Data transmission method and electronic equipment

Abstract

A data transmission method and an electronic device, which relate to the technical field of communications, can reduce the overhead consumed by reporting an RSRP value to a second device by a first device, and are applied to the first device, the method comprising: obtaining a first reference signal received power (RSRP) set through first beam scanning; reporting a first reference RSRP value, wherein the first reference RSRP value is determined from the first RSRP set; obtaining a second RSRP set through second wave beam scanning; reporting a first differential RSRP set according to the second RSRP set and the first reference RSRP value; wherein the first differential RSRP set is obtained by performing differential calculation on the RSRP value in the second RSRP set and the first reference RSRP value.

Description

Technical Field

[0001] The present application relates to the field of communication technology, and in particular to a data transmission method and an electronic device. Background Art

[0002] Devices with communication functions can establish communication connections by means of beam scanning. A device with communication functions (such as a network device, etc.) sends out multiple downlink beams, and another device with communication functions (such as a terminal device, etc.) sends out multiple uplink beams. The aligned uplink beams and downlink beams form a beam pair. The terminal device can obtain the reference signal received power (RSRP) value of the beam pair, and select a preset number of beam pairs with the largest RSRP value, and report the RSRP value of the selected beam pair to the network device. The network device selects a beam pair from the beam pairs that report RSRP values ​​to establish a connection with the terminal device. Reporting the RSRP value consumes a large amount of overhead.

[0003] In the related art, a method is proposed in which a terminal device reports a differential RSRP value by differentiating the RSRP value. For example, each time the terminal device reports the RSRP values ​​corresponding to 5 beams, the largest RSRP value among the 5 beam pairs is used as the reference RSRP value, and the remaining 4 RSRP values ​​are respectively differentiated from the reference RSRP value to obtain the RSRP differential measurement value. The terminal device reports the reference RSRP value and the report value corresponding to the 4 RSRP differential measurement values, thereby reporting the RSRP value overhead.

[0004] However, this method of reporting RSRP values ​​still wastes overhead. Summary of the invention

[0005] The present application provides a data transmission method and an electronic device, which can reduce the overhead consumed by a first device in reporting an RSRP value to a second device.

[0006] In order to achieve the above objectives, the embodiments of the present application provide the following technical solutions:

[0007] In a first aspect, a data transmission method is provided, which is applied to a first device, and the method includes: obtaining a first reference signal received power RSRP set through a first beam scanning; reporting a first reference RSRP value, which is determined from the first RSRP set; obtaining a second RSRP set through a second beam scanning; reporting a first differential RSRP set based on the second RSRP set and the first reference RSRP value; wherein the first differential RSRP set is obtained by differentially calculating the RSRP value in the second RSRP set and the first reference RSRP value.

[0008] Based on the above scheme, when the first device reports the RSRP value, it can perform differential calculation on the RSRP value to be reported based on the reference RSRP value selected last time, and report the first differential RSRP set obtained by the differential calculation. The first differential RSRP set occupies less overhead, thereby saving the overhead of reporting the RSRP value.

[0009] In a possible implementation, reporting the first reference RSRP value includes: reporting the first reference RSRP value and a second differential RSRP set; the second differential RSRP set is obtained by differentially calculating the RSRP value other than the first reference RSRP value in the first RSRP set and the first reference RSRP value.

[0010] Based on the above possible implementation methods, the first device reports the first reference RSRP value and the second differential RSRP set, the second device can receive the first reference RSRP value and the second differential RSRP set, and input the first reference RSRP value, the second differential RSRP set and the first differential RSRP set into the AI ​​model to predict the RSRP value or the optimal beam at a future time, thereby facilitating the second device to select the optimal beam at a future time.

[0011] In a second aspect, a data transmission method is provided, which is applied to a second device, and the method includes: receiving a first reference RSRP value, wherein the first reference RSRP value is determined by the first device from a first RSRP set obtained by a first beam scan; receiving a first differential RSRP set; the first differential RSRP set is obtained by the first device performing a differential calculation between an RSRP value in a second RSRP set obtained by the first device through a second beam scan and the first reference RSRP value; obtaining the second RSRP set based on the first reference RSRP value and the first differential RSRP set; wherein the second RSRP set is obtained by the second device performing a reverse differential calculation between the RSRP value in the first differential RSRP set and the first reference RSRP value.

[0012] In one possible implementation, the method also includes: receiving a second differential RSRP set; the second differential RSRP set is obtained by differentially calculating the RSRP values ​​other than the first reference RSRP value in the first RSRP set by the first device and the first reference RSRP value; the second differential RSRP set, the first differential RSRP set and the first reference RSRP value are used to input an artificial intelligence AI model; or, according to the first reference RSRP value and the second differential RSRP set, the first RSRP set is obtained; wherein the RSRP values ​​other than the first reference RSRP value in the first RSRP set are obtained by reverse differentially calculating the RSRP values ​​in the second differential RSRP set and the first reference RSRP value; the first RSRP set and the second RSRP set are used to input an AI model.

[0013] It can be understood that the beneficial effects that can be achieved by the method provided in the above second aspect can refer to the beneficial effects in the first aspect and possible implementation methods provided above, and will not be repeated here.

[0014] According to a third aspect, a data transmission method is provided, which is applied to a first device, and the method includes: obtaining a first RSRP set through a first beam scanning; obtaining a second RSRP set through a second beam scanning; obtaining a predicted RSRP set according to the first RSRP set and the second RSRP set; wherein the number of the predicted RSRP sets is multiple, and the multiple predicted RSRP sets include a first predicted RSRP set and a second predicted RSRP set; according to the first predicted RSRP set, reporting a second reference RSRP value; the second reference RSRP value is determined from the first predicted RSRP set; according to the second predicted RSRP set and the second reference RSRP value, reporting a first target differential RSRP set; the first target differential RSRP set is obtained by differentially calculating the RSRP value in the second predicted RSRP set and the second reference RSRP value.

[0015] Based on the above scheme, when the first device reports the predicted RSRP value, it can perform differential calculation on the predicted RSRP value to be reported based on the second reference RSRP value selected last time, and report the first target differential RSRP set obtained by the differential calculation. The first target differential RSRP set occupies less overhead, thereby saving the overhead of reporting the RSRP value.

[0016] In a possible implementation, reporting a second reference RSRP value according to the first predicted RSRP set includes: reporting a second reference RSRP value and a second target differential RSRP set according to the first predicted RSRP set; the second target differential RSRP set is obtained by differentially calculating the RSRP value other than the second reference RSRP value in the first predicted RSRP set and the second reference RSRP value.

[0017] Based on the above possible implementation methods, the first device reports the second reference RSRP value and the second target differential RSRP set, the second device can receive the reference RSRP value and the second differential RSRP set, and judge whether the RSRP value predicted by the first device meets the preset conditions based on the first reference RSRP value, the second differential RSRP set and the first differential RSRP set, thereby facilitating the second device to select the optimal beam at a future moment.

[0018] In a possible implementation, obtaining a predicted RSRP set according to the first RSRP set and the second RSRP set includes: obtaining the predicted RSRP set by predicting through an AI model according to the first RSRP set and the second RSRP set.

[0019] In a fourth aspect, a data transmission method is provided, which is applied to a second device, and the method includes: receiving a second reference RSRP value; the second reference RSRP value is determined by the first device from a first predicted RSRP set; the first predicted RSRP set is in the predicted RSRP set; the predicted RSRP set is predicted by the first device based on the first RSRP set and the second RSRP set; according to the second reference RSRP value, a first predicted RSRP set is obtained; receiving a first target differential RSRP set; the first target differential RSRP set is obtained by differentially calculating the RSRP value in the second predicted RSRP set and the second reference RSRP value; the second predicted RSRP set is in the predicted RSRP set; according to the second reference RSRP value and the first target differential RSRP set, a second predicted RSRP set is obtained; wherein, the second predicted RSRP set is obtained by inversely differentially calculating the RSRP value in the first target differential RSRP set and the second reference RSRP value.

[0020] In a possible implementation, the method also includes: receiving a second target differential RSRP set; the second target differential RSRP set is obtained by differentially calculating the RSRP value other than the second reference RSRP value in the first predicted RSRP set and the second reference RSRP value by the first device; obtaining the first predicted RSRP set according to the second reference RSRP value includes: obtaining the first predicted RSRP set according to the second reference RSRP value and the second target differential RSRP set; wherein the RSRP value other than the second reference RSRP value in the first predicted RSRP set is obtained by reversely differentially calculating the RSRP value in the second target differential RSRP set and the second reference RSRP value.

