Channel information prediction method, terminal, computing unit, device, program product

Abstract

The disclosure provides a channel information prediction method, a communication terminal module, a subject computing unit, a target device and a computer program product. The target device of the embodiment of the disclosure comprises a functional subject module and a communication terminal module, the functional subject module comprises a subject computing unit; wherein the channel information prediction method for the communication terminal module comprises: measuring actual measurement channel information, sending the actual measurement channel information to the subject computing unit; receiving the predicted channel information sent by the subject computing unit.

Description

Technical Field

[0001] This disclosure relates to the field of channel information prediction technology, and in particular to a method for channel information prediction, a communication terminal module, a main computing unit, a target device, and a computer program product. Background Technology

[0002] Channel information prediction for autonomous vehicles is usually performed by the communication terminal module. However, the communication terminal cannot obtain vehicle information such as environmental information, status information, and navigation information that may affect the channel status. Therefore, the prediction accuracy is poor, it is easily affected by interference, and has low robustness. Moreover, the communication terminal module usually has limited computing resources, which restricts the prediction performance. Increasing the computing resources of the communication terminal module would increase its cost. Summary of the Invention

[0003] This disclosure provides a method for channel information prediction, a communication terminal module, a main computing unit, a target device, and a computer program product.

[0004] In a first aspect, embodiments of this disclosure provide a method for channel information prediction, used in a communication terminal module of a target device. The target device includes a functional main module and the communication terminal module, the functional main module including a main computing unit, wherein the method includes:

[0005] The measured channel information is obtained and then sent to the main computing unit.

[0006] Receive the predicted channel information sent by the main computing unit.

[0007] Secondly, embodiments of this disclosure provide a method for channel information prediction, used in a main computing unit within a functional main module of a target device, the target device including the functional main module and a communication terminal module, wherein the method includes:

[0008] Obtain the device information of the target device and receive the measured channel information sent by the communication terminal module;

[0009] Based on the measured channel information and the device information, the predicted channel information is calculated.

[0010] The predicted channel information is sent to the communication terminal module.

[0011] Thirdly, embodiments of this disclosure provide a communication terminal module, which includes a memory and a processor; the memory stores a computer program that can be executed by the processor, and when the computer program is executed by the processor, it implements any one of the channel information prediction methods of embodiments of this disclosure.

[0012] Fourthly, embodiments of this disclosure provide a main computing unit, which includes a memory and a processor; the memory stores a computer program that can be executed by the processor, and when the computer program is executed by the processor, it implements any one of the channel information prediction methods of embodiments of this disclosure.

[0013] Fifthly, embodiments of this disclosure provide a target device, comprising:

[0014] Any communication terminal module according to the embodiments of this disclosure;

[0015] The functional main module includes any one of the main computing units in the embodiments of this disclosure.

[0016] Sixthly, embodiments of this disclosure provide a computer program product, which includes a computer program that, when executed by a processor, implements any of the channel information prediction methods of embodiments of this disclosure.

[0017] In this embodiment, the communication terminal module of the target device sends the measured channel information to the main computing unit of the functional main module. The main computing unit combines the device information with the "multi-mode information" to predict the channel information, thus achieving high prediction accuracy and robustness. Moreover, compared to the communication terminal module, the main computing unit usually has more computing resources, so it can perform predictions and achieve better prediction performance without increasing the cost of the communication terminal module. In addition, although the functional main module obtains the measured channel information, the sensitivity of the measured channel information is much lower than that of the device information, and the more important device information is not sent to the communication terminal module. Therefore, this embodiment can also ensure good data security. Attached Figure Description

[0018] In the accompanying drawings of the embodiments disclosed herein:

[0019] Figure 1 This is a block diagram of a target device provided in an embodiment of the present disclosure.

[0020] Figure 2 A flowchart illustrating a method for channel information prediction in a communication terminal module, provided as an embodiment of this disclosure.

[0021] Figure 3 A flowchart of a method for channel information prediction for a main computing unit provided in an embodiment of this disclosure.

[0022] Figure 4 This is a schematic diagram illustrating the process of a channel information prediction method provided in an embodiment of this disclosure.

[0023] Figure 5This is a block diagram of a communication terminal module provided in an embodiment of the present disclosure.

[0024] Figure 6 This is a block diagram of a main computing unit provided in an embodiment of the present disclosure.

[0025] Figure 7 This is a block diagram illustrating the composition of a computer-readable medium provided in an embodiment of the present disclosure. Detailed Implementation

[0026] To enable those skilled in the art to better understand the technical solutions of this disclosure, the channel information prediction method, communication terminal module, main computing unit, target device, and computer program product provided in the embodiments of this disclosure will be described in detail below with reference to the accompanying drawings.

