Model scheduling method and device based on navigation signal, and storage medium

Abstract

The present application relates to the field of neural network model, and discloses a model scheduling method and device based on navigation signal and storage medium.The method provided by the present application comprises the following steps: determining the signal complexity of the navigation signal based on the pre-acquired navigation signal, wherein the signal complexity is determined by comparing the value of the navigation signal with a preset value range; generating a scheduling instruction corresponding to the signal complexity based on the signal complexity; in response to the scheduling instruction, calling the corresponding convolution layer in the signal processing model to process the navigation signal at the corresponding precision level, wherein the number and precision level of the called convolution layer are positively correlated with the signal complexity; and mapping the processed navigation signal at the corresponding precision level to generate an output signal.The method provided by the present application can schedule the corresponding convolution layer and precision level in the signal processing module according to the complexity of the navigation signal to process the navigation signal, so as to reduce the calculation amount and power consumption when processing the navigation signal.

Description

Technical Field

[0001] This invention relates to the field of neural network models, and more particularly to a model scheduling method, device, and storage medium based on navigation signals. Background Technology

[0002] With the development of satellite navigation technology, convolutional neural networks (CNNs) have been gradually integrated into satellite navigation chips to enable them to classify, detect, and predict trends in data such as spectrograms, pseudocode residual maps, and channel energy maps. Currently, the mainstream approach is to load static CNN models into the chip to perform various data processing tasks. However, in practical applications, this "fixed structure + fixed precision" strategy has the following problems:

[0003] 1. Due to the fixed model structure, computing resources cannot be scheduled as needed when executing tasks of different complexities, resulting in lightweight tasks being "executed with high precision redundancy," which causes the chip to generate a lot of unnecessary power consumption.

[0004] 2. Some data processing tasks do not require high computational precision (such as coarse classification and multipath counting), while other data processing tasks require high-precision computation (such as signal loss warning). Fixed CNN models, due to their uniformly set computational precision, cannot meet the needs of multiple tasks with different computational precision. Summary of the Invention

[0005] This invention provides a model scheduling method, device, and storage medium based on navigation signals to solve at least one of the above-mentioned problems.

[0006] In a first aspect, embodiments of the present invention provide a model scheduling method based on navigation signals, comprising: generating a corresponding scheduling instruction based on a pre-acquired navigation signal; responding to the scheduling instruction, calling a corresponding convolutional layer in a signal processing model to process the navigation signal at a corresponding precision level; and mapping the processed navigation signal at a corresponding precision level to generate an output signal.

[0007] The model scheduling method based on navigation signals provided in this invention can generate corresponding scheduling instructions based on the acquired navigation signals, thereby scheduling different convolutional layers in the signal processing model to process the navigation signals with corresponding precision levels. This allows the signal processing model to call on corresponding levels of computing power and computational precision to process the navigation signals according to their complexity, avoiding wasting computing power and generating unnecessary power consumption when processing low-power tasks.

[0008] Optionally, the step of generating corresponding scheduling instructions based on pre-acquired navigation signals includes: determining the signal complexity of the navigation signals based on the pre-acquired navigation signals; and generating scheduling instructions corresponding to the signal complexity based on the signal complexity.

[0009] Optionally, when the navigation signal is within a first numerical range, the signal complexity is at the first level; when the navigation signal is within a second numerical range, the signal complexity is at the second level; and when the navigation signal is within a third numerical range, the signal complexity is at the third level; wherein the first numerical range is greater than the second numerical range, and the second numerical range is greater than the third numerical range.

[0010] Optionally, the step of invoking the corresponding convolutional layer in the signal processing model to process the navigation signal at the corresponding accuracy level in response to the scheduling instruction includes: invoking at least one, at least two, or at least three convolutional layers in the signal processing model in response to the scheduling instruction; and processing the navigation signal at the corresponding accuracy level based on the number of convolutional layers invoked.

[0011] Optionally, the step of processing navigation signals with a corresponding accuracy level based on the number of convolutional layers invoked includes: configuring a corresponding number of output channels in the corresponding convolutional layers based on the number of convolutional layers invoked; obtaining the accuracy level corresponding to the number of convolutional layers invoked; and processing the navigation signals based on the invoked convolutional layers, the output channels configured for each convolutional layer, and the corresponding accuracy level.

[0012] Optionally, in the step of configuring the corresponding number of output channels in the corresponding convolutional layer, the model scheduling method based on navigation signals includes: obtaining mask field information corresponding to the output channels; and configuring the corresponding number of output channels in the corresponding convolutional layer based on the mask field information.

