Wireless model, information processing method and device, and system

Abstract

The present application provides a wireless model, an information processing method and device, and a system. The wireless model comprises a first sub-model and a second sub-model, wherein the first sub-model is used for processing first channel information to obtain a first channel feature parameter, the second sub-model is used for processing first ambient information to obtain a first ambient feature parameter, the first channel information is associated with the first ambient information, and the first channel feature parameter and the first ambient feature parameter correspond to a first high-dimensional feature vector. Through training, the wireless model can enable ambient information and channel information to obtain a same representation in a high-dimensional feature space, and thus can obtain the mutual prediction capability of the two pieces of information.

Description

Wireless model, information processing method, device, and system

[0001] This application claims priority to the Chinese patent application with application number 202410250904.3 filed with the State Intellectual Property Office of China on March 5, 2024, and priority to the Chinese patent application with the invention name “Wireless model, information processing method, device and system”, all contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of artificial intelligence (AI), and in particular to a wireless model, an information processing method and device, and a system. Background Art

[0003] In recent years, large models have garnered widespread attention in computer science, particularly in natural language processing and computer vision, due to their superior performance, spawning a multitude of applications. Large models are pre-trained on massive amounts of data, extracting and storing extensive knowledge within their parameters. In downstream tasks, fine-tuning the model on a small number of samples, or even no fine-tuning at all, can yield excellent performance, demonstrating the superior generalization capabilities of large models.

[0004] In existing wireless communications, AI / machine learning (ML) technology is modularly designed for each task, with independent data collection, model design, training, and management performed for different tasks. This results in the inability to effectively share data and functions between different models. Summary of the Invention

[0005] The present application discloses a wireless model, an information processing method and device, and a system, which can enable environmental information and channel information to obtain the same representation in a high-dimensional feature space, and obtain the mutual prediction capability of the two types of information.

[0006] In a first aspect, an embodiment of the present application provides a wireless model. The wireless model includes a first sub-model (also referred to as a channel encoder, etc.) and a second sub-model (also referred to as an environment encoder, etc.). The first sub-model is used to process first channel information to obtain first channel characteristic parameters. The second sub-model is used to process first environment information to obtain first environment characteristic parameters. The first channel information and the first environment information are associated, and the first channel characteristic parameters and the first environment characteristic parameters correspond to a first high-dimensional feature vector.

[0007] Through training, the wireless model can make the environmental information and channel information obtain the same representation in the high-dimensional feature space, thereby obtaining the mutual prediction ability of the two types of information.

[0008] This association can be understood as that the first channel information and the first environment information are information corresponding to the same environment.

[0009] The first high-dimensional feature vector is a mapping of the first channel information and the first environmental information in a high-dimensional feature space. In the physical world, due to the principle of electromagnetic field transmission, environmental information and channel information have a one-to-one correspondence. By finding a high-dimensional physical feature space in which environmental information and channel information are represented as the same high-dimensional physical feature, the conversion between features and information can be achieved. In a high-dimensional physical feature space, feature vectors of similar environments and channels are close in space, while feature vectors of different environments and channels are far apart in space.

[0010] The first channel characteristic parameter and the first environmental characteristic parameter correspond to a first high-dimensional feature vector. That is, the first channel characteristic parameter and the first environmental characteristic parameter correspond to the same high-dimensional feature vector. The same high-dimensional feature vector may correspond to one or more channel characteristic parameters and one or more environmental characteristic parameters, which is not limited in this solution.

[0011] In other words, the first high-dimensional feature vector is used to associate the first channel characteristic parameter with the first environmental characteristic parameter. For example, the first high-dimensional feature vector includes the first channel characteristic parameter and the first environmental characteristic parameter, or the first high-dimensional feature vector is obtained by performing other processing on the first channel characteristic parameter and the first environmental characteristic parameter. This solution is not limited to this. It is understandable that the first high-dimensional feature vector is also used to associate the first channel information with the first environmental information.

[0012] In a possible implementation, the wireless model may map the first channel information, the first environment information, and the first high-dimensional feature vector to each other.

[0013] This mutual mapping can be understood as inputting one or two of the first channel information, the first environment information and the first high-dimensional feature vector, and outputting the other items of the first channel information, the first environment information and the first high-dimensional feature vector except the input.

[0014] In a possible implementation manner, the input of the wireless model is the first channel information, and the output of the wireless model is at least one of first environment information and a first high-dimensional feature vector.

[0015] In another possible implementation manner, the input of the wireless model is the first environment information, and the output of the wireless model is at least one of the first channel information and a first high-dimensional feature vector.

[0016] In another possible implementation, the input of the wireless model is the first high-dimensional feature vector, and the output of the wireless model is at least one of first channel information and first environment information. That is, the input of the wireless model is the high-dimensional feature vector, and the output is at least one of channel information and environment information.

[0017] In another possible implementation, the input of the wireless model is the first channel information and the first environment information, and the output of the wireless model is the first high-dimensional feature vector.

[0018] In another possible implementation manner, the input of the wireless model is the first channel information and the first high-dimensional feature vector, and the output of the wireless model is the first environment information.

[0019] In another possible implementation manner, the input of the wireless model is the first environment information and the first high-dimensional feature vector, and the output of the wireless model is the first channel information.

[0020] In one possible implementation, the first submodel is further used to process a third high-dimensional feature vector to obtain second channel information, and / or the second submodel is further used to process the third high-dimensional feature vector to obtain second environmental information. The third high-dimensional feature vector may be the first high-dimensional feature vector described above, or may be a feature vector different from the first high-dimensional feature vector. It is understood that the second channel information is associated with the second environmental information.

[0021] In one possible implementation, when the wireless model is applied to a downstream task, the input of the downstream model includes a second high-dimensional feature vector, which is obtained by processing the first channel characteristic parameter and the first environment characteristic parameter according to a preset ratio.

[0022] Based on the different downstream tasks, the output of the first sub-model and the output of the second sub-model are selectively activated to adapt to the downstream tasks.

[0023] In one possible implementation, the downstream model can be augmented with a correction task. Specifically, the downstream model's input can include not only the wireless model's output but also local measured values. Accordingly, the downstream model's output generates a correction value, which is used to correct for discrepancies between the training data and the real data. This can improve model performance.

[0024] In a possible implementation manner, the first channel information includes at least one of the following:

[0025] Multipath information, frequency domain channel response, channel impulse response, channel eigenvector, power delay spectrum, path loss, reference signal received power, signal-to-noise ratio, Doppler frequency offset, interference information, angle of arrival and departure, transmission delay, timing advance.

[0026] In a possible implementation, the first environment information includes at least one of the following:

[0027] Map and scale, building / obstruction information, location of network equipment and / or user equipment, configuration of the network equipment and / or user equipment and / or cell, density and mobility status of the user equipment, and weather.

[0028] In the second aspect, an embodiment of the present application provides an information processing method, which is performed by an information processing system. The system includes an information processing device (such as a first device, the first device can be a terminal device, which can be a device or apparatus with a chip, or a device or apparatus with an integrated circuit, or a chip, chip system, module, or control unit in the aforementioned device or apparatus, which is not limited in this application) and an information processing device (such as a second device, the second device can be a network device, which can be a device or apparatus with a chip, or a device or apparatus with an integrated circuit, or a chip, chip system, module or control unit in the aforementioned device or apparatus, which is not limited in this application), wherein the method adopts the wireless model provided by any implementation method of the first aspect, and the first submodel of the wireless model is deployed on the first device, and the second submodel of the wireless model is deployed on the second device. The method includes:

[0029] A first device sends first information to a second device, the first information being used to request prediction of first environment information. The first information includes a first high-dimensional feature vector, which is obtained based on first channel information and a first sub-model of the wireless model. In response, the second device receives the first information.

[0030] The second device obtains the initialized first environment information, and processes the first environment information based on the first high-dimensional feature vector, the initialized first environment information, and the second sub-model of the wireless model to obtain predicted first environment information.

[0031] The second device sends second information to the first device, where the second information includes the predicted first environment information. Correspondingly, the first device receives the second information.

[0032] In this example, the predicted value of the first environmental information is obtained by processing the initialized first environmental information, the first high-dimensional feature vector, and the second sub-model of the wireless model. This method can be used to predict one or more items in the environmental information.

[0033] In a third aspect, an embodiment of the present application provides an information processing method, which is executed by a first device or a circuit for a first device, the method comprising: the first device sends first information to a second device, the first information being used to request prediction of first environmental information; the first information comprising a first high-dimensional feature vector, the first high-dimensional feature vector being obtained based on first channel information and a first sub-model of the wireless model.

[0034] Then, the first device receives second information from the second device, where the second information includes predicted first environment information, obtained by processing the first high-dimensional feature vector, the initialized first environment information, and the second sub-model of the wireless model. The first sub-model and the second sub-model of the wireless model are trained based on channel training information and first environment training information. The first environment training information is associated with the channel training information. The predicted first environment information is associated with the first channel information.

[0035] In this example, the first high-dimensional feature vector is sent to the second device, thereby helping the second device to predict the first environmental information. Using this solution, environmental information can be predicted.

[0036] In one possible implementation, the first information also includes third environmental information, and the predicted first environmental information is obtained based on the first high-dimensional feature vector, the third environmental information, the initialized first environmental information, and the second sub-model of the wireless model, and the third environmental information is associated with the first channel information.

[0037] In one possible implementation, the first sub-model and the second sub-model of the wireless model are trained based on channel training information, first environment training information and second environment training information, and the second environment training information corresponds to the third environment information.

[0038] This example can achieve prediction of one or more items of environmental information.

[0039] In a fourth aspect, embodiments of the present application provide an information processing method, performed by a second device or a circuit for the second device, the method comprising: the second device receiving first information from a first device, the first information being used to request prediction of first environmental information. The first information includes a first high-dimensional feature vector, the first high-dimensional feature vector being obtained based on first channel information and a first sub-model of the wireless model.

[0040] Then, the second device obtains the initialized first environment information and processes it based on the first high-dimensional feature vector, the initialized first environment information, and the second sub-model of the wireless model to obtain predicted first environment information. The first sub-model and the second sub-model of the wireless model are trained based on the channel training information and the first environment training information. The first environment training information is associated with the channel training information, and the predicted first environment information is associated with the first channel information.

[0041] Furthermore, the second device sends second information to the first device, where the second information includes the predicted first environment information.

[0042] In this example, the second device can obtain the predicted first environment information based on the first high-dimensional feature vector sent by the first device and the initialized first environment information. Using this solution, the prediction of environment information can be achieved.

[0043] In one possible implementation, the second device obtains a fourth high-dimensional feature vector based on the initialized first environmental information and the second sub-model; then, the second device processes based on the fourth high-dimensional feature vector and the first high-dimensional feature vector to obtain the predicted first environmental information.

[0044] In one possible implementation, the first information also includes third environmental information, and the predicted first environmental information is obtained based on the first high-dimensional feature vector, the third environmental information, the initialized first environmental information, and the second sub-model of the wireless model, and the third environmental information is associated with the first channel information.

[0045] In one possible implementation, the first sub-model and the second sub-model of the wireless model are trained based on channel training information, first environment training information and second environment training information, and the second environment training information corresponds to the third environment information.

[0046] This example can achieve prediction of one or more items of environmental information.

[0047] In a fifth aspect, an embodiment of the present application provides an information processing method, which is performed by an information processing system. The system includes an information processing device (such as a first device) and an information processing device (such as a second device), wherein the method adopts the wireless model provided by any implementation of the first aspect, the first sub-model of the wireless model is deployed on the first device, and the second sub-model of the wireless model is deployed on the second device. The method includes:

[0048] The second device sends third information to the first device, the third information being used to request prediction of the first channel information; the third information including a first high-dimensional feature vector, the first high-dimensional feature vector being obtained based on the first environment information and the second sub-model of the wireless model. In response, the first device receives the third information.

[0049] The first device obtains initialized first channel information, and processes the information based on the first high-dimensional feature vector, the initialized first channel information, and the first sub-model of the wireless model to obtain predicted first channel information.

[0050] Furthermore, the first device sends fourth information to the second device, where the fourth information includes the predicted first channel information. Correspondingly, the second device receives the fourth information.

[0051] In this example, the predicted value of the first channel information is obtained by processing the initialized first channel information, the first high-dimensional feature vector, and the first sub-model of the wireless model. This method can be used to predict one or more items in the channel information.

[0052] In a sixth aspect, an embodiment of the present application provides an information processing method, which is performed by a first device or a circuit for the first device, and the method includes:

[0053] The first device receives third information from the second device, the third information being used to request prediction of first channel information. The third information includes a first high-dimensional feature vector, which is obtained based on the first environment information and the second sub-model of the wireless model.

[0054] Then, the first device obtains the initialized first channel information and processes it based on the first high-dimensional feature vector, the initialized first channel information, and the first sub-model of the wireless model to obtain predicted first channel information. The first sub-model and the second sub-model of the wireless model are trained based on the first channel training information and the environment training information. The environment training information is associated with the first channel training information, and the predicted first channel information is associated with the first environment information.

[0055] Furthermore, the first device sends fourth information to the second device, where the fourth information includes the predicted first channel information.

[0056] In this example, the first device can obtain predicted first channel information based on the first high-dimensional feature vector sent by the second device and the initialized first channel information. Using this solution, channel information prediction can be achieved.

[0057] In one possible implementation, the first device obtains a fifth high-dimensional feature vector based on the initialized first channel information and the first sub-model; then, the first device processes based on the fifth high-dimensional feature vector and the first high-dimensional feature vector to obtain the predicted first channel information.

[0058] In one possible implementation, the third information also includes third channel information, the predicted first channel information is obtained based on the first high-dimensional feature vector, the initialized first channel information, the third channel information, and the first sub-model of the wireless model, and the third channel information is associated with the first environmental information.

[0059] In a possible implementation, the first sub-model and the second sub-model of the wireless model are trained based on the first channel training information, the second channel training information, and the environment training information, and the second channel training information corresponds to the third channel information.

[0060] This example can predict one or more items of channel information.

[0061] In a seventh aspect, an embodiment of the present application provides an information processing method, performed by a second device or a circuit for the second device, the method comprising: the second device sending third information to the first device, the third information being used to request prediction of first channel information. The third information includes a first high-dimensional feature vector, the first high-dimensional feature vector being obtained based on the first environment information and the second sub-model of the wireless model.

[0062] Furthermore, the second device receives fourth information from the first device, the fourth information including predicted first channel information, the predicted first channel information being obtained by processing based on the first high-dimensional feature vector, the initialized first channel information, and the first sub-model of the wireless model. The first sub-model and the second sub-model of the wireless model are trained based on first channel training information and environment training information. The environment training information is associated with the first channel training information, and the predicted first channel information is associated with the first environment information.

[0063] In this example, the first high-dimensional feature vector is sent to the first device, thereby helping the first device predict the first channel information. Using this solution, channel information can be predicted.

[0064] In one possible implementation, the third information also includes third channel information, the predicted first channel information is obtained based on the first high-dimensional feature vector, the initialized first channel information, the third channel information, and the first sub-model of the wireless model, and the third channel information is associated with the first environmental information.

[0065] In one possible implementation, the first sub-model and the second sub-model of the wireless model are trained based on the first channel training information, the second channel training information and the environment training information, and the second channel training information corresponds to the third channel information.

[0066] This example can predict one or more items of channel information.

[0067] In an eighth aspect, an embodiment of the present application provides a model training method, which is performed by a model training system. The system includes a first device and a second device, wherein a first sub-model of a wireless model is deployed on the first device, and a second sub-model of the wireless model is deployed on the second device. The method includes:

[0068] The first device obtains channel training information, and obtains a sixth high-dimensional feature vector based on the channel training information and the initial first sub-model.

[0069] The first device sends fifth information to the second device, where the fifth information includes the sixth high-dimensional feature vector. Correspondingly, the second device receives the fifth information.

[0070] The second device obtains environmental training information, and obtains a seventh high-dimensional feature vector based on the environmental training information and the initial second sub-model.

[0071] The second device performs optimization based on the sixth high-dimensional feature vector and the seventh high-dimensional feature vector to obtain an updated second sub-model and updated parameters of the first sub-model.

[0072] Furthermore, the second device sends sixth information to the first device, where the sixth information includes updated parameters of the first sub-model. Correspondingly, the first device receives the sixth information.

[0073] The first device updates the initial first sub-model according to the update parameters of the first sub-model to obtain a trained first sub-model.

[0074] In this example, based on the aforementioned contrastive learning training method, the training objective is independent of the downstream task, which can provide a model with stronger generalization.

[0075] In a ninth aspect, an embodiment of the present application provides a model training method, which is performed by a first device or a circuit for the first device, and the method includes:

[0076] The first device obtains channel training information, and obtains a sixth high-dimensional feature vector based on the channel training information and the initial first sub-model.

[0077] Then, the first device sends fifth information to the second device, where the fifth information includes the sixth high-dimensional feature vector.

[0078] Furthermore, the first device receives sixth information from the second device, where the sixth information includes updated parameters of the first sub-model.

[0079] The first device also updates the initial first sub-model according to the update parameters of the first sub-model to obtain a trained first sub-model.

[0080] In the tenth aspect, an embodiment of the present application provides a model training method, which is executed by a second device or a circuit for a second device, the method comprising: the second device receives fifth information from the first device, and the fifth information comprises a sixth high-dimensional feature vector.