[0027] The present disclosure will be described more fully below with reference to the accompanying drawings; however, the embodiments shown may be embodied in different forms, and the present disclosure should not be construed as limited to the embodiments set forth below. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will enable those skilled in the art to fully understand the scope of the disclosure.

[0028] The accompanying drawings are provided to further illustrate this disclosure and form part of the specification. They are used together with the detailed embodiments to explain this disclosure and do not constitute a limitation thereof. These and other features and advantages will become more apparent to those skilled in the art from the description of detailed embodiments with reference to the accompanying drawings.

[0029] Unless otherwise specified, each embodiment and feature of this disclosure may be used individually or in combination with other embodiments and features thereof.

[0030] Those skilled in the art will understand that various changes in form and detail may be made to the embodiments of this disclosure without departing from the scope of this disclosure as set forth by the appended claims.

[0031] The terminology used in this disclosure is for the purpose of describing particular embodiments only and is not intended to limit the disclosure. The term "and / or" as used in this disclosure includes any and all combinations of one or more of the associated enumerated entries. The singular forms "a" and "the" as used in this disclosure are also intended to include the plural forms, unless the context clearly indicates otherwise. The terms "comprising," "made of," etc., as used in this disclosure specify the presence of the stated feature, integral, step, operation, element, and / or component, but do not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof.

[0032] Unless otherwise specified, all terms used in this disclosure (including technical and scientific terms) have the same meaning as commonly understood by one of ordinary skill in the art. It will also be understood that terms such as those defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant art and this disclosure, and will not be interpreted as having an idealized or overly formal meaning, unless expressly so defined in this disclosure.

[0033] During mobile communication, if the base station can obtain channel information, it can perform more accurate communication scheduling based on the channel information, such as multi-antenna scheduling in a frequency division multiplexing system, thereby improving the efficiency and reliability of information transmission, enhancing network performance, optimizing resource allocation, ensuring service quality, and improving user experience.

[0034] The actual state of the channel changes constantly, and the measurement of channel information and communication scheduling also require a certain amount of time. Therefore, even when communication scheduling is carried out based on the "latest" measured "current" channel information, the actual state of the channel may have already changed, leading to inaccurate communication scheduling.

[0035] To address this challenge, one approach is to perform "channel information prediction," which involves calculating N predicted channel information values ​​for the "future" based on M previous "historical" measured channel information values. This predicted channel information is then used for communication scheduling. Channel information prediction can be performed at the base station or at the communication terminal. However, since the measured channel information needs to be measured by the communication terminal, if channel information prediction is performed at the base station, the communication terminal must send a large amount of measured channel information to the base station, which consumes valuable uplink resources. Conversely, if the channel information prediction is performed by the communication terminal, it only needs to upload the "prediction results" to the base station, significantly reducing uplink feedback overhead.

[0036] With the development of communication technologies, such as sixth-generation mobile communication technology (6G), network density has increased, data rates have improved, and transmission latency has decreased, which has placed higher demands on channel information prediction.

[0037] The actual state of a channel is also affected by other factors such as the environment and scenario in which the communication terminal is located, including multipath effects, shadowing fading, and Doppler shift. For example, the channel state of an autonomous vehicle is also related to vehicle information such as environmental information, status information, and navigation information. Therefore, combining vehicle information with channel information prediction can significantly improve the accuracy of prediction.

[0038] In autonomous vehicles, the actual communication is conducted by the "communication terminal module," which can measure the actual channel information; while the vehicle's main functions are realized through "functional main modules" such as the autonomous driving system and the intelligent cockpit system. Therefore, vehicle information such as environmental information, status information, and navigation information are all obtained by the functional main modules.

[0039] The main functional module and the communication terminal module are interconnected but also relatively independent. The main functional module does not participate in communication, and the communication terminal module does not participate in vehicle control. Moreover, the two are usually designed and manufactured by different manufacturers. Therefore, to ensure data security, the main functional module will not provide vehicle information to the communication terminal module, and the communication terminal module will not provide measured channel information to the main functional module.

[0040] Therefore, the channel information prediction of the vehicle can only be performed by the communication terminal module. However, the communication terminal module cannot obtain vehicle information and can only make predictions based on the measured channel information alone. As a result, the prediction accuracy is poor, it is easily affected by interference, and its robustness is low, which may not meet the requirements of channel information prediction.

[0041] Moreover, as a module dedicated to communication in a vehicle, the communication terminal module often has limited computing resources and poor predictive performance, such as the limited amount of measured channel information it can process and the limited parameters of the channel information prediction model. Increasing the computing resources of the communication terminal module would increase its cost.

