of the first loss function, the unindicated parameters of the first loss function may be predefined by the protocol.

[0235] As one possible implementation, the second communication device may also indicate the expected value of the first loss function to the first communication device, and / or indicate the expected value of at least one index of the first loss function, wherein the at least one index of the first loss function may include at least one of APSL, CPSL, AISL, CISL, or PAPR. For example, the second communication device may indicate the expected value through first information; or, the second communication device may send third information to the first communication device to indicate the expected value, and correspondingly, the first communication device may receive the third information from the second communication device to obtain the expected value.

[0236] For example, taking wAPSL+(1-w)CPSL as the first loss function, the second communication device can indicate the expected value of wAPSL+(1-w)CPSL, and / or can indicate the expected value of APSL and the expected value of CPSL.

[0237] For example, the third information and the first information may be carried in the same message or in different messages, and this application does not specifically limit this.

[0238] As one possible implementation, the second communication device can also indicate the parameters of the first optimizer to the first communication device. For example, the second communication device can indicate the parameters of the first optimizer through first information; or, the second communication device can send fourth information to the first communication device to indicate the parameters of the first optimizer, and correspondingly, the first communication device can receive the fourth information from the second communication device to obtain the parameters of the first optimizer.

[0239] S503. The first communication device determines the first sequence set according to the first training conditions.

[0240] As one possible implementation, the first communication device can use the first initialization sequence as the initial model parameters / initial output of the neural network. Subsequently, based on the first loss function, or based on the first loss function and the first optimizer, the model parameters of the neural network are continuously updated, so that the value of the first loss function generally shows a decreasing trend, or the value of the first loss function reaches the desired value, or at least one metric of the first loss function reaches the desired value, ultimately obtaining the first sequence set. In this scenario, it can be assumed that multiple communication device nodes generate the sequence set using the same training conditions.

[0241] For example, the parameters of the first loss function and / or the parameters of the first optimizer can be determined by instructions from the second communication device, such as by determining the parameters of the first loss function and / or the parameters of the first optimizer through first information; or, by determining the parameters of the first loss function through second information, and / or, by determining the parameters of the first optimizer through fourth information. Alternatively, the parameters of the first loss function and / or the parameters of the first optimizer can be predefined by the protocol and are not limited.

[0242] For example, the expected value of the first loss function, and / or the expected value of at least one index of the first loss function, may be indicated by the second communication device, such as by the second communication device through first information or third information; or, the expected value may be predefined by the protocol, without limitation.

[0243] For example, if the first communication device cannot achieve the desired value no matter how it is optimized, it indicates that the first communication device does not have the ability to generate AI sequences and cannot generate the first sequence set. In this case, the first communication device can report to the second communication device that it does not have the ability to generate AI sequences, and the second communication device can send the first sequence set to the first communication device based on the report from the first communication device.

[0244] It should be noted that, in this embodiment of the application, the first communication device is described as having the ability to generate AI sequences and can generate a first sequence set.

[0245] As another possible implementation, the first communication device can determine another loss function (referred to as a third loss function) that is similar to the first loss function in the first training conditions, and then determine the first sequence set based on the first initialization sequence and the third loss function. In this scenario, it can be assumed that multiple communication device nodes generate sequence sets using similar training conditions.

[0246] For example, the first communication device can use the first initialization sequence as the initial model parameters / initial output of the neural network, and then continuously update the model parameters of the neural network based on the third loss function, or based on the third loss function and the first optimizer, so that the value of the third loss function generally shows a downward trend, or the value of the third loss function reaches the expected value, or at least one index of the third loss function reaches the expected value, and finally obtain the first sequence set.

[0247] In this context, "same training conditions" can refer to having the same initialization sequence and loss function, while "similar training conditions" can refer to having the same initialization sequence and similar loss functions. Different devices may generate the same or similar sequence sets based on the same training conditions, and may generate similar sequence sets based on similar training conditions.

[0248] For example, loss function similarity can be understood as: the metrics for determining the loss function are the same, but the form and / or parameters of the loss function are different. For example, the loss functions corresponding to index 1 and index 2 in Table 1 can be understood as similar loss functions.

[0249] As one possible implementation, when the second communication device is a core network device, the core network device sends first information to multiple first communication devices, each of which determines a set of sequences based on a first training condition. The sequence sets determined by the multiple first communication devices based on the first training condition are similar or identical. For example, the first initialization sequences and first loss functions in the first training conditions indicated by the core network device to the multiple first communication devices are the same.

[0250] For example, when the core network device instructs the same first loss function to multiple first communication devices, these multiple first communication devices may generate a sequence set using the same training conditions. When the core network device instructs similar first loss functions to multiple first communication devices, these multiple first communication devices generate a sequence set using similar training conditions.

[0251] As another possible implementation, in the case where the second communication device is a RAN node, the second communication device also determines a sequence set according to the first training condition, and the sequence sets determined by the second communication device and the second communication device according to the first training condition are similar or the same.

[0252] For example, the second communication device and the first communication device may use the same training conditions, such as both using the first training condition, to generate a sequence set. Alternatively, the second communication device and the first communication device may use similar training conditions to generate the sequence set, such as the second communication device using the first training condition and the first communication device using a first initialization sequence and a third loss function, wherein the third loss function is similar to the first loss function.

[0253] S504. The first communication device transmits and / or receives a reference signal according to a first sequence in the first sequence set. For example, the first sequence can be any sequence in the first sequence set.

[0254] As one possible implementation, in a communication or positioning scenario, the first communication device can send or receive reference signals according to a first sequence in a first sequence set, for example, sending DMRS or PRS to the terminal according to the first sequence; or receiving a preamble in SRS or PRACH from the terminal according to the first sequence.

[0255] As another possible implementation, in a sensing scenario, the first communication device can transmit and / or receive a reference signal according to a first sequence in a first sequence set. In a sensing scenario, the reference signal can also be called a sensing signal. For example, in a self-transmitting and self-receiving mode, the first communication device transmits and receives the reference signal according to the first sequence; in a self-transmitting and third-party-receiving mode, the first communication device transmits the reference signal according to the first sequence, and the third communication device receives the reference signal according to the first sequence; or, the third communication device transmits the reference signal according to the first sequence, and the first communication device receives the reference signal according to the first sequence. For example, the third communication device can be a terminal.