[0081] The second device obtains environmental training information, and obtains a seventh high-dimensional feature vector based on the environmental training information and the initial second sub-model.

[0082] Furthermore, the second device performs optimization based on the sixth high-dimensional feature vector and the seventh high-dimensional feature vector to obtain an updated second sub-model and updated parameters of the first sub-model.

[0083] The second device sends sixth information to the first device, where the sixth information includes updated parameters of the first sub-model.

[0084] In an eleventh aspect, an embodiment of the present application provides a model training method, which is performed by a model training system. The system includes a first device and a second device, wherein a first sub-model of a wireless model is deployed on the first device, and a second sub-model of the wireless model is deployed on the second device. The method includes:

[0085] The first device obtains channel training information, and obtains an eighth high-dimensional feature vector based on the channel training information and the initial first sub-model.

[0086] The first device sends seventh information to the second device, where the seventh information includes the eighth high-dimensional feature vector. Correspondingly, the second device receives the seventh information.

[0087] The second device obtains environmental training information, and obtains a ninth high-dimensional feature vector based on the environmental training information and the initial second sub-model.

[0088] The second device sends eighth information to the third device, where the eighth information includes the eighth high-dimensional feature vector and the ninth high-dimensional feature vector.

[0089] The third device processes the eighth high-dimensional feature vector and the ninth high-dimensional feature vector to obtain processed high-dimensional feature vectors; and inputs the processed high-dimensional feature vectors into the downstream model for processing to obtain an updated first sub-model and an updated second sub-model.

[0090] The third device sends ninth information to the second device, where the ninth information includes the updated second sub-model and at least one of the gradient, weight, and intermediate gradient of the initial first sub-model. In response, the second device receives the information.

[0091] The second device sends tenth information to the first device, where the tenth information includes at least one of the gradient, weight, and intermediate gradient of the initial first sub-model. Correspondingly, the first device receives the tenth information.

[0092] The first device updates the initial first sub-model based on at least one of the gradient, weight, and intermediate gradient of the initial first sub-model to obtain a trained first sub-model.

[0093] Based on this processing, the trained first sub-model and second sub-model can be obtained.

[0094] In a twelfth aspect, an embodiment of the present application provides a model training method, which is performed by a first device or a circuit for the first device, and the method includes:

[0095] The first device obtains channel training information, and obtains an eighth high-dimensional feature vector based on the channel training information and the initial first sub-model.

[0096] The first device sends seventh information to the second device, where the seventh information includes the eighth high-dimensional feature vector.

[0097] Then, the first device receives tenth information from the second device, where the tenth information includes at least one of the gradient, weight, and intermediate gradient of the initial first sub-model.

[0098] The first device updates the initial first sub-model based on at least one of the gradient, weight, and intermediate gradient of the initial first sub-model to obtain a trained first sub-model.

[0099] In a thirteenth aspect, an embodiment of the present application provides a model training method, which is performed by a second device or a circuit for a second device, and the method includes:

[0100] The second device receives seventh information from the first device, where the seventh information includes the eighth high-dimensional feature vector.

[0101] The second device obtains environmental training information, and obtains a ninth high-dimensional feature vector based on the environmental training information and the initial second sub-model.

[0102] The second device sends eighth information to the third device, where the eighth information includes the eighth high-dimensional feature vector and the ninth high-dimensional feature vector.

[0103] The second device receives ninth information from the third device, where the ninth information includes the updated second sub-model and at least one of the gradient, weight, and intermediate gradient of the initial first sub-model.

[0104] The second device sends tenth information to the first device, where the tenth information includes at least one of the gradient, weight, and intermediate gradient of the initial first sub-model.

[0105] In a fourteenth aspect, an embodiment of the present application provides a model training method, which is performed by a model training system. The system includes a first device and a second device, wherein a first sub-model of a wireless model is deployed on the first device, and a second sub-model of the wireless model is deployed on the second device. The method includes:

[0106] The first device obtains channel training information, and obtains a tenth high-dimensional feature vector based on the channel training information and the initial first sub-model.

[0107] The second device obtains environmental training information, and inputs the environmental training information into the initial second sub-model for processing to obtain an eleventh high-dimensional feature vector.

[0108] The second device sends twelfth information to the third device, where the twelfth information includes the eleventh high-dimensional feature vector. Correspondingly, the third device receives the twelfth information.

[0109] The third device inputs the eleventh high-dimensional feature vector into the downstream model for processing to obtain the output of the downstream model.

[0110] The third device calculates a loss value based on the output of the downstream model and the eleventh high-dimensional feature vector, and reversely updates the downstream model and the initial second sub-model based on the loss value to obtain an updated second sub-model.

[0111] The third device sends thirteenth information to the second device, where the thirteenth information includes the updated second sub-model. Correspondingly, the second device receives the thirteenth information.

[0112] The second device sends fourteenth information to the first device, where the fourteenth information includes the eleventh high-dimensional feature vector. Correspondingly, the first device receives the fourteenth information.

[0113] The first device obtains a spatial loss function according to the tenth high-dimensional eigenvector and the eleventh high-dimensional eigenvector.

[0114] The first device updates the initial first sub-model based on the spatial loss function to obtain a trained first sub-model.

[0115] Based on this processing, the trained first sub-model and second sub-model can be obtained.

[0116] In a fifteenth aspect, an embodiment of the present application provides a model training method, which is performed by a first device or a circuit for the first device, and the method includes:

[0117] The first device obtains channel training information, and obtains a tenth high-dimensional feature vector based on the channel training information and the initial first sub-model.

[0118] The first device receives fourteenth information from the second device, where the fourteenth information includes an eleventh high-dimensional feature vector.

[0119] The first device obtains a spatial loss function according to the tenth high-dimensional eigenvector and the eleventh high-dimensional eigenvector.

[0120] The first device updates the initial first sub-model based on the spatial loss function to obtain a trained first sub-model.

[0121] In a sixteenth aspect, an embodiment of the present application provides a model training method, which is performed by a second device or a circuit for a second device, the method comprising:

[0122] The second device obtains environmental training information, and inputs the environmental training information into the initial second sub-model for processing to obtain an eleventh high-dimensional feature vector.

[0123] The second device sends twelfth information to the third device, where the twelfth information includes the eleventh high-dimensional feature vector.

[0124] The second device receives thirteenth information from the third device, where the thirteenth information includes the updated second sub-model.

[0125] The second device sends fourteenth information to the first device, where the fourteenth information includes the eleventh high-dimensional feature vector.

[0126] In a seventeenth aspect, an embodiment of the present application provides an information processing device, which may include a transceiver module, wherein:

[0127] a transceiver module, configured to send first information to a second device, wherein the first information is used to request prediction of first environment information; the first information includes a first high-dimensional feature vector, wherein the first high-dimensional feature vector is obtained based on the first channel information and the first sub-model of the wireless model;

[0128] The transceiver module is also used to receive second information from the second device, where the second information includes predicted first environmental information, which is obtained by processing the first high-dimensional feature vector, the initialized first environmental information, and the second sub-model of the wireless model, wherein the first sub-model and the second sub-model of the wireless model are trained based on channel training information and first environmental training information, the first environmental training information is associated with the channel training information, and the predicted first environmental information is associated with the first channel information.

[0129] In one possible implementation, the first information also includes third environmental information, and the predicted first environmental information is obtained based on the first high-dimensional feature vector, the third environmental information, the initialized first environmental information, and the second sub-model of the wireless model, and the third environmental information is associated with the first channel information.

[0130] In one possible implementation, the first sub-model and the second sub-model of the wireless model are trained based on channel training information, first environment training information and second environment training information, and the second environment training information corresponds to the third environment information.

[0131] In an eighteenth aspect, an embodiment of the present application provides an information processing device, which may include a transceiver module and a processing module, wherein:

[0132] a transceiver module, configured to receive first information from a first device, the first information being used to request prediction of first environment information; the first information comprising a first high-dimensional feature vector, the first high-dimensional feature vector being obtained based on first channel information and a first sub-model of the wireless model;

[0133] a processing module, configured to obtain initialized first environmental information, and perform processing based on the first high-dimensional feature vector, the initialized first environmental information, and the second sub-model of the wireless model to obtain predicted first environmental information, wherein the first sub-model and the second sub-model of the wireless model are trained based on channel training information and first environmental training information, the first environmental training information is associated with the channel training information, and the predicted first environmental information is associated with the first channel information;

[0134] The transceiver module is further configured to send second information to the first device, where the second information includes the predicted first environment information.

[0135] In a possible implementation, the processing module is configured to:

[0136] Obtaining a fourth high-dimensional feature vector based on the initialized first environment information and the second sub-model;

[0137] The predicted first environmental information is obtained by performing processing based on the fourth high-dimensional feature vector and the first high-dimensional feature vector.

[0138] In one possible implementation, the first information also includes third environmental information, and the predicted first environmental information is obtained based on the first high-dimensional feature vector, the third environmental information, the initialized first environmental information, and the second sub-model of the wireless model, and the third environmental information is associated with the first channel information.

[0139] In one possible implementation, the first sub-model and the second sub-model of the wireless model are trained based on channel training information, first environment training information and second environment training information, and the second environment training information corresponds to the third environment information.

[0140] In a nineteenth aspect, an embodiment of the present application provides an information processing device, which may include a transceiver module for sending third information to a first device, where the third information is used to request prediction of first channel information; the third information includes a first high-dimensional feature vector, where the first high-dimensional feature vector is obtained based on the first environment information and the second sub-model of the wireless model;

[0141] The transceiver module is also used to receive fourth information from the first device, where the fourth information includes predicted first channel information, where the predicted first channel information is obtained based on the first high-dimensional feature vector, the initialized first channel information, and the first sub-model of the wireless model, wherein the first sub-model and the second sub-model of the wireless model are trained based on first channel training information and environmental training information, the environmental training information is associated with the first channel training information, and the predicted first channel information is associated with the first environmental information.

[0142] In one possible implementation, the third information also includes third channel information, the predicted first channel information is obtained based on the first high-dimensional feature vector, the initialized first channel information, the third channel information, and the first sub-model of the wireless model, and the third channel information is associated with the first environmental information.

[0143] In one possible implementation, the first sub-model and the second sub-model of the wireless model are trained based on the first channel training information, the second channel training information and the environment training information, and the second channel training information corresponds to the third channel information.

[0144] In a twentieth aspect, an embodiment of the present application provides an information processing device, which may include a transceiver module for receiving third information from a second device, wherein the third information is used to request prediction of first channel information; the third information includes a first high-dimensional feature vector, wherein the first high-dimensional feature vector is obtained based on the first environment information and the second sub-model of the wireless model;

[0145] a processing module, configured to obtain initialized first channel information, and perform processing based on the first high-dimensional feature vector, the initialized first channel information, and the first sub-model of the wireless model to obtain predicted first channel information, wherein the first sub-model and the second sub-model of the wireless model are trained based on first channel training information and environment training information, the environment training information is associated with the first channel training information, and the predicted first channel information is associated with the first environment information;

[0146] The transceiver module is further configured to send fourth information to the second device, where the fourth information includes the predicted first channel information.

[0147] In a possible implementation, the processing module is configured to:

[0148] Obtaining a fifth high-dimensional feature vector based on the initialized first channel information and the first sub-model;

[0149] Processing is performed based on the fifth high-dimensional feature vector and the first high-dimensional feature vector to obtain the predicted first channel information.

[0150] In one possible implementation, the third information also includes third channel information, the predicted first channel information is obtained based on the first high-dimensional feature vector, the initialized first channel information, the third channel information, and the first sub-model of the wireless model, and the third channel information is associated with the first environmental information.

[0151] In one possible implementation, the first sub-model and the second sub-model of the wireless model are trained based on the first channel training information, the second channel training information and the environment training information, and the second channel training information corresponds to the third channel information.

[0152] In a twenty-first aspect, an embodiment of the present application provides a model training device, which may include a processing module for: obtaining channel training information, and obtaining a sixth high-dimensional feature vector based on the channel training information and an initial first sub-model;

[0153] a transceiver module, configured to send fifth information to the second device, where the fifth information includes the sixth high-dimensional feature vector;

[0154] The transceiver module is further configured to receive sixth information from the second device, wherein the sixth information includes updated parameters of the first sub-model;

[0155] The processing module is further used to update the initial first sub-model according to the update parameters of the first sub-model to obtain a trained first sub-model.

[0156] In a twenty-second aspect, an embodiment of the present application provides a model training device, which may include a transceiver module for receiving fifth information from a first device, wherein the fifth information includes a sixth high-dimensional feature vector;

[0157] a processing module, configured to obtain environmental training information, and obtain a seventh high-dimensional feature vector based on the environmental training information and the initial second sub-model;

[0158] The processing module is further configured to perform optimization based on the sixth high-dimensional eigenvector and the seventh high-dimensional eigenvector to obtain updated parameters of the second sub-model and the first sub-model;

[0159] The transceiver module is further used to send sixth information to the first device, where the sixth information includes updated parameters of the first sub-model.

[0160] In a twenty-third aspect, an embodiment of the present application provides a model training device, which may include a processing module for obtaining channel training information and obtaining an eighth high-dimensional feature vector based on the channel training information and an initial first sub-model;

[0161] The transceiver module is configured to send seventh information to the second device, where the seventh information includes the eighth high-dimensional feature vector.

[0162] The transceiver module is also used to receive tenth information from the second device, where the tenth information includes at least one of the gradient, weight, and intermediate gradient of the initial first sub-model.

[0163] The processing module is also used to update the initial first sub-model based on at least one of the gradient, weight, and intermediate gradient of the initial first sub-model to obtain a trained first sub-model.

[0164] In a twenty-fourth aspect, an embodiment of the present application provides a model training device, which may include a transceiver module for receiving seventh information from a first device, where the seventh information includes the eighth high-dimensional feature vector;

[0165] a processing module, configured to obtain environmental training information, and obtain a ninth high-dimensional feature vector based on the environmental training information and the initial second sub-model;

[0166] The transceiver module is further configured to send eighth information to the third device, where the eighth information includes the eighth high-dimensional feature vector and the ninth high-dimensional feature vector;

[0167] The transceiver module is further configured to receive ninth information from the third device, wherein the ninth information includes the updated second sub-model and at least one of the gradient, weight, and intermediate gradient of the initial first sub-model;

[0168] The transceiver module is also used to send tenth information to the first device, where the tenth information includes at least one of the gradient, weight, and intermediate gradient of the initial first sub-model.

[0169] In a twenty-fifth aspect, an embodiment of the present application provides a model training device, which may include a processing module for obtaining channel training information and obtaining a tenth high-dimensional feature vector based on the channel training information and an initial first sub-model;

[0170] a transceiver module, configured to receive fourteenth information from the second device, the fourteenth information including an eleventh high-dimensional feature vector;

[0171] The processing module is further used to obtain a spatial loss function according to the tenth high-dimensional eigenvector and the eleventh high-dimensional eigenvector.

[0172] The processing module is further used to update the initial first sub-model based on the spatial loss function to obtain a trained first sub-model.

[0173] In a twenty-sixth aspect, an embodiment of the present application provides a model training device, which may include a processing module for obtaining environmental training information and inputting the environmental training information into an initial second sub-model for processing to obtain an eleventh high-dimensional feature vector;

[0174] The transceiver module is configured to send twelfth information to a third device, where the twelfth information includes the eleventh high-dimensional feature vector.

[0175] The transceiver module is further configured to receive thirteenth information from a third device, where the thirteenth information includes an updated second sub-model.

[0176] The transceiver module is further configured to send fourteenth information to the first device, where the fourteenth information includes the eleventh high-dimensional feature vector.

[0177] In aspect 27, the present application provides an information processing device (or communication device) comprising at least one processor, wherein the at least one processor is used to execute a method provided in any possible implementation of the second aspect, or a method provided in any possible implementation of the third aspect, or a method provided in any possible implementation of the fourth aspect, or a method provided in any possible implementation of the fifth aspect, or a method provided in any possible implementation of the sixth aspect, or a method provided in any possible implementation of the seventh aspect.

[0178] In one possible implementation, the device also includes a memory; wherein the memory is used to store program code, and the processor is used to call the program code to execute the method provided in any possible implementation of the second aspect, or the method provided in any possible implementation of the third aspect, or the method provided in any possible implementation of the fourth aspect, or the method provided in any possible implementation of the fifth aspect, or the method provided in any possible implementation of the sixth aspect, or the method provided in any possible implementation of the seventh aspect.

[0179] In aspect 28, the present application provides a model training device comprising at least one processor, wherein the at least one processor is used to execute the method provided in any possible implementation manner of aspect 8, or the method provided in any possible implementation manner of aspect 9, or the method provided in any possible implementation manner of aspect 10; or the method provided in any possible implementation manner of aspect 11, or the method provided in any possible implementation manner of aspect 12; or the method provided in any possible implementation manner of aspect 13, or the method provided in any possible implementation manner of aspect 14; or the method provided in any possible implementation manner of aspect 15; or the method provided in any possible implementation manner of aspect 16.