[0013] Optionally, the step of mapping the processed navigation signal to a corresponding accuracy level to generate an output signal includes: mapping the numerical range of the processed navigation signal to a numerical range corresponding to the accuracy level based on the accuracy level used to process the navigation signal, thereby obtaining a mapped navigation signal; and generating an output signal based on the mapped navigation signal.

[0014] Optionally, after generating the output signal, the model scheduling method based on the navigation signal further includes: generating quantization range information corresponding to the numerical range of the output signal based on the numerical range of the output signal; and updating the quantization parameters of the model used to receive the output signal based on the quantization range information.

[0015] Optionally, the navigation signal includes a signal-to-noise ratio signal and / or a residual signal and / or a phase-locked signal and / or an interference signal.

[0016] In a second aspect, embodiments of the present invention provide a model scheduling device, comprising: a processor and a memory, wherein the memory stores instructions; the processor invokes the instructions in the memory to cause the processor to execute the model scheduling method based on navigation signals according to any of the foregoing embodiments of the first aspect of the present invention.

[0017] The processor of the model scheduling device provided in this embodiment of the invention executes the model scheduling method based on navigation signals according to any of the foregoing embodiments of the first aspect of the invention by calling instructions in the memory. It can generate corresponding scheduling instructions according to the acquired navigation signals, thereby scheduling different convolutional layers in the signal processing model to process the navigation signals with corresponding precision levels. This allows the signal processing model to call corresponding levels of computing power and computational precision to process the navigation signals according to their complexity, avoiding wasting computing power and generating unnecessary power consumption when processing low-power tasks.

[0018] Thirdly, embodiments of the present invention provide a computer-readable storage medium storing instructions that, when executed by a processor, implement the model scheduling method based on navigation signals according to any of the foregoing embodiments of the first aspect of the present invention.

[0019] The instructions stored in the computer-readable storage medium provided in the embodiments of the present invention can be called by a processor and executed by the model scheduling method based on navigation signals according to any of the foregoing embodiments of the first aspect of the present invention. The method generates corresponding scheduling instructions based on the acquired navigation signals, thereby scheduling different convolutional layers in the signal processing model to process the navigation signals at corresponding precision levels. This enables the signal processing model to call corresponding levels of computing power and computational precision to process the navigation signals according to their complexity, avoiding wasting computing power and generating unnecessary power consumption when processing low-power tasks. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.

[0021] Figure 1 This is a flowchart of the first embodiment of the model scheduling method based on navigation signals of the present invention;

[0022] Figure 2 This is a flowchart of step S110 in the first embodiment of the model scheduling method based on navigation signals of the present invention;

[0023] Figure 3 This is a flowchart of step S120 in the first embodiment of the model scheduling method based on navigation signals of the present invention;

[0024] Figure 4 This is a flowchart of step S122 in the first embodiment of the model scheduling method based on navigation signals of the present invention;

[0025] Figure 5 This is a flowchart of step S130 in the first embodiment of the model scheduling method based on navigation signals of the present invention;

[0026] Figure 6 This is a flowchart of a second embodiment of the model scheduling method based on navigation signals of the present invention;

[0027] Figure 7 A structural block diagram of a first embodiment of a satellite navigation device for implementing the model scheduling method based on navigation signals of the present invention;

[0028] Figure 8 A scheduling flowchart for a satellite navigation device implementing the model scheduling method based on navigation signals of the present invention;

[0029] Figure 9 This is a schematic representation of the structural configuration of the first embodiment of the model scheduling method based on navigation signals of the present invention;

[0030] Figure 10 This is a structural block diagram of the switching accuracy level of the first embodiment of the model scheduling method based on navigation signals of the present invention;

[0031] Figure 11 This is a structural block diagram of one embodiment of the model scheduling device of the present invention. Detailed Implementation

[0032] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0033] It should be noted that all directional indications in the embodiments of the present invention, such as up, down, left, right, front, back, etc., are only used to explain the relative positional relationship and movement of the components in a specific posture as shown in the attached figure. If the specific posture changes, the directional indication will also change accordingly.

[0034] Furthermore, the use of terms such as "first" and "second" in this invention is for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature. Additionally, the technical solutions of the various embodiments can be combined with each other, but only on the basis of being achievable by those skilled in the art. When the combination of technical solutions is contradictory or impossible to implement, such a combination of technical solutions should be considered non-existent and not within the scope of protection claimed by this invention.