[0256] For example, the first communication device transmitting a reference signal according to a first sequence can be understood as: the first communication device generating a reference signal according to the first sequence and transmitting the reference signal. The first communication device receiving a reference signal according to the first sequence can be understood as: performing correlation operations on the received reference signal according to the first sequence.

[0257] As one possible implementation, the first communication device transmitting and / or receiving reference signals according to the first sequence can be understood as follows: the first communication device transmits or receives reference signals according to the first sequence during communication with a terminal; or, during a single sensing process, transmits and / or receives reference signals according to the first sequence. Furthermore, the first communication device can communicate with different terminals according to different sequences in the first sequence set, or transmit and / or receive reference signals according to different sequences in the first sequence set during different sensing processes.

[0258] In one possible implementation, in a communication or positioning scenario, or in a self-transmitting and receiving mode, the third communication device also needs to acquire a sequence similar to or identical to the first sequence in order to send or receive a reference signal. For example, the third communication device can be a terminal. The first communication device can indicate a sequence similar to or identical to the first sequence to the third communication device through the following three possible implementations:

[0259] As a first possible implementation, the first communication device sends a seventh message to the third communication device, the seventh message indicating a first training condition. Optionally, the seventh message also indicates training parameters associated with the first training condition. The training parameters include parameters of the loss function and / or parameters of the optimizer; that is, the training parameters associated with the first training condition include parameters of the first loss function and / or parameters of the first optimizer.

[0260] In this possible implementation, after receiving the seventh information, the third communication device can determine a second sequence set based on the first training conditions, and send or receive reference signals based on the sequences in the second sequence set that correspond to the first sequence (such as sequences with the same index, hereinafter referred to as the second sequences). For example, the second sequence set may be similar to or identical to the first sequence set, and the second sequence may be similar to or identical to the first sequence.

[0261] As a second possible implementation, the first communication device sends a first sequence set and an index of the first sequence to the third communication device. The third communication device can determine the first sequence from the first sequence set based on the index of the first sequence, and thus send or receive a reference signal based on the first sequence.

[0262] As a third possible implementation, the first communication device sends a first sequence to the third communication device. After receiving the first sequence, the third communication device sends or receives a reference signal according to the first sequence.

[0263] Based on the above scheme, the second communication device can instruct the first communication device to provide a training condition, enabling the first communication device to determine a sequence set based on the training condition, and then send and / or receive reference signals according to the sequences in the sequence set. The second communication device can be a core network device or a RAN node, and the first communication device is a RAN node. When the second communication device is a core network device, it can be assumed that the core network device configures the training condition to the RAN node, thus allowing adjacent RAN nodes to be configured with the same or similar training conditions. When the second communication device is a RAN node, it can be assumed that multiple RAN nodes interact with each other regarding training conditions, thus allowing these multiple RAN nodes to use the same or similar training conditions. Since similar or identical sequence sets can be generated based on the same or similar training conditions, and different sequences within the same sequence set have low mutual ambiguity sidelobes, different sequences within similar or identical sequence sets also have low mutual ambiguity sidelobes, thereby reducing interference between terminals served by multiple RAN nodes.

[0264] For example, taking sequence set 1 and sequence set 2 both containing 30 sequences, each with a length of 102, and the sequences being frequency domain constant modulus sequences, if sequence set 1 and sequence set 2 were generated based on an optimized approach but using different initialization sequences, then as follows... Figure 6 As shown in (a), this is a phase comparison between sequence m in sequence set 1 and sequence m in sequence set 2, where the phase value of each sequence element ranges from [0, 2π]. Figure 6 As shown in (b), this represents the phase difference between the individual sequence elements of sequence m in sequence set 1 and sequence m in sequence set 2. Figure 7It can be seen that the phase difference between the sequence elements of sequence m in sequence set 1 and sequence m in sequence set 2 is relatively large and the phase difference is relatively random, that is, the similarity between the two sequences is poor.

[0265] If sequence set 1 and sequence set 2 were generated using the same initialization sequence and based on an optimized approach, then as follows: Figure 7 As shown in (a), this is a phase comparison between sequence m in sequence set 1 and sequence m in sequence set 2, where the phase value of each sequence element ranges from [0, 2π]. Figure 7 As shown in (b), this represents the phase difference between the individual sequence elements of sequence m in sequence set 1 and sequence m in sequence set 2. Figure 6 It can be seen that the phases of the sequence elements of sequence m in sequence set 1 and sequence m in sequence set 2 are similar, and the phase difference is concentrated around 0 or 2π, that is, the similarity between the two sequences is good.

[0266] In other words, two sequence sets optimized based on the same initialization sequence are relatively similar, thus exhibiting good mutual ambiguity performance between sequences corresponding to different sequence identifiers within the two sequence sets. For example, the mutual ambiguity performance between sequence 1 in sequence set 1 and sequence 2 in sequence set 2 is good. This is because the sequences in sequence set 1 have good mutual ambiguity performance, such as the mutual ambiguity performance between sequence 1 and sequence 2 in sequence set 1, while sequence 2 in sequence set 2 is similar to or identical to sequence 2 in sequence set 1. Therefore, the mutual ambiguity performance between sequence 1 in sequence set 1 and sequence 2 in sequence set 2 is good.

[0267] For example, for Figure 7 For the two corresponding sequence sets, the mutual blurring peak sidelobe level between sequence 1 in sequence set 1 and sequence 2 in sequence set 2 is approximately -14.8 dB. And for... Figure 7 For the two corresponding sequence sets, the mutual blurring peak sidelobe level between sequence 1 in sequence set 1 and sequence 2 in sequence set 2 is approximately -17.5 dB. This is because for Figure 8 The corresponding two sequences, Sequence 1 and Sequence 2 in Sequence Set 1, have low mutual ambiguity peak side lobes, while Sequence 2 in Sequence Set 2 is similar to or the same as Sequence 2 in Sequence Set 1.

[0268] In one possible implementation, the second communication device described above can be a core network device. For example, in step S501, the core network device can determine the first training conditions in three ways.

[0269] Method 1: The core network equipment determines the first training condition based on the training conditions recommended by each RAN node.