[0042] Firstly, referring to Figures 1 to 4 This disclosure provides a method for channel information prediction, used in the communication terminal module of a target device. The target device includes a functional main module and a communication terminal module, and the functional main module includes a main computing unit.

[0043] The channel information prediction method of this embodiment is executed by the communication terminal module of the target device, which can cooperate with the main computing unit in the main functional module of the target device to jointly realize the channel information prediction of the communication terminal module or the target device.

[0044] In this embodiment of the disclosure, the target device is a device that has certain functions and communication capabilities, which can be referred to as... Figure 1 It includes a main functional module and a communication terminal module, and the main functional module includes a main computing unit.

[0045] In some embodiments, the target device includes any one of the following: road vehicle, rail vehicle, air traffic equipment, or robot.

[0046] As one embodiment of this disclosure, the target device can be a road vehicle that travels on a regular road, such as an autonomous vehicle or other transportation vehicle, as well as a special operation vehicle such as a city sweeper or a sprinkler truck; or, the target device can be a rail vehicle such as a high-speed rail, a train, or a light rail; or, the target device can be an air transportation device such as an airplane, a helicopter, or a drone; or, the target device can be a robot such as a home robot or a humanoid robot.

[0047] It should be understood that the above are only some specific examples of the target device, and the form of the target device in the embodiments of this disclosure is not limited thereto.

[0048] In this embodiment of the disclosure, the "functional main module" is a module used to implement the main functions of the target device "itself". For example, when the target device is an autonomous vehicle, the functional main module may include its body system, power system, autonomous driving system, intelligent cockpit system, etc.

[0049] In this embodiment of the disclosure, the "main computing unit" is a computing device with data processing capabilities within the main functional module, such as a microcontroller (MCU), a central processing unit (CPU), or a graphics processing unit (GPU), which performs data processing to implement the main functions of the target device. For example, when the target device is an autonomous vehicle, the main functional module can be an on-board computing unit, which can acquire environmental information of the vehicle through sensors in the main functional module and perform warnings, autonomous driving, etc., based on the environmental information.

[0050] In this embodiment, the "communication terminal module" is a module with communication capabilities that is connected to the main functional module. Therefore, the external communication of the main functional module or the target device can be realized through the communication terminal module. For example, when the target device is an autonomous vehicle, the communication terminal module can be an in-vehicle communication terminal.

[0051] In this embodiment of the disclosure, "channel information" refers to information used to characterize the state of a wireless channel, which may include channel state information (CSI), a channel matrix, eigenvectors, etc. CSI characterizes the attenuation factors of the signal along each path, such as signal scattering, environmental attenuation, and distance attenuation. The channel matrix is ​​the original form of CSI, representing the complete response characteristics of the wireless channel in the spatial, temporal, and frequency domains. It can be in the form of a complex matrix, reflecting the channel gain and phase information of each antenna and each subcarrier. The eigenvector information is a dimensionality-reduced representation extracted from the channel matrix, commonly used for feedback and precoding.

[0052] In this embodiment of the disclosure, "measured channel information" is the "real-world" channel information obtained by the communication terminal module through actual measurement.

[0053] In this embodiment of the disclosure, "predicted channel information" refers to channel information that is "possible" within a certain period of time "afterwards" and is "calculated" based on other information.

[0054] It should be understood that since the predicted channel information is calculated rather than actually measured, it is not necessarily the same as the actual channel information at the corresponding time.

[0055] Reference Figure 2The method for channel information prediction for a communication terminal module according to embodiments of this disclosure includes:

[0056] S101. Measure the actual channel information and send the measured channel information to the main computing unit.

[0057] S102, Receive the predicted channel information sent by the main computing unit.

[0058] Reference Figure 3 The method for channel information prediction for a main computing unit according to embodiments of this disclosure includes:

[0059] S201. Obtain the device information of the target device and receive the measured channel information sent by the communication terminal module.

[0060] S202. Based on the measured channel information and equipment information, the predicted channel information is calculated.

[0061] S203. Send the predicted channel information to the communication terminal module.

[0062] Reference Figure 4 In this embodiment of the present disclosure, the communication terminal module of the target device measures the measured channel information and sends it to the main computing unit.

[0063] It should be understood that there are various specific methods used by communication terminal modules to measure actual channel information. For example, one can refer to... Figure 4 The base station can send a Channel State Information Reference Signal (CSI-RS) to the communication terminal module, and the communication terminal module can perform detection and analysis based on the CSI-RS to determine the measured channel information.

[0064] It should be understood that the communication terminal module can also send the "measurement results" to the base station so that the base station can make corresponding parameter adjustments.

[0065] Reference Figure 4 In addition to receiving the measured channel information sent by the communication terminal module, the main computing unit can also obtain the "device information" of the target device.