[0021] In a fifth aspect, an electronic device is provided, comprising a memory and a processor; the memory and the processing unit are coupled; the memory is used to store computer program code, the computer program code comprising computer instructions, and when the processing unit executes the computer instructions, the electronic device executes the method described in the first aspect and any one of its implementations.

[0022] In a sixth aspect, a chip system is provided, comprising: a processor and an interface circuit; the processor and the interface circuit are interconnected via a line; the interface circuit is used to read instructions stored in a memory, and when the instructions are executed by the processor, the chip system executes the method described in the first aspect and any one of its implementations.

[0023] In a seventh aspect, a chip system is provided, the chip system including a processor for supporting an electronic device to implement the functions involved in the first aspect. In a possible design, the chip system also includes a memory for storing program instructions and data necessary for the electronic device. The chip system may be composed of a chip, or may include a chip and other discrete devices.

[0024] In an eighth aspect, an electronic device is provided, which has the function of implementing any one of the methods in the first aspect. The function can be implemented by hardware, or by hardware executing corresponding software. The hardware or software includes one or more modules corresponding to the above functions.

[0025] In a ninth aspect, an electronic device is provided, comprising: a processor; the processor is used to couple with a memory, and after reading instructions in the memory, execute any method as described in the first aspect above according to the instructions.

[0026] In a tenth aspect, a computer-readable storage medium is provided, comprising computer instructions. When the computer instructions are executed on an electronic device, the electronic device executes the method as described in the first aspect and any one of its implementations.

[0027] It can be understood that the beneficial effects that can be achieved by the method provided in the fourth aspect can refer to the beneficial effects in the third aspect and any possible implementation provided above. The beneficial effects that can be achieved by the device and computer-readable storage medium provided in the fifth to tenth aspects can refer to the beneficial effects in the first aspect, the third aspect and any possible implementation provided above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 A schematic diagram of narrow beam and wide beam;

[0029] Figure 2 is another schematic diagram of narrow beam and wide beam;

[0030] Figure 3 A flowchart of beam management is shown;

[0031] Figure 4 Schematic diagram of RSRP reporting for a terminal;

[0032] Figure 5 A schematic diagram of transmitting multiple RSRP messages to a terminal;

[0033] Figure 6 Schematic diagram of neuron structure;

[0034] Figure 7 Schematic diagram of the layer relationship of the neural network;

[0035] Figure 8 A flowchart of AI-based beam prediction;

[0036] Fig. 9 This is a schematic diagram of a second entity reporting an RSRP set to a first entity in an embodiment of the present application;

[0037] Fig.10 A schematic diagram of the architecture of a communication system provided in an embodiment of the present application;

[0038] Fig.11A A schematic diagram of the architecture of another communication system provided in an embodiment of the present application;

[0039] Fig. 11B A schematic diagram of the hardware structure of a communication device provided in an embodiment of the present application;

[0040] Fig.12A schematic diagram of a data transmission method according to an embodiment of the present application;

[0041] Fig.13 Another schematic diagram of a data transmission method according to an embodiment of the present application;

[0042] Fig.14 Another schematic diagram of a data transmission method according to an embodiment of the present application;

[0043] Fig.15 Another schematic diagram of a data transmission method according to an embodiment of the present application;

[0044] Fig.16 A schematic diagram of the structure of a communication device provided in an embodiment of the present application;

[0045] Fig.17 A schematic diagram of the structure of a chip system provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] The terms "first", "second", "first time" and "second time" in the description and drawings of the embodiments of the present application are used to distinguish different objects, or to distinguish different processing of the same object, rather than to describe the specific order of objects. Before the processing of the object is performed for the "first time", it may also include one or more processing of the object.

[0047] In addition, the terms "including" and "having" and any variations thereof mentioned in the description of the present application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but may optionally include other steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0048] It should be noted that, in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0049] To facilitate understanding of the technical solutions provided in the embodiments of the present application, first, the technical terms involved in the embodiments of the present application are introduced:

[0050] 1. Beam

[0051] A beam is a communication resource. Communication can be achieved by transmitting information between base stations, terminals and other communication devices through beams. With the development of communication technology, the spectrum of beams used for communication between communication devices has gradually evolved to high frequency bands. Due to the physical transmission characteristics of the beam, the free space transmission loss and penetration loss of high frequency band beams are significantly higher than those of low frequency band beams. In order to compensate for the above disadvantages, larger antenna arrays are often used in high frequency bands to counteract the attenuation of the received beam energy caused by losses. A wide beam can be obtained through antenna beamforming technology, or the energy can be concentrated in a narrower beam to form a narrow beam. Refer to Figure 1-Figure 2 , wide beams have a wider coverage area and a shorter coverage distance. Compared with wide beams, narrow beams have a longer coverage distance. Shaping the beam into a narrow beam can increase the energy of the signal reaching the receiving end and counteract the loss of beam energy due to the path.

[0052] 2. Reference signal

[0053] Reference signal (RS) is also called reference signal or pilot signal. Reference signal includes at least one of the following: synchronization signal block (SSB) and channel state information reference signal (CSI-RS). In the existing standards, wide beam is sent by configuring SSB, and narrow beam is sent by configuring CSI-RS.

[0054] SSB is a cell broadcast signal, which includes at least one of the following: primary synchronization signal (PSS), secondary synchronization signal (SSS), physical broadcast channel (PBCH) and demodulation reference signal (DMRS). In addition, SSB is not only used for beam management, but also can be used to achieve initial access, time-frequency synchronization and other functions.

[0055] The CS I-RS signal is a user-level signal. The network side sends one or more groups of CS I-RS signals according to actual conditions.

[0056] 3. Beam management

[0057] Two communication entities can communicate through a beam pair, and the process of establishing and maintaining a beam pair between two communication entities can be called beam management. Exemplarily, a first entity (such as a base station) selects a suitable transmit beam, and a second entity (such as a terminal) selects a suitable receive beam. The transmit beam and the receive beam form a set of beam pairs, and the base station and the terminal can maintain a communication connection through the beam pair.

[0058] Reference Figure 3 , beam management can include processes such as beam training, beam maintenance, and beam failure recovery (also called beam recovery). In scenarios such as terminal movement, the original beam pair may be blocked, making it impossible for the terminal and the base station to maintain the original communication connection. In this case, the terminal and the base station may not be able to quickly restore the connection of the beam pair through beam adjustment. The beam failure recovery process can be used to quickly select and establish another set of beam pairs.

[0059] 3.1 Beam Scanning

[0060] Due to hardware limitations of the base station, in some cases, multiple beams cannot be sent simultaneously to cover the entire cell. That is, the base station can send a beam in a certain direction at a certain time, and send different beams at multiple times to cover the entire cell with multiple beams. In order to select the beam that best suits it, the terminal needs to scan a large number of beams sent by the base station. Since narrow beams have a long coverage distance and a narrow coverage range, compared with scanning wide beams, the terminal needs to scan more narrow beams, which increases the overhead of the terminal for beam scanning.

[0061] In order to reduce the overhead consumed by beam scanning, the related technology adopts a layered scanning method, first scanning a wide beam and then scanning a narrow beam, thereby reducing the number of scanned beams in each beam scan and reducing the total overhead consumed by beam scanning.

[0062] For example, Figure 3 , the terminal can feedback the measurement result of the RSRP value of the wide beam sent by the base station. The terminal scans the wide beam, obtains the RSRP corresponding to the corresponding wide beam, and reports the RSRP to the base station. The base station can determine the identifier of the wide beam with a larger RSRP from the received RSRP. For example, the base station sends wide beam 1, wide beam 2, and wide beam 3. The terminal scans wide beam 1, wide beam 2, and wide beam 3, obtains the RSRP value after scanning wide beam 1, the RSRP value after scanning wide beam 2, and the RSRP value after scanning wide beam 3, and reports the above RSRP values ​​to the base station. The base station can select the beam with a larger RSRP value based on the RSRP value of wide beam 1, the RSRP value of wide beam 2, and the RSRP value of wide beam 3, and obtain the identifier of the beam.

[0063] The base station configures one or more groups of CSI-RS, where one or more groups of CSI-RS form a group of narrow beams. The base station configures one or more groups of CSI-RS resources in the direction of the wide beam with larger RSRP and sends a narrow beam. The terminal scans the narrow beam, obtains the RSRP value corresponding to the corresponding narrow beam, and reports the RSRP value of the narrow beam to the base station. The base station can determine the identifier of the narrow beam with larger RSRP based on the received RSRP. In addition, the CSI-RS signal is not only used for beam management, but also for channel quality measurement, etc.