[0180] In one possible implementation, the device also includes a memory; wherein the memory is used to store program code, and the processor is used to call the program code to execute the method provided in any possible implementation manner of the eighth aspect, or the method provided in any possible implementation manner of the ninth aspect, or the method provided in any possible implementation manner of the tenth aspect; or the method provided in any possible implementation manner of the eleventh aspect, or the method provided in any possible implementation manner of the twelfth aspect; or the method provided in any possible implementation manner of the thirteenth aspect, or the method provided in any possible implementation manner of the fourteenth aspect; or the method provided in any possible implementation manner of the fifteenth aspect; or the method provided in any possible implementation manner of the sixteenth aspect.

[0181] In aspect 29, the present application provides an information processing system, comprising a module provided by any possible implementation of any aspect of aspect 17, and a module provided by any possible implementation of any aspect of aspect 18; or, comprising a module provided by any possible implementation of any aspect of aspect 19, and a module provided by any possible implementation of any aspect of aspect 20.

[0182] In aspect 30, the present application provides a model training system, comprising a module provided by any possible implementation of any aspect of aspect 21, and a module provided by any possible implementation of any aspect of aspect 22; or, comprising a module provided by any possible implementation of any aspect of aspect 23, and a module provided by any possible implementation of any aspect of aspect 24; or, comprising a module provided by any possible implementation of any aspect of aspect 25, and a module provided by any possible implementation of any aspect of aspect 26.

[0183] In aspect 31, the present application provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program or instructions, and the computer program or instructions are executed by a processor to implement a method provided in any possible implementation of any aspect from aspect 2 to aspect 16.

[0184] In aspect 32, the present application provides a computer program product, characterized in that when the computer program product is run on a computer, the computer is caused to execute a method provided in any possible implementation of any aspect from aspect 2 to aspect 16.

[0185] It is understandable that the apparatuses described in aspects 17 to 28, the system described in aspect 29, the system described in aspect 30, the computer-readable storage medium described in aspect 31, or the computer program product described in aspect 32 are all used to perform the method provided in any one of aspects 2 to 16. Therefore, the beneficial effects that can be achieved can be referenced to the beneficial effects of the corresponding methods and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0186] The following is an introduction to the drawings used in the embodiments of this application.

[0187] FIG1 is a simplified schematic diagram of a wireless communication system provided by an embodiment of the present application;

[0188] FIG2a is a schematic diagram of a communication system provided by an embodiment of the present application;

[0189] FIG2b is a schematic diagram of another communication system provided in an embodiment of the present application;

[0190] FIG3a is a schematic diagram of a possible application framework in a communication system provided in an embodiment of the present application;

[0191] FIG3 b is a schematic diagram of another possible application framework in the communication system provided in an embodiment of the present application;

[0192] FIG4 is a schematic diagram of an encoder and a decoder provided in an embodiment of the present application;

[0193] FIG5 is a schematic diagram of an AI application framework provided in an embodiment of the present application;

[0194] FIG6 is a schematic structural diagram of a wireless model provided in an embodiment of the present application;

[0195] FIG7 is a flow chart of an information processing method provided in an embodiment of the present application;

[0196] FIG8 is a flow chart of another information processing method provided in an embodiment of the present application;

[0197] FIG9 is a schematic diagram of an application of a wireless model provided in an embodiment of the present application;

[0198] FIG10 is a schematic diagram of a training of a wireless model provided in an embodiment of the present application;

[0199] FIG11 is a schematic diagram of another wireless model training embodiment provided in the present application;

[0200] FIG12 is a schematic diagram of training of another wireless model provided in an embodiment of the present application;

[0201] FIG13 is a schematic structural diagram of an information processing device provided in an embodiment of the present application;

[0202] FIG14 is a schematic structural diagram of another information processing device provided in an embodiment of the present application;

[0203] FIG15 is a schematic structural diagram of another information processing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0204] The following describes the embodiments of the present application in conjunction with the accompanying drawings. The terms used in the implementation methods of the embodiments of the present application are only used to explain the specific embodiments of the present application and are not intended to limit the present application.

[0205] In order to make the objectives, technical solutions and advantages of the present disclosure more clear, the present disclosure will be further described in detail below with reference to the accompanying drawings.

[0206] The present disclosure relates to at least one (item) as follows, indicating one (item) or more (items). More than one (item) refers to two (items) or more than two (items). "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. In addition, it should be understood that although the terms first, second, etc. may be used to describe each object in the present disclosure, these objects should not be limited to these terms. These terms are only used to distinguish each object from each other.

[0207] The terms "including" and "having" and any variations thereof mentioned in the following description of the present disclosure are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes other steps or units that are not listed, or optionally includes other steps or units that are inherent to these processes, methods, products or devices. It should be noted that in the present disclosure, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any method or design described in the present disclosure as "exemplary" or "for example" should not be interpreted as being more preferred or more advantageous than other methods or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a concrete way.

[0208] It should be noted that in this application, "send" can be understood as "output" and "receive" can be understood as "input". "Send information to A", where "to A" only indicates the direction of information transmission, A is the destination, and does not limit "sending information to A" to direct transmission on the air interface. "Sending information to A" includes sending information directly to A, and also includes sending information indirectly to A through a transmitter, so "sending information to A" can also be understood as "outputting information to A". Similarly, "receiving information from A" indicates that the source of the information is A, including receiving information directly from A, and also including receiving information indirectly from A through a receiver, so "receiving information from A" can also be understood as "inputting information from A".

[0209] It is understood that, in this application, "indication" can include direct indication, indirect indication, explicit indication, and implicit indication. When describing a certain indication information as indicating A, it can be understood that the indication information carries A, directly indicates A, or indirectly indicates A. In this application, the information indicated by the indication information is referred to as the information to be indicated. In the specific implementation process, there are many ways to indicate the information to be indicated. For example, but not limited to, the information to be indicated can be directly indicated, such as the information to be indicated itself or an index of the information to be indicated, or it can be indirectly indicated by indicating other information, where there is an association between the other information and the information to be indicated. It is also possible to indicate only a part of the information to be indicated, while the rest of the information to be indicated is known or agreed in advance. For example, it is also possible to indicate specific information by using a pre-agreed (e.g., protocol-specified) order of arrangement of various information, thereby reducing the indication overhead to a certain extent. The information to be indicated can be sent as a whole or divided into multiple sub-information and sent separately, and the sending period and / or sending time of these sub-information can be the same or different. The specific sending method is not limited in this application. The sending period and / or sending timing of these sub-information may be predefined, for example, predefined according to a protocol, or may be configured by the transmitting end device by sending configuration information to the receiving end device.

[0210] The technology provided by the present disclosure can be applied to various communication systems, for example, the communication system can be a fifth generation (5G) or new radio (NR) system, a long term evolution (LTE) system, an LTE frequency division duplex (FDD) system, an LTE time division duplex (TDD) system, a wireless local area network (WLAN) system, a satellite communication system, a future communication system such as a sixth generation (6G) mobile communication system, or a fusion system of multiple systems. The technical solution provided by the present application can also be applied to device to device (D2D) communication, vehicle-to-everything (V2X) communication, machine to machine (M2M) communication, machine type communication (MTC), and Internet of Things (IoT) communication systems or other communication systems.

[0211] A device in a communication system can send a signal to another device or receive a signal from another device. The signal may include information, signaling, or data, etc. The device can also be replaced by an entity, a network entity, a network element, a communication device, a communication module, a node, a communication node, etc. The present disclosure uses the device as an example for description. For example, the communication system may include at least one terminal device and at least one access network device. The access network device can send a downlink signal to the terminal device, and / or the terminal device can send an uplink signal to the access network device. In addition, it can be understood that if the communication system includes multiple terminal devices, the multiple terminal devices can also send signals to each other, that is, the signal sending device and the signal receiving device can both be terminal devices.

[0212] The information generation method provided in the embodiment of the present application can be applied to wireless communication systems such as 5G, 6G, and satellite communications. Referring to Figure 1, Figure 1 is a simplified schematic diagram of the wireless communication system provided in the embodiment of the present application. As shown in Figure 1, the wireless communication system includes a wireless access network 100. The wireless access network 100 can be a next-generation (e.g., 6G or higher) wireless access network, or a traditional (e.g., 5G, 4G, 3G, or 2G) wireless access network. One or more communication devices (120a-120j, collectively referred to as 120) can be connected to each other or to one or more network devices (110a, 110b, collectively referred to as 110) in the wireless access network 100. Optionally, Figure 1 is only a schematic diagram, and the wireless communication system may also include other devices, such as core network devices, wireless relay devices, and / or wireless backhaul devices, which are not shown in Figure 1.

[0213] Optionally, in actual applications, the wireless communication system may include multiple network devices (also called access network devices) or multiple communication devices at the same time. A network device may serve one or more communication devices at the same time. A communication device may also access one or more network devices at the same time. The embodiments of the present application do not limit the number of communication devices and network devices included in the wireless communication system.

[0214] The network device may be an entity on the network side for transmitting or receiving signals. The network device may be an access device for a communication device to access the wireless communication system in a wireless manner, such as a base station. The base station can broadly cover various names as follows, or be replaced with the following names, such as: NodeB, evolved NodeB (eNB), next generation NodeB (gNB), access network equipment in open radio access network (O-RAN), relay station, access point, transmission point (transmit / receive point or transmitting and receiving point, TRP), transmission point (transmit point or transmitting point, TP), master eNodeB (MeNB), secondary eNodeB (SeNB), multi-standard radio (MSR) node, home base station, network controller, access node, wireless node, access point (AP), transmission node, transceiver node, baseband unit (BBU), remote radio unit (RRU), active antenna unit (AAU), remote radio head (RRH), central unit (CU), distributed unit (DUT), etc. unit, DU), radio unit (radio unit, RU), centralized unit control plane (CU control plane, CU-CP) node, centralized unit user plane (CU user plane, CU-UP) node, positioning node, etc. The base station can be a macro base station, a micro base station, a relay node, a donor node or the like, or a combination thereof. The network device can also refer to a communication module, a modem or a chip for being set in the aforementioned device or apparatus. The network device can also be a mobile switching center and a device that performs the base station function in device-to-device (D2D), vehicle-to-everything (V2X), and machine-to-machine (M2M) communications, a network side device in a 6G network, and a device that performs the base station function in a future communication system. The network device can support networks with the same or different access technologies. The embodiments of the present application do not limit the specific technology and specific device form adopted by the network device.

[0215] Network devices can be fixed or mobile. For example, base stations 110a and 110b are stationary and are responsible for wireless transmission and reception in one or more cells from communication device 120. The helicopter or drone 120i shown in Figure 1 can be configured to act as a mobile base station, and one or more cells can move according to the location of the mobile base station 120i. In other examples, the helicopter or drone (120i) can be configured to act as a communication device communicating with base station 110b.

[0216] In the present disclosure, the communication device used to implement the above-mentioned access network functions can be an access network device, a network device that has some of the access network functions, or a device that can support the implementation of the access network functions, such as a chip system, a hardware circuit, a software module, or a hardware circuit and a software module. The device can be installed in the access network device or used in conjunction with the access network device. The method of the present disclosure is described using the example of the communication device used to implement the access network device functions being an access network device.

[0217] A communication device may be an entity on the user side for receiving or transmitting signals, such as a mobile phone. A communication device may be used to connect people, objects, and machines. A communication device may communicate with one or more core networks through a network device. A communication device includes a handheld device with wireless connection capabilities, other processing devices connected to a wireless modem, or an on-board device. A communication device may be a portable, pocket-sized, handheld, computer-built-in, or vehicle-mounted mobile device. The communication device 120 may be widely used in various scenarios, such as cellular communication, device-to-device D2D, vehicle-to-everything V2X, peer-to-peer (P2P), machine-to-machine M2M, machine-type communication MTC, Internet of Things (IoT), virtual reality (VR), augmented reality (AR), industrial control, autonomous driving, telemedicine, smart grid, smart furniture, smart office, smart wearables, smart transportation, smart city, drones, robots, remote sensing, passive sensing, positioning, navigation and tracking, autonomous delivery and mobility, etc. Some examples of the communication device 120 include: user equipment (UE) of the 3GPP standard, fixed devices, mobile devices, handheld devices, wearable devices, cellular phones, smart phones, Session Initialization Protocol (SIP) phones, laptops, personal computers, smart books, vehicles, satellites, Global Positioning System (GPS) devices, target tracking devices, drones, helicopters, aircraft, ships, remote control devices, smart home devices, industrial devices, personal communication service (PCS) phones, wireless local loop (WLL) stations, personal digital assistants (PDAs), wireless network cameras, tablet computers, handheld computers, mobile internet devices (MIDs), wearable devices such as smart watches, virtual reality (VR) devices, augmented reality (AR) devices, wireless terminals in industrial control, terminals in vehicle networking systems, wireless terminals in self-driving cars, wireless terminals in smart grids, wireless terminals in transportation safety, and smart cities. Wireless terminals in smart cities, such as smart gas pumps, terminal equipment on high-speed trains, and wireless terminals in smart homes, such as smart speakers, smart coffee machines, and smart printers.The communication device 120 can be a wireless device in the above various scenarios or a device used to be set in a wireless device, for example, a communication module, modem or chip in the above devices. The communication device can also be called a terminal, terminal device, user equipment UE, mobile station (MS), mobile terminal (MT), etc. The communication device can also be a communication device in a future wireless communication system. The communication device can be used in a dedicated network device or a general device. The embodiments of the present application do not limit the specific technology and specific device form adopted by the communication device.

[0218] Alternatively, a communication device can function as a base station. For example, a UE can function as a dispatching entity, providing sidelink signals between UEs in V2X, D2D, or P2P scenarios. As shown in Figure 1 , a cell phone 120a and a car 120b communicate with each other using sidelink signals. Cell phone 120a and smart home device 120e communicate without relaying the communication signals through base station 110b.

[0219] In the present disclosure, a communication device for realizing the functions of a communication device may be a terminal device, or a terminal device having some of the functions of the above communication devices, or a device capable of supporting the functions of the above communication devices, such as a chip system, which may be installed in the terminal device or used in combination with the terminal device. In the present disclosure, a chip system may be composed of a chip, or may include a chip and other discrete devices. In the technical solution provided in the present disclosure, the communication device is described as a terminal device or UE as an example.

[0220] Optionally, a wireless communication system is typically composed of cells, with base stations providing cell management and communication services to multiple mobile stations (MS) in the cell. The base station includes a baseband unit (BBU) and a remote radio unit (RRU). The BBU and RRU can be placed in different locations, for example: the RRU is remote and placed in an area with high traffic volume, while the BBU is placed in a central computer room. The BBU and RRU can also be placed in the same computer room. The BBU and RRU can also be different components under the same rack. Optionally, a cell can correspond to a carrier or component carrier.

[0221] It can be understood that the present disclosure can be applied between a network device and a communication device, between a network device and a network device, or between a communication device and a communication device, that is, between a primary device and a secondary device. The primary device can be a network device or a communication device. When the primary device is a network device, the secondary device can be another network device or a communication device. When the primary device is a communication device, the secondary device can be another communication device.

[0222] The following describes the solution using the example of a primary device being a network device, such as an access network device, and a secondary device being a communication device, such as a terminal device. The downlink communication direction is from the primary device to the secondary device, and the uplink communication direction is from the secondary device to the primary device.

[0223] Protocol layer structure between access network equipment and terminal equipment

[0224] The communication between the access network device and the terminal device follows a certain protocol layer structure. The protocol layer structure may include a control plane protocol layer structure and a user plane protocol layer structure. For example, the control plane protocol layer structure may include the functions of protocol layers such as the radio resource control (RRC) layer, the packet data convergence protocol (PDCP) layer, the radio link control (RLC) layer, the medium access control (MAC) layer, and the physical layer. For example, the user plane protocol layer structure may include the functions of protocol layers such as the PDCP layer, the RLC layer, the MAC layer, and the physical layer. In one possible implementation, a service data adaptation protocol (SDAP) layer may also be included above the PDCP layer.

[0225] Optionally, the protocol layer structure between the access network device and the terminal may also include an artificial intelligence (AI) layer for transmitting data related to AI functions.

[0226] Taking data transmission between access network equipment and terminal devices as an example, data transmission needs to pass through the user plane protocol layers, such as the SDAP layer, PDCP layer, RLC layer, MAC layer, and physical layer. The SDAP layer, PDCP layer, RLC layer, MAC layer, and physical layer can also be collectively referred to as the access layer. Data transmission is divided into sending or receiving based on the direction of transmission, and each of these layers is further divided into a sending part and a receiving part. Taking downlink data transmission as an example, after the PDCP layer obtains data from the upper layer, it transmits the data to the RLC layer and MAC layer. The MAC layer then generates a transport block, which is then wirelessly transmitted through the physical layer. Data is encapsulated accordingly in each layer. For example, data received by a layer from the layer above it is considered a service data unit (SDU) of that layer. After encapsulation by that layer, it becomes a protocol data unit (PDU) and is then passed to the next layer.

[0227] For example, a terminal device may also have an application layer and a non-access layer. The application layer can be used to provide services to applications installed in the terminal device. For example, downlink data received by the terminal device can be sequentially transmitted from the physical layer to the application layer, and then provided by the application layer to the application. For another example, the application layer can obtain data generated by the application and sequentially transmit the data to the physical layer for transmission to other communication devices. The non-access layer can be used to forward user data, such as forwarding uplink data received from the application layer to the SDAP layer, or forwarding downlink data received from the SDAP layer to the application layer.