[0035] For ease of understanding, the model scheduling method based on navigation signals according to embodiments of the present invention will be described below, such as... Figure 1 As shown, the model scheduling method based on navigation signals in this embodiment of the invention includes steps S110 to S130.

[0036] In step S110, a corresponding scheduling instruction is generated based on the pre-acquired navigation signal.

[0037] like Figure 2 As shown, in some optional embodiments, step S110 includes steps S111 to S112.

[0038] In step S111, the signal complexity of the navigation signal is determined based on the pre-acquired navigation signal.

[0039] In step S112, a scheduling instruction corresponding to the signal complexity is generated based on the signal complexity.

[0040] In this embodiment, the navigation signal includes a signal-to-noise ratio signal and / or a residual signal and / or a phase-locked signal and / or an interference signal.

[0041] Specifically, when the navigation signal falls within a first numerical range, the signal complexity is at level one. When the navigation signal falls within a second numerical range, the signal complexity is at level two. When the navigation signal falls within a third numerical range, the signal complexity is at level three.

[0042] The first numerical range is greater than the second numerical range, and the second numerical range is greater than the third numerical range.

[0043] A high signal-to-noise ratio (SNR) indicates a strong navigation signal with minimal interference, while a low SNR indicates weak signal strength and significant interference. A lower residual value in the residual signal indicates a more stable navigation signal. The phase-locked signal (PLS) is used to determine whether carrier phase locking has been achieved during navigation. A stable phase indicates successful carrier phase locking, while phase jumps, fading, or interference indicate a lack of phase lock. Interference signals are the intensity of broadband, narrowband, or pulse signals generated by the external environment; higher interference intensity indicates greater interference to the navigation signal.

[0044] In this embodiment, when the navigation signal is a signal-to-noise ratio signal, the first value range is greater than or equal to 40 dB-Hz, the second value range is 30 dB-Hz to 40 dB-Hz, and the third value range is less than 30 dB-Hz.

[0045] When the navigation signal also includes residual signal, phase-locked signal, and interference signal, if the signal complexity is at level one, that is, when the signal-to-noise ratio is greater than or equal to 40 dB-Hz, the residual value of the residual signal is the lowest, the phase of the phase-locked signal is stable, carrier phase locking is completed, and there is no interference signal.

[0046] If the signal complexity is at level two, i.e. the signal-to-noise ratio is between 30 dB-Hz and 40 dB-Hz, the residual value of the residual signal is larger than that at level one but smaller than that at level three. The phase-locked signal loses its lock and the interference signal is of medium strength.

[0047] If the signal complexity is at level three, i.e. the signal-to-noise ratio is less than 30 dB-Hz, the residual value of the residual signal is larger than that at level two, the phase-locked signal frequently loses lock, and the intensity of the interference signal is the greatest.

[0048] The residual value of the residual signal, the frequency at which the phase-locked signal loses lock, and the intensity of the interference signal can be preset, and this application does not impose any limitations on them.

[0049] After determining the signal complexity, corresponding scheduling instructions are generated based on the level of signal complexity, enabling the signal processing model to process the corresponding navigation signals according to the scheduling instructions. The specific process of calling the signal processing model is as follows.

[0050] In step S120, in response to the scheduling instruction, the corresponding convolutional layer in the signal processing model is invoked to process the navigation signal at the corresponding accuracy level.

[0051] like Figure 3 As shown, in some optional embodiments, step S120 includes steps S121 to S122.

[0052] In step S121, in response to the scheduling instruction, at least one convolutional layer, or at least two convolutional layers, or at least three convolutional layers in the signal processing model are invoked.

[0053] In step S122, the navigation signal is processed with a corresponding level of precision based on the number of convolutional layers invoked.

[0054] In this embodiment, the signal processing model is a convolutional neural network (CNN) model. In response to scheduling instructions, when the signal complexity is at level one (lowest level), at least one convolutional layer in the signal processing model is invoked to process the navigation signal; when the signal complexity is at level two (medium level), at least two convolutional layers in the signal processing model are invoked to process the navigation signal; and when the signal complexity is at level three (highest level), at least three convolutional layers in the signal processing model are invoked to process the navigation signal.