[0064] The following is an introduction to the RSRP reporting mode. Figure 4 , Figure 4 Schematic diagram of RSRP reporting for a terminal. The RSRP reporting mode defined in the existing standard 3rd generation partnership project (3GPP) 38.133 is differential reporting, that is, the communication device selects a maximum RSRP as a reference RSRP (also referred to as an RSRP tag) in the RSRP set that needs to be reported each time, and the other RSRPs in the RSRP set are differentially calculated with the reference RSRP to obtain a differential RSRP value, which is called an RSRP differential value, and can also be referred to as an RSRP differential measurement value, or an RSRP measurement value. The communication device receiving the RSRP set can determine the beam to which the RSRP value belongs according to the identifier of the beam corresponding to each RSRP value. Exemplarily, the identifier of the beam can be a CSI reference signal resource indicator (CSI-RS re source indicator, CRI). Referring to Table 1, Table 1 is an example of a differential accuracy list of RSRP. According to the RSRP differential measurement value (ΔRSRP), the corresponding RSRP report value in Table 1 is obtained, and the terminal reports the reference RSRP value and the RSRP report value. Optionally, when the differential RSRP value exceeds the range of the measured value, the differential RSRP value may not be transmitted.

[0065] In this RSRP reporting mode, the reference RSRP is reported with high precision, occupying 7 bits of overhead, and the differential RSRP is reported with low precision, occupying 4 bits of overhead.

[0066] Table 1 RSRP differential accuracy list

[0067]

[0068]

[0069] Exemplarily, the RSRP set that the terminal needs to report includes RSRP1-RSRP4, where RSRP1-RSRP4 are -50dBm, -70dBm, -75dBm and -90dBm respectively. RSRP 1 with the largest RSRP value is taken as the reference RSRP, the RSRP2 measurement value obtained by differentiating RSRP2 from RARP1 is -20, the RSRP3 measurement value obtained by differentiating RSRP3 from RARP1 is -25, and the RSRP4 measurement value obtained by differentiating RSRP4 from RARP 1 is -40. Referring to Table 1, the RSRP2 report value is DIFFRSRP_9, the RSRP3 report value is DIFFRSRP_12, and the RSRP4 report value is DIFFRSRP_15, where DIFFRSRP_15 may indicate that the RSRP report value exceeds the range of RSRP differential accuracy. Refer to Table 1. Figure 5 , Figure 5 The schematic diagram of a terminal transmitting multiple RSRP messages. The terminal reports RSRP1-RSRP3, with the reported RSRP1 occupying 7 bits, and RSRP2 and RSRP3 occupying 4 bits respectively.

[0070] According to the above RSRP reporting method, each time the terminal reports the RSRP set, it needs to select a reference RSRP that occupies 7 bits of overhead from the RSRP set. That is, if the number of RSRPs in the RSRP set is 4, it is necessary to occupy 7 bits of overhead to transmit the reference RSRP, and occupy 3×4 bits (each RSRP report value occupies 4 bits) to transmit the report values ​​of the other 3 RSRPs, consuming a total of 7+3×4=19 bits.

[0071] 3.2 Beam Selection

[0072] The terminal can determine the transmission beam corresponding to the beam pair with the largest RSRP as the working beam among the multiple beams obtained by scanning. The terminal and the base station can establish a beam pair in the direction of the beam and perform subsequent communications through the established beam pair. The process of the terminal determining the working beam among the multiple beams obtained by beam scanning can be called beam selection.

[0073] 4. AI Model

[0074] In order to reduce the overhead of beam scanning, another related technology also proposes a beam management method using artificial intelligence (AI) technology. Through artificial intelligence technology, the parameters of the beam at a future moment are predicted based on the parameters of the beam already obtained by beam scanning, thereby reducing the beam scanning at a future moment.

[0075] AI model is a kind of mathematical algorithm model that uses machine learning ideas to solve practical problems. According to the problem solved by the AI ​​model, data is input into the AI ​​model to obtain the output of the AI ​​model for the problem solved. Machine learning can be divided into supervised learning, unsupervised learning, reinforcement learning, etc. Deep neural network (DNN) is a specific implementation form of machine learning. According to the way the network is constructed, DNN can be divided into feedforward neural network (FNN), convolutional neural network (CNN) and recurrent neural network (RNN).

[0076] Supervised learning uses machine learning algorithms to learn the mapping relationship from sample values ​​to sample labels based on the collected sample values ​​and sample labels, and uses machine learning models to express the learned mapping relationship. The process of training a machine learning model is the process of learning this mapping relationship. For example, in signal detection, the received signal containing noise is the sample, and the real constellation point corresponding to the signal is the label. Machine learning expects to learn the mapping relationship between samples and labels through training, that is, to make the machine learning model learn a signal detector. During training, the model parameters are optimized by calculating the error between the model's predicted value and the real label. Once the mapping relationship is learned, the learned mapping can be used to predict each new sample label. The mapping relationship learned by supervised learning can include linear mapping and nonlinear mapping. According to the type of label, the learning task can be divided into classification task and regression task.

[0077] Unsupervised learning is based only on the collected sample values, using algorithms to discover the inherent patterns of samples. There is a type of algorithm in unsupervised learning that uses the sample itself as a supervisory signal, that is, the model learns the mapping relationship from sample to sample, which is called self-supervised learning. During training, the model parameters are optimized by calculating the error between the model's predicted value and the sample itself. Self-supervised learning can be used in applications such as signal compression and decompression recovery. Common algorithms include autoencoders and adversarial generative networks.

[0078] Reinforcement learning is different from supervised learning. It is a type of algorithm that learns problem-solving strategies by interacting with the environment. Unlike supervised and unsupervised learning, reinforcement learning problems do not have clear "correct" action label data. The algorithm needs to interact with the environment to obtain reward signals from the environment, and then adjust the decision-making actions to obtain a larger reward signal value. For example, in downlink power control, the reinforcement learning model adjusts the downlink transmission power of each user according to the total system throughput fed back by the wireless network, and then expects to obtain a higher system throughput. The goal of reinforcement learning is also to learn the mapping relationship between the state of the environment and the optimal decision action. However, because the label of the "correct action" cannot be obtained in advance, the network cannot be optimized by calculating the error between the action and the "correct action". Reinforcement learning training is achieved through iterative interaction with the environment.

[0079] Deep neural network (DNN) is a specific implementation form of machine learning. According to the universal approximation theorem, neural networks can theoretically approximate any continuous function, which enables neural networks to have the ability to learn any mapping. Traditional communication systems require rich expert knowledge to design communication modules, while deep learning communication systems based on DNN can automatically discover implicit pattern structures from large data sets, establish mapping relationships between data, and achieve performance that is superior to traditional modeling methods.

[0080] The idea of ​​DNN comes from the neuron structure of brain tissue. Each neuron performs a weighted sum operation on its input value, and the weighted sum result generates an output through a nonlinear function, such as Figure 6 As shown, Figure 6 is a schematic diagram of the neuron structure. Specifically, assuming that the input of the neuron is x = [x0,...,x n ], and the weight corresponding to the input is d=[d0,...,d n ], the weighted sum bias is b, the form of nonlinear function can be diversified, an example is the max{0, x} maximum function. Then the effect of a neuron's execution can be DNN generally has a multi-layer structure. Each layer of DNN can contain multiple neurons. The input layer passes the received values ​​to the middle hidden layer after being processed by neurons. Similarly, the hidden layer passes the calculation results to the final output layer to generate the final output of DNN, such as Figure 7 As shown, Figure 7 Schematic diagram of the layer relationship of the neural network.

[0081] DNN generally has more than one hidden layer, and the hidden layer often directly affects the ability to extract information and fit functions. Increasing the number of hidden layers of DNN or expanding the width of each layer can improve the function fitting ability of DNN. The weighted value in each neuron is the parameter of the DNN network model. The model parameters are optimized through the training process, so that the DNN network has the ability to extract data features and express mapping relationships. DNN generally uses supervised learning or unsupervised learning strategies to optimize model parameters.

[0082] According to the way the network is constructed, DNN can be divided into feedforward neural network (FNN), convolutional neural network (CNN) and recurrent neural network (RNN). Figure 7 The figure shows an FNN network, which is characterized by that neurons in adjacent layers are fully connected to each other, which usually requires a large amount of storage space and leads to high computational complexity.