[0228] Structure of access network equipment

[0229] The access network equipment may include a centralized unit (CU) and a distributed unit (DU). Multiple DUs may be centrally controlled by one CU. As an example, the interface between the CU and the DU may be referred to as an F1 interface. Among them, the control plane (CP) interface may be F1-C, and the user plane (UP) interface may be F1-U. The CU and DU may be divided according to the protocol layers of the wireless network: for example, the functions of the PDCP layer and above protocol layers are set in the CU, and the functions of the protocol layers below the PDCP layer (such as the RLC layer and the MAC layer, etc.) are set in the DU; for another example, the functions of the protocol layers above the PDCP layer are set in the CU, and the functions of the protocol layers below the PDCP layer are set in the DU.

[0230] It is understandable that the above division of the processing functions of CU and DU according to the protocol layer is only an example, and can also be divided in other ways, for example, the CU or DU can be divided into functions with more protocol layers, and for example, the CU or DU can also be divided into partial processing functions with the protocol layer. In one design, some functions of the RLC layer and the functions of the protocol layers above the RLC layer are set in the CU, and the remaining functions of the RLC layer and the functions of the protocol layers below the RLC layer are set in the DU. In another design, the functions of the CU or DU can also be divided according to the service type or other system requirements, for example, by delay, the functions whose processing time needs to meet the delay requirements are set in the DU, and the functions that do not need to meet the delay requirements are set in the CU. In another design, the CU can also have one or more functions of the core network. For example, the CU can be set on the network side to facilitate centralized management. In another design, the RU of the DU is set remotely. Among them, the RU has a radio frequency function.

[0231] Optionally, the DU and the RU may be divided at the physical layer (PHY). For example, the DU may implement high-level functions in the PHY layer, and the RU may implement low-level functions in the PHY layer. When used for transmission, the functions of the PHY layer may include adding cyclic redundancy check (CRC) codes, channel coding, rate matching, scrambling, modulation, layer mapping, precoding, resource mapping, physical antenna mapping, and / or RF transmission functions. When used for reception, the functions of the PHY layer may include CRC, channel decoding, rate matching, descrambling, demodulation, layer mapping, channel detection, resource demapping, physical antenna demapping, and / or RF reception functions. The high-level functions in the PHY layer may include a portion of the functions of the PHY layer, such as a portion of the functions that is closer to the MAC layer, and the low-level functions in the PHY layer may include another portion of the functions of the PHY layer, such as a portion of the functions that is closer to the RF functions. For example, the high-level functions in the PHY layer may include adding CRC codes, channel coding, rate matching, scrambling, modulation, and layer mapping, and the low-level functions in the PHY layer may include precoding, resource mapping, physical antenna mapping, and RF transmission functions; or, the high-level functions in the PHY layer may include adding CRC codes, channel coding, rate matching, scrambling, modulation, layer mapping, and precoding, and the low-level functions in the PHY layer may include resource mapping, physical antenna mapping, and RF transmission functions.

[0232] For example, the functions of the CU can be implemented by one entity, or by different entities. For example, the functions of the CU can be further divided, that is, the control plane and the user plane are separated and implemented by different entities, namely the control plane CU entity (i.e., CU-CP entity) and the user plane CU entity (i.e., CU-UP entity). The CU-CP entity and the CU-UP entity can be coupled with the DU to jointly complete the functions of the access network device.

[0233] In the above architecture, signaling generated by the CU can be sent to the terminal device via the DU, and vice versa. For example, RRC or PDCP layer signaling is ultimately processed into physical layer signaling and sent to the terminal device, or converted from received physical layer signaling. In this architecture, the RRC or PDCP layer signaling can be considered to be sent via the DU, or via the DU and RU.

[0234] Optionally, any of the above-mentioned DU, CU, CU-CP, CU-UP, and RU can be a software module, a hardware structure, or a software module + hardware structure, without limitation. The existence forms of different entities can be different and are not limited. For example, DU, CU, CU-CP, and CU-UP are software modules, and RU is a hardware structure. These modules and their execution methods are also within the scope of protection of this disclosure.

[0235] The access network equipment may support one or more types of fronthaul interfaces, and different fronthaul interfaces correspond to DUs and RUs with different functions. If the fronthaul interface between the DU and the RU is a common public radio interface (CPRI), the DU is configured to implement one or more baseband functions, and the RU is configured to implement one or more radio frequency functions. If the fronthaul interface between the DU and the RU is another type of interface, relative to the CPRI, some of the downlink and / or uplink baseband functions, such as precoding, digital beamforming (BF), or one or more of inverse fast Fourier transform (IFFT) / cyclic prefix (CP) for downlink, are moved from the DU to the RU for implementation; and for uplink, one or more of digital beamforming (BF), or fast Fourier transform (FFT) / cyclic prefix (CP) removal, are moved from the DU to the RU for implementation. In one possible implementation, the interface may be an enhanced common public radio interface (eCPRI). In the eCPRI architecture, the division between the DU and RU is different, corresponding to different types (category, Cat) of eCPRI, such as eCPRI Cat A, B, C, D, E, and F.

[0236] Taking eCPRI Cat A as an example, for downlink transmission, based on layer mapping, the DU is configured to implement layer mapping and one or more functions preceding it (i.e., one or more of coding, rate matching, scrambling, modulation, and layer mapping). Other functions after layer mapping (e.g., resource element (RE) mapping, digital beamforming (BF), or one or more of inverse fast Fourier transform (IFFT) / cyclic prefix (CP) addition) are moved to the RU for implementation. For uplink transmission, based on RE demapping, the DU is configured to implement demapping and one or more functions preceding it (i.e., one or more of decoding, rate matching, descrambling, demodulation, inverse discrete Fourier transform (IDFT), channel equalization, and RE demapping). Other functions after demapping (e.g., one or more of digital BF or fast Fourier transform (FFT) / CP removal) are moved to the RU for implementation. It is understandable that for the functional description of DU and RU corresponding to various types of eCPRI, reference can be made to the eCPRI protocol, which will not be described in detail here.

[0237] In one possible design, the processing unit for implementing baseband functions in the BBU is called a baseband high layer (BBH) unit, and the processing unit for implementing baseband functions in the RRU / AAU / RRH is called a baseband low layer (BBL) unit.

[0238] In different systems, CU (or CU-CP and CU-UP), DU or RU may also have different names, but those skilled in the art can understand their meanings. For example, in an open radio access network (open RAN, ORAN) system, CU may also be referred to as O-CU (open CU), DU may also be referred to as O-DU, CU-CP may also be referred to as O-CU-CP, CU-UP may also be referred to as O-CU-UP, and RU may also be referred to as O-RU. Any of the CU (or CU-CP, CU-UP), DU and RU in this application may be implemented by a software module, a hardware module, or a combination of a software module and a hardware module.

[0239] In the embodiments of the present application, the device for implementing the functions of the network device can be a network device; it can also be a device that can support the network device to implement the functions, such as a chip system, a hardware circuit, a software module, or a hardware circuit and a software module. The device can be installed in the network device or used in conjunction with the network device. In the embodiments of the present application, only the device for implementing the functions of the network device is used as an example to illustrate, and does not constitute a limitation on the solutions of the embodiments of the present application.

[0240] The network device and / or terminal device can be deployed on land, including indoors or outdoors, handheld or vehicle-mounted; it can also be deployed on the water surface; it can also be deployed on aircraft, balloons and satellites in the air. The embodiments of this application do not limit the scenarios in which the network device and the terminal device are located. In addition, the terminal device and the network device can be hardware devices, or they can be software functions running on dedicated hardware, software functions running on general-purpose hardware, such as virtualization functions instantiated on a platform (e.g., a cloud platform), or entities including dedicated or general-purpose hardware devices and software functions. This application does not limit the specific forms of the terminal device and the network device.

[0241] It should be understood that the number and type of each device in the communication system shown in Figure 1 are for illustration only, and the present disclosure is not limited thereto. In actual applications, the communication system may also include more terminal devices, more access network devices, and other network elements, such as core network devices and / or network elements for implementing artificial intelligence functions. Among them, the network element for implementing artificial intelligence functions may be a RAN intelligent controller (RIC). Figure 2a is a schematic diagram of a communication system applicable to an embodiment of the present application. As shown in Figure 2a, the communication system 200 may include at least one network device, such as the network device 210 shown in Figure 2a; the communication system 200 may also include at least one terminal device, such as the terminal device 220 and the terminal device 230 shown in Figure 2a. The network device 210 and the terminal device (such as the terminal device 220 and the terminal device 230) can communicate via a wireless link. The communication devices in the communication system, such as the network device 210 and the terminal device 220, can communicate using multi-antenna technology.

[0242] Figure 2b is a schematic diagram of another communication system applicable to an embodiment of the present application. Compared to the communication system 200 shown in Figure 2a, the communication system 300 shown in Figure 2b also includes an AI network element 240. AI network element 240 is used to perform AI-related operations, such as constructing a training dataset or training an AI model.

[0243] In one possible implementation, the network device 210 may send data related to the training of the AI ​​model to the AI ​​network element 240, which constructs a training data set and trains the AI ​​model. For example, the data related to the training of the AI ​​model may include data reported by the terminal device. The AI ​​network element 240 may send the results of the operations related to the AI ​​model to the network device 210, and forward them to the terminal device through the network device 210. For example, the results of the operations related to the AI ​​model may include at least one of the following: an AI model that has completed training, an evaluation result or a test result of the model, etc. Exemplarily, a portion of the trained AI model may be deployed on the network device 210, and another portion may be deployed on the terminal device. Alternatively, the trained AI model may be deployed on the network device 210. Alternatively, the trained AI model may be deployed on the terminal device.

[0244] It should be understood that Figure 2b illustrates only the example of a direct connection between AI network element 240 and network device 210. In other scenarios, AI network element 240 may also be connected to a terminal device. Alternatively, AI network element 240 may be connected to both network device 210 and a terminal device simultaneously. Alternatively, AI network element 240 may be connected to network device 210 via a third-party network element (also referred to as a third-party device or third-party entity). This embodiment of the present application does not limit the connection relationship between the AI ​​network element and other network elements.

[0245] The AI ​​network element 240 may also be provided as a module in a network device and / or a terminal device, for example, in the network device 210 or the terminal device shown in FIG. 2 a .

[0246] It should be noted that Figures 2a and 2b are simplified schematic diagrams for ease of understanding. For example, the communication system may also include other devices, such as wireless relay devices and / or wireless backhaul devices, which are not shown in Figures 2a and 2b. In actual applications, the communication system may include multiple network devices and multiple terminal devices. The embodiments of the present application do not limit the number of network devices and terminal devices included in the communication system.

[0247] In order to support AI technology in wireless networks, AI nodes may also be introduced into the network.

[0248] Optionally, the AI ​​node can be deployed in one or more of the following locations in the communication system: access network equipment, terminal equipment, or core network equipment. Alternatively, the AI ​​node can be deployed separately, for example, in a location other than any of the above devices, such as a host or cloud server in an over-the-top (OTT) system. The AI ​​node can communicate with other devices in the communication system, such as one or more of the following: network equipment, terminal equipment, or core network elements.

[0249] It is understood that this application does not limit the number of AI nodes. For example, when there are multiple AI nodes, the multiple AI nodes can be divided based on function, such as different AI nodes are responsible for different functions.

[0250] It can also be understood that AI nodes can be independent devices, or they can be integrated into the same device to implement different functions, or they can be network elements in hardware devices, or they can be software functions running on dedicated hardware, or they can be virtualized functions instantiated on a platform (for example, a cloud platform). This application does not limit the specific form of the above-mentioned AI nodes.

[0251] An AI node can be an AI network element or an AI module.

[0252] Figure 3a is a schematic diagram of a possible application framework in a communication system. As shown in Figure 3a, network elements in the communication system are connected through interfaces (such as NG, Xn) or air interfaces. One or more AI modules are provided in one or more devices of these network element nodes, such as core network equipment, access network (radio access network, RAN) nodes, terminals, and network management (operation, administration and maintenance, OAM) (for clarity, only one is shown in Figure 3a). The access network node can be a separate RAN node, or it can include multiple RAN nodes, for example, including CU and DU. The CU and / or DU can also be provided with one or more AI modules. Optionally, the CU can also be split into CU-CP and CU-UP. One or more AI models are provided in the CU-CP and / or CU-UP.

[0253] The AI ​​module is used to implement the corresponding AI function. The AI ​​modules deployed in different network elements may be the same or different. The model of the AI ​​module can implement different functions according to different parameter configurations. The model of the AI ​​module can be configured based on one or more of the following parameters: structural parameters (such as the number of neural network layers, the width of the neural network, the connection relationship between layers, the weight of the neuron, the activation function of the neuron, or at least one of the bias in the activation function), input parameters (such as the type of input parameters and / or the dimension of the input parameters), or output parameters (such as the type of output parameters and / or the dimension of the output parameters). Among them, the bias in the activation function can also be called the bias of the neural network.

[0254] An AI module can have one or more models. A model can infer an output, which includes one or more parameters. The learning, training, or inference processes of different models can be deployed on different nodes or devices, or on the same node or device.

[0255] Figure 3b is a schematic diagram of another possible application framework in a communication system. As shown in Figure 3b, the communication system includes a RAN intelligent controller (RIC). For example, the RIC can be the AI ​​module in Figure 3a, which is used to implement AI-related functions. The RIC includes a near-real-time RIC (near-real time RIC, near-RT RIC) and a non-real-time RIC (non-real time RIC, Non-RT RIC). Among them, the non-real-time RIC mainly processes non-real-time information, such as data that is not sensitive to delay, and the delay of this data can be in the order of seconds. The real-time RIC mainly processes near-real-time information, such as data that is relatively sensitive to delay, and the delay of this data is in the order of tens of milliseconds.

[0256] The near real-time RIC is used for model training and reasoning. For example, it is used to train an AI model and use the AI ​​model for reasoning. The near real-time RIC can obtain network-side and / or terminal-side information from a RAN node (e.g., CU, CU-CP, CU-UP, DU, and / or RU) and / or a terminal. This information can be used as training data or reasoning data. Optionally, the near real-time RIC can deliver the reasoning result to the RAN node and / or the terminal. Optionally, the reasoning result can be exchanged between the CU and the DU, and / or between the DU and the RU. For example, the near real-time RIC delivers the reasoning result to the DU, and the DU sends it to the RU.

[0257] The non-real-time RIC is also used for model training and reasoning. For example, it is used to train an AI model and use the model for reasoning. The non-real-time RIC can obtain network-side and / or terminal-side information from RAN nodes (such as CU, CU-CP, CU-UP, DU and / or RU) and / or terminals. This information can be used as training data or reasoning data, and the reasoning results can be submitted to the RAN node and / or terminal. Optionally, the reasoning results can be exchanged between the CU and the DU, and / or between the DU and the RU. For example, the non-real-time RIC submits the reasoning results to the DU, and the DU sends it to the RU.

[0258] The near-real-time RIC and non-real-time RIC may also be separately configured as network elements. Optionally, the near-real-time RIC and non-real-time RIC may also be part of other devices. For example, the near-real-time RIC may be configured in a RAN node (e.g., a CU or DU), while the non-real-time RIC may be configured in an OAM, a server (e.g., a cloud server), a core network device, or other network devices.

[0259] It is understandable that all or part of the functions implemented by one or more of the terminal equipment, access network equipment, core network equipment, or network elements for implementing artificial intelligence functions can be virtualized, that is, implemented by one or more of the proprietary processors or general-purpose processors and the corresponding software modules. Among them, since the terminal equipment and the access network equipment involve interfaces for air interface transmission, the transceiver functions of the interfaces can be implemented by hardware. Core network equipment, such as operation administration and maintenance (OAM) network elements, can be virtualized. Optionally, one or more functions of the virtualized terminal equipment, access network equipment, core network equipment, or network elements for implementing artificial intelligence functions can be implemented by cloud devices, such as cloud devices in over the top (OTT) systems.

[0260] The method provided in the present disclosure can be used for communication between access network equipment and terminal equipment, and can also be used for communication between other communication equipment, such as communication between macro base stations and micro base stations in a wireless backhaul link, and communication between two terminal devices in a side link (SL), etc., without limitation.

[0261] To facilitate understanding of the solutions of the embodiments of the present application, the terms that may be involved in the embodiments of the present application are explained below.

[0262] (1) AI model:

[0263] An AI model is an algorithm, computer program, or instruction that implements AI functionality. It represents the mapping between the model's inputs and outputs. AI models can be neural networks, linear regression models, decision tree models, support vector machines (SVMs), Bayesian networks, Q-learning models, or other machine learning (ML) models.

[0264] (2) Two-end model:

[0265] The two-end model can also be called a bilateral model, collaborative model, dual model, or two-side model. A two-end model is a model composed of multiple sub-models. The sub-models that make up the model must match each other. These sub-models can be deployed on different nodes.

[0266] In one possible design, an embodiment of the present application relates to an encoder for compressing channel state information (CSI) and a decoder for recovering compressed CSI. The encoder and decoder are matched for use, and it can be understood that the encoder and decoder are matching AI models. An encoder may include one or more AI models, and the decoder matched with the encoder also includes one or more AI models. The number of AI models included in the matching encoder and decoder is the same and corresponds one to one.