[0270] In one possible implementation, the communication method provided in this application may further include the following steps: a first communication device sends fifth information to a second communication device, and correspondingly, the second communication device receives the fifth information from the first communication device.

[0271] The fifth piece of information indicates the second training conditions, which are the training conditions recommended by the first communication device. For example, the second training conditions include a second initialization sequence and / or a second loss function. Further, the second training conditions also include a second optimizer.

[0272] Optionally, the fifth piece of information also indicates the training parameters associated with the second training condition. The training parameters associated with the second training condition include the parameters of the second loss function and / or the parameters of the second optimizer. The parameters of the second loss function can be found in the aforementioned description of the parameters of the loss function, and the parameters of the second optimizer can be found in the aforementioned description of the parameters of the optimizer; they will not be repeated here.

[0273] For example, multiple first communication devices may send fifth information to a second communication device. The fifth information sent by a particular first communication device indicates the training conditions and / or training parameters recommended by that first communication device. The second communication device can determine the first training conditions by combining the training conditions recommended by each of the first communication devices. Furthermore, the training parameters associated with the first training conditions can also be determined by combining the training parameters recommended by each of the first communication devices.

[0274] In other words, the second communication device can determine the first training condition based on the fifth information. Furthermore, it can also determine the training parameters associated with the first training condition based on the training parameters associated with the second training condition indicated by the fifth information.

[0275] For example, the second communication device can determine the training condition that is recommended most frequently as the first training condition. For instance, if the first communication devices #1, #2, and #3 recommend second training condition #1, second training condition #2, and second training condition #1 to the second communication device respectively, then the second communication device will determine second training condition #1 as the first training condition. Furthermore, the training parameters associated with second training condition #1 can also be determined as the training parameters associated with the first training condition.

[0276] Optionally, if multiple first communication devices send fifth information to a second communication device, in step S502 above, the second communication device may send first information to each of the multiple first communication devices to indicate the first training condition. Furthermore, the second communication device may also send eighth information to the first communication device, which may indicate the training parameters associated with the first training condition.

[0277] In one possible implementation, the second training condition indicated by the fifth information sent by the first communication device may be determined by the first communication device itself. Alternatively, it may be determined by the first communication device based on recommendations from terminals. For example, at least one terminal may send a sixth message to the first communication device, whereby the sixth message sent by a terminal indicates the training conditions and / or training parameters recommended by that terminal. Accordingly, the second communication device receives the sixth message from at least one terminal and determines the second training condition and / or the training parameters associated with the second training condition based on the sixth message from at least one terminal. That is, the first communication device comprehensively determines the second training condition and / or the training parameters associated with the second training condition based on the training conditions and / or training parameters reported by each terminal.

[0278] As one possible implementation, the training conditions recommended by the terminal to the first communication device may include a loss function. The training parameters recommended by the terminal may include parameters of the loss function, such as Doppler frequency offset range, time delay range, etc. For example, the parameters of the loss function can be determined based on at least one of the terminal's speed, the speed of the target to be sensed, or the distance to the target to be sensed.

[0279] As one possible implementation, the first communication device can determine the training condition that is recommended most frequently as the second training condition. Refer to the relevant explanation of the second communication device determining the first training condition above; it will not be repeated here. Alternatively, the first communication device can determine the training condition recommended by the terminal with the highest moving speed as the second training condition, or determine the training parameters recommended by the terminal with the highest moving speed as the training parameters associated with the second training condition. This application does not specifically limit the implementation of the first communication device determining the second training condition and / or the training parameters associated with the second training condition based on the sixth information.

[0280] Method 2: The core network equipment uses the training conditions reported by the fourth communication device as the first training condition.

[0281] For example, the fourth communication device may be a RAN node. The fourth communication device and the first communication device may be different RAN nodes.

[0282] For example, the fourth communication device can send a ninth message to the second communication device, the ninth message indicating a first training condition, and further, the ninth message also indicating training parameters associated with the first training condition. Correspondingly, the second communication device receives the ninth message from the fourth communication device, obtains the first training condition, and then sends a first message to at least one first communication device to indicate the first training condition. Furthermore, it also indicates the training parameters associated with the first training condition to at least one first communication device.

[0283] In other words, after receiving training conditions reported by a RAN node, the core network device can instruct other RAN nodes to use those training conditions to generate sequence sets. Furthermore, if the RAN node also reports training parameters, the core network device can also instruct those training parameters to other RAN nodes.

[0284] Method 3: The core network equipment determines the first training conditions on its own.

[0285] For example, in method three, the RAN node may not recommend training conditions to the core network device, or the core network device may not refer to any training conditions recommended by the RAN node, but instead determine the first training conditions directly based on the actual situation, business scenario, or preset rules, and indicate the first training conditions to multiple first communication devices.

[0286] In one possible implementation, in the embodiments of this application, the information sent by each device to indicate training conditions may include the index of the training condition in at least one predefined training condition, that is, the training condition is indicated by the index of the training condition.

[0287] In the above method, different RAN nodes can interact directly or through core network equipment to exchange training conditions, thereby ensuring that different RAN nodes can generate sequence sets using the same training conditions. Furthermore, this application also provides a communication method in which a terminal can recommend training conditions and / or training parameters to RAN nodes. Figure 9 As shown, the communication method includes the following steps:

[0288] S801, the terminal sends the first information to the RAN node. Correspondingly, the RAN node receives the first information from the terminal.

[0289] The first piece of information indicates the training conditions and / or training parameters recommended / desired by the terminal. The training conditions recommended by the terminal include an initialization sequence and / or a loss function. For example, the terminal may recommend an initialization sequence, a loss function, or both. The training parameters recommended by the terminal may include parameters of the loss function, such as Doppler frequency offset range, time delay range, etc. For example, the parameters of the loss function can be determined based on at least one of the terminal's speed, the speed of the target to be sensed, or the distance to the target to be sensed. The initialization sequence, loss function, and parameters of the loss function can be referred to the foregoing related descriptions, and will not be repeated here.

[0290] Optionally, the terminal's recommended training conditions may also include an optimizer; that is, the terminal may also recommend an optimizer. Correspondingly, the terminal's recommended training parameters may also include the optimizer's parameters. The optimizer and its parameters can be found in the aforementioned explanations and will not be repeated here.