[0083] CNN is a neural network that is specifically designed to process data with a grid-like structure. For example, time series data (discrete sampling on the time axis) and image data (discrete sampling on two dimensions) can be considered to be data with a grid-like structure. CNN does not use all the input information for calculations at once, but uses a fixed-size window to intercept part of the information for convolution operations, which greatly reduces the amount of calculation of model parameters. In addition, depending on the type of information intercepted by the window (for example, people and objects in a picture are different types of information), each window can use different convolution kernel operations, which enables CNN to better extract the features of the input data.

[0084] RNN is a type of DNN network that uses feedback time series information. Its input includes the new input value at the current moment and its own output value at the previous moment. RNN is suitable for obtaining sequence features that are correlated in time, and is particularly suitable for applications such as speech recognition and channel coding.

[0085] The above-mentioned FNN, CNN, and RNN are common neural network structures, which are all constructed based on neurons. As mentioned above, each neuron performs a weighted sum operation on its input values, and the weighted sum result generates an output through a nonlinear function. We call the weights of the weighted sum operation of neurons in the neural network and the nonlinear function the parameters of the neural network. Take the neuron with max{0, x} as the nonlinear function as an example, The parameters of the operated neuron are weights d = [d0, ..., d n]The weighted sum is biased by b, and the nonlinear function max{0,x}. The parameters of all neurons in a neural network constitute the parameters of this neural network.

[0086] 5. AI-based beam prediction

[0087] Reference Figure 8 , Figure 8 Figure 1 is a flowchart of AI-based beam prediction. When a terminal moves along a certain trajectory at a certain speed, it will perform beam scanning at one or more sampling points on the trajectory (such as the location of the terminal). Each beam scan can obtain multiple RSRP values, and all or part of the RSRP values ​​in the multiple RSRP values ​​can constitute an RSRP set. The terminal or base station uses the AI ​​model to predict the RSRP set obtained by the beam scan to predict the optimal beam of the terminal at the sampling point on the trajectory at a future moment. The above beam prediction is called AI-based beam prediction.

[0088] Especially when using AI-based time domain beam management, the terminal is required to report the RSRP set multiple times and continuously, and adopt the reporting mode of differential reporting of RSRP in the related technology. Each time the RSRP set is reported, the reporting overhead is fixed.

[0089] Based on this, an embodiment of the present application provides a data transmission method, in which the second entity performs a differential operation on the RSRP value in the RSRP set and the previously reported reference RSRP value to obtain an RSRP differential measurement value set, and the second entity reports the RSRP differential measurement value set to reduce the overhead occupied by reporting the RSRP value. Fig. 9 When the second entity reports the RSRP set to the first entity, it only needs to report the reference RSRP value in the first report, instead of selecting the reference RSRP value each time the RSRP set is reported after the first report, thereby reducing the overhead occupied by the reference RSRP value over the RSRP differential measurement value, that is, reducing the overhead consumed in the beam training process. For example, Fig. 9 , the reference RSRP value and three RSRP report values ​​are reported for the first time, and four RSRP report values ​​are reported for the second, third, fourth, and other subsequent RSRP values. Among them, the RSRP report value reported subsequently is obtained by differential calculation based on the RSRP value reported for the first time and the RSRP value to be reported each time thereafter.

[0090] The RSRP differential measurement value set is a set of RSRP differential measurement values ​​obtained by differentiating the RSRP value in the RSRP set from the reference RSRP value.

[0091] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application. Among them, in the description of the present application, unless otherwise specified, " / " indicates that the objects associated before and after are in an "or" relationship, for example, A / B can represent A or B; "and / or" in the present application is only a description of the association relationship of the associated objects, indicating that there can be three relationships, for example, A and / or B, which can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. And, in the description of the present application, unless otherwise specified, "multiple" refers to two or more than two. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can represent: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple. In addition, in order to clearly describe the technical solutions of the embodiments of the present application, in the embodiments of the present application, words such as "first" and "second" are used to distinguish the same items or similar items with substantially the same functions and effects. Those skilled in the art can understand that words such as "first" and "second" do not limit the quantity and execution order, and words such as "first" and "second" do not necessarily limit the difference.

[0092] The network architecture and business scenarios described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. A person of ordinary skill in the art can appreciate that with the evolution of the network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0093] The technical solution of the embodiment of the present application can be applied to the fifth generation (5th generation, 5G) system or the new radio (new radio, NR) system. The technical solution of the embodiment of the present application can also be applied to other communication systems. For example: the evolution system of the NR system, the LTE system, the LTE frequency division duplex (frequency division duplex, FDD) system, the LTE time division duplex (time division duplex, TDD) system, the universal mobile telecommunication system (universal mobile telecommunication system, UMTS), the world-wide interoperability for microwave access (worldwide interoperability for microwave access, WiMAX) communication system, etc. Among them, the 5G system involved in the present application includes a non-standalone (NSA) NR system or a standalone (SA) NR system. The technical solution provided in the present application can also be applied to future communication systems, such as the sixth generation mobile communication system. The communication system can also be a land public mobile communication network (public land mobile network, PLMN) network, a D2D communication system, a machine to machine (machine to machine, M2M) communication system, an Internet of Things (Internet of Things, IoT) communication system or other communication systems.

[0094] Fig.10 A schematic diagram of the architecture of a communication system corresponding to the data transmission method provided in an embodiment of the present application. Fig.10 The communication system used in the embodiment of the present application only needs to have a first entity and a second entity, and the first entity and the second entity can send data to each other. The entity can be a device, a module, a device, etc., such as a communication device. The communication device can include a network device, a terminal device, etc.

[0095] A network device refers to an entity on the network side for transmitting or receiving signals. The network device may be a network unit, such as a base station (BS), or a device in a network unit, such as a chip (system) or other parts or components in a base station, or a device including a network device, which is not limited in this application. The network device may include a sending module, a receiving module, a processing module, a storage module, and the like. The network side may have an AI module, such as a processing module based on a neural network model. The network device may obtain the processing results of the AI ​​module. Among them, the AI ​​module may be set in the network device or may be set separately from the network device, which is not specifically limited in this embodiment of the present application.

[0096] A terminal device, also known as user equipment (UE), or terminal for short, refers to an entity on the user side for transmitting or receiving signals, such as a mobile phone, a vehicle-mounted device, etc. The terminal device may include a sending module, a receiving module, a processing module, a storage module, etc. The user side may have an AI module, such as a processing module based on a neural network model. The terminal device can obtain processing results based on the AI ​​module. Among them, the AI ​​module can be set in the terminal device or separately from the terminal device, and the embodiments of the present application do not specifically limit this.

[0097] The above-mentioned processing module based on the neural network model can realize functions such as beamforming, feature extraction, feature analysis, channel modeling, etc. based on the neural network model.

[0098] The first entity and the second entity can send data through a physical channel, which may be a physical downlink control channel (PDCCH), a physical downlink shared channel (PDSCH), a physical uplink shared channel (PUSCH), a physical uplink control channel (PUCCH), a physical side link control channel (PSCCH) or a physical side link shared channel (PSSCH), etc.

[0099] For example, refer to Fig.11A The communication system includes 1 first entity and 6 second entities. The first entity is a network device and the second entity is a terminal. The terminals are terminal 1 to terminal 6. In the system, the terminal can send uplink data to the network device, and the network device receives uplink data from the terminal. The network device can send configuration information to the terminal and configure the parameters of the terminal through the configuration information.

[0100] For example, refer to Fig.11A , terminals 4 to 6 can also constitute a communication system, in which case the first entity and the second entity are both terminals. In the system constituted by terminals 4 to 6, terminal 5 is the first entity, and terminals 4 and 6 are the second entities. Terminals 4 and 6 send data to terminal 5, and terminal 5 receives data sent by terminals 4 and 6. For example, in a car networking system, terminal 5 can be the central control of the vehicle, terminal 4 can be a display screen, and terminal 6 can be a Bluetooth speaker.

[0101] The terminal or network device in the embodiment of the present application can be Fig. 11B The communication device of the described structure is implemented. Fig. 11B The hardware structure diagram of the communication device provided in the embodiment of the present application is shown in FIG. 400 . The communication device 400 includes at least one processor 401 , a memory 403 and at least one communication interface 404 . The memory 403 may also be included in the processor 401 .