[0267] In one possible design, a matched set of encoders and decoders can be specifically two parts of the same auto-encoder (AE), as shown in Figure 4. An AE model, in which the encoder and decoder are deployed on different nodes, is a typical bilateral model. The encoder and decoder of an AE model are typically trained together. The encoder processes the input V to produce the processed output z, and the decoder decodes the encoder output z into the desired output V'.

[0268] An autoencoder is a type of neural network that uses unsupervised learning. Its characteristic is that it uses input data as labels, so it can also be understood as a self-supervised learning neural network. Autoencoders can be used for data compression and recovery. For example, the encoder in an autoencoder can compress (encode) data A to obtain data B; the decoder in the autoencoder can decompress (decode) data B to recover data A. Alternatively, the decoder can be understood as the inverse operation of the encoder.

[0269] For example, the AI ​​model in the embodiments of the present application may include an encoder and a decoder. The encoder and decoder are used in combination, and it can be understood that the encoder and decoder are a matching AI model. The encoder and decoder can be deployed on terminal devices and network devices respectively.

[0270] Alternatively, the AI ​​model in the embodiment of the present application may be a single-end model, which may be deployed on a terminal device or a network device.

[0271] (3) Neural network (NN):

[0272] Neural networks are a specific implementation of AI or machine learning. According to the universal approximation theorem, neural networks can theoretically approximate any continuous function, giving them the ability to learn arbitrary mappings.

[0273] A neural network can be composed of neural units, which can be a computational unit that takes xs and an intercept 1 as input. A neural network is formed by connecting many of these single neural units, meaning that the output of one neural unit can be the input of another. The input of each neural unit can be connected to the local receptive field of the previous layer to extract features from that local receptive field, which can be an area consisting of several neural units.

[0274] Taking the AI ​​model type as a neural network as an example, the AI ​​model involved in this disclosure can be a deep neural network (DNN). Depending on the network construction method, DNN can include feedforward neural networks (FNN), convolutional neural networks (CNN), and recurrent neural networks (RNN).

[0275] (4) Training data set and inference data:

[0276] In the field of machine learning, ground truth usually refers to data that is believed to be accurate or real.

[0277] A training dataset is used to train an AI model. It may include the input to the AI ​​model, or the input and target output of the AI ​​model. A training dataset includes one or more training data. Training data may include training samples input to the AI ​​model, or the target output of the AI ​​model. The target output may also be referred to as a label, sample label, or labeled sample. A label is the true value.

[0278] In the communications field, training datasets can include simulated data collected through simulation platforms, experimental data collected in experimental scenarios, or measured data collected in actual communication networks. Because the geographical environments and channel conditions in which data are generated vary, such as indoor and outdoor locations, mobile speeds, frequency bands, or antenna configurations, the collected data can be categorized during acquisition. For example, data with the same channel propagation environment and antenna configuration can be grouped together.

[0279] Model training essentially involves learning certain characteristics from training data. When training an AI model (such as a neural network), the goal is to ensure that the model's output is as close as possible to the desired predicted value. This is done by comparing the network's predictions with the desired target values. The weight vectors of each layer of the AI ​​model are then updated based on the difference between the two. (Of course, before the first update, there's usually an initialization process, which pre-configures the parameters for each layer of the AI ​​model.) For example, if the network's prediction is too high, the weight vectors are adjusted to predict a lower value. This adjustment is repeated until the AI ​​model predicts the desired target value, or a value very close to it. Therefore, it's necessary to predefine how to compare the difference between the predicted and target values. This is known as the loss function, or objective function. These are important equations used to measure the difference between the predicted and target values. For example, a higher loss function indicates a greater difference. Therefore, training an AI model becomes a process of minimizing this loss, keeping the loss function below a threshold or ensuring that the loss function meets the target requirement. For example, the AI ​​model is a neural network, and adjusting the model parameters of the neural network includes adjusting at least one of the following parameters: the number of layers, width, weights of neurons, or parameters in the activation function of neurons of the neural network.

[0280] Inference data can be used as input to a trained AI model for inference. During the inference process, the inference data is input into the AI ​​model, and the corresponding output is the inference result.

[0281] (5) AI model design:

[0282] The design of an AI model primarily involves data collection (e.g., collecting training data and / or inference data), model training, and model inference. Furthermore, it can also include the application of inference results.

[0283] FIG5 shows an AI application framework.

[0284] In the aforementioned data collection phase, the data source is used to provide training data sets and inference data. In the model training phase, an AI model is obtained by analyzing or training the training data provided by the data source. The AI ​​model represents the mapping relationship between the model's input and output. Learning the AI ​​model through the model training node is equivalent to learning the mapping relationship between the model's input and output using the training data. In the model inference phase, the AI ​​model trained in the model training phase is used to perform inference based on the inference data provided by the data source, obtaining an inference result. This phase can also be understood as inputting the inference data into the AI ​​model and obtaining an output from the AI ​​model, which is the inference result. The inference result can indicate the configuration parameters used (executed) by the execution object and / or the operations performed by the execution object. In the inference result application phase, the inference result is published. For example, the inference result can be centrally planned by the execution (actor) entity, for example, the execution entity can send the inference result to one or more execution objects (e.g., network devices or terminal devices) for execution. Alternatively, the execution entity can provide feedback on the model's performance to the data source to facilitate subsequent model update and training.

[0285] It is understandable that a communication system may include network elements with artificial intelligence functions. The above-mentioned AI model design-related links can be performed by one or more network elements with artificial intelligence functions. In one possible design, AI functions (such as AI modules or AI entities) can be configured in existing network elements in the communication system to implement AI-related operations, such as training and / or reasoning of AI models. For example, the existing network element can be a network device or a terminal device. Or in another possible design, an independent network element can also be introduced into the communication system to perform AI-related operations, such as training an AI model. The independent network element can be called an AI network element, an AI node, or an AI entity, etc., and the embodiments of the present application do not limit this name. For example, the AI ​​network element can be directly connected to the network device in the communication system, or it can be indirectly connected through a third-party network element and the network device. Among them, the third-party network element can be a core network element such as an authentication management function (AMF) network element, an access and mobility management function (AMF) network element, a user plane function (UPF) network element, an operation administration and maintenance (OAM), a server (such as a cloud server), an over the top (OTT) device or other network element, without limitation. Exemplarily, the independent AI network element or AI entity or AI node can be deployed on one or more of the network device side, the terminal device side, or the core network side. Optionally, it can be deployed on a server, such as a cloud server, or an OTT device, or other device. Exemplarily, an AI network element 240 is introduced in the communication system shown in Figure 2b. It will be understood that the aforementioned AI modules, AI entities, AI network elements, or AI nodes can be used to perform one or more AI functions, where the AI ​​functions may include: processing of AI models, such as training and / or updating of AI models, monitoring of AI models, management of AI models, such as registration and / or deregistration of AI models, or application reasoning of AI models.

[0286] The training process of different models can be deployed in different devices or nodes, or in the same device or node. The inference process of different models can be deployed in different devices or nodes, or in the same device or node. Taking the completion of the model training phase of a terminal device as an example, the terminal device can train the matching encoder and decoder, and then send the model parameters of the decoder to the network device. Taking the completion of the model training phase of a network device as an example, after the network device trains the matching encoder and decoder, it can indicate the model parameters of the encoder to the terminal device. Taking the completion of the model training phase of an independent AI network element as an example, the AI ​​network element can train the matching encoder and decoder, and then send the model parameters of the encoder to the terminal device and the model parameters of the decoder to the network device. Then, the model inference phase corresponding to the encoder is performed in the terminal device, and the model inference phase corresponding to the decoder is performed in the network device.

[0287] Among them, the model parameters may include one or more of the following structural parameters of the model (such as the number of layers and / or weights of the model, etc.), the input parameters of the model (such as input dimension, number of input ports), or the output parameters of the model (such as output dimension, number of output ports). It can be understood that the input dimension may refer to the size of an input data. For example, when the input data is a sequence, the input dimension corresponding to the sequence may indicate the length of the sequence. The number of input ports may refer to the number of input data. Similarly, the output dimension may refer to the size of an output data. For example, when the output data is a sequence, the output dimension corresponding to the sequence may indicate the length of the sequence. The number of output ports may refer to the number of output data.

[0288] (6) Channel information:

[0289] In a communication system (for example, an LTE communication system or an NR communication system, etc.), the network device needs to determine the resources, modulation and coding scheme (MCS) and precoding configurations of the downlink data channel of the scheduling terminal device based on the channel information. It can be understood that the channel information can also be referred to as channel state information CSI or channel environment information, which is a kind of information that can reflect the channel characteristics and channel quality. In this application, the meaning of CSI is broader than that of CSI in the traditional scheme, and is not limited to channel quality indicator (CQI), precoding matrix indicator (PMI), rank indicator (RI), or channel information reference signal (CSI-RS) resource indicator (CSI-RS resource indicator, CRI). It can also be channel response information (such as channel response matrix), weight information corresponding to the channel response, reference signal received power (RSRP) or signal to interference plus noise ratio (SINR). One or more of the above.

[0290] CSI measurement refers to the receiver solving the channel information based on the reference signal sent by the transmitter, that is, estimating the channel information using the channel estimation method. Exemplarily, the reference signal may include one or more of the channel information reference signal CSI-RS, synchronization signal / physical broadcast channel block (SS / PBCH block, abbreviated as SSB), channel sounding reference signal (SRS) or demodulation reference signal (DMRS). CSI-RS, SSB and DMRS can be used to measure downlink CSI. SRS and DMRS can be used to measure uplink CSI.

[0291] Taking FDD communication scenarios as an example, in FDD communication scenarios, because uplink and downlink channels are not reciprocal or cannot be guaranteed, network equipment typically transmits a downlink reference signal to the terminal device. The terminal device performs channel and interference measurements based on the received downlink reference signal to estimate the downlink CSI. The terminal device generates a CSI report based on a protocol predefined method or a network device configuration method and feeds it back to the network device to obtain the downlink CSI.

[0292] Exemplarily, the CSI may include at least one of the following: CQI, PMI, RI, CRI, layer indicator (LI), RSRP, or signal to interference plus noise ratio SINR, etc. The signal to interference plus noise ratio may also be referred to as signal to interference plus noise ratio.

[0293] The RI indicates the number of downlink transmission layers recommended by the terminal device, the CQI indicates the modulation and coding scheme supported by the current channel conditions as determined by the terminal device, and the PMI indicates the precoding recommended by the terminal device. The number of precoding layers indicated by the PMI corresponds to the RI.

[0294] It should be understood that the RI, CQI, and PMI indicated in the above CSI report are only recommended values ​​for the terminal device, and the network device may perform downlink transmission according to part or all of the information indicated in the CSI report. Alternatively, the network device may not perform downlink transmission according to the information indicated in the CSI report.

[0295] The introduction of AI technology into wireless communication networks has resulted in a CSI feedback method based on AI models. Terminal devices use AI models to compress and feedback CSI, and network equipment uses AI models to recover the compressed CSI. AI-based CSI feedback transmits a sequence (such as a bit sequence), resulting in lower overhead than traditional CSI feedback.

[0296] Taking Figure 4 as an example, the encoder in Figure 4 can be a CSI generator, and the decoder can be a CSI reconstructor. The encoder can be deployed in a terminal device, and the decoder can be deployed in a network device. The terminal device can use the encoder to generate CSI feedback information z from the original CSI information V. The terminal device then reports a CSI report, which can include the CSI feedback information z. The network device can use the decoder to reconstruct the CSI information, thereby obtaining the recovered CSI information V'.

[0297] The CSI original information V may be obtained by the terminal device through CSI measurement. For example, the CSI original information V may include the channel response of the downlink channel or the eigenvector matrix (a matrix composed of eigenvectors) of the downlink channel. The encoder processes the eigenvector matrix of the downlink channel to obtain CSI feedback information z. In other words, the compression and / or quantization operation of the eigenmatrix according to the codebook in the related scheme is replaced by the operation of processing the eigenmatrix by the encoder to obtain CSI feedback information z. The terminal device reports the CSI feedback information z. The network device processes the CSI feedback information z through the decoder to obtain CSI recovery information V'.

[0298] The following further illustrates the training process and reasoning process of the AI ​​model in the embodiments of the present application.

[0299] The training data used to train AI models includes training samples and sample labels. For example, the training samples are channel information determined by the terminal device, and the sample labels are the actual channel information, i.e., the true value CSI. If the encoder and decoder belong to the same autoencoder, the training data can only include the training samples, or the training samples are the sample labels.

[0300] In the field of wireless communications, the true CSI may be high-precision CSI.

[0301] The specific training process is as follows: the model training node uses an encoder to process channel information, that is, training samples, to obtain channel feedback information, such as CSI feedback information, and uses a decoder to process the feedback information to obtain recovered channel information, that is, channel recovery information, such as CSI recovery information. Then, the difference between the channel recovery information and the corresponding sample label is calculated, that is, the value of the loss function, and the parameters of the encoder and decoder are updated according to the value of the loss function, so that the difference between the recovered channel information and the corresponding sample label is minimized, that is, the loss function is minimized. Exemplarily, the loss function can be the minimum mean square error (MSE) or cosine similarity. Repeat the above operations to obtain an encoder and decoder that meet the target requirements. The above model training node can be a terminal device, a network device, or other network elements with AI functions in a communication system.

[0302] It should be understood that the above description uses the AI ​​model for CSI compression as an example. The AI ​​model can also be used in other scenarios in CSI feedback. For example, the AI ​​model can be used for CSI prediction, that is, predicting channel information at one or more future moments based on channel information measured at one or more historical moments. The embodiments of this application do not limit the specific use of the AI ​​model in CSI feedback scenarios.

[0303] It should be understood that, in this application, indication includes direct indication (also known as explicit indication) and implicit indication. Direct indication of information A refers to including information A; implicit indication of information A refers to indicating information A through the correspondence between information A and information B and the direct indication of information B. The correspondence between information A and information B can be predefined, pre-stored, pre-burned, or pre-configured.

[0304] It should be understood that, in this application, information C is used to determine information D, which includes both information D being determined solely based on information C and information D being determined based on information C and other information. Furthermore, information C can also be used to determine information D indirectly, for example, where information D is determined based on information E, and information E is determined based on information C.

[0305] In addition, in each embodiment of the present application, "network element A sends information A to network element B" can be understood as the destination end of the information A or the intermediate network element in the transmission path between the destination end and the network element B, which may include directly or indirectly sending information to network element B. "Network element B receives information A from network element A" can be understood as the source end of the information A or the intermediate network element in the transmission path between the source end and the network element A, which may include directly or indirectly receiving information from network element A. The information may be processed as necessary between the source end and the destination end of the information transmission, such as format changes, but the destination end can understand the valid information from the source end. Similar expressions in this application can be understood similarly and will not be elaborated here.

[0306] The following is a detailed introduction to the embodiments of the present application.

[0307] Referring to Figure 6, there is shown a schematic diagram of a wireless model provided in an embodiment of the present application. As shown in Figure 6, the wireless model includes a first sub-model (which may also be referred to as a channel encoder, etc.) and a second sub-model (which may also be referred to as an environment encoder, etc.). The first sub-model is used to process the first channel information to obtain first channel characteristic parameters. This processing may, for example, be feature extraction, etc. The second sub-model is used to process the first environment information to obtain first environment characteristic parameters. The first channel information is associated with the first environment information, and the first channel characteristic parameters and the first environment characteristic parameters correspond to a first high-dimensional feature vector.

[0308] This association can be understood as that the first channel information and the first environment information are information corresponding to the same environment.

[0309] Among them, the first channel information may include at least one of the following: multipath information, frequency domain channel response, channel impulse response, channel eigenvector, power delay spectrum, path loss, reference signal receiving power, signal-to-noise ratio, Doppler frequency deviation, interference information, arrival angle and departure angle, transmission delay, time advance, etc.

[0310] The first environmental information may include at least one of the following: a two-dimensional (2D) or three-dimensional (3D) map and scale, building / obstruction information (such as location, material, error, etc.), the location (or distribution) of network equipment and / or user equipment, the configuration of the network equipment and / or the user equipment and / or the cell, the density, mobility status, weather, etc. of the user equipment.

[0311] The first high-dimensional feature vector is a mapping of the first channel information and the first environmental information in a high-dimensional feature space. In the physical world, due to the principle of electromagnetic field transmission, environmental information and channel information have a one-to-one correspondence. By finding a high-dimensional physical feature space in which environmental information and channel information are represented as the same high-dimensional physical feature, the conversion between features and information can be achieved. In a high-dimensional physical feature space, feature vectors of similar environments and channels are close in space, while feature vectors of different environments and channels are far apart in space.

[0312] The first channel characteristic parameter and the first environmental characteristic parameter correspond to a first high-dimensional feature vector. That is, the first channel characteristic parameter and the first environmental characteristic parameter correspond to the same high-dimensional feature vector. The same high-dimensional feature vector may correspond to one or more channel characteristic parameters and one or more environmental characteristic parameters, which is not limited in this solution.

[0313] In other words, the first high-dimensional feature vector is used to associate the first channel characteristic parameter with the first environmental characteristic parameter. For example, the first high-dimensional feature vector includes the first channel characteristic parameter and the first environmental characteristic parameter, or the first high-dimensional feature vector is obtained by performing other processing on the first channel characteristic parameter and the first environmental characteristic parameter. This solution is not limited to this. It is understandable that the first high-dimensional feature vector is also used to associate the first channel information with the first environmental information.