[0055] Specifically, in this embodiment, when processing navigation signals with a signal complexity of level one, the signal processing model calls the convolutional layer of the first layer of the signal processing model to achieve fast classification and simple judgment of the navigation signals. When processing navigation signals with a signal complexity of level two, the convolutional layers of the first and second layers of the signal processing model are called to identify the multipath of the navigation signals. When processing navigation signals with a signal complexity of level three, the convolutional layers of the first, second, and third layers of the signal processing model are called to identify and calculate the pseudorange oscillation and sliding window period of the navigation signals.

[0056] That is, the model scheduling method based on navigation signals in this embodiment of the invention increases the number of convolutional layers and output channels used to process navigation signals and improves the accuracy level only when the navigation signals are unstable and interference occurs. When the received navigation signals are in a stable state and are not interfered with, the signal processing model processes the navigation signals by default with the signal complexity level as the first level.

[0057] like Figure 4 As shown, step S122 further includes steps S1221 to S1223.

[0058] In step S1221, based on the number of convolutional layers invoked, a corresponding number of output channels are configured in the corresponding convolutional layers.

[0059] In step S1222, the precision level corresponding to the number of convolutional layers invoked is obtained.

[0060] Specifically, in step S1221, the step of configuring the corresponding number of output channels in the corresponding convolutional layer includes: obtaining the mask field information corresponding to the output channels, and configuring the corresponding number of output channels in the corresponding convolutional layer based on the mask field information.

[0061] In step S1223, the navigation signal is processed based on the invoked convolutional layer, the output channel configured for each convolutional layer, and the corresponding accuracy level.

[0062] In this embodiment, when processing navigation signals with a complexity level of 1, the signal processing model calls the first convolutional layer and processes the navigation signal with an INT2 precision level, at which point the number of output channels configured is 4 to 8. When processing navigation signals with a complexity level of 2, the signal processing model calls the first and second convolutional layers and processes the navigation signal with an INT4 precision level, at which point the number of output channels configured is 8 to 16. When processing navigation signals with a complexity level of 3, the signal processing model calls the first, second, and third convolutional layers and processes the navigation signal with an INT8 precision level, at which point the number of output channels configured is 16 to 32.

[0063] When the corresponding convolutional layer and output channel are invoked, the uninvoked convolutional layer and output channel skip the data processing of the navigation signal, thereby reducing unnecessary computation and lowering the power consumption generated during the operation of the signal processing model.

[0064] In step S130, the processed navigation signal is mapped to the corresponding accuracy level to generate an output signal.

[0065] like Figure 5 As shown, step S130 further includes steps S131 to S132.

[0066] In step S131, based on the accuracy level used to process the navigation signal, the numerical range of the processed navigation signal is mapped to the numerical range corresponding to the accuracy level, thereby obtaining the mapped navigation signal.

[0067] In step S132, an output signal is generated based on the mapped navigation signal.

[0068] In this embodiment, the processed navigation signal is mapped according to the accuracy level when processing the navigation signal, so that the numerical range of the processed navigation signal is the same as the numerical range corresponding to the accuracy level, thereby achieving numerical synchronization and obtaining an output signal, which is used for subsequent data processing.

[0069] Figure 6This is a flowchart of a second embodiment of the model scheduling method based on navigation signals of the present invention. Some steps of the second embodiment are the same as those of the first embodiment. The differences between the two will be described below, while the similarities will not be detailed.

[0070] like Figure 6 As shown, in the second embodiment of the present invention, after generating the output signal, the model scheduling method based on navigation signals further includes steps S240 to S250. The steps of the model scheduling method based on navigation signals in the second embodiment of the present invention are as follows:

[0071] In step S210, a corresponding scheduling instruction is generated based on the pre-acquired navigation signal.

[0072] In step S220, in response to the scheduling instruction, the corresponding convolutional layer in the signal processing model is invoked to process the navigation signal at the corresponding accuracy level.

[0073] In step S230, the processed navigation signal is mapped to the corresponding accuracy level to generate an output signal.

[0074] In step S240, based on the numerical range of the output signal, quantization range information corresponding to the numerical range of the output signal is generated.

[0075] In step S250, the quantization parameters of the model used to receive the output signal are updated based on the quantization range information.

[0076] In this embodiment, the output signal is used for further signal processing, such as being transmitted to an LSTM (Long Short-Term Memory) model. This allows the LSTM model to match the accuracy level used for computation based on the output signal, thereby updating the quantization parameters based on the quantization range information and improving the accuracy and efficiency of the LSTM model when using the output signal for sequence modeling.

[0077] The model scheduling method based on navigation signals provided in this invention can be applied to, for example... Figure 7 The satellite navigation device shown includes a receiving module 201, a judgment module 202, a scheduling module 203, and an execution module 204.