[0102] The processor 401 may be composed of one or more processing units, which may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the present application.

[0103] There are communication lines between the above components for transmitting information between the components.

[0104] Communication interface 404, used to communicate with other devices. In the embodiment of the present application, the communication interface can be a module, a circuit, an interface or other device capable of implementing a communication function, used to communicate with other devices. Optionally, the communication interface can be an independently arranged transmitter, which can be used to send information to other devices, and the communication interface can also be an independently arranged receiver, which is used to receive information from other devices. The communication interface can also be a component that integrates the functions of sending and receiving information, and the embodiment of the present application does not limit the specific implementation of the communication interface.

[0105] The memory 403 may be a read-only memory (ROM) or other types of storage modules that can store static information and instructions, a random access memory (RAM) or other types of storage modules that can dynamically store information and instructions, or an electrically erasable programmable read-only memory (EEPROM), an optical disk, a magnetic disk or other magnetic storage device. The memory may be independent and connected to the processor via a communication line. The memory may also be integrated with the processor.

[0106] The memory 403 is used to store computer-executable instructions, and the computer-executable instructions can be called by one or more processing units in the processor 401 to execute corresponding steps in each method provided in the following embodiments.

[0107] Optionally, the computer-executable instructions in the embodiments of the present application may also be referred to as application code, instructions, computer program or other names, which are not specifically limited in the embodiments of the present application.

[0108] In a specific implementation, as an embodiment, the communication device 400 may include multiple processors, such as Fig. 11B401 and processor 407 in the embodiment. Each of these processors may be a single-core processor or a multi-core processor. The processor herein may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0109] like Fig. 11B It should be understood that the communication device shown in the figure is only an example, and in actual applications, the communication device may have more Fig. 11B More or fewer components may be shown, two or more components may be combined, or there may be a different configuration of components.

[0110] The communication device 400 may be a general-purpose device or a dedicated device. The embodiment of the present application does not limit the type of the communication device 400. Fig. 11B Devices of similar structure.

[0111] In the following, in conjunction with the accompanying drawings, the data transmission method of an embodiment of the present application is described by taking the first entity as a base station, the second entity as a terminal, and the interaction between the first entity and the second entity as an example.

[0112] An embodiment of the present application provides a data transmission method, such as Fig.12 As shown, Fig.12 This is a flow chart of an embodiment of the present application. The method comprises the following steps:

[0113] S 101. The terminal obtains a first RSRP set through a first beam scanning.

[0114] The first beam scan is performed between the base station and the terminal, and the base station can obtain RSRP values ​​corresponding to one or more beam pairs according to the result of the beam scan. The terminal can filter from the RSRP values ​​corresponding to the one or more beam pairs according to a preset screening method to obtain a first RSRP set.

[0115] Exemplarily, the terminal may form a first RSRP set with all RSRP values ​​obtained by this beam scanning.

[0116] As another example, the terminal may form a first RSRP set with the largest M RSRP values ​​among the RSRP values ​​obtained in this beam scanning, where M is a positive integer.

[0117] As another example, the terminal may form a first RSRP set with the RSRP values ​​that meet the preset conditions obtained by this beam scanning. The preset condition may be that the RSRP value is greater than the preset RSRP value, the RSRP value is greater than or equal to the preset RSRP value, etc. For example, the preset condition is that the RSRP value is greater than the preset RSRP value, the preset RSRP value is -50dB, and the RSRP values ​​obtained by the terminal through this beam scanning include {-10dB, -10dB, -30dB, -40dB, -50dB, -60dB, -70dB, -80dB}. Among them, there are 4 RSRP values ​​that meet the preset conditions, then the first RSRP set includes {-10dB, -10dB, -30dB, -40dB}.

[0118] S102: The terminal reports a first reference RSRP value, where the first reference RSRP value is determined from a first RSRP set. Correspondingly, the base station receives the first reference RSRP value from the terminal.

[0119] Reference Fig.13 , Fig.13 Another flowchart of an embodiment of the present application is shown in FIG.

[0120] The terminal may determine a first reference RSRP value in the first RSRP set, and report the first reference RSRP value to the base station. The base station receives the first reference RSRP value.

[0121] In the embodiment of the present application, determining can also be described as selecting or choosing, for example, the terminal selects the first reference RSRP value from the first RSRP set.

[0122] In the embodiment of the present application, reporting can also be described as sending, transmitting, reporting, etc. The reporting referred to in the embodiment of the present application means that one entity sends information to another entity, and the information can be a reference RSRP value, an RSRP set, etc. Reporting cannot be understood as sending information only through an uplink channel, and the embodiment of the present application does not limit the channel selected for reporting.

[0123] Optionally, the terminal determines the first reference RSRP value by: taking the smallest RSRP value in the first RSRP set as the first reference RSRP value, and taking the largest RSRP value in the first RSRP set as the first reference RSRP value. Alternatively, the RSRP values ​​in the first RSRP set are sorted, and the RSRP value with the middle value is taken as the first reference RSRP value.

[0124] For example, the first RSRP set is {-10dB, -10dB, -30dB, -40dB}. The terminal may select a minimum RSRP value and use -40dB as the first reference RSRP value. Alternatively, the maximum RSRP value -10dB may be used as the first reference RSRP value. Alternatively, the RSRP value of -30dB, which is the median value, may be used as the first reference RSRP value.

[0125] S 103: The terminal obtains a second RSRP set through a second beam scanning.

[0126] Similarly, the terminal and the base station perform beam scanning again, and obtain a second RSRP set according to the result of the second beam scanning. The method for obtaining the second RSRP set can refer to the method for obtaining the first RSRP set, which will not be repeated here.

[0127] Exemplarily, the second RSRP set obtained by the second beam scanning between the terminal and the base station is {-20dB, -10dB, -30dB, -35dB}.

[0128] S104: The terminal reports a first differential RSRP set according to the second RSRP set and the first reference RSRP value, wherein the first differential RSRP set is obtained by differentially calculating the RSRP value in the second RSRP set and the first reference RSRP value. Accordingly, the base station receives the first differential RSRP set.

[0129] After obtaining the second RSRP set, the terminal performs a differential operation on the RSRP value in the second RSRP set and the first reference RSRP value to obtain a first differential RSRP set. The terminal reports the first differential RSRP set to the base station, so that the base station obtains the beam information in the second beam scan between the terminal and the base station according to the first differential RSRP set.

[0130] Exemplarily, taking the first reference RSRP value of -10dB as an example, the second RSRP set {-20dB, -10dB, -30dB, -35dB} is differentially calculated with the first reference RSRP value to obtain a measured value of {-10dB, 0, -20dB, -25dB}. The terminal can refer to Table 1 above and obtain RSRP report values ​​{DIFFRSRP_5, DIFFRSRP_0, DIFFRSRP_10, DIFFRSRP_12} according to the measured values, and the above RSRP report values ​​constitute the first differential RSRP set.

[0131] Table 1 above mainly sets 16 different RSRP report values ​​for the measurement value of 0 to -30. In binary, the above 16 RSRP report values ​​can be represented by 16 different 4-bit numbers, and each RSRP value occupies 4 bits of overhead. For example, {DIFFRSRP_5, DIFFRSRP_0, DIFFRSRP_10, DIFFRSRP_12} is represented as {0101, 0000, 1010, 1100}.

[0132] The reference RSRP value is an RSRP value that has not been processed by a differential calculation or other calculation method, and the bandwidth occupied by it is 7 bits. By sending a second RSRP set that does not include the reference RSRP value to the base station, the terminal saves the overhead occupied by the reference RSRP value over the RSRP report value (3 bits in the embodiment of the present application), thereby saving space resources.

[0133] In other embodiments, a different correspondence between the measured value and the RSRP report value can also be set so that the RSRP report value occupies less bandwidth. Exemplarily, refer to Table 2, which is another example of a differential accuracy list for RSRP. Set the report value to DIFFRSRP_0 to DIFFRSRP_8, and the terminal uses the RSRP value with energy to -30dB as the reference RSRP value. The above-mentioned second RSRP set {-20dB, -10dB, -30dB, -35dB} is differentially calculated with the first reference RSRP value to obtain a measured value of {10dB, 20dB, 0, -5dB}. Referring to Table 2, the RSRP report value is {DIFFRSRP_2, DIFFRSRP_0, DIFFRSRP_5, DIFFRSRP_6}. The above 9 RSRP report values ​​can be represented by a 3-bit binary number, and the RSRP report value actually sent by the terminal is {010, 000, 101, 110}. Through the differential precision list of RSRP shown in Table 2, each RSRP report value in the second RSRP set only occupies 3 bits, and the second RSRP set sent by the terminal occupies less overhead.