[0066] In this embodiment of the disclosure, "device information" refers to information representing various states of the target device, but does not include channel information.

[0067] Information representing the status of the target device can be generated or determined by the devices in the main functional module, measured by the sensors in the main functional module, or obtained by the main computing unit through data processing. Thus, "device information" is information that the main functional module or the main computing unit can "directly" obtain.

[0068] In some embodiments, the device information includes at least one of the following: device status information, device environment information, device location information, and device navigation information.

[0069] Reference Figure 4 In this embodiment of the disclosure, the device information may include one or more of the following:

[0070] (1) Equipment status information

[0071] Device status information refers to the "self-state" information of the target device, which can be generated by devices in the main functional module. For example, when the target device is an autonomous vehicle, the device status information may include the vehicle's speed, acceleration, remaining fuel, remaining battery power, etc., which can be generated by the autonomous driving system and intelligent cockpit system in the main functional module.

[0072] (2) Equipment environment information

[0073] Device status information refers to information about the environment surrounding the target device's location, such as the position, geometry, and material of objects around the target device, as well as weather information such as temperature, humidity, and rainfall. This information can be obtained through sensors located in the main functional modules. For example, when the target device is an autonomous vehicle, the sensors may include cameras, LiDAR, millimeter-wave radar, temperature sensors, humidity sensors, etc.

[0074] (3) Equipment location information

[0075] Device location information refers to the geographical location of the target device, such as its longitude, latitude, and altitude. For example, when the target device is an autonomous vehicle, its location information can be obtained through the Global Positioning System (GPS) in the main functional module.

[0076] (4) Equipment navigation information

[0077] Device navigation information refers to information related to navigating the "movement" of a target device, such as map information of the target device's location, historical driving route information, and navigation plan route information. For example, when the target device is an autonomous vehicle, the main computing unit can obtain device navigation information based on user input commands, information from the Global Positioning System (GPS), and information from the autonomous driving system.

[0078] It should be understood that the specific forms and methods of obtaining equipment information are not limited to the examples listed above.

[0079] Furthermore, the calculation unit can combine the measured channel information and device information above to calculate the predicted channel information; since the above calculation is based not only on the measured channel information but also on the device information, the predicted channel information it calculates has higher accuracy.

[0080] It should be understood that there are various specific methods for calculating and predicting channel information based on certain information. For example, channel information can be predicted using a pre-defined artificial intelligence (AI) channel information prediction model. That is, the measured channel information and equipment information can be used as the "input" of the channel information prediction model, while the "output" of the channel information prediction model can be used as the predicted channel information. Since channel information has a time correlation, the channel information prediction model can be a model capable of processing data sequences, such as a recurrent neural network (RNN) model, a long short-term memory network (LSTM) model, a gated recurrent unit network (GRU) model, or a transformer model.

[0081] It should be understood that it is also feasible to calculate and predict channel information using other algorithms.

[0082] It should be understood that the more computational resources used in channel information prediction, the more complex the algorithm can be. For example, the channel information prediction model can have more parameters and allow more inputs, thus resulting in better prediction performance.

[0083] For example, to meet the requirements of channel information prediction in 5G or 6G mobile communication technologies, the required computing power is between 0.2 and 5 TOPS, and the required storage space is approximately 50 MB. However, with the development of technology, the computing units of most target devices can meet the above computing resource requirements. For example, when the target device is an autonomous vehicle, its intelligent cockpit system has a computing power of at least 8 TOPS, and may even reach tens of TOPS, while the running memory is at least 8-16 GB, and may even reach hundreds of GB, all of which far exceed the requirements of channel information prediction.

[0084] Therefore, the main computing unit of the functional module usually has large computing resources, which can greatly improve the channel information prediction performance without increasing the hardware cost, and meet the high requirements of 5G and 6G for prediction performance.

[0085] After obtaining the predicted channel information, refer to Figure 4 The main computing unit can also quantize and encode the predicted channel information and send it back to the communication terminal module, thereby enabling the communication terminal module to obtain high-quality predicted channel information.

[0086] It should be understood that the communication terminal module can also make further use of the received predicted channel information.

[0087] For example, the communication terminal module can adjust its own parameters based on predicted channel information; and refer to Figure 4The communication terminal module can also send the predicted channel information to the base station so that the base station can perform corresponding communication scheduling based on the predicted channel information, such as precoding of multiple-input multiple-output (MIMO) antennas, beamforming, adaptive modulation and coding, etc., to improve network capacity and speed and improve user experience.