[0291] S802, the RAN node determines the first training condition and / or the training parameters associated with the first training condition based on the first information.

[0292] The first training condition includes a first initialization sequence and a first loss function. Optionally, the first training condition may also include a first optimizer.

[0293] The training parameters associated with the first training condition include the parameters of the first loss function. Optionally, the training parameters associated with the first training condition may also include the parameters of the first optimizer.

[0294] As one possible implementation, when the terminal recommends training conditions, the RAN node determines the first training conditions based on the first information; when the terminal recommends training parameters, the RAN node determines the training parameters associated with the first training conditions based on the first information.

[0295] For example, the first training conditions determined by the RAN node and the training conditions recommended by the terminal may be the same or different. Similarly, the training parameters associated with the first training conditions determined by the RAN node and the training parameters recommended by the terminal may be the same or different.

[0296] In one possible implementation, at least one terminal may send first information to the first communication device, wherein the first information sent by a terminal indicates the training conditions and / or training parameters recommended by that terminal. Correspondingly, the RAN node receives the first information from at least one terminal and determines the first training conditions and / or the training parameters associated with the first training conditions based on the first information from at least one terminal. That is, the RAN node comprehensively determines the first training conditions and / or the training parameters associated with the first training conditions based on the training conditions and / or training parameters reported by each terminal.

[0297] As one possible implementation, the RAN node can determine the training condition that is recommended most frequently as the first training condition, referring to the relevant explanation of the second communication device determining the first training condition in Method 1 above, which will not be repeated here. Alternatively, the RAN node can determine the training condition recommended by the terminal with the highest mobile speed as the first training condition, or determine the training parameters recommended by the terminal with the highest mobile speed as the training parameters associated with the first training condition.

[0298] As one possible implementation, the RAN node can also generate a sequence set based on the first training conditions. For ease of description, the sequence set generated by the RAN node based on the first training conditions will be referred to as the first sequence set in the following embodiments of this application.

[0299] S803, the RAN node sends the second information to the terminal. Correspondingly, the terminal receives the second information from the RAN node.

[0300] As a first possible implementation, the second information indicates the first training condition and / or the training parameters associated with the first training condition. For example, the second information indicates the first training condition, and further, it can also indicate the training parameters associated with the first training condition. The implementation of the second information indicating the first training condition can be referred to in the relevant description of the first information indicating the first training condition in step S502 above, and will not be repeated here. Accordingly, after receiving the second information, the terminal can determine the sequence set based on the second information, such as generating a sequence set (hereinafter referred to as the second sequence set) based on the first training condition, which can be referred to in the relevant description in step S503 above, and will not be repeated here.

[0301] As a second possible implementation, the second information may indicate the set of sequences obtained by the RAN node according to the first training conditions, i.e., the first set of sequences. For example, the second information may include the sequence elements of each sequence in the first set of sequences; or, the second information may include the compressed first set of sequences, and accordingly, after receiving the second information, the terminal may use a corresponding decompression algorithm to decompress it, thereby obtaining the first set of sequences.

[0302] As a third possible implementation, the second information can indicate the first sequence, which is a sequence in the sequence set obtained by the (RAN node) according to the first training conditions, that is, the first sequence is a sequence in the first sequence set.

[0303] In one possible implementation, after step S803, the RAN node and the terminal may send and / or receive reference signals based on the sequences in the above sequence set.

[0304] As a first possible implementation, when the second information indicates the first training condition and / or the training parameters associated with the first training condition, the RAN node transmits or receives a reference signal according to the first sequence, and correspondingly, the terminal receives or transmits a reference signal according to the second sequence. The second sequence can be a sequence in a second sequence set that has the same index as the first sequence; for example, the first sequence is sequence 1 in the first sequence set, and the second sequence is sequence 2 in the second sequence set.

[0305] As a second possible implementation, when the second information indicates the first sequence set, the RAN node transmits or receives a reference signal according to the first sequence, and correspondingly, the terminal receives or transmits a reference signal according to the second sequence. The second sequence can be a sequence in the second sequence set that has the same index as the first sequence.

[0306] Optionally, in either of the above two possible implementations, the RAN node also needs to indicate the index of the first sequence (or the second sequence) to the terminal so that the terminal can determine the second sequence.

[0307] As a third possible implementation, in the case where the second information indicates the first sequence, the RAN node sends or receives a reference signal according to the first sequence, and correspondingly, the terminal receives or sends a reference signal according to the first sequence.

[0308] The implementation of RAN nodes and terminals sending or receiving reference signals can be referred to in step S504 above, where the first communication device sends and / or receives reference signals according to the first sequence, and will not be repeated here.

[0309] Based on the above scheme, the terminal can report its recommended or desired training conditions to the RAN node, enabling the RAN node to reasonably select training conditions to generate a sequence set, thereby improving the adaptability of the sequence set and thus improving the performance of subsequent communication or sensing based on the sequences in the sequence set.

[0310] Furthermore, when the RAN node instructs the terminal on training conditions, the terminal can generate a sequence set based on those conditions. This allows the RAN node and the terminal to generate similar or identical sequence sets based on the same or similar training conditions (e.g., the first sequence set and the second sequence set are the same or similar), enabling subsequent sensing or communication based on these sequence sets. On one hand, since it is not necessary to send the first sequence set generated by the RAN node to the terminal, signaling overhead can be reduced. On the other hand, since the RAN node and the terminal can generate similar or identical sequence sets based on the same or similar training conditions, they can use similar or identical sequences for sensing or communication, thus reducing signaling overhead while having a minimal impact on sensing or communication performance.

[0311] In one possible implementation, in the above embodiments of this application, the similarity of two sequence sets can be understood as: sequences in two sequence sets with the same index or identifier are similar, and their correlation results have obvious main lobes.

[0312] For example, let's take generating sequence set 1 and sequence set 2 based on the same training conditions as an example. Figure 9 In the diagram, (a) represents the autocorrelation result of sequence 1 in sequence set 1, such as... Figure 9As shown in (a), there is a distinct main lobe at the position where the time delay offset is 0, and the amplitudes of the other side lobes are all lower than that of the main lobe. Figure 9 (b) in the table represents the correlation results between sequence 1 in sequence set 2 and sequence 1 in sequence set 1, such as... Figure 5 As shown in (b), the correlation results of the two also show obvious main lobes at the position where the time delay offset is 0, that is, sequence 1 in sequence set 2 is similar to sequence 1 in sequence set 1.