[0134] Table 2 RSRP differential accuracy List 2

[0135] RSRP Report Value Measured value (difference between differential RSRP and reference RSRP) Unit (dB) DIFFRSRP_0 20≥ΔRSRP>16 dB DIFFRSRP_1 16≥ΔRSRP>12 dB DIFFRSRP_2 12≥ΔRSRP>8 dB DIFFRSRP_3 8≥ΔRSRP>4 dB DIFFRSRP_4 4≥ΔRSRP>0 dB DIFFRSRP_5 0≥ΔRSRP>-4 dB DIFFRSRP_6 -4 ≥ ΔRSRP > -8 dB DIFFRSRP_7 -8≥ΔRSRP>-12 dB

[0136] S105: The base station obtains a second RSRP set according to the first reference RSRP value and the first differential RSRP set. The base station may perform a reverse differential calculation on the RSRP value in the first differential RSRP set and the first reference RSRP value to obtain the second RSRP set.

[0137] The terminal and the base station report RSRP values ​​according to the rules of RSRP differential measurement values ​​and RSRP report values ​​shown in the RSRP differential accuracy list of the example in Table 1. After receiving the first differential RSRP set, the base station can obtain the RSRP differential measurement value according to Table 1, and perform a reverse differential calculation on the measurement value and the first reference RSRP value reported by the terminal in S102 to obtain the second RSRP set.

[0138] Exemplarily, the first reference RSRP value received by the base station is -10dB, and the first differential RSRP set is {0101, 0000, 1010, 1100}. For example, the report values ​​corresponding to {0101, 0000, 1010, 1100} are {DIFFRSRP_5, DIFFRSRP_0, DIFFRSRP_10, DIFFRSRP_12}. According to Table 1, the base station obtains RSRP differential measurement values ​​of {-10dB, 0, -20dB, -25dB}. The base station performs a reverse differential operation on each measurement value and the first reference RSRP value to obtain a second RSRP set {-20dB, -10dB, -30dB, -35dB}.

[0139] In the above manner, the terminal does not need to send a reference RSRP value when sending an RSRP value set to the base station for the second time, so that the sent RSRP set occupies less overhead and reduces the waste of space resources.

[0140] The above example uses the case where the terminal sends two RSRP values ​​to the base station (the first time the reference RSRP value is sent, and the second time the first differential RSRP set is sent) to illustrate the data transmission method of the embodiment of the present application. It can be understood that in the embodiment of the present application, the terminal can send more RSRP values ​​to the base station, such as 3 times, 4 times, 10 times, 20 times, etc. The RSRP values ​​sent by the terminal to the base station multiple times can be differentially calculated with the reference RSRP value sent for the first time, so that the RSRP value sent by the terminal each time consumes less overhead and saves space resources.

[0141] In the embodiment of the present application, the order of steps S102 and S103 is not limited. For example, S103 can be executed before S102, or after S102, or simultaneously with S102.

[0142] In some embodiments, after the base station receives the RSRP value sent by the terminal, the RSRP value can be input into the AI ​​model. The AI ​​model can output the predicted RSRP value or beam information, and predict the beam at a future time based on the RSRP value.

[0143] Exemplarily, the AI ​​model may output the RSRP value and the identifier of the beam corresponding to the RSRP value. The base station may select a beam that meets the conditions from the beams output by the AI ​​model according to preset conditions as the beam for subsequent communication with the terminal. Exemplarily, the identifier of the beam may be the identity information (identify, ID) of the beam.

[0144] As another example, the AI ​​model can output the identification of the beam, and the base station can directly use the beam as the beam for subsequent communications with the terminal.

[0145] In some embodiments, the terminal runs along a certain trajectory, and the RSRP value sent by the terminal to the base station is the RSRP value obtained by beam scanning with the base station when the terminal runs along the certain trajectory. The base station can predict the RSRP value obtained by the terminal scanning at a future time when the terminal runs along the trajectory based on the RSRP value, or the beam with the RSRP value.

[0146] Reference Fig.13 In an embodiment of the present application, the terminal further includes reporting a second differential RSRP set. The second differential RSRP set is obtained by differentially calculating the RSRP values ​​other than the first reference RSRP value in the first RSRP set and the first reference RSRP value. Accordingly, the base station receives the second differential RSRP set.

[0147] Exemplarily, the first RSRP set includes {-10dB, -10dB, -30dB, -40dB}, and the first reference RSRP value is -10dB. The terminal can perform differential operations on {-10dB, -30dB, -40dB} and -30dB respectively to obtain RSRP differential measurement values ​​{0, -20dB, -30dB}, and refer to Table 1 above to obtain RSRP report values ​​{DIFFRSRP_0, DIFFRSRP_10, DIFFRSRP_15} according to the RSRP differential measurement values.

[0148] The terminal reports the first reference RSRP value and the second differential RSRP set to the base station. After receiving the first reference RSRP value and the second differential RSRP set, the base station can obtain the RSRP differential measurement value of the second differential RSRP set according to Table 1, and perform reverse differential calculation on the measurement value and the first reference RSRP value to obtain the first RSRP set. The specific example of the terminal obtaining the first RSRP set according to Table 1 can refer to the example of the terminal obtaining the second RSRP set, which will not be repeated here.

[0149] In an embodiment of the present application, when the base station receives more than two RSRP sets sent by the terminal (the above examples illustrate the first RSRP set and the second RSRP set, and may also include multiple RSRP sets such as the third RSRP set), only one RSRP value among the multiple RSRP sets is the reference RSRP value, and the remaining RSRP values ​​are in the form of differential operations with the reference RSRP value. When the terminal sends the above RSRP set, the overhead occupied by RSRP is reduced, saving overhead resources.

[0150] like Fig.14 As shown, Fig.14 This is another flow chart of an embodiment of the present application. Fig.14 A data transmission method provided by another embodiment of the present application is shown, and the method includes the following steps.

[0151] S 1201. The terminal obtains a first RSRP set through the first beam scanning.

[0152] S 1202: The terminal obtains a second RSRP set through a second beam scanning.

[0153] S 1203. The terminal obtains a predicted RSRP set according to the first RSRP set and the second RSRP set. There are multiple predicted RSRP sets, and the multiple predicted RSRP sets include the first predicted RSRP set and the second predicted RSRP set.

[0154] In some embodiments, each predicted RSRP set predicted by the terminal may represent an RSRP set obtained by the terminal and the base station through beam scanning at a future time. There may be a time relationship between multiple predicted RSRP sets, for example, the future time corresponding to the first predicted RSRP set is before the future time corresponding to the second predicted RSRP set.

[0155] The terminal predicts the RSRP value at a future time based on the RSRP set obtained by the first beam scan and the second beam scan, and reports the predicted RSRP value to the base station, and the base station receives the RSRP value at a future time. The base station can select the beam for communicating with the terminal in advance based on the RSRP value at a future time. At a future time, the terminal can directly communicate with the base station through the beam, reducing the time spent by the terminal on beam selection and improving the operating speed of the terminal. In addition, the input amount of the AI ​​model is usually greater than the output amount of the AI ​​model. The overhead consumed by the terminal sending the predicted RSRP value to the base station is less than the overhead consumed by the terminal sending the RSRP value that needs to be input into the AI ​​model to the base station. Therefore, the embodiment of the present application sets the AI ​​model in the terminal, which can consume less overhead and save overhead resources.

[0156] Reference Fig.15 In some embodiments, the terminal obtains a predicted RSRP set through AI-based beam prediction, wherein the AI ​​model used in the AI-based beam prediction can be set on the terminal or other devices connected to the terminal for communication.

[0157] Reference Fig.15 In some embodiments, the terminal can obtain W RSRP sets through n beam scans, and obtain a predicted RSRP set based on the W RSRP sets. The number of beam scans n can be 2 as in the above example, or more times, for example, n can be a positive integer greater than or equal to 3. It should be noted that the number of predicted RSRP sets W obtained by AI-based beam prediction can be equal to or different from the number of beam scans, and the values ​​of n and W can be selected by the configuration of the AI ​​model, which is not limited in the embodiments of the present application.

[0158] In other embodiments, the RSRP set predicted by the terminal further includes a third predicted RSRP set, a fourth predicted RSRP set, etc. The terminal may set the number of predicted RSRP sets as needed.