[0088] In this embodiment, the communication terminal module of the target device sends the measured channel information to the main computing unit of the functional main module. The main computing unit combines the device information with the "multi-mode information" to predict the channel information, thus achieving high prediction accuracy and robustness. Moreover, compared to the communication terminal module, the main computing unit usually has more computing resources, so it can perform predictions and achieve better prediction performance without increasing the cost of the communication terminal module. In addition, although the functional main module obtains the measured channel information, the sensitivity of the measured channel information is much lower than that of the device information, and the more important device information is not sent to the communication terminal module. Therefore, this embodiment can also ensure good data security.

[0089] In some embodiments, transmitting the measured channel information to the main computing unit (S101) includes:

[0090] S1011, Send channel information prediction requirements to the main computing unit.

[0091] Channel information prediction requirements characterize the resources needed to compute and predict channel information.

[0092] S1012A: In response to receiving the acknowledgment instruction sent by the main computing unit, the measured channel information is sent to the main computing unit.

[0093] The confirmation indicates that the main computing unit meets the channel information prediction requirements.

[0094] In some embodiments, receiving measured channel information sent by the communication terminal module (S201) includes:

[0095] S2011, Receive channel information prediction requirements sent by the communication terminal module.

[0096] S2012. Determine whether the main computing unit meets the channel information prediction requirements.

[0097] S2012A: In response to the main computing unit meeting the channel information prediction requirements, an acknowledgment instruction is sent to the communication terminal module, and the measured channel information sent by the communication terminal module is received.

[0098] As one embodiment of this disclosure, in order to prevent the main computing unit from having insufficient computing resources to predict channel information, the communication terminal module may first "negotiate" with the main computing unit, and only send the measured channel information to the main computing unit when it is determined that the main computing unit has sufficient computing resources.

[0099] The communication terminal module can first send information representing the computational resources required to calculate and predict channel information, or in other words, the "channel information prediction requirements," to the main computing unit. For example, the channel information prediction requirements may include: the computing power required to calculate and predict channel information, such as the number of GFLOPS; the storage space required to calculate and predict channel information, such as "T1 × 2 × Nt × Nr × Nb × number of quantization bits" if T1 time slots of measured channel information need to be processed each time; the channel information prediction model used to calculate and predict channel information, such as a specific LSTM model or a Transformer model; and the latency requirements, such as the required time frame for obtaining feedback on the predicted channel information.

[0100] After receiving a channel information prediction request, the main computing unit can analyze whether its currently available computing resources meet the requirements. For example, based on the current situation, the main computing unit can determine which high-priority applications need to be guaranteed to operate, such as autonomous driving applications and cockpit instrument applications in autonomous vehicles; then calculate how many computing resources are needed to ensure the operation of these high-priority applications; and determine whether the remaining computing resources after subtracting the occupied computing resources from its total computing resources meet the channel information prediction requirements.

[0101] If the main computing unit determines that the current channel information prediction requirement is met, it can send a "confirmation instruction" to the communication terminal module. Only after receiving the confirmation instruction will the communication terminal module send the measured channel information to the main computing unit, and only then will the main computing unit begin to perform channel information prediction.

[0102] In some embodiments, after sending the channel information prediction request to the main computing unit (S1011), the method further includes:

[0103] S1012B: In response to receiving a rejection indication, calculate alternative predicted channel information based on the measured channel information.

[0104] The rejection indicates that the computational unit representing the main body does not meet the channel information prediction requirements.

[0105] In some embodiments, after determining whether the main computing unit meets the channel information prediction requirement (S2012), the method further includes:

[0106] S2012B: In response to the main computing unit not meeting the channel information prediction requirements, a rejection indication is sent to the communication terminal module.

[0107] As one embodiment of this disclosure, if the main computing unit determines that it does not meet the channel information prediction requirements, it can send a "rejection indication" to the communication terminal module. After receiving the rejection indication, the communication terminal module will "not" send the measured channel information to the main computing unit. Furthermore, the communication terminal module can use its own computing resources to calculate "alternative predicted channel information" using "only" the measured channel information, and use it as the result of the channel information prediction.

[0108] It should be understood that, due to the limited computing resources of the communication terminal module and its inability to obtain device information, the accuracy of the alternative predicted channel information calculated by it may be lower than that of the predicted channel information calculated by the main computing unit.

[0109] It should be understood that when the channel information prediction requirement is not met, the main computing unit may not send a rejection indication, but instead "do not reply". Thus, if the communication terminal module does not receive feedback within a certain period of time after sending the channel information prediction requirement, it can be determined that the main computing unit does not meet the channel information prediction requirement.

[0110] It should be understood that when the main computing unit does not meet the channel information prediction requirements, the communication terminal module may also completely "not perform" channel information prediction and directly use the measured channel information.

[0111] It should be understood that the channel information prediction model can be loaded directly when the main computing unit starts up, or it can be dynamically loaded when the main computing unit successfully determines that the channel information prediction should be performed by the main computing unit during the "first" negotiation.