[0313] In one possible implementation, for the above method embodiments, in a CU-DU architecture or ORAN system, the function of interaction between the RAN node and the terminal can be implemented by the DU or O-DU. The information sent by the RAN node to the terminal can be generated by the DU or O-DU, or it can be generated by the CU or O-CU and sent to the DU or O-DU. The function of interaction between the RAN node and the core network can be implemented by the CU or O-CU. The processing function of the RAN node can be implemented by the CU or O-CU, or by the DU or O-DU, or by a combination of CU and DU (or O-CU and O-DU), without limitation.

[0314] For example, as described above Figure 10 Taking the method shown as an example, when the second communication device is a core network device, the CU can receive first information from the core network device and then send the first information to the DU. The DU determines the first sequence set according to the first training conditions indicated by the first information. Subsequently, the DU can generate a reference signal based on the first sequence in the first sequence set and send it to the RU, which then transmits the reference signal in the form of radio waves; alternatively, the RU can receive the reference signal in the form of radio waves and then send the baseband reference signal to the DU, which processes the reference signal according to the first sequence. The specific implementation of each step can be found in the relevant descriptions above, and will not be repeated here.

[0315] The method provided in this application has been described above. In addition, this application also provides a communication device for implementing the functions described in the above method embodiments.

[0316] It is understood that, in order to achieve the aforementioned functions, the communication device includes hardware structures and / or software modules corresponding to the execution of each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware 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 this application.

[0317] This application embodiment can divide the communication device into functional modules according to the above method embodiment. For example, each function can be divided into a separate functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. It should be noted that the module division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0318] Figure 10 A schematic diagram of a communication device 100 is shown. The communication device 100 includes a processing module 1001 and a transceiver module 1002. This communication device 100 can be used to implement the functions of the aforementioned RAN node, terminal, or core network equipment.

[0319] In some embodiments, the communication device 100 may further include a storage module. Figure 10 (Not shown in the image) is used to store program instructions and data.

[0320] In some embodiments, the transceiver module 1002, also referred to as a transceiver unit, is used to implement sending and / or receiving functions. The transceiver module 1002 may consist of a transceiver circuit, a transceiver, a transceiver unit, or a communication interface.

[0321] In some embodiments, the transceiver module 1002 may include a receiving module and a sending module, respectively used to perform the receiving and sending steps performed by the RAN node, terminal, or core network device in the above method embodiments, and / or other processes to support the technology described herein; the processing module 1001 may be used to perform the processing steps performed by the RAN node, terminal, or core network device in the above method embodiments, and / or other processes to support the technology described herein.

[0322] When the communication device 100 is used to perform the functions of the first communication device:

[0323] The transceiver module 1002 is used to receive first information, the first information indicating first training conditions, the first training conditions including a first initialization sequence and a first loss function; the processing module 1001 is used to determine a first sequence set according to the first training conditions; the transceiver module 1002 is also used to send and / or receive reference signals according to the first sequence in the first sequence set.

[0324] Optionally, the transceiver module 1002 is also used to receive second information, which indicates the parameters of the first loss function.

[0325] Optionally, the transceiver module 1002 is also configured to receive third information, which indicates the expected value of the first loss function, and / or indicates the expected value of at least one index of the first loss function.

[0326] Optionally, the first training condition also includes a first optimizer. The transceiver module 1002 is further configured to receive fourth information, which indicates the parameters of the first optimizer.

[0327] Optionally, the transceiver module 1002 is also used to send a fifth message, which indicates a second training condition, which is a training condition recommended by the first communication device.

[0328] Optionally, the transceiver module 1002 is further configured to receive sixth information, which indicates the training conditions and / or training parameters recommended by the terminal; the processing module 1001 is further configured to determine the second training conditions and / or the training parameters associated with the second training conditions based on the sixth information.

[0329] Optionally, the transceiver module 1002 is also used to send a seventh message, which indicates the first training condition.

[0330] When the communication device 100 is used to implement the functions of the second communication device:

[0331] The processing module 1001 is used to determine the first training conditions, which include a first initialization sequence and a first loss function; the transceiver module 1002 is used to send first information, which indicates the first training conditions.

[0332] Optionally, the transceiver module 1002 is also used to send second information, which indicates the parameters of the first loss function.

[0333] Optionally, the transceiver module 1002 is also configured to send third information, the third information indicating the expected value of the first loss function, and / or indicating the expected value of at least one index of the first loss function.

[0334] Optionally, the first training condition also includes a first optimizer; the transceiver module 1002 is also used to send fourth information, which indicates the parameters of the first optimizer.

[0335] Optionally, the processing module 1001 is used to determine the first training condition, including: the processing module 1001 is used to receive fifth information through the transceiver module 1002, the fifth information indicating the second training condition, the second training condition being the training condition recommended by the first communication device; the processing module 1001 is also used to determine the first training condition based on the fifth information.

[0336] Optionally, the fifth information also indicates the training parameters associated with the second training condition; the processing module 1001 is further configured to determine the training parameters associated with the first training condition based on the training parameters associated with the second training condition; the transceiver module 1002 is further configured to send an eighth information, which indicates the training parameters associated with the first training condition.

[0337] Optionally, the processing module 1001 is used to determine the first training condition, including: the processing module 1001 is used to receive the ninth information through the transceiver module 1002, the ninth information indicating the first training condition.

[0338] When this communication device is used to implement the functions of a RAN node:

[0339] The transceiver module 1002 is configured to receive first information, which indicates training conditions and / or training parameters recommended by the terminal. The recommended training conditions include an initialization sequence and / or a loss function, and the recommended training parameters include parameters of the loss function. The processing module 1001 is configured to determine the first training conditions and / or training parameters associated with the first training conditions based on the first information. The first training conditions include a first initialization sequence and a first loss function. The transceiver module 1002 is further configured to send second information. The second information indicates the first training conditions and / or training parameters associated with the first training conditions, or it indicates a set of sequences obtained based on the first training conditions; or it indicates a first sequence, where the first sequence is a sequence from the set of sequences obtained based on the first training conditions.