[0159] S 1204: The terminal reports a second reference RSRP value according to the first predicted RSRP set, where the second reference RSRP value is determined from the first predicted RSRP set.

[0160] Correspondingly, the base station receives the second reference RSRP value.

[0161] Referring to the method of determining the first reference RSRP value from the first RSRP set in the above embodiment, the above method can also be used to determine the second reference RSRP value in the first predicted RSRP set. For example, the maximum RSRP value in the first predicted RSRP set is selected as the reference RSRP value. The method of selecting the reference RSRP value is not repeated here.

[0162] S 1205. The base station obtains a first predicted RSRP set according to the second reference RSRP value.

[0163] In the embodiment of the present application, the first predicted RSRP set includes a second reference RSRP value. The second reference RSRP value received by the base station is all RSRP values ​​in the first predicted RSRP set.

[0164] S 1206: The terminal reports a first target differential RSRP set according to the second predicted RSRP set and the second reference RSRP value. The first target differential RSRP set is obtained by differentially calculating the RSRP value in the second predicted RSRP set and the second reference RSRP value.

[0165] Correspondingly, the base station receives the first target differential RSRP set.

[0166] S 1207. The base station obtains a second predicted RSRP set according to the second reference RSRP value and the first target differential RSRP set.

[0167] The base station may perform a reverse differential calculation on the RSRP value in the first target differential RSRP set and the second reference RSRP value to obtain a second predicted RSRP set.

[0168] According to the above method of the embodiment of the present application, after obtaining the first predicted RSRP set, the base station can determine whether the RSRP value in the first predicted RSRP set meets the preset requirements. If there is an RSRP value that meets the preset requirements in the first predicted RSRP set, the base station can use the beam corresponding to the RSRP value to communicate with the terminal at a future time. Alternatively, after obtaining multiple predicted RSRP sets (such as the first predicted RSRP set and the second predicted RSRP set mentioned above), the base station can determine whether the RSRP values ​​in multiple predicted RSRP sets meet the preset requirements. If there is an RSRP value that meets the preset requirements in multiple predicted RSRP sets, the base station can use the beam corresponding to the RSRP value to communicate with the terminal at a future time.

[0169] If the base station determines whether the RSRP values ​​in multiple predicted RSRP sets meet the preset requirements, and finds that there is no RSRP value that meets the preset requirements in the predicted RSRP set, the base station can perform one more round of beam scanning with the terminal, and the terminal reports the RSRP value predicted again to the base station through the method of the embodiment of the present application, and the base station judges the predicted RSRP set again. Each time the terminal reports the RSRP value to the base station using the method of the embodiment of the present application, it consumes less overhead than the RSRP value reporting method in the related art, and can save overhead resources.

[0170] Alternatively, when the base station determines whether the RSRP values ​​in multiple predicted RSRP sets meet the preset requirements and finds that there is no RSRP value in the predicted RSRP set that meets the preset requirements, the base station can select the beam with the best quality in the predicted RSRP set and use the beam to communicate with the terminal at a future time.

[0171] Exemplarily, the preset requirement may be that the RSRP value is greater than a first threshold, wherein the first threshold may be preset in the base station or may be obtained by the base station according to a certain instruction, and the embodiments of the present application do not impose any specific limitation thereto.

[0172] When there are multiple RSRP values ​​in the predicted RSRP set that meet the preset requirements, the base station can select a beam for communicating with the terminal from the beams corresponding to the multiple RSRP values ​​according to the preset screening conditions. Exemplarily, the preset screening conditions can be random selection, selection of the largest RSRP value, etc., and the base station can also select the beam for communicating with the terminal with reference to other attributes of the beam.

[0173] Exemplarily, the base station may select a beam according to the RSRP value of the beam, and use the beam with the largest RSRP value as the beam with the best quality.

[0174] Reference Fig.15 In the embodiment of the present application, the first predicted RSRP set may include more than two RSRP values, and S 1204 also includes the terminal reporting a second target differential RSRP set according to the first predicted RSRP set. The second target differential RSRP set is obtained by differentially calculating the RSRP values ​​other than the second reference RSRP value in the first predicted RSRP set and the second reference RSRP value.

[0175] Correspondingly, the base station receives the second target differential RSRP set.

[0176] The terminal reports the second reference RSRP value and the second target differential RSRP set to the base station. After receiving the second reference RSRP value and the second target differential RSRP set, the base station can obtain the RSRP differential measurement value of the second target differential RSRP set according to Table 1, and perform reverse differential calculation on the measurement value and the second reference RSRP value to obtain the first predicted RSRP set.

[0177] The above content takes beam scanning between the base station and the terminal, and in the scenario of beam prediction based on the AI ​​model, the terminal reports the RSRP set to the base station as an example to illustrate the data transmission method of an embodiment of the present application.

[0178] The data transmission method of the embodiment of the present application can also be applied in the AI ​​model monitoring process. During the model monitoring process, the terminal can scan all beams sent by the base station, compare the prediction results of the AI ​​output with the optimal beam obtained from the beams scanned by the base station at multiple times, and if the AI ​​performance does not meet the requirements, the AI ​​model can be retrained or updated. The optimal beam is the beam with the best performance among the beams scanned by the terminal. It can also be understood that the performance of the optimal beam is the upper limit of the performance of the beam scanned by the terminal. For example, the optimal beam may be the beam with the largest RSRP value.

[0179] When in the model monitoring process, the terminal scans all beams sent by the base station and reports the results of scanning all beams. At this time, the terminal can select the maximum RSRP of the beam in the first moment when the terminal reports the RSRP value of the beam as the high-precision label. All subsequent moments, including the RSRP corresponding to all beams in the observation window and prediction window of the above example, can be based on this maximum high-precision RSRP difference, and low-precision reporting. For example, using the RSRP report value corresponding to Table 1 for reporting, this solution can save the bit overhead occupied by reporting RSRP values ​​of (X-1)*3 bits. Among them, X is the number of times the terminal reports the RSRP value of the beam to the base station.

[0180] Any method of each embodiment of this embodiment can be used in combination or independently. The combination of any methods of each embodiment is not limited thereto, and the methods formed by various combinations are all within the protection scope of the embodiments of this application.

[0181] It should be noted that the above-mentioned multiple embodiments can be combined and the combined scheme can be implemented. Optionally, some operations in the process of each method embodiment are optionally combined, and / or the order of some operations is optionally changed. In addition, the execution order between the steps of each process is only exemplary and does not constitute a limitation on the execution order between the steps. There can also be other execution orders between the steps. It is not intended to indicate that the execution order is the only order in which these operations can be performed. Ordinary technicians in this field will think of many ways to reorder the operations of this article. In addition, it should be pointed out that the process details involved in a certain embodiment of this article are also applicable to other embodiments in a similar manner, or different embodiments can be used in combination.

[0182] In addition, some steps in the method embodiment may be equivalently replaced by other possible steps. Alternatively, some steps in the method embodiment may be optional and may be deleted in certain usage scenarios. Alternatively, other possible steps may be added to the method embodiment.

[0183] Furthermore, the above method embodiments may be implemented separately or in combination.

[0184] It is understandable that the device in the embodiment of the present application includes a hardware structure and / or software module corresponding to each function in order to realize the above functions. In combination with the units and algorithm steps of each example described in the embodiment disclosed in the present application, the embodiment of the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or 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 to exceed the scope of the technical solution of the embodiment of the present application.

[0185] The embodiment of the present application can divide the functional units of the communication device according to the above method example. For example, each functional unit can be divided according to each function, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0186] The present application also provides a device in an embodiment of the present application, which may be the above-mentioned first entity or second entity or corresponding component. The device may include: a memory and one or more processors. The memory and the processor are coupled. The memory is used to store computer program code, and the computer program code includes computer instructions. When the processor executes the computer instructions, the device may perform the various functions or steps performed by the first entity or the second entity in the above-mentioned method embodiment. The structure of the device can refer to Fig. 11B The structure of the device shown.

[0187] Among them, the core structure of the device can be expressed as Fig.16 In the structure shown, the device includes: a processing module 1301 and a storage module 1303.

[0188] The processing module 1301 may include at least one of a central processing unit (CPU), an application processor (AP) or a communication processor (CP). The processing module 1301 may perform operations or data processing related to control and / or communication of at least one of other elements of the user communication device.