[0112] It should be understood that after the "first" negotiation is successful, the computing resources required for channel information prediction can be "reserved" in the main computing unit, so that negotiation is not required in subsequent channel information prediction processes.

[0113] It should be understood that sufficient computing resources can be "directly reserved" in the target device when it leaves the factory or when the main computing unit is started, so that the main computing unit will necessarily meet the channel information prediction requirements, and the communication terminal module and the main computing unit do not need to negotiate.

[0114] In some embodiments, the measured channel information is obtained, and the measured channel information is sent to the main computing unit (S101), including:

[0115] S101A: Measure the actual channel information and send the measured channel information to the main computing unit.

[0116] In some embodiments, receiving measured channel information sent by the communication terminal module (S201) includes:

[0117] S201A receives multiple measured channel information sent by the communication terminal module.

[0118] Based on the measured channel information and device information, the predicted channel information (S202) is calculated, including:

[0119] S202A. Based on the measured channel information and equipment information, the predicted channel information is calculated.

[0120] When performing channel information prediction, the more measured channel information inputs, the more information is available for prediction, and the higher the accuracy of the prediction result.

[0121] Therefore, as one embodiment of this disclosure, the communication terminal module can obtain "multiple" measured channel information through "multiple" measurements, and send the multiple measured channel information to the main computing unit, so that the main computing unit can calculate the predicted channel information based on the multiple measured channel information each time.

[0122] It should be understood that the "device information" used by the main computing unit in each calculation can also be "multiple". For example, multiple pieces of device information corresponding to the measurement time of multiple measured channel information can be input into the channel information prediction model together with the measured channel information to further increase the amount of information on which the channel information prediction is based and further improve the accuracy of the prediction.

[0123] In some embodiments, the measured channel information is obtained, and the measured channel information is sent to the main computing unit (S101), including:

[0124] S101AA: Multiple measured channel information is obtained through multiple measurements. After each measurement, the measured channel information obtained from the measurement is sent to the main computing unit.

[0125] As one embodiment of this disclosure, the communication terminal module can send the latest measured "current" channel information to the main computing unit after obtaining a measured channel information "each" time. Through multiple measurements and multiple transmissions, the computing unit can receive multiple measured channel information. For example, the computing unit can save the M most recently received measured channel information and input the saved M measured channel information into the channel information prediction model each time channel information prediction is performed.

[0126] In some embodiments, the measured channel information is obtained, and the measured channel information is sent to the main computing unit (S101), including:

[0127] S101AB: After obtaining multiple measured channel information through multiple measurements, the measured channel information obtained from the most recent measurement and the multiple measured channel information obtained from previous measurements are sent together to the main computing unit.

[0128] As another embodiment of this disclosure, the communication terminal module can also continuously measure and obtain multiple measured channel information, and save these measured channel information. When conditions permit, the latest measured "current" measured channel information and multiple previously measured "historical" measured channel information can be sent together to the main computing unit. For example, when the main computing unit starts "later" than the communication terminal module, or when the main computing unit does not meet the channel information prediction requirements for a period of time, but "becomes" to meet the channel information prediction requirements due to the release of some computing resources, it has not obtained any measured channel information. Therefore, the communication terminal module can send multiple previously "accumulated" measured channel information together to the main computing unit so that the main computing unit can complete the "initial few" channel information predictions.

[0129] It should be understood that it is also feasible if the communication terminal module sends only one measured channel information and the computing unit performs channel information prediction based only on one measured channel information.

[0130] Secondly, referring to Figures 1 to 4 This disclosure provides a method for channel information prediction, used in the main computing unit of the functional main module of a target device, the target device including the functional main module and the communication terminal module.

[0131] The channel information prediction method of this disclosure is executed by the main computing unit in the functional main module of the target device, which can cooperate with the communication terminal module of the target device to jointly realize the channel information prediction of the communication terminal module or the target device.

[0132] In some embodiments, the target device includes any one of the following: road vehicle, rail vehicle, air traffic equipment, or robot.

[0133] Reference Figure 3 The method for channel information prediction for a main computing unit according to embodiments of this disclosure includes:

[0134] S201. Obtain the device information of the target device and receive the measured channel information sent by the communication terminal module.

[0135] S202. Based on the measured channel information and equipment information, the predicted channel information is calculated.

[0136] S203. Send the predicted channel information to the communication terminal module.

[0137] In some embodiments, the device information includes at least one of the following: device status information, device environment information, device location information, and device navigation information.

[0138] In some embodiments, receiving measured channel information sent by the communication terminal module (S201) includes:

[0139] S2011, Receive channel information prediction requirements sent by the communication terminal module.