[0340] When this communication device is used to implement the functions of a terminal:

[0341] The transceiver module 1002 is configured to send first information, which indicates training conditions and / or training parameters recommended by the terminal. The recommended training conditions include an initialization sequence and / or a loss function, and the recommended training parameters include parameters of the loss function. The transceiver module 1002 is also configured to receive second information. The second information indicates the first training conditions and / or the training parameters associated with the first training conditions; or, the second information indicates a set of sequences obtained according to the first training conditions; or, the second information indicates a first sequence, which is a sequence from the set of sequences obtained according to the first training conditions. The first training conditions include a first initialization sequence and a first loss function.

[0342] All relevant content of each step involved in the above method embodiments can be referenced from the functional description of the corresponding functional module, and will not be repeated here.

[0343] In this application, the communication device 100 can be presented in an integrated manner by dividing it into various functional modules. Here, "module" can refer to an application-specific integrated circuit (ASIC), a circuit, a processor and memory that executes one or more software or firmware programs, integrated logic circuits, and / or other devices that can provide the above functions.

[0344] In some embodiments, when Figure 11 When the communication device 100 is a chip or chip system, the function / implementation process of the transceiver module 1002 can be implemented through the input / output interface (or communication interface) of the chip or chip system, and the function / implementation process of the processing module 1001 can be implemented through the processor (or processing circuit) of the chip or chip system.

[0345] Since the communication device 100 provided in this embodiment can execute the above method, the technical effects it can achieve can be referred to the above method embodiment, and will not be repeated here.

[0346] As a possible product form, the RAN node, terminal, or core network equipment described in the embodiments of this application can be implemented using the following: one or more field programmable gate arrays (FPGAs), programmable logic devices (PLDs), controllers, state machines, gate logic, discrete hardware components, any other suitable circuits, or any combination of circuits capable of performing the various functions described throughout this application.

[0347] As another possible product form, the RAN node, terminal, or core network device described in the embodiments of this application can be implemented using a general bus architecture. For ease of explanation, see [link to documentation]. Figure 11 , Figure 11 This is a schematic diagram of the structure of a communication device 1100 provided in an embodiment of this application. The communication device 1100 includes a processor 1101 and a transceiver 1102. The communication device 1100 can be a RAN node, or a chip or chip system therein; or, the communication device 1100 can be a terminal, or a chip or module therein; or, the communication device 1100 can be a core network device, or a chip or chip module therein. Figure 11 Only the main components of the communication device 1100 are shown. In addition to the processor 1101 and transceiver 1102, the communication device may further include a memory 1103 and input / output devices. Figure 11 (Not indicated).

[0348] Optionally, the processor 1101 is mainly used to process communication protocols and communication data, control the entire communication device, execute software programs, and process the data of the software programs, thereby implementing the methods provided in the above-described method embodiments. The memory 1103 is mainly used to store software programs and data. The transceiver 1102 may include a radio frequency (RF) circuit and an antenna. The RF circuit is mainly used for converting baseband signals to RF signals and processing RF signals. The antenna is mainly used for transmitting and receiving RF signals in the form of electromagnetic waves. Input / output devices, such as touch screens, displays, and keyboards, are mainly used to receive user input data and output data to the user.

[0349] Optionally, the processor 1101, transceiver 1102, and memory 1103 can be connected via a communication bus.

[0350] When the communication device is powered on, the processor 1101 can read the software program in the memory 1103, execute the instructions of the software program, and process the data of the software program. When data needs to be transmitted wirelessly, the processor 1101 performs baseband processing on the data to be transmitted and outputs the baseband signal to the radio frequency (RF) circuit. The RF circuit processes the baseband signal and transmits the RF signal outward in the form of electromagnetic waves through the antenna. When data is sent to the communication device, the RF circuit receives the RF signal through the antenna, converts the RF signal into a baseband signal, and outputs the baseband signal to the processor 1101. The processor 1101 converts the baseband signal into data and processes the data.

[0351] In another implementation, the radio frequency circuitry and antenna can be set up independently of the processor performing baseband processing. For example, in a distributed scenario, the radio frequency circuitry and antenna can be arranged remotely, independent of the communication device.

[0352] In some embodiments, those skilled in the art will recognize that the above-described communication device 100 can be implemented in hardware using... Figure 10 The communication device 1100 shown is in the form of this device.

[0353] As an example, Figure 11 The function / implementation process of the processing module 1001 can be achieved through... Figure 10 The processor 1101 in the communication device 1100 shown calls computer execution instructions stored in memory 1103 to implement the function. Figure 11 The function / implementation process of the transceiver module 1002 can be obtained through Figure 12 This is achieved through the transceiver 1102 in the communication device 1100 shown.

[0354] As another possible product form, the RAN node, terminal, or core network equipment in this application can adopt... Figure 12The shown composition structure, or including Figure 12 The components shown. Figure 12 The present application provides a schematic diagram of the composition of a communication device 1200, which can be a RAN node or a chip or system-on-a-chip in a RAN node; or, it can be a terminal or a chip or system-on-a-chip in a terminal; or, it can be core network equipment or a chip or system-on-a-chip in core network equipment.

[0355] like Figure 12 As shown, the communication device 1200 includes at least one processor 1201 and at least one communication interface. Figure 12 (This is merely an example illustration, using a communication interface 1204 and a processor 1201 as examples. Optionally, the communication device 1200 may also include a communication bus 1202 and a memory 1203.)

[0356] Processor 1201 may be a general-purpose central processing unit (CPU), a general-purpose processor, a network processor (NP), a digital signal processor (DSP), a microprocessor (e.g., x86, ARM), a microcontroller, an FPGA, a PLD, a state machine, gated logic, discrete hardware circuitry, other suitable hardware configured to perform various functions, or any combination thereof. Processor 1201 may also be other devices with processing capabilities, such as circuits, devices, or software modules, without limitation.

[0357] The communication bus 1202 is used to connect different components in the communication device 1200, enabling communication between them. The communication bus 1202 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. This bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 10 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus. For example, the communication bus 1202 may include any number of interconnect buses and bridges, depending on the specific application of the communication device and the overall design constraints. In addition, the communication bus 1202 may also link various other circuits, such as timing sources, peripherals, voltage regulators, and power management circuits.