[0078] The receiving module 201 is used to receive navigation signals, the judging module 202 is used to generate corresponding scheduling instructions based on the pre-acquired navigation signals, the scheduling module 203 is used to call the corresponding convolutional layer in the signal processing model to process the navigation signals at the corresponding precision level according to the scheduling instructions, and the execution module 204 is used to map the processed navigation signals at the corresponding precision level to generate output signals.

[0079] like Figure 8As shown, the receiving module 201 is the front end of the satellite navigation device. After processing the received navigation signal at the front end of the satellite navigation device, it generates the corresponding spectrum diagram and / or pseudocode residual diagram, and transmits them to the judgment module 202. The judgment module 202 performs task level determination to determine the signal complexity. Then, through the scheduling module 203 and the execution module 204, it realizes the scheduling of the signal processing model and the selection of the corresponding accuracy level. Finally, it generates the output signal and transmits the output signal to the main control CPU or LSTM inference module (i.e., LSTM model) for further data processing.

[0080] like Figure 9 and Figure 10 As shown, Figure 9 The diagram illustrates that when the scheduling module 203 of the satellite navigation device calls the signal processing model according to the received scheduling instructions, it reads the calling method through the stored structure configuration table to call the corresponding convolutional layer and output channel, and masks the uncalled convolutional layer and output channel. Figure 10 The scheduling module 203 of the satellite navigation device Figure 10 The single PE (Processing Element) shown selects the corresponding precision level through its channel selection path, thereby completing the data processing of the navigation signal with the corresponding convolutional layer, output channel, and computational precision level.

[0081] The model scheduling method based on navigation signals provided in this embodiment of the invention includes: generating a corresponding scheduling instruction based on a pre-acquired navigation signal; responding to the scheduling instruction, calling the corresponding convolutional layer in the signal processing model to process the navigation signal at a corresponding precision level; and mapping the processed navigation signal at a corresponding precision level to generate an output signal.

[0082] The model scheduling method based on navigation signals provided in this invention can generate corresponding scheduling instructions based on the acquired navigation signals, thereby scheduling different convolutional layers in the signal processing model to process the navigation signals with corresponding precision levels. This allows the signal processing model to call on corresponding levels of computing power and computational precision to process the navigation signals according to their complexity, avoiding wasting computing power and generating unnecessary power consumption when processing low-power tasks.

[0083] In addition to the above method embodiments, the present invention also provides, for example, Figure 11 The model scheduling device shown includes a processor 301 and a memory 302, wherein the memory 302 stores instructions; the processor 301 calls the instructions in the memory 302 to cause the processor 301 to execute the model scheduling method based on navigation signals according to any of the foregoing embodiments of the present invention.

[0084] The model scheduling method based on navigation signals in the above embodiments of the present invention includes: generating a corresponding scheduling instruction based on a pre-acquired navigation signal; responding to the scheduling instruction, calling the corresponding convolutional layer in the signal processing model to process the navigation signal at a corresponding precision level; and mapping the processed navigation signal at a corresponding precision level to generate an output signal.

[0085] The model scheduling device provided in this embodiment of the invention implements the above-described model scheduling method based on navigation signals. It can generate corresponding scheduling instructions based on the acquired navigation signals, thereby scheduling different convolutional layers in the signal processing model to process the navigation signals with corresponding precision levels. This allows the signal processing model to call upon the corresponding level of computing power and computational precision to process the navigation signals according to their complexity, avoiding wasting computing power and generating unnecessary power consumption when processing low-power tasks.

[0086] Furthermore, the model scheduling device provided in this embodiment of the invention may also include a communication interface 303 and a bus 304, with the processor 301, memory 302 and communication interface 303 electrically connected via the bus 304.

[0087] The memory 302 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 303 (which can be wired or wireless), such as the Internet, wide area network, local area network, metropolitan area network, etc. The bus 304 can be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 11 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0088] Processor 301 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of processor 301 or by instructions in software form. Processor 301 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this invention. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this invention can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a readily available storage medium in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory 302. The processor 301 reads the information from memory 302 and, in conjunction with its hardware, completes the steps of the method described in the foregoing embodiments.

[0089] This invention also provides a computer-readable storage medium, which can be a non-volatile computer-readable storage medium or a volatile computer-readable storage medium. The computer-readable storage medium stores instructions that, when executed on a computer, cause the computer to perform the steps of the above-described model scheduling method based on navigation signals.