[0189] The storage module 1303 may include a volatile memory and / or a non-volatile memory. The storage module is used to store at least one instruction or data related to other modules of the device.

[0190] Optionally, a communication module 1305 is also included to support the device to communicate with other devices (through a communication network). For example, the communication module can be connected to a network via wireless communication or wired communication to communicate with other devices. Wireless communication can use at least one of cellular communication protocols, such as long term evolution (LTE), advanced long term evolution (LTE-A), code division multiple access (CDMA), wideband code division multiple access (WCDMA), universal mobile telecommunications system (UMTS), wireless broadband (WiBro) or global mobile communication system (GSM). Wireless communication may include, for example, short-range communication. Short-range communication may include at least one of wireless fidelity (Wi-Fi), Bluetooth, near field communication (NFC), magnetic stripe transmission (MST) or GNSS.

[0191] The present application also provides a chip system, such as Fig.17 As shown, the chip system includes at least one processor 1401 and at least one interface circuit 1402. The processor 1401 and the interface circuit 1402 can be interconnected via lines. For example, the interface circuit 1402 can be used to receive signals from other devices (such as a memory of a communication device). For another example, the interface circuit 1402 can be used to send signals to other devices (such as processor 1401). Exemplarily, the interface circuit 1402 can read instructions stored in the memory and send the instructions to the processor 1401. When the instruction is executed by the processor 1401, the communication device can perform the various steps in the above embodiments. Of course, the chip system can also include other discrete devices, which are not specifically limited in the embodiments of the present application.

[0192] An embodiment of the present application also provides a computer storage medium, which includes computer instructions. When the computer instructions are executed on the above-mentioned communication device, the communication device executes each function or step executed by the mobile phone in the above-mentioned method embodiment.

[0193] The embodiment of the present application also provides a computer program product. When the computer program product is run on a computer, the computer executes each function or step executed by the mobile phone in the above method embodiment.

[0194] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0195] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0196] The units described as separate components may or may not be physically separated, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple different places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0197] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0198] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium, including several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to perform all or part of the steps of each embodiment method of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program code.

[0199] The above contents are only specific implementation methods of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present application shall be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A data transmission method, characterized in that: Applied to a first device, the method includes: Obtaining a first reference signal received power RSRP set through the first beam scanning; Reporting a first reference RSRP value, where the first reference RSRP value is determined from the first RSRP set; Through the second beam scanning, a second RSRP set is obtained; A first differential RSRP set is reported according to the second RSRP set and the first reference RSRP value; wherein the first differential RSRP set is obtained by differentially calculating the RSRP value in the second RSRP set and the first reference RSRP value.

2. The method according to claim 1, characterized in that Reporting the first reference RSRP value includes: reporting the first reference RSRP value and a second differential RSRP set; the second differential RSRP set is obtained by differentially calculating the first reference RSRP value and the RSRP value other than the first reference RSRP value in the first RSRP set.

3. A data transmission method, characterized in that: Applied to the second device, the method includes: Receiving a first reference RSRP value, where the first reference RSRP value is determined by the first device from a first RSRP set obtained through a first beam scan; Receiving a first differential RSRP set; the first differential RSRP set is obtained by differentially calculating the RSRP value in the second RSRP set obtained by the first device through the second beam scanning and the first reference RSRP value by the first device; The second RSRP set is obtained according to the first reference RSRP value and the first differential RSRP set; wherein the second RSRP set is obtained by the second device performing a reverse differential calculation on the RSRP value in the first differential RSRP set and the first reference RSRP value.

4. The data transmission method according to claim 3, characterized in that: The method further comprises: receiving a second differential RSRP set; the second differential RSRP set is obtained by differentially calculating, by the first device, RSRP values ​​other than the first reference RSRP value in the first RSRP set and the first reference RSRP value; The second differential RSRP set, the first differential RSRP set and the first reference RSRP value are used to input an artificial intelligence AI model; or, The first RSRP set is obtained according to the first reference RSRP value and the second differential RSRP set; wherein the RSRP values ​​other than the first reference RSRP value in the first RSRP set are obtained by performing a reverse differential calculation between the RSRP values ​​in the second differential RSRP set and the first reference RSRP value; The first RSRP set and the second RSRP set are used to input an AI model.

5. A data transmission method, characterized in that: Applied to a first device, the method includes: Through the first beam scanning, a first RSRP set is obtained; Through the second beam scanning, a second RSRP set is obtained; According to the first RSRP set and the second RSRP set, a predicted RSRP set is obtained; wherein the number of the predicted RSRP sets is multiple, and the multiple predicted RSRP sets include the first predicted RSRP set and the second predicted RSRP set; Reporting a second reference RSRP value according to the first predicted RSRP set; the second reference RSRP value is determined from the first predicted RSRP set; According to the second predicted RSRP set and the second reference RSRP value, a first target differential RSRP set is reported; the first target differential RSRP set is obtained by differentially calculating the RSRP value in the second predicted RSRP set and the second reference RSRP value.

6. The data transmission method according to claim 5, characterized in that: Reporting a second reference RSRP value according to the first predicted RSRP set includes: reporting a second reference RSRP value and a second target differential RSRP set according to the first predicted RSRP set; the second target differential RSRP set is obtained by differentially calculating the RSRP value other than the second reference RSRP value in the first predicted RSRP set and the second reference RSRP value.

7. The data transmission method according to claim 5 or 6, characterized in that: Obtaining a predicted RSRP set according to the first RSRP set and the second RSRP set, including: According to the first RSRP set and the second RSRP set, a predicted RSRP set is obtained through AI model prediction.

8. A data transmission method, characterized in that: Applied to the second device, the method includes: receiving a second reference RSRP value; the second reference RSRP value is determined by the first device from a first predicted RSRP set; the first predicted RSRP set is in the predicted RSRP set; the predicted RSRP set is predicted by the first device based on the first RSRP set and the second RSRP set; Obtaining a first predicted RSRP set according to the second reference RSRP value; receiving a first target differential RSRP set; the first target differential RSRP set is obtained by differentially calculating the RSRP value in the second predicted RSRP set and the second reference RSRP value; the second predicted RSRP set is in the predicted RSRP set; A second predicted RSRP set is obtained according to the second reference RSRP value and the first target differential RSRP set; wherein the second predicted RSRP set is obtained by performing an inverse differential calculation between the RSRP value in the first target differential RSRP set and the second reference RSRP value.

9. The method according to claim 8, characterized in that The method further comprises: receiving a second target differential RSRP set; the second target differential RSRP set is obtained by differentially calculating the second reference RSRP value and the RSRP value other than the second reference RSRP value in the first predicted RSRP set by the first device; The obtaining, according to the second reference RSRP value, a first predicted RSRP set includes: The first predicted RSRP set is obtained according to the second reference RSRP value and the second target differential RSRP set; wherein the RSRP values ​​other than the second reference RSRP value in the first predicted RSRP set are obtained by performing inverse differential calculation between the RSRP values ​​in the second target differential RSRP set and the second reference RSRP value.

10. An electronic device, characterized in that: The electronic device includes a memory and a processor; the memory is coupled to the processing unit; the memory is used to store computer program code, and the computer program code includes computer instructions, and when the processing unit executes the computer instructions, the electronic device executes the method as described in any one of claims 1-2; or, the electronic device executes the method as described in any one of claims 3-4; or, the electronic device executes the method as described in any one of claims 5-7; or, the electronic device executes the method as described in any one of claims 8-9.

11. An electronic device, characterized in that: include: processor; The processor is used to be coupled to the memory, and after reading the instructions in the memory, execute the method according to any one of claims 1 to 2 according to the instructions; Or, the method according to any one of claims 3-4; or, the method according to any one of claims 5-7; or, the method according to any one of claims 8-9.

12. A chip system, characterized in that: include: A processor and an interface circuit; the processor and the interface circuit are interconnected via a line; The interface circuit is used to read instructions stored in the memory. When the instructions are executed by the processor, the chip system executes the method as described in any one of claims 1-2; or, the chip system executes the method as described in any one of claims 3-4; or, the chip system executes the method as described in any one of claims 5-7; or, the chip system executes the method as described in any one of claims 8-9.

13. A computer-readable storage medium, characterized in that: Comprising computer instructions, when the computer instructions are executed on an electronic device, the electronic device executes the method as described in any one of claims 1-2; or the chip system executes the method as described in any one of claims 3-4; or the chip system executes the method as described in any one of claims 5-7; or the chip system executes the method as described in any one of claims 8-9.

Images