[0314] Exemplarily, as shown in Table 1, this is a mapping table between channel information, environmental information, and high-dimensional feature vectors provided in an embodiment of the present application.

[0315] Table 1

[0316] In a possible implementation, the wireless model may map the first channel information, the first environment information, and the first high-dimensional feature vector to each other.

[0317] This mutual mapping can be understood as inputting one or two of the first channel information, the first environment information and the first high-dimensional feature vector, and outputting the other items of the first channel information, the first environment information and the first high-dimensional feature vector except the input.

[0318] Exemplarily, in a possible implementation manner, the input of the wireless model is the first channel information, and the output of the wireless model is at least one of first environment information and a first high-dimensional feature vector.

[0319] In another possible implementation manner, the input of the wireless model is the first environment information, and the output of the wireless model is at least one of the first channel information and a first high-dimensional feature vector.

[0320] In another possible implementation, the input of the wireless model is the first high-dimensional feature vector, and the output of the wireless model is at least one of first channel information and first environment information.

[0321] In another possible implementation, the input of the wireless model is the first channel information and the first environment information, and the output of the wireless model is the first high-dimensional feature vector.

[0322] In another possible implementation manner, the input of the wireless model is the first channel information and the first high-dimensional feature vector, and the output of the wireless model is the first environment information.

[0323] In another possible implementation manner, the input of the wireless model is the first environment information and the first high-dimensional feature vector, and the output of the wireless model is the first channel information.

[0324] In one possible implementation, the first submodel is further used to process a third high-dimensional feature vector to obtain second channel information, and / or the second submodel is further used to process the third high-dimensional feature vector to obtain second environmental information. The third high-dimensional feature vector can be the first high-dimensional feature vector described above, or a feature vector different from the first high-dimensional feature vector, which is not limited in this solution. It is understood that the second channel information is associated with the second environmental information.

[0325] In one possible implementation, the first sub-model can be deployed on a network device, and the second sub-model can be deployed on a user device. Alternatively, the first sub-model can be deployed on a user device, and the second sub-model can be deployed on a network device. For another example, both the first sub-model and the second sub-model can be deployed on a network device or a user device. This solution does not impose any restrictions on this.

[0326] Through training, the wireless model can make the environmental information and channel information obtain the same representation in the high-dimensional feature space, thereby obtaining the mutual prediction ability of the two types of information.

[0327] The application of this wireless model is introduced below.

[0328] In which, the wireless model can be applied to downstream task 1, which is to predict first environmental information (such as speed) based on actual data (first channel information (such as channel impulse response)). In which, the first submodel and the second submodel of the wireless model are trained based on channel training information and first environmental training information, and the first environmental training information is associated with the channel training information. It can be understood that the above-mentioned first channel information and the predicted first environmental information are also associated. Based on this, referring to Figure 7, it is a flow chart of an information processing method provided by an embodiment of the present application. Optionally, the method can be applied to the aforementioned communication system, such as the communication system shown in Figure 1. This example is described by taking the first submodel deployed on the user equipment (first device) and the second submodel deployed on the network equipment (second device) as an example, and the present application is also applicable to other execution entities. The information processing method shown in Figure 7 may include steps 701-703. It should be understood that for the convenience of description, the present application is described in the order of 701-703, and is not intended to be limited to execution in the above order. The embodiment of the present application does not limit the order of execution, execution time, number of executions, etc. of the above one or more steps. Steps 701-703 are as follows:

[0329] 701. A first device sends first information to a second device, the first information being used to request prediction of first environment information; the first information including a first high-dimensional feature vector, the first high-dimensional feature vector being obtained based on first channel information and a first sub-model of the wireless model. In response, the second device receives the first information.

[0330] Exemplarily, the first environmental information may be speed or the like.

[0331] In one possible implementation, the first device inputs first channel information (e.g., a channel impulse response) into a first submodel of a wireless model for processing to obtain first channel characteristic parameters. The first high-dimensional feature vector is obtained by mapping the first channel characteristic parameters to a high-dimensional feature space.

[0332] It can be understood that the first channel information can also include multiple items, for example, one or more of multipath information, frequency domain channel response, channel eigen vector, power delay spectrum, path loss, reference signal receiving power, signal-to-noise ratio, Doppler frequency deviation, interference information, arrival angle and departure angle, transmission delay, time advance, etc. This solution does not limit this.

[0333] 702. The second device obtains the initialized first environment information, and processes it based on the first high-dimensional feature vector, the initialized first environment information, and the second sub-model of the wireless model to obtain predicted first environment information.

[0334] The first sub-model and the second sub-model of the wireless model are trained based on channel training information and first environment training information. The first environment training information is associated with the channel training information. The predicted first environment information is associated with the first channel information.

[0335] It is understood that the first environment training information corresponds to the predicted first environment information. The channel training information corresponds to the first channel information. The first environment training information corresponds to the predicted first environment information. That is, when the first environment training information is speed, the predicted first environment information is also speed. The channel training information corresponds to the first channel information. That is, when the channel training information is a channel impulse response, the first channel information is also a channel impulse response.

[0336] In this example, the wireless model is trained based on environmental information (speed) and channel information. The downstream task is to predict environmental information (speed) when the channel information is known.

[0337] In a possible implementation, the second device randomly sets the first environment information to obtain initialized first environment information.

[0338] In a possible implementation, the second device performs processing based on the first high-dimensional feature vector, the initialized first environment information, and the second sub-model of the wireless model to obtain the predicted first environment information, including:

[0339] The second device obtains a fourth high-dimensional feature vector based on the initialized first environment information and the second sub-model. For example, the second device inputs the initialized first environment information into the second sub-model of the wireless model for processing to obtain first environment feature parameters, and obtains the fourth high-dimensional feature vector by mapping the first environment feature parameters.

[0340] The second device performs processing based on the fourth high-dimensional feature vector and the first high-dimensional feature vector to obtain the predicted first environment information.

[0341] Exemplarily, the second device performs comparative learning based on the fourth high-dimensional feature vector and the first high-dimensional feature vector to update the initialized first environment information, thereby obtaining updated first environment information. The updated first environment information is used as the predicted first environment information. For an introduction to this comparative learning, please refer to the description of the embodiments below and will not be repeated here.

[0342] In one possible implementation, the second device inputs the updated first environment information into the second sub-model for processing, obtaining an updated fourth high-dimensional feature vector. The updated fourth high-dimensional feature vector is then processed with the first high-dimensional feature vector to obtain further updated first environment information. The above steps are repeated until a preset condition is met, at which point the above steps are stopped and the final updated first environment information is used as the predicted first environment information. For example, the preset condition may be that the difference between two consecutive first environment information is less than a preset value.

[0343] During the information processing, the parameters of the wireless model are frozen, that is, the parameters of the wireless model are not changed, and only the first environment information is updated.

[0344] 703. The second device sends second information to the first device, where the second information includes the predicted first environment information. Correspondingly, the first device receives the second information.

[0345] Exemplarily, the first device may configure a reference signal of the UE, etc. based on the predicted first environmental information (such as speed).

[0346] In one possible implementation, the first information also includes third environmental information (such as location). Exemplarily, the second device processes the first high-dimensional feature vector, the third environmental information, the initialized first environmental information, and the second sub-model of the wireless model to obtain predicted first environmental information. The wireless model is trained based on channel training information, the first environmental training information, and the second environmental training information, and the second environmental training information corresponds to the third environmental information.

[0347] In other words, the wireless model in this example is trained based on environmental information (speed and position) and channel information. The downstream task is to know some of the environmental information (position) and channel information and need to predict other environmental information (speed).

[0348] This example uses the example of predicting another type of environmental information (such as speed) given one type of environmental information (such as location) and channel information. Alternatively, the wireless model's environmental information may include {e1, e2, e3}, and the channel information may include {c1, c2, c3}. The downstream task is to predict {e2} based on {e1, e3} and {c1, c2, c3}, etc. This solution does not impose any restrictions on this. For example, e1 represents location, e2 represents speed, and e3 represents a map. c1, c2, and c3 represent multipath information, frequency domain channel response, and signal-to-noise ratio, respectively.

[0349] In this example, the predicted value of the first environmental information is obtained by processing the initialized first environmental information, the first high-dimensional feature vector, and the second sub-model of the wireless model. This method can be used to predict one or more items in the environmental information.

[0350] The embodiment shown in FIG7 above is introduced by taking the prediction of environmental information as an example. The following is introduced by taking the prediction of channel information as an example. The wireless model can be applied to downstream task 2, and the downstream task 2 is to predict the first channel information (such as channel impulse response) based on actual data (first environmental information (such as speed)). Among them, the first sub-model and the second sub-model of the wireless model are trained based on the first channel training information and the environmental training information, and the environmental training information is associated with the first channel training information. It can be understood that the predicted first channel information and the first environmental information are also associated. Based on this, referring to FIG8 , it is a flow chart of another information processing method provided by an embodiment of the present application. This example is illustrated by taking the first sub-model deployed on the user equipment (first device) and the second sub-model deployed on the network equipment (second device) as an example, and the present application is also applicable to other execution entities. The method may include steps 801-803, as follows:

[0351] 801. A second device sends third information to a first device, the third information being used to request prediction of first channel information; the third information including a first high-dimensional feature vector, the first high-dimensional feature vector being obtained based on first environment information and a second sub-model of the wireless model. In response, the first device receives the third information.

[0352] Exemplarily, the first channel information may be a channel impulse response or the like.

[0353] In one possible implementation, the second device inputs the first environmental information (such as speed) into the second sub-model of the wireless model for processing to obtain a first environmental characteristic parameter, and then maps the first environmental characteristic parameter to a high-dimensional feature space to obtain a first high-dimensional feature vector.

[0354] It can be understood that the first environmental information can also be one or more of a two-dimensional 2D or three-dimensional 3D map and scale, building / obstruction information (such as location, material, error, etc.), the location (or distribution) of network equipment and / or user equipment, the configuration of the network equipment and / or the user equipment and / or the cell, the density of the user equipment, weather, etc., and this solution does not impose any restrictions on this.

[0355] 802. The first device obtains initialized first channel information, and processes it based on the first high-dimensional feature vector, the initialized first channel information, and the first sub-model of the wireless model to obtain predicted first channel information.

[0356] The first sub-model and the second sub-model of the wireless model are trained based on first channel training information and environment training information. The environment training information is associated with the first channel training information. The predicted first channel information is associated with the first environment information.

[0357] In this example, the wireless model is trained based on environmental and channel information. The downstream task requires predicting channel information when the environmental information is known.

[0358] For example, the first device randomly sets the first channel information to obtain initialized first channel information.

[0359] In a possible implementation, the first device performs processing based on the first high-dimensional feature vector, the initialized first channel information, and the first sub-model of the wireless model to obtain predicted first channel information, including:

[0360] The first device obtains a fifth high-dimensional feature vector based on the initialized first channel information and the first sub-model. For example, the first device inputs the initialized first channel information into the first sub-model for processing to obtain first channel characteristic parameters. Furthermore, the first channel characteristic parameters are mapped to obtain the fifth high-dimensional feature vector.

[0361] Then, the first device performs processing based on the fifth high-dimensional feature vector and the first high-dimensional feature vector to obtain the predicted first channel information.

[0362] Exemplarily, the first device performs comparative learning based on the fifth high-dimensional feature vector and the first high-dimensional feature vector to obtain updated first channel information.

[0363] The updated first channel information is used as the predicted first channel information.

[0364] In one possible implementation, the first device inputs the updated first channel information into the first sub-model for processing, obtaining an updated fifth high-dimensional feature vector. Processing is performed based on the first high-dimensional feature vector and the updated fifth high-dimensional feature vector to obtain further updated first channel information. The above steps are repeated until a preset condition is met, at which point the above steps are stopped and the final updated first channel information is used as the predicted first channel information. For example, the preset condition may be that the difference between two consecutive first channel information items is less than a preset value.

[0365] During the information processing, the parameters of the wireless model are frozen, that is, the parameters of the wireless model are not changed, and only the first channel parameters are updated.

[0366] 803. The first device sends fourth information to the second device, where the fourth information includes the predicted first channel information. Correspondingly, the second device receives the fourth information.

[0367] In one possible implementation, the third information also includes third channel information (such as path loss). Exemplarily, the first device performs processing based on the first high-dimensional feature vector, the initialized first channel information, the third channel information, and the first sub-model of the wireless model to obtain the predicted first channel information. The first sub-model and the second sub-model of the wireless model are trained based on the first channel training information, the second channel training information and the environmental training information. The second channel training information corresponds to the third channel information. That is, in this example, the wireless model is trained based on environmental information and channel information (such as channel impulse response and path loss). The downstream task is to know the environmental information and partial channel information (path loss), and to predict other channel information (channel impulse response).

[0368] In this example, the predicted value of the first channel information is obtained by processing the initialized first channel information, the first high-dimensional feature vector, and the first sub-model of the wireless model. This method can be used to predict one or more items in the channel information.

[0369] The above example illustrates the application of a wireless model to a downstream prediction task. Figure 9 shows another schematic diagram of an embodiment of the present application illustrating the application of a wireless model to a downstream task. As shown in Figure 9, the downstream task can obtain a high-dimensional feature vector of the wireless model as input to complete the training or inference of the downstream model.

[0370] In one possible implementation, the input of the downstream model includes a second high-dimensional feature vector, which is obtained by processing the first channel feature parameter and the first environment feature parameter according to a preset ratio in the embodiment shown in FIG. 6 .

[0371] It can be understood that the second high-dimensional feature vector can be the above-mentioned first high-dimensional feature vector, or can be a feature vector different from the above-mentioned first high-dimensional feature vector, and this solution does not impose any limitation on this.

[0372] Among them, according to the difference between tasks and task inputs, the first sub-model and the second sub-model can be activated according to preset weights. For example, in downstream task a, the first sub-model is not activated, and only the second sub-model is used for reasoning application. That is, only the output of the second sub-model is mapped as the input of the downstream model. For example, in downstream task b, 30% of the output of the first sub-model and 70% of the output of the second sub-model are processed as the input of the downstream model for reasoning application. Of course, in downstream task b, 50% of the output of the first sub-model and 50% of the output of the second sub-model are processed as the input of the downstream model, etc. This solution does not limit this.

[0373] The above example maps the percentage of the sub-model's output to the input of the downstream model. Of course, other processing methods are also possible and this solution does not limit this.

[0374] In one possible implementation, the downstream model can use a cross-attention mechanism to fuse the wireless model's output with its own output to obtain the final output. This fusion can, for example, involve concatenating the high-dimensional feature vector obtained by mapping the wireless model's output with the downstream model's own output.

[0375] In one possible implementation, when training a downstream model, the parameters of the wireless model can be frozen or fine-tuned.

[0376] In one possible implementation, the downstream model can be augmented with a correction task. Specifically, the downstream model's input can include not only the high-dimensional feature vectors mapped from the wireless model's output but also locally measured values. Accordingly, the downstream model's output generates a correction value, which is used to correct for discrepancies between the training data and the real data. This can improve model performance.

[0377] The above example introduces the application of the wireless model. The following describes the training of the wireless model.

[0378] 10 is a schematic diagram of a wireless model training method provided by an embodiment of the present application. As shown in FIG10 , the method may include steps 1001-1006, which are as follows:

[0379] 1001. A first device obtains channel training information, and obtains a sixth high-dimensional feature vector based on the channel training information and an initial first sub-model.

[0380] For example, the first device inputs the channel training information into the initial first sub-model for processing to obtain channel characteristic parameters, and obtains the sixth high-dimensional feature vector by mapping the channel characteristic parameters.

[0381] In one possible implementation, the first device randomly masks the channel training information and then inputs the processed channel training information into the initial first sub-model. For example, if the channel training information E is {e1, e2, e3, e4, e5, ...}, after masking, E becomes {e1, x, e2, e3, x, e5, ...}, where x is a constant or a trainable parameter. It is understood that x can have different values ​​at different locations, and this solution does not impose any restrictions on this.

[0382] Based on this processing, data enhancement can be achieved, thereby improving the generalization of the model.

[0383] 1002. The first device sends fifth information to the second device, where the fifth information includes the sixth high-dimensional feature vector. Correspondingly, the second device receives the fifth information.

[0384] 1003. The second device obtains environmental training information, and obtains a seventh high-dimensional feature vector based on the environmental training information and the initial second sub-model.

[0385] For example, the second device inputs the environmental training information into the initial second sub-model for processing to obtain environmental feature parameters, and obtains the seventh high-dimensional feature vector by mapping the environmental feature parameters.

[0386] For example, the second device obtains the environment training information from the first device. Of course, other methods can also be used, and this solution does not limit this.

[0387] In one possible implementation, the second device performs random masking on the environmental training information and then inputs the processed environmental training information into the initial second sub-model. For an introduction to this, please refer to the description of step 1001 above, which will not be repeated here.

[0388] 1004. The second device performs optimization based on the sixth high-dimensional feature vector and the seventh high-dimensional feature vector to obtain an updated second sub-model and updated parameters of the first sub-model.

[0389] The optimization may be performed by performing comparative learning on the sixth high-dimensional feature vector and the seventh high-dimensional feature vector.