[0090] The computer-readable storage medium provided in this embodiment of the invention stores data and computer-executable instructions for the above-described model scheduling method based on navigation signals. The above-described model scheduling method based on navigation signals includes: generating corresponding scheduling instructions based on pre-acquired navigation signals; responding to the scheduling instructions, calling the corresponding convolutional layer in the signal processing model to process the navigation signals at a corresponding precision level; and mapping the processed navigation signals at a corresponding precision level to generate an output signal.

[0091] The computer-readable storage medium provided in this embodiment of the invention implements the above-described model scheduling method based on navigation signals. It can generate corresponding scheduling instructions based on the acquired navigation signals, thereby scheduling different convolutional layers in the signal processing model to process the navigation signals at corresponding precision levels. This allows the signal processing model to call upon corresponding levels of computing power and computational precision to process the navigation signals based on their complexity, avoiding wasting computing power and generating unnecessary power consumption when processing low-power tasks.

[0092] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0093] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0094] The above-described embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A model scheduling method based on navigation signals, characterized in that, The method includes: Based on the pre-acquired navigation signal, the signal complexity of the navigation signal is determined, wherein the navigation signal includes a signal-to-noise ratio signal and / or a residual signal and / or a phase-locked signal and / or an interference signal, and the signal complexity is determined by comparing the value of the navigation signal with a preset value range; Based on the complexity of the signal, generate scheduling instructions corresponding to the complexity of the signal; In response to the scheduling instruction, the corresponding convolutional layer in the signal processing model is invoked to process the navigation signal at the corresponding accuracy level, wherein the number of convolutional layers invoked and the corresponding accuracy level are positively correlated with the complexity of the signal; The processed navigation signal is mapped to the corresponding accuracy level to generate an output signal.

2. The model scheduling method based on navigation signals according to claim 1, characterized in that, When the navigation signal is within a first numerical range, the signal complexity is at level one. When the navigation signal is within the second numerical range, the signal complexity is at the second level; When the navigation signal is within the third numerical range, the signal complexity is at level three. Wherein, the first numerical range is greater than the second numerical range, and the second numerical range is greater than the third numerical range.

3. The model scheduling method based on navigation signals according to claim 1, characterized in that, The step of responding to the scheduling instruction by invoking the corresponding convolutional layer in the signal processing model to process the navigation signal at the corresponding accuracy level includes: In response to the scheduling instruction, at least one convolutional layer, at least two convolutional layers, or at least three convolutional layers in the signal processing model are invoked; The navigation signal is processed at the corresponding level of precision based on the number of convolutional layers invoked.

4. The model scheduling method based on navigation signals according to claim 3, characterized in that, The step of processing the navigation signal according to the number of convolutional layers invoked, with a corresponding level of precision, includes: Based on the number of convolutional layers invoked, configure the corresponding number of output channels in the corresponding convolutional layers; Obtain the precision level corresponding to the number of convolutional layers invoked; The navigation signal is processed based on the invoked convolutional layers, the output channels configured for each convolutional layer, and the corresponding accuracy level.

5. The model scheduling method based on navigation signals according to claim 4, characterized in that, In the step of configuring the corresponding number of output channels in the corresponding convolutional layer, the method includes: Obtain the mask field information corresponding to the output channel; Based on the mask field information, the corresponding number of output channels are configured in the corresponding convolutional layer.

6. The model scheduling method based on navigation signals according to claim 1, characterized in that, The step of mapping the processed navigation signal to the corresponding accuracy level to generate an output signal includes: Based on the accuracy level used to process the navigation signal, the numerical range of the processed navigation signal is mapped to a numerical range corresponding to the accuracy level to obtain the mapped navigation signal. The output signal is generated based on the mapped navigation signal.

7. The model scheduling method based on navigation signals according to claim 6, characterized in that, After generating the output signal, the method further includes: Based on the numerical range of the output signal, quantization range information corresponding to the numerical range of the output signal is generated; Based on the quantization range information, the quantization parameters of the model used to receive the output signal are updated.

8. A model scheduling device, characterized in that, The model scheduling device includes a processor and a memory, wherein the memory stores instructions; The processor invokes the instructions in the memory to cause the model scheduling device to implement the model scheduling method based on navigation signals as described in any one of claims 1 to 7.

9. A computer-readable storage medium storing instructions thereon, characterized in that, When the instruction is executed by the processor, it implements the model scheduling method based on navigation signals as described in any one of claims 1 to 7.

Images