[0358] Communication interface 1204 is used for communicating with other devices or communication networks. For example, communication interface 1204 can be a module, circuit, or any device capable of enabling communication.

[0359] As one possible implementation, the communication interface 1204 can also be an input / output interface located within the processor 1201, used to implement signal input and signal output of the processor.

[0360] As another possible implementation, communication interface 1204 can also be understood as a bus interface. It provides an interface between the communication bus and the transceiver. The transceiver can provide an interface or device for communicating with various other devices via wireless / wired transmission media. The transceiver can be coupled to an antenna array, and the transceiver and antenna array can be used together for communication with the appropriate type of network.

[0361] The memory 1203 can be a device with storage function for storing instructions and / or data. The instructions can be computer programs. For example, the memory 1203 can be a read-only memory (ROM) or other type of static storage device capable of storing static information and / or instructions; it can also be a random access memory (RAM) or other type of dynamic storage device capable of storing information and / or instructions; it can also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, universal optical discs, Blu-ray discs, etc.), magnetic disk storage media, or other magnetic storage devices, etc., without limitation.

[0362] It should be noted that the memory 1203 can exist independently of the processor 1201, or it can be integrated with the processor 1201. The memory 1203 can be located inside or outside the communication device 1200, without limitation.

[0363] The processor 1201 can be used to execute instructions stored in the memory 1203, or to execute computer programs or instructions stored in a computer-readable storage medium, to implement the methods provided in the above embodiments of this application.

[0364] Optionally, the processor 1201 and / or memory 1203 may include an artificial intelligence (AI) module, which is used to implement AI-related functions. The AI ​​module can be implemented through software, hardware, or a combination of both. For example, the AI ​​module may include a radio network intelligent controller (RIC) module. For example, the AI ​​module can be a near real-time RIC or a non-real-time RIC.

[0365] As an optional implementation, the communication device 1200 may also include an output device 1205 and an input device 1206. The output device 1205 communicates with the processor 1201 and can display information in various ways. For example, the output device 1205 may be a liquid crystal display (LCD), a light-emitting diode (LED) display device, a cathode ray tube (CRT) display device, or a projector, etc. The input device 1206 communicates with the processor 1201 and can receive user input in various ways. For example, the input device 1206 may be a mouse, keyboard, touchscreen device, or sensing device, etc.

[0366] In some embodiments, the hardware implementation will be apparent to those skilled in the art as described above. Figure 12 The communication device 100 shown can be adopted Figure 10 The communication device 1200 shown is in the form of this device.

[0367] As an example, Figure 12 The function / implementation process of the processing module 1001 can be achieved through... Figure 10 The processor 1201 in the communication device 1200 shown calls computer execution instructions stored in memory 1203 to implement the function. Figure 12 The function / implementation process of the transceiver module 1002 can be obtained through Figure 12 This is achieved through the communication interface 1204 in the communication device 1200 shown.

[0368] It should be noted that, ​ The structures shown do not constitute a specific limitation on RAN nodes, terminals, or core network equipment. For example, in other embodiments of this application, RAN nodes, terminals, or core network equipment may include more or fewer components than those shown, or combine some components, split some components, or have different component arrangements. The components shown may be implemented in hardware, software, or a combination of software and hardware.

[0369] In some embodiments, this application also provides a communication device, which includes a processor for implementing the methods in any of the above method embodiments.

[0370] As one possible implementation, the communication device also includes a memory. This memory stores necessary computer programs and data. The computer program may include instructions, which a processor can invoke to instruct the communication device to execute the methods described in any of the above method embodiments. Alternatively, the memory may not be present in the communication device.

[0371] As another possible implementation, the communication device also includes an interface circuit, which is a code / data read / write interface circuit, used to receive computer execution instructions (which are stored in memory and may be read directly from memory or may be transmitted through other devices) and transmit them to the processor.

[0372] As another possible implementation, the communication device also includes a communication interface for communicating with modules outside the communication device.

[0373] It is understood that the communication device can be a chip or a chip system. When the communication device is a chip system, it can be composed of chips or may include chips and other discrete devices. This application does not specifically limit this.

[0374] This application also provides a computer-readable storage medium having a computer program or instructions stored thereon, which, when executed by a computer, implements the functions of any of the above-described method embodiments.

[0375] This application also provides a computer program product that, when executed by a computer, implements the functions of any of the above method embodiments.

[0376] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0377] It is understood that the systems, apparatuses, and methods described in this application can also be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the couplings or direct couplings or communication connections shown or discussed may be through some interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms.

[0378] The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. The components shown as units may or may not be physical units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0379] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0380] In the above embodiments, implementation can be achieved, in whole or in part, through software, hardware, firmware, or any combination thereof. When implemented using software programs, implementation can be, in whole or in part, in the form of a computer program product. This computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device containing one or more servers, data centers, etc., that can be integrated with the medium. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid-state drive (SSD)). In this embodiment, the computer may include the aforementioned apparatus.

[0381] Although this application has been described herein in conjunction with various embodiments, those skilled in the art, by reviewing the accompanying drawings, disclosure, and appended claims, will understand and implement other variations of the disclosed embodiments in carrying out the claimed application. In the claims, the word "comprising" does not exclude other components or steps, and "a" or "an" does not exclude a plurality. A single processor or other unit can implement several functions listed in the claims. While different dependent claims may recite certain measures, this does not mean that these measures cannot be combined to produce good results.

[0382] Although this application has been described in conjunction with specific features and embodiments, it is obvious that various modifications and combinations can be made thereto without departing from the scope of this application. Accordingly, this specification and drawings are merely illustrative descriptions of the application as defined by the appended claims, and are considered to cover any and all modifications, variations, combinations, or equivalents within the scope of this application. Clearly, those skilled in the art can make various alterations and modifications to this application without departing from its scope. Thus, if such modifications and modifications fall within the scope of the claims and their equivalents, this application is also intended to include such modifications and modifications.

Claims

1. A communication method characterized by comprising: The method comprises: receiving first information, the first information indicating a first training condition, the first training condition comprising a first initialization sequence and a first loss function; determining a first sequence set according to the first training condition; sending and / or receiving a reference signal according to a first sequence in the first sequence set.