[0390] Exemplarily, the second device performs data pair optimization on the environmental information (such as the above environmental training information) and the channel information (such as the above channel training information) to establish a connection between the environmental information and the channel information. For example, the sixth high-dimensional feature vector f is calculated. a and the seventh high-dimensional eigenvector f b The cosine similarity between them is used to obtain the G matrix: f ai is the i-th element in the sixth high-dimensional eigenvector, f bj is the jth element in the seventh high-dimensional eigenvector. Minimize the cross entropy for the rows and columns of the G matrix respectively. When the target value is i=j, the value of the corresponding element in the G matrix is ​​1, otherwise it is 0, that is, f ai With f bi As a positive sample, f ai With f bi as negative samples; i and j are the indexes of the model training data in this batch of data.

[0391] Alternatively, the second device performs data internal optimization on the environmental information and channel information, and independently clusters different environmental information or channel information. For example, first cluster the high-dimensional feature vector f (including the sixth high-dimensional feature vector f a and the seventh high-dimensional eigenvector f b ) to cluster and sample f from the category i With f j , for f i With f j Calculate the cosine similarity and obtain the G matrix: Minimize the cross entropy for the rows or columns of the matrix, where i and j are the cluster indices after the data is clustered. That is, samples from different clusters are regarded as negative samples, and samples in the same cluster are regarded as positive samples.

[0392] That is, the optimization goal is to maximize the distance between negative samples and minimize the distance between positive samples. Based on the above optimization process, one or more of the gradient, weight, and intermediate gradient of the first sub-model and the updated parameters of the second sub-model can be obtained.

[0393] 1005. The second device sends sixth information to the first device, where the sixth information includes updated parameters of the first sub-model. Correspondingly, the first device receives the sixth information.

[0394] The update parameter includes at least one of the gradient, weight, and intermediate gradient of the initial first sub-model.

[0395] 1006. The first device updates the initial first sub-model according to the update parameters of the first sub-model to obtain a trained first sub-model.

[0396] In this example, at least one of the gradient, weight, and intermediate gradient of the first submodel is indicated by a second device (e.g., a network device). Of course, at least one of the gradient, weight, and intermediate gradient of the first submodel corresponding to the first device can also be synchronously updated between multiple UEs, and this solution does not limit this.

[0397] In this example, based on the aforementioned contrastive learning training method, the training objective is independent of the downstream task, which can provide a model with stronger generalization.

[0398] For example, referring to FIG11 , a schematic diagram of another wireless model training method provided in an embodiment of the present application is shown. In this example, the wireless model and the downstream model complete the training of the wireless model together. The downstream task requires both environmental information and channel information. As shown in FIG11 , the method may include steps 1101-1108, specifically as follows:

[0399] 1101. The first device obtains channel training information, and obtains an eighth high-dimensional feature vector based on the channel training information and an initial first sub-model.

[0400] For example, the first device inputs the channel training information into the initial first sub-model for processing to obtain channel characteristic parameters, and obtains the eighth high-dimensional feature vector by mapping the channel characteristic parameters.

[0401] 1102. The first device sends seventh information to the second device, where the seventh information includes the eighth high-dimensional feature vector. Correspondingly, the second device receives the seventh information.

[0402] 1103. The second device obtains environmental training information, and obtains a ninth high-dimensional feature vector based on the environmental training information and the initial second sub-model.

[0403] For example, the second device inputs the environmental training information into the initial second sub-model for processing to obtain environmental feature parameters, and obtains a ninth high-dimensional feature vector by mapping the environmental feature parameters.

[0404] 1104. The second device sends eighth information to the third device, where the eighth information includes the eighth high-dimensional feature vector and the ninth high-dimensional feature vector.

[0405] 1105. The third device processes the eighth high-dimensional feature vector and the ninth high-dimensional feature vector to obtain processed high-dimensional feature vectors; and inputs the processed high-dimensional feature vectors into a downstream model for processing to obtain an updated first sub-model and an updated second sub-model.

[0406] The downstream model is deployed on the third device.

[0407] For example, the third device performs weighted processing on the eighth high-dimensional feature vector and the ninth high-dimensional feature vector to obtain a processed high-dimensional feature vector. Of course, the weighted processing can also be performed by the second device, and then the second device sends the processed high-dimensional feature vector to the third device. This solution does not impose any restrictions on this.

[0408] Then, the third device calculates the loss value based on the output of the downstream model and the processed high-dimensional feature vector, and reversely updates the downstream model and the initial first sub-model and the initial second sub-model based on the loss value to obtain an updated first sub-model and an updated second sub-model.

[0409] 1106. The third device sends ninth information to the second device, where the ninth information includes the updated second sub-model and at least one of the gradient, weight, and intermediate gradient of the initial first sub-model. Accordingly, the second device receives the information.

[0410] 1107. The second device sends tenth information to the first device, where the tenth information includes at least one of the initial gradient, weight, and intermediate gradient of the first sub-model. Correspondingly, the first device receives the tenth information.

[0411] 1108. The first device updates the initial first sub-model based on at least one of the gradient, weight, and intermediate gradient of the initial first sub-model to obtain a trained first sub-model.

[0412] Based on this processing, the trained first sub-model and second sub-model can be obtained.

[0413] The above example describes the training of a wireless model using the example of a downstream task requiring both environmental information and channel information. The following describes the training of a wireless model using the example of a downstream task requiring only one of environmental information and channel information. As shown in FIG12 , this example describes the training of a wireless model using the example of a downstream task requiring only environmental information. The method may include steps 1201-1209, specifically as follows:

[0414] 1201. The first device obtains channel training information, and obtains a tenth high-dimensional feature vector based on the channel training information and an initial first sub-model.

[0415] 1202. The second device obtains environmental training information, and inputs the environmental training information into the initial second sub-model for processing to obtain an eleventh high-dimensional feature vector.

[0416] 1203. The second device sends twelfth information to the third device, where the twelfth information includes the eleventh high-dimensional feature vector. Correspondingly, the third device receives the twelfth information.

[0417] 1204. The third device inputs the eleventh high-dimensional feature vector into a downstream model for processing to obtain an output of the downstream model.

[0418] 1205. The third device calculates a loss value based on the output of the downstream model and the eleventh high-dimensional feature vector, and reversely updates the downstream model and the initial second sub-model based on the loss value to obtain an updated second sub-model.

[0419] 1206. The third device sends thirteenth information to the second device, where the thirteenth information includes the updated second sub-model. Correspondingly, the second device receives the thirteenth information.

[0420] 1207. The second device sends fourteenth information to the first device, where the fourteenth information includes the eleventh high-dimensional feature vector. Correspondingly, the first device receives the fourteenth information.

[0421] 1208. The first device obtains a spatial loss function according to the tenth high-dimensional eigenvector and the eleventh high-dimensional eigenvector.

[0422] 1209. The first device updates the initial first sub-model based on the spatial loss function to obtain a trained first sub-model.

[0423] Based on this processing, the trained first sub-model and second sub-model can be obtained.

[0424] It should be noted that when only channel information is required for the downstream task, the high-dimensional feature vector corresponding to the channel training information is sent to the third device. For this example, please refer to the description of the example shown in Figure 12, which will not be repeated here.

[0425] It should be noted that in the various embodiments of the present application, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between the various embodiments are consistent and can be referenced by each other. The technical features in different embodiments can be combined to form new embodiments according to their internal logical relationships.

[0426] The above describes in detail the method of the embodiment of the present application, and the following provides the device of the embodiment of the present application. It will be understood that in the various device embodiments of the present application, the division of multiple units or modules is only a logical division based on function, and is not intended to limit the specific structure of the device. In a specific implementation, some functional modules may be subdivided into more small functional modules, and some functional modules may be combined into one functional module, but no matter whether these functional modules are subdivided or combined, the general process performed by the device is the same. For example, some devices include a receiving unit and a sending unit. In some designs, the sending unit and the receiving unit can also be integrated into a communication unit, which can implement the functions implemented by the receiving unit and the sending unit. Typically, each unit corresponds to its own program code (or program instructions), and when the program code corresponding to each of these units runs on the processor, the unit is controlled by the processing unit to execute the corresponding process to implement the corresponding function.

[0427] The embodiments of the present application also provide an apparatus for implementing any of the above methods. For example, an information processing apparatus is provided that includes a module (or means) for implementing each step performed by the first device in any of the above methods. Another example is an information processing apparatus that includes a module (or means) for implementing each step performed by the second device in any of the above methods.

[0428] For example, referring to Figure 13, it is a schematic diagram of the structure of an information processing device provided in an embodiment of the present application. As shown in Figure 13, the device may include a transceiver module 1301. It can be understood that the transceiver module 1301 shown in Figure 13 can implement corresponding communication functions. The transceiver module 1301 can also be called a communication interface or a communication module. Optionally, the transceiver module 1301 may include a sending module and a receiving module. The sending module is used to perform the sending operation in the above method embodiment. The receiving module is used to perform the receiving operation in the above method embodiment. It should be noted that the communication device may include a sending module but not a receiving module. Alternatively, the communication device may include a receiving module but not a sending module. It may depend on whether the above scheme executed by the communication device includes a sending action and a receiving action.

[0429] Optionally, the communication device may further include a storage module, which may be used to store instructions and / or data. The processing module may read the instructions and / or data in the storage module, so that the communication device implements the aforementioned method embodiment.

[0430] Optionally, the communication device is used to perform the actions performed by the first device or terminal device or user equipment, etc. in any of the embodiments shown in Figures 7, 8, 10, 11 and 12 above.

[0431] For example, the communication device is used to perform the following scheme:

[0432] The transceiver module 1301 is configured to send first information to the second device, where the first information is used to request prediction of first environment information; the first information includes a first high-dimensional feature vector, where the first high-dimensional feature vector is obtained based on the first channel information and the first sub-model of the wireless model;

[0433] The transceiver module 1301 is also used to receive second information from the second device, where the second information includes predicted first environmental information, which is obtained by processing the first high-dimensional feature vector, the initialized first environmental information, and the second sub-model of the wireless model, wherein the first sub-model and the second sub-model of the wireless model are trained based on channel training information and first environmental training information, the first environmental training information is associated with the channel training information, and the predicted first environmental information is associated with the first channel information.

[0434] In one possible implementation, the first information also includes third environmental information, and the predicted first environmental information is obtained based on the first high-dimensional feature vector, the third environmental information, the initialized first environmental information, and the second sub-model of the wireless model, and the third environmental information is associated with the first channel information.

[0435] In one possible implementation, the first sub-model and the second sub-model of the wireless model are trained based on channel training information, first environment training information and second environment training information, and the second environment training information corresponds to the third environment information.

[0436] For another example, referring to FIG14 , there is shown a schematic diagram of the structure of another information processing device provided in an embodiment of the present application. As shown in FIG14 , the device may include a transceiver module 1401 and a processing module 1402. It can be understood that the processing module 1402 shown in FIG14 is used to perform data processing. The transceiver module 1401 can implement corresponding communication functions. The transceiver module 1401 can also be called a communication interface or a communication module. Optionally, the transceiver module 1401 may include a sending module and a receiving module. The sending module is used to perform the sending operation in the above-mentioned method embodiment. The receiving module is used to perform the receiving operation in the above-mentioned method embodiment. It should be noted that the communication device may include a sending module but not a receiving module. Alternatively, the communication device may include a receiving module but not a sending module. Specifically, it may depend on whether the above-mentioned scheme executed by the communication device includes a sending action and a receiving action.

[0437] Optionally, the communication device may further include a storage module, which may be used to store instructions and / or data. The processing module 1402 may read the instructions and / or data in the storage module so that the communication device implements the aforementioned method embodiment.

[0438] Optionally, the communication device is used to perform the actions performed by the second device or network device in any of the embodiments shown in Figures 7, 8, 10, 11 and 12.

[0439] For example, the communication device is used to perform the following scheme:

[0440] The transceiver module 1401 is configured to receive first information from a first device, where the first information is used to request prediction of first environment information; the first information includes a first high-dimensional feature vector, where the first high-dimensional feature vector is obtained based on first channel information and a first sub-model of the wireless model;

[0441] A processing module 1402 is configured to obtain initialized first environmental information and process the information based on the first high-dimensional feature vector, the initialized first environmental information, and the second sub-model of the wireless model to obtain predicted first environmental information, wherein the first sub-model and the second sub-model of the wireless model are trained based on channel training information and first environmental training information, the first environmental training information is associated with the channel training information, and the predicted first environmental information is associated with the first channel information;

[0442] The transceiver module 1401 is further configured to send second information to the first device, where the second information includes the predicted first environment information.

[0443] In a possible implementation, the processing module 1402 is configured to:

[0444] Obtaining a fourth high-dimensional feature vector based on the initialized first environment information and the second sub-model;

[0445] The predicted first environmental information is obtained by performing processing based on the fourth high-dimensional feature vector and the first high-dimensional feature vector.

[0446] In one possible implementation, the first information also includes third environmental information, and the predicted first environmental information is obtained based on the first high-dimensional feature vector, the third environmental information, the initialized first environmental information, and the second sub-model of the wireless model, and the third environmental information is associated with the first channel information.

[0447] In one possible implementation, the first sub-model and the second sub-model of the wireless model are trained based on channel training information, first environment training information and second environment training information, and the second environment training information corresponds to the third environment information.

[0448] For another example, referring to the information processing apparatus shown in FIG13 , the transceiver module 1301 is configured to send third information to the first device, where the third information is used to request prediction of the first channel information; the third information includes a first high-dimensional feature vector, where the first high-dimensional feature vector is obtained based on the first environment information and the second sub-model of the wireless model;

[0449] The transceiver module 1301 is also used to receive fourth information from the first device, where the fourth information includes predicted first channel information, where the predicted first channel information is obtained based on the first high-dimensional feature vector, the initialized first channel information, and the first sub-model of the wireless model, wherein the first sub-model and the second sub-model of the wireless model are trained based on first channel training information and environmental training information, the environmental training information is associated with the first channel training information, and the predicted first channel information is associated with the first environmental information.

[0450] In one possible implementation, the third information also includes third channel information, the predicted first channel information is obtained based on the first high-dimensional feature vector, the initialized first channel information, the third channel information, and the first sub-model of the wireless model, and the third channel information is associated with the first environmental information.

[0451] In one possible implementation, the first sub-model and the second sub-model of the wireless model are trained based on the first channel training information, the second channel training information and the environment training information, and the second channel training information corresponds to the third channel information.

[0452] For another example, referring to the information processing apparatus shown in FIG14 , the transceiver module 1401 is configured to receive third information from the second device, the third information being used to request prediction of the first channel information; the third information including a first high-dimensional feature vector, the first high-dimensional feature vector being obtained based on the first environment information and the second sub-model of the wireless model;

[0453] a processing module 1402, configured to obtain initialized first channel information, and perform processing based on the first high-dimensional feature vector, the initialized first channel information, and the first sub-model of the wireless model to obtain predicted first channel information, wherein the first sub-model and the second sub-model of the wireless model are trained based on first channel training information and environment training information, the environment training information is associated with the first channel training information, and the predicted first channel information is associated with the first environment information;

[0454] The transceiver module 1401 is further configured to send fourth information to the second device, where the fourth information includes the predicted first channel information.

[0455] In a possible implementation, the processing module 1402 is configured to:

[0456] Obtaining a fifth high-dimensional feature vector based on the initialized first channel information and the first sub-model;

[0457] Processing is performed based on the fifth high-dimensional feature vector and the first high-dimensional feature vector to obtain the predicted first channel information.

[0458] In one possible implementation, the third information also includes third channel information, the predicted first channel information is obtained based on the first high-dimensional feature vector, the initialized first channel information, the third channel information, and the first sub-model of the wireless model, and the third channel information is associated with the first environmental information.

[0459] In one possible implementation, the first sub-model and the second sub-model of the wireless model are trained based on the first channel training information, the second channel training information and the environment training information, and the second channel training information corresponds to the third channel information.

[0460] It should be understood that the specific process of each module executing the above corresponding process has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here.

[0461] The processing module 1402 in the above embodiment can be implemented by at least one processor or processor-related circuits. The transceiver module 1301 or transceiver module 1401 can be implemented by a transceiver or transceiver-related circuits. The transceiver module 1301 or transceiver module 1401 can also be referred to as a communication module or communication interface. The storage module can be implemented by at least one memory.

[0462] It should be understood that the division of the modules in the above devices is only a division of logical functions. In actual implementation, they can be fully or partially integrated into a physical entity, or they can be physically separated. In addition, the modules in the information processing device can be implemented in the form of a processor calling software; for example, the information processing device includes a processor, the processor is connected to a memory, and the memory stores instructions. The processor calls the instructions stored in the memory to implement any of the above methods or realize the functions of the modules of the device, wherein the processor is, for example, a general-purpose processor, such as a central processing unit (CPU) or a microprocessor, and the memory is a memory within the device or a memory outside the device. Alternatively, the modules in the device can be implemented in the form of hardware circuits, and the functions of some or all units can be realized by designing the hardware circuits. The hardware circuit can be understood as one or more processors. For example, in one implementation, the hardware circuit is an application-specific integrated circuit (ASIC), which realizes the functions of some or all of the above units by designing the logical relationship of the components in the circuit. For another example, in another implementation, the hardware circuit can be implemented by a programmable logic device (PLD). Taking a field programmable gate array (FPGA) as an example, it can include a large number of logic gate circuits, and the connection relationship between the logic gate circuits is configured by configuring the configuration file, thereby realizing the functions of some or all of the above units. All modules of the above devices can be implemented in the form of software called by the processor, or in the form of hardware circuits, or in part by the form of software called by the processor, and the rest by hardware circuits.