[0140] Channel information prediction requirements characterize the resources needed to compute and predict channel information.

[0141] S2012. Determine whether the main computing unit meets the channel information prediction requirements.

[0142] S2013A: In response to the main computing unit meeting the channel information prediction requirements, an acknowledgment instruction is sent to the communication terminal module, and the measured channel information sent by the communication terminal module is received.

[0143] In some embodiments, after determining whether the main computing unit meets the channel information prediction requirement (S2012), the method further includes:

[0144] S2013B: In response to the main computing unit not meeting the channel information prediction requirements, a rejection indication is sent to the communication terminal module.

[0145] In some embodiments, receiving measured channel information sent by the communication terminal module (S201) includes:

[0146] S201A receives multiple measured channel information sent by the communication terminal module.

[0147] Based on the measured channel information and device information, the predicted channel information (S202) is calculated, including:

[0148] S202A. Based on the measured channel information and equipment information, the predicted channel information is calculated.

[0149] In some embodiments, after obtaining the device information of the target device and receiving the measured channel information sent by the communication terminal module (S203), the method further includes:

[0150] S204. Save the device information and measured channel information as time-corresponding device channel information mapping data.

[0151] As one embodiment of this disclosure, the main computing unit can save the device information it acquires together with the measured channel information sent by the communication terminal module to form "device channel information mapping data"; and in the device channel information mapping data, the device information and the measured channel information have a corresponding relationship, that is, the measured channel information measured at a certain time corresponds to the device information acquired at that time.

[0152] As mentioned earlier, in related technologies, the main functional module does not provide device information to the communication terminal module, and the communication terminal module does not provide measured channel information to the main functional module. Therefore, although both measured channel information and device information exist in the target device, it is impossible to obtain "integrated data" that includes both measured channel information and device information and has a corresponding relationship between them. As a result, training sample data is lacking in the training and updating of the channel information prediction model.

[0153] According to embodiments of this disclosure, the main computing unit can simultaneously obtain device information and measured channel information with a clear correspondence, forming device channel information mapping data to solve the problem of lack of training sample data for the channel information prediction model.

[0154] In some embodiments, after saving the device information and measured channel information as time-corresponding device channel information mapping data (S204), the method further includes:

[0155] S205. Send the device channel information mapping data to the channel information prediction model training unit.

[0156] As one embodiment of this disclosure, after the main computing unit obtains the above-mentioned "device channel information mapping data", it can also send it to the channel information prediction model training unit, which then "trains" the channel information prediction model based on this data. For example, the channel information prediction model training unit can be a server in the "cloud". The main computing unit can send the device channel information mapping data to the server online or offline. The server can train the channel information prediction model based on the device channel information mapping data sent by multiple target devices to improve the prediction accuracy of the channel information prediction model. Afterwards, the server can distribute the updated channel information prediction model to the main computing units of each target device via over-the-air (OTA) technology or offline.

[0157] It should be understood that there are various ways to train a model using training data. For example, the measured channel information and device information at a certain time in the device channel information mapping data can be input together into the channel information prediction model, and the output of the channel information prediction model can be compared with the measured channel information at a subsequent time in the device channel information mapping data, which serves as the "standard output". For example, a loss function can be calculated, and then the parameters of the channel information prediction model can be adjusted based on the loss function.

[0158] It should be understood that the application of device channel information mapping data is not limited to sending it to the channel information prediction model training unit. For example, the main computing unit can also directly update its own channel information prediction model based on the device channel information mapping data, or use the device channel information mapping data in other fields.

[0159] Thirdly, referring to Figure 5 This disclosure provides a communication terminal module, which includes a memory and a processor; the memory stores a computer program that can be executed by the processor, and when the computer program is executed by the processor, it implements any one of the channel information prediction methods of this disclosure.

[0160] Fourthly, refer to Figure 6 This disclosure provides a main computing unit, which includes a memory and a processor; the memory stores a computer program that can be executed by the processor, and when the computer program is executed by the processor, it implements any of the channel information prediction methods of this disclosure.

[0161] Fifthly, refer to Figure 7 This disclosure provides a target device, comprising:

[0162] Any communication terminal module according to the embodiments of this disclosure;

[0163] The functional main module includes any one of the main computing units in the embodiments of this disclosure.

[0164] In some embodiments, the target device includes any of the following:

[0165] Road vehicles, rail vehicles, air transport equipment, robots.

[0166] Sixthly, embodiments of this disclosure provide a computer program product, which includes a computer program that, when executed by a processor, implements any of the channel information prediction methods of embodiments of this disclosure.