2. The method of claim 1, wherein, The first training condition is one of at least one predefined training condition.

3. The method according to claim 1 or 2, characterized in that, The first initialization sequence is one of a ZC sequence, a sequence obtained by extending a ZC sequence, a Gold sequence, or an M sequence.

4. The method of claim 3, wherein, The first initialization sequence is a Gold sequence, and the first information further indicates an initialization parameter of the Gold sequence; or The first initialization sequence is an M sequence, and the first information further indicates an initialization parameter of the M sequence.

5. The method according to any one of claims 1 to 4, characterized in that, The first loss function is related to at least one of the following indicators: a self-fuzzing peak side lobe level APSL, a cross-fuzzing peak side lobe level CPSL, a self-fuzzing integrated side lobe level AISL, a cross-fuzzing integrated side lobe level CISL, or a peak-to-average power ratio PAPR.

6. The method of claim 5, wherein, Parameters of the first loss function include at least one of the following corresponding to the at least one indicator: a weight, a constraint value, a Doppler frequency offset range, a time delay range, or a sequence sending duration.

7. The method of claim 6, wherein, The first information further indicates the parameters of the first loss function; or The method further comprises: receiving second information, the second information indicating the parameters of the first loss function.

8. The method according to any one of claims 1 to 7, characterized in that, The method further comprises: receiving third information, the third information indicating an expected value of the first loss function, and / or indicating an expected value of at least one indicator of the first loss function.

9. The method according to any one of claims 1 to 8, characterized in that, The first training condition further comprises a first optimizer.

10. The method of claim 9, wherein, Parameters of the first optimizer include at least one of the following: a learning rate, a learning rate decay value, or a momentum parameter.

11. The method according to claim 9 or 10, characterized in that, The first information further indicates the parameters of the first optimizer; or The method further comprises: receiving fourth information, the fourth information indicating the parameters of the first optimizer.

12. The method according to any one of claims 1 to 11, characterized in that, The method further comprises: sending fifth information, the fifth information indicating a second training condition, the second training condition being a training condition recommended by a first communication device.

13. The method of claim 12, wherein, The fifth information further indicates training parameters associated with the second training condition; the training parameters associated with the second training condition include parameters of a second loss function and / or parameters of a second optimizer, the second loss function being a loss function included in the second training condition, and the second optimizer being an optimizer included in the second training condition.

14. The method according to claim 12 or 13, characterized in that, The method further comprises: receiving sixth information, the sixth information indicating a training condition and / or training parameters recommended by a terminal; determining the second training condition and / or the training parameters associated with the second training condition according to the sixth information.

15. The method according to any one of claims 1 to 14, characterized in that, The method further comprises: sending seventh information, the seventh information indicating the first training condition.

16. The method of claim 15, wherein, The seventh information further indicates training parameters associated with the first training condition.

17. A method of communication, comprising: The method comprises: determining a first training condition, the first training condition comprising a first initialization sequence and a first loss function; sending first information, the first information indicating the first training condition.

18. The method of claim 17, wherein, The first information further indicates a parameter of the first loss function; or The method further includes: sending second information, the second information indicating a parameter of the first loss function.

19. The method of claim 17 or 18, wherein, The method further includes: sending third information, the third information indicating an expected value of the first loss function, and / or indicating an expected value of at least one index of the first loss function.

20. The method according to any one of claims 17-19, characterized by, The first training condition further includes a first optimizer; The first information further indicates a parameter of the first optimizer; or The method further includes: sending fourth information, the fourth information indicating a parameter of the first optimizer.

21. The method according to any one of claims 17-20, characterized by, The determination of the first training condition includes: receiving fifth information, the fifth information indicating a second training condition, the second training condition being a training condition recommended by a first communication device; determining the first training condition according to the fifth information.

22. The method of claim 21, wherein, The fifth information further indicates a training parameter associated with the second training condition; the method further includes: determining a training parameter associated with the first training condition according to the training parameter associated with the second training condition; sending eighth information, the eighth information indicating the training parameter associated with the first training condition.

23. The method according to any one of claims 17-20, characterized by, The determination of the first training condition includes: receiving ninth information, the ninth information indicating the first training condition.

24. A method of communication, comprising: The method includes: receiving first information, the first information indicating a training condition and / or a training parameter recommended by a terminal, the training condition recommended by the terminal including an initialization sequence and / or a loss function, the training parameter recommended by the terminal including a parameter of the loss function; determining a first training condition and / or a training parameter associated with the first training condition according to the first information, the first training condition including a first initialization sequence and a first loss function; sending second information; wherein the second information indicates the first training condition and / or the training parameter associated with the first training condition, or the second information indicates a sequence set obtained according to the first training condition, or the second information indicates a first sequence, the first sequence being one sequence in the sequence set obtained according to the first training condition.

25. A method of communication, comprising: The method includes: sending first information, the first information indicating a training condition and / or a training parameter recommended by a terminal, the training condition recommended by the terminal including an initialization sequence and / or a loss function, the training parameter recommended by the terminal including a parameter of the loss function; receiving second information; wherein the second information indicates a first training condition and / or a training parameter associated with the first training condition, or the second information indicates a sequence set obtained according to the first training condition, or the second information indicates a first sequence, the first sequence being one sequence in the sequence set obtained according to the first training condition; the first training condition including a first initialization sequence and a first loss function.

26. The method of claim 24 or 25, wherein, The training condition recommended by the terminal and the first training condition are the same or different; or The training parameter recommended by the terminal and the training parameter associated with the first training condition are the same or different.

27. A communications device, characterized by The communication device comprises a processor; the processor is configured to run computer programs or instructions, so that the communication device performs the method according to any one of claims 1-16, or so that the communication device performs the method according to any one of claims 17-23, or so that the communication device performs the method according to any one of claims 24-26.

28. A computer-readable storage medium, characterized in that, A computer readable storage medium stores computer instructions or programs, when the computer instructions or programs are run on a computer, so that the method according to any one of claims 1-16 is performed, or so that the method according to any one of claims 17-23 is performed, or so that the method according to any one of claims 24-26 is performed.

29. A computer program product, characterised in that, The computer program product comprises computer instructions; when part or all of the computer instructions are run on a computer, so that the method according to any one of claims 1-16 is performed, or so that the method according to any one of claims 17-23 is performed, or so that the method according to any one of claims 24-26 is performed.

Images