[0463] Referring to Figure 15, it is a schematic diagram of the hardware structure of another information processing device provided in an embodiment of the present application. It can be understood that the information processing device 1500 includes necessary forms such as modules, units, elements, circuits, or interfaces, which are appropriately configured together to implement this solution. The information processing device 1500 can be a wireless access network, communication equipment, core network equipment or other network equipment in Figure 1, or a component (such as a chip) in these devices to implement the method described in the above method embodiment. The information processing device 1500 includes one or more processors 1501. The processor 1501 can be a general-purpose processor or a dedicated processor. For example, it can be a baseband processor or a central processing unit. The baseband processor can be used to process communication protocols and communication data, and the central processing unit can be used to control communication devices (such as RAN nodes, terminals, or chips, etc.), execute software programs, and process data of software programs.

[0464] Optionally, in one design, the processor 1501 may include a program 1503 (sometimes also referred to as code or instructions), which may be executed on the processor 1501 to enable the information processing device 1500 to perform the methods described in the above embodiments. In another possible design, the information processing device 1500 includes circuitry (not shown in FIG15 ), which is used to implement the information processing functions in the above embodiments, etc.

[0465] Exemplarily, the processor 1501 is a processing circuit. A processing circuit is a circuit capable of processing signals. In one implementation, the processing circuit may be a circuit capable of reading and executing instructions, such as one or more of the following processors: a central processing unit (CPU), a microprocessor, a graphics processing unit (GPU) (which can be understood as a microprocessor), or a digital signal processor (DSP), or a processing circuit in the aforementioned processors. In another implementation, the processing circuit may implement certain functions through the logical relationship of a hardware circuit, and the logical relationship of the hardware circuit may be fixed or reconfigurable. For example, the processing circuit may be one or more of the following processors: a hardware circuit implemented by an ASIC or a programmable logic device (PLD), such as an FPGA, or a processing circuit in the aforementioned processors. In a reconfigurable hardware circuit, the process of the processor loading a configuration document to implement hardware circuit configuration can be understood as the process of the processor loading instructions to implement the functions of some or all of the above modules. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC or a processing circuit in an ASIC, such as one or more of the following processors: a neural network processing unit (NPU), a tensor processing unit (TPU), a deep learning processing unit (DPU), etc., or a processing circuit in the aforementioned processor. The processing circuit is used to execute relevant programs to implement the functions required to be performed by the units in the information processing device of the embodiment of the present application, or to execute the information processing method of the method embodiment of the present application.

[0466] Optionally, the information processing device 1500 may include one or more memories 1502 on which a program 1504 (sometimes also referred to as code or instructions) is stored. The program 1504 can be executed on the processor 1501, so that the information processing device 1500 performs the method described in the above method embodiment. Optionally, the memory 1502 may be located in the one or more processors, or located outside the one or more processors, or may include a storage portion located in the one or more processors and a storage portion located outside the one or more processors.

[0467] The memory 1502 may be a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM).

[0468] Optionally, the processor 1501 and / or the memory 1502 may include AI modules 1507 and 1508, each configured to implement AI-related functions. The AI ​​module may be implemented using software, hardware, or a combination of software and hardware. For example, the AI ​​module may include a real-time information processing (RIC) module. For example, the AI ​​module may be a near-real-time RIC or a non-real-time RIC.

[0469] Optionally, data may be stored in the processor 1501 and / or the memory 1502. The processor and the memory may be provided separately or integrated together.

[0470] Optionally, the information processing device 1500 may further include a transceiver 1505 and / or an antenna 1506. The processor 1501 may also be sometimes referred to as a processing unit, and controls a communication device (e.g., a RAN node or terminal). The transceiver 1505 may also be sometimes referred to as a transceiver unit, a transceiver, a transceiver circuit, or a transceiver, and is configured to implement the transceiver function of the communication device through the antenna 1506.

[0471] The processor 1501 may also be referred to as a processing unit, a processing board, a processing module, a processing device, etc. The transceiver 1505 may also be referred to as a transceiver unit, a transceiver, a transceiver device, etc.

[0472] Alternatively, the device implementing the receiving function in transceiver 1505 may be considered a receiving module, and the device implementing the transmitting function in transceiver 1505 may be considered a transmitting module. That is, transceiver 1505 includes a receiver and a transmitter. A transceiver may also be sometimes referred to as a transceiver, a transceiver module, or a transceiver circuit. A receiver may also be sometimes referred to as a receiver, a receiving module, or a receiving circuit. A transmitter may also be sometimes referred to as a transmitter, a transmitting module, or a transmitting circuit.

[0473] The processor 1501 is configured to execute the processing actions on the terminal device (e.g., the first device) in the embodiments shown in Figures 7, 8, and 10 to 12 above, and the transceiver 1505 is configured to execute the transceiver actions on the terminal device in the embodiments shown in Figures 7, 8, 10 to 12 above. For example, the processor 1501 is configured to execute step 1001 in the embodiment shown in Figure 10. The transceiver 1505 is configured to execute step 1002 in the embodiment shown in Figure 10. Optionally, the transceiver 1505 is also configured to execute step 1005 in the embodiment shown in Figure 10.

[0474] For another example, the processor 1501 is configured to execute the processing actions on the network device (e.g., the second device) side in the embodiments shown in Figures 7, 8, and 10 to 12, and the transceiver 1505 is configured to execute the transceiver actions on the network device side in the embodiments shown in Figures 7, 8, 10 to 12. For example, the processor 1501 is configured to execute step 1103 in the embodiment shown in Figure 11. The transceiver 1505 is configured to execute step 1104 in the embodiment shown in Figure 11. Optionally, the transceiver 1505 is further configured to execute step 1107 in the embodiment shown in Figure 11.

[0475] The modules in the above devices can be fully or partially integrated together, or can be implemented independently. In one implementation, when the information processing device 1500 is a chip, the chip includes a processor and may also include a transceiver. The transceiver may be an input / output circuit or a communication interface; the processor may be a processing module or a microprocessor or an integrated circuit integrated on the chip. The sending operation of the first device or the second device in the above method embodiment can be understood as the output of the chip, and the receiving operation of the first device or the second device in the above method embodiment can be understood as the input of the chip. Optionally, a memory may also be included. That is, these modules are integrated together and implemented in the form of a system-on-a-chip (SOC). The SOC may include at least one processor for implementing any of the above methods or implementing the functions of the various modules of the device. The types of the at least one processor may be different, for example, including a CPU and an FPGA, a CPU and an artificial intelligence processor, a CPU and a GPU, etc.

[0476] It should be noted that although the apparatus 1500 shown in FIG15 only shows a processor, a transceiver, a memory, and an antenna, during specific implementation, those skilled in the art will understand that the apparatus 1500 also includes other components necessary for normal operation. Furthermore, those skilled in the art will understand that, depending on specific needs, the apparatus 1500 may also include hardware components that implement other additional functions. Furthermore, those skilled in the art will understand that the apparatus 1500 may also include only the components necessary to implement the embodiments of the present application, and need not include all of the components shown in FIG15.

[0477] An embodiment of the present application further provides a computer-readable storage medium, which stores instructions. When the computer-readable storage medium is executed on a computer or a processor, the computer or processor executes one or more steps in any of the above methods.

[0478] The present application also provides a computer program product comprising instructions, which, when executed on a computer or processor, causes the computer or processor to execute one or more steps in any of the above methods.

[0479] It should be understood that in the description of this application, unless otherwise specified, " / " indicates that the objects associated with each other are in an "or" relationship. For example, A / B can mean A or B; where A and B can be singular or plural. Also, in the description of this application, unless otherwise specified, "multiple" means 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 or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or plural. In addition, to facilitate the clear description of the technical solutions of the embodiments of this application, in the embodiments of this application, words such as "first" and "second" are used to distinguish between identical or similar items with substantially the same functions and effects. Those skilled in the art will understand that words such as "first" and "second" do not limit the quantity or execution order, and words such as "first" and "second" do not necessarily mean different. At the same time, in the embodiments of this 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 this application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner to facilitate understanding.

[0480] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the division of the units is only a logical function division, and there may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. The mutual coupling, direct coupling, or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of devices or units, and can be electrical, mechanical or other forms.

[0481] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0482] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments may be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program or instructions are loaded and executed on a computer, all or part of the processes or functions according to the embodiments of the present application are generated. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium or transmitted via the computer-readable storage medium. The computer instructions may be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated therein. The available medium may be a read-only memory (ROM), a random access memory (RAM), a magnetic medium such as a floppy disk, a hard disk, a tape, a magnetic disk, or an optical medium such as a digital versatile disc (DVD), or a semiconductor medium such as a solid state disk (SSD).

[0483] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A wireless model, characterized in that, The wireless model includes a first sub-model and a second sub-model, the first sub-model is used to process the first channel information to obtain the first channel characteristic parameter, and the second sub-model is used to process the first environment information to obtain the first environment characteristic parameter, wherein the first channel information and the first environment information are associated, and the first channel characteristic parameter and the first environment characteristic parameter correspond to a first high-dimensional feature vector.

2. The wireless model according to claim 1, characterized in that The input of the downstream model includes a second high-dimensional feature vector, where the second high-dimensional feature vector is obtained by processing the first channel feature parameter and the first environment feature parameter according to a preset ratio.

3. The wireless model according to claim 1, characterized in that The first sub-model is further used to process the third high-dimensional feature vector to obtain second channel information, and / or the second sub-model is further used to process the third high-dimensional feature vector to obtain second environmental information.

4. The wireless model according to any one of claims 1 to 3, characterized in that The first channel information includes at least one of the following: Multipath information, frequency domain channel response, channel impulse response, channel eigenvector, power delay spectrum, path loss, reference signal received power, signal-to-noise ratio, Doppler frequency offset, interference information, angle of arrival and departure, transmission delay, timing advance.

5. The wireless model according to any one of claims 1 to 4, characterized in that: The first environmental information includes at least one of the following: Map and scale, building / obstruction information, location of network equipment and / or user equipment, configuration of the network equipment and / or user equipment and / or cell, density and mobility status of the user equipment, and weather.

6. An information processing method, characterized in that: The method adopts the wireless model according to any one of claims 1 to 5, wherein the first sub-model of the wireless model is deployed on a first device, and the second sub-model of the wireless model is deployed on a second device. The method includes: The first device sends first information to the second device, where the first information is used to request prediction of first environment information; the first information includes a first high-dimensional feature vector, where the first high-dimensional feature vector is obtained based on the first channel information and the first sub-model of the wireless model; The first device receives second information from the second device, and the second information includes predicted first environmental information, which is obtained by processing the first high-dimensional feature vector, the initialized first environmental information, and the second sub-model of the wireless model, wherein the first sub-model and the second sub-model of the wireless model are trained based on channel training information and first environmental training information, the first environmental training information is associated with the channel training information, and the predicted first environmental information is associated with the first channel information.

7. The method according to claim 6, characterized in that The first information also includes third environmental information. The predicted first environmental information is obtained based on the first high-dimensional feature vector, the third environmental information, the initialized first environmental information, and the second sub-model of the wireless model. The third environmental information is associated with the first channel information.

8. The method according to claim 7, characterized in that The first sub-model and the second sub-model of the wireless model are trained based on channel training information, first environment training information and second environment training information, and the second environment training information corresponds to the third environment information.

9. An information processing method, characterized in that: The method adopts the wireless model according to any one of claims 1 to 5, wherein the first sub-model of the wireless model is deployed on a first device, and the second sub-model of the wireless model is deployed on a second device. The method includes: The second device receives first information from the first device, where the first information is used to request prediction of first environment information; the first information includes a first high-dimensional feature vector, where the first high-dimensional feature vector is obtained based on the first channel information and the first sub-model of the wireless model; The second device obtains the initialized first environment information, and processes it based on the first high-dimensional feature vector, the initialized first environment information, and the second sub-model of the wireless model to obtain predicted first environment information, wherein the first sub-model and the second sub-model of the wireless model are trained based on channel training information and first environment training information, the first environment training information is associated with the channel training information, and the predicted first environment information is associated with the first channel information; The second device sends second information to the first device, where the second information includes the predicted first environment information.

10. The method according to claim 9, characterized in that The second device performs processing based on the first high-dimensional feature vector, the initialized first environment information, and the second sub-model of the wireless model to obtain predicted first environment information, including: The second device obtains a fourth high-dimensional feature vector based on the initialized first environment information and the second sub-model; The second device performs processing based on the fourth high-dimensional feature vector and the first high-dimensional feature vector to obtain the predicted first environment information.

11. The method according to claim 9 or 10, characterized in that The first information also includes third environmental information. The predicted first environmental information is obtained based on the first high-dimensional feature vector, the third environmental information, the initialized first environmental information, and the second sub-model of the wireless model. The third environmental information is associated with the first channel information.

12. The method according to claim 11, characterized in that The first sub-model and the second sub-model of the wireless model are trained based on channel training information, first environment training information and second environment training information, and the second environment training information corresponds to the third environment information.

13. An information processing method, characterized in that: The method adopts the wireless model according to any one of claims 1 to 5, wherein the first sub-model of the wireless model is deployed on a first device, and the second sub-model of the wireless model is deployed on a second device. The method includes: The second device sends third information to the first device, where the third information is used to request prediction of the first channel information; the third information includes a first high-dimensional feature vector, where the first high-dimensional feature vector is obtained based on the first environment information and the second sub-model of the wireless model; The second device receives fourth information from the first device, and the fourth information includes predicted first channel information, and the predicted first channel information is obtained by processing based on the first high-dimensional feature vector, the initialized first channel information, and the first sub-model of the wireless model, wherein the first sub-model and the second sub-model of the wireless model are trained based on first channel training information and environment training information, the environment training information is associated with the first channel training information, and the predicted first channel information is associated with the first environment information.

14. The method according to claim 13, characterized in that The third information also includes third channel information. The predicted first channel information is obtained based on the first high-dimensional feature vector, the initialized first channel information, the third channel information, and the first sub-model of the wireless model. The third channel information is associated with the first environmental information.

15. The method according to claim 14, characterized in that The first sub-model and the second sub-model of the wireless model are trained based on the first channel training information, the second channel training information and the environment training information, and the second channel training information corresponds to the third channel information.

16. An information processing method, characterized in that: The method adopts the wireless model according to any one of claims 1 to 5, wherein the first sub-model of the wireless model is deployed on a first device, and the second sub-model of the wireless model is deployed on a second device. The method includes: The first device receives third information from the second device, where the third information is used to request prediction of first channel information; the third information includes a first high-dimensional feature vector, where the first high-dimensional feature vector is obtained based on the first environment information and the second sub-model of the wireless model; The first device obtains initialized first channel information, and processes it based on the first high-dimensional feature vector, the initialized first channel information, and the first sub-model of the wireless model to obtain predicted first channel information, wherein the first sub-model and the second sub-model of the wireless model are trained based on first channel training information and environment training information, the environment training information is associated with the first channel training information, and the predicted first channel information is associated with the first environment information; The first device sends fourth information to the second device, where the fourth information includes the predicted first channel information.

17. The method according to claim 16, characterized in that The first device performs processing based on the first high-dimensional feature vector, the initialized first channel information, and the first sub-model of the wireless model to obtain predicted first channel information, including: The first device obtains a fifth high-dimensional feature vector based on the initialized first channel information and the first sub-model; The first device performs processing based on the fifth high-dimensional feature vector and the first high-dimensional feature vector to obtain the predicted first channel information.

18. The method according to claim 16 or 17, characterized in that The third information also includes third channel information. The predicted first channel information is obtained based on the first high-dimensional feature vector, the initialized first channel information, the third channel information, and the first sub-model of the wireless model. The third channel information is associated with the first environmental information.

19. The method according to claim 18, characterized in that The first sub-model and the second sub-model of the wireless model are trained based on the first channel training information, the second channel training information and the environment training information, and the second channel training information corresponds to the third channel information.

20. An information processing device, characterized in that: Comprising a module for implementing the method according to any one of claims 6 to 8; or, a module for implementing the method according to any one of claims 9 to 12; or, a module for implementing the method according to any one of claims 13 to 15; or, a module for implementing the method according to any one of claims 16 to 19.

21. An information processing system, characterized in that Including an information processing device corresponding to the method according to any one of claims 6 to 8, and an information processing device corresponding to the method according to any one of claims 9 to 12; or, including an information processing device corresponding to the method according to any one of claims 13 to 15, and an information processing device corresponding to the method according to any one of claims 16 to 19.

22. A computer-readable storage medium, characterized in that A computer program or instruction is stored, and when the computer program or instruction is executed by a processor, the method according to any one of claims 6 to 8 is implemented; or the method according to any one of claims 9 to 12 is implemented; or the method according to any one of claims 13 to 15 is implemented; or the method according to any one of claims 16 to 19 is implemented.

23. A computer program product comprising instructions which, when executed on a processor, causes the method according to any one of claims 6 to 8 to be implemented; or causes the method according to any one of claims 9 to 12 to be implemented; or causes the method according to any one of claims 13 to 15 to be implemented; or causes the method according to any one of claims 16 to 19 to be implemented.

Images