[0167] In this embodiment of the disclosure, the processor is a device with data processing capabilities, including but not limited to a central processing unit (CPU); the memory is a device with data storage capabilities, including but not limited to random access memory (RAM), more specifically such as SDRAM, DDR, etc., read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory (FLASH); the I / O interface, or read-write interface, is connected between the processor and the memory, enabling information exchange between the memory and the processor, including but not limited to a data bus (Bus).

[0168] Those skilled in the art will understand that all or some of the steps, systems, and devices disclosed above, as functional modules / units, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0169] In hardware implementations, the division between functional modules / units mentioned in the above description does not necessarily correspond to the division of physical components; for example, a physical component may have multiple functions, or a function or step may be executed by several physical components working together.

[0170] Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit (CPU), digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit (ASIC). Such software may be distributed on a computer-readable medium, which may include computer storage media and communication media. In embodiments of this disclosure, computer storage media include volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information, and any other media that can be used to store desired information and can be accessed by a computer. In embodiments of this disclosure, communication media typically contain computer-readable instructions, data structures, program modules, or other data in modulated data signals such as carrier waves or other transmission mechanisms, and may include any information delivery medium.

Claims

1. A method for channel information prediction, used in a communication terminal module of a target device, the target device comprising a functional main module and the communication terminal module, the functional main module comprising a main computing unit, wherein, The method includes: The measured channel information is obtained and then sent to the main computing unit. Receive the predicted channel information sent by the main computing unit.

2. The method according to claim 1, wherein, The step of sending the measured channel information to the main computing unit includes: The main computing unit sends a channel information prediction request; the channel information prediction request represents the resources required to calculate the predicted channel information. In response to receiving an acknowledgment from the main computing unit, the measured channel information is sent to the main computing unit; the acknowledgment indicates that the main computing unit meets the channel information prediction requirement.

3. The method according to claim 2, wherein, After sending the channel information prediction request to the main computing unit, the method further includes: In response to receiving a rejection indication, alternative predicted channel information is calculated based on the measured channel information; the rejection indication indicates that the main calculation unit does not meet the channel information prediction requirements.

4. The method according to claim 1 or 2, wherein, The measurement obtains measured channel information, and the measured channel information is sent to the main computing unit, including: Multiple measurements are taken to obtain multiple measured channel information. After each measurement, the measured channel information obtained in that measurement is sent to the main computing unit. or, After obtaining multiple measured channel information through multiple measurements, the measured channel information obtained from the most recent measurement and the multiple measured channel information obtained from the previous measurements are sent together to the main computing unit.

5. A method for channel information prediction, used in a main computing unit of a functional main module of a target device, the target device comprising the functional main module and a communication terminal module, wherein, The method includes: Obtain the device information of the target device and receive the measured channel information sent by the communication terminal module; Based on the measured channel information and the device information, the predicted channel information is calculated. The predicted channel information is sent to the communication terminal module.

6. The method according to claim 5, wherein, The device information includes at least one of the following: Equipment status information, equipment environment information, equipment location information, and equipment navigation information.

7. The method according to claim 5, wherein, The receipt of the measured channel information sent by the communication terminal module includes: The system receives a channel information prediction request sent by the communication terminal module; the channel information prediction request represents the resources required to calculate the predicted channel information. Determine whether the main computing unit meets the channel information prediction requirements; In response to the main computing unit meeting the channel information prediction requirement, it sends an acknowledgment instruction to the communication terminal module and receives the measured channel information sent by the communication terminal module.

8. The method according to any one of claims 5 to 7, wherein, After acquiring the device information of the target device and receiving the measured channel information sent by the communication terminal module, the method further includes: The device information and the measured channel information are saved as device information and measured channel information data corresponding to time.

9. The method according to any one of claims 5 to 7, wherein, After saving the device information and the measured channel information as time-corresponding device channel information mapping data, the method further includes: The device channel information mapping data is sent to the channel information prediction model training unit.

10. A communication terminal module, wherein, It includes a memory and a processor; the memory stores a computer program that can be executed by the processor, and when the computer program is executed by the processor, it implements the channel information prediction method according to any one of claims 1 to 4.

11. A main computing unit, wherein, It includes a memory and a processor; the memory stores a computer program that can be executed by the processor, and when the computer program is executed by the processor, it implements the channel information prediction method according to any one of claims 5 to 9.

12. A target device, wherein, include: The communication terminal module as described in claim 10; The main functional module includes the main computing unit as described in claim 11.

13. The target device according to claim 12, wherein, The target device includes any one of the following: Road vehicles, rail vehicles, air transport equipment, robots.

14. A computer program product, wherein, The method includes a computer program that, when executed by a processor, implements the channel information prediction method according to any one of claims 1 to 4, or the channel information prediction method according to any one of claims 5 to 9